{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:13:31Z","timestamp":1777706011709,"version":"3.51.4"},"reference-count":32,"publisher":"SAGE Publications","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2023,7,2]]},"abstract":"<jats:p>Modern industrial processes often have nonlinearity, multivariate, time-delay, and measurement outliers, which make accurate data-driven modeling of key performance indicators difficult. To address these issues, a robust and regularized long short-term memory (LSTM) neural network for soft sensors in complex industrial processes was proposed. First, a conventional LSTM architecture was used as the basic model to deal with nonlinearity and time delay. Thereafter, a novel LSTM loss function that combines the excellent resistance to outliers of Huber M-Loss with the superior model reduction capability of \u21131 regularization was designed. Subsequently, a backpropagation through time training algorithm for the proposed LSTM was developed, including the chain derivative calculation and updating formulas. The adaptive moment estimation was applied to perform the gradient update, while the grid search and moving window cross-validation were used to find the optimal hyperparameters. Finally, nonlinear artificial datasets with time series and outliers, as well as an industrial dataset of a desulfurization process, were applied to investigate the performance of the proposed soft sensor. Simulation results show that the proposed algorithm outperforms other state-of-the-art soft sensors in terms of predictive accuracy and training time. The causal relationship of the data-driven soft sensor trained by the proposed algorithm is consistent with the field operation and chemical reactions of the desulfurization process.<\/jats:p>","DOI":"10.3233\/jifs-224557","type":"journal-article","created":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T12:28:07Z","timestamp":1682425687000},"page":"323-343","source":"Crossref","is-referenced-by-count":4,"title":["A new regularized and robust LSTM learning algorithm for industrial soft sensors"],"prefix":"10.1177","volume":"45","author":[{"given":"Lei","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Information and Automation Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junmei","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Information and Automation Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Information and Automation Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"},{"name":"State Key Laboratory of Process Automation in Ming & Metallurgy, Beijing, China"},{"name":"Beijing Key Laboratory of Process Automation in Ming & Metallurgy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"issue":"9","key":"10.3233\/JIFS-224557_ref1","doi-asserted-by":"crossref","first-page":"5853","DOI":"10.1109\/TII.2021.3053128","article-title":"A survey on deep learning for data-driven soft sensors","volume":"17","author":"Sun","year":"2021","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"11\u201312","key":"10.3233\/JIFS-224557_ref2","doi-asserted-by":"crossref","first-page":"2350","DOI":"10.1016\/j.applthermaleng.2008.11.022","article-title":"A study on thermal stress deformation using analytical methods based on the temperature distribution of storage material in a rotary air-preheater","volume":"29","author":"Wang","year":"2009","journal-title":"Applied Thermal Engineering"},{"issue":"9","key":"10.3233\/JIFS-224557_ref3","doi-asserted-by":"crossref","first-page":"5859","DOI":"10.1109\/TII.2021.3131471","article-title":"A data-driven self-supervised lstm-deepfm model for industrial soft sensor","volume":"18","author":"Ren","year":"2021","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"1","key":"10.3233\/JIFS-224557_ref4","doi-asserted-by":"crossref","first-page":"015102","DOI":"10.1088\/1361-6501\/ac2ca4","article-title":"Mixed kernel principal component weighted regression based on just-in-time learning for soft sensor modeling","volume":"33","author":"Yin","year":"2021","journal-title":"Measurement Science and Technology"},{"key":"10.3233\/JIFS-224557_ref5","first-page":"1","article-title":"ANFIS soft sensing model of SMB chromatographic separation process based on new adaptive population evolution particle swarm optimization algorithm","author":"Wang","year":"2021","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"issue":"9","key":"10.3233\/JIFS-224557_ref6","doi-asserted-by":"crossref","first-page":"1637","DOI":"10.1016\/j.jprocont.2012.06.017","article-title":"An inferential modeling method using enumerative PLS based nonnegative garrote regression","volume":"22","author":"Pan","year":"2012","journal-title":"Journal of Process Control"},{"issue":"5","key":"10.3233\/JIFS-224557_ref7","doi-asserted-by":"crossref","first-page":"10099","DOI":"10.3233\/JIFS-202812","article-title":"A combined model based on feature selection and support vector machine for PM2. 5 prediction","volume":"40","author":"Lai","year":"2021","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"issue":"1","key":"10.3233\/JIFS-224557_ref8","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1007\/s10462-021-10038-8","article-title":"Artificial neural networks for water quality soft-sensing in wastewater treatment: a review","volume":"55","author":"Wang","year":"2022","journal-title":"Artificial Intelligence Review"},{"issue":"9","key":"10.3233\/JIFS-224557_ref9","doi-asserted-by":"crossref","first-page":"3939","DOI":"10.1007\/s00521-020-05488-0","article-title":"MLP neural network-based regional logistics demand prediction","volume":"33","author":"Guo","year":"2021","journal-title":"Neural Computing and Applications"},{"issue":"4","key":"10.3233\/JIFS-224557_ref10","doi-asserted-by":"crossref","first-page":"5641","DOI":"10.3233\/JIFS-190861","article-title":"Layer-wise learning based stochastic gradient descent method for the optimization of deep convolutional neural network","volume":"37","author":"Zheng","year":"2019","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"issue":"10","key":"10.3233\/JIFS-224557_ref11","doi-asserted-by":"crossref","first-page":"3466","DOI":"10.1109\/TCYB.2017.2734043","article-title":"Stochastic configuration networks: fundamentals and algorithms","volume":"47","author":"Wang","year":"2017","journal-title":"IEEE Transactions on Cybernetic"},{"key":"10.3233\/JIFS-224557_ref12","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1016\/j.renene.2021.12.056","article-title":"Convolutional neural network fault classification based on time-series analysis for benchmark wind turbine machine","volume":"185","author":"Rahimilarki","year":"2022","journal-title":"Renewable Energy"},{"issue":"6","key":"10.3233\/JIFS-224557_ref13","doi-asserted-by":"crossref","first-page":"2749","DOI":"10.3233\/IFS-151552","article-title":"Z-source inverter fed induction motor drive control using particle swarm optimization recurrent neural network","volume":"28","author":"Selva","year":"2015","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"issue":"5","key":"10.3233\/JIFS-224557_ref14","doi-asserted-by":"crossref","first-page":"4404","DOI":"10.1109\/TIE.2020.2984443","article-title":"Deep learning with spatiotemporal attention-based LSTM for industrial soft sensor model development","volume":"68","author":"Yuan","year":"2020","journal-title":"IEEE Transactions on Industrial Electronics"},{"key":"10.3233\/JIFS-224557_ref15","doi-asserted-by":"crossref","first-page":"104964","DOI":"10.1016\/j.compag.2019.104964","article-title":"Attention-based recurrent neural networks for accurate short-term and long-term dissolved oxygen prediction","volume":"165","author":"Liu","year":"2019","journal-title":"Computers and Electronics in Agriculture"},{"issue":"1","key":"10.3233\/JIFS-224557_ref16","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1177\/0142331220932390","article-title":"LSTM-based soft sensor design for oxygen content of flue gas in coal-fired power plant","volume":"43","author":"Pan","year":"2021","journal-title":"Transactions of the Institute of Measurement and Control"},{"key":"10.3233\/JIFS-224557_ref17","first-page":"1","article-title":"Novel stacked input-enhanced supervised autoencoder integrated with gated recurrent unit for soft sensing","volume":"71","author":"Tian","year":"2022","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"issue":"19","key":"10.3233\/JIFS-224557_ref18","doi-asserted-by":"crossref","first-page":"1861","DOI":"10.1109\/JSEN.2022.3199474","article-title":"A novel bidirectional gated recurrent unit-based soft sensor modeling framework for quality prediction in manufacturing processes","volume":"22","author":"Ma","year":"2022","journal-title":"IEEE Sensors Journal"},{"key":"10.3233\/JIFS-224557_ref19","first-page":"30","article-title":"Attention is all you need.","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"3","key":"10.3233\/JIFS-224557_ref20","doi-asserted-by":"crossref","first-page":"1521","DOI":"10.1109\/TII.2021.3086798","article-title":"Novel transformer based on gated convolutional neural network for dynamic soft sensor modeling of industrial processes","volume":"18","author":"Geng","year":"2021","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"1","key":"10.3233\/JIFS-224557_ref21","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the LASSO","volume":"58","author":"Tibshirani","year":"1996","journal-title":"Journal of the Royal Statistical Society: Series B (Methodological)"},{"issue":"6","key":"10.3233\/JIFS-224557_ref22","doi-asserted-by":"crossref","first-page":"1386","DOI":"10.1109\/TNNLS.2016.2542866","article-title":"Design and application of a variable selection method for multilayer perceptron neural network with LASSO","volume":"28","author":"Sun","year":"2016","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"7","key":"10.3233\/JIFS-224557_ref23","doi-asserted-by":"crossref","first-page":"3972","DOI":"10.1109\/TIM.2019.2947126","article-title":"A data-driven soft sensor based on multilayer perceptron neural network with a double LASSO approach","volume":"69","author":"Fan","year":"2019","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.3233\/JIFS-224557_ref24","first-page":"1","article-title":"Nonlinear dynamic soft-sensing modeling of NOx emission of a selective catalytic reduction denitration system","volume":"71","author":"Wu","year":"2022","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"issue":"2","key":"10.3233\/JIFS-224557_ref25","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1504\/IJRAPIDM.2009.029380","article-title":"A comparative analysis of predictive data mining techniques","volume":"1","author":"Li","year":"2009","journal-title":"International Journal of Rapid Manufacturing"},{"issue":"2","key":"10.3233\/JIFS-224557_ref26","doi-asserted-by":"crossref","first-page":"1630","DOI":"10.1007\/s10489-021-02473-5","article-title":"A hybrid robust system considering outliers for electric load series forecasting","volume":"52","author":"Yang","year":"2022","journal-title":"Applied Intelligence"},{"key":"10.3233\/JIFS-224557_ref27","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.ins.2018.09.026","article-title":"Robust stochastic configuration networks with maximum correntropy criterion for uncertain data regression","volume":"473","author":"Li","year":"2019","journal-title":"Information Sciences"},{"key":"10.3233\/JIFS-224557_ref28","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.knosys.2017.06.009","article-title":"Least absolute deviation-based robust support vector regression","volume":"131","author":"Chen","year":"2017","journal-title":"Knowledge-Based Systems"},{"key":"10.3233\/JIFS-224557_ref29","unstructured":"Kingma D.P. and Ba J. , Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"10.3233\/JIFS-224557_ref30","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/j.ins.2011.12.028","article-title":"On the use of cross-validation for time series predictor evaluation","volume":"191","author":"Bergmeir","year":"2012","journal-title":"Information Sciences"},{"issue":"1","key":"10.3233\/JIFS-224557_ref31","first-page":"1","article-title":"Multivariate adaptive regression splines","volume":"19","author":"Friedman","year":"1991","journal-title":"The Annals of Statistics"},{"issue":"3","key":"10.3233\/JIFS-224557_ref32","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1109\/TEMC.2019.2916837","article-title":"Prediction of MRI RF exposure for implantable plate devices using artificial neural network","volume":"62","author":"Zheng","year":"2019","journal-title":"IEEE Transactions on Electromagnetic Compatibility"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-224557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:45:48Z","timestamp":1777455948000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-224557"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,2]]},"references-count":32,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.3233\/jifs-224557","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,2]]}}}