Machinery health indicator construction based on convolutional neural networks considering trend burr

Guo, Liang; Lei, Yaguo; Li, Naipeng; Yan, Tao; Li, Ningbo

doi:10.1016/j.neucom.2018.02.083

Cited by 232 publications

(97 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) RQA + SVM [19]: independent use of RQA for feature learning and optimal binary tree SVM for classification (2) LSTM: independent use of the proposed LSTM architecture on raw data 0.20 0.00 0.00 0.30 0.00 0.00 0.00 0.00 0.00 100.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 100.00 0.00 0.00 0.30 0.70 0.00 0.00 0.50 0.00 98.50 0.00 0.00 0.00 0.00 100.00 0.00 0.00 0.00 (3) MLP [7]: multilayer neural network on statistical features (4) CNN [32]: one-dimension CNN on raw data (5) SIFT + CNN [13]: short-time Fourier transform for feature learning and CNN for classification (6) CDFL [14]: convolutional discriminative learning of a BP network…”

Section: Performance Comparisonsmentioning

confidence: 99%

Fault Diagnosis of Induction Motors Using Recurrence Quantification Analysis and LSTM with Weighted BN

Xiao

Huang

Qin

et al. 2019

Shock and Vibration

View full text Add to dashboard Cite

Motor fault diagnosis has gained much attention from academic research and industry to guarantee motor reliability. Generally, there exist two major approaches in the feature engineering for motor fault diagnosis: (1) traditional feature learning, which heavily depends on manual feature extraction, is often unable to discover the important underlying representations of faulty motors; (2) state-of-the-art deep learning techniques, which have somewhat improved diagnostic performance, while the intrinsic characteristics of black box and the lack of domain expertise have limited the further improvement. To cover those shortcomings, in this paper, two manual feature learning approaches are embedded into a deep learning algorithm, and thus, a novel fault diagnosis framework is proposed for three-phase induction motors with a hybrid feature learning method, which combines empirical statistical parameters, recurrence quantification analysis (RQA) and long short-term memory (LSTM) neural network. In addition, weighted batch normalization (BN), a modification of BN, is designed to evaluate the contributions of the three feature learning approaches. The proposed method was experimentally demonstrated by carrying out the tests of 8 induction motors with 8 different faulty types. Results show that compared with other popular intelligent diagnosis methods, the proposed method achieves the highest diagnostic accuracy in both the original dataset and the noised dataset. It also verifies that RQA can play a bigger role in real-world applications for its excellent performance in dealing with the noised signals.

show abstract

Section: Performance Comparisonsmentioning

confidence: 99%

Fault Diagnosis of Induction Motors Using Recurrence Quantification Analysis and LSTM with Weighted BN

Xiao

Huang

Qin

et al. 2019

Shock and Vibration

View full text Add to dashboard Cite

show abstract

“…It is crucial to choose suitable degradation index when the condition of ball screw is detected by vibration signals. Degradation index attempts to construct a representative indicator from the acquired signals to reveal the degradation process [38,39]. Excellent degradation index is usually characterized by monotonicity and correlation.…”

Section: Derivation Of Degradation Model Based On Wear Volumementioning

confidence: 99%

Wear Calculation-Based Degradation Analysis and Modeling for Remaining Useful Life Prediction of Ball Screw

Zhang

Gao

Dong

et al. 2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Ball screw is a kind of precise transmission element in drive system of machine tool. In this paper, the degradation model of ball screw is proposed based on wear calculation-based degradation analysis and experimental data-based validation. At first, fatigue wear is analyzed to be the predominant degradation mode of ball screw. The wear volume formula of ball screw is derived as the function of working load and stroke number. Secondly, the degradation rate of ball screw is analyzed to be affected by the total degradation and wear rate. Based on this finding, the degradation model of ball screw is theoretically derived as an exponential model by inputting wear volume formula. Thirdly, experimental data-based cross-validation method is proposed to validate the exponential degradation model. Determination coefficients are calculated to evaluate the fitting degree between the degradation model and real degradation path. Next, run-to-failure test of ball screw is carried out to collect experimental data in different working conditions. The average determination coefficient of different working conditions is calculated as 0.7848, which indicates that the proposed model can well fit the actual degradation path. In addition, the proposed model is applied to predict remaining useful life (RUL) of the tested ball screw by using collected data. RUL is estimated in a high and stable accuracy after 168000 strokes. For further validation, comparison with linear model is performed. All results show that the exponential degradation model is reasonable and correct in reflecting the degradation process of ball screw.

show abstract

“…To address these issues, online detection of bearing health is urgently required to effectively enhance the safety of mechanical equipment operation [5][6][7], predict bearing remaining useful life (RUL), and to implement an action plan to prevent catastrophic events and extend the bearing life cycle [7]. Advances in bearing RUL prediction technology have provided increasingly powerful technical support for intelligent bearing RUL prediction and health management [8][9][10]. In the past few decades, the research has achieved theoretical results that have been widely applied.…”

Section: Introductionmentioning

confidence: 99%

An Ensemble Learning and RUL Prediction Method Based on Bearings Degradation Indicator Construction

Tian

Wang

2020

Applied Sciences

View full text Add to dashboard Cite

The prediction of the remaining life of a bearing plays a vital role in reducing the accident-related maintenance costs of machinery and in improving the reliability of machinery and equipment. To predict bearing remaining useful life (RUL), the abilities of statistical characteristics to reflect the bearing degradation state differ, and the single prediction model has low generalization ability and a poor prediction effect. An ensemble robust prediction method is proposed here to predict bearing RUL based on the construction of a bearing degradation indicator set: the initial bearing degradation indicator subsets were constructed using the Fast Correlation-Based Filter with Approximate Markov Blankets (FCBF-AMB) and Maximal Information Coefficient (MIC) selection methods. Through the cross-operation of the obtained subsets, we obtained a set of robust degradation indicators. These selected degradation indicators were fed into the long short-term memory (LSTM) neural network prediction model enhanced by the AdaBoost algorithm. We found through calculation that the average prediction accuracy of the proposed method is 91.40%, 92.04%, and 93.25% at 2100, 2250, and 2400 rpm, respectively. Compared with other methods, the proposed method improves the prediction accuracy by 1.8% to 14.87% at most. Therefore, the method proposed in this paper is more accurate than the other methods in terms of RUL prediction.

show abstract

Machinery health indicator construction based on convolutional neural networks considering trend burr

Cited by 232 publications

References 26 publications

Fault Diagnosis of Induction Motors Using Recurrence Quantification Analysis and LSTM with Weighted BN

Fault Diagnosis of Induction Motors Using Recurrence Quantification Analysis and LSTM with Weighted BN

Wear Calculation-Based Degradation Analysis and Modeling for Remaining Useful Life Prediction of Ball Screw

An Ensemble Learning and RUL Prediction Method Based on Bearings Degradation Indicator Construction

Contact Info

Product

Resources

About