Streaming big data for failure prediction in mechanical engineering

Authors: Pavlov A.M.
Published in issue: #3(56)/2021
DOI: 10.18698/2541-8009-2021-3-679
Category: Economics and Production Organization
Keywords: big data, fault prediction, predictive equipment maintenance, mechanical engineering, productivity improvement, intelligent management
Published: 23.03.2021

In today’s industrial scenario, big data processing plays a leading role in improving business efficiency - reducing equipment maintenance costs and increasing productivity. An increasing number of machine tools are equipped with intelligent devices (such as sensors and actuators) that monitor the condition of the machine in real time and take corrective action before the quality of the workpiece is reduced or the machine is damaged. However, many manufacturing companies are still not taking advantage of big data coming from manufacturing systems. In some cases, big data analytics is an unexplored problem because it is believed to take time and resources. Moreover, the real benefits of real-time industrial data processing are usually underestimated. The article focuses on the component manufacturing process, as well as a description of the main developments and lessons learned when setting up a big data analytical platform for processing and analyzing data from sensors of numerically controlled machines.

References

[1] Coleman C., Chandramouli M., Damodaran S., et al. Making maintenance smarter. deloitte.com: website. URL: https://www2.deloitte.com/us/en/insights/focus/industry-4-0/using-predictive-technologies-for-asset-maintenance.html (accessed: 15.12.2020).

[2] Vlasov A.I., Grigor’yev P.V., Krivoshein A.I. Model of predictive equipment maintenance with application of wireless touch networks. Nadezhnost’ i kachestvo slozhnykh system [Reliability & Quality of Complex Systems], 2018, no. 2, pp. 26–35. DOI: https://doi.org/10.21685/2307-4205-2018-2-4 (in Russ.).

[3] Amruthnath N., Gupta T. A research study on unsupervised machine learning algorithms for early fault detection in predictive maintenance. 5th ICIEA, 2018, pp. 355–361. DOI: https://doi.org/10.1109/IEA.2018.8387124

[4] Ermakov V.A., Korzun D.Zh. [Digital services of predictive analytics at maintenance of production equipment]. Tsifrovye tekhnologii v obrazovanii, nauke, obshchestve [Digital Technologies in Education, Science, Society], 2019, pp. 73–75 (in Russ.).

[5] Chandola V., Banerjee A., Kumar V. Anomaly detection: a survey. ACM Comput. Surv., 2009, vol. 41, no. 3, art. 15. DOI: https://doi.org/10.1145/1541880.1541882

[6] Harding J.A., Shahbaz M., Kusiak A. Data mining in manufacturing: a review. J. Manuf. Sci. Eng., 2006, vol. 128, no. 4, pp. 969–976. DOI: https://doi.org/10.1115/1.2194554

[7] Crespino A.M., Di Biccari C., Lazoi M., et al. Fault prediction in aerospace product manufacturing: a model‐based big data analytics service. In: Enterprise Interoperability. Wiley, 2018, pp. 193–200. DOI: https://doi.org/10.1002/9781119564034

[8] Wan J., Tang S., Li D., et al. A manufacturing big data solution for active preventive maintenance. IEEE Trans. Ind. Informat., 2017, vol. 13, no. 4, pp. 2039–2047. DOI: https://doi.org/10.1109/TII.2017.2670505

[9] Yu W., Dillon T., Mostafa F., et al. A global manufacturing big data ecosystem for fault detection in predictive maintenance. IEEE Trans. Ind. Informat., 2020, vol. 16, no. 1, pp. 183–192. DOI: https://doi.org/10.1109/TII.2019.2915846

[10] Ardagna C.A., Bellandi V., Ceravolo P., et al. A model-driven methodology for big data analytics-as-a-service. IEEE BigData Congress, 2017, pp. 105–112. DOI: https://doi.org/10.1109/BigDataCongress.2017.23