File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.microrel.2023.115027
- Scopus: eid_2-s2.0-85162747027
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Article: Lifetime prediction of electronic devices based on the P-stacking machine learning model
| Title | Lifetime prediction of electronic devices based on the P-stacking machine learning model |
|---|---|
| Authors | |
| Keywords | IGBT device Lifetime prediction Lithium-ion battery Machine learning Pearson correlation analysis Stacking algorithm |
| Issue Date | 1-Jul-2024 |
| Publisher | Elsevier |
| Citation | Microelectronics Reliability, 2023, v. 146 How to Cite? |
| Abstract | Nowadays the data-driven artificial intelligence (AI) and machine learning (ML) provide novel approaches for the effective lifetime prediction of the electronic devices with complicated mechanisms and multiple controlling factors. However, the existing ML prediction models cannot process both high accuracy and high efficiency at the meantime. To address this problem, this paper proposes the new P-Stacking ML algorithm model, which combines the Pearson correlation analysis and the Stacking multi-model fusion. The Pearson correlation analysis is first applied to select the multiple base learner models with weak correlations for the following Stacking multi-model fusion. Two neutral network layers are built to perform the Stacking algorithm. In this work, two distinct types of electronic devices are utilized to verify the effectiveness of the P-Stacking ML model, which are the IGBT devices and the lithium-ion batteries respectively. For the IGBT lifetime prediction, the results have shown that compared with the long-term and short-term memory neural network (LSTM) model in the previous literature, the mean square error (MSE) of the P-Stacking ML model is improved by 6 %, and the average model training time is reduced by 90 %. Moreover, for the lithium batteries, the lifetime prediction accuracy of the P-Stacking model is increased by 65 %, and the training time is decreased by 90 %. The results demonstrated that the P-Stacking ML model can significantly improve both the prediction accuracy and efficiency simultaneously. |
| Persistent Identifier | http://hdl.handle.net/10722/344326 |
| ISSN | 2023 Impact Factor: 1.6 2023 SCImago Journal Rankings: 0.394 |
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Wang, Fei | - |
| dc.contributor.author | Yang, Ye | - |
| dc.contributor.author | Huang, Tao | - |
| dc.contributor.author | Xu Yang | - |
| dc.date.accessioned | 2024-07-24T13:50:45Z | - |
| dc.date.available | 2024-07-24T13:50:45Z | - |
| dc.date.issued | 2024-07-01 | - |
| dc.identifier.citation | Microelectronics Reliability, 2023, v. 146 | - |
| dc.identifier.issn | 0026-2714 | - |
| dc.identifier.uri | http://hdl.handle.net/10722/344326 | - |
| dc.description.abstract | <p>Nowadays the data-driven <a href="https://www.sciencedirect.com/topics/computer-science/artificial-intelligence" title="Learn more about artificial intelligence from ScienceDirect's AI-generated Topic Pages">artificial intelligence</a> (AI) and <a href="https://www.sciencedirect.com/topics/computer-science/machine-learning" title="Learn more about machine learning from ScienceDirect's AI-generated Topic Pages">machine learning</a> (ML) provide novel approaches for the effective lifetime prediction of the electronic devices with complicated mechanisms and multiple controlling factors. However, the existing ML prediction models cannot process both high accuracy and high efficiency at the meantime. To address this problem, this paper proposes the new P-Stacking <a href="https://www.sciencedirect.com/topics/engineering/machine-learning-algorithm" title="Learn more about ML algorithm from ScienceDirect's AI-generated Topic Pages">ML algorithm</a> model, which combines the <a href="https://www.sciencedirect.com/topics/computer-science/pearson-correlation" title="Learn more about Pearson correlation from ScienceDirect's AI-generated Topic Pages">Pearson correlation</a> analysis and the Stacking multi-model fusion. The <a href="https://www.sciencedirect.com/topics/engineering/pearsons-linear-correlation-coefficient" title="Learn more about Pearson from ScienceDirect's AI-generated Topic Pages">Pearson</a> correlation analysis is first applied to select the multiple base learner models with weak correlations for the following Stacking multi-model fusion. Two neutral network layers are built to perform the Stacking algorithm. In this work, two distinct types of electronic devices are utilized to verify the effectiveness of the P-Stacking ML model, which are the <a href="https://www.sciencedirect.com/topics/materials-science/bipolar-transistor" title="Learn more about IGBT from ScienceDirect's AI-generated Topic Pages">IGBT</a> devices and the lithium-ion batteries respectively. For the <a href="https://www.sciencedirect.com/topics/engineering/insulated-gate-bipolar-transistor" title="Learn more about IGBT from ScienceDirect's AI-generated Topic Pages">IGBT</a> lifetime prediction, the results have shown that compared with the long-term and short-term memory <a href="https://www.sciencedirect.com/topics/computer-science/neural-network" title="Learn more about neural network from ScienceDirect's AI-generated Topic Pages">neural network</a> (LSTM) model in the previous literature, the <a href="https://www.sciencedirect.com/topics/engineering/mean-square-error" title="Learn more about mean square error from ScienceDirect's AI-generated Topic Pages">mean square error</a> (MSE) of the P-Stacking ML model is improved by 6 %, and the average model training time is reduced by 90 %. Moreover, for the <a href="https://www.sciencedirect.com/topics/engineering/lithium-battery" title="Learn more about lithium batteries from ScienceDirect's AI-generated Topic Pages">lithium batteries</a>, the lifetime prediction accuracy of the P-Stacking model is increased by 65 %, and the training time is decreased by 90 %. The results demonstrated that the P-Stacking ML model can significantly improve both the prediction accuracy and efficiency simultaneously.<br></p> | - |
| dc.language | eng | - |
| dc.publisher | Elsevier | - |
| dc.relation.ispartof | Microelectronics Reliability | - |
| dc.rights | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. | - |
| dc.subject | IGBT device | - |
| dc.subject | Lifetime prediction | - |
| dc.subject | Lithium-ion battery | - |
| dc.subject | Machine learning | - |
| dc.subject | Pearson correlation analysis | - |
| dc.subject | Stacking algorithm | - |
| dc.title | Lifetime prediction of electronic devices based on the P-stacking machine learning model | - |
| dc.type | Article | - |
| dc.identifier.doi | 10.1016/j.microrel.2023.115027 | - |
| dc.identifier.scopus | eid_2-s2.0-85162747027 | - |
| dc.identifier.volume | 146 | - |
| dc.identifier.eissn | 1872-941X | - |
| dc.identifier.issnl | 0026-2714 | - |