No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Modeling reconfigurable supply chains using knowledge graphs: towards Supply Chain 5.0
Abstract
The Reconfigurable Supply Chain offers a cost-effective approach to adapting to the dynamic evolution of unpredictable events that have demonstrated the vulnerability of the Traditional Supply Chain. However, the effective management and exploitation of massive amounts of reconfiguration knowledge remains a crucial challenge to improve the capabilities of this management. Information is dispersed in such massive and varied quantities that the task of organizing and understanding is becoming increasingly complex. Therefore, the idea of developing a knowledge graph model is emerging to delineate these capabilities. This innovative model aims to overcome the obstacles associated with knowledge management and to promote effective adaptation to change, while emphasizing the importance of human resources in this process. By combining Supply Chain 5.0 concepts with the capabilities of the knowledge graph, this model offers the possibility of maintaining a sustainable, resilient and human-centered reconfiguration. Such an original and unique model for a Reconfigurable Supply Chain offers a promising solution for companies seeking to optimize their supply chain in a constantly changing environment. The knowledge graph is constructed on the basis of supply chain ontologies and reconfiguration concepts. Then, Cypher queries in Neo4j are executed to validate our model in terms of matching available reconfiguration knowledge with the ability to represent knowledge and manage it efficiently.
ResearchGate has not been able to resolve any citations for this publication.
The ongoing digitization of the industrial sector has reached a pivotal juncture with the emergence of Digital Twins, offering a digital representation of physical assets and processes. One key aspect of these digital representations is the utilization of simulation models, enabling a deeper insight into the asset’s current state and its characteristics. This paper asserts that the next evolutionary step in this digitization journey involves the integration of intelligent linkages between diverse simulation models within the Digital Twin framework. Crucially, for the Digital Twin to be a scalable and cost-effective solution, there is a pressing need for automated adaption, (re-)configuration, and generation of simulation models. Recognizing the inherent challenges in achieving such automation, this paper analyses the utilization of knowledge graphs as a potentially very suitable technological solution. Knowledge graphs, acting as interconnected and interrelated databases, provide a means of seamlessly integrating different data sources, facilitating the efficient integration and automated adaption of data and (simulation) models in the Digital Twin. We conducted a comprehensive literature review to analyze the current landscape of knowledge graphs in the context of Digital Twins with a focus on simulation models. By addressing the challenges associated with scalability and maintenance, this research contributes to the effective adoption of Digital Twins in the industrial sector, paving the way for enhanced efficiency, adaptability, and resilience in the face of evolving technological landscapes.
Cyber-physical systems, cloud computing, the Internet of Things, and big data play significant roles in shaping digital and automated landscape manufacturing. However, to fully realize the potential of these technologies and achieve tangible benefits, such as reduced manufacturing lead times, improved product quality, and enhanced organizational performance, new decision support models need development. Game theory offers a promising approach to address multi-objective problems and streamline decision-making processes, thereby reducing computational time. This paper aims to provide a comprehensive and up-to-date systematic review of the literature on the application of game theory models in various areas of digital manufacturing, including production and capacity planning, scheduling, sustainable production systems, and cloud manufacturing. This review identifies key research themes that have been explored and examines the main research gaps that exist within these domains. Furthermore, this paper outlines potential future research directions to inspire both researchers and practitioners to further explore and develop game theory models that can effectively support the digital transformation of manufacturing systems.
Market convergence challenges socially sustainable supply chain management (SSSCM) due to the increasing competition. Identifying market convergence trends allows companies to respond quickly to market changes and improve supply chain resilience (SCR). Conventional approaches are one-sided and biased and cannot predict market convergence trends comprehensively and accurately. To address this issue, we propose a framework based on info2vec that solves the problem of matching multidimensional data by using the technology layer as the focal layer and the supply chain as the supporting layer. The framework enriches the supply chain dimension with the technology dimension. A knowledge graph is constructed to facilitate cross-domain information connectivity by integrating different data sources. The nodes in the knowledge graph were characterized using a representation learning algorithm, which enhanced feature mining during supply chain and market convergence. Changes in market demand were predicted based on link prediction experiments. Market convergence has an impact on firm cooperation and, thus, on SCR. The framework recommends potential technological and innovative cooperation opportunities for firms. In this way, it has been demonstrated to improve SSSCM through network resilience experiments. This method predicts market convergence efficiently based on the supply chain knowledge graph, which provides decision support for enterprise development.
The increasing demand for personalized products and cost-effectiveness has highlighted the necessity of integrating intelligence into production systems. This integration is crucial for enabling intelligent control that can adapt to variations in features, parts, and conditions, thereby enhancing functionalities while reducing costs. This research emphasizes the incorporation of intelligence in testing processes within production systems. We introduce a novel approach for controlling testing functionality using an asset administration shell enriched with modular artificial intelligence. The proposed architecture is not only effective in controlling the execution behavior through services but also offers the distinct advantage of a modular design. This modularity significantly contributes to the system's adaptability and scalability, allowing for more efficient and cost-effective solutions as different machine-learning models may be substituted to meet requirements. The effectiveness of this approach is validated through a practical use case of leak testing, demonstrating the benefits of the modular architecture in a real-world application.
This exploratory study sought to deepen the understanding of the benefits of using the knowledge graph technological solution for knowledge management. Through a bibliometric analysis of 45 academic articles selected from the Scopus database, with no time range determined, it was observed that the term has been addressed in academic productions on various topics with a greater number of publications from Asian researchers (71%). To understand the relationships of the keywords used by the authors of these articles, the VOSviewer tool was used to create the graph, making it possible to visualize the terms' clusters. It was identified that the theme is emerging, as the first article published in the Scopus database took place in 2011 and an expressive growth of publications can be observed in 2020. The production of academic knowledge with the use of the coupled knowledge graph stands out to the design of algorithms that support tutoring and curation activities with a focus on knowledge management in the areas of Health - including during the Covid-19 pandemic - and Education. The transversality of this solution is also noted, with studies using knowledge graphs in the areas of Engineering and Computer Science being observed. After further analysis, the authors selected 12 articles that presented initiatives focused on the area of Management and the use of the technological solution in activities aimed at intelligent recommendation can be observed, including the adoption of artificial intelligence and sampling algorithms for the study and development of solutions that resulted in the visualization of knowledge bases through the knowledge graph. The trend of using knowledge graphs for knowledge management pointed out by Knowledge Management (KM) World magazine can be found in business environments, such as Google and Wikipedia. It is believed that more empirical studies with knowledge graphs for knowledge management will be intensified in the digital age and this can be followed up in scientific congresses on the subject.
This document presents research on an intelligent policy based on fuzzy logic for dynamically adjusting the number of Kanban cards in a pull production system operating in a stochastic environment, while taking into account fluctuations in customer demand. The objective is to maintain a high level of performance measures in terms of production costs and customer satisfaction. The proposed approach involves developing a fuzzy controller for adaptive control of the number of cards that considers only the level of inventory and the number of additional cards in circulation. However, this real-time dynamic adaptation can lead to an excessive number of changes that can negatively affect the production system. To evaluate the decisions made by the fuzzy controller in real-time, a simulation model was developed using a discrete event simulation environment based on Rockwell’s ARENA® platform. Furthermore, the optimization of the fuzzy system’s parameters was calculated using the OptQuest optimizer to reduce costs while ensuring customer satisfaction. The results were compared with other adaptive control approaches from the literature for a stochastic environment, without any estimation of future demands. The effectiveness of our fuzzy adaptive control approach was demonstrated in terms of relative performance measures for production costs and customer satisfaction. Additionally, the robustness of our fuzzy controller was tested in terms of nervousness, as measured by the number of changes in Kanban cards.
Globalisation has enabled long-distance supply chains with minimal inventories and a sole focus on maximising efficiency and minimising costs. In recent years, the focus has shifted to resilience-oriented supply chain management as the global business environment becomes increasingly uncertain. One possible response to supply chain dynamics can be dynamic
networks. These should enable the rapid rearrangement of the supply network structure, for example, through the rapid change of suppliers. This scoping review outlines the body of knowledge of this research field by identifying drivers, triggers,characteristics, challenges, and
future research directions. For each of these aspects, a classification framework describes essential features. The literature on dynamic networks spreads across several supply chain paradigms, all of which describe this topic as a critical element to some extent. However, the paradigm of reconfigurable supply chains is the only coherent field of research with the highest relevance to dynamic networks. The main drivers are uncertain markets and fluctuations in demand and
supply, as well as disruptions, with disruptions focusing on natural catastrophes, trade disputes, and disease outbreaks. Many authors expect network reconfigurations to be carried out with
minimal effort while maintaining operational efficiency, service level, and costs. However, the publications considered remain predominantly at a high level of abstraction and need more
guidance on practical implementation. Therefore, there are still open challenges and future research directions, such as reconfiguration decision-making.
Artificial Intelligence (AI) has emerged as a complementary technology in supply chain research. However, the majority of AI approaches explored in this context afford little to no explainability, which is a significant barrier to a broader adoption of AI in supply chains. In recent years, the need for explainability has been a strong impetus for research in hybrid AI methodologies that combine neural architectures with logic-based reasoning, which are collectively referred to as Neurosymbolic AI. The aim of this paper is to provide a comprehensive overview of supply chain management literature that employees approaches within the neurosymbolic AI spectrum. To that end, a systematic review is conducted, followed by bibliometric, descriptive and thematic analyses on the identified studies. Our findings indicate that researchers have primarily focused on the limited subset of neurofuzzy approaches, while some supply chain applications, such as performance evaluation and sustainability, and sectors such as pharmaceutical and construction have received less attention. To help address these gaps, we propose five pillars of neurosymbolic AI research for supply chains and provide three use cases of applying unexplored neurosymbolic AI approaches to address typical problems in supply chain management, including a discussion of prerequisites for adopting such technologies. We envision that the findings and contributions of this survey will help encourage further research in neu-rosymbolic AI for supply chains and increase adoption of such technologies within supply chain practice.
This paper delves into the nascent paradigm of Explainable AI (XAI) and its pivotal role in enhancing the acceptability of growing AI systems shaping the Digital Management 5.0 era. XAI holds significant promise, promoting compliance with legal and ethical standards and offering transparent decision-making tools. The imperative of interpretable AI systems to counter the black box effect and adhere to data protection laws like GDPR is highlighted. This paper aims to achieve a dual objective. Firstly, it provides an in-depth understanding of the emerging XAI paradigm, helping practitioners and academics project their future research trajectories. Secondly, it proposes a new taxonomy of XAI models with potential applications that could facilitate AI acceptability. Although the academic literature reflects a crucial lack of exploration into the full potential of XAI, existing models remain mainly theoretical and lack practical applications. By bridging the gap between abstract models and the pragmatic implementation of XAI in management, this paper breaks new ground by launching the scientific foundations of XAI in the upcoming era of Digital Management 5.0.
Reconfigurable Manufacturing System (RMS) provides a cost-effective approach for manufacturers to adapt to fluctuating market demands by reconfiguring assets through automated analysis of asset utilization and resource allocation. Achieving this automation necessitates a clear understanding, formalization, and documentation of asset capabilities and capacity utilization. This paper introduces a unified model employing semantic modeling to delineate the manufacturing sector's capabilities, capacity, and reconfiguration potential. The model illustrates the integration of these three components to facilitate efficient system reconfiguration. Additionally, semantic modeling allows for the capture of historical experiences, thus enhancing long-term system reconfiguration through a knowledge graph. Two use cases are presented: capability matching and reconfiguration solution recommendation based on the proposed model. A thorough explication of the methodology and outcomes is provided, underscoring the advantages of this approach in terms of heightened efficiency, diminished costs, and augmented productivity.
The purpose was to investigate the impact of the Industry 5.0 paradigm on the supply chain research field. Our study contributes to the conceptualization of supply chain 5.0, a term that has been receiving increased attention as supply chains adapt to the fifth industrial revolution. We conducted a systematic literature network analysis (SLNA) to examine the research landscape of Industry 5.0 supply chains. We used VOSViewer software and Bibliometrix R-package for multiple bibliometric analyses using 682 documents published between 2016 and 2022. We present a comprehensive framework of supply chain 5.0, including its key concepts, technologies, and trends. Additionally, this research offers a future research agenda to inspire and support further development in this field. We utilized three academic databases for bibliometric analyses: Dimension, Scopus and Lens. Additional databases could provide a wider research landscape and better field representation. We demonstrate how Industry 5.0 enables supply chain evaluation and optimization to assist companies in navigating disruptions without compromising competitiveness and profitability and provide a unique contribution to the field of supply chain 5.0 by exploring promising research areas and guiding the transition to this new paradigm for practitioners and scholars.
Global crises and regulatory developments require increased supply chain transparency and resilience. Companies do not only need to react to a dynamic environment but have to act proactively and implement measures to prevent production delays and reduce risks in the supply chains. However, information about supply chains, especially at the deeper levels, is often intransparent and incomplete, making it difficult to obtain precise predictions about prospective risks. By connecting different data sources, we model the supply network as a knowledge graph and achieve transparency up to tier-3 suppliers. To predict missing information in the graph, we apply state-of-the-art knowledge graph completion methods and attain a mean reciprocal rank of 0.4377 with the best model. Further, we apply graph analysis algorithms to identify critical entities in the supply network, supporting supply chain managers in automated risk identification.
Artificial intelligence (AI) is currently being utilized in a wide range of sophisticated applications, but the outcomes of many AI models are challenging to comprehend and trust due to their black-box nature. Usually, it is essential to understand the reasoning behind an AI model’s decision-making. Thus, the need for eXplainable AI (XAI) methods for improving trust in AI models has arisen. XAI has become a popular research subject within the AI field in recent years. Existing survey papers have tackled the concepts of XAI, its general terms, and post-hoc explainability methods but there have not been any reviews that have looked at the assessment methods, available tools, XAI datasets, and other related aspects. Therefore, in this comprehensive study, we provide readers with an overview of the current research and trends in this rapidly emerging area with a case study example. The study starts by explaining the background of XAI, common definitions, and summarizing recently proposed techniques in XAI for supervised machine learning. The review divides XAI techniques into four axes using a hierarchical categorization system: (i) data explainability, (ii) model explainability, (iii) post-hoc explainability, and (iv) assessment of explanations. We also introduce available evaluation metrics as well as open-source packages and datasets with future research directions. Then, the significance of explainability in terms of legal demands, user viewpoints, and application orientation is outlined, termed as XAI concerns. This paper advocates for tailoring explanation content to specific user types. An examination of XAI techniques and evaluation was conducted by looking at 410 critical articles, published between January 2016 and October 2022, in reputed journals and using a wide range of research databases as a source of information. The article is aimed at XAI researchers who are interested in making their AI models more trustworthy, as well as towards researchers from other disciplines who are looking for effective XAI methods to complete tasks with confidence while communicating meaning from data.
The COVID-19 pandemic revealed weaknesses in the global supply chain management. With stock-outs, transportation problems and the bullwhip effect caused by ever-changing demand, it is necessary for decision-makers to review their supply chain configuration. The latter must adapt to new market changes and respond quickly and cost-effectively to customer requirements. In fact, the selection criteria of the most reconfigurable configuration, i.e., the configuration that adapts its structure and its functions to the new market changes, must respond to this problem. The aim of this paper is to conduct a literature review of the criteria and methods for configuration selection in reconfigurable manufacturing systems and reconfigurable supply chains. This study allows to define a roadmap for the configuration selection in reconfigurable supply chains based on the most efficient reconfigurability criteria. We provide new trends to consider in this selection problem. This paper allows managers to choose the most appropriate criteria to implement a reconfigurable supply chain.
This research presents a systematic literature review of using artificial intelligence (AI) in the supply chain (SC). We examine the works done so far in relation to AI research, which still needs to be investigated in light of the potential benefits of implementing AI in supply chain management. Dynamic supply chain processes require artificial intelligence techniques capable of dealing with their increasing complexity. Artificial intelligence techniques such as machine learning, Deep learning, natural language processing, expert systems, knowledge representation, Fuzzy logic and models, social intelligence, Artificial neural networks, Support vector machines, Gaussian models, robotics, Ant colony, and computer vision can transform and optimize the supply chain. In order to classify the study material, we looked at 50 research papers from the Scopus database that were published between 2002 and 2022 and assigned each one a grade based on two fundamental structural factors are as follows: AI techniques and sector of application.KeywordsArtificial IntelligenceSupply chainSystematic literature reviewTaxonomy of artificial intelligence
Knowledge graph technology plays an important role in knowledge supporting for efficient supply chain management (SCM) of manufacturing enterprises, a SCM knowledge graph can be constructed based on the relevant case corpus. In order to solve the problems of coarse concept granularity of event ontology knowledge in SCM cases, potential words of characters in the existing entity recognition models may not be matched or matched incorrectly, key features of entities with different lengths may interfere with each other in the expression of attention mechanism, and lack of a large number of annotation training samples, a top-down construction method of SCM event logic knowledge graph (ELKG) is proposed. Firstly, SCM event argument classes and class relations are defined, an event logic ontology model is built, and the event argument entities according to event logic ontology are labeled. Then, an active learning event argument entity recognition (EAER) model based on two-stage generative adversarial network (GAN) is proposed. In GAN generator, an EAER model based on binocular attention-based stacked BiLSTM with CNN (BACSBN) is proposed, which combines word-level character feature attention mechanism and entity key information attention mechanism to improve the attention to character features of constituent words and highlight entity key information, respectively. Two-stage GAN adversarial training and label space attention mechanism are introduced to select the correct prediction label samples for active learning training. The experimental results show that BACSBN can improve the entity recognition accuracy, and the two-stage GAN's active learning can further improve the recognition effect on the basis of full annotation sample training, and can still maintain a high accuracy in the absence of a large number of manual annotation data. Further, according to the sentence pattern and keyword matching, the matching relations of argument entities are completed, and the SCM ELKG is constructed to provide knowledge support for autonomous SCM.
The COVID-19 pandemic has triggered new research areas in supply chain resilience. One of these new areas is viability. Viability extends the resilience understanding from performance-based assessment of firm’s responses to disruptions towards survivability of both supply chains and associated ecosystems not only during some short-term disruptions but also under conditions of long-term crises. To explore the state-of-the-art knowledge on methods, models, capabilities, and technologies of supply chain viability, we edited this important IJPR special issue. To introduce the special issue, we review the existing literature on supply chain viability, conceptualise seven major pillars of supply chain viability theory (i.e. viable supply chain design, viability in process planning and control, ripple effect, intertwined and reconfigurable supply networks, ecosystems, digital supply chain, and Industry 5.0), and establish some associated future research directions. The findings of this editorial paper, as well as the articles in the special issue, can be used by researchers and practitioners alike to consolidate recent advances and practices of viability in supply chain networks and lay the solid foundation for further developments in this area.
Nowadays, the business area cannot be sustainable and efficient without the presence of the Supply Chain. However, Supply Chain Management is by no means an easy task. Experts, in their effort to achieve the most efficient Supply Chain Management, have turned their attention to the management of knowledge related to supply chains. Thus, they model the concepts and the semantic relationships between them in Supply Chain Networks and create conceptual models and ontologies. In this paper, a survey of the existing ontologies in this field is carried out, with the aim of creating a new ontology of the Supply Chain that will unify its structural elements and lead to the integration of all supply systems. For this purpose, 22 ontological models from different supply systems, from over 90 sources, have been collected, briefly presented and commented on. These models, although being an intersection in the effort to model business operations and delineate a good basis for businesses to engage in Logistics processes, they lack an adequate formulation of appropriate semantics and terminology to describe all the different functions of the Supply Chain. Consequently, this lack inevitably leads to incompatible interpretations and uses of the knowledge that results from intercompany transactions.
Digital twins and artificial intelligence have shown promise for improving the robustness, responsiveness, and productivity of industrial systems. However, traditional digital twin approaches are often only employed to augment single, static systems to optimise a particular process. This article presents a paradigm for combining digital twins and modular artificial intelligence algorithms to dynamically reconfigure manufacturing systems, including the layout, process parameters, and operation times of numerous assets to allow system decision-making in response to changing customer or market needs. A knowledge graph has been used as the enabler for this system-level decision-making. A simulation environment has been constructed to replicate the manufacturing process, with the example here of an industrial robotic manufacturing cell. The simulation environment is connected to a data pipeline and an application programming interface to assist the integration of multiple artificial intelligence methods. These methods are used to improve system decision-making and optimise the configuration of a manufacturing system to maximise user-selectable key performance indicators. In contrast to previous research, this framework incorporates artificial intelligence for decision-making and production line optimisation to provide a framework that can be used for a wide variety of manufacturing applications. The framework has been applied and validated in a real use case, with the automatic reconfiguration resulting in a process time improvement of approximately 10%.
With manufacturing companies outsourcing to each other, multi-echelon supply chain networks emerge in which risks can propagate over multiple entities. Considerable structural and organizational barriers hamper obtaining the supply chain visibility that would be required for a company to monitor and mitigate these risks. Our work proposes to combine the automated extraction of supply chain relations from web data using NLP with augmenting the results using link prediction. For this, the first graph neural network based approach to model uncertainty in supply chain knowledge graph reasoning is shown. We illustrate our approach on a novel dataset and manage to improve the state-of-the-art performance by 60% in uncertainty link prediction. Generated confidence scores support real-world decision-making.
Human-centricity is the core value behind the evolution of manufacturing towards Industry 5.0. Nevertheless, there is a lack of architecture that considers safety, trustworthiness, and human-centricity at its core. Therefore, we propose an architecture that integrates Artificial Intelligence (Active Learning, Forecasting, Explainable Artificial Intelligence), simulated reality, decision-making, and users' feedback, focussing on synergies between humans and machines. Furthermore, we align the proposed architecture with the Big Data Value Association Reference Architecture Model. Finally, we validate it on three use cases from real-world case studies.
Reconfigurable supply chains received increasing interest from academia and industry in the past years, especially because recent events such as the COVID-19 pandemic revealed the vulnerability of present supply chains. Especially the rapid digitalization and the emergence of artificial intelligence in supply chain management create new opportunities for implementing reconfigurable supply chains. In this paper, we propose a concept that uses a knowledge graph and graph-based artificial intelligence to recommend reconfigurations of the supply chain. Due to the importance of these strategic decisions, the concept considers a human-centric approach using a recommender system. The knowledge graph exploits the inherent graph structure of supply chains to create a machine-readable and human-understandable database that also supports reasoning. Finally, we provide three research hypotheses and examine the integration of open-source knowledge graphs and news monitoring tools.
Industry 5.0 is a combination of organisational principles and technologies to design and manage operations and supply chains as resilient, sustainable, and human-centric systems. While the general notion of Industry 5.0 has been elaborated, its implications for future operations and supply chains remain underexplored. This paper contributes to the conceptualisation of Industry 5.0 from the perspective of viability. We contextualise a framework of Industry 5.0 through the lens of the viable supply chain model, the reconfigurable supply chain, and human-centric ecosystems. Our study uncovers the major dimensions that characterise Industry 5.0 as a technological-organisational framework. First, the major technological principles of Industry 5.0 are collaboration, coordination, communication, automation, data analytics processing, and identification. Second, Industry 5.0 covers four areas: organisation, management, technology, and performance assessment. Third, Industry 5.0 spans three levels: society level, network level, and plant level. Last but not least, Industry 5.0 frames a new triple bottom line: resilient value creation, human well-being, and sustainable society. We provide a definition of Industry 5.0 and discuss its implications by elaborating on the understanding of value in Industry 5.0, which spans the dimensions of profit, people, and society. We also discuss open research areas.
Information extraction methods proved to be effective at triple extraction from structured or unstructured data. The organization of such triples in the form of (head entity, relation, tail entity) is called the construction of Knowledge Graphs (KGs). Most of the current knowledge graphs are incomplete. In order to use KGs in downstream tasks, it is desirable to predict missing links in KGs. Different approaches have been recently proposed for representation learning of KGs by embedding both entities and relations into a low-dimensional vector space aiming to predict unknown triples based on previously visited triples. According to how the triples will be treated independently or dependently, we divided the task of knowledge graph completion into conventional and graph neural network representation learning and we discuss them in more detail. In conventional approaches, each triple will be processed independently and in GNN-based approaches, triples also consider their local neighborhood.
Modern supply chains are complex, interconnected systems that contain emergent, invisible dependencies. Lack of visibility often hinders effective risk planning and results in delayed discovery of supply chain problems, with examples ranging from product contamination, unsustainable production practices, or exposure to suppliers clustered in geographical areas prone to natural or man-made disasters. Initiatives that rely on manual collection of data often fail due to supply chain complexity and unwillingness of suppliers to share data. In this paper, we propose a neurosymbolic machine learning technique to proactively uncover hidden risks in supply chains and discover new information. Our method uses a combination of graph neural networks and knowledge graph reasoning. Unlike existing research our model is able to infer multiple types of hidden relationship risks, presenting a step change in automated supply chain surveillance. The approach has been tested on two empirical datasets from the automotive and energy industries, illustrating that it can provide inference in multiple types of links such as companies, products, production capabilities, certifications; thereby facilitating complex queries that go beyond who-supplies-whom. As such, additional risk insights can emerge from graph structure, providing practitioners with new knowledge.
In recent years, supply chains seem to be moving more towards reconfiguring their networks to become more profitable. In the times of COVID-19, where the whole supply chains have been disrupted, suppliers are unable to supply, and manufacturers are unable to manufacture because of lockdowns in the various regions around the world. This pandemic can be compared to past earthquakes and tsunamis, as the coronavirus is also a natural disaster. Due to these past disruptions, organizations have taken many precautions and developed risk mitigation strategies to manage them. Because the COVID-19 outbreak shows the importance of new business perspectives like repurposing a viability strategy, that comes with sustainability and reconfigurability. Where reconfiguration focuses on adaptation, which directly means changes in resources and capabilities and repurposing focuses on a quick response solution to address the shortage. In this paper, a study has been done in two phases to model viability in an automobile supply chain during the COVID-19 times. In the first phase, a hybrid Multi-criteria Decision Making (MCDM) approach is used to get the best criteria and alternatives with sustainability and reconfigurability under consideration. The multi-objective mixed-integer linear programming (MOMILP) model has been developed in the second phase. Suppliers' weight that is obtained will be used to get the optimal order and allocation. This model will help develop supply chain strategies to cope with situations that hinder the firm's competitiveness. A case study of an Indian automobile manufacturer has been taken to show the applicability and effectiveness of the proposed methodology using GAMS/CPLEX solver.
Knowledge graphs (KGs) have emerged as a compelling abstraction for organizing the world's structured knowledge and for integrating information extracted from multiple data sources. They are also beginning to play a central role in representing information extracted by AI systems, and for improving the predictions of AI systems by giving them knowledge expressed in KGs as input. The goals of this article are to (a) introduce KGs and discuss important areas of application that have gained recent prominence; (b) situate KGs in the context of the prior work in AI; and (c) present a few contrasting perspectives that help in better understanding KGs in relation to related technologies.
In many production applications, plants that produce multiple products with random demands share the required items among suppliers. The decision of how to allocate requests between suppliers to achieve the desired level of customer service is relevant to the efficiency of the production network. The literature highlighted how the long chain has the same level of performance as the full flexible network. This research proposes a decision model based on the game theory model to improve the performance of the production network. The model uses the Gale-Shapley algorithm with low computational complexity to share the demand among the suppliers. A simulation environment allows the evaluation of the proposed model in different conditions, and the model is compared to the dedicated, full flexibility, and long chain models. The numerical results show how the proposed model improves the efficiency of the production environment by keeping the number of connections with the supplier closer to the long chain model.
Supply chain network in the automotive industry has complex, interconnected, multiple-depth relationships. Recently, the volume of supply chain data increases significantly with Industry 4.0. The complex relationships and massive volume of supply chain data can cause visibility and scalability issues in big data analysis and result in less responsive and fragile inventory management. The authors develop a graph data modeling framework to address the computational problem of big supply chain data analysis. In addition, this paper introduces Time-to-Stockout analysis for supply chain resilience and shows how to compute it through a labeled property graph model. The computational result shows that the proposed graph data model is efficient for recursive and variable-length data in supply chain, and relationship-centric graph query language has capable of handling a wide range of business questions with impressive query time.
Supply chain business interruption has been identified as a key risk factor in recent years, with high-impact disruptions due to disease outbreaks, logistic issues such as the recent Suez Canal blockage showing examples of how disruptions could propagate across complex emergent networks. Researchers have highlighted the importance of gaining visibility into procurement interdependencies between suppliers to develop more informed business contingency plans. However, extant methods such as supplier surveys rely on the willingness or ability of suppliers to share data and are not easily verifiable. In this article, we pose the supply chain visibility problem as a link prediction problem from the field of Machine Learning (ML) and propose the use of an automated method to detect potential links that are unknown to the buyer with Graph Neural Networks (GNN). Using a real automotive network as a test case, we show that our method performs better than existing algorithms. Additionally, we use Integrated Gradient to improve the explainability of our approach by highlighting input features that influence GNN’s decisions. We also discuss the advantages and limitations of using GNN for link prediction, outlining future research directions.
As an emerging technology, the knowledge graph (KG) has been successfully applied in various industries. Though some potential benefits of the KG have been identified, there is still little work on implementing the KG in supply chain risk management (SCRM). This study develops a KG-based risk management framework to improve the resilience of Supply Chains (SCs). Specifically, the construction of the SC knowledge graph (SC-KG) framework, including the implementation steps, is presented in detail for the purpose of SC knowledge retrieval, data visualization analysis, risk monitoring, early warning, and decision support. Furthermore, the SC-KG is well constructed to build a scenario-based SCRM framework under consideration of the severity of disruptions. Especially during long-term disruptions, the continuity of SCs is maintained through the employment of a product change strategy and a structurally scalable and dynamically adapted network design method. The findings of the study are instructive for SC managers in adopting digital technologies for SC mitigation and recovery under disruptions. Finally, a practical SC-KG containing over 2.5 million entities and 11 types of relationships has been developed and its basic functions have been implemented, which contributes to improving the quality of SC management.
Supply Chain Risk Management focuses on the identification, assessment and management of disruptive events that can affect companies, transport routes and resources involved in critical goods supply chains. Modern supply chains consist of interconnected components that can be complex and dynamic in nature. In this demo, we present our system for analysing the resilience of supply chains for crisis relevant products. A dependency Bayesian Network is automatically generated from relevant information about the supply chain maintained in a Knowledge Graph. The main objective of the proposed approach is the early identification of bottlenecks and timely prediction of the consequences of probable disruptions of the network.
Automatic knowledge graph construction aims to manufacture structured human knowledge. To this end, much effort has historically been spent extracting informative fact patterns from different data sources. However, more recently, research interest has shifted to acquiring conceptualized structured knowledge beyond informative data. In addition, researchers have also been exploring new ways of handling sophisticated construction tasks in diversified scenarios. Thus, there is a demand for a systematic review of paradigms to organize knowledge structures beyond data-level mentions. To meet this demand, we comprehensively survey more than 300 methods to summarize the latest developments in knowledge graph construction. A knowledge graph is built in three steps: knowledge acquisition, knowledge refinement, and knowledge evolution. The processes of knowledge acquisition are reviewed in detail, including obtaining entities with fine-grained types and their conceptual linkages to knowledge graphs; resolving coreferences; and extracting entity relationships in complex scenarios. The survey covers models for knowledge refinement, including knowledge graph completion, and knowledge fusion. Methods to handle knowledge evolution are also systematically presented, including condition knowledge acquisition, condition knowledge graph completion, and knowledge dynamic. We present the paradigms to compare the distinction among these methods along the axis of the data environment, motivation, and architecture. Additionally, we also provide briefs on accessible resources that can help readers to develop practical knowledge graph systems. The survey concludes with discussions on the challenges and possible directions for future exploration.
The COVID-19 pandemic has illustrated the unprecedented challenges of ensuring the continuity of operations in a supply chain as suppliers' and their suppliers stop producing due the spread of infection, leading to a degradation of downstream customer service levels in a ripple effect. In this paper, we contextualize a dynamic approach and propose an optimal control model for supply chain reconfiguration and ripple effect analysis integrated with an epidemic dynamics model. We provide supply chain managers with the optimal choice over a planning horizon among subsets of interchangeable suppliers and corresponding orders; this will maximize demand satisfaction given their prices, lead times, exposure to infection, and upstream suppliers' risk exposure. Numerical illustrations show that our prescriptive forward-looking model can help reconfigure a supply chain and mitigate the ripple effect due to reduced production because of suppliers' infected workers. A risk aversion factor incorporates a measure of supplier risk exposure at the upstream echelons. We examine three scenarios: (a) infection limits the capacity of suppliers, (b) the pandemic recedes but not at the same pace for all suppliers, and (c) infection waves affect the capacity of some suppliers, while others are in a recovery phase. We illustrate through a case study how our model can be immediately deployed in manufacturing or retail supply chains since the data are readily accessible from suppliers and health authorities. This work opens new avenues for prescriptive models in operations management and the study of viable supply chains by combining optimal control and epidemiological models.
As the fourth industrial revolution has passed an early stage of development, many companies are developing intelligent systems and cutting-edge innovations of Industry 4.0 to improve productivity and quality. Meanwhile, the next phase of industrialization has been started to introduce, known as Industry 5.0. One of the most prominent features of Industry 5.0 is that it places the well-being of humans at the center of the manufacturing process. Advanced technologies are also created to keep up with the trend of the fifth industrial revolution. Artificial intelligence (AI) algorithms have proven to play a key role in Industry 4.0. Moving to Industry 5.0, with the human-centric orientation, AI was developed in combination with human intelligence (HI), leading to the new concept of Augmented Intelligence (AuI). AI and AuI algorithms are expected to bring significant benefits for enabling smart manufacturing in Industry 5.0. In this study, we provide a survey on AI-based methods, applications, and challenges for smart manufacturing in Industry 5.0. The discussions will help to clarify some important issues related to the applications and the potential of AI algorithms in smart manufacturing.KeywordsArtificial intelligenceSmart manufacturingIndustry 5.0Augmented intelligenceCyber-physical systemsHuman-centric manufacturing
Artificial intelligence (AI) is a rapidly growing field with vast potential to revolutionize supply chain management practices. This review paper provides a comprehensive overview of the various AI applications in different stages of the supply chain, including demand forecasting and inventory management, supplier selection and management, production scheduling and quality control, logistics and transportation management, and reverse logistics and sustainability.The literature review discusses the history of AI in supply chain management and highlights the different types of AI technologies commonly used. The paper also examines the benefits of AI in enhancing supply chain performance, such as reducing costs, increasing efficiency, and improving customer service. Additionally, the review discusses the challenges that organizations may face when adopting AI technologies, such as data quality issues, privacy concerns, and skill gaps.The paper draws on recent academic and industry research to provide insights into the potential for AI to optimize supply chain operations. The findings suggest that AI can significantly improve supply chain efficiency, reduce costs, and enhance customer satisfaction. Overall, this review paper offers a comprehensive understanding of the applications and benefits of AI in supply chain management and highlights the need for organizations to embrace AI technologies to stay competitive in today's fast-paced business environment. Introduction Supply chain management (SCM) is a critical aspect of modern business operations, involving the planning, sourcing, manufacturing, delivery, and returns of goods and services. The success of SCM relies on the ability to optimize processes, reduce costs, and improve efficiency while maintaining high levels of quality and customer satisfaction. One emerging technology that is transforming SCM is artificial intelligence (AI).AI refers to the use of algorithms and machine learning techniques to enable machines to perform tasks that would typically require human intelligence, such as pattern recognition, decision-making, and language processing. In the context of SCM, AI has the potential to revolutionize the way businesses manage their supply chains by enabling real-time data analysis, predictive modeling, and automated decision-making.The purpose of this review paper is to provide a comprehensive overview of AI applications in SCM. The paper will explore the types of AI technologies used in SCM and their applications in different stages of the supply chain, including demand forecasting, inventory management, supplier selection, production scheduling, logistics, transportation management, and sustainability. Additionally, the paper will examine the benefits and challenges of implementing AI in SCM and provide real-world case studies of AI in action. Finally, the paper will explore future trends and directions of AI in SCM and identify areas for further research. [1-2] The integration of AI in SCM has the potential to bring significant benefits to businesses. One major benefit is the ability to optimize supply chain operations and reduce costs. AI can help businesses analyze large volumes of data to identify patterns and trends, which can be used to optimize inventory levels, reduce lead times, and improve production scheduling. Additionally, AI can help businesses improve their responsiveness to demand fluctuations by predicting future demand based on historical data, weather patterns, and other factors.Another benefit of AI in SCM is the ability to improve decision-making. With AI-powered analytics and predictive modeling, businesses can make better-informed decisions about supplier selection, production planning, and logistics management. This can lead to improved quality, reduced waste, and better customer satisfaction. However, implementing AI in SCM also comes with several challenges. One of the main challenges is data quality. AI algorithms rely on accurate and timely data to make predictions and decisions. If the data is incomplete or inaccurate, the results will be unreliable, which can lead to suboptimal decisions and outcomes. Additionally, there may be resistance from employees who are reluctant to adopt new technologies or fear that AI may replace their jobs. Furthermore, ethical considerations, such as bias in algorithms and data privacy, need to be addressed when implementing AI in SCM.Despite these challenges, the benefits of AI in SCM are too significant to ignore. As such, businesses need to stay abreast of the latest developments in AI and explore ways to integrate it into their supply chain operations. This review paper aims to provide businesses with a comprehensive overview of AI applications in SCM, including the benefits, challenges, and real-world case studies of AI in action. The paper will also explore future trends and directions of AI in SCM, providing businesses with valuable insights into how they can leverage AI to stay ahead of the competition. [3-5]
The unpredictable market scenario in the manufacturing industry demands the adoption of reconfigurability enablers. These enablers reduce the reconfiguration effort throughout the system life cycle and allow frequent reconfigurations of the manufacturing system. Despite the relevance of the subject, examples and concepts of reconfigurability enablers are fragmented in literature. Therefore, this study systematically reviews literature in order to: (i) outline the state of the art on reconfigurability enablers in automated, mixed and manual systems; and, (ii) provides classification frameworks for reconfigurability enablers for manufacturing systems, machines, robots, material handling systems, and operators. Additionally, new reconfigurability enablers related to Industry 4.0 are outlined, which connect systems and human resources with different roles and facilitate responsive adaptation of humans to changes. Directions for future research include extending the theory on reconfigurable manufacturing with fundamentals of human-centric automation and operationalising the proposed classification framework.
In this paper, a production planning game with single and multiobjectives in uncertain environment is considered. In this problem, the parameters are assumed to be fuzzy variables. By the notions of the expected value and the critical value, the concept of the solutions in the game is introduced. It is shown that the game is balanced and the core of game is nonempty. The duality theory in single-objective and the weighted sum method in multiobjective games are proposed to obtain the payoffs of the players. Finally, the validity and applicability of the method are illustrated by a practical example.
The design and management of an efficient, resilient, and viable supply chain (SC) capable of operations and demand fulfillment continuity despite severe disruptions is imperative for the survivability of firms and for providing society with essential goods and services in long-term crises. This Special Issue focuses on SC adaptation and viability as novel decision-making settings for operations research and management science (OR/MS) emerged in the wake of the COVID-19 pandemic, which goes beyond short-term, singular event-driven disruptions. Papers in the Special Issue present new and original OR/MS research to support decision-making related to long-term SC crises with inherent uncertainty about the present and future. Since SC viability theory is relatively new, this Special Issue contributes to advancing our knowledge and application fields for designing and managing SCs as viable systems. We present fundamentals of SC viability theory, review and summarize papers in the Special Issue, and project some future research directions.
Unpredictable disruptions of the supply chain, as they have been caused by the Covid-19 pandemic, require a rapid adaptation of the supply chain, i.e., the reconfiguration of processes and structures to re-establish resilience and maintain viability. Promising reconfigurations need to be identified and assessed regarding anticipatable supply chain performance and costs. Nevertheless, a comprehensive comparison of all potential reconfigurations is difficult as several objectives need to be aligned. To support a rapid preselection of the most promising ones, this paper presents the novel approach of a Supply Chain Resilience Analysis (SCRA), which allows to quantitatively evaluate the effectiveness and efficiency of supply chain reconfigurations under disruption to ensure long-term recovery. Key concept of the SCRA is the combination of all relevant metrics into a single Supply Chain Resilience Index (SCRI) that builds upon an adapted process capability index (PCI). The PCI is usually applied in quality management of production processes to assess if a process adheres to specified limits of quality characteristics. In combination with a digital twin of the supply chain, the SCRA methodology can be applied for an automatic pre-selection of supply chain reconfigurations. For verification and validation of the developed methodology and its index, the presented methodology has been applied in a use case of an automotive supply chain.
Production logistics (PL) is increasingly receiving attention from supply chain research. The spatial disorder and temporal asynchrony of the PL resources due to the uncertainty and dynamicity pose great challenges to efficient resource allocation. The inability to obtain and rational use of PL resource spatial-temporal values causes unnecessary long travelling distances and excessive waiting time, which impede the sustainable performance of PL operations. In response, this research proposes a PL resource allocation approach based on the dynamic spatial-temporal knowledge graph (DSTKG). Internet of Things(IoT) signals data generated from large-scale deployed IoT devices are investigated and analysed to spatial-temporal values through deep neural networks. The DSTKG model is established for representing the digital twin replica with spatial-temporal consistency, followed by reasoning and completion of relationships based on PL task information. The PL resources are allocated efficiently through the graph algorithm from the directed and weighted graph. The case study is conducted to verify the feasibility and practicality of the proposed solution based on large-scale deployment. Finally, the result demonstrates the effectiveness of the proposed methodology.
Resilience is one of the key characteristics that manufacturing systems should have as it offers the ability to withstand difficult situations and be able to accommodate disruptions without the incurrence of significant additional costs. The main contribution of this study is the presentation of a method for quantifying resilience in manufacturing systems based on calculating the penalty of possible changes. The method is applied to an industrially-relevant scenario to estimate the resilience of two production systems when COVID-19 disrupts their production. The first system uses additive manufacturing (3D printing), and the second uses injection moulding. Several scenarios, related to the systems’ operational environment, are presented on the basis of pandemic-related possible events. The validation of the proposed resilience measure demonstrates the method’s suitability and reliability to be considered in industrial practice, in support of decision-making. The resilience measure can be used by managers to assess, compare and improve their production systems, and decide on strategic investment costs to improve systems’ resilience. It can be applied for several disruption scenarios or variations of the same disruption scenario with different disruption characteristics, such as duration, recovery time and impact on the production system.
It is important to manage operational disruptions to ensure the success of supply chain operations. To achieve this aim, researchers have developed techniques that determine the occurrence of operational risk events which assists supply chain operational risk managers develop plans to manage them by detection/monitoring, mitigation/management, or optimization techniques. Various artificial intelligence (AI) approaches have been used to develop such techniques in the broad activities of operational risk management. However, all of these techniques are black box in their working nature. This means that the chosen technique cannot explain why it has given that output and whether it is correct and free from bias. To address this, researchers argue the need for supply chain management professionals to move towards using explainable AI methods for operational risk management. In this paper, we conduct a systematic literature review on the techniques used to determine operational risks and analyse whether they satisfy the requirement of them being explainable. The findings highlight the shortcomings and inspires directions for future research. From a managerial perspective, the paper encourages risk managers to choose techniques for supply chain operational risk management that can be auditable as this will ensure that the risk managers know why they should take a particular risk management action rather than just what they should do to manage the operational risks.