Design and development of a smart system for efficient engineering applications
Keywords:
Smart Systems, Deep Learning, Fault Detection, Industrial IoT, Edge Computing, Predictive Maintenance.Abstract
The blistering development of Industry 4.0 has generated an increasing need to find smart systems that can handle sophisticated engineering processes with minimal human intervention. The given paper introduces the design and development of a Smart System of Efficient Engineering Applications (SSEEA) - the combination of deep learning-based fault detection, edge computing and real-time process optimization to optimize the performance of industrial operation. SSEEA relies on a hybrid neural network consisting of spatial and temporal pattern recognition neural networks which combine Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM). This system is built to have five functional layers, including data acquisition, edge pre-processing, AI inference, decision support and visualization, with low-latency high throughput behavior on resource-constrained industrial systems. It was tested on a benchmark dataset of 48,000 labeled operational cycles in one of a chemical process plant and demonstrated in an actual manufacturing environment. The SSEEA had an accuracy of 97.3% in fault detection, a precision of 96.9% and a recall of 97.1%, which is better than the baseline classifiers such as Support Vector Machines, Random Forest and standalone neural networks. SSEEA was found to have a 65.9% lower fault detection latency, 59.6% lower energy usage and eight times the prediction horizon than traditional threshold-based monitoring systems. ANOVA and Wilcoxon signed-rank tests were used to statistically prove all gains in performance. These findings substantiate the practicability and efficiency of SSEEA to be implemented in energy-intensive and safety-reliant industrial systems and provide a scalable and intelligible addition to the industrial digitalization process towards sustainable industrial digitalization.
Downloads
References
[1] J. Lee, B. Bagheri, H.-A. Kao, 'A Cyber-Physical Systems architecture for Industry 4.0-based manufacturing systems', Manuf. Lett., vol. 3, pp. 18-23, Jan. 2015. doi.org/10.1016/j.mfglet.2014.12.001
[2] Y. Lu, 'Industry 4.0: A survey on technologies, applications and open research issues', J. Ind. Inf. Integr., vol. 6, pp. 1-10, June 2017. doi.org/10.1016/j.jii.2017.04.005
[3] T. Zhang, G. Yan, M. Ren, L. Cheng, R. Li, G. Xie, 'Dynamic transfer soft sensor for concept drift adaptation', J. Process Control, vol. 123, pp. 50-63, Mar. 2023. doi.org/10.1016/j.jprocont.2023.01.012
[4] F. Tao, H. Zhang, A. Liu, A. Y. C. Nee, 'Digital twin in industry: State-of-the-art', IEEE Trans. Industr. Inform., vol. 15, no. 4, pp. 2405-2415, Apr. 2019. doi.org/10.1109/TII.2018.2873186
[5] A. Salem, H. Hegab, S. Rahnamayan, H. A. Kishawy, 'Multi-objective optimization and innovization-based knowledge discovery of sustainable machining process', J. Manuf. Syst., vol. 64, pp. 636-647, July 2022. doi.org/10.1016/j.jmsy.2022.04.013
[6] Z. Dai, S. C. Perera, J.-J. Wang, S. K. Mangla, G. Li, 'Elective surgery scheduling under uncertainty in demand for intensive care unit and inpatient beds during epidemic outbreaks', Comput. Ind. Eng., vol. 176, no. 108893, p. 108893, Feb. 2023. doi.org/10.1016/j.cie.2022.108893
[7] Y. Lecun, L. Bottou, Y. Bengio, P. Haffner, 'Gradient-based learning applied to document recognition', Proc. IEEE Inst. Electr. Electron. Eng., vol. 86, no. 11, pp. 2278-2324, 1998. doi.org/10.1109/5.726791
[8] M. Sakurada and T. Yairi, 'Anomaly detection using autoencoders with nonlinear dimensionality reduction', in Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis, Gold Coast Australia QLD Australia, 2014. doi.org/10.1145/2689746.2689747
[9] J. Chen, H. Jing, Y. Chang, Q. Liu, 'Gated recurrent unit based recurrent neural network for remaining useful life prediction of nonlinear deterioration process', Reliab. Eng. Syst. Saf., vol. 185, pp. 372-382, May 2019. doi.org/10.1016/j.ress.2019.01.006
[10] S. Boschert and R. Rosen, 'Digital Twin-The Simulation Aspect', in Mechatronic Futures, Cham: Springer International Publishing, 2016, pp. 59-74. doi.org/10.1007/978-3-319-32156-1_5
[11] S. J. Qin, 'Survey on data-driven industrial process monitoring and diagnosis', Annu. Rev. Control, vol. 36, no. 2, pp. 220-234, Dec. 2012. doi.org/10.1016/j.arcontrol.2012.09.004
[12] B. Samanta and K. R. Al-Balushi, 'Artificial neural network based fault diagnostics of rolling element bearings using time-domain features', Mech. Syst. Signal Process., vol. 17, no. 2, pp. 317-328, Mar. 2003. doi.org/10.1006/mssp.2001.1462
[13] L. Breiman, 'Random forests', Mach. Learn., vol. 45, no. 1, pp. 5-32, Oct. 2001. doi.org/10.1023/A:1010933404324
[14] W. Zhang, G. Peng, C. Li, Y. Chen, Z. Zhang, 'A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals', Sensors (Basel), vol. 17, no. 2, p. 425, Feb. 2017. doi.org/10.3390/s17020425
[15] S. Hochreiter and J. Schmidhuber, 'Long short-term memory', Neural Comput., vol. 9, no. 8, pp. 1735-1780, Nov. 1997. doi.org/10.1162/neco.1997.9.8.1735
[16] M. Sakurada and T. Yairi, 'Anomaly detection using autoencoders with nonlinear dimensionality reduction', in Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis, Gold Coast Australia QLD Australia, 2014. doi.org/10.1145/2689746.2689747
[17] Z. Wu, H. Jiang, K. Zhao, X. Li, 'An adaptive deep transfer learning method for bearing fault diagnosis', Measurement (Lond.), vol. 151, no. 107227, p. 107227, Feb. 2020. doi.org/10.1016/j.measurement.2019.107227
[18] X. Li, W. Zhang, Q. Ding, 'Deep learning-based remaining useful life estimation of bearings using multi-scale feature extraction', Reliab. Eng. Syst. Saf., vol. 182, pp. 208-218, Feb. 2019. doi.org/10.1016/j.ress.2018.11.011
[19] A. Krizhevsky, I. Sutskever, G. E. Hinton, 'ImageNet classification with deep convolutional neural networks', Commun. ACM, vol. 60, no. 6, pp. 84-90, May 2017. doi.org/10.1145/3065386
[20] W. Shi, J. Cao, Q. Zhang, Y. Li, L. Xu, 'Edge Computing: Vision and Challenges', IEEE Internet Things J., vol. 3, no. 5, pp. 637-646, Oct. 2016. doi.org/10.1109/JIOT.2016.2579198
[21] R. Zhao, R. Yan, Z. Chen, K. Mao, P. Wang, R. X. Gao, 'Deep learning and its applications to machine health monitoring', Mech. Syst. Signal Process., vol. 115, pp. 213-237, Jan. 2019. doi.org/10.1016/j.ymssp.2018.05.050
[22] M. Wollschlaeger, T. Sauter, J. Jasperneite, 'The future of industrial communication: Automation networks in the era of the internet of things and industry 4.0', IEEE Ind. Electron. Mag., vol. 11, no. 1, pp. 17-27, Mar. 2017. doi.org/10.1109/MIE.2017.2649104
[23] L. Dai, Y. Yu, D.-H. Zhai, T. Huang, Y. Xia, 'Robust model predictive tracking control for robot manipulators with disturbances', IEEE Trans. Ind. Electron., vol. 68, no. 5, pp. 4288-4297, May 2021. doi.org/10.1109/TIE.2020.2984986
[24] P. Kairouz and H. B. McMahan, 'Advances and open problems in federated learning', Found. Trends® Mach. Learn., vol. 14, no. 1-2, pp. 1-210, June 2021. doi.org/10.1561/2200000083
[25] Z. C. Lipton, 'The Mythos of Model Interpretability', ACM Queue, vol. 16, no. 3, pp. 31-57, June 2018. doi.org/10.1145/3236386.3241340
Published
How to Cite
Issue
Section
Copyright (c) 2026 Authors
This work is licensed under a Creative Commons Attribution 4.0 International License.
