Considerable studies have been carried out in recent years regarding fault diagnosis and prediction for the rotating machinery in industrial plants. However, few works present the use of clustering approaches applied to time series to diagnose machine faults. With the increasing practical requirement of safety, reliability, availability and maintainability of machinery running, predictive maintenance based on the technologies of fault diagnosis and prediction has also received significant attention in recent years. In the present study, under Cyber-physical systems (CPS) condition, k-means clustering analysis based on the fault case big data machine learning is applied to investigate the fault identification of the rotating machinery without external expert support. K-means cluster-based fault identification model, which includes the kmeans cluster analysis module, fault modefault cluster centroid knowledge base module and fault identification module has been constructed. Moreover, the fault feature extraction and fault eigenvectors screening are studied in detail. The vibration data of surge, rubbing, misalignment and normal status of the centrifugal compressor in industrial plants are utilized to train and verify the effectiveness of the k-means cluster fault recognition model. The obtained result shows that recognition accuracy rates of the surge, rubbing and misalignment faults reach 94%, 100% and 80%, respectively. However, the effectiveness of the cluster analysis of vibration data for five or more operating states should be studied in the future.INDEX TERMS k-means clustering, fault feature extraction, fault eigenvectors screening, fault cluster centroid, fault identification model.
Poor model generalization, missing or false alarms, and heavy dependence on expert's experience are some of the major problems which exist in traditional incipient fault detection (IFD) methods. An IFD rolling bearing application method based on combination of improved 1 trend filtering (L1TF) and support vector data description (SVDD) is proposed. First, spectral distance index and multi-scale dispersion entropy based on normal vibration data, which is sensitive to incipient faults, are extracted. The improved 1 trend filter (IL1TF) method is employed for processing the feature values and obtaining a trend factor with less fluctuation and better incipient fault indication ability. Then, after determining the kernel function bandwidth of the SVDD by analyzing the characteristics of the training data, a suitable offline SVDD model is trained. Finally, incipient faults are identified by estimating the distance between the trend factor of the real-time data and the center of the hypersphere in the SVDD model. This method employs full performance of SVDD to detect abnormal data files, while reducing the influence of abnormal data files on the model via IL1TF. Furthermore, the method increases the discrimination between the incipient fault data and the normal data. By utilizing Intelligent Maintenance Systems of University of Cincinnati bearing laboratory data and Chinese petrochemical company's centrifugal pump bearing engineering data, the effectiveness of the constructed model is demonstrated. In addition, the proposed method is compared against existing representative IFD methods. The results indicate that the method proposed in this paper can solve false alarms and detect incipient failure data files more accurately without depending on the external expert's experience. This is of great significance for providing guidelines to enterprises which employ predictive maintenance techniques. INDEX TERMS Improved 1 trend filtering, support vector data description, kernel function bandwidth determination, incipient fault detection
Research on the intelligent fault diagnosis method of rolling bearing based on laboratory data has made some achievements. However, due to the change of working conditions and the lack of historical data of the same equipment in the actual diagnosis, some methods mostly have problems such as poor generalization. Model training and verification data are insufficient, and engineering practice still lacks effective intelligent fault diagnosis methods. In this paper, we propose a weighted k-nearest neighbor (WKNN) fault diagnosis model based on multi-dimensional sensitive features, and propose a fault diagnosis method for rolling bearings that adapts to different equipment and different operating conditions. First, we extract time domain, frequency domain, and entropy features of the original signal to form the raw signal feature set. Then, the iterative ReliefF feature screening method is used to evaluate the joint feature set, calculate the weight of each feature, remove insensitive and redundant features, and obtain a highdimensional sensitive feature set. Finally, the WKNN classification model is used to identify bearing failure modes. The fault diagnosis model was trained using rolling bearing data from the Case Western Reserve University (CWRU), while laboratory data from the Intelligent Maintenance System (IMS), the Society of Mechanical Failure Prevention Technology (MFPT) and the engineering case data were used for testing. The results show that the model proposed in this paper has high fault diagnosis accuracy and can accurately determine the fault type after early warning. Compared with other comparison methods, the fault recognition accuracy rate is higher. And it is suitable for different working conditions and different equipment, and has good engineering application value.INDEX TERMS Different working conditions, fault diagnosis, multi-dimensional sensitive features, ReliefF, WKNN.
Many researches have been carried out on incipient fault prediction technology for key machine components (such as bearings) based on historical and real-time condition monitoring data. However, there is still lack of well-understood systematic methodologies for detecting incipient fault for rotating machines. Based on machine learning technology, this paper studies an incipient fault prediction model applying with wavelet packet decomposition and dynamic kernel principal component analysis (WPD-DKPCA) to meet the needs of engineering applications. The incipient fault prediction WPD-DKPCA model, which does not require knowledge on equipment structure and failure mechanisms, only requires normal state data of the machine, and incipient fault prediction can be achieved through self-learning. Run-to-failure experimental data and engineering case data have been used to verify the constructed model, and the verification results show that the constructed model can reliably and accurately detect an incipient bearing fault. Comparisons of fault prediction effects prove that using T 2 statistic monitoring can detect upcoming faults of machines much earlier than Kurtosis and Root Mean Square (RMS).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.