A cylinder block dynamic characteristics-based data augmentation method for wear state identification under data imbalance condition

Abstract

The deterioration of the wear state in the key friction pairs will degenerate the performance of the axial piston pump. The wear rates differ under different wear states in practical applications. Therefore, the amount of monitoring data is significantly different under different wear states, which causes data imbalance problem. In addition, the distribution characteristics of the external signals are often drowned by environmental noise. To address these issues, a novel cylinder block dynamic characteristics-based data augmentation method is presented for wear state identification. Firstly, a cylinder block’s dynamic characteristics state perception method is proposed to obtain the time domain data. Then, to reduce the computing costs, the raw data is fused into multi-channel time–frequency domain data by the short-time Fourier transform (STFT) based method. Finally, the minority time–frequency data is augmented by the designed deep convolutional generative adversarial network (DCGAN). To verify the wear state identification performance of the proposed method, a convolutional neural network (CNN) is designed. Wear states injection experiments are adopted to verify the feasibility of the proposed method. The advantage of the developed method is that it obtains prominent data distribution characteristics from internal signals to enhance the performance of the data augmentation process.