Multiple and diverse factory digital twins have been proposed in the literature. However, despite the recognized growing importance of workers in smart and autonomous industrial settings, such models still lack or oversimplify human representation. Human digital twins must include human monitoring and behavioural data and models based on psychophysical status, knowledge, skills, and personal needs to manage production systems that aim, at the same time, to achieve process performance and workers’ wellbeing. This paper proposes a metamodel based on data, events, and connectors that supports the modular composition of tailored human digital twins. This work also addresses an industrial application of the metamodel for preliminary validation.
Today, there are many examples in the literature where digital copies of machines, devices, products or entire production systems are used to improve performance, make predictions and take decisions. However, humans have been so far excluded from these digital representations, even though their influence on process quality, performance and continuous improvement is significant. Typically, human factors are only considered in the context of job design and not in continuous decision-making and control. However, to create production systems that seamlessly complement human capabilities, the digital factory must include an accurate and realistic digital representation of workers: the Human Digital Twin. Human Digital Twins must incorporate data and behavioural models based on psychophysical status, skills, performance and personal needs, and communicate with decision-making and control systems. This research explores the concept of Human Digital Twin from a modelling perspective and proposes a meta-model that supports the definition of digital representation of workers in manufacturing. This meta-model is based on the analysis of the existing literature on humans modelling in industrial contexts and on the need for a flexible and modular representation of the worker in the digital factory. The proposed meta-model was instantiated and validated through an experiment in an injection moulding work cell to demonstrate its effectiveness and industrial relevance. The results showed that workers' well-being improved, while production and quality performance were optimised.
Optimization on the basis of sustainability brings important benefits to manufacturing process as sustainable productions constitute a crucial aspect in modern manufacturing. This paper presents a new formalized framework for optimizing the sustainability of manufacturing processes. Unlike previous approaches, the proposed technique combines a methodology for selecting the sustainability indicators and a multi-objective optimization for improving the three sustainability pillars (economy, environment and society). While selecting the significant sustainability indicators in the considered manufacturing process relies on the ABC judgment method, the Saaty’s method enables weighting the chosen indicators in order to combine them into suitable economic, environmental and social sustainability indexes. Other technological aspects, usually taken as objectives in previous works, are considered constraints in the proposed approach. The optimization is performed by using nature inspired heuristics, which return the set of non-dominated solutions (also known as Pareto front), from which the most convenient alternative is chosen by the decision maker, depending on the specific conditions of the process. For illustrating the usage of the proposed framework, it is applied to the optimization of a submerged arc welding process. Compared with currently used welding parameters, the computed optimal solution outperforms the economic and environmental sustainability while keeps equal the social impact. The results show not only the effectiveness of the proposed approach, but also its flexibility by giving a set of possible solutions which can be chosen depending on how are ranked the sustainability pillars.
Nowadays, one important challenge in cyber-physical production systems is updating dynamic production schedules through an automated decision-making performed while the production is running. The condition of the manufacturing equipment may in fact lead to schedule unfeasibility or inefficiency, thus requiring responsiveness to preserve productivity and reduce the operational costs. In order to address current limitations of traditional scheduling methods, this work proposes a new framework that exploits the aggregation of several digital twins, representing different physical assets and their autonomous decision-making, together with a global digital twin, in order to perform production scheduling optimization when it is needed. The decision-making process is supported on a fuzzy inference system using the state or conditions of different assets and the production rate of the whole system. The condition of the assets is predicted by the condition-based monitoring modules in the local digital twins of the workstations, whereas the production rate is evaluated and assured by the global digital twin of the shop floor. This paper presents a framework for decentralized and integrated decision-making for re-scheduling of a cyber-physical production system, and the validation and proof-of-concept of the proposed method in an Industry 4.0 pilot line of assembly process. The experimental results demonstrate that the proposed framework is capable to detect changes in the manufacturing process and to make appropriate decisions for re-scheduling the process.
In recent years, digitalization has taken an important role in the manufacturing industry. Digital twins (DT) are one of the key enabling technologies that are leading the digital transformation. Integrating DT with IoT and artificial intelligence enables the development of more accurate models to improve scheduling tasks, production performance indices, optimization and decision-making. This work proposes a distributed DT framework to improve decision making at local level in manufacturing processes. A decision-making module supported on an adaptive threshold procedure is designed and implemented. Finally, the proposed framework is evaluated on a pilot line, highlighting the behavior of the decision-making module for detecting possible faults, alerting the operator and notifying the manufacturing execution system to trigger actions of reconfiguration and scheduling.
In the first months of the KITT4SME project, SUPSI, WUT and Ginkgo Analytics collaborate to realise the KITT4SME report 2021. This report includes: - a sum-up of a methodology to assess AI readiness and maturity level in SMEs; - the results obtained through a survey investigating AI adoption that involved 36 European manufacturing companies; - a set of guidelines supporting AI adoption in SMEs.
Today literature proposes several models to assess the level of digitisation of a company. However, digitisation includes innumerable elements and aspects that require either models that are too complex to be easily applied by Small and Medium Enterprises (SMEs) or too high-level to provide significant hints for improvement. This paper proposes a model for measuring Artificial Intelligence (AI) readiness and promoting its adoption in SMEs. By focusing the approach, a model is obtained that is easy to apply, also for SMEs, and sufficiently detailed to provide relevant information and guidelines. The model has been already applied in a sample of 39 companies. It could serve for organizations to assess themselves and for authorities, industrial organisations and academia to diagnose selected populations (e.g. clusters, sectors, economies).