Abstract

Error diagnosis and detection have become important in modern production due to the importance of spinning equipment. Artificial neural network pattern recognition methods are widely utilized in rotating equipment fault detection. These methods often need a large quantity of sample data to train the model; however, sample data (especially fault samples) are uncommon in engineering. Preliminary work focuses on dimensionality reduction for big data sets using semisupervised methods. The rotary machine’s polar coordinate signal is used to build a GAN network structure. ANN and tiny samples are utilized to identify DCGAN model flaws. The time-conditional generative adversarial network is proposed for one-dimensional vibration signal defect identification under data imbalance. Finally, auxiliary samples are gathered under similar conditions, and CCNs learn about target sample characteristics. Convolutional neural networks handle the problem of defect identification with small samples in different ways. In high-dimensional data sets with nonlinearities, low fault type recognition rates and fewer marked fault samples may be addressed using kernel semisupervised local Fisher discriminant analysis. The SELF method is used to build the optimum projection transformation matrix from the data set. The KNN classifier then learns low-dimensional features and detects an error kind. Because DCGAN training is unstable and the results are incorrect, an improved deep convolutional generative adversarial network (IDCGAN) is proposed. The tests indicate that the IDCGAN generates more real samples and solves the problem of defect identification in small samples. Time-conditional generation adversarial network data improvement lowers fault diagnosis effort and deep learning model complexity. The TCGAN and CNN are combined to provide superior fault detection under data imbalance. Modeling and experiments demonstrate TCGAN’s use and superiority.

Highlights

  • With the rapid development of industrial technology and science and technology, rotating machinery is widely used in modern industrial fields such as electric power, aerospace, metallurgy, wind power, nuclear power, and national defense

  • When using a generative countermeasure network, it is necessary to convert a one-dimensional time series signal into a twodimensional image signal. is increases the workload of fault diagnosis, and the generative confrontation network suitable for two-dimensional images often has a complicated model and takes too long to train. is chapter directly starts from the time series vibration acceleration data of the original rotating machinery and proposes to use the time series condition to generate the confrontation network to directly enhance the vibration data. e experimental results prove the feasibility and superiority of TCGAN

  • With the development of intelligent equipment, the data obtained based on the monitoring of mechanical equipment often have the characteristics of massive high dimensionality, nonstationarity, and nonlinearity. is makes the extracted initial fault characteristics unable to effectively identify the state and fault diagnosis of the mechanical equipment

Read more

Summary

Introduction

With the rapid development of industrial technology and science and technology, rotating machinery is widely used in modern industrial fields such as electric power, aerospace, metallurgy, wind power, nuclear power, and national defense. With the high speed, continuity, and automation in the operation of mechanical equipment, once the core components of the equipment such as rotors and bearings break down or fail to work, it will affect the normal operation of the entire mechanical system and even lead to its paralysis, resulting in inaccessibility estimated loss [1]. Ese methods include short-time Fourier transform, wavelet transform, and Hilbert yellow transform [4] and use specific classifiers such as support vector machine and artificial neural network for pattern recognition, so as to achieve the purpose of fault diagnosis for rotating machinery. Due to the continuous development of deep learning and its excellent feature extraction capabilities, the use of deep learning for fault diagnosis has become one of the most popular breakthrough technologies

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call