Research on the Predictive Algorithm of Wear Degree Based on Adaptive Feature Learning
Source abstract
Abstract
In the prediction and modeling analysis of wear degree in the field of industrial parts processing, there are problems such as poor prediction ability for long sequence data and low sensitivity of output feedback to changes in input signals. In this paper, a combined prediction model is proposed that integrates dual attention mechanisms and self-regressive correction. Firstly, pre-processing is performed on the collected wear data to eliminate noise and aberrant mutation data. Then, the feature attention mechanism is introduced to analyze the input data sequence, and the weights of each feature under the temporal condition are set based on the contribution of the prediction results, thereby obtaining the LSTM hidden state at the current time. Subsequently, the temporal attention mechanism is introduced to perform a weighted calculation of the hidden state information, analyze the correlation of long-term sequential wear data, and decode and output the analysis results. Finally, the ARIMA model is used to perform linear correction on the predicted results to improve the accuracy of wear degree prediction. The proposed model is compared and analyzed with the models that are highly related in recent research on real-world wear degree datasets. The experimental results show that the improved model has a better ability to improve the corresponding problems and has a significant increase in prediction accuracy.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China
Chongqing Research Institute, Changchun University of Science and Technology, Chongqing 401120, China
School of Mechanical Engineering, University of Houston, Houston, TX 77204, USA
Funding
Jilin Province Science and Technology Innovation Platform Construction Project
References (32)
Show source-provided references
1. Perspectives on Big Data Modeling of Process Industries
2. Data-driven industrial intelligence: Current status and future directions
3. Application and Practical Research of Industrial Big Data
4. Intelligent Prediction Model of Tool Wear Based on Deep Signal Processing and Stacked-ResGRU
5. Tool wear monitoring based on deep learning
6. Predicting tool wear with multi-sensor data using deep belief networks10.1007/s00170-018-2571-z ↗
7. The comparison among ARIMA and hybrid ARIMA-GARCH models in forecasting the exchange rate of Iran
8. Structural Damage Identification Based on Time Series Analysis
9. Damage Identification Based on AR Model and PCA
10. Dynamic Outlier Detection for Process Control Time Series
11. A Wind Speed Time Series Modelling Method Based on Probability Measure Transformation
12. Network Traffic Forecasting Based on Combined Model
13. Prediction on the Value Trends of Bitcoin and Gold-on Account of ARMA Time Series Forecasting Model
14. Short-term Passenger Flow Prediction for Urban Rail Transit Based on Ensemble Models
15. Condition Prediction of Reactor Coolant Pump in Nuclear Power Plants based on the Combination of ARIMA and LSTM
16. Application of ARIMA Model for Mid-and Long-term Forecasting of Ozone Concentration
17. Temporal pattern attention for multivariate time series forecasting10.1007/s10994-019-05815-0 ↗
18. Huang, Q., Huang, H., Zhang, Y., and Han, Y. (2021, January 22–24). Tool wear prediction based on multi-scale convolution attention network fusion. Proceedings of the 2021 China Automation Congress, Beijing, China.
19. Multistage attention network for multivariate time series prediction10.1016/j.neucom.2019.11.060 ↗
20. Temporal self-attention-based Conv-LSTM network for multivariate time series prediction10.1016/j.neucom.2022.06.014 ↗
21. Improving time series forecasting using LSTM and attention models10.1007/s12652-020-02761-x ↗
22. Multivariate time series forecasting via attention-based encoder–decoder framework10.1016/j.neucom.2019.12.118 ↗
23. Anomaly Detection Method of Network Traffic Based on Secondary Feature Extraction and BiLSTM-Attention
24. Aeroengine residual life prediction based on attention mechanism and CNN-BiLSTM model
25. Short-term traffic flow prediction based on spatio-temporal attention Bi-LSTM model
26. Sutskever, I., Vinyals, O., and Le, Q.V. (2014, January 8–13). Sequence to sequence learning with neural networks. Proceedings of the Advances in neural information processing systems, Montreal, QC, Canada.
27. Lai, G., Chang, W.C., Yang, Y., and Liu, H. (2018, January 8–12). Modeling long-and short-term temporal patterns with deep neural networks. Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, Ann Arbor, MI, USA.10.1145/3209978.3210006 ↗
28. Activation functions in neural networks
29. Agogino, A., and Goebel, K. (2023, February 01). Mill Data Set [EB/OL], Available online: https://ti.arc.nasa.gov/project/prognostic-data-repository.
30. Chen, M., Zeng, W., Xu, Z., and Li, J. (2018, January 21–23). Delay prediction based on deep stacked autoencoder networks. Proceedings of the Asia-Pacific Conference on Intelligent Medical 2018 & International Conference on Transportation and Traffic Engineering 2018, Beijing, China.10.1145/3321619.3321669 ↗
31. Milling Tool Wear Prediction Research Based on Optimized PCANet Model10.3901/JME.2023.01.278 ↗
32. Tool status recognition method based on sample expansion and IDANN