Bearing Fault Diagnosis Based on Improved Convolutional Deep Belief Network

Abstract

Mechanical equipment fault detection is critical in industrial applications. Based on vibration signal processing and analysis, the traditional fault diagnosis method relies on rich professional knowledge and artificial experience. Achieving accurate feature extraction and fault diagnosis is difficult using such an approach. To learn the characteristics of features from data automatically, a deep learning method is used. A qualitative and quantitative method for rolling bearing faults diagnosis based on an improved convolutional deep belief network (CDBN) is proposed in this study. First, the original vibration signal is converted to the frequency signal with the fast Fourier transform to improve shallow inputs. Second, the Adam optimizer is introduced to accelerate model training and convergence speed. Finally, the model structure is optimized. A multi-layer feature fusion learning structure is put forward wherein the characterization capabilities of each layer can be fully used to improve the generalization ability of the model. In the experimental verification, a laboratory self-made bearing vibration signal dataset was used. The dataset included healthy bearings, nine single faults of different types and sizes, and three different types of composite fault signals. The results of load 0 kN and 1 kN both indicate that the proposed model has better diagnostic accuracy, with an average of 98.15% and 96.15%, compared with the traditional stacked autoencoder, artificial neural network, deep belief network, and standard CDBN. With improved diagnostic accuracy, the proposed model realizes reliable and effective qualitative and quantitative diagnosis of bearing faults.

Early Bearing Fault Diagnosis of Rotating Machinery by 1D Self-Organized Operational Neural Networks

“…Recently, modern data-driven deep learning models developed by the machine learning researchers have been proposed as solution to FDD problems. As opposed to shallow supervised learners, deep learning networks (DNNs) can learn the required features from the raw input data via training fully automatically voiding the need for the handcrafted statistical or transform-domain feature representations [10]- [17]. However, for a proper training, they need well-labelled training datasets with massive size.…”

“…Generative adversarial networks (GANs)-based framework was proposed by Shao et al [16] to learn to generate 1D realistic raw data from mechanical sensor signals to augment real sensor data to resolve the issues of unbalanced data on training deep networks for applications in machine fault diagnosis. In [17], an improved convolutional deep belief network (CDBN) was proposed for diagnosis of rolling bearing faults where the original vibration signal was first transformed to the frequency-domain via FFT before being input to an optimized model structure to achieve better accuracy than traditional SAE, ANN, DBN and CBDN models. Such deep models [15]- [17] have a high computational complexity in common which prevents their usage in low-power computing environments in real-time.…”

“…In [17], an improved convolutional deep belief network (CDBN) was proposed for diagnosis of rolling bearing faults where the original vibration signal was first transformed to the frequency-domain via FFT before being input to an optimized model structure to achieve better accuracy than traditional SAE, ANN, DBN and CBDN models. Such deep models [15]- [17] have a high computational complexity in common which prevents their usage in low-power computing environments in real-time. Additionally, they have not dealt with small training rate (small train data size compared to test data) which is usually the case for practical applications.…”

Mutual Information and Meta-Heuristic Classifiers Applied to Bearing Fault Diagnosis in Three-Phase Induction Motors

“…Recently, deep learning (DL) has attracted researchers' attention in several areas, such as image processing, computer vision, and pattern recognition, due to their better understanding of the intrinsic information of the analyzed data [5]. Besides, DL algorithms are being used in rotating machine failure diagnosis due to their ability to classify data without specific tools for extracting signal characteristics [5,6,23,24].…”

“…In Liu et al [24], a deep-belief convolutionary network (CBDN) approach to extracting and learning the relevant characteristics of bearing fault signals in electrical machines was presented. The main advantages of CBDN over other DL approaches are that they are quickly processed to perform calculations and extract features.…”