The mechanical fault model of 10 kV circuit breakers based on voiceprint features is susceptible to environmental noise, resulting in low recognition accuracy and long recognition time. This article proposes a multi-feature hybrid voiceprint diagnosis method for mechanical faults of 10 kV circuit breakers based on improved FastICA and Bi-LSTM. Firstly, the FastICA algorithm is improved by using Pearson coefficients. The collected sound is separated by noise using the improved FastICA algorithm, and pure 10 kV circuit breaker state voiceprint signals are extracted. Then, the Fourier transform is used to analyze the frequency domain information of the 10 kV circuit breaker in various states. Based on the analysis results, appropriate time-domain, frequency-domain, and acoustic features are selected, and through difference analysis, features with high contribution are selected to form one-dimensional mixed features. Finally, using mixed features as diagnostic criteria, a fault classification model based on Bi-LSTM is established. The results indicate that this method can effectively identify eight common mechanical faults in 10 kV circuit breakers. The recognition accuracy can reach 99.3%, meeting the accuracy and speed requirements of the power grid for electrical equipment fault diagnosis.
WANGJunbo, LIGuowei, HEShenghong, et al. Wiring location error analysis and dynamic compensation for 10 kV high voltage circuit breaker electrical experiment robot[J]. High Voltage Engineering, 2021, 47(10): 3642-3649. (in Chinese)
ZHANGXun, HUANGJunkai, ZHAOChao, et al. High voltage circuit breaker mechanical fault diagnosis technology based on KPCA-SVM[J]. Journal of Test and Measurement Technology, 2023, 37(2): 158-164. (in Chinese)
DOULongjiang, HEYuling, WANShuting, et al. Detecting method of high voltage circuit breaker spring fatigue based on vibration signal[J]. Transactions of China Electrotechnical Society, 2022, 37(24): 6420-6430. (in Chinese)
CHENJin, XINGZhanli, ZHANGLing, et al. Design of fault diagnosis system for power transmission and transformation equipment based on PMS[J]. Journal of Test and Measurement Technology, 2022, 36(5): 449-454. (in Chinese)
LIUXiaojing, CHENXianda, CAOShuai, et al. Visual operation and inspection technology for overhead power line faults based on sparse data features [J]. Journal of Test and Measurement Technology, 2023, 37(2): 135-139. (in Chinese)
CUIJiajia, MAHongzhong. A voiceprint recognition model for transformer iron core loosening fault based on improved MFCC and 3D-CNN [J] Journal of Motor and Control, 2022, 26(12): 150-160. (in Chinese)
LIUYunpeng, WANGBowen, HANShuai, et al. Fast resolution method of OLTC action acoustic signal based on mixed cepstrum coefficient and CNN[J]. Journal of Vibration and Shock, 2022, 41(21): 45-52. (in Chinese)
BAOWeichuan, SUHao, LILu, et al. Fault diagnosis method of operating mechanism for high voltage circuit breaker based on combined analysis of current and vibration signals[J]. High Voltage Apparatus, 2023, 59(8): 164-172. (in Chinese)
CAOYupeng, LUOLin, WANGQiao, et al. Fault diagnosis of high-voltage vacuum circuit breaker with a convolutional deep network[J]. Power System Protection and Control, 2021, 49(3): 39-47. (in Chinese)
ZHOUJing, LUORicheng, HUANGJun. White noise suppression method of partial discharge ultrasonic signal of transformer based on improved wavelet threshold-CEEMDAN[J]. High Voltage Apparatus, 2024, 60(1): 163-171. (in Chinese)
LIMuzi, YIYongli. Common faults and maintenance of spring operating mechanism of VS1 circuit breaker[J]. Electric Explosion Protection, 2023(1): 26-29. (in Chinese)
GAOBaoming, SUNGuofan, FENGJunjie, et al. Speech recognition method of sound spectrum feature for intelligent operation and maintenance of substations[J]. High Voltage Apparatus, 2023, 59(11): 40-47. (in Chinese)
LIUPeng, QIAOXiaoyan. EEG emotion recognition based on deep auto-encoder and LSTM[J]. Journal of Test and Measurement Technology, 2022, 36(2): 129-134. (in Chinese)