Data-Driven Incipient Fault Prediction for Non-Stationary and Non-Linear Rotating Systems: Methodology, Model Construction and Application

Wang, Qingfeng; Wei, Bingkun; Liu, Jiahe; Ma, Wensheng

doi:10.1109/access.2020.3032445

Cited by 6 publications

(3 citation statements)

References 29 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A failure case data set of a P3409A centrifugal pump from a hydrocracking production unit of a Chinese petroleum company is selected as the model training data set and validation data set [50]. As indicated in Fig.…”

Section: B Engineering Case Verificationmentioning

confidence: 99%

Online Incipient Fault Detection Method Based on Improved ℓ₁ Trend Filtering and Support Vector Data Description

et al. 2021

Self Cite

View full text Add to dashboard Cite

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

show abstract

Section: B Engineering Case Verificationmentioning

confidence: 99%

Online Incipient Fault Detection Method Based on Improved ℓ₁ Trend Filtering and Support Vector Data Description

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is also used to map data from multidimensional space to low-dimensional subspace to mitigate dimensionality and perceive the variance of the data in the best way possible. The Kernel Principal Component Analysis (KPCA) and the SVM were used for the real-time fault diagnosis of a high-voltage circuit breaker, whereas a sample reduction algorithm based on a similarity degree function was used to analyse the similarity among the samples to detect faults [17] and with the dynamic kernel principal component analysis (DKPCA) [18]. However, if the number of dimensions is greater than the number of data points, the convergence matrix is always large, making it difficult to obtain a convergence matrix for data that has varying properties and capabilities [16,19].…”

Section: Introductionmentioning

confidence: 99%

Transmission Line Fault Classification of Multi-Dataset Using CatBoost Classifier

Ogar

Hussain

Gamage

2022

Signals

View full text Add to dashboard Cite

Transmission line fault classification forms the basis of fault protection management in power systems. Because faults have adverse effects on transmission lines, adequate measures must be implemented to avoid power outages. This paper focuses on using the categorical boosting (CatBoost) algorithm classifier to analyse and train multiple voltage and current data from a 330 kV and 500 km-long simulated faulty transmission line model designed using Matlab/Simulink. From it, 93,340 fault data sizes were extracted. The CatBoost classifier was employed to classify the faults after different machine learning algorithms were used to train the same data with different parameters. The trainer achieved the best accuracy of 99.54%, with an error of 0.46% for 748 iterations out of 1000. The algorithm was selected for its high performance in classifying faults based on accuracy, precision and speed. In addition, it is easy to use and handles multiple data-sets. In contrast, a support vector machine and an artificial neural network each has a longer training time than the proposed method’s 58.5 s. Proper fault classification techniques assist in the effective fault management and planning of power system control thereby preventing energy waste and providing high performance.

show abstract

“…Two neural network models are used to realize multi-dimensional feature sequence prediction and waveform prediction; finally, fault prediction is realized by associating fault diagnosis knowledge. In the literature [30], an early defect prediction model based on wavelet packet decomposition and dynamic kernel principal component analysis (wpd-dkpca) is investigated using machine learning technology to fulfill the demands of engineering applications. In the literature [31], to maintain the objectivity of prediction model, the multi-objective particle swarm optimization technique and random walk strategy are employed to optimize long-term and short-term memory (LSTM) network.…”

Section: Introductionmentioning

confidence: 99%

Fault Critical Point Prediction Method of Nuclear Gate Valve with Small Samples Based on Characteristic Analysis of Operation

Liu

et al. 2022

Materials

View full text Add to dashboard Cite

The number of fault samples for the new nuclear valve is commonly rare; thus, the machine learning algorithm is not suitable for the fault prediction of this kind of equipment. In order to overcome this difficulty, this paper proposes a novel method for the fault critical point prediction of the gate valve based on the characteristic analysis of the operation process variables. The operation process of gate valve switch often contains various fault characteristics and information, and this method first adopts the Shannon entropy to describe the power spectrum of vibration signal relevant to the operation process of gate valve switch, and then employs the mean value of the power spectrum entropy as an indirect process variable and further investigates the differences between the indirect process variable under the healthy state and the fault state with a different fault degree. In addition, the power signal of the gate valve is also employed as the direct process variable and the features of the direct process variable under the healthy state and the fault state with different fault degrees are also investigated. Based on the previous indirect process variable and direct process variable, the prediction approach for the critical point of the gate valve fault is established by analyzing the change in the indirect process variable and direct process variable before and after faults. Finally, the data of a nuclear gate valve experiment are employed to demonstrate the feasibility of the proposed method and the results show that the proposed method can effectively predict the fault critical point of the mentioned nuclear gate valve. If the diagnostic threshold is set properly, the critical point prediction of a nuclear gate valve fault can be realized as 100% or close to 100%. Furthermore, the proposed method can be directly applied to the nuclear gate valve in a nuclear power plant to improve the operation reliability of the valve. At the same time, the method can be applied to the fault diagnosis and prediction of valves in other fields, such as the chemical industry.

show abstract

Data-Driven Incipient Fault Prediction for Non-Stationary and Non-Linear Rotating Systems: Methodology, Model Construction and Application

Cited by 6 publications

References 29 publications

Online Incipient Fault Detection Method Based on Improved ℓ₁ Trend Filtering and Support Vector Data Description

Online Incipient Fault Detection Method Based on Improved ℓ₁ Trend Filtering and Support Vector Data Description

Transmission Line Fault Classification of Multi-Dataset Using CatBoost Classifier

Fault Critical Point Prediction Method of Nuclear Gate Valve with Small Samples Based on Characteristic Analysis of Operation

Contact Info

Product

Resources

About

Data-Driven Incipient Fault Prediction for Non-Stationary and Non-Linear Rotating Systems: Methodology, Model Construction and Application

Cited by 6 publications

References 29 publications

Online Incipient Fault Detection Method Based on Improved ℓ1 Trend Filtering and Support Vector Data Description

Online Incipient Fault Detection Method Based on Improved ℓ1 Trend Filtering and Support Vector Data Description

Transmission Line Fault Classification of Multi-Dataset Using CatBoost Classifier

Fault Critical Point Prediction Method of Nuclear Gate Valve with Small Samples Based on Characteristic Analysis of Operation

Contact Info

Product

Resources

About

Online Incipient Fault Detection Method Based on Improved ℓ₁ Trend Filtering and Support Vector Data Description

Online Incipient Fault Detection Method Based on Improved ℓ₁ Trend Filtering and Support Vector Data Description