A Novel Domain Adaptation-Based Intelligent Fault Diagnosis Model to Handle Sample Class Imbalanced Problem

Abstract

As the key component to transmit power and torque, the fault diagnosis of rotating machinery is crucial to guarantee the reliable operation of mechanical equipment. Regrettably, sample class imbalance is a common phenomenon in industrial applications, which causes large cross-domain distribution discrepancies for domain adaptation (DA) and results in performance degradation for most of the existing mechanical fault diagnosis approaches. To address this issue, a novel DA approach that simultaneously reduces the cross-domain distribution difference and the geometric difference is proposed, which is defined as MRMI. This work contains three parts to improve the sample class imbalance issue: (1) A novel distance metric method (MVD) is proposed and applied to improve the performance of marginal distribution adaptation. (2) Manifold regularization is combined with instance reweighting to simultaneously explore the intrinsic manifold structure and remove irrelevant source-domain samples adaptively. (3) The ℓ2-norm regularization is applied as the data preprocessing tool to improve the model generalization performance. The gear and rolling bearing datasets with class imbalanced samples are applied to validate the reliability of MRMI. According to the fault diagnosis results, MRMI can significantly outperform competitive approaches under the condition of sample class imbalance.

An Adaptive Sampling Framework for Life Cycle Degradation Monitoring

“…Taking the popular statistical learning techniques as the example, many methods has been applied in degradation monitoring, including supervised learning [ 28 ], unsupervised learning [ 29 ], transfer learning [ 30 ], statistical model [ 31 ], integrated learning [ 32 ], etc. For existing data problems, a large number of studies have also been carried out to reduce their impacts in the tasks of classification [ 33 , 34 ] and regression [ 5 , 35 ]. However, they all deal with this problem from the perspective of methodology, and the solutions from a data perspective have been underestimated.…”

Using Data From Similar Systems for Data-Driven Condition Diagnosis and Prognosis of Engineering Systems: A Review and an Outline of Future Research Challenges

“…It is based on the same principle as MMD but focuses on second-order statistics instead of first-order statistics. PHM approaches were presented by Zhang et al [228] and Zhang et al [229] for the condition diagnosis of bearings and gearboxes. Other measures used in PHM to compare the similarity between datasets are the cosine distance [137], [144], the log-Euclidean metric of second-order statistics [230], and the a-distance [192].…”

“…Zhang et al [228] enhanced TJM by the additional use of MVD and applied the approach to bearing condition diagnosis. Zhang et al [229] also assigned weights to the source samples to reduce the influence of irrelevant samples and used MVD as a similarity measure. In addition, a manifold regularization term was added.…”

A Systematic Literature Review on Transfer Learning for Predictive Maintenance in Industry 4.0

“…Instance-based [25], [26], [27] Feature-based [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51], [52], [53], [54], [55], [56], [57], [58], [59], [60], [61], [62], [63], [64], [65], [66], [67], [68], [69], [70], [71], [72], [73], [74], [75],…”