A CNN-Regression-Based Contact Erosion Measurement Method for AC Contactors

Abstract

This paper proposes a method that indirectly measures the contact erosion of alternating current (AC) contactors via mapping electrical signals to the contacting alloy erosion condition which is represented by the accumulated contact mass loss (ACML). Electrical signal waveforms and their corresponding ACMLs of every make-and-break operation are acquired in endurance tests. A supervised convolutional neural network regression (CNNR) architecture containing six onedimensional convolution layers is proposed to model the relation between waveforms and ACMLs. We compare different CNNR architectures as well as different training schemes by the test precision to obtain the optimal solution. Experiments prove that the proposed CNNR architecture with an optimized training scheme can achieve a precise ACML measurement when only voltage waveforms of make operations are used. The best results reach mean absolute errors of 3.29% and 1.59% corresponding to two datasets respectively, which are superior to the results of other regression methods in the comparison and prove the theoretical significance and applicational values.

Remaining electrical life prediction of AC contactor based on CAE-BiGRU-Attention

“…In the literature [12], the audio signals of AC contactors in three abnormal states were selected as features to develop a neural network prediction model for predicting the remaining electrical life. In the literature [13], the contact electrical signals and contact cumulative mass loss of the AC contactor were collected, and a method based on CNN regression was proposed to predict the erosion state of the contact effectively. In the literature [14], an long shortterm memory (LSTM) model was built to predict the remaining electrical life of AC contactors based on the correlation before and after degradation data of AC contactors.…”

Data-driven condition monitoring of stator winding terminal insulation for inverter-fed machine using enhanced switching oscillation signals

“…Nowadays, machine learning methods, especially deep learning methods, have made a series of breakthroughs in fault diagnosis [18,19] and nonlinear regression [20,21,22]. Deep learning methods have a strong ability to extract complex and abstract features without any physical models [23].…”