Fast Spectral Correlation Based on Sparse Representation Self-Learning Dictionary and Its Application in Fault Diagnosis of Rotating Machinery

Abstract

Rolling element bearing and gear are the typical supporting or rotating parts in mechanical equipment, and it has important economy and security to realize their quick and accurate fault detection. As one kind of powerful cyclostationarity signal analyzing method, spectral correlation (SC) could identify the impulsive characteristic component buried in the vibration signals of rotating machinery effectively. However, the fault feature such as impulsive characteristic component is often interfered by other background noise, and the situation is serious especially in early weak fault stage. Besides, the traditional SC method has a drawback of low computation efficiency which hinders its wide application to some extent. To address the above problems, an impulsive feature-enhanced method which combines fast spectral correlation (FSC) with sparse representation self-learning dictionary is proposed in the paper. Firstly, the sparse representation self-learning dictionary method-K-means singular value decomposition (KSVD) is improved and the improved KSVD (IKSVD) method is used to denoise the original signal, and the periodic impulses are highlighted. Then, the FSC algorithm is applied on the denoised signal and spectral correlation image could be obtained. Finally, the calculated enhanced envelope spectrum (EES) of the denoised signal is obtained by using the spectral correlation image to identify the accurate fault position. The feasibility and superiority of the proposed method is verified through simulation, experiment, and engineering application.

Machine learning techniques applied to mechanical fault diagnosis and fault prognosis in the context of real industrial manufacturing use-cases: a systematic literature review

“…As can be seen in Fig. 6, 53.3% of publications employ supervised learning techniques, 28.9% use unsupervised learning techniques, 15.6% make use of both supervised and unsupervised techniques and 2.2% [56] conference Advances in Manufacturing [57] journal Applied Sciences [58] journal Business & Information Systems Engineering [59] journal Complexity [60] journal Computers & Industrial Engineering [61] journal Electronics [62] journal Engineering Applications of Artificial Intelligence [63] journal Expert Systems with Applications [64] journal IEEE Transactions on Industrial Electronics [31] journal IEEE Transactions on Industrial Informatics [65] journal Journal of Manufacturing Systems [66] journal Simulation Modelling Practice and Theory [67] journal Studies in Informatics and Control [68] journal 2019 31st International Conference on Advanced Information Systems Engineering (CAiSE) [69,70] conference CIRP Annals [71,72] journal Sensors [73,74] journal The International Journal of Advanced Manufacturing Technology [75,76] journal IEEE Access [77][78][79][80][81] journal Fig. 4 Proportion of publications in conferences and journals combine semi-supervised, unsupervised, and supervised techniques.…”

“…Instance-based algorithms K-NN [39] supervised Latent Variable Models PCA [65] unsupervised GMM [47] unsupervised K-Means [54] unsupervised PLSR [64] supervised K-SVD [60] unsupervised K-MDTSC [62] unsupervised Artificial Neural Networks ANN [57] supervised BPNN [40] supervised CNN [78] supervised DNN [77] supervised LSTM [70] supervised MLP [56] supervised SSAE + BPNN [31] unsupervised + supervised SSAE + Softmax Classifier [81] unsupervised + supervised LSTM Autoencoder [73] supervised LSTM -GAN [79] supervised RNN [55] supervised Conditional Variational Autoencoder [66] unsupervised Rule-based models R4RE ("Rules 4 Rare Events" based on QARMA) [49] supervised XCSR [51] supervised consists in the principal components obtained from the application of DPCA, which do not represent any physical properties or measurements of the system. The study presented in [67] used an ensemble method as well due to its efficiency in terms of computation time and memory when handling large amounts of data.…”

“…Proposed approach: Produces stable and consistent results. [60] Algorithm: high computational efficiency; greater adaptability; robust to noise; uncovers patterns in raw time series data.…”

“…The authors of [60] took advantage of K-SVD's robustness to noise and its ability to capture the characteristic Algorithm: performance decreases when training and test data don't share the same distribution. Proposed approach: handles data with asynchronous sampling rates; doesn't require comprehensive domain knowledge.…”

Transient Electromagnetic Weak Signal Extraction Method Based on Multi-Scale Combined Difference Product Morphological Filtering

“…There are many electromagnetic signal detection methods under strong background noise, all of which have achieved good extraction resultssuch as mechanical fault signal di- VOLUME 4, 2016 agnosis, weak vibration signal extraction, etc [3], [4]. In traditional transient signal detection methods, the short-time spectral correlation method requires prior knowledge of the detected signal [5], [6]. Power-Law detection method [7], transient energy detection method [8], and cepstral analysis [9] results are greatly affected by noise.…”