Fault Diagnosis with Evolving Fuzzy Classifier Based on Clustering Algorithm and Drift Detection

Abstract

The emergence of complex machinery and equipment in several areas demands efficient fault diagnosis methods. Several fault diagnosis methods based on different theories and approaches have been proposed in the literature. According to the concept of intelligent maintenance, the application of intelligent systems to accomplish fault diagnosis from process historical data has been shown to be a promising approach. In problems involving complex nonstationary dynamic systems, an adaptive fault diagnosis system is required to cope with changes in the monitored process. In order to address fault diagnosis in this scenario, use of the so-called “evolving intelligent systems” is suggested. This paper proposes the application of an evolving fuzzy classifier for fault diagnosis based on a new approach that combines a recursive clustering algorithm and a drift detection method. In this approach, the clustering update depends not only on a similarity measure, but also on the monitoring changes in the input data flow. A merging cluster mechanism was incorporated into the algorithm to enable the removal of redundant clusters. Multivariate Gaussian memberships functions are employed in the fuzzy rules to avoid information loss if there is interaction between variables. The novel approach provides greater robustness to outliers and noise present in data from process sensors. The classifier is evaluated in fault diagnosis of a DC drive system. In the experiments, a DC drive system fault simulator was used to simulate normal operation and several faulty conditions. Outliers and noise were added to the simulated data to evaluate the robustness of the fault diagnosis model.

Clustering Application for Condition-Based Maintenance in Time-Varying Processes: A Review Using Latent Dirichlet Allocation

“…Another contribution in this topic highlighting the presence of noise is [45], in which spectrum entropy clustering is applied to extract features to be used for fault diagnosis analysis in a gear system. Another solution proposes the application of a recursive clustering algorithm for diagnostic analysis [46]. Clustering for noise management is important because it allows analyses to be implemented without having prior knowledge of the process, e.g., applying the algorithm of mean shift clustering [47].…”

“…Among the keywords, k-means also stands out, as among the clustering algorithms present in this one, it is the one with the highest number of hits. In this topic, as in topic 1, some of the proposed solutions involve a recursive approach [46].…”

Predictive Maintenance: A Novel Framework for a Data-Driven, Semi-Supervised, and Partially Online Prognostic Health Management Application in Industries

“…As new input data arrive, the system integrates these data into existing clusters if the data are compatible with the existing model structure and adapts the local parameters of the corresponding cluster (parameter adaptation); otherwise, the algorithm creates a new cluster (structure evolving) [61]. In [62], a recursive clustering algorithm incorporating a drift detection method is proposed, in which the clustering updating process depends not only on the similarity measure but also on the monitoring changes in the input data flow, which gives the algorithm greater robustness with respect to the presence of outliers and noise. However, these methods require the membership function to be determined a priori.…”

Clustering Application for Condition-based Maintenance in Time-varying Processes: A Review

“…Other contributions in this topic highlighting the presence of noise are [45], in which spectrum entropy clustering is applied to extract features to be used for fault diagnosis analysis in a gear system. Another solution, on the other hand, proposes the application of a recursive clustering algorithm for diagnostic analysis [46]. The importance of clustering for noise management lies in the fact that it allows analyses to be implemented without having prior knowledge of the process.…”

“…Among the keywords, k-means also stands out, as among the clustering algorithms present in this one, it is the one with the highest number of hits. In this topic, as in topic 1, weight is again given to the fact that some of the proposed solutions involve a recursive approach [46].…”