Submit to Processes Review for Processes Propose a Special Issue

Journal Browser

Machine Learning and Data-Driven Techniques for Complex Industrial Processes

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Processes (ISSN 2227-9717). This special issue belongs to the section "Process Control and Monitoring".

Deadline for manuscript submissions: closed (30 December 2023) | Viewed by 10645

Share This Special Issue

Special Issue Editors

Dr. Fei Zhao

E-Mail Website
Guest Editor

State Key Laboratory of Industrial Control Technology, Institute of Industrial Intelligence and Systems Engineering, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China
Interests: modeling & optimization on complex systems; machine learning & Industrial intelligence; process design & optimization; uncertainty analysis; digital twin

Dr. Yachao Dong

E-Mail Website
Guest Editor

Frontiers Science Center for Smart Materials Oriented Chemical Engineering, Institute of Chemical Process Systems Engineering, School of Chemical Engineering, Dalian University of Technology, Dalian 116024, China
Interests: data-driven methods in chemical processes; production scheduling & optimization; process control & optimization

Special Issue Information

Dear Colleagues,

Data science is rapidly transforming the scientific and industrial landscapes; in particular, big data and machine learning techniques are broadly redefining the state of the art in complex industrial and chemical processes. Due to process nonlinearities, high-dimensional variable coupling and unknown model structures, it is difficult to establish mechanistic models using first-principle methods. Using datasets collected from manufacturing, maintenance, operations and environments, data-driven methods make it possible to explore the functioning of complex manufacturing processes and behaviors on the largest scale via combining technologies. Known physical properties are widely incorporated into data-driven models for high-performance process modeling and optimization. The application of industrial big data to enhance industrial intelligence has attracted an increasing amount of interest, including in the areas of process modeling, production design, process control, optimization and scheduling, as well as digital twins for smart manufacturing. This Special Issue aims to address the state-of-the-art advances in research and applications of machine learning and data-driven techniques for complex industrial processes. Topics of interest include, but are not limited to:

New methodologies for data-driven modeling and machine learning techniques;
Data-driven process modeling, monitoring, control, optimization and scheduling;
Hybrid modeling methods based on industrial big data and process mechanisms for various processes;
Industrially relevant applications of data-driven models;
Example usages of digital twins in various complex industries;
Challenges and potential research directions regarding data-driven techniques for complex industrial processes.

Dr. Fei Zhao
Dr. Yachao Dong
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Processes is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

machine learning
industrial intelligence
industrial big data
data-driven methods
industrial and chemical processes
soft sensing
process modeling and control
optimization and integration
digital twin

Published Papers (5 papers)

Download All Papers

Research

Jump to: Review

18 pages, 4239 KiB

Open AccessArticle

Intelligent Fault Diagnosis of Marine Diesel Engines Based on Efficient Channel Attention-Improved Convolutional Neural Networks

by Jihui Wang, Hui Cao, Zhichao Cui, Zeren Ai and Kuo Jiang

Processes 2023, 11(12), 3360; https://doi.org/10.3390/pr11123360 - 3 Dec 2023

Cited by 1 | Viewed by 1023

Abstract

With the rapid development of smart ships, the ship maintenance model is also changing. In order to extract the fault characteristics of diesel engine thermal parameters more easily, reduce the model’s complexity and improve the model’s accuracy, a new approach is proposed: first, the traditional convolutional neural networks (improved convolutional neural networks (ICNN)) are improved by using Meta-ACON as the activation function, improved AdamP as the optimizer, and label smoothing regularization (LSR) as the loss function, which enhances the stability of the model. Secondly, efficient channel attention (ECA) is added to achieve the mastery of global feature information, reduce the complexity of the traditional self-attention module, and enhance the model’s feature extraction ability. Lastly, the accuracy and reliability of the model are verified through ablation and comparison experiments. The accuracy rate reaches 97.6%, which is significantly improved by 32.1% compared with the original model, and the robustness of the model is verified through the introduction of noise. The experimental results demonstrate the applicability of the model in the field of diesel engine fault diagnosis. Full article

(This article belongs to the Special Issue Machine Learning and Data-Driven Techniques for Complex Industrial Processes)

► Show Figures

Figure 1

13 pages, 1999 KiB

Open AccessArticle

The Decomposition of Dilute 1-Butene in Tubular Multilayer Dielectric Barrier Discharge Reactor: Performance, By-Products and Reaction Mechanism

by Chao Li, Xiao Zhu, Shiqiang Wang, Yafeng Guo, Yu Du, Yinxia Guan and Shiya Tang

Processes 2023, 11(7), 1926; https://doi.org/10.3390/pr11071926 - 26 Jun 2023

Viewed by 801

Abstract

Butene is a typical component of exhaust gas in the petrochemical industry, the emission of which into the atmosphere would lead to air pollution. In this study, a tubular multilayer dielectric barrier discharge (TM-DBD) reactor was developed to decompose 1-butene at ambient pressure. The experimental results show that a decomposition efficiency of more than 99% and CO_x selectivity of at least 43% could be obtained at a specific energy density of 100 J/L with an inlet concentration of 1-butene ranging from 100 to 400 ppm. Increasing the volume ratio of O₂/N₂ from 0 to 20% and the specific energy density from 33 to 132 J/L were beneficial for 1-butene destruction and mineralization. Based on organic byproduct analysis, it was inferred that the nitrogenous organic compounds were the main products in N₂ atmosphere, while alcohol, aldehyde, ketone, acid and oxirane were detected in the presence of O₂. In addition, the contents of formaldehyde, acetaldehyde, ethyl alcohol, acetic acid and propionic acid increased with an increase in specific energy density, but the contents of propionaldehyde, ethyl oxirane, butyraldehyde and formic acid decreased. Three main pathways of 1-butene destruction were proposed involving Criegee intermediates and ozonolysis of the olefins, and the following degradation could be the dominant pathways rather than epoxidation. Overall, the developed TM-DBD system paved the way for scaling up the applications of plasma technology for gaseous pollutant decomposition. Full article

(This article belongs to the Special Issue Machine Learning and Data-Driven Techniques for Complex Industrial Processes)

► Show Figures

Figure 1

24 pages, 9172 KiB

Open AccessArticle

A Three-Step Framework for Multimodal Industrial Process Monitoring Based on DLAN, TSQTA, and FSBN

by Hao Wu, Wangan Fu, Xin Ren, Hua Wang and Enmin Wang

Processes 2023, 11(2), 318; https://doi.org/10.3390/pr11020318 - 18 Jan 2023

Cited by 4 | Viewed by 1234

Abstract

The process monitoring method for industrial production can technically achieve early warning of abnormal situations and help operators make timely and reliable response decisions. Because practical industrial processes have multimodal operating conditions, the data distributions of process variables are different. The different data distributions may cause the fault detection model to be invalid. In addition, the fault diagnosis model cannot find the correct root cause variable of system failure by only identifying abnormal variables. There are correlations between the trend states of the process variables. If we do not consider these correlations, this may result in an incorrect fault root cause. Therefore, multimodal industrial process monitoring is a tough issue. In this paper, we propose a three-step framework for multimodal industrial process monitoring. The framework aims for multimodal industrial processes to detect the faulty status timely and then find the correct root variable that causes the failure. We present deep local adaptive network (DLAN), two-stage qualitative trend analysis (TSQTA), and five-state Bayesian network (FSBN) to implement fault detection, identification, and diagnosis step by step. This framework can detect the system failure timely, identify abnormal variables, and find the root cause variable and the fault propagation path. The case studies on the Tennessee Eastman simulation and a practical chlorobenzene production process are provided to verify the effectiveness of the proposed framework in multimodal industrial process monitoring. Full article

(This article belongs to the Special Issue Machine Learning and Data-Driven Techniques for Complex Industrial Processes)

► Show Figures

Figure 1

19 pages, 7230 KiB

Open AccessArticle

Control of Precalciner Temperature in the Cement Industry: A Novel Method of Hammerstein Model Predictive Control with ISSA

by Chao Sun, Pengfei Liu, Haoran Guo, Yinlu Di, Qingquan Xu and Xiaochen Hao

Processes 2023, 11(1), 214; https://doi.org/10.3390/pr11010214 - 9 Jan 2023

Cited by 4 | Viewed by 3974

Abstract

As the most critical equipment in the pre-calcination process of dry cement production, the temperature of the precalciner is an essential factor affecting the quality of cement. However, the cement calcination system is time-delayed, nonlinear, and multi-disturbance, which makes it difficult to predict and control the precalciner temperature. In this study, a deep learning-based Hammerstein model is proposed, and a model predictive control system is built to predict and control the precalciner temperature. In the prediction model, the CNN-GRU network architecture is used to extract the operating states of the precalciner, and an attention mechanism is employed to find and emphasize the important historical information in the extracted states. Then, an ARX model is built to predict the temperature of the precalciner using the extracted operating state information. The complex nonlinear model solution in the control system is formed into a linear control problem and an inverse solution problem. The generalized predictive control (GPC) is used for linear control, and the improved sparrow search algorithm (ISSA) is used for the problem of an inverse solution. Tested with data from a cement plant in Hebei, China, the prediction accuracy of the model proposed in this paper is 99%, and the established control algorithm has less overshoot compared to PID and better stability in anti-disturbance tests. It is demonstrated that the prediction model developed in this study has better accuracy and the control strategy based on this model has good robustness. Full article

(This article belongs to the Special Issue Machine Learning and Data-Driven Techniques for Complex Industrial Processes)

► Show Figures

Figure 1

Review

Jump to: Research

23 pages, 2917 KiB

Open AccessReview

Data-Driven Modeling Methods and Techniques for Pharmaceutical Processes

by Yachao Dong, Ting Yang, Yafeng Xing, Jian Du and Qingwei Meng

Processes 2023, 11(7), 2096; https://doi.org/10.3390/pr11072096 - 13 Jul 2023

Cited by 4 | Viewed by 2435

Abstract

As one of the most influential industries in public health and the global economy, the pharmaceutical industry is facing multiple challenges in drug research, development and manufacturing. With recent developments in artificial intelligence and machine learning, data-driven modeling methods and techniques have enabled fast and accurate modeling for drug molecular design, retrosynthetic analysis, chemical reaction outcome prediction, manufacturing process optimization, and many other aspects in the pharmaceutical industry. This article provides a review of data-driven methods applied in pharmaceutical processes, based on the mathematical and algorithmic principles behind the modeling methods. Different statistical tools, such as multivariate tools, Bayesian inferences, and machine learning approaches, i.e., unsupervised learning, supervised learning (including deep learning) and reinforcement learning, are presented. Various applications in the pharmaceutical processes, as well as the connections from statistics and machine learning methods, are discussed in the narrative procedures of introducing different types of data-driven models. Afterwards, two case studies, including dynamic reaction data modeling and catalyst-kinetics prediction of cross-coupling reactions, are presented to illustrate the power and advantages of different data-driven models. We also discussed current challenges and future perspectives of data-driven modeling methods, emphasizing the integration of data-driven and mechanistic models, as well as multi-scale modeling. Full article

(This article belongs to the Special Issue Machine Learning and Data-Driven Techniques for Complex Industrial Processes)

► Show Figures