The intelligent diagnosis of wheel flat based on vibration image classification is a promising research subject for performance maintenance of railway vehicles. However, the image representation method of vibration signal and classification network construction under small samples have become two obstacles to intelligent diagnosis of wheel flat. This paper presents a novel frequency-domain Gramian angular field (FDGAF) algorithm to encode the vibration signal of wheel flat to featured images. Furthermore, a modified transfer learning network is introduced to classify these featured images under small samples without any involvement of prior knowledge. The proposed FDGAF can calculate the Gramian angular matrix of axle box acceleration signal in frequency domain and assign frequency position dependence to the featured images to preserve original characteristic information. Then, these featured images can be intelligent classified by a transfer learning network under the condition of 30 sample without require of prior knowledge. To verify the efficiency of this proposed method, 12 cases of artificial wheel flats are processed on a scaled railway test rig, and their axle box acceleration signals are collected to obtain visual diagnosis results. The verfication proves that FDGAF is able to obtain accurate diagnostic results with high separability, for separability indexes of FDGAF reaches 10.8, 8.7, 14.9, and 5.8. We anticipate that this method will find use in the performance maintenance of railway vehicles and the improvement of industrial condition monitoring. INDEX TERMS Intelligent transportation system, fault diagnosis, railway safety, wheels, frequency domain analysis, knowledge transfer.

No abstract

The application of the multi-scale intrinsic mode function permutation entropy and extreme learning machine classifiers in railway rolling bearing fault diagnosis is here proposed in this article. The original signal is first denoised using wavelet de-noising as a pre-filter, which improves the subsequent decomposition into a number of intrinsic mode functions using ensemble empirical mode decompose. Second, the multi-scale intrinsic mode function permutation entropy is extracted as feature parameters. Finally, the extracted features are entered into extreme learning machine for an automated fault diagnosis procedure. Case studies have been carried out to evaluate the validity of the approach. The results demonstrate its effectiveness for diagnosis of faults in railway rolling bearings.

No abstract