Multiple degradation mode analysis via gated recurrent unit mode recognizer and life predictors for complex equipment

Luo, Qinyuan; Chang, Yanhai; Chen, Jinglong; Jing, Hongjie; Lv, Haixin

doi:10.1016/j.compind.2020.103332

Cited by 21 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some research endeavors are directed toward health management and quality prediction, seeking to mitigate quality-related risks through the application of systematic quality management methods. Luo et al (2020) propose a novel remaining useful life (RUL) prediction method to predict and manage the health status of the equipment and ensure the reliability and safety of industrial complex equipment. Dinis et al (2022) explore the integration of forecasting capabilities in a tool for maintenance capacity planning of complex product systems (CoPS).…”

Section: Literature Reviewmentioning

confidence: 99%

A novel quality risk evaluation framework for complex equipment development integrating PHFS-QFD and grey clustering

Wang,

Wang

et al. 2023

View full text Add to dashboard Cite

PurposeThe purpose of this research is to provide a theoretical framework for complex equipment quality risk evaluation. The primary aim of the framework is to enhance the ability to identify risks and improve risk control efficiency during the development phase.Design/methodology/approachA novel framework for quality risk evaluation in complex equipment is proposed, which integrates probabilistic hesitant fuzzy set-quality function deployment (PHFS-QFD) and grey clustering. PHFS-QFD is applied to identify the quality risk factors, and grey clustering is used to evaluate quality risks in cases of poor quality information during the development stage. The unfolding function of QFD is applied to simplify complex evaluation problems.FindingsThe methodology presents an innovative approach to quality risk evaluation for complex equipment development. The case analysis demonstrates that this method can efficiently evaluate the quality risks for aircraft development and systematically trace back the risk factors through hierarchical relationships. In comparison to traditional failure mode and effects analysis methods for quality risk assessment, this approach exhibits superior effectiveness and reliability in managing quality risks for complex equipment development.Originality/valueThis study contributes to the field by introducing a novel theoretical framework that combines PHFS-QFD and grey clustering. The integration of these approaches significantly improves the quality risk evaluation process for complex equipment development, overcoming challenges related to data scarcity and simplifying the assessment of intricate systems.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A novel quality risk evaluation framework for complex equipment development integrating PHFS-QFD and grey clustering

Wang,

Wang

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Xiong et al [16] used a FM recognizer fusing a physical information FM classifier with DCNN to improve the interpretability and accuracy of the recognition model, then selected the model for RUL prediction based on the FM recognition results. Regarding the problem of feature multi-labeling caused by different rate decay, Luo et al [17] first analyzed the degradation mode and then used prediction factors to predict RUL under specific modes. While these methods take care of modeling for different FMs, they neglect the fact that different FMs need to be inputted separately by selecting windows of different lengths to make full use of the condition monitoring data.…”

Section: Introductionmentioning

confidence: 99%

Remaining useful life prediction of mechanical equipment based on time-series auto-correlation decomposition and CNN

Hu,

Fu,

Zhong

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Remaining Useful Life (RUL) prediction can provide critical information for complex equipment Health States (HS) assessment. Historical long-term HS degradation trends and current short-term HS changes are two key factors affecting RUL prediction. However, most existing deep learning-based RUL prediction methods only consider learning short-term HS change features but ignore learning long-term HS degradation trend features, which limits to improvement of RUL prediction performance. To address this problem, this paper develops a RUL prediction framework based on a combination of Time-Series Auto-Correlation Decomposition (TSACD) and Convolutional Neural Network (CNN), which can learn both long-term and short-term features of mechanical equipment, so that achieves more robust and accurate RUL prediction. First, a novel time-series Auto-Correlation decomposition method is proposed to extract historical long-term features from collected long-term monitoring data. The advantage of TSACD is to highlight the true signal by reinforcing periodic features through Auto-Correlation mechanism and to separate pure trend components using a deep time-series decomposition architecture. Second, the long-term features are mapped to the same space as the short-term HS monitoring data using a group linear layer, which is intended to be aligned and fused with short-term monitoring data. Third, the fused features are fed into a CNN for RUL prediction. Finally, a series of comparison experiments on C-MAPSS dataset validate the outstanding prognostic performance of the proposed method. The experimental results show that the proposed method outperforms the other 16 state-of-the-art RUL prediction methods.

show abstract

“…The latest research trend is employing deep learning technologies, particularly CNN and Recurrent Neural Networks (RNN) (Han et al, 2021), to process cable data, aiming to enhance prediction accuracy and robustness. The application of deep learning in cable equipment's lifespan prediction and health status assessment mainly encompasses Deep Belief Networks (DBN) (Peng et al, 2019), Long Short-Term Memory networks (LSTM) (Zhang et al, 2018), Gated Recurrent Units (GRU) (Luo et al, 2020), CNN, Graph Neural Networks (GNN) (Kong et al, 2022), and Transfer Learning (TL) (Zhang et al, 2021). These cutting-edge studies are continually advancing the monitoring and lifespan prediction technologies for cable equipment.…”

mentioning

confidence: 99%

Evaluating and forecasting methods for assessing the health status of cables under the load of large-scale electric vehicle charging

Lei,

Rufeng,

Baofeng

et al. 2024

Front. Energy Res.

View full text Add to dashboard Cite

The assessment of the health status and prediction of the lifespan of cable equipment are critical for ensuring the stability and efficiency of the power grid. This paper develops a temperature-current-capacity-life calculation model for cables, considering the fast and slow charging demands of electric vehicles (EVs). Analyses under scenarios of rapid and slow charging demands are conducted, introducing a cable health index and establishing a health status assessment framework based on this index. The framework accounts for various factors leading to cable faults, offering a comprehensive evaluation of the health status of cables with different fault rates. Building upon this, a prediction method using the Fire Hawk Optimization (FHO) Algorithm and Convolutional Neural Network (CNN) is proposed. This method enhances performance by optimizing the hyperparameters of Bidirectional Gated Recurrent Unit (BiGRU) through FHO, effectively searching and determining the optimal hyperparameter configuration. The impact of different scenarios and varying EV penetration rates on cable temperature is analyzed through case studies, facilitating the assessment and prediction of health status.

show abstract

Multiple degradation mode analysis via gated recurrent unit mode recognizer and life predictors for complex equipment

Cited by 21 publications

References 23 publications

A novel quality risk evaluation framework for complex equipment development integrating PHFS-QFD and grey clustering

A novel quality risk evaluation framework for complex equipment development integrating PHFS-QFD and grey clustering

Remaining useful life prediction of mechanical equipment based on time-series auto-correlation decomposition and CNN

Evaluating and forecasting methods for assessing the health status of cables under the load of large-scale electric vehicle charging

Contact Info

Product

Resources

About