Explainable AI in thermal modelling enhancing precision in thermal gradient monitoring for additive manufacturing using LSTM networks

IF 5.1 3区工程技术 Q2 ENERGY & FUELS

Thermal Science and Engineering Progress Pub Date : 2025-03-01 DOI:10.1016/j.tsep.2025.103465

Ajmeera Kiran , Harish Kumar , S. Sivanandam , P.Gururama Senthilvel , R.V.S. Lalitha , C.S. Preetham Reddy

{"title":"Explainable AI in thermal modelling enhancing precision in thermal gradient monitoring for additive manufacturing using LSTM networks","authors":"Ajmeera Kiran , Harish Kumar , S. Sivanandam , P.Gururama Senthilvel , R.V.S. Lalitha , C.S. Preetham Reddy","doi":"10.1016/j.tsep.2025.103465","DOIUrl":null,"url":null,"abstract":"<div><div>The paper introduces an unprecedented technique for enhancing the measurement accuracy of thermal gradients in additive manufacturing by applying Explainable Artificial Intelligence (XAI) combined with Long Short-Term Memory (LSTM) networks. Temperature control during fabricating of thermoplastic and thermosetting polymer composites remains fundamental since it dictates the resulting material properties, structural integrity, and layer bonding. Our LSTM model predicts temperature changes during printing operations, providing stable manufacturing processes by reducing common defects, including warping deformation delamination and inconsistent curing. The framework now includes Layer-wise Relevance Propagation (LRP) and SHapley Additive exPlanations (SHAP) techniques to analyse crucial elements affecting temperature distribution.</div><div>The thermal model shows 0.183 °C MAE and 0.224 °C RMSE values, delivering 46.5 % better precision than previous thermal modelling approaches. Evaluation tests report system adjustments to take place after 86 ms during thermal perturbations and reach full stabilisation by 2.3 s. Its 97.3 % prediction accuracy rate and decision consistency make it dependable for optimal temperature processing control. The research creates a connection between automated thermal modelling and manufacturing through additive technology which leads to better process management together with material efficiency as well as environmentally responsible creation of polymer parts. The introduced framework shows great promise for use in the aerospace, automotive and biomedical sectors of additive manufacturing, which demand accurate thermal control.</div></div>","PeriodicalId":23062,"journal":{"name":"Thermal Science and Engineering Progress","volume":"60 ","pages":"Article 103465"},"PeriodicalIF":5.1000,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Thermal Science and Engineering Progress","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2451904925002550","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENERGY & FUELS","Score":null,"Total":0}

引用次数: 0

Abstract

The paper introduces an unprecedented technique for enhancing the measurement accuracy of thermal gradients in additive manufacturing by applying Explainable Artificial Intelligence (XAI) combined with Long Short-Term Memory (LSTM) networks. Temperature control during fabricating of thermoplastic and thermosetting polymer composites remains fundamental since it dictates the resulting material properties, structural integrity, and layer bonding. Our LSTM model predicts temperature changes during printing operations, providing stable manufacturing processes by reducing common defects, including warping deformation delamination and inconsistent curing. The framework now includes Layer-wise Relevance Propagation (LRP) and SHapley Additive exPlanations (SHAP) techniques to analyse crucial elements affecting temperature distribution.

The thermal model shows 0.183 °C MAE and 0.224 °C RMSE values, delivering 46.5 % better precision than previous thermal modelling approaches. Evaluation tests report system adjustments to take place after 86 ms during thermal perturbations and reach full stabilisation by 2.3 s. Its 97.3 % prediction accuracy rate and decision consistency make it dependable for optimal temperature processing control. The research creates a connection between automated thermal modelling and manufacturing through additive technology which leads to better process management together with material efficiency as well as environmentally responsible creation of polymer parts. The introduced framework shows great promise for use in the aerospace, automotive and biomedical sectors of additive manufacturing, which demand accurate thermal control.

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Thermal Science and Engineering Progress Chemical Engineering-Fluid Flow and Transfer Processes

CiteScore

7.20

自引率

10.40%

发文量

327

审稿时长

41 days

期刊介绍： Thermal Science and Engineering Progress (TSEP) publishes original, high-quality research articles that span activities ranging from fundamental scientific research and discussion of the more controversial thermodynamic theories, to developments in thermal engineering that are in many instances examples of the way scientists and engineers are addressing the challenges facing a growing population – smart cities and global warming – maximising thermodynamic efficiencies and minimising all heat losses. It is intended that these will be of current relevance and interest to industry, academia and other practitioners. It is evident that many specialised journals in thermal and, to some extent, in fluid disciplines tend to focus on topics that can be classified as fundamental in nature, or are ‘applied’ and near-market. Thermal Science and Engineering Progress will bridge the gap between these two areas, allowing authors to make an easy choice, should they or a journal editor feel that their papers are ‘out of scope’ when considering other journals. The range of topics covered by Thermal Science and Engineering Progress addresses the rapid rate of development being made in thermal transfer processes as they affect traditional fields, and important growth in the topical research areas of aerospace, thermal biological and medical systems, electronics and nano-technologies, renewable energy systems, food production (including agriculture), and the need to minimise man-made thermal impacts on climate change. Review articles on appropriate topics for TSEP are encouraged, although until TSEP is fully established, these will be limited in number. Before submitting such articles, please contact one of the Editors, or a member of the Editorial Advisory Board with an outline of your proposal and your expertise in the area of your review.