Bearing Fault Diagnosis Under Small Data Set Condition: A Bayesian Network Method With Transfer Learning for Parameter Estimation

Abstract

Bearings are broadly applied in various types of industrial systems. Fault diagnosis, as a promising way for reliability of modern industrial internet of thing applications, has attracted increasing attention from both academia and industry fields. Being ideal modeling and inference tool in uncertainty situations, Bayesian network (BN) is becoming increasingly popular in many systems. However, in practical uncertain and complicated engineering surroundings, it's difficult or expensive to collect massive labeled fault data for the sake of fault diagnosis model learning. To address the issue of BN parameter learning under small data set conditions, this paper proposes a Varying Coefficient Transfer Learning (VCTL) algorithm based on aggregation and transfer learning, that considers both knowledge from the resource domain and the resource relevance contributions. The balancing weight function is designed to determine whether the learning task in the resource domain is activated. Relevance weight factors are proposed to measure the relevance of resource and target parameters quantitatively, by combing parameter information from resource domains with those obtained from the target domain, using maximum a posterior (MAP) or maximum likelihood estimation (MLE). Finally, the target parameters are aggregated with both the target initial parameters and the parameter knowledge from the resource domain. Based on VCTL, a bearing fault diagnosis approach is proposed and verified. The experimental results show that, under the condition of the small data set, learning accuracy of VCTL algorithm with varying coefficient aggregation is better than MLE algorithm, MAP algorithm or state-of-the-art parameter transfer method, local linear pooling transfer learning (LoLP) algorithm. Under the condition of sufficient data set, learning accuracy of VCTL algorithm approaches the classical MLE or MAP, and the correctness of the proposed algorithm is verified. Moreover, we illustrate the successful application to real-world bearing fault diagnosis case with VCTL, where we had access to expert-provided resource knowledge and real fault diagnosis data.

Prediction of Nugget Diameter and Analysis of Process Parameters of RSW with Machine Learning Based on Feature Fusion

“…In order to avoid the overfitting phenomenon, this study combines the Bayesian optimization algorithm [17] to complete the parameter selection of the basic model, thus improving the model performance and reducing variance. Therefore, this study proposes a machine learning synthesis model based on Bayesian optimization:…”

On Model-Based Transfer Learning Method for the Detection of Inter-Turn Short Circuit Faults in PMSM

“…Because of its fast optimization efficiency, it is widely applied. It is composed of two parts: the Bayesian statistical model and the acquisition function [16]. Bayesian statistical models employ prior observations and information to evaluate the hypothesis of the posterior distribution for the function to be optimized.…”

“…Secondly, the training of deep learning models needs a large volume of data, and in practice, the amount of data available for model training is often limited, which tends to restrict the performance of the model [15]. Thirdly, due to the small volume of the samples in fault diagnosis, the depth of the deep learning models is usually no more than 5, which will limit the performance of their final predictions [16]. Fourthly, the hyperparameter tuning of the deep learning model is time-consuming, particularly for those unfamiliar with the process of parameter optimization [17].…”

Model-Based Fault Diagnosis Algorithms for Robotic Systems

“…The associate editor coordinating the review of this manuscript and approving it for publication was Guillermo Valencia-Palomo . decomposition, Bayesian network method, statistical and expert methods are the examples of this approach [3], [4], [5], [6]. Recent advancement based on this approach is by using machine learning methods, such as deep learning [7], [8], long short-term memory (LSTM) [9], and support vector machine [10].…”