A Novel Deep Feature Learning Method Based on the Fused-Stacked AEs for Planetary Gear Fault Diagnosis

Xihui Chen,Gang Cheng,Aimin Ji

doi:10.3390/en12234522

Xihui Chen, Gang Cheng + Show 1 more

Open Access

https://doi.org/10.3390/en12234522

Copy DOI

Abstract

Planetary gear is the key component of the transmission system of electromechanical equipment for energy industry, and it is easy to damage, which affects the reliability and operation efficiency of electromechanical equipment of energy industry. Therefore, it is of great significance to extract the useful fault features and diagnose faults based on raw vibration signals. In this paper, a novel deep feature learning method based on the fused-stacked autoencoders (AEs) for planetary gear fault diagnosis was proposed. First, to improve the data learning ability and the robustness of feature extraction process of AE model, the sparse autoencoder (SAE) and the contractive autoencoder (CAE) were studied, respectively. Then, the quantum ant colony algorithm (QACA) was used to optimize the specific location and key parameters of SAEs and CAEs in deep learning architecture, and multiple SAEs and multiple CAEs were stacked alternately to form a novel deep learning architecture, which gave the deep learning architecture better data learning ability and robustness of feature extraction. The experimental results show that the proposed method can address the raw vibration signals of planetary gear. Compared with other deep learning architectures and shallow learning architecture, the proposed method has better diagnosis performance, and it is an effective method of deep feature learning and fault diagnosis.

Highlights

With the rapid development of science and industrial technology, the electromechanical equipment for energy industry is becoming more and more efficient, reliable, and intelligent [1]
The vibration signals of six types of planetary gear states are shown in Figure 5, and it can be seen from Figure 5 that there were no significant differences among the vibration signals in the time domain
In this paper, considering that the excellent feature extraction method should be sensitive to different faults of planetary gear, and that the robustness and adaptability of feature extraction process should be guaranteed, a novel deep feature learning method based on the fused-stacked AEs for planetary gear fault diagnosis was proposed

Summary

Introduction

With the rapid development of science and industrial technology, the electromechanical equipment for energy industry is becoming more and more efficient, reliable, and intelligent [1]. Due to the advantages of planetary gear, it has become a key component of the transmission system of electromechanical equipment for energy industry, such as the wind turbine, shearer, and so on. Planetary gear generally works in harsh working conditions with heavy load, strong interference and high pollution, so faults often occur, which directly affect the transmission efficiency and even lead to catastrophic accidents of the electromechanical equipment in the energy industry [2,3]. The planetary gear composed of sun gear, planet gears, planet carrier, and inner ring gear has a more complex structure than fixed-axis gear, which provides a special form of motion [4]. The special movement of planetary gear which causes its vibration signal is affected by the “passing effect” of planet gear and planet carrier and makes the transmission

Results

Discussion

Conclusion