[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125865-en":3,"doc-seo-125865-105":31,"detail-sidebar-cat-0-en-105":97},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},125865,1099523882367,"Hazel","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",6,"Technology","Applications of Machine Learning to Optimizing Polyolefin Manufacturing - Section 10","Applications of Machine Learning to Optimizing Polyolefin Manufacturing presents an accessible, graduate-level overview of machine learning methods tailored to chemical and polymer process optimization, with emphasis on polyolefin manufacturing. It introduces key historical context for AI/ML adoption in chemical process industries, explains core ML components and learning paradigms, and surveys supervised, unsupervised, ensemble, and deep learning approaches. The chapter also includes practical workshop-style examples covering HDPE melt index prediction, time-dependent modeling, polymer property prediction from molecular structure, and automated ML, concluding with algorithm-selection guidelines and pointers to hybrid SGML modeling.","Applications of Machine Learning to Optimizing Polyolefin Manufacturing  \nLiu, Y. A., & Sharma, N.  \nAbstract  \nThis is a preprint version of the chapter of our book-Liu, Y. A., & Sharma, N. (2023) . Integrated Process Modeling, Advanced Control and Data Analytics for Optimizing Polyolefin Manufacturing. Wiley-VCH [GmbH. lease](GmbH. lease) cite the original work [169,170] if referenced.  \nThis chapter covers the applications of machine learning (ML) to optimizing chemical and polymer processes, particularly polyolefin manufacturing. Our goal is to prepare an overview of ML for university students and faculty, and practicing engineers and scientists who are new to the field, and also for those who are knowledgeable, but wish to know the new developments and application literature in chemical and polymer processes.  \nSection 10.1 presents an introduction, beginning in Section 10.1.1 with the historical developments of artificial intelligence (AI) and machine learning (ML) in chemical process industries (CPIs), and suggests the time for actively adopting AI and ML in CPIs has arrived. Section 10.1.2 continues with three key components of ML applications, namely data, representations and learning, and explains the concepts of supervised learning, semi-supervised learning, unsupervised learning, and reinforcement learning. Section 10.1.3 suggests resources for the readers to get started with ML, including reference books, list of top free online Python training courses, Python reference libraries, and books with ML principles and coding examples. Appendix B of the book gives an introduction to Python for chemical engineers.  \nSection 10.2 gives an overview of selected ML methods and applications to regression and classification problems. Section 10.2.1 covers supervised learning methods for regression applications. We discuss linear regression, polynomial regression, underfitting, overfitting and regularization, Ridge linear regression and Lasso linear regression, bias-variance tradeoff, and performance evaluation metrics for regression problems. Section 10.2.2 discusses supervised learning methods for classification applications. We cover logistic regression (classification), radial basis function network, and K-means clustering, P-nearest neighbor algorithm, support vector machine classification and regression, decision trees for classification and regression, and performance evaluation metrics for classification problems. Section 10.2.3 covers unsupervised learning for dimensionality reduction, outlier detection and clustering applications. We have already introduced principal component analysis (PCA) in Chapter 9. In this section, we introduce kernel PCA, K-means clustering, hierarchical clustering, density-based spatial clustering of applications with noise (DBSCAN), and Gaussian mixture model, together with their similarities and differences.  \nSection 10.3 presents enhanced learning by ensemble methods, including bagging, boosting and stacking, and introduces the popular methods of random forest, AdaBoost, XGBoost, among others.  \nSection 10.4 discusses enhanced learning by deep neural networks. Section 10.4.1 first reviews the key concepts, parameters and training of a multilayer perceptron (MLP), focusing on its limitations and required changes when applied to deep neural networks (DNNs) . We explain the vanishing and  \nexploding gradient problems in the popular gradient descent training algorithm, and discuss techniques to improve the performance of DNNs, such as batch normalization, regularization by weight decay and dropout, and fast optimizer. Section 10.4.2 covers deep learning by recurrent neural networks (RNNs) for modeling time-dependent processes, including backpropagation through time, long short-term memory (LSTM) RNNs, gated recurrent units (GRUs), and bidirectional RNNs. Section 10.4.3 introduces convolutional neural networks (CNNs) . Section 10.4.4 presents the transformer neural network that finds growing a","cbCaigzCtIICvrNw","https://ap.wps.com/l/cbCaigzCtIICvrNw","pdf",3217961,9,1,114,"English","en",105,"# 10.1 Introduction\n## 10.1.1 The Time for AI, Particularly Machine Learning, in Chemical Industries Has Finally Arrived\n## 10.1.2 Key Components of ML Applications\n## 10.1.3 Resources to Get Started with ML\n# 10.2 Overview of Selected ML Methods\n## 10.2.1 Supervised Learning for Regression\n## 10.2.2 Supervised Learning for Classification\n## 10.2.3 Unsupervised Learning\n# 10.3 Enhanced Learning by Ensemble Methods\n# 10.4 Enhanced Learning by Deep Neural Networks\n## 10.4.1 Multilayer Perceptron and Deep Neural Networks\n## 10.4.2 Recurrent Neural Networks for Time-Dependent Processes\n## 10.4.3 Convolutional Neural Networks\n## 10.4.4 Transformer Neural Networks\n## 10.5 General Guidelines for Choosing ML Algorithms\n# 10.6–10.12 Hands-on Workshops and Supporting Material\n## 10.6 HDPE Melt Index Workshop (Random Forest and XGBoost)\n## 10.7 HDPE Melt Index Workshop (Deep Neural Network)\n## 10.8 Time-Dependent RNN Workshop (LSTM/GRU)\n## 10.9 Polymer Property Prediction from Molecular Structure\n## 10.10 Melt Index Workshop (Automated ML)\n## 10.11 Limits of Stand-alone Data-based Models and Hybrid SGML Transition\n## 10.12 Detailed Bibliography and Software Implementation","[{\"question\":\"What learning paradigms does the chapter introduce for applying ML in chemical and polymer processes?\",\"answer\":\"It explains supervised learning, semi-supervised learning, unsupervised learning, and reinforcement learning, framed around core ML components such as data, representations, and learning.\"},{\"question\":\"Which ML methods are covered for regression and how are their performance aspects discussed?\",\"answer\":\"The chapter covers linear and polynomial regression, addresses underfitting and overfitting, introduces regularization via Ridge and Lasso, discusses the bias-variance tradeoff, and reviews regression performance evaluation metrics.\"},{\"question\":\"What workshop examples are provided for polyolefin-related modeling tasks like the HDPE melt index?\",\"answer\":\"It includes multiple workshop-style workflows to predict the HDPE melt index using ensemble learning (random forest, XGBoost), deep neural networks, and time-dependent RNN approaches (LSTM and GRU).\"},{\"question\":\"How does the chapter motivate hybrid science-guided machine learning after presenting stand-alone ML approaches?\",\"answer\":\"It highlights limitations of stand-alone data-based models and points readers to Chapter 11 for integrating first-principle-based models with data-driven ML, improving both interpolation and extrapolation accuracy in chemical process optimization.\"}]","Applications of Machine Learning to Optimizing Polyolefin Manufacturing - Section 10 | PDF",1785901667,287,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":92,"head_meta":94,"extra_data":96,"updated_unix":29},"applications-of-machine-learning-to-optimizing-polyolefin-manufacturing-section-10","",{"@graph":37,"@context":91},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/technology/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/applications-of-machine-learning-to-optimizing-polyolefin-manufacturing-section-10/125865/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83,87],{"name":74,"@type":75,"acceptedAnswer":76},"What learning paradigms does the chapter introduce for applying ML in chemical and polymer processes?","Question",{"text":77,"@type":78},"It explains supervised learning, semi-supervised learning, unsupervised learning, and reinforcement learning, framed around core ML components such as data, representations, and learning.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"Which ML methods are covered for regression and how are their performance aspects discussed?",{"text":82,"@type":78},"The chapter covers linear and polynomial regression, addresses underfitting and overfitting, introduces regularization via Ridge and Lasso, discusses the bias-variance tradeoff, and reviews regression performance evaluation metrics.",{"name":84,"@type":75,"acceptedAnswer":85},"What workshop examples are provided for polyolefin-related modeling tasks like the HDPE melt index?",{"text":86,"@type":78},"It includes multiple workshop-style workflows to predict the HDPE melt index using ensemble learning (random forest, XGBoost), deep neural networks, and time-dependent RNN approaches (LSTM and GRU).",{"name":88,"@type":75,"acceptedAnswer":89},"How does the chapter motivate hybrid science-guided machine learning after presenting stand-alone ML approaches?",{"text":90,"@type":78},"It highlights limitations of stand-alone data-based models and points readers to Chapter 11 for integrating first-principle-based models with data-driven ML, improving both interpolation and extrapolation accuracy in chemical process optimization.","https://schema.org",{"og:url":53,"og:type":93,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":95,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":98},[99,103,107,111,116,119,124,129,133,136,140],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},"Exam",70,"exam",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":117,"slug":118},50,"technology",{"id":120,"doc_module":4,"doc_module_name":47,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},8,"Research & Report",30,"research-report",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":131,"slug":132},"Religion & Spirituality",20,"religion-spirituality",{"id":131,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":131,"slug":135},"World Cup","world-cup",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":137,"slug":139},10,"Lifestyle","lifestyle",{"id":141,"doc_module":4,"doc_module_name":47,"category_name":142,"show_sort_weight":112,"slug":143},19,"General","general"]