Deep Learning-Based Remaining Useful Life Prediction for Mechatronical Components

Abstract submission deadline

closed (15 November 2023)

Manuscript submission deadline

closed (15 January 2024)

Viewed by

10328

Topic Information

Dear Colleagues,

Typical mechanical and electronic (mechatronical) components, including gearboxes, bearings, motors, and principal axes, are used extensively in a variety of engineering fields. Due to their harsh operating conditions, mechatronical components are often subject to faults, such as cracking, wear, pitting, spalling, fracturing, looseness, friction between rotor and stator, broken bars, and short circuiting, etc., resulting in huge economic losses and serious injuries or even casualties. Consequently, it is of great concern to intelligently predict the remaining useful life (RUL) of key mechatronical components to ensure that the equipment's reliable operation and making optimal maintenance decisions.

With the rapid development of industrial big data and artificial intelligence technology, deep learning-based fault prognosis and diagnosis methods have attracted a lot of attention, as they can greatly reduce the interference of expertise and enhance diagnostic efficiency. When there is a significant amount of annotated training data, deep learning (DL) models demonstrate appealing performance. However, high-quality labeled life-cycle data are still rare in actual engineering practice, and various monitoring data from different but similar components and the varied working conditions have prominent distribution discrepancy; thus, DL-based RUL prediction methods still face great challenges. Aiming to address these issues, transfer learning has been proposed to improve the accuracy and generalization performance of RUL prediction, becoming a research hotspot.

In order to facilitate the development of intelligent RUL prediction, we are organizing a Topic titled “Deep Learning-Based Remaining Useful Life Prediction for Mechatronical Components”. The Topic will be published in the journals Machines, Applied Sciences, Sensors, Electronics and Chips. This topic hopes to attract studies including health indicator construction, remaining useful life (RUL) prediction for mechanical and electronic components, transfer RUL prediction, interpretable deep learning RUL prediction models, federal learning-based RUL prediction, etc.

Topics mainly include:

• Supervised health indicator construction;
• Unsupervised health indicator construction;
• Time series prediction models based on recurrent neural works;
• RUL prediction based on pattern recognition;
• Transfer RUL prediction based on domain adaptation;
• Interpretable deep learning models for RUL prediction;
• Federal learning-based RUL prediction.

Participating Journals

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Applied Sciences applsci	2.5	5.3	2011	18.4 Days	CHF 2400
Chips chips	-	-	2022	22.2 Days	CHF 1000
Electronics electronics	2.6	5.3	2012	16.4 Days	CHF 2400
Machines machines	2.1	3.0	2013	15.5 Days	CHF 2400
Sensors sensors	3.4	7.3	2001	18.6 Days	CHF 2600

Preprints.org is a multidisciplinary platform offering a preprint service designed to facilitate the early sharing of your research. It supports and empowers your research journey from the very beginning.

MDPI Topics is collaborating with Preprints.org and has established a direct connection between MDPI journals and the platform. Authors are encouraged to take advantage of this opportunity by posting their preprints at Preprints.org prior to publication:

1. Share your research immediately: disseminate your ideas prior to publication and establish priority for your work.
2. Safeguard your intellectual contribution: Protect your ideas with a time-stamped preprint that serves as proof of your research timeline.
3. Boost visibility and impact: Increase the reach and influence of your research by making it accessible to a global audience.
4. Gain early feedback: Receive valuable input and insights from peers before submitting to a journal.
5. Ensure broad indexing: Web of Science (Preprint Citation Index), Google Scholar, Crossref, SHARE, PrePubMed, Scilit and Europe PMC.

Published Papers (4 papers)

Order results

Content type Publication Date

Result details

Normal Extended Compact

Journals

All Applied Sciences Chips Electronics Machines Sensors

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

Error

Oops... you haven't selected anything for export.

Ok

clear

18 pages, 2984 KiB  

Open AccessArticle

Failure Identification Method of Sound Signal of Belt Conveyor Rollers under Strong Noise Environment

by Yuxuan Ban, Chunyang Liu, Fang Yang, Nan Guo, Xiqiang Ma, Xin Sui and Yan Huang

Electronics 2024, 13(1), 34; https://doi.org/10.3390/electronics13010034 - 20 Dec 2023

Cited by 8 | Viewed by 1487

Abstract

Accurately extracting faulty sound signals from belt conveyor rollers within the high-noise environment of coal mine operations presents a formidable challenge. To address this issue, this study introduces an innovative fault diagnosis method that merges the variational modal de-composition (VMD) model with the [...] Read more.

Accurately extracting faulty sound signals from belt conveyor rollers within the high-noise environment of coal mine operations presents a formidable challenge. To address this issue, this study introduces an innovative fault diagnosis method that merges the variational modal de-composition (VMD) model with the Swin Transformer deep learning network model. First, the study employed the adaptive VMD method to eliminate intense noise from the original signal of the rollers, while also assessing the reconstruction accuracy of the VMD signal across different modal components. Subsequently, we delved into the impact of the parameter structure of the Swin Transformer network model on the fault diagnosis accuracy. Finally, the accuracy of the method was validated using a sound test dataset from the rollers. The results indicated that optimizing the K-value of the VMD method effectively reduced the noise in the reconstructed signal, and the Swin Transformer excelled in extracting both local and global features. Specifically, on the conveyor roller sound dataset, it was shown that, after the VMD reconstruction of the signal so that the highest Pearson correlation coefficient corresponded to a modal component of 3 and adjusting the parameters of the Swin Transformer coding layer, the combination of the VMD+Swin-S model achieved an accuracy of 99.36%, while the VMD+Swin-T model achieved an accuracy of 98.6%. Meanwhile, the accuracy of the VMD+Swin-S model was higher than that of the VMD + CNN model combination, with 95.4% accuracy, and the VMD+ViT model, with 97.68% accuracy. In the example application experiments, compared with other models the VMD+Swin-S model achieved the highest accuracy rate at all three speeds, with 98.67%, 98.32%, and 97.65%, respectively. Overall, this approach demonstrated high accuracy and robustness, rendering it an optimal choice for diagnosing conveyor belt roller faults within environments characterized by strong noise. Full article

(This article belongs to the Topic Deep Learning-Based Remaining Useful Life Prediction for Mechatronical Components)

►▼ Show Figures

Figure 1

22 pages, 14232 KiB  

Open AccessArticle

A Novel Method for Multistage Degradation Predicting the Remaining Useful Life of Wind Turbine Generator Bearings Based on Domain Adaptation

by Miao Tian, Xiaoming Su, Changzheng Chen and Wenjie An

Appl. Sci. 2023, 13(22), 12332; https://doi.org/10.3390/app132212332 - 15 Nov 2023

Cited by 4 | Viewed by 1342

Abstract

Predicting the remaining useful life (RUL) of wind turbine generator rolling bearings can effectively prevent damage to the transmission chain and significant economic losses resulting from sudden failures. However, the working conditions of generator bearings are variable, and the collected run-to-failure data combine [...] Read more.

Predicting the remaining useful life (RUL) of wind turbine generator rolling bearings can effectively prevent damage to the transmission chain and significant economic losses resulting from sudden failures. However, the working conditions of generator bearings are variable, and the collected run-to-failure data combine multiple working conditions, which significantly impacts the accuracy of model predictions. To solve the problem, a local enhancement temporal convolutional network with multistage degenerate distribution matching based on domain adaptation (MDA-LETCN) is proposed, extracting degradation features of wind turbine generator bearings and predicting their remaining service life in composite working conditions. This method first utilizes the local enhancement temporal convolutional network (LETCN) to extract time series features and used the K-means method for unsupervised division of the degradation status of rolling bearings. Secondly, the multistage degradation stage distribution matching (MDSDM) module is proposed to learn domain-invariant temporal features at different stages of bearing degradation under composite working conditions. Finally, the model is transferred to the target bearing using some health data that are easily available from the target bearing to solve the problem of individual differences in the degradation of generator bearings in different wind turbines. Comparative experiments were conducted using actual wind farm data, and the results showed that MDA-LETCN has high prediction accuracy. Full article

(This article belongs to the Topic Deep Learning-Based Remaining Useful Life Prediction for Mechatronical Components)

►▼ Show Figures

Figure 1

17 pages, 7013 KiB  

Open AccessArticle

Adaptively Lightweight Spatiotemporal Information-Extraction-Operator-Based DL Method for Aero-Engine RUL Prediction

by Junren Shi, Jun Gao and Sheng Xiang

Sensors 2023, 23(13), 6163; https://doi.org/10.3390/s23136163 - 5 Jul 2023

Cited by 3 | Viewed by 1524

Abstract

Accurate prediction of machine RUL plays a crucial role in reducing human casualties and economic losses, which is of significance. The ability to handle spatiotemporal information contributes to improving the prediction performance of machine RUL. However, most existing models for spatiotemporal information processing [...] Read more.

Accurate prediction of machine RUL plays a crucial role in reducing human casualties and economic losses, which is of significance. The ability to handle spatiotemporal information contributes to improving the prediction performance of machine RUL. However, most existing models for spatiotemporal information processing are not only complex in structure but also lack adaptive feature extraction capabilities. Therefore, a lightweight operator with adaptive spatiotemporal information extraction ability named Involution GRU (Inv-GRU) is proposed for aero-engine RUL prediction. Involution, the adaptive feature extraction operator, is replaced by the information connection in the gated recurrent unit to achieve adaptively spatiotemporal information extraction and reduce the parameters. Thus, Inv-GRU can well extract the degradation information of the aero-engine. Then, for the RUL prediction task, the Inv-GRU-based deep learning (DL) framework is firstly constructed, where features extracted by Inv-GRU and several human-made features are separately processed to generate health indicators (HIs) from multi-raw data of aero-engines. Finally, fully connected layers are adopted to reduce the dimension and regress RUL based on the generated HIs. By applying the Inv-GRU-based DL framework to the Commercial Modular Aero Propulsion System Simulation (C-MAPSS) datasets, successful predictions of aero-engines RUL have been achieved. Quantitative comparative experiments have demonstrated the advantage of the proposed method over other approaches in terms of both RUL prediction accuracy and computational burden. Full article

(This article belongs to the Topic Deep Learning-Based Remaining Useful Life Prediction for Mechatronical Components)

►▼ Show Figures

Figure 1

31 pages, 6838 KiB  

Open AccessArticle

Intelligent Position Controller for Unmanned Aerial Vehicles (UAV) Based on Supervised Deep Learning

by Javier A. Cardenas, Uriel E. Carrero, Edgar C. Camacho and Juan M. Calderon

Machines 2023, 11(6), 606; https://doi.org/10.3390/machines11060606 - 2 Jun 2023

Cited by 4 | Viewed by 3601

Abstract

In recent years, multi-rotor UAVs have become valuable tools in several productive fields, from entertainment to agriculture and security. However, during their flight trajectory, they sometimes do not accurately perform a specific set of tasks, and the implementation of flight controllers in these [...] Read more.

In recent years, multi-rotor UAVs have become valuable tools in several productive fields, from entertainment to agriculture and security. However, during their flight trajectory, they sometimes do not accurately perform a specific set of tasks, and the implementation of flight controllers in these vehicles is required to achieve a successful performance. Therefore, this research describes the design of a flight position controller based on Deep Neural Networks and subsequent implementation for a multi-rotor UAV. Five promising Neural Network architectures are developed based on a thorough literature review, incorporating LSTM, 1-D convolutional, pooling, and fully-connected layers. A dataset is then constructed using the performance data of a PID flight controller, encompassing diverse trajectories with transient and steady-state information such as position, speed, acceleration, and motor output signals. The tuning of hyperparameters for each type of architecture is performed by applying the Hyperband algorithm. The best model obtained (LSTMCNN) consists of a combination of LSTM and CNN layers in one dimension. This architecture is compared with the PID flight controller in different scenarios employing evaluation metrics such as rise time, overshoot, steady-state error, and control effort. The findings reveal that our best models demonstrate the successful generalization of flight control tasks. While our best model is able to work with a wider operational range than the PID controller and offers step responses in the Y and X axis with $97\%$ and $98\%$ similarity, respectively, within the PID’s operational range. This outcome opens up possibilities for efficient online training of flight controllers based on Neural Networks, enabling the development of adaptable controllers tailored to specific application domains. Full article

(This article belongs to the Topic Deep Learning-Based Remaining Useful Life Prediction for Mechatronical Components)

►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

 

Error

Oops... you haven't selected anything for export.

Ok

clear

Displaying articles 1-4