A deep learning based health indicator construction and fault prognosis with uncertainty quantification for rolling bearings

Wang, Zhiyuan; Guo, Junyu; Wang, Jiang; Yang, Yulai; Dai, Liyi; Huang, Cheng-Geng

doi:10.1088/1361-6501/ace072

Cited by 13 publications

(11 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A value converging towards 1 indicates a pronounced trend and superior predictive performance of the data. For the evaluation, the Monotonicity measurement methodology delineated by Baptista and Henriques [43] was adopted, as expressed in equation (32),…”

Section: D-wgan-gp Denoising Experiments Resultsmentioning

confidence: 99%

“…Guo et al [31] also employed LSTM to construct HI for bearings, with network inputs composed of handcrafted features covering the time domain, frequency domain, and timefrequency domain. Wang et al [32] proposed an integrated approach to construct automated HI, employing empirical mode decomposition with adaptive noise, principal component analysis, and a CNN-BiGRU framework; this approach not only accounts for predictive errors due to model parameters and noise but also for predictive inaccuracies that stem from various feature combinations in the model. Yang et al [33] investigated an effective approach for monitoring the degradation of rolling bearings and predicting the HIs of the bearings.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Construction health indicator using physically-informed 1D-WGAN-GP joint attention LSTM-DenseNet method

Yang,

Sun

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

In data-driven prognosis methods, the accuracy of predicting the remaining useful life (RUL) of mechanical systems is predominantly contingent upon the efficacy of system health indicators, typically amalgamated from statistical features derived from collected signals. Nevertheless, the majority of extant health indicators are beset by two principal shortcomings: (1) During traditional data denoising processes, degradation information from raw data is prone to loss owing to the lack of incorporation of the true physical properties of the data; and (2) The performance evaluation of constructed health indicators is imbalanced due to the influence of network structures on single models, often resulting in strong performance in only one or two indicators. To overcome such shortcomings, a mechanical health indicator construction method based on physical properties was proposed, termed 1D-WGAN-GP Joint Attention LSTM-DenseNet (ALD). Firstly, artificial sample data is generated by analysing the physical properties of the original dataset, which is then used to train the 1D-WGAN-GP model to achieve data denoising. Subsequently, the fusion of the Attention LSTM (A-LSTM) network and DenseNet network is utilised to extract crucial feature vectors of health indicators under varying health conditions from the denoised data. Finally, the extracted feature vectors are used to construct system health indicators using the Euclidean distance method, and these indicators are used for predicting the system's RUL. The results indicate that the proposed method outperformed traditional methods in terms of denoising effectiveness. Further, through ablation experiment analysis, the health indicators constructed by the proposed method demonstrated obvious complementarity in terms of monotonicity, correlation, robustness, and comprehensive evaluation. In RUL prediction applications, the proposed method also exhibited good performance, thereby validating its effectiveness.

show abstract

Section: D-wgan-gp Denoising Experiments Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Construction health indicator using physically-informed 1D-WGAN-GP joint attention LSTM-DenseNet method

Yang,

Sun

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Industrial equipment, even of the same model and batch, often shows significant individual differences in reliability [31][32][33]. These differences originate from production uncertainties, including minor variations in material properties, fluctuations in processing precision, and slight assembly errors.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Fusion of Degradation and Failure Time Data for Reliability Assessment of Industrial Equipment Considering Individual Differences

Fu,

Zhang,

et al. 2024

Processes

View full text Add to dashboard Cite

In the field of industrial equipment reliability assessment, dependency on either degradation or failure time data is common. However, practical applications often reveal that single-type reliability data for certain industrial equipment are insufficient for a comprehensive assessment. This paper introduces a Bayesian-fusion-based methodology to enhance the reliability assessment of industrial equipment. Operating within the hierarchical Bayesian framework, the method innovatively combines the Wiener process with available degradation and failure time data. It further integrates a random effects model to capture individual differences among equipment units. The robustness and applicability of this proposed method are substantiated through an in-depth case study analysis.

show abstract

“…This innovation incorporates the 3σ statistical approach, specifically applied to ascertain the first prediction time, thereby enhancing the precision and reliability of the predictive model. Wang et al [24] presented a method to quantify the prediction interval for the RUL of rolling bearings. Utilizing an advanced algorithmic approach that combines complete ensemble empirical mode decomposition with adaptive noise and principal component analysis (CEEMDAN-PCA), along with the integration of the CNN-BiGRU architecture, they skillfully constructed indicators to assess bearing health degradation.…”

Section: Introductionmentioning

confidence: 99%

Remaining useful life prediction of rolling bearings based on TCN-MSA

Jiang,

Duan,

Zhao

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Abstracts: As a pivotal element within the drive system of mechanical equipment, the Remaining Useful Life (RUL) of rolling bearings not only dictates the lifespan of the equipment's drive system but also the overall machine. An inaccurate prediction of the RUL of rolling bearings could hinder the formulation of maintenance strategies and lead to a chain of failures stemming from bearing malfunction, culminating in potentially catastrophic accidents. This paper designs a novel Temporal Convolutional Network-Multi-head Self-Attention (TCN-MSA) model for predicting the RUL of rolling bearings. This model considers the intricate non-linearity and complexity of mechanical equipment systems. It captures long-term dependencies using the causally inflated convolutional structure within the Temporal Convolutional Network (TCN) and simultaneously extracts features from the frequency domain signal. Subsequently, by employing the Multi-head Self-Attention (MSA) mechanism, the model discerns the significance of different features throughout the degradation process of rolling bearings by analyzing global information. The final prediction for rolling bearings' RUL has been successfully attained. To underline the excellence of the method presented in this paper, a comparative analysis was performed with existing methods, such as Convolutional Neural Network (CNN), Gate Recurrent Unit (GRU), and Temporal Convolutional Network (TCN). The results highlight that the model designed in this paper surpasses other existing methods in predicting the RUL of rolling bearings, demonstrating superior prediction accuracy and robust generalization capability.

show abstract

A deep learning based health indicator construction and fault prognosis with uncertainty quantification for rolling bearings

Cited by 13 publications

References 45 publications

Construction health indicator using physically-informed 1D-WGAN-GP joint attention LSTM-DenseNet method

Construction health indicator using physically-informed 1D-WGAN-GP joint attention LSTM-DenseNet method

Bayesian Fusion of Degradation and Failure Time Data for Reliability Assessment of Industrial Equipment Considering Individual Differences

Remaining useful life prediction of rolling bearings based on TCN-MSA

Contact Info

Product

Resources

About