Research on Anomaly Detection Method of Non-Standard Machinery Production Process Based on Semi-Supervised Learning

Xinghui Zhu

¹ School of Computer Science, Xidian University, Xi’an, Shaanxi, 710162, China

² Information Science and Technology (BNRist), Department of Automation, Tsinghua University, Beijing 100084, China

*Corresponding author

The non-standard machinery refers to customized machinery produced to meet specific customer demands. The mainstream research direction in data stream anomaly detection focuses on deep learning, which involves learning data distribution through a large amount of training data. However, non-standard machinery equipment has the characteristics of a small production scale and sparse samples, making it difficult to obtain sufficient annotated training sets. This inadequacy in training data results in the model not learning enough, thereby rendering it unable to effectively detect abnormal events. In this paper, we propose a semi-supervised learning (SSL) based anomaly detection method. We employ a hybrid C-LSTM network based on the self-attention mechanism as an abnormality prediction model, where the convolutional neural network (CNN) and long short-term memory network (LSTM) extract spatiotemporal features of industrial data streams. The self-attention mechanism calculates the relationship weights between different positions in the input data, capturing long-term dependencies in time series data to fully learn data distribution. To improve the training effectiveness of the prediction model, we use an updating algorithm based on weighted fuzzy rough set (WFDA) to update the prediction model in a reverse manner. This algorithm can classify data streams in real-time, compare the classification results of the prediction model, and retrain unreliable data. The experimental results show that our proposed method achieves an F1 score of 0.955 and a recall value of 0.957 on a real-world data set, which is a 4.1% improvement in F1 score and a 6.4%improvement in recall compared to similar anomaly detection algorithms that do not use our proposed method.

Non-standard achinery anomaly detection, Semi-supervised learning, Fuzzy-rough-set, CNN, LSTM

Longlong Lv, Helong Qiu, Huihui Wu, Jun Dou, Qiang Cao, Qiyuan Zhang, Wenchao Zhao, and Xinghui Zhu (2023). Research on Anomaly Detection Method of Non-Standard Machinery Production Process Based on Semi-Supervised Learning. Journal of Networking and Network Applications, Volume 3, Issue 2, pp. 81–88. https://doi.org/10.33969/J-NaNA.2023.030204.

[1] Sisinni E, Saifullah A, Han S, et al. Industrial internet of things: Chal-lenges, opportunities, and directions[J]. IEEE transactions on industrial informatics, 2018, 14(11): 4724-4734.

[2] Malik P K, Sharma R, Singh R, et al. Industrial Internet of Things and its applications in industry 4.0: State of the art[J]. Computer Communi-cations, 2021, 166: 125-139.

[3] Li G, Fu Y, Chen D, et al. Deep anomaly detection for CNC machine cutting tool using spindle current signals[J]. Sensors, 2020, 20(17): 4896.

[4] Chen W. Intelligent manufacturing production line data monitoring system for industrial internet of things[J]. Computer communications, 2020, 151: 31- 41.

[5] Liu Y, Tong K D, Mao F, et al. Research on digital production technology for traditional manufacturing enterprises based on industrial Internet of Things in 5G era[J]. The International Journal of Advanced Manufactur-ing Technology, 2020, 107: 1101-1114.

[6] Sain S R. The nature of statistical learning theory[J]. 1996.

[7] Breiman L. Random forests[J]. Machine learning, 2001, 45: 5-32.

[8] Shahzad S, Ilyas M, Lali M, et al. Sperm Abnormality Detection Using Sequential Deep Neural Network[J]. Mathematics, 2023, 11(3): 515.

[9] Zhang Q. Financial data anomaly detection method based on decision tree and random forest algorithm[J]. Journal of Mathematics, 2022, 2022.

[10] Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors[J]. nature, 1986, 323(6088): 533-536.

[11] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural com-putation, 1997, 9(8): 1735-1780.

[12] Greff K, Srivastava R K, Koutn´ık J, et al. LSTM: A search space odyssey[J]. IEEE transactions on neural networks and learning systems, 2016, 28(10): 2222-2232.

[13] Wang Z, Liu N, Chen C, et al. Adaptive self-attention LSTM for RUL prediction of lithium-ion batteries[J]. Information Sciences, 2023.

[14] Glielmo A, Husic B E, Rodriguez A, et al. Unsupervised learning methods for molecular simulation data[J]. Chemical Reviews, 2021, 121(16): 9722-9758.

[15] Verma V, Kawaguchi K, Lamb A, et al. Interpolation consistency training for semi-supervised learning[J]. Neural Networks, 2022, 145: 90-106.

[16] Yuan Z, Chen B, Liu J, et al. Anomaly detection based on weighted fuzzy-rough density[J]. Applied Soft Computing, 2023: 109995.

[17] Glas A S, Lijmer J G, Prins M H, et al. The diagnostic odds ratio: a single indicator of test performance[J]. Journal of clinical epidemiology, 2003, 56(11): 1129-1135.

[18] Yacouby R, Axman D. Probabilistic extension of precision, recall, and f1 score for more thorough evaluation of classification mod-els[C]//Proceedings of the first workshop on evaluation and comparison of NLP systems. 2020: 79-91.