Special Issue "Modelling, Monitoring, Control and Optimization for Complex Industrial Processes"

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

Deadline for manuscript submissions: 10 April 2022.

Special Issue Editor

Dr. Zhiwei Gao
E-Mail Website
Guest Editor
Department of Mathematics, Physics and Electrical Engineering, Northumbria University, Newcastle upon Tyne NE1 8ST, UK
Interests: power conversion systems; machine learning; intelligent optimization; condition monitoring; tolerant control; wind turbine systems; offshore renewable energy; complex systems
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Industrial automation systems, such as chemical processes, manufacturing processes, power networks, transportation systems, sustainable energy systems, wireless sensor networks, robotic systems, and biomedical systems, are becoming more complex, but more expensive, and have higher requirements for operation performance, quality of products, productiveness, and reliability. Stimulated by Industry 4.0, automation industries are keen to improve the reliability and operational performance of complex industrial processes by using advanced modelling, monitoring, optimization and control techniques. Recently, artificial intelligence, data-driven techniques, cyber–physical systems, digital-twin, and cloud computation have further stimulated research and applications of modelling, monitoring, optimization and control techniques.

The Special Issue on "Modelling, Monitoring, Control and Optimization for Complex Industrial Processes " aims to provide a forum for researchers and engineers to report their recent results, exchange research ideas, and overlook emerging research and application directions in modelling, condition monitoring, optimization and advanced control for complex industrial processes.

Potential topics include, but are not limited to, the following:

  • Complex dynamic analysis and modelling of industrial processes
  • Data-driven modelling approaches for complex industrial processes
  • Multiscale dynamic simulations of industrial processes
  • Condition monitoring and fault diagnosis techniques
  • Prognosis and predictive maintenance for complex industrial systems
  • Advanced optimization methodologies
  • Resilient control techniques
  • Advanced approaches and techniques for cyber–physical systems
  • Validation and real-time applications

Dr. Zhiwei Gao
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 papers will be 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 2000 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

  • data-driven modeling and simulations
  • advanced control
  • intelligent optimization
  • complex industrial processes
  • dynamic analysis
  • real-time validation and applications

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Article
Real-Time Parameter Identification for Forging Machine Using Reinforcement Learning
Processes 2021, 9(10), 1848; https://doi.org/10.3390/pr9101848 - 18 Oct 2021
Viewed by 236
Abstract
It is a challenge to identify the parameters of a mechanism model under real-time operating conditions disrupted by uncertain disturbances due to the deviation between the design requirement and the operational environment. In this paper, a novel approach based on reinforcement learning is [...] Read more.
It is a challenge to identify the parameters of a mechanism model under real-time operating conditions disrupted by uncertain disturbances due to the deviation between the design requirement and the operational environment. In this paper, a novel approach based on reinforcement learning is proposed for forging machines to achieve the optimal model parameters by applying the raw data directly instead of observation window. This approach is an online parameter identification algorithm in one period without the need of the labelled samples as training database. It has an excellent ability against unknown distributed disturbances in a dynamic process, especially capable of adapting to a new process without historical data. The effectiveness of the algorithm is demonstrated and validated by a simulation of acquiring the parameter values of a forging machine. Full article
Show Figures

Figure 1

Article
Data-Driven State Prediction and Sensor Fault Diagnosis for Multi-Agent Systems with Application to a Twin Rotational Inverted Pendulum
Processes 2021, 9(9), 1505; https://doi.org/10.3390/pr9091505 - 26 Aug 2021
Viewed by 276
Abstract
When a multi-agent system is subjected to faults, it is necessary to detect and classify the faults in time. This paper is motivated to propose a data-driven state prediction and sensor fault classification technique. Firstly, neural network-based state prediction model is trained through [...] Read more.
When a multi-agent system is subjected to faults, it is necessary to detect and classify the faults in time. This paper is motivated to propose a data-driven state prediction and sensor fault classification technique. Firstly, neural network-based state prediction model is trained through historical input and output data of the system. Then, the trained model is implemented to the real-time system to predict the system state and output in absence of fault. By comparing the predicted healthy output and the measured output, which can be abnormal in case of sensor faults, a residual signal can be generated. When a sensor fault occurs, the residual signal exceeds the threshold, a fault classification technique is triggered to distinguish fault types. Finally, the designed data-driven state prediction and fault classification algorithms are verified through a twin rotational inverted pendulum system with leader-follower mechanism. Full article
Show Figures

Figure 1

Article
Analysis and Design of a Standalone Electric Vehicle Charging Station Supplied by Photovoltaic Energy
Processes 2021, 9(7), 1246; https://doi.org/10.3390/pr9071246 - 19 Jul 2021
Cited by 5 | Viewed by 660
Abstract
Nowadays, there is a great development in electric vehicle production and utilization. It has no pollution, high efficiency, low noise, and low maintenance. However, the charging stations, required to charge the electric vehicle batteries, impose high energy demand on the utility grid. One [...] Read more.
Nowadays, there is a great development in electric vehicle production and utilization. It has no pollution, high efficiency, low noise, and low maintenance. However, the charging stations, required to charge the electric vehicle batteries, impose high energy demand on the utility grid. One way to overcome the stress on the grid is the utilization of renewable energy sources such as photovoltaic energy. The utilization of standalone charging stations represents good support to the utility grid. Nevertheless, the electrical design of these systems has different techniques and is sometimes complex. This paper introduces a new simple analysis and design of a standalone charging station powered by photovoltaic energy. Simple closed-form design equations are derived, for all the system components. Case-study design calculations are presented for the proposed charging station. Then, the system is modeled and simulated using Matlab/Simulink platform. Furthermore, an experimental setup is built to verify the system physically. The experimental and simulation results of the proposed system are matched with the design calculations. The results show that the charging process of the electric vehicle battery is precisely steady for all the PV insolation disturbances. In addition, the charging/discharging of the energy storage battery responds perfectly to store and compensate for PV energy variations. Full article
Show Figures

Figure 1

Article
A Real-Time Optimization Strategy for Small-Scale Facilities and Implementation in a Gas Processing Unit
Processes 2021, 9(7), 1179; https://doi.org/10.3390/pr9071179 - 07 Jul 2021
Cited by 1 | Viewed by 401
Abstract
The rise of new digital technologies and their applications in several areas pushes the process industry to update its methodologies with more intensive use of mathematical models—commonly denoted as digital twins—and artificial intelligence (AI) approaches to continuously enhance operational efficiency. In this context, [...] Read more.
The rise of new digital technologies and their applications in several areas pushes the process industry to update its methodologies with more intensive use of mathematical models—commonly denoted as digital twins—and artificial intelligence (AI) approaches to continuously enhance operational efficiency. In this context, Real-time Optimization (RTO) is a strategy that is able to maximize an economic function while respecting the existing constraints, which enables keeping the operation at its optimum point even though the plant is subjected to nonlinear behavior and frequent disturbances. However, the investment related to the project of commercial RTOs may make its application infeasible for small-scale facilities. In this work, an in-house, small-scale RTO is presented and its successful application in a real industrial case—a Natural Gas Processing Unit—is shown. Besides that, a new method for enhancing the efficiency of using sequential-modular simulator inside an optimization framework and a new method to account for the economic return of optimization-based tools are proposed and described. The application of RTO in the industrial case showed an enhancement in the stability of the main variables and an increase in profit of 0.64% when compared to the operation of the regulatory control layer alone. Full article
Show Figures

Graphical abstract

Article
Successful Pass Schedule Design in Open-Die Forging Using Double Deep Q-Learning
Processes 2021, 9(7), 1084; https://doi.org/10.3390/pr9071084 - 22 Jun 2021
Viewed by 448
Abstract
In order to not only produce an open-die forged part with the desired final geometry but to also maintain economic production, precise process planning is necessary. However, due to the incremental forming of the billet, often with several hundred strokes, the process design [...] Read more.
In order to not only produce an open-die forged part with the desired final geometry but to also maintain economic production, precise process planning is necessary. However, due to the incremental forming of the billet, often with several hundred strokes, the process design is arbitrarily complicated and, even today, often only based on experience or simple mathematical models describing the geometry development. Hence, in this paper, fast process models were merged with a double deep Q-learning algorithm to enable a pass schedule design including multi-objective optimization. The presented implementation of a double deep Q-learning algorithm was successfully trained on an industrial-scale forging process and converged stably against high reward values. The generated pass schedules reliably produced the desired final ingot geometry, utilized the available press force well without exceeding plant limits, and, at the same time, minimized the number of passes. Finally, a forging experiment was performed at the institute of metal forming to validate the generated results. Overall, a proof of concept for the pass schedule design in open-die forging via double deep Q-learning was achieved which opens various starting points for future work. Full article
Show Figures

Graphical abstract

Planned Papers

The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.

Title: Real-time parameter identification for forging machine using reinforcement learning
Authors: Zhiwei Gao
Affiliation: Department of Mathematics, Physics and Electrical Engineering, Northumbria University, Newcastle upon Tyne NE1 8ST, UK

Back to TopTop