A Review on AI for Smart Manufacturing: Deep Learning Challenges and Solutions
Source abstract
Abstract
Artificial intelligence (AI) has been successfully applied in industry for decades, ranging from the emergence of expert systems in the 1960s to the wide popularity of deep learning today. In particular, inexpensive computing and storage infrastructures have moved data-driven AI methods into the spotlight to aid the increasingly complex manufacturing processes. Despite the recent proverbial hype, however, there still exist non-negligible challenges when applying AI to smart manufacturing applications. As far as we know, there exists no work in the literature that summarizes and reviews the related works for these challenges. This paper provides an executive summary on AI techniques for non-experts with a focus on deep learning and then discusses the open issues around data quality, data secrecy, and AI safety that are significant for fully automated industrial AI systems. For each challenge, we present the state-of-the-art techniques that provide promising building blocks for holistic industrial AI solutions and the respective industrial use cases from several domains in order to better provide a concrete view of these techniques. All the examples we reviewed were published in the recent ten years. We hope this paper can provide the readers with a reference for further studying the related problems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Anomaly Detection Techniques and Applications · Adversarial Robustness in Machine Learning
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Applied Network Technology Lab, Huawei Technologies Duesseldorf GmbH, Riesstrasse 25, 80992 Munich, Germany
Fraunhofer Institute for Open Communication Systems, Kaiserin-Augusta-Allee 31, 10589 Berlin, Germany
Laboratory of Process Automation System, TU Dortmund University, Emil-Figge-Strasse 70, 44227 Dortmund, Germany
References (100+)
Show source-provided references
1. Mastering the Game of Go with Deep neural Networks and Tree Search10.1038/nature16961 ↗
2. Google (2022, July 18). Cloud Vision API. Available online: https://cloud.google.com/vision.
3. Research, D. (2020). AI Enablement on the Way to Smart Manufacturing: Deloitte Survey on AI Adoption in Manufacturing, Deloitte. Technical Report.
4. Ellström, M., Erwin, T., Ringland, K., and Lulla, S. (2020). AI in European Manufacturing Industries 2020, Microsoft. Technical Report.
5. A Generic Semi-Supervised Deep Learning-Based Approach for Automated Surface Inspection10.1109/ACCESS.2020.3003588 ↗
6. Surface Defect Classification of Steels with a New Semi-Supervised Learning Method10.1016/j.optlaseng.2019.01.011 ↗
7. Zhao, R., Yan, R., Wang, J., and Mao, K. (2017). Learning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks. Sensors, 17.10.3390/s17020273 ↗
8. Yoon, A.S., Lee, T., Lim, Y., Jung, D., Kang, P., Kim, D., Park, K., and Choi, Y. (2017). Semi-Supervised Learning with Deep Generative Models for Asset Failure Prediction. arXiv.
9. Mittel, D., and Kerber, F. (2019, January 10–13). Vision-Based Crack Detection using Transfer Learning in Metal Forming Processes. Proceedings of the 24th International Conference on Emerging Technologies and Factory Automation (ETFA’19), Zaragoza, Spain.10.1109/ETFA.2019.8869084 ↗
10. Convolutional Neural Networks and Transfer Learning for Quality Inspection of Different Sugarcane Varieties
11. A Semi-Supervised and Incremental Modeling Framework for Wafer Map Classification10.1109/TSM.2020.2964581 ↗
12. Imoto, K., Nakai, T., Ike, T., Haruki, K., and Sato, Y. (2018, January 10–11). A CNN-Based Transfer Learning Method for Defect Classification in Semiconductor Manufacturing. Proceedings of the International Symposium on Semiconductor Manufacturing (ISSM’18), Tokyo, Japan.10.1109/ISSM.2018.8651174 ↗
13. Enhancing Incremental Deep Learning for FCCU End-Point Quality Prediction10.1016/j.ins.2020.04.013 ↗
14. A Robust Data-Driven Approach for Online Learning and Manipulation of Unmodeled 3-D Heterogeneous Compliant Objects10.1109/LRA.2018.2863376 ↗
15. Bynum, J. (2020). A Semi-Supervised Machine Learning Approach for Acoustic Monitoring of Robotic Manufacturing Facilities. [Ph.D. Dissertation, George Mason University].
16. Mrazovic, P., Larriba-Pey, J.L., and Matskin, M. (2018, January 23–27). A Deep Learning Approach for Estimating Inventory Rebalancing Demand in Bicycle Sharing Systems. Proceedings of the 42nd Annual Computer Software and Applications Conference (COMPSAC’18), Tokyo, Japan.10.1109/COMPSAC.2018.10213 ↗
17. A Supervised Machine Learning Approach to Data-Driven Simulation of Resilient Supplier Selection in Digital Manufacturing10.1016/j.ijinfomgt.2019.03.004 ↗
18. Integrated Production Inventory Routing Planning for Intelligent Food Logistics Systems10.1109/TITS.2018.2835145 ↗
19. Woschank, M., Rauch, E., and Zsifkovits, H. (2020). A Review of Further Directions for Artificial Intelligence, Machine Learning, and Deep Learning in Smart Logistics. Sustainability, 12.10.3390/su12093760 ↗
20. Ran, Y., Zhou, X., Lin, P., Wen, Y., and Deng, R. (2019). A Survey of Predictive Maintenance: Systems, Purposes and Approaches. arXiv.
21. Large-scale Machine Learning Systems in Real-World Industrial Settings: A Review of Challenges and Solutions10.1016/j.infsof.2020.106368 ↗
22. Deep Learning in Industry 4.0—Brief Overview10.24867/JPE-2018-02-001 ↗
23. Deep Learning for Smart Manufacturing: Methods and Applications10.1016/j.jmsy.2018.01.003 ↗
24. Data Analytics and Machine Learning for Smart Process Manufacturing: Recent Advances and Perspectives in the Big Data Era10.1016/j.eng.2019.01.019 ↗
25. Machine Learning for Industrial Applications: A Comprehensive Literature Review10.1016/j.eswa.2021.114820 ↗
26. Machine Learning and Data Mining in Manufacturing10.1016/j.eswa.2020.114060 ↗
27. A Survey of the Advancing Use and Development of Machine Learning in Smart Manufacturing10.1016/j.jmsy.2018.02.004 ↗
28. Smart Machining Process using Machine Learning: A Review and Perspective on Machining Industry10.1007/s40684-018-0057-y ↗
29. Çınar, Z.M., Abdussalam Nuhu, A., Zeeshan, Q., Korhan, O., Asmael, M., and Safaei, B. (2020). Machine Learning in Predictive Maintenance towards Sustainable Smart Manufacturing in Industry 4.0. Sustainability, 12.10.3390/su12198211 ↗
30. A Review on Deep Learning in Machining and Tool Monitoring: Methods, Opportunities, and Challenges10.1007/s00170-021-07325-7 ↗
31. A Review of Machine Learning for the Optimization of Production Processes10.1007/s00170-019-03988-5 ↗
32. Machine learning in additive manufacturing: State-of-the-art and perspectives
33. Yang, J., Li, S., Wang, Z., Dong, H., Wang, J., and Tang, S. (2020). Using Deep Learning to Detect Defects in Manufacturing: A Comprehensive Survey and Current Challenges. Materials, 13.10.3390/ma13245755 ↗
34. Machine Learning and Deep Learning in Smart Manufacturing: The Smart Grid Paradigm10.1016/j.cosrev.2020.100341 ↗
35. Deep Learning for Edge Computing Applications: A State-of-the-art Survey10.1109/ACCESS.2020.2982411 ↗
36. A Survey on Deep Learning Empowered IoT Applications10.1109/ACCESS.2019.2958962 ↗
37. Ng, A. (2021, August 08). Machine Learning. Available online: https://www.coursera.org/learn/machine-learning.
38. Nwankpa, C., Ijomah, W., Gachagan, A., and Marshall, S. (2018). Activation Functions: Comparison of Trends in Practice and Research for Deep Learning. arXiv.
39. Approximation Capability in C (R/sup n/) by Multilayer Feedforward Networks and Related Problems10.1109/72.363453 ↗
40. Deng, L. (2014). A Tutorial Survey of Architectures, Algorithms, and Applications for Deep Learning. APSIPA Trans. Signal Inf. Process., 3.10.1017/atsip.2013.9 ↗
41. Bengio, Y. (2009). Learning Deep Architectures for AI, Now Publishers Inc.10.1561/9781601982957 ↗
42. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2013, January 5–10). Imagenet Classification with Deep Convolutional Neural Networks. Proceedings of the 26th Annual Conference on Neural Information Processing Systems (NIPS’12), Lake Tahoe, NV, USA.
43. Lipton, Z.C., Berkowitz, J., and Elkan, C. A Critical Review of Recurrent Neural Networks for Sequence Learning. arXiv, 2015.
44. Nanduri, A., and Sherry, L. (2016, January 26–30). Anomaly Detection in Aircraft Data using Recurrent Neural Networks (RNN). Proceedings of the 12th International Conference on Networking and Services (ICNS’16), Lisbon, Portugal.10.1109/ICNSURV.2016.7486356 ↗
45. Kingma, D.P., and Welling, M. (2013, January 2–4). Auto-Encoding Variational Bayes. Proceedings of the 1st International Conference on Learning Representations (ICLR’13), Scottsdale, AZ, USA.
46. Dzmitry, B., Kyunghyun, C., and Yoshua, B. (2015, January 7–9). Neural Machine Translation by Jointly Learning to Align and Translate. Proceedings of the 3rd International Conference on Learning Representations (ICLR’15), San Diego, CA, USA.
47. Clothing Sale Forecasting by a Composite GRU–Prophet Model With an Attention Mechanism10.1109/TII.2021.3057922 ↗
48. Temporal Convolutional Network with Soft Thresholding and Attention Mechanism for Machinery Prognostics10.1016/j.jmsy.2021.07.008 ↗
49. van Veen, F. (2021, August 10). The Neural Network Zoo. Available online: https://www.asimovinstitute.org/neural-network-zoo/.
50. Kadar, M., and Onita, D. (2019, January 27–29). A deep CNN for image analytics in automated manufacturing process control. Proceedings of the 2019 11th International Conference on Electronics, Computers and Artificial Intelligence (ECAI’19), Pitesti, Romania.10.1109/ECAI46879.2019.9042159 ↗
51. CNN-based reference comparison method for classifying bare PCB defects
52. Curreri, F., Patanè, L., and Xibilia, M.G. (2021). RNN-and LSTM-based soft sensors transferability for an industrial process. Sensors, 21.10.3390/s21030823 ↗
53. Obstacle avoidance and tracking control of redundant robotic manipulator: An RNN-based metaheuristic approach10.1109/TII.2019.2941916 ↗
54. Forecasting and Anomaly Detection approaches using LSTM and LSTM Autoencoder techniques with the applications in supply chain management10.1016/j.ijinfomgt.2020.102282 ↗
55. Yun, H., Kim, H., Jeong, Y.H., and Jun, M.B. (2021). Autoencoder-based anomaly detection of industrial robot arm using stethoscope based internal sound sensor. J. Intell. Manuf., 1–18.10.1007/s10845-021-01862-4 ↗
56. Autoencoder-based anomaly detection for surface defect inspection10.1016/j.aei.2021.101272 ↗
57. A novel predictive maintenance method based on deep adversarial learning in the intelligent manufacturing system10.1109/ACCESS.2021.3069256 ↗
58. Graph neural networks for anomaly detection in industrial internet of things10.1109/JIOT.2021.3094295 ↗
59. Anomaly detection in milling tools using acoustic signals and generative adversarial networks10.1016/j.promfg.2020.05.059 ↗
60. A novel transformer-based neural network model for tool wear estimation10.1088/1361-6501/ab7282 ↗
61. A Survey on Image Data Augmentation for Deep Learning10.1186/s40537-019-0197-0 ↗
62. Arcidiacono, C.S. (2021, August 10). An Empirical Study on Synthetic Image Generation Techniques for Object Detectors. Available online: http://www.diva-portal.se/smash/get/diva2:1251485/FULLTEXT01.pdf.
63. Lessmeier, C., Kimotho, J., Zimmer, D., and Sextro, W. (2021, August 10). Condition Monitoring of Bearing Damage in Electromechanical Drive Systems by Using Motor Current Signals of Electric Motors: A Benchmark Data Set for Data-Driven Classification. Available online: https://mb.uni-paderborn.de/en/kat/main-research/datacenter/bearing-datacenter/data-sets-and-download/.
64. Cui, W., Zhang, Y., Zhang, X., Li, L., and Liou, F. (2020). Metal Additive Manufacturing Parts Inspection Using Convolutional Neural Network. Appl. Sci., 10.10.3390/app10020545 ↗
65. Gao, J., Song, X., Wen, Q., Wang, P., Sun, L., and Xu, H. (2020). RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks. arXiv.
66. Data Augmentation in Fault Diagnosis based on the Wasserstein Generative Adversarial Network with Gradient Penalty10.1016/j.neucom.2018.10.109 ↗
67. Bird, J.J., Faria, D.R., Ekárt, A., and Ayrosa, P.P. (2020, January 28–30). From Simulation to Reality: CNN Transfer Learning for Scene Classification. Proceedings of the 10th International Conference on Intelligent Systems (IS’18), Varna, Bulgaria.10.1109/IS48319.2020.9199968 ↗
68. Semi-Supervised Learning10.1109/TNN.2009.2015974 ↗
69. Lee, D.H. (2013, January 16–21). Pseudo-label: The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks. Proceedings of the Workshop on Challenges in Representation Learning, ICML 2013, Atlanta, GA, USA.
70. Rajani, C., Klami, A., Salmi, A., Rauhala, T., Hæggström, E., and Myllymäki, P. (2018, January 17–20). Detecting Industrial Fouling by Monotonicity During Ultrasonic Cleaning. Proceedings of the International Workshop on Machine Learning for Signal Processing (MLSP’18), Aalborg, Denmark.10.1109/MLSP.2018.8517080 ↗
71. Kingma, D.P., Mohamed, S., Rezende, D.J., and Welling, M. (2014, January 8–13). Semi-Supervised Learning with Deep Generative Models. Proceedings of the Advances in Neural Information Processing Systems (NIPS’14), Montréal, QC, Canada.
72. Zhang, S., Ye, F., Wang, B., and Habetler, T.G. (2019). Semi-Supervised Learning of Bearing Anomaly Detection via Deep Variational Autoencoders. arXiv.
73. Yang, Z., Cohen, W., and Salakhudinov, R. (2016, January 19–24). Revisiting Semi-Supervised Learning with Graph Embeddings. Proceedings of the International Conference on Machine Learning (ICML’16), New York, NY, USA.
74. Energy Consumption Modelling using Deep Learning Embedded Semi-Supervised Learning10.1016/j.cie.2019.06.052 ↗
75. Jospin, L.V., Buntine, W.L., Boussaid, F., Laga, H., and Bennamoun, M. (2018). Hands-on Bayesian Neural Networks—A Tutorial for Deep Learning Users. arXiv.
76. Houlsby, N., Huszár, F., Ghahramani, Z., and Lengyel, M. (2018). Bayesian active learning for classification and preference learning. arXiv.
77. Kirsch, A., Van Amersfoort, J., and Gal, Y. (2019, January 8–14). Batchbald: Efficient and diverse batch acquisition for deep bayesian active learning. Proceedings of the 33rd Conference Neural Information Processing Systems (NIPS’19), Vancouver, BC, Canada.
78. Martínez-Arellano, G., and Ratchev, S. (2019, January 11–14). Towards An Active Learning Approach To Tool Condition Monitoring With Bayesian Deep Learning. Proceedings of the ECMS 2019, Caserta, Italy.10.7148/2019-0223 ↗
79. Geifman, Y., and El-Yaniv, R. (2017). Deep Active Learning over the Long Tail. arXiv.
80. Sener, O., and Savarese, S. (2018, January 13–16). Active Learning for Convolutional Neural Networks: A Core-Set Approach. Proceedings of the International Conference Neural Information Processing Systems (ICLR’18), Siem Reap, Cambodia.
81. An Active Learning Method based on Uncertainty and Complexity for Gearbox Fault Diagnosis10.1109/ACCESS.2019.2890979 ↗
82. Xu, Z., Liu, J., Luo, X., and Zhang, T. (2018, January 20–23). Cross-Version Defect Prediction via Hybrid Active Learning with Kernel Principal Component Analysis. Proceedings of the 25th International Conference on Software Analysis, Evolution and Reengineering (SANER’18), Campobasso, Italy.10.1109/SANER.2018.8330210 ↗
83. A Survey on Transfer Learning10.1109/TKDE.2009.191 ↗
84. Perdana, R.S., and Ishida, Y. (2019, January 27–28). Instance-Based Deep Transfer Learning on Cross-domain Image Captioning. Proceedings of the International Electronics Symposium (IES’2019), Surabaya, Indonesia.10.1109/ELECSYM.2019.8901660 ↗
85. Wang, B., Qiu, M., Wang, X., Li, Y., Gong, Y., Zeng, X., Huang, J., Zheng, B., Cai, D., and Zhou, J. (2019, January 4–8). A Minmax Game for Instance-based Selective Transfer Learning. Proceedings of the 25th International Conference on Knowledge Discovery and Data Mining (KDD’19), Anchorage, AK, USA.10.1145/3292500.3330841 ↗
86. Instance-based Ensemble Deep Transfer Learning Network: A New Intelligent Degradation Recognition Method and Its Application on Ball Screw10.1016/j.ymssp.2020.106681 ↗
87. Long, M., and Wang, J. (2017, January 4–9). Learning Multiple Tasks with Deep Relationship Networks. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS’17), Long Beach, CA, USA.
88. A New Deep Transfer Learning Method for Bearing Fault Diagnosis under Different Working Conditions10.1109/JSEN.2019.2936932 ↗
89. Kim, S., Kim, W., Noh, Y.K., and Park, F.C. (2017, January 14–19). Transfer Learning for Automated Optical Inspection. Proceedings of the International Joint Conference on Neural Networks (IJCNN’17), Anchorage, AK, USA.10.1109/IJCNN.2017.7966162 ↗
90. Krizhevsky, A. (2021, September 20). Learning Multiple Layers of Features from Tiny Images. Available online: https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf.
91. Weiaicunzai (2021, September 20). Awesome—Image Classification. Available online: https://github.com/weiaicunzai/awesome-image-classification.
92. Continual Lifelong Learning with Neural Networks: A Review10.1016/j.neunet.2019.01.012 ↗
93. Zenke, F., Poole, B., and Ganguli, S. (2017, January 6–11). Continual Learning through Synaptic Intelligence. Proceedings of the 34th International Conference on Machine Learning (ICML’17), Sydney, Australia.
94. Learning without Forgetting10.1109/TPAMI.2017.2773081 ↗
95. Li, D., Tasci, S., Ghosh, S., Zhu, J., Zhang, J., and Heck, L. (2019, January 7–9). RILOD: Near Real-Time Incremental Learning for Object Detection at the Edge. Proceedings of the 4th Symposium on Edge Computing (SEC’19), Arlington, VA, USA.10.1145/3318216.3363317 ↗
96. De Lange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., and Tuytelaars, T. (2019). Continual Learning: A Comparative Study on How to Defy Forgetting in Classification Tasks. arXiv.
97. Lopez-Paz, D., and Ranzato, M. (2017, January 4–9). Gradient Episodic Memory for Continual Learning. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS’17), Long Beach, CA, USA.
98. Shin, H., Lee, J.K., Kim, J., and Kim, J. (2017, January 4–9). Continual Learning with Deep Generative Replay. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS’17), Long Beach, CA, USA.
99. Wiewel, F., and Yang, B. (2019, January 12–17). Continual Learning for Anomaly Detection with Variational Autoencoder. Proceedings of the 44th International Conference on Acoustics, Speech and Signal Processing (ICASSP’19), Brighton, UK.10.1109/ICASSP.2019.8682702 ↗
100. Mallya, A., and Lazebnik, S. (2018, January 18–22). Packnet: Adding Multiple Tasks to A Single Network by Iterative Pruning. Proceedings of the 34th Conference on Computer Vision and Pattern Recognition (CVPR’18), Salt Lake City, UT, USA.10.1109/CVPR.2018.00810 ↗