Control Of Complex Industrial Processes Research Articles

False data injection attacks detection based on Laguerre function in nonlinear Cyber‐Physical systems

This paper focus on the detection for false data injection (FDI) attacks. Under external conditions, the state and the output variables of Nonlinear Cyber‐Physical Systems (NCPSs) cannot be described by a linear relationship. It is difficult to detect the attacked systems. The Laguerre function model has excellent approximation capability to change structural parameters such as system delay and order, making it convenient for online parameter identification and suitable for complex industrial process control. Accordingly, in order to detect FDI attacks for NCPSs, the Laguerre function is adopted to detect FDI attacks and improve the detection rate. Numerical simulations verify the effectiveness of this method.

A deep learning-based edge caching optimization method for cost-driven planning process over IIoT

Edge computing has been considered as a leading paradigm to satisfy the low latency demand for some computation-intensive or data-intensive applications, especially for IIoT applications such as automatic line scheduling of the Internet of Vehicles, time-sensitive supply-chain supervision, and smart control of complex industrial processes. In the edge computing environment, app vendors prefer to cache their app data on edge servers to ensure low latency service. However, it is frequently a challenge in practice, because cache spaces on edge servers are limited and expensive. In view of this challenge, a deep learning-based edge caching optimization method, named DLECO, is proposed to reduce the cost during the cache planning process. In this paper, the edge app data caching problem is formulated as a constrained optimization problem. Then, the specific design of DLECO with a deep learning model is shown, which aims to minimize the overall system cost with lower service latency. The performance of DLECO is analyzed theoretically and experimentally with a collection of data from the real world. The experimental results show its superior performance through comparison with three representative methods.

Deep learning feature-based setpoint generation and optimal control for flotation processes

Computer vision-based control is a nonintrusive, cost-effective, and reliable technique for flotation process control. It is known that deep learning features can depict the complex behavior of the froth surface more comprehensively and accurately than handcrafted features. However, few studies have tried to use additional information to improve flotation performance through optimal control. To this end, we have attempted to develop a novel deep learning feature-based two-layer optimal control scheme. The first layer is proposed for setpoint generation of high-dimensional features using improved fuzzy association rule reasoning. Then, an offline conservative double Q-learning control layer that can learn from historical industrial records by mitigating bootstrapping error in action value functions is developed. The proposed method can adapt the setpoint to the change in process feeds. Meanwhile, in contrast to traditional approximate dynamic programming methods that need to interact with real/simulated process systems, this controller can work without any further interactions, which makes it possible to transfer the success of reinforcement learning algorithms to complex industrial process control where opportunities to explore are missing. Experiments demonstrate that the proposed method is effective and promising for practical flotation process control.

Special Issue on “Advances in Condition Monitoring, Optimization and Control for Complex Industrial Processes”

Complex industrial automation systems and processes, such as chemical processes, manufacturing systems, wireless network systems, power and energy systems, smart grids and so forth, have greatly contributed to our daily life [...]

Формування розподілення конусних поверхонь у структурі оптичних дифузорів-гомогенізаторів

An analysis and research of formation of random and regular relief structures in optical diffusers-homogenizers are carried out. The features of the methods for manufacturing optical diffusers are considered too. The implementation of the formation of random relief structures in optical diffusers is proposed.The optical diffusers are widely used in beam guidance systems, remote control of complex industrial processes, lighting systems for various industrial applications and in other devices where there is a need to form a lighting beam with specified parameters. Unlike conventional frosted glass, the optical diffusers-homogenizers allow one to control the width of the light scattering indicator for more efficient use of the light beam in guidance systems.There are different methods of manufacturing optical diffusers, depending on the final purpose of use, including the conversion of amplitude holographic recording in relief-phase on halogen-silver photoemulsions, the formation of holographic structures on the surface of the photoemulsion in the form of relief indentation of the film layer on the layer of acrylic resin with the formation of a series of evenly distributed convex microspots on the layer of acrylic resin.The proposed methods have certain disadvantages with respect to their use in the guidance systems. The optical diffuser is made of soft polymeric material, which complicates its operation. Therefore, improving the methods of manufacturing optical diffusers remains an urgent task To solve this problem, a method of manufacturing an optical diffuser in the form of a relief microstructure is proposed, including the application of a hard-alloy conical indenter with an apex angle of 120–160° conical depressions on a metal substrate, which is later used as a stamp for thermal pressing of a relief microstructure in the form of conical protrusions on an optically transparent polymer material.To achieve high efficiency during homogenization and to avoid the appearance of a zero-order spot, the optical elements created by conical surfaces have to be structured with a fill factor of 100 %.The analysis and research of the formation of the distribution of conical surfaces in the structure of optical diffusers-homogenizers to obtain the most homogeneous structure of the light flux at the sites of the photodetector have been widely presented. Fig.: 7. Refs: 6 titles.

An Approach to Intelligent Control of Complex Industrial Processes: An Example of Ferrous Metal Industry

This paper proposes an original approach to the design of intelligent control systems for complex time-varying (nonstationary) objects in which industrial processes are repeatedly reproduced over a certain period of time. Such reproduction allows accumulating data and knowledge about control programs, conditions and results of their implementation, and the trajectories of controlled variables. The motion of a controlled object is decomposed into perturbed and unperturbed motions. The unperturbed programmed motion of the object is described using expert systems and the concept of case-based reasoning (CBR); the perturbed motion of the object, using artificial neural networks.

A Survey of Computer Modeling, Simulation and Control of Complex Industrial Processes

A Survey of Computer Modeling, Simulation and Control of Complex Industrial Processes

A novel approach for multivariate process monitoring using several intelligences

This paper presents a multi-agent system for multivariate process monitoring. The proposed multi-agent system combines several intelligences which are: multivariate control charts, neural networks, Bayesian networks, and expert systems. This system aims to realise a complete control of complex industrial process. In order to demonstrate the efficiency of the proposed multi-agent system, it has been applied and evaluated in the monitoring of the complex process Tennessee Eastman process (TEP).

A novel approach for multivariate process monitoring using several intelligences

This paper presents a multi-agent system for multivariate process monitoring. The proposed multi-agent system combines several intelligences which are: multivariate control charts, neural networks, Bayesian networks, and expert systems. This system aims to realise a complete control of complex industrial process. In order to demonstrate the efficiency of the proposed multi-agent system, it has been applied and evaluated in the monitoring of the complex process Tennessee Eastman process (TEP).

Annular Heating Furnace Temperature Control Based on the Fuzzy-PID Algorithm and Cascade Double-Cross Limiting Control

Annular heating furnace temperature control is a typical and complex industrial process control system,with the characteristics of multivariable,time-varying parameters,nonlinear,coupling, large inertia and pure delay,so it is difficult to obtain satisfactory control effect when using conventional PID control. In view of the above problems, adopting fuzzy PID algorithm and cascade double-cross limiting control, combustion control effect is greatly improved, self-tuning of PID parameters is realized, and control quality is enhanced. The experimental results show that, fuzzy PID control shows good dynamic and steady performance, its control effect is significantly improved when compared with conventional PID control, and it has better overall performance.

Optimal operational control for complex industrial processes

Process control should ensure not only controlled variables to follow their setpoint values, but also the whole process plant to meet operational requirements optimally (e.g., quality, efficiency and consumptions). Process control should also enable that operational indices for quality and efficiency be improved continuously, while keeping the indices related to consumptions at the lowest possible level. This paper starts with a survey on the existing operational optimization and control methodologies and then presents a data-driven hybrid intelligent optimal operational control for complex industrial processes where process operational models are difficult to obtain. Applications via a hybrid simulation system and an industrial roasting process for hematite ore mineral processing are presented to demonstrate the effectiveness of the proposed operational control method. Issues for future research on the optimal operational control for complex industrial processes are outlined before concluding the paper.

DESIGNING MULTI-AGENT BASED LINKED STATE MACHINE

Every industrial process control algorithm can be r epresented as an ASM chart and every ASM chart can be implemented using the state agent based approach. This paper describes a simplified approach to implementing complex process control systems using the agent-based paradigm. It shows that when the system is complex, it can be broken up into a series of A SM charts, and each of those ASM charts can be implemented using agent-based app roach comprising of one process agent and a number of state agents. These agent based systems together perform the complex in dustrial process control. This structure can be int erconnected to form a linked state machine in order to realize a multi-agent bas ed linked state structure. This is a ‘divide and co nquer’ approach that is much simpler than tackling the control system implementa tion as one very complex effort. Index Terms: Process control, ASM chart, State Transition Table (STT), Multi-agent, Link state machines, Beverage blending

Operational Optimization and Feedback Control for Complex Industrial Processes

摘要: 过程控制不仅使被控对象的输出尽可能好地跟踪控制器设定值, 而且要对整个工业装置的运行进行控制, 使反映产品在该装置加工过程中质量、效率与消耗等指标, 即运行指标在目标值范围内, 尽可能提高质量与效率指标, 尽可能降低消耗指标, 即实现工业过程运行优化控制. 本文在综述了已有的运行优化与控制方法的基础上, 重点介绍了复杂工业过程的数据驱动的混合智能运行优化控制和运行控制半实物仿真系统, 并以赤铁矿磨矿过程为应用研究案例, 仿真实验和工业应用结果表明所提方法的有效性, 并指出了复杂工业过程运行优化控制研究需要关注的问题. 关键词: 复杂工业过程 / 运行优化 / 运行反馈控制 / 运行指标预报 / 半实物仿真系统

Optimal Operational Control for Complex Industrial Processes

Process control should aim at not only ensuring that controlled variables to best follow their set points, but also requiring the optimal control for the operation of the whole plant to make the operational indices (e.g. quality, efficiency and consumptions during the production phase) into their targeted ranges. It also requires that operational indices for quality and efficiency should be enhanced as high as possible, whilst the indices related to consumptions are kept at their lowest possible level. Based upon a survey on the existing operational optimization and control methodologies, this paper presents a data-driven hybrid intelligent optimal operational control for complex industrial processes and a hybrid simulation system. Simulations and industrial applications to a roasting process for the hematite ore mineral processing industry are used to demonstrate the effectiveness of the proposed method. Issues for future research on the optimal operational control for complex industrial processes are outlined in the final section.

Controlling Nonlinear Processes, using Laguerre Functions Based Adaptive Model Predictive Control (AMPC) Algorithm

Laguerre function has many advantages such as good approximation capability for different systems, low computational complexity and the facility of on-line parameter identification. Therefore, it is widely adopted for complex industrial process control. In this work, Laguerre function based adaptive model predictive control algorithm (AMPC) was implemented to control continuous stirred tank reactor (CSTR) process temperature runaways. Simulation result reveals that AMPC has a good performance in set-point tracking and load rejection. For comparison, a nonlinear model predictive control based on Laguerre- wiener model was also applied to the process. Simulation result demonstrates that the two controllers have the same performance in set point tracking and load rejection problem.

PLS and its Application within Model Predictive Controllers

Many system identification techniques have been proposed over the last few decades, including ordinary and recursive least squares. Recently, Partial Least Squares (PLS) has become a popular tool in the chemometric community and is beginning to be applied to solve complex industrial process control problems. These studies have tended to ignore the issue of bias with this form of model and it is this issue that is addressed in this article. The paper describes the development of an unbiased recursive PLS algorithm that is successfully applied to two simulated processes.

Adaptive predictive control algorithm based on Laguerre Functional Model

AbstractLaguerre Functional Model has many advantages such as good approximation capability for the variances of system time‐delay, order and other structural parameters, low computational complexity, and the facility of online parameter identification, etc., so this model is suitable for complex industrial process control. A series of successful applications have been gained in linear and non‐linear predictive control fields by the control algorithm based on Laguerre Functional Model, however, former researchers have not systemically brought forward the theoretical analyses of the stability, robustness, and steady‐state performance of this algorithm, which are the keys to guarantee the feasibility of the control algorithm fundamentally. Aimed at this problem, we introduce the principles of the Incremental Mode Linear Laguerre Predictive Control (IMLLPC) algorithm, and then systemically propose the theoretical analyses and proofs of the stability and robustness of the algorithm, in addition, we also put forward the steady‐state performance analysis. At last, the control performances of this algorithm on two different physical industrial plants are presented in detail, and a number of experimental results validate the feasibility and superiority of IMLLPC algorithm. Copyright © 2005 John Wiley & Sons, Ltd.

Sensitivity analysis based objective coordination of constrained multi-objective multi-degree-of-freedom optimization

Constrained multi-objective multi-degree-of-freedom optimization (CMMO) is proposed from the application background of optimization control for complex industrial processes. CMMO is formulated as a QP problem. Through transforming it into a linear complementary programming problem with parameters, the formulas for right and left sided sensitivity are obtained. Based on them, the objective coordination method for CMMO is developed.

Heterogeneous intelligent control systems

Intelligent control of complex industrial processes requires that knowledge from a variety of sources be used to maintain control over an extended set of operating conditions. It is asserted that to maintain the integrity of such heterogeneous knowledge, it should be encoded in distinct models. Control then consists of selecting and executing the most appropriate model for a given situation. Adaptive intelligent control can then be implemented by developing switching strategies that allow a trade-off between the various model properties. A prototype system (MuRaLi) is presented that has multiple models based on three primitive dimensions: precision, scope and generality. Generality is realised through three different knowledge representation mechanisms: procedures, rules and equations. Homogeneous control consists of constant generality and variable precision and scope to generate the most appropriate control action. Heterogeneous control consists of potential variations in all three dimensions. Simple switching strategies are investigated for both forms of control. The system has been applied to the control of a simulated 800 MW thermal power plant. Examples of homogeneous and heterogeneous control are given, with experimental results of adaptation based on the proposed switching strategies.

An Experimental Study on Human Supervisory Control and Its Implication to Process System and Automation System Design

In this paper, a laboratory study reveals how human operators experience the complexity and difficulty in supervisory control of complex industrial processes. Four structured operation environments were introduced and examined. The implications of this research for process system and automation system design are discussed.