Fault diagnosis is significant to guarantee the safety and reliability of the machinery. Local fault will make the collected vibration signals deviate from the normal signals. In order to extract fault-related features from vibration signals, many deep learning-based methods have been proposed for machinery fault diagnosis recently. However, due to the extreme conditions (e.g., high background noise, limited labeled training samples), it is a challenging task to implement features extraction from the collected signals with non-linear and non-stationary characteristics. To implement feature extraction and noise reduction of vibration signals, this paper proposes a novel network, i.e., deep morphological shrinkage convolutional auto-encoder (DMSCAE) for gearbox fault diagnosis considering the insufficient labeled training samples. Firstly, a morphological convolutional auto-encoder is proposed for noise filtering and feature extraction. Secondly, a multi-branch structure with different structural elements (SEs) is used in the morphological layer to extract impulsive components. Finally, a soft thresholding-based shrinkage is employed to filter ineffective features, where an adaptative method is developed to adjust the threshold automatically in the back-propagation procedure. The experiments on two gearbox fault diagnosis tests are conducted to verify the performance of DMSCAE. The results indicate that DMSCAE obtains a better performance for fault diagnosis than other DNNs, e.g., efficient channel attention network (ECANet), self-calibrated convolutional network (SCNet).
29 July 2024 in IEEE Transactions on Power Electronics
Most existing methods for battery state-of-health (SOH) estimation rely on centralized training mode. However, in practical applications, it is difficult for a single user to collect sufficient battery degradation data to train a model. In addition, in order to protect data privacy, users are unwilling to share data, where centralized training mode is not the best choice. To overcome these barriers, a source-free dynamic weighted federated transfer (SF-DWFT) method for battery SOH estimation is proposed, which utilizes a distributed learning paradigm to combine multiple source clients to train a global model while protecting data privacy. First, a Gaussian mixture model is used to model the high-level features extracted by the client model, thus the feature representation can be shared without needing access to the source data; then, in order to reduce the effect of distribution differences between the source and target clients on the global model, a dynamic weighted federated aggregation algorithm is proposed according to their contributions, which is measured by calculating the modified Bhattacharya distance between the source and target clients and testing error. Finally, the effectiveness of SF-DWFT is verified on several battery datasets and it achieves a statistic estimation error of 1.12% on 18 650 lithium-ion battery datasets and 4.46% on NASA battery dataset.
1 March 2017 in IET Generation, Transmission & Distribution
Natural disasters caused by tropical cyclones such as Typhoon, Hurricane, Tornados, etc., are bringing severe damage to modern power transmission systems throughout the world. These natural disasters each have their individual patterns at specific locations, and the current pre‐disaster analysis is performed primarily relying on simple weather forecasting results, which lacks the acknowledgment of microclimate analytics. This paper presents heuristic transmission line failure model regarding microclimate analysis, which serves as more accurate and active prediction reference for regional transmission lines. Anti‐disaster preventive activities can be thereafter designed prior to the occurrence of the disaster, and post‐disaster remedy actions can be well prepared accordingly as well to prevent severe damages. This paper provides detailed modelling of Typhoon in typical areas of China as examples, and comes up with the corresponding transmission line failure model by accounting the microclimate prediction method and historical line tripping data sets. Validation process of the model returns a passing result of the vast majority of prediction equations for trip‐out rate of transmission lines on the significant test with the confidence level of 95%, and a reasonable prediction ratio of all the transmission lines.
In real industry, local damages often appear on multiple parts of bearings simultaneously and these compound faults coupling heavily troubles those regular diagnosis methods. In this paper, an energy-constrained swarm decomposition and adaptive spectral amplitude modulation method (ECSWD-ASAM) is proposed to extract compound fault features from bearing vibration signals. Firstly, a rectangular window is convolved with the energy spectrum to generate a smooth upper envelope curve to overcome the instant noisy peaks and highlight dominant frequencies in the vibration signals. Secondly, an energy filter is constructed to concentrate the energy of each oscillating component and suppress the spectrum overlap during the signal decomposition. Thirdly, envelope correlation coefficient (ECC) is used as the evaluation criterion to constraint the over decomposition between adjacent components. Finally, a new index called kurtosis-enhanced entropy (KEE) is proposed to adaptively locate the optimal fault frequency band of the SAM results, which can enhance the weak fault features in the extracted components. ECSWD-ASAM effectively separates different fault components on simulated data, Paderborn university (PU) dataset and vibration signals of bearing-gearbox testbed. The testing results indicate that ECSWD-ASAM has better denoising and compound fault extraction performance than these representative methods, i.e., successive variational mode decomposition (SVMD), improved complete ensemble empirical mode decomposition adaptive noise (ICEEMDAN) and local mean decomposition (LMD).
14 February 2025 in IEEE Transactions on Industrial Informatics
Valve-regulated lead–acid (VRLA) battery module is one of the important components of the uninterruptible power supply system in a large Internet data center. Battery health monitoring and anomaly diagnosis in time is significant to ensure the safe operation of a data center. In this article, a multitask joint network (MTJNet) is proposed to perform anomaly diagnosis and inconsistency identification simultaneously. First, an unsupervised learning-based encoder-decoder structure is proposed in MTJNet for battery inconsistency identification, where only health data are required for training. Second, the other branch with a classifier is further constructed to recognize the anomaly of the battery module. Third, a multitask joint training method is used to update the parameters of the two task models in MTJNet. The reconstruction error obtained by inconsistency identification task is fed into the anomaly diagnosis task. The predicted pseudo labels by the anomaly diagnosis task are feedback to inconsistency identification task to guide the encoder-decoder to provide the discriminate features. Finally, the effectiveness of MTJNet is verified on VRLA battery modules in a large data center. The experimental results illustrate that MTJNet is a good tool for anomaly diagnosis and inconsistency identification of VRLA battery modules.