Optimized DTW-Resnet for Fault Diagnosis by Data Augmentation Toward Unequal Length Time Series
- 25 September 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-11
Abstract
In this paper, a fault diagnosis method based on data augmentation technology is proposed to investigate the unequal length series by combining Dynamic Time Warping (DTW) with Deep Residual Network (Resnet) for excavator, where the hydraulic and power units are operated in a hybrid manner. A data augmentation method is designed to segment time series with unequal length by enhancing appropriate statistical features based on the working characteristics of excavators. Based on instantaneous calculation, an optimized DTW algorithm is proposed to reduce the calculation cost and ensure the effectiveness of the searched optimal warping path. In order to achieve fault diagnosis in industrial applications, a DTW-Resnet model combining optimized DTW algorithm with Resnet model is proposed, which overcomes the disadvantage of neural networks being unable to learn time series with unequal length easily. Results with respect to SANY excavator datasets and four publicly available datasets have well indicated that the proposed method is provided with preferable diagnostic performance compared with state-of-the-art neural networks and traditional models. Furthermore, the ablative experiment shows that the data augmentation and optimized DTW are of great significance to improve the classification accuracy of the model.Keywords
Funding Information
- National Nature Science Foundation of China (62373128)
- Natural Science Foundation of Heilongjiang Province of China (LH2021F025)
This publication has 30 references indexed in Scilit:
- ROCKET: exceptionally fast and accurate time series classification using random convolutional kernelsData Mining and Knowledge Discovery, 2020
- Multiscale cascading deep belief network for fault identification of rotating machinery under various working conditionsKnowledge-Based Systems, 2020
- RNN-Based Path Prediction of Obstacle Vehicles With Deep EnsembleIEEE Transactions on Vehicular Technology, 2019
- RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time SeriesProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Unsupervised Person Re-Identification by Deep Asymmetric Metric EmbeddingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Series AC Arc Fault Detection Method Based on Hybrid Time and Frequency Analysis and Fully Connected Neural NetworkIEEE Transactions on Industrial Informatics, 2018
- Bearing vibration data collected under time-varying rotational speed conditionsData in Brief, 2018
- Comparative study of conventional time series matching techniques for word spottingPattern Recognition, 2018
- Deep Residual Learning for Image Recognition2016
- Efficient word image retrieval using fast DTW distance2015