The quantitative identification of broken wires is of great significance to maintain the safety of mechanical systems, such as steel wire ropes. However, in order to achieve high accuracy recognition results, a large number of fault samples are necessary, which is difficult to achieve in practical industrial detection. In this paper, a novel quantitative identification approach, based on generative adversarial nets (GANs) and a convolutional neural network (CNN), is proposed to solve the broken wire recognition problem in situations where real inspections have generated only a small sample of broken wires for analysis. One-dimensional original signals of broken wires are transformed into two-dimensional time-frequency images by continuous wavelet transform (CWT). Next, these time-frequency images are used for quantitative identification of various defects by combing GANs and CNN with limited samples. The main innovation of this paper is that the identification accuracy of broken wires can be improved by generating fault samples through GANs. The experimental results demonstrate that the proposed method achieves better recognition rates for broken wires compared with the existing detection methods.

Envelope demodulation remains the most widely used technique for diagnosing rolling bearing faults, but its performance depends on the demodulation frequency band (DFB) identified. Despite extensive developments in DFB identification approaches, their performance often degrades under severe interference conditions due to the inherent methodological limitations. To address these deficiencies, this research introduces a novel DFB identification approach called Mehpsogram. Initially, a new pyramid-structure-based multi-scale adaptive spectral segmentation method is proposed to segment the spectrum of the bearing vibration signal into discrete subbands. Subsequently, a modified envelope harmonic product spectrum (MEHPS) is presented to suppress the interference frequency components while highlighting the spectral peaks generated by the fault characteristic frequency and its harmonics in the discretized squared envelope spectrum of the filtered subband signals. Finally, the optimal DFB is determined through frequency domain signal-to-noise ratio analysis of the MEHPSs derived from the filtered subband signals. Comprehensive evaluations on simulated and real-world datasets consistently demonstrate that the proposed Mehpsogram method outperforms existing representative DFB identification methods.