Article
Chemistry, Multidisciplinary
Guangjun Cui, Shenghua Xiong, Cuiying Zhou, Zhen Liu
Summary: This study optimized LSSVM model parameters using the homotopy continuation method to construct the HC-LSSVM model, which accurately predicts soft ground settlement and solves the issue of non-optimal parameter solutions in the LSSVM model.
APPLIED SCIENCES-BASEL
(2021)
Article
Polymer Science
Yun Dai, Angpeng Liu, Meng Chen, Yi Liu, Yuan Yao
Summary: In this study, a novel soft sensor named SWGAN-SVR is proposed to enhance quality prediction with limited training samples. The SWGAN-SVR utilizes selective Wasserstein generative adversarial network and gradient penalty-based support vector regression to capture data distribution and generate virtual samples, while employing effective data selection strategy to deal with limited labeled data and sample quality variations.
Article
Polymer Science
Charlotte Fornaciari, Dario Pasini, Olivier Coulembier
Summary: This study describes the oxyanionic ring-opening polymerization of propylene oxide using an exogenous alcohol activated with benign metal-alkali carboxylates. The equimolar mixture of potassium acetate and 18-crown-6 ether is shown to be the most effective complex for preparing poly(propylene oxide) in a controlled manner. The presence of 18C6/KOAc allows alcohol to act as a soft nucleophile, promoting the ring-opening process while limiting parasitic hydrogen abstraction.
MACROMOLECULAR RAPID COMMUNICATIONS
(2022)
Article
Polymer Science
Min Jun Song, Sung Hyun Ju, Sungkyu Kim, Seung Hwan Oh, Jong Min Lee
Summary: This research paper presents a hybrid modeling approach that combines mechanistic modeling and machine learning to predict the melt index (MI) of an industrial polymerization process. The results indicate that the proposed hybrid model has an increased prediction accuracy and generalizability for MI prediction in an industrial polymerization process.
JOURNAL OF APPLIED POLYMER SCIENCE
(2022)
Article
Chemistry, Multidisciplinary
Erfan Dashtimoghadam, Mitchell Maw, Andrew N. Keith, Foad Vashahi, Verena Kempkes, Yulia D. Gordievskaya, Elena Yu Kramarenko, Egor A. Bersenev, Evgeniia A. Nikitina, Dimitri A. Ivanov, Yuan Tian, Andrey Dobrynin, Mohammad Vatankhah-Varnosfaderani, Sergei S. Sheiko
Summary: In this study, a A-g-B brush-like graft copolymer platform was proposed to fabricate materials with independently tunable softness and firmness. These materials have a strength comparable to stress-supporting tissues and diverse mechanical phenotypes can be achieved through architectural control, making it applicable for various chemistries.
MATERIALS HORIZONS
(2022)
Article
Automation & Control Systems
Mingwei Jia, Danya Xu, Tao Yang, Yi Liu, Yuan Yao
Summary: In this study, a soft sensor based on a graph convolutional network is developed to model the nonlinear time-varying characteristics of the process industry. The focus is on obtaining localized spatial-temporal correlations to understand the intricate interactions among variables. The model is trained with regularization terms and learns distinctive localized spatial-temporal correlations in an end-to-end manner, capturing both the localized spatial-temporal correlations and time-series properties.
JOURNAL OF PROCESS CONTROL
(2023)
Proceedings Paper
Automation & Control Systems
Min Jun Song, Sungkyu Kim, Seung Hwan Oh, Pil Sung Jo, Jong Min Lee
Summary: This paper presents a soft sensor model based on LSTM network for predicting the melt index (MI) in an industrial polymerization process. The developed model provides more accurate predictions compared to other soft sensor models and has significant advantages in capturing the complex nature of chemical processes.
Article
Engineering, Electrical & Electronic
Haibin Yin, Yi Zhang, Jiayuan Wang, Jianguo Cao
Summary: This study verified the effectiveness of using FBG sensors to predict the real-time deformation of soft fingers based on Cosserat theory and experimental validation.
IEEE SENSORS JOURNAL
(2021)
Article
Engineering, Electrical & Electronic
Zhongguan Zhu, Shihui Guo, Yipeng Qin, Xiaowei Chen, Ronghui Wu, Yating Shi, Xiangyang Liu, Minghong Liao
Summary: This paper addresses the issue of aging soft sensors affecting the stability of resistance by leveraging Deep Learning technology and proposing an output-level domain adaptation method, which enables accurate prediction of elbow angles despite sensor aging.
IEEE SENSORS JOURNAL
(2021)
Article
Chemistry, Physical
Jin Huang, Yuchun Cai, Chengyuan Xue, Jin Ge, Haoyu Zhao, Shu-Hong Yu
Summary: A new solvothermal polymerization process was proposed in this study to modify the cross-linking network structure of siloxane rubber, achieving PDMS elastomer with controllable mechanical properties. Compared to conventional curing methods, this approach resulted in higher elongation and lower tensile modulus for the PDMS elastomer.
Article
Mathematical & Computational Biology
Ping Wang, Qiaoyan Sun, Yuxin Qiao, Lili Liu, Xiang Han, Xiangguang Chen
Summary: In this study, a new approach based on soft sensor and optimal control is proposed to address the problem of the inability to measure total sugar content online during CTC fermentation. By analyzing the relationship between measurable parameters and total sugar content, a soft sensor model is established to predict total sugar content and optimize the control of glucose feed rate.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2022)
Article
Engineering, Environmental
Jun-Jie Zhu, Nathan Q. Sima, Ting Lu, Adrienne Menniti, Peter Schauer, Zhiyong Jason Ren
Summary: In this study, a daily-adaptive, probabilistic soft sensor prediction model was developed and evaluated for forecasting the average receiving river flowrate of the next month and guiding wastewater utility operations. Extra trees regression exhibited the desired deterministic prediction accuracy and the overall classification accuracy improved over the course of the predicted month.
Article
Engineering, Multidisciplinary
Wenhua Wang, Hengqian Wang, Lei Chen, Kuangrong Hao
Summary: Soft sensor plays a crucial role in contemporary industrial processes. This study proposes a feature enhancement stacked fusion autoencoder (FE-SFAE) to effectively extract feature representations from complex process data. The FE-SFAE leverages spatiotemporal characteristics and linear residual fusion for modeling, and has shown superiority in an industrial case involving the esterification process of polyester polymerization.
Article
Automation & Control Systems
Bailun Zhang, Jing Zhang, Yongming Han, Zhiqiang Geng
Summary: The article presents a novel DSS modeling method based on OESN-CMI-IDE, which achieves better prediction results for the melt index through calculating mutual information and optimizing parameters.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2021)
Article
Mathematical & Computational Biology
Xiaoshan Qian, Lisha Xu, Xinmei Yuan
Summary: This study proposes a soft measurement strategy for online detection of mother liquor concentration in alumina production. By employing comprehensive grey correlation analysis and kernel principal component analysis, the input dimension and computational complexity of the data are reduced, and a reduced robust least squares support-vector machine model is used for modeling and predicting the principal components. An improved Pattern Search Differential Evolution algorithm is used to optimize the model parameters, resulting in superior tracking capabilities and accuracy.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2023)
Article
Automation & Control Systems
Haifei Peng, Jian Long, Cheng Huang, Shibo Wei, Zhencheng Ye
Summary: This paper proposes a novel multi-modal hybrid modeling strategy (GMVAE-STA) that can effectively extract deep multi-modal representations and complex spatial and temporal relationships, and applies it to industrial process prediction.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2024)