Application of Rotating Machinery Fault Diagnosis Based on Deep Learning

Abstract

With the continuous progress of modern industry, rotating machinery is gradually developing toward complexity and intelligence. The fault diagnosis technology of rotating machinery is one of the key means to ensure the normal operation of equipment and safe production, which has very important significance. Deep learning is a useful tool for analyzing and processing big data, which has been widely used in various fields. After a brief review of early fault diagnosis methods, this paper focuses on the method models that are widely used in deep learning: deep belief networks (DBN), autoencoders (AE), convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), and transfer learning methods are summarized from the two aspects of principle and application in the field of fault diagnosis of rotating machinery. Then, the commonly used evaluation indicators used to evaluate the performance of rotating machinery fault diagnosis methods are summarized. Finally, according to the current research status in the field of rotating machinery fault diagnosis, the current problems and possible future development and research trends are discussed.

Fault Diagnosis Method for Imbalanced Data of Rotating Machinery Based on Time Domain Signal Prediction and SC-ResNeSt

“…2) The normalized time series is mapped onto a polar coordinate system by (2). Where 𝑡 𝑖 is the time stamp, 𝑁 is a constant factor for adjusting the radial span of the polar coordinates, and 𝑋 ̃ is the normalized time series.…”

“…With the continuous development of heavy industry, precision mechanical devices have been widely used in aerospace, construction, transportation, and other fields. Some rotating machinery such as bearings or gears as the key components of the mechanical transmission system, and their health plays an important role in the stable operation of mechanical equipment 0, [2]. Any damage to bearings and gears can lead to the sudden failure of the whole mechanical apparatus, resulting in large property losses and even more serious casualties [3].…”

Research on deep-learning-based fault diagnosis and prediction methods for electrical systems

“…Deep learning is a branch of machine learning that uses multiple layers of artificial neural networks to learn complex and nonlinear patterns from large amounts of data. Deep learning has shown remarkable performance in many tasks, such as image recognition [2], natural language processing [3], speech recognition [4], and computer vision [5]. Compared with traditional methods, deep learning has some advantages for FDP in electrical systems, such as being able to automatically extract key features from raw data without prior knowledge or assumptions [6], being able to handle high-dimensional and heterogeneous data with different modalities and scales [7] being able to adapt to dynamic and changing environments with online learning and transfer learning [3].…”

A New Method Based on Encoding Data Probability Density and Convolutional Neural Network for Rotating Machinery Fault Diagnosis

“…In the industrial background of big data, the data-driven fault diagnosis method only needs to collect a large amount of historical data to complete the fault diagnosis [5], does not need to establish a complex mechanism model and reduces the dependence on expert experience as much as possible. Therefore, data-driven fault diagnosis methods have become the mainstream of research in recent years [6].…”