Abstract
The advent of Internet of Things and artificial intelligence in the era of Industry 4.0 has transformed decision-making within production systems. In particular, many decisions that previously required significant human activity are now made automatically with minimal human intervention via so-called digital twins (DTs). In the context of maintenance and reliability modeling, this naturally calls for new paradigms that can be seamlessly integrated within DTs for decision-making. The input data for time to failure needed in reliability computations are directly collected from the work center in a digital setting and often do not satisfy a known distribution. A neural network (NN) is proposed here to bypass this difficulty within the DT. Further, an algorithm inspired from machine learning is employed to solve the underlying semi-Markov decision process, whose transition model is captured via the NN. Numerical studies are carried out to demonstrate the usefulness of the approach. Finally, convergence properties of the algorithm are analyzed mathematically.
Similar content being viewed by others
References
Aghezzaf, E. H., Jamali, M. A., & Ait-Kadi, D. (2007). An integrated production and preventive maintenance planning model. European Journal of Operational Research, 181(2), 679–685.
Ahuja, I., & Khamba, J. (2008). Total productive maintenance: Literature review and directions. International Journal of Quality & Reliability Management, 25(7), 709–756.
Askin, R., & Goldberg, J. (2007). Design and analysis of lean production systems. Wiley.
Ayvaz, S., & Alpay, K. (2021). Predictive maintenance system for production lines in manufacturing: A machine learning approach using IoT data in real-time. Expert Systems with Applications, 173, 114598.
Barlow, E., Bedford, T., Revie, M., Tan, J., & Walls, L. (2021). A performance-centred approach to optimising maintenance of complex systems. European Journal of Operational Research, 292(2), 579–595.
Bertsekas, D. P. (2012). Dynamic programming and optimal control: Volumes I and II. Athena Scientific.
Bertsekas, D. P., & Tsitsiklis, J. N. (1996). Neuro-dynamic programming. Athena Scientific.
Borkar, V. (2008). Stochastic approximation: A dynamical systems viewpoint. Hindusthan Book Agency.
Brauer, F., & Nohel, J. A. (1989). The qualitative theory of ordinary differential equations: An introduction. Dover Publications.
Chelbi, A., & Ait-Kadi, D. (2004). Analysis of a production/inventory system with randomly failing production unit submitted to regular preventive maintenance. European Journal of Operational Research, 156(3), 712–718.
Chen, D., & Trivedi, K. (2005). Optimization for condition-based maintenance with semi-Markov decision process. Reliability Engineering & System Safety, 90(1), 25–29.
Das, T., & Sarkar, S. (1999). Optimal preventive maintenance in a production inventory system. IIE Transactions, 31, 537–551.
Denardo, E. (1970). On linear programming in a Markov decision problem. Management Science, 16(5), 281–288.
Giannoccaro, I., & Pontrandolfo, P. (2002). Inventory management in supply chains: A reinforcement learning approach. International Journal of Production Economics, 78(2), 153–161.
Gosavi, A. (2006). A risk-sensitive approach to total productive maintenance. Automatica, 42, 1321–1330.
Gosavi, A. (2013). Relative value iteration for average reward semi-Markov control via simulation. In Proceedings of the winter simulation conference (pp. 623–630). IEEE.
Gosavi, A. (2015). Simulation-based optimization: Parametric optimization techniques and reinforcement learning (2nd ed.). Springer.
Grinstead, C. M., & Snell, J. L. (1997). Introduction to probability (2nd ed.). American Mathematical Society.
Hao, T., & Tamio, A. (2009). Look-ahead control of conveyor-serviced production station by using potential-based online policy iteration. International Journal of Control, 82(10), 1917–1928.
Hofmann, E., & Rusch, M. (2017). Industry 4.0 and the current status as well as future prospects on logistics. Computers in Industry, 89, 23–34.
Jin, H., Han, F., & Sang, Y. (2020). An optimal maintenance strategy for multi-state deterioration systems based on a semi-Markov decision process coupled with simulation technique. Mechanical Systems and Signal Processing, 139, 106570.
Koh, L., Orzes, G., & Jia, F. J. (2019). The fourth industrial revolution (industry 4.0): Technologies disruption on operations and supply chain management. International Journal of Operations & Production Management, 39, 817–828.
Kuo, T.-C., Hsu, N.-Y., Li, T. Y., & Chao, C.-J. (2021). Industry 4.0 enabling manufacturing competitiveness: Delivery performance improvement based on theory of constraints. Journal of Manufacturing Systems, 60, 152–161.
Kushner, H., & Clark, D. (1978). Stochastic approximation methods for constrained and unconstrained systems. Springer.
Kyriakidis, E., & Dimitrakos, T. (2006). Optimal preventive maintenance of a production system with an intermediate buffer. European Journal of Operational Research, 168(1), 86–99.
Lei, Y., Li, N., Gontarz, S., Lin, J., Radkowski, S., & Dybala, J. (2016). A model-based method for remaining useful life prediction of machinery. IEEE Transactions on Reliability, 65(3), 1314–1326.
Lewis, E. E. (1995). Introduction to reliability engineering (2nd ed.). Wiley.
Li, Q., Zhao, L., Gao, J., Liang, H., Zhao, L., & Tang, X. (2018). SMDP-based coordinated virtual machine allocations in cloud-fog computing systems. IEEE Internet of Things Journal, 5(3), 1977–1988.
Liu, K., Gebraeel, N. Z., & Shi, J. (2013). A data-level fusion model for developing composite health indices for degradation modeling and prognostic analysis. IEEE Transactions on Automation Science and Engineering, 10(3), 652–664.
McKone, K. E., & Weiss, E. (1998). TPM: planned and autonomous maintenance: Bridging the gap between practice and research. Production and Operations Management, 7(4), 335–351.
Melesse, T. Y., Di Pasquale, V., & Riemma, S. (2020). Digital twin models in industrial operations: A systematic literature review. Procedia Manufacturing, 42, 267–272.
Michalski, R. S., Carbonell, J. G., & Mitchell, T. (2013). Machine learning: An artificial intelligence approach. Springer Science.
Pham, H. (2003). Handbook of reliability engineering. Springer.
Platzman, L. (1977). Improved conditions for convergence in undiscounted Markov renewal programming. Operations Research, 25(3), 529–533.
Puterman, M. (1994). Markov decision processes. Wiley Interscience.
Ross, S. (2014). Introduction to probability models (9th ed.). Academic Press.
Ruiz-Sarmiento, J.-R., Monroy, J., Moreno, F.-A., Galindo, C., Bonelo, J.-M., & Gonzalez-Jimenez, J. (2020). A predictive model for the maintenance of industrial machinery in the context of industry 4.0. Engineering Applications of Artificial Intelligence, 87, 103289.
Sanders, A., Elangeswaran, C., & Wulfsberg, J. P. (2016). Industry 4.0 implies lean manufacturing: Research activities in industry 4.0 function as enablers for lean manufacturing. Journal of Industrial Engineering and Management (JIEM), 9(3), 811–833.
Schouten, F., & Vanneste, S. (1992). Maintenance optimization with buffer capacity. European Journal of Operational Research, 82, 323–338.
Schume, P. (2020). Improve product quality and yield with intelligent, secure, and adaptable manufacturing operations: Industry 4.0 brings opportunities to infuse AI into manufacturing. https://www.ibm.com/blogs/internet-of-things/iot-manufacturing-ready/.
Schweitzer, P. J. (1971). Iterative solution of the functional equations of undiscounted Markov renewal programming. Journal of Mathematical Analysis and Applications, 34(3), 495–501.
Sennott, L. (1999). Stochastic dynamic programming and the control of queueing systems. Wiley.
Silvestri, L., Forcina, A., Introna, V., Santolamazza, A., & Cesarotti, V. (2020). Maintenance transformation through industry 4.0 technologies: A systematic literature review. Computers in Industry, 123, 103335.
Singh, S., Tadic, V., & Doucet, A. (2007). A policy-gradient method for semi-Markov decision processes with application to call admission control. European Journal of Operational Research, 178, 808–818.
Song, C., Liu, K., & Zhang, X. (2017). Integration of data-level fusion model and kernel methods for degradation modeling and prognostic analysis. IEEE Transactions on Reliability, 67(2), 640–650.
Sutton, R., & Barto, A. G. (1998). Reinforcement learning. The MIT Press.
Swanson, L. (2001). Linking maintenance strategies to performance. International Journal of Production Economics, 70(3), 237–244.
van Noortwijk, J. (2009). A survey of the application of gamma processes in maintenance. Reliability Engineering & System Safety, 94(1), 2–21.
Velmurugan, R. S., & Dhingra, T. (2015). Maintenance strategy selection and its impact in maintenance function: A conceptual framework. International Journal of Operations & Production Management, 35(12), 1622–1661.
Wang, F., Du, J., Zhao, Y., Tang, T., & Shi, J. (2020). A deep learning based data fusion method for degradation modeling and prognostics. IEEE Transactions on Reliability, 70(2), 775–789.
Wang, H., & Pham, H. (2006). Reliability and optimal maintenance (Springer series in reliability engineering) (Vol. 14197). Springer.
White, D. J. (1963). Dynamic programming, Markov chains, and the method of successive approximations. Journal of Mathematical Analysis and Applications, 6, 373–376.
Yan, J., Meng, Y., Lu, L., & Li, L. (2017). Industrial big data in an industry 4.0 environment: Challenges, schemes, and applications for predictive maintenance. IEEE Access, 5, 23484–23491.
Zakharchuk, A. (2021). Turn predictive maintenance into a success story for your manufacturing company. https://www.ai.intelliarts.com/pdm-whitepaper.
Zhang, X., & Gao, H. (2012). Road maintenance optimization through a discrete-time semi-Markov decision process. Reliability Engineering & System Safety, 103, 110–119.
Acknowledgements
The authors thank the three anonymous reviewers and the editor for their careful reading of the manuscript and the numerous suggestions. In particular, the authors thank the first reviewer for improving the discussion on the contributions of the paper, the second reviewer for the careful presentation of the notation used, and the third reviewer for the suggestion to introduce a flowchart for the algorithm.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix
A Failure Data
The failure data are shown via Table .
B Classical TTF
For the classical case where the time to failure has a known (continuous) distribution, whose cdf is denoted by \(G_c\): the probability of failure in the ith production cycle is computed via the following conditional probability:
This leads to the following transition probability model for the continuous TTF:
-
Transition probabilities for production action: For \(i\in {{\mathcal {S}}}\):
$$\begin{aligned} p(i,1,j) = {\left\{ \begin{array}{ll} \frac{G_c(i+1)-G_c(i)}{1-G_c(i)} &{} \text {if j=0} \\ 1-\frac{G_c(i+1)-G_c(i)}{1-G_c(i)} &{} \text {if j=i+1} \\ 0 &{} \text {otherwise.} \end{array}\right. } \end{aligned}$$
The rest of the transition kernel, i.e., the transition probability matrix for the maintenance action and the transition reward and transition time matrices for both actions, is identical to that described in the main body of the paper.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Gosavi, A., Le, V.K. Maintenance optimization in a digital twin for Industry 4.0. Ann Oper Res (2022). https://doi.org/10.1007/s10479-022-05089-1
Accepted:
Published:
DOI: https://doi.org/10.1007/s10479-022-05089-1