Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.5
2.8
Journals
Processes
Special Issues
Machine Learning Optimization of Chemical Processes
share announcement

Machine Learning Optimization of Chemical Processes

A special issue of Processes (ISSN 2227-9717). This special issue belongs to the section "Chemical Processes and Systems".

Deadline for manuscript submissions: 10 January 2026 | Viewed by 17420

Special Issue Editor

Dr. An Su

E-Mail Website
Guest Editor
College of Chemical Engineering, Zhejiang University of Technology, Hangzhou 310014, China
Interests: artificial intelligence; machine learning; computer assisted synthesis planning; chemical reaction optimization; continuous flow synthesis (flow chemistry); automated chemical synthesis
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The integration of machine learning techniques into chemical process optimization represents a transformative approach in the field of chemical engineering. As industries strive for efficiency, sustainability, and innovation, the application of machine learning offers unprecedented opportunities to enhance process design, control, and optimization.

This Special Issue on "Machine Learning Optimization of Chemical Processes" aims to gather cutting-edge research that explores the intersection of machine learning and chemical engineering. We invite submissions that demonstrate the application of machine learning algorithms to optimize chemical processes, improve process safety, and enhance product quality.

Topics of interest include, but are not limited to, the following:

  • Machine learning models for process optimization;
  • Predictive maintenance and fault detection;
  • Data-driven process control strategies;
  • Process simulation and modeling using AI;
  • Sustainable process design through machine learning;
  • Real-time process monitoring and analytics;
  • Case studies on industrial applications of machine learning.

Dr. An Su
Guest Editor

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

  • process optimization
  • process control
  • machine learning
  • models
  • fault detection

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (8 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

21 pages, 3369 KB  
Article
Thermal Runaway Critical Threshold and Gas Release Safety Boundary of 18,650 Lithium-Ion Battery in State of Charge
by Jingyu Zhao, Kexin Xing, Xinrong Jiang, Chi-Min Shu and Xiangrong Sun
Processes 2025, 13(7), 2175; https://doi.org/10.3390/pr13072175 - 8 Jul 2025
Cited by 1 | Viewed by 2827
Abstract
In this study, we systematically investigated the characteristic parameter evolution laws of thermal runaway with respect to 18,650 lithium-ion batteries (LIBs) under thermal abuse conditions at five state-of-charge (SOC) levels: 0%, 25%, 50%, 75%, and 100%. In our experiments, we combined infrared thermography, [...] Read more.
In this study, we systematically investigated the characteristic parameter evolution laws of thermal runaway with respect to 18,650 lithium-ion batteries (LIBs) under thermal abuse conditions at five state-of-charge (SOC) levels: 0%, 25%, 50%, 75%, and 100%. In our experiments, we combined infrared thermography, mass loss analysis, temperature monitoring, and gas composition detection to reveal the mechanisms by which SOC affects the trigger time, critical temperature, maximum temperature, mass loss, and gas release characteristics of thermal runaway. The results showed that as the SOC increases, the critical and maximum temperatures of thermal runaway increase notably. At a 100% SOC, the highest temperature on the positive electrode side reached 1082.1 °C, and the mass loss increased from 6.90 g at 0% SOC to 25.75 g at 100% SOC, demonstrating a salient positive correlation. Gas analysis indicated that under high-SOC conditions (75% and 100%), the proportion of flammable gases such as CO and CH4 produced during thermal runaway significantly increases, with the CO/CO2 ratio exceeding 1, indicating intensified incomplete combustion and a significant increase in fire risk. In addition, flammability limit analysis revealed that the lower explosive limit for gases is lower (17–21%) at a low SOC (0%) and a high SOC (100%), indicating greater explosion risks. We also found that the composition of gases released during thermal runaway varies substantially at different SOC levels, with CO, CO2, and CH4 accounting for over 90% of the total gas volume, while toxic gases, such as HF, although present in smaller proportions, pose noteworthy hazards. Unlike prior studies that relied on post hoc analysis, this work integrates real-time multi-parameter monitoring (temperature, gas composition, and mass loss) and quantitative explosion risk modeling (flammability limits via the L-C formula). This approach reveals the unique dynamic SOC-dependent mechanisms of thermal runaway initiation and gas hazards. This study provides theoretical support for the source tracing of thermal runaway fires and the development of preventive LIB safety technology and emphasizes the critical influence of the charge state on the thermal safety of batteries. Full article
(This article belongs to the Special Issue Machine Learning Optimization of Chemical Processes)
►▼ Show Figures

Figure 1

16 pages, 2448 KB  
Article
RadicalRetro: A Deep Learning-Based Retrosynthesis Model for Radical Reactions
by Jiangcheng Xu, Jun Dong, Kui Du, Wenwen Liu, Jiehai Peng and Wenbo Yu
Processes 2025, 13(6), 1792; https://doi.org/10.3390/pr13061792 - 5 Jun 2025
Viewed by 1561
Abstract
With the rapid development of radical initiation technologies such as photocatalysis and electrocatalysis, radical reactions have become an increasingly attractive approach for constructing target molecules. However, designing efficient synthetic routes using radical reactions remains a significant challenge due to the inherent complexity and [...] Read more.
With the rapid development of radical initiation technologies such as photocatalysis and electrocatalysis, radical reactions have become an increasingly attractive approach for constructing target molecules. However, designing efficient synthetic routes using radical reactions remains a significant challenge due to the inherent complexity and instability of radical intermediates. While computer-aided synthesis planning (CASP) has advanced retrosynthetic analysis for polar reactions, radical reactions have been largely overlooked in AI-driven approaches. In this study, we introduce RadicalRetro, the first deep learning-based retrosynthesis model specifically tailored for radical reactions. Our work is distinguished by three key contributions: (1) RadicalDB: A novel, manually curated database of 21.6 K radical reactions, focusing on high-impact literature and mechanistic clarity, addressing the critical gap in dedicated radical reaction datasets. (2) Model Innovation: By pretraining Chemformer on ZINC-15 and USPTO datasets followed by fine-tuning with RadicalDB, RadicalRetro achieves a Top-1 accuracy of 69.3% in radical retrosynthesis, surpassing the state-of-the-art models LocalRetro and Mol-Transformer by 23.0% and 25.4%, respectively. (3) Interpretability and Practical Utility: Attention weight analysis and case studies demonstrate that RadicalRetro effectively captures radical reaction patterns (e.g., cascade cyclizations and photocatalytic steps) and proposes synthetically viable routes, such as streamlined pathways for Tamoxifen precursors and glycoside derivatives. RadicalRetro’s performance highlights its potential to transform radical-based synthetic planning, offering chemists a robust tool to leverage the unique advantages of radical chemistry in drug synthesis. Full article
(This article belongs to the Special Issue Machine Learning Optimization of Chemical Processes)
►▼ Show Figures

Figure 1

19 pages, 4266 KB  
Article
Accurate and Efficient Process Modeling and Inverse Optimization for Trench Metal Oxide Semiconductor Field Effect Transistors: A Machine Learning Proxy Approach
by Mingqiang Geng, Jianming Guo, Yuting Sun, Dawei Gao and Dong Ni
Processes 2025, 13(5), 1544; https://doi.org/10.3390/pr13051544 - 16 May 2025
Viewed by 1601
Abstract
This study proposes a novel framework integrating long short-term memory (LSTM) networks with Bayesian optimization (BO) to address process–device co-optimization challenges in trench-gate metal–oxide–semiconductor field-effect transistor (MOSFET) manufacturing. Conventional TCAD simulations, while accurate, suffer from computational inefficiency in high-dimensional parameter spaces. To overcome [...] Read more.
This study proposes a novel framework integrating long short-term memory (LSTM) networks with Bayesian optimization (BO) to address process–device co-optimization challenges in trench-gate metal–oxide–semiconductor field-effect transistor (MOSFET) manufacturing. Conventional TCAD simulations, while accurate, suffer from computational inefficiency in high-dimensional parameter spaces. To overcome this, an LSTM-based TCAD proxy model is developed, leveraging hierarchical temporal dependencies to predict electrical parameters (e.g., breakdown voltage, threshold voltage) with deviations below 3.5% compared to physical simulations. The model, validated on both N-type and P-type 20 V trench MOS devices, outperforms conventional RNN and GRU architectures, reducing average relative errors by 1.78% through its gated memory mechanism. A BO-driven inverse optimization methodology is further introduced to navigate trade-offs between conflicting objectives (e.g., minimizing on-resistance while maximizing breakdown voltage), achieving recipe predictions with a maximum deviation of 8.3% from experimental data. Validation via TCAD-simulated extrapolation tests and SEM metrology confirms the framework’s robustness under extended operating ranges (e.g., 0–40 V drain voltage) and dimensional tolerances within industrial specifications. The proposed approach establishes a scalable, data-driven paradigm for semiconductor manufacturing, effectively bridging TCAD simulations with production realities while minimizing empirical trial-and-error iterations. Full article
(This article belongs to the Special Issue Machine Learning Optimization of Chemical Processes)
►▼ Show Figures

Figure 1

16 pages, 2497 KB  
Article
Bayesian Deep Reinforcement Learning for Operational Optimization of a Fluid Catalytic Cracking Unit
by Jingsheng Qin, Lingjian Ye, Jiaqing Zheng and Jiangnan Jin
Processes 2025, 13(5), 1352; https://doi.org/10.3390/pr13051352 - 28 Apr 2025
Viewed by 904
Abstract
The emerging machine learning techniques provide great opportunities for optimal operation of chemical systems. This paper presents a Bayesian deep reinforcement learning method for the optimization of a fluid catalytic cracking (FCC) unit, which is a key process in the petroleum refining industry. [...] Read more.
The emerging machine learning techniques provide great opportunities for optimal operation of chemical systems. This paper presents a Bayesian deep reinforcement learning method for the optimization of a fluid catalytic cracking (FCC) unit, which is a key process in the petroleum refining industry. Unlike the traditional reinforcement learning (RL) methods that use deterministic network weights, Bayesian neural networks are incorporated to represent the RL agent. The Bayesian treatment is integrated with the primal-dual method to handle the process constraints. Simulated experiments for FCC determined that the proposed algorithm achieves more stable control performance and higher economic profits, especially under parameter fluctuations and external disturbances. Full article
(This article belongs to the Special Issue Machine Learning Optimization of Chemical Processes)
►▼ Show Figures

Figure 1

18 pages, 6092 KB  
Article
VideoMamba Enhanced with Attention and Learnable Fourier Transform for Superheat Identification
by Yezi Hu, Xiaofang Chen, Lihui Cen, Zeyang Yin and Ziqing Deng
Processes 2025, 13(5), 1310; https://doi.org/10.3390/pr13051310 - 25 Apr 2025
Viewed by 675
Abstract
Superheat degree (SD) is an important indicator for identifying the status of aluminum electrolytic cells. The fire hole video of the aluminum electrolytic cell captured by an industrial camera is an important basis for identifying SD. This article proposes a novel method that [...] Read more.
Superheat degree (SD) is an important indicator for identifying the status of aluminum electrolytic cells. The fire hole video of the aluminum electrolytic cell captured by an industrial camera is an important basis for identifying SD. This article proposes a novel method that VideoMamba enhances with attention and learnable Fourier transform (CFVM) for SD identification. With a lower computational complexity and feature extraction capabilities comparable to transformers, VideoMamba offers the CFVM model a stronger feature extraction basis. The channel attention mechanism (CAM) block can achieve information exchange between channels. Through matrix eigenvalue manipulation, the learnable nonlinear Fourier transform (LNFT) block may guarantee stable convergence of the model. Furthermore, the LNFT block can efficiently use mixed frequency domain channels to capture global dependency information. The model is trained using the aluminum electrolysis fire hole dataset. Compared with recent fire hole identification models that primarily rely on neural networks, the method proposed in this paper is based on the concept of state space modeling, offering lower model complexity and enhanced feature extraction capability. Experimental results demonstrate that the proposed model achieves competitive performance in fire hole video identification tasks, reaching an identification accuracy of 85.7% on the test set. Full article
(This article belongs to the Special Issue Machine Learning Optimization of Chemical Processes)
►▼ Show Figures

Figure 1

16 pages, 754 KB  
Article
Transfer Learning for Thickener Control
by Samuel Arce Munoz and John D. Hedengren
Processes 2025, 13(1), 223; https://doi.org/10.3390/pr13010223 - 14 Jan 2025
Viewed by 1373
Abstract
Thickener control is a key area of focus in the minerals processing industry, particularly due to its crucial role in water recovery, which is essential for sustainable resource management. The highly nonlinear nature of thickener dynamics presents significant challenges in modeling and optimization, [...] Read more.
Thickener control is a key area of focus in the minerals processing industry, particularly due to its crucial role in water recovery, which is essential for sustainable resource management. The highly nonlinear nature of thickener dynamics presents significant challenges in modeling and optimization, making it a strong candidate for advanced surrogate modeling techniques. However, traditional data-driven approaches often require extensive datasets, which are frequently unavailable, especially in new plants or unexplored operational domains. Developing data-driven models without enough data representative of the dynamics of the system could result in incorrect predictions and consequently, unstable response of the controller. This paper proposes the application of a methodology that leverages transfer learning to address these data limitations to enhance surrogate modeling and model predictive control (MPC) of thickeners. The performance of three approaches—a base model, a transfer learning model, and a physics-informed neural network (PINN)—are compared to demonstrate the effectiveness of transfer learning in improving control strategies under limited data conditions. Full article
(This article belongs to the Special Issue Machine Learning Optimization of Chemical Processes)
►▼ Show Figures

Figure 1

Review

Jump to: Research

26 pages, 5810 KB  
Review
Bayesian Optimization for Chemical Synthesis in the Era of Artificial Intelligence: Advances and Applications
by Runqiu Shen, Guihua Luo and An Su
Processes 2025, 13(9), 2687; https://doi.org/10.3390/pr13092687 - 23 Aug 2025
Viewed by 3183
Abstract
This review highlights recent advances in the application of Bayesian optimization to chemical synthesis. In the era of artificial intelligence, Bayesian optimization has emerged as a powerful machine learning approach that transforms reaction engineering by enabling efficient and cost-effective optimization of complex reaction [...] Read more.
This review highlights recent advances in the application of Bayesian optimization to chemical synthesis. In the era of artificial intelligence, Bayesian optimization has emerged as a powerful machine learning approach that transforms reaction engineering by enabling efficient and cost-effective optimization of complex reaction systems. We begin with a concise overview of the theoretical foundations of Bayesian optimization, emphasizing key components such as Gaussian process-based surrogate models and acquisition functions that balance exploration and exploitation. Subsequently, we examine its practical applications across various chemical synthesis contexts, including reaction parameter tuning, catalyst screening, molecular design, synthetic route planning, self-optimizing systems, and autonomous laboratories. In addition, we discuss the integration of emerging techniques, such as noise-robust methods, multi-task learning, transfer learning, and multi-fidelity modeling, which enhance the versatility of Bayesian optimization in addressing the challenges and limitations inherent in chemical synthesis. Full article
(This article belongs to the Special Issue Machine Learning Optimization of Chemical Processes)
►▼ Show Figures

Figure 1

26 pages, 692 KB  
Review
Smart Biofloc Systems: Leveraging Artificial Intelligence (AI) and Internet of Things (IoT) for Sustainable Aquaculture Practices
by Mansoor Alghamdi and Yasmeen G. Haraz
Processes 2025, 13(7), 2204; https://doi.org/10.3390/pr13072204 - 10 Jul 2025
Cited by 2 | Viewed by 3566
Abstract
The rising demand for sustainable aquaculture necessitates innovative solutions to environmental and operational challenges. Biofloc technology (BFT) has emerged as an effective method, leveraging microbial communities to enhance water quality, reduce feed costs, and improve fish health. However, traditional BFT systems are susceptible [...] Read more.
The rising demand for sustainable aquaculture necessitates innovative solutions to environmental and operational challenges. Biofloc technology (BFT) has emerged as an effective method, leveraging microbial communities to enhance water quality, reduce feed costs, and improve fish health. However, traditional BFT systems are susceptible to water quality fluctuations, demanding precise monitoring and control. This review explores the integration of Artificial Intelligence (AI) and Internet of Things (IoT) technologies in smart BFT systems, highlighting their capacity to automate processes, optimize resource utilization, and boost system performance. IoT devices facilitate real-time monitoring, while AI-driven analytics provide actionable insights for predictive management. We present a comparative analysis of AI models, such as LSTM, Random Forest, and SVM, for various aquaculture prediction tasks, emphasizing the importance of performance metrics like RMSE and MAE. Furthermore, we discuss the environmental and economic impacts, including quantitative case studies on cost reduction and productivity increases. This paper also addresses critical aspects of AI model reliability, interpretability (SHAP/LIME), uncertainty quantification, and failure mode analysis, advocating for robust testing protocols and human-in-the-loop systems. By addressing these challenges and exploring future opportunities, this article underscores the transformative potential of AI and IoT in advancing BFT for sustainable aquaculture practices, offering a pathway to more resilient and efficient food production. Full article
(This article belongs to the Special Issue Machine Learning Optimization of Chemical Processes)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-8
Back to TopTop