Conference Paper

An AI based decision support system for preventive maintenance and production optimization in energy intensive manufacturing plants

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Besides pursuing the economic goals of low costs and high profits, companies are becoming more and more aware of the environmental and social impact of their actions. Companies striving for the integrated optimization of environmental and economic perspectives within their production processes, need to be supported by tools helping to understand the effects of the decision making process. In this context, this paper describes a Decision Support System (DSS) enabling the early identification of problems occurring on manufacturing lines thus suggesting related recovery actions, together with the potential repercussions of their adoption, at economic and environmental level. The decision making process beneath the DSS starts from the aggregation of production lines sensors data in Key Performance Indicators (KPI). The data are then processed by means of an Artificial Neural Networks (ANN) based knowledge system which enables to suggest preventive maintenance interventions. The proposed maintenance activities, elaborated throughout a scheduling engine, are integrated within the weekly production schedule, according to the selected optimization policy. Preliminary tests have been carried out in manufacturing plants of IKEA industries and Brembo.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Monitored data empower: performance optimization, support to guarantee standardization and legal compliance, sustainability communication and marketing [19], [20], [21]. The exploitation of indexes is recognized to be an effective support to decision-making [22] [23], allowing designers and managers to check the current sustainability performances, fix benchmarks and thus promote product, processes, company and supply chain sustainability enhancement, and understand where to act in order to obtain more effective improvements. The monitoring of product and company through quantifiable measures is also fostering the compliance with mandatory regulations and voluntary standards, since a more complete and deep knowledge on internal and external processes is encouraged [24]. ...
... 2) Heterogeneity of the assessment scope: as identified by [19], [20], [21], [24], the adoption of the LCA analysis is prone to different industrial needs, going from product and process monitoring and optimization to sustainability communication and marketing. Decision-making at different levels in the value network has therefore to be supported in an integrated way, by providing the means to exploit the different uses that LCA derived indicators can offer [22], [23]. ...
... Furthermore, due to the development of Artificial Intelligence technology, big data analysis has achieved unprecedented progress and expansion [4][5][6]. AI-based decision-making support [7] is also becoming increasingly popular in the operation and maintenance of manufacturing systems such as production scheduling [8], stock management [9], preventive maintenance [10], etc. Although decision-making support systems are more and more popular, it is worth noting that most enterprise support decisions today are mainly based on the analysis results of a single data source. ...
Article
Full-text available
In recent years, the development of sensor technology in industry has profoundly changed the way of operation and management in manufacturing enterprises. Due to the popularization and promotion of sensors, the maintenance of machines on the production line are also changing from the subjective experience-based machine maintenance to objective data-driven maintenance decision-making. Therefore, more and more data decision model has been developed through AI technology and intelligence algorithms. Equally important, the information fusion between decision results, which got by data decision model, has also received widespread attention. Information fusion is performed on symmetric data structures. The asymmetric data under the symmetric structure leads to the difference in information fusion results. Therefore, fully considering the potential differences of asymmetric data under a symmetric structure is an important content of information fusion. In view of the above, this paper studies how to make information fusion between different decision results through the framework of D-S evidence theory and discusses the deficiency of D-S evidence theory in detail. Based on D-S evidence theory, then a comprehensive evidence method for information fusion is proposed in this paper. We illustrate the rationality and effectiveness of our method through analysis of experiment case. And, this method is applied to a real case from industry. Finally, the irrationality of the traditional D-S method in the comprehensive decision-making results of machine operation and maintenance was solved by our novel method.
... [6] presents an integrated system health management-oriented maintenance decision support methodology and framework for a multi-state system based on data mining. [7] describes a Decision Support System (DSS) enabling the early identification of problems occurring on manufacturing lines thus suggesting related recovery actions, together with the potential repercussions of their adoption, at economic and environmental level. [8] proposes an outline of the architectural design and the conceptual framework for a Smart Maintenance Decision Support System (SMDSS) which is capable of providing end users with recommendations to improve asset lifecycles. ...
Conference Paper
Full-text available
The current work presents a decision support system architecture for evaluating the features representing the health status to predict maintenance actions and remaining useful life of component. The evaluation is possible through pattern analysis of past and current measurements of the focused research components. Data mining visualization tools help in creating the most suitable patterns and learning insights from them. Estimations like features split values or measurement frequency of the component is achieved through classification methods in data mining. This paper presents how the quantitative results generated from data mining can be used to support decision making of domain experts.
... A more extensive and in depth analysis of the Factory-Ecomation DSS can be found in Confalonieri et al. [15]. ...
Chapter
Besides pursuing the economic goals of low costs and high profits, companies are becoming more and more aware of the environmental and social impact of their actions. Companies striving for the integrated optimization of environmental and economic perspectives within their production processes, need to be supported by tools helping to understand the effects of the decision making process. In this context, this paper describes the Artificial Intelligence developed for a Decision Support System (DSS) which enables the early identification of problems occurring on manufacturing. The decision making process beneath the DSS starts from the aggregation of production lines sensors data in Key Performance Indicators (KPI). The data are then processed by means of an Artificial Neural Networks (ANN) based knowledge system which enables to suggest preventive maintenance interventions. The proposed maintenance activities, elaborated throughout a scheduling engine, are integrated within the weekly production schedule, according to the selected optimization policy.
Article
Predictive maintenance has the potential to improve the reliability of production and service provisioning. However, there is little knowledge about the proper implementation of predictive maintenance in research and practice. Therefore, we conducted a multi-case study and investigated underlying conditions and technological aspects for implementing a predictive maintenance system and where it leads to. We found that predictive maintenance initiatives are triggered by severe impacts of failures on revenue and profit. Furthermore, successful predictive maintenance initiatives require that pre-conditions are fulfilled: Data must be available and accessible. Very important is also the support by the management. We identified four factors important for the implementation of predictive maintenance. The integration of data is highly facilitated by Cloud-based mechanisms. The detection of events is enabled by advanced analytics. The execution of predictive maintenance operations is supported by data-driven process automation and visualization.
Article
Full-text available
This paper introduces the concepts of neural networks and presents an overview of the applications of neural networks in decision support systems (DSS). Neural networks can be viewed as supporting at least two types of DSS: data driven and model-driven. First, neural networks can be employed as data analysis tools for forecasting and prediction based on historical data in a data-driven DSS. Second, neural networks also can be viewed as a class of quantitative models to be used in a model-driven DSS. After describing the basics of neural networks, we present selected applications of neural networks in DSS. We then describe a web-based DSS built by us that employs a neural network. This DSS has been built to assist a Hollywood decision maker in making decisions on a movie’s parameters. The paper concludes with a list of issues to consider in employing a neural network for a DSS application.
Chapter
Full-text available
A number of retail firms use a “private-label” strategy in which merchandise is sold under a brand name exclusive to the retail firm, but manufactured by one or more independent vendors. While offering a number of benefits, this approach also poses a different set of supply chain challenges than manufacturer-brand-based retailing, in that the retail firm must take a more active role in organizing and coordinating the planning and materials management activities in a supply base that is often dispersed and heterogenous. This chapter describes a methodology for planning capacity commitments, scheduling shipments, and managing inventory for an assortment of private-label retail merchandise produced by multiple vendors. The vendors differ in their lead time requirements, costs, and production flexibility. Product demand is uncertain, and fluctuates over time. We develop an optimization model to choose the production commitments that maximize the retailer’s expected gross profit, given market demand forecasts and vendors’ capacity and flexibility constraints. The model has been incorporated into a PC-based decision support system called the Sourcing Allocation Manager (SAM). This was developed in collaboration with supply chain planners at a global retailer of seasonal and fashion merchandise, and has been tested by buyers at two major retailers.
Article
A manager tries to put together the various resources under his control into an activity that achieves his objectives. A model of his operation can assist him but probably will not unless it meets certain requirements. A model that is to be used by a manager should be simple, robust, easy to control, adaptive, as complete as possible, and easy to communicate with. By simple is meant easy to understand; by robust, hard to get absurd answers from; by easy to control, that the user knows what input data would be required to produce desired output answers; adaptive means that the model can be adjusted as new information is acquired; completeness implies that important phenomena will be included even if they require judgmental estimates of their effect; and, finally, easy to communicate with means that the manager can quickly and easily change inputs and obtain and understand the outputs. Such a model consists of a set of numerical procedures for processing data and judgments to assist managerial decision making and so will be called a decision calculus. An example from marketing is described. It is an on-line model for use by product managers on advertising budgeting questions. The model is currently in trial use by several product managers.
Article
This article discusses how Predictive Maintenance (PdM) technologies can be successfully applied to both GMP and non-GMP utility systems in the pharmaceutical industry. The discussion also demonstrates the clear benefits of PdM, including the use of a proactive approach to maintenance.
Conference Paper
Energy consumption of a machine tool increases dramatically as reliability decreases, which indicates performance degradation. From the perspective of near-zero downtime and energy conservation, preventive maintenance is usually carried out. This research aims at modeling the energy consumption of machine tools after they are maintained preventively. The relationship between reliability and energy consumption is modeled based on historical data and then the energy consumption of a machine tool is calculated. Reliability is modeled by Weibull distribution, the parameters of which are estimated utilizing the Maximum Likelihood Estimation method. Reliability after preventive maintenance is modeled by employing Malik's Proportional Age Reduction model. The carbon emission is assessed referring to the standard developed by the Climate Registry in North America.
Article
This chapter surveys the state of the art of decision support systems (DSSs) for operations management (OM) with the intent to highlight the important role that DSSs play in facilitating decision processes in OM. Organized along the temporal dimension of OM decisions, our discussion starts with DSSs for long-term OM decisions including operations strategy, capacity planning, location planning, product/process design and design/manufacturing integration. This is followed by a discussion on DSSs for medium- and short-term OM decisions on production planning and control that includes systems such as communication- oriented production information and control systems, material requirements planning, manufacturing resources planning, distribution requirements planning, enterprise resources planning, and operations/project scheduling. After a brief discussion on DSSs for service operations, we conclude our book chapter by providing some perspectives on future development in DSSs for OM.
Article
Manufacturing industries are in the midst of a new technological revolution, characterised by the increasing advances and application of information and communication technology for both information processing and automatic control. A unique manufacturing methodology for non-destructive, real-time process optimization and quality certification has been developed. This includes the design of a decision support system (DSS) for controlling the optimized process. The DSS comprises the capability of supporting both the process operator and manager in the decision-making process, allowing them to take advantage of the degrees of freedom of the physical system to make it work in a way where the optimized process control variables are under statistical control, resulting in optimized output factors that, in turn, secure higher productivity and improved quality.
Article
From the Publisher:How data mining delivers a powerful competitive advantage!Are you fully harnessing the power of information to support management and marketing decisions? You will,with this one-stop guide to choosing the right tools and technologies for a state-of-the-art data management strategy built on a Customer Relationship Management (CRM) framework. Authors Alex Berson,Stephen Smith,and Kurt Thearling help you understand the principles of data warehousing and data mining systems,and carefully spell out techniques for applying them so that your business gets the biggest pay-off possible. Find out about Online Analytical Processing (OLAP) tools that quickly navigate within your collected data. Explore privacy and legal issues. . . evaluate current data mining application packages. . . and let real-world examples show you how data mining can impact — and improve — all of your key business processes. Start uncovering your best prospects and offering them the products they really want (not what you think they want)!How data mining delivers a powerful competitive advantage! Are you fully harnessing the power of information to support management and marketing decisions? You will,with this one-stop guide to choosing the right tools and technologies for a state-of-the-art data management strategy built on a Customer Relationship Management (CRM) framework. Authors Alex Berson,Stephen Smith,and Kurt Thearling help you understand the principles of data warehousing and data mining systems,and carefully spell out techniques for applying them so that your business gets the biggest pay-off possible. Find out about Online Analytical Processing (OLAP) tools thatquickly navigate within your collected data. Explore privacy and legal issues. . . evaluate current data mining application packages. . . and let real-world examples show you how data mining can impact — and improve — all of your key business processes. Start uncovering your best prospects and offering them the products they really want (not what you think they want)!
Article
The paper describes the fundamental concepts of maintenance and the role that information technology can play in the support of maintenance activities. Function-Behaviour-State modelling is used to describe faults and deterioration of mechanisms in terms of user perception and measurable quantities. Fault diagnosis, repair and maintenance strategies are explained briefly. Model-based Maintenance is discussed in terms of inspection, monitoring, diagnosis and planning, based on functional, behavioural and state models. Some examples of mechanisms illustrate the advantage of using computer-based models as a reference for fault diagnosis. Underlying techniques like qualitative physics, tolerance analysis, and dynamic simulation are discussed. The proposed method is aiming at functionally robust designs, reduction of preventive maintenance cost and more effective fault diagnosis.
Article
Value-based Management (VBM) concepts are prevalent in theory and practice since shareholder value creation is commonly considered the paramount business goal. However. VBM mainly applies data-driven concepts to support decision-making, disregarding model-driven approaches. This paper develops a comprehensive approach to designing model-driven DSS for VBM. First, we derive a conceptual architecture for Integrated Business Planning (IBP) as the foundation for a model-driven approach to VBM. Second, we present a unified modeling approach for value-based performance and risk optimization that implements Value Added (xVA) performance metrics and applies robust optimization methods to mitigate risk impact.
Article
Clothing manufacturers’ direct investment and joint ventures in developing regions have grown rapidly in the last few decades. An inappropriate decision on site selection can cause adverse affects on productivity and increase manufacturing and logistical costs. Manufacturers often face with difficulties during the decision-making process, due to vague and subjective considerations. The process is hampered with variables that cannot be represented in terms of objective values, such as country risk and community facilities. The decision on plant location thus relies mostly on the subjective intuition and assessment of the manufacturer. This paper explains the development of a decision-making model for a clothing plant location, using the feed-forward neural network with an error back-propagation (EBP) learning algorithm and a fuzzy analytical hierarchy process (FAHP). Significant variables in the selection of a clothing plant location will be identified and input into the proposed decision-making model. A suitability index was computed for each site. The sites with higher suitability indices were more appropriate for the establishment of a clothing plant. It was also identified that those variables considered on plant location with lower evaluation weights can be neglected without affecting the prediction accuracy of the proposed decision model .
Article
The economic and political realities of the 1990s forced managers to reverse long-standing organizational cultures in order to reduce costs and energy expenditures in their organisations. For instance, these can be achieved, with respect to maintenance, by replacing a reactive repair-focused attitude by a proactive reliability-focused culture. Thereby far less (i) human effort is expended and (ii) energy would be wasted, both of which lead to increased profitability. (c) 2006 Published by Elsevier Ltd.
Article
The importance of maintenance function has increased due to its role in keeping and improving the system availability and safety but also the product quality. To support this new role, the maintenance concept has undergone through several major developments to lead to proactive considerations mainly based on prognosis process allowing normally to select the best maintenance action to carry out. In this paper the extension of a prognosis process by means of the integration of maintenance alternative impacts is proposed. The deployment of this extended prognosis process follows a methodology based both on probabilistic and event approaches. The feasibility and added value of this new prognosis is experimented on the manufacturing TELMA platform supporting the unwinding of metal bobbins.
Article
This paper presents a decision support system (DSS) for the modeling and management of project risks and risk interactions. This is a crucial activity in project management, as projects are facing a growing complexity with higher uncertainties and tighter constraints. Existing classical methods have limitations for modeling the complexity of project risks. For example, some phenomena like chain reactions and loops are not properly taken into account. This will influence the effectiveness of decisions for risk response planning and will lead to unexpected and undesired behavior in the project. Based on the concepts of DSS and the classical steps of project risk management, we develop an integrated DSS framework including the identification, assessment and analysis of the risk network. In the network, the nodes are the risks and the edges represent the cause and effect potential interactions between risks. The proposed simulation-based model makes it possible to re-evaluate risks and their priorities, to suggest and test mitigation actions, and then to support project manager in making decisions regarding risk response actions. An example of application is provided to illustrate the utility of the model.
Conference Paper
Production scheduling is a complex decision-making process that is becoming more important than ever in competitive markets today. However, effective production scheduling remains a very challenging task, and the current production scheduling systems tend to be inflexible and expensive. Although domain knowledge and information are very important to scheduling decisions, scheduling systems usually cannot effectively make use of them. In this paper, A multi-scenario analysis (MSA) model is proposed for distributed collaborative decision-making, based on which a multi-scenario analysis-based production scheduling platform (MSAPSP) is developed The platform comprises a toolkit (MSADev) and an engine (MSARE) powered by a script language (EXASL). It provides a flexible and cost-effective tool to exploit domain knowledge and information for scheduling and rescheduling decisions.
Corporate Dashboards for Integrated Business and Engineering Decisions in Oil Refineries: An Agent- Based Approach Decision Support SystemsAn integrated platform for distributed knowledge-based production schedulingDecision support system: real‐time control of manufacturing processes
  • W Hu
  • A Almansoori
  • P Kannan
  • S Azarm
  • Z Wang
W. Hu, A. Almansoori, P. Kannan, S. Azarm and Z. Wang, "Corporate Dashboards for Integrated Business and Engineering Decisions in Oil Refineries: An Agent- Based Approach," Decision Support Systems, pp. 729- 741, 2012. [15] S. Choi and S. Kang, "An integrated platform for distributed knowledge-based production scheduling," IEEE, pp. 111-116, 2005. [16] K. Swanepoel, "Decision support system: real‐time control of manufacturing processes," Journal of Manufacturing Technology Management, pp. 68-75, 2004.
Using Mixed-Integer Programming to Reduce
  • E Katok
  • D Ott
E. Katok and D. Ott, "Using Mixed-Integer Programming to Reduce," 2000.
Models and Managers: The Concept of a Decision CalculusSam: A Decision Support System for Retail Supply Chain Planning for Private-label Merchandise with Multiple Vendors
  • J D Little
J. D. Little, "Models and Managers: The Concept of a Decision Calculus," Management Science, pp. 1841- 1853, 1970. [11] S. A. Smith, N. Agrawal and A. A. Tsay, "Sam: A Decision Support System for Retail Supply Chain Planning for Private-label Merchandise with Multiple Vendors," Supply Chain Management: Models, Applications, and Research Directions, pp. 163-198, 2005.
Advantages and Disadvantages of Using Neural Network for predictions
  • V M Ciobanu
V. M. Ciobanu D, "Advantages and Disadvantages of Using Neural Network for predictions," Ovidius University Annals, Economic sciences series, vol. 13, no. 1, pp. 444-450, 2013.