An ensemble approach for enhancing generalization and extendibility of deep learning facilitated by transfer learning: principle and application in curing monitoring

Zhu, Jianjian1,2; Su, Zhongqing1,2; Han, Zhibin3; Lan, Zifeng4; Wang, Qingqing1,6; Ho, Mabel Mei-po5

2023-11-01

10.1088/1361-665X/acfde0

SMART MATERIALS AND STRUCTURES   影响因子和分区

0964-1726

1361-665X

Machine learning (ML) and deep learning (DL) have exhibited significant advantages compared to conventional data analysis methods. However, the limitations of poor generalization and extendibility impede the broader application of these methods beyond specific learning tasks. To address this challenge, this study proposes a transfer learning-based ensemble approach called SMART. This approach incorporates synthetic minority oversampling technique, average reinforced interpolation, series data imaging, and fine-tuning. To validate the effectiveness of SMART, we conduct experiments on curing monitoring of polymeric composites and construct a hybrid dataset with highly heterogeneous features. We compare the performance of SMART with exemplary ML algorithms using conventional evaluation indicators, including Accuracy, Precision, Recall, and F1-score. The experimental results demonstrate that the SMART approach exhibits superior generalization capacity and extendibility, achieving indicator scores above 0.9900 in new scenarios. These findings suggest that the proposed SMART approach has the potential to break through the limitations of conventional ML and DL models, enabling wider applications in the industrial sectors.

machine learning deep learning transfer learning polymetric composites curing monitoring

SCI ; EI

英语

其他

Dr Jianjian Zhu acknowledges the support from the Young Scientists Fund of the National Natural Science Foundation of China (Grant No. 52205171). Professor Zhongqing Su acknowledges the support from the Hong Kong Research Grants Council via General Researc[52205171] ; Young Scientists Fund of the National Natural Science Foundation of China["15202820","15204419"]

Instruments & Instrumentation ; Materials Science

Instruments & Instrumentation ; Materials Science, Multidisciplinary

WOS:001081583700001

IOP Publishing Ltd

20234515021704

Deep learning ; Learning systems

Ergonomics and Human Factors Engineering:461.4 ; Chemical Reactions:802.2

Web of Science

1.Hong Kong Polytech Univ, Dept Mech Engn, Kowloon, Hong Kong, Peoples R China
2.Hong Kong Polytech Univ, Shenzhen Res Inst, Shenzhen 518057, Peoples R China
3.Chinese Univ Hong Kong, Dept Mech & Automat Engn, Hong Kong, Peoples R China
4.Univ Tokyo, Sch Engn, Tokyo, Japan
5.Hong Kong Polytech Univ, Ind Ctr, Kowloon, Hong Kong, Peoples R China
6.Southern Univ Sci & Technol, Sch Syst Design & Intelligent Mfg, Shenzhen 518055, Peoples R China

Zhu, Jianjian,Su, Zhongqing,Han, Zhibin,et al. An ensemble approach for enhancing generalization and extendibility of deep learning facilitated by transfer learning: principle and application in curing monitoring[J]. SMART MATERIALS AND STRUCTURES,2023,32(11).

Zhu, Jianjian,Su, Zhongqing,Han, Zhibin,Lan, Zifeng,Wang, Qingqing,&Ho, Mabel Mei-po.(2023).An ensemble approach for enhancing generalization and extendibility of deep learning facilitated by transfer learning: principle and application in curing monitoring.SMART MATERIALS AND STRUCTURES,32(11).

Zhu, Jianjian,et al."An ensemble approach for enhancing generalization and extendibility of deep learning facilitated by transfer learning: principle and application in curing monitoring".SMART MATERIALS AND STRUCTURES 32.11(2023).