Abstract
Industry 4.0 is based on machine learning and advanced digital technologies, such as Industrial-Internet-of-Things and Cyber-Physical-Production-Systems, to collect and process data coming from manufacturing systems. Thus, several industrial issues may be further investigated including, flows disruptions, machines’ breakdowns, quality crisis, and so on. In this context, traditional machine learning techniques require the data to be stored and processed in a central entity, e.g., a cloud server. However, these techniques are not suitable for all manufacturing use cases, due to the inaccessibility of private data such as resources’ localization in real time, which cannot be shared at the cloud level as they contain personal and sensitive information. Therefore, there is a critical need to go toward decentralized learning solutions to handle efficiently distributed private sub-datasets of manufacturing systems.
In this article, we design a new monitoring tool for system disruption related to the localization of mobile resources. Our tool may identify mobile resources (human operators) that are in unexpected locations, and hence has a high probability to disturb production planning. To do so, we use federated deep learning, as distributed learning technique, to build a prediction model of resources locations in manufacturing systems. Our prediction model is generated based on resources locations defined in the initial tasks schedule. Thus, system disruptions are detected, in real time, when comparing predicted locations to the real ones, that is collected through the IoT network. In addition, our monitoring tool is deployed at Fog computing level that provides local data processing support with low latency.
Furthermore, once a system disruption is detected, we develop a dynamic rescheduling module that assigns each task to the nearest available resource while improving the execution accuracy and reducing the execution delay. Therefore, we formulate an optimization problem of tasks rescheduling, before solving it using the meta-heuristic Tabu search. The numerical results show the efficiency of our schemes in terms of prediction accuracy when compared to other machine learning algorithms, in addition to their ability to detect and resolve system disruption in real time.
- [1] [n.d.]. TensorFlow Federated. Retrived May 29, 2020 from https://www.tensorflow.org/federated.Google Scholar
- [2] [n.d.]. What Is Industry 4.0. Retrieved July 1, 2020 from https://www.forbes.com/sites/bernardmarr/2018/09/02/what-is-industry-4-0-heres-a-super-easy-explanation-for-anyone/14ca62909788.Google Scholar
- [3] . 2018. Deploying fog computing in industrial internet of things and industry 4.0. IEEE Trans. Industr. Inf. 14, 10 (
October 2018), 4674–4682. Google ScholarCross Ref - [4] . 2015. Internet of Things: A survey on enabling technologies, protocols, and applications. IEEE Commun. Surv. Tutor. 17, 4 (2015), 2347–2376. Google ScholarDigital Library
- [5] . 2019. Towards predicting system disruption in industry 4.0: Machine learning-based approach. Proc. Comput. Sci. 151 (2019), 667–674.Google ScholarDigital Library
- [6] . 2019. Accuracy and localization-aware rescheduling for flexible flow shops in industry 4.0. In Proceedings of the 6th International Conference on Control, Decision and Information Technologies (CoDIT’19). IEEE, 1929–1934.Google ScholarCross Ref
- [7] . 2020. Federated learning for UAVs-enabled wireless networks: Use cases, challenges, and open problems. IEEE Access 8 (2020), 53841–53849. Google ScholarCross Ref
- [8] . 1999. Logistic regression modeling for context-based classification. In Proceedings of the 10th International Workshop on Database and Expert Systems Applications (DEXA’99). 755–759. Google ScholarCross Ref
- [9] . 2018. Smart factory of industry 4.0: Key technologies, application case, and challenges. IEEE Access 6 (2018), 6505–6519. Google ScholarCross Ref
- [10] . 2011. Towards proactive event-driven computing. In Proceedings of the 5th ACM International Conference on Distributed Event-based System (DEBS’11). ACM, New York, NY, 125–136. Google ScholarDigital Library
- [11] . 2020. AutoMEC: LSTM-based user mobility prediction for service management in distributed MEC resources. In Proceedings of the 23rd International ACM Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems (MSWiM’20). New York, NY, 155–159. Google ScholarDigital Library
- [12] . 2013. Proactive event processing in action: A case study on the proactive management of transport processes (industry article). In Proceedings of the 7th ACM International Conference on Distributed Event-based Systems (DEBS’13). ACM, New York, NY, 97–106. Google ScholarDigital Library
- [13] . 2018. Flexible job-shop rescheduling for new job insertion by using discrete jaya algorithm. IEEE Trans. Cybernet. 49, 5 (2019), 1944–1955. Google ScholarCross Ref
- [14] . 1995. Genetic algorithms and tabu search: Hybrids for optimization. Comput. Operat. Res. 22, 1 (1995), 111–134.
Genetic Algorithms. Google ScholarDigital Library - [15] . 2016. iFogSim: A toolkit for modeling and simulation of resource management techniques in internet of things, edge and fog computing environments. Software: Practice and Experience 47, 9 (2017), 1275–1296. arXiv:Google ScholarCross Ref
- [16] . 2018. Challenges facing the industrial implementation of fog computing. In Proceedings of the IEEE 6th International Conference on Future Internet of Things and Cloud (FiCloud’18). IEEE, 341–348.Google Scholar
- [17] . 2010. An agent-based approach to care in independent living. In Ambient Intelligence. Springer, Berlin, 177–186.Google ScholarDigital Library
- [18] . 2010. A Tabu search DSA algorithm for reward maximization in cellular networks. In Proceedings of the IEEE 6th International Conference on Wireless and Mobile Computing, Networking and Communications. 40–45. Google ScholarCross Ref
- [19] . 2012. Machine Scheduling Problems: Classification, Complexity and Computations. Springer Science & Business Media.Google Scholar
- [20] . 2019. A review of deep learning with recurrent neural network. In Proceedings of the International Conference on Smart Systems and Inventive Technology (ICSSIT’19). 460–465. Google ScholarCross Ref
- [21] . 2018. A disruption framework. Technol. Forecast. Soc. Change 129 (2018), 275–284. Google Scholar
- [22] . 1994. The total tardiness problem: Review and extensions. Operat. Res. 42 (
12 1994), 1025–1041. Google ScholarDigital Library - [23] . 2017. Manufacturing analytics and industrial internet of things. IEEE Intell. Syst. 32, 3 (
May 2017), 74–79. Google ScholarDigital Library - [24] . 2017. A method for pattern mining in multiple alarm flood sequences. Chem. Eng. Res. Des. 117 (2017), 831–839.Google ScholarCross Ref
- [25] . 2018. Cost-efficient deployment of fog computing systems at logistics centers in industry 4.0. IEEE Trans. Industr. Inf. 14, 10 (
October 2018), 4603–4611. Google ScholarCross Ref - [26] . 2006. Learning an optimal Naive bayes classifier. In Proceedings of the 18th International Conference on Pattern Recognition (ICPR’06), Vol. 3. 1236–1239. Google ScholarDigital Library
- [27] . 2012. Predictive monitoring of heterogeneous service-oriented business networks: The transport and logistics case. In Proceedings of the Annual SRII Global Conference. 313–322. Google ScholarDigital Library
- [28] . 2019. Deployment of fog computing platform for cyber physical production system based on docker technology. In Proceedings of the International Conference on Applied Automation and Industrial Diagnostics (ICAAID’19), Vol. 1. 1–6. Google ScholarCross Ref
- [29] . 2017. Fog computing based efficient IoT scheme for the industry 4.0. In Proceedings of the IEEE International Workshop of Electronics, Control, Measurement, Signals and Their Application to Mechatronics (ECMSM’17). 1–6. Google ScholarCross Ref
- [30] . 2016. Jaya: A simple and new optimization algorithm for solving constrained and unconstrained optimization problems. Int. J. Industr. Eng. Comput. 7, 1 (2016), 19–34.Google Scholar
- [31] . 1991. A survey of decision tree classifier methodology. IEEE Trans. Syst. Man Cybernet. 21, 3 (
May 1991), 660–674. Google ScholarCross Ref - [32] . 2016. Proactive and dynamic event-driven disruption management in the manufacturing domain. In Proceedings of the IEEE 14th International Conference on Industrial Informatics (INDIN’16). 1320–1325. Google ScholarCross Ref
- [33] . 2012. Rescheduling of parallel machines under machine failures. In Manufacturing Science and Materials Engineering (Advanced Materials Research), Vol. 443. 724–730.Google Scholar
- [34] . 2018. Industrial internet of things: Challenges, opportunities, and directions. IEEE Trans. Industr. Inf. 14, 11 (2018), 4724–4734.Google ScholarCross Ref
- [35] . 2018. Solving multi-objective rescheduling problems in dynamic permutation flow shop environments with disruptions. Int. J. Product. Res. 56, 19 (2018), 6363–6377.Google ScholarCross Ref
- [36] . 2013. Robust scheduling for multi-objective flexible job-shop problems with random machine breakdowns. Int. J. Product. Econ. 141, 1 (2013), 112–126. Google ScholarCross Ref
Index Terms
- Fog-supported Low-latency Monitoring of System Disruptions in Industry 4.0: A Federated Learning Approach
Recommendations
Towards Predicting System Disruption in Industry 4.0: Machine Learning-Based Approach
AbstractIndustry 4.0 is the most recent industrial revolution that aims to improve not only the productivity in the 21st century, but also the flexibility, adaptability, and resilience of the industrial systems. It enables the collection of real-time data ...
Multi-level Federated Learning for Industry 4.0 - A Crowdsourcing Approach
AbstractFederated learning is one of the emerging areas of research in computer science. It has shown great potential in some application areas and we are witnessing evidence of new approaches where millions or even billions of IoT devices can contribute ...
Industry 4.0 tools in lean production: A systematic literature review
AbstractThe present article focuses its attention on the tools of the Industry 4.0 with the purpose to analyze how these tools can be useful for the companies to increase factors like efficiency and productivity. In the age of the fourth industrial ...
Comments