Fault Detection of Bearing by Resnet Classifier with Model-Based Data Augmentation

Abstract

It is always an important and challenging issue to achieve an effective fault diagnosis in rotating machinery in industries. In recent years, deep learning proved to be a high-accuracy and reliable method for data-based fault detection. However, the training of deep learning algorithms requires a large number of real data, which is generally expensive and time-consuming. To cope with this, we proposed a Resnet classifier with model-based data augmentation, which is applied for bearing fault detection. To this end, a dynamic model was first established to describe the bearing system by adjusting model parameters, such as speed, load, fault size, and the different fault types. Large amounts of data under various operation conditions can then be generated. The training dataset was constructed by the simulated data, which was then applied to train the Resnet classifier. In addition, in order to reduce the gap between the simulation data and the real data, the envelop signals were used instead of the original signals in the training process. Finally, the effectiveness of the proposed method was demonstrated by the real bearing experimental data. It is remarkable that the application of the proposed method can be further extended to other mechatronic systems with a deterministic dynamic model.

Fault diagnosis for spent fuel shearing machines based on Bayesian optimization and CBAM-ResNet

“…BO hopes to be used as few times as possible to evaluate the posterior probability of the optimization function using the objective function to obtain the optimal hyperparameter combination [29]. The choice of hyperparameter combinations for BO can be expressed as:…”

“…Liang et al [28] proposed a fault diagnosis method based on wavelet transform (WT) with global singular value decomposition to improve the ResNet with better robustness to noise signals. Qian et al [29] proposed a ResNet classifier based on model data augmentation and applied it to bearing fault diagnosis. Lin et al [30] proposed a fault diagnosis model of ResNet based on multiscale SE attention module.…”

Unsupervised Outlier Detection for Time-Series Data of Indoor Air Quality Using LSTM Autoencoder with Ensemble Method

“…In outlier detection in the field of networks, an anomaly is defined as an exceptional pattern that does not follow the expected normal pattern of network traffic (Bhuyan et al, 2013). In autonomous driving, ResNet classification is used to diagnose component failures, and cases different from dynamic characteristics are defined as fault diagnoses (Qian et al, 2022). Moreover, in natural images, when evaluating outlier detection methods through multi-class classification, class labels are adjusted to the existing classification datasets (Bergmann et al, 2021).…”

“…In time-series data research, many studies have been conducted on bearing defect diagnosis problems or multivariate outlier detection (Qian et al, 2022), (Filzmoser et al, 2004). In a univariate time series, a point or subsequence that exceeds a certain threshold can be considered an anomaly (Zheng et al, 2016).…”

A Parallel Ensemble Learning Model for Fault Detection and Diagnosis of Industrial Machinery

“…In this regard, DL models have become widely used in FDD of machinery [15][16][17], as they can address the limitations of traditional ML methods in performing automated feature extraction. On the other hand, ensemble methods, which combine the strengths of multiple techniques to overcome their individual limitations, have been adopted for solving FDD problems [17,18]. However, many existing DL-based solutions employ single models, which are often not efficient and effective in handling large-scale data and complex systems [19].…”