Optimal Process Control Research Articles

Chance constrained policy optimization for process control and optimization

Chemical process optimization and control are affected by (1) plant-model mismatch, (2) process disturbances, and (3) constraints for safe operation. Reinforcement learning by policy optimization would be a natural way to solve this due to its ability to address stochasticity, plant-model mismatch, and directly account for the effect of future uncertainty and its feedback in a proper closed-loop manner; all without the need of an inner optimization loop. One of the main reasons why reinforcement learning has not been considered for industrial processes (or almost any engineering application) is that it lacks a framework to deal with safety critical constraints. Present algorithms for policy optimization use difficult-to-tune penalty parameters, fail to reliably satisfy state constraints or present guarantees only in expectation. We propose a chance constrained policy optimization (CCPO) algorithm which guarantees the satisfaction of joint chance constraints with a high probability — which is crucial for safety critical tasks. This is achieved by the introduction of constraint tightening (backoffs), which are computed simultaneously with the feedback policy. Backoffs are adjusted with Bayesian optimization using the empirical cumulative distribution function of the probabilistic constraints, and are therefore self-tuned. This results in a general methodology that can be imbued into present policy optimization algorithms to enable them to satisfy joint chance constraints with high probability. We present case studies that analyse the performance of the proposed approach.

Parameter optimal identification and dynamic behavior analysis of nonlinear model for the solution purification process of zinc hydrometallurgy

<p style='text-indent:20px;'>Impurity removal is a momentous part of zinc hydrometallurgy process, and the quality of products and the stability of the whole process are affected directly by its control effect. The application of dynamic model is of great significance to the prediction of key indexes and the optimization of process control. In this paper, considering the complex coupling relationship of stage II purification process, a hybrid modeling method of mechanism modeling and parameter identification modeling was proposed on the basis of not changing the actual production process of lead-zinc smeltery. Firstly, the overall nonlinear dynamic mechanism model was established, and then the deviation between the theoretical value and the actual detected outlet ion concentration was taken as the objective function to establish the parameter identification optimization model. Since the built model is nonlinear, it may pose implementation problems. On the premise of deriving the gradient vector and Hessian matrix of the objective function with respect to the parameter vector, an optimization algorithm based on the steepest descent method and Newton method is proposed. Finally, using the historical production data of a lead-zinc smeltery in China, the model parameters were accurately inversed. An intensive simulation validation and analysis of the dynamic characteristics about the whole model shows the accuracy and the potential of the model, also in the perspective of practical implementation, which provides the basis for the optimal control of system output and the guidance for the optimal control of zinc powder addition.</p>

Optimal control of inverse thermal processes in a parabolic equation with nonlinear deviations in time

Optimal control of inverse thermal processes in a parabolic equation with nonlinear deviations in time

Optimal control of compound Poisson processes

The problem of controlling a compound Poisson process until it leaves an interval is considered. This type of problem is known as a homing problem. To determine the value of the optimal control, we must solve a nonlinear integro-differential equation. Exact and explicit solutions are obtained for two possible jumps size distributions.

ANALYSIS OF THE DEVELOPED METHODOLOGY OF POWERLIFTING TRAINING CLASSES FOR SENIOR SECONDARY SCHOOL STUDENTS

This article provides a comparative analysis of the developed methodology of powerlifting training sessions for students of a senior secondary school; The study was conducted at the Pokrovskobagachan Lyceum of the Khorolsk City Council of the Lubensky District of the Poltava Region. 20 high school students took part in the study. During the experiment, the expediency of applying the proposed volumes of training loads to the physical fitness of high school students (girls, boys) during the annual training cycle was confirmed. The main integral indicator of the improvement of students’ preparedness is the sports result. During the period of the one-year experiment, there is an increase in the number of winners and prize-winners of a number of prestigious regional and national competitions among high school students engaged in powerlifting sections. Thus, the effectiveness of the application of the annual program of powerlifting training loads for high school students is confirmed not only by the results of the benchmarks of the study on improving physical fitness, but also by their sports achievements. The conducted research made it possible to determine the level of general and special physical fitness of high school students who systematically attend sectional powerlifting classes, which enables them to move to a new, higher level of improvement and increases the chances of winning in competitive matches. The given data can be used for the purpose of optimal construction and control of the training process according to the level of physical fitness of athletes who specialize in powerlifting. The author’s technique included exercises that were performed in static-dynamic and strength modes. The study of the effectiveness of the introduction of the author’s methodology in the training process of high school students in a general educational institution determined a positive effect on special and physical fitness.

Numerical solution to optimal control problems of oscillatory processes

<p style='text-indent:20px;'>A numerical approach to the investigation of optimal control problems of oscillatory processes with boundary and intermediate concentrated (lumped) control actions has been proposed in this paper. The corresponding analytical formulas for the components of the target functional gradient with respect to control actions considered on the class of piecewise continuous functions are obtained. The results of numerical experiments on the examples of solving model problems of optimal control of oscillatory processes with boundary and intermediate concentrated controls are provided. These results illustrate the dependence of the minimum settling time of oscillatory processes on the number and locations of concentrated control actions, on the process parameters, on the resistance coefficient of the medium (dissipation factor), and other factors.</p>

Intelligent boring automatic machine for optimal control drilling of oil and gas wells

The main methods of ensuring optimal conditions for drilling oil and gas wells are considered. The method concern the optimal control of the drilling process and an adaptive method of automatic control of the axial load on the bit by using a boring automatic machine, in which rock at the borehole bottom is recognized, the calculation of the optimal axial load and the borehole bottom is drilled according to the optimization criterion «maximum mechanical speed». Keywords well drilling, adaptive optimal control, drilling model, boring automatic machinewell drilling, adaptive optimal control, drilling model, boring automatic machine

Emergency Decision-making Method of Unconventional Emergencies in Higher Education Based on Intensive Learning.

In order to improve the emergency decision-making and management ability of unconventional emergencies in Colleges and universities, an emergency decision-making method for unconventional emergencies in Colleges and Universities based on reinforcement learning is proposed. The function of the emergency decision-making model of unconventional emergencies in Colleges and universities is constructed, and the optimal control of the emergency decision-making process of unconventional emergencies in Colleges and universities is realized by using the queuing theory model. Based on the sub-sequence decomposition method, the reinforcement learning function is optimized. Combined with big data scheduling and the empirical mode decomposition method, the effective probability density function of emergency decision-making for unconventional emergencies in higher education is calculated, and the optimal solution vector analysis of emergency management and scheduling decision-making for unconventional emergencies in Colleges and universities is realized according to parameter estimation and quantitative optimization results. The test results show that this method has a good ability to optimize and schedule the emergency decision-making of unconventional emergencies in higher education, and has strong convergence. This method improves the emergency response-ability, and the time cost is short.

Application of the method of artificial immune systems in solving the problem of optimal control of a chemical process with terminal constraints

Application of the method of artificial immune systems in solving the problem of optimal control of a chemical process with terminal constraints

A big step ahead in Metal Science and Technology through the application of Artificial Intelligence

Digitalization is a key enabling factor of the dramatic transformation of metal industry since the 90-ies. Important applications were implemented since then, exploiting multi-physical modelling, complex real time process control and Machine Learning. This trend was further enhanced and accelerated by Industry 4.0. Digitalization implies harvesting impressive volumes of heterogeneous data, which need to be stored, processed and, mostly, interpreted to extract relevant information and “knowledge”. Knowledge means capability of interpreting data, of explaining and representing material transformation and product evolution during the different process stages considering complex interactions among process and product variables, including aspects still not perfectly understood. Artificial Intelligence supports knowledge extraction by enabling optimal process management and control, higher flexibility and product quality, stronger resource and energy efficiency, namely sustainability. Challenges and opportunities of enhancing metallurgical science and technology through Artificial intelligence are considered in this review.

УПРАВЛЕНИЕ ТЕМПЕРАТУРНЫМ РЕЖИМОМ НИЖНИХ ЗОН МЕТОДИЧЕСКИХ ПЕЧЕЙ

Introduction. The problem of ensuring the identity of the heating trajectories of the upper and lower halves of the slab (slab heating symmetry) is considered for significantly different numerical values of the external heat transfer parameters for its upper and lower surfaces. This is due, in particular, to poor thermal insulation of the hearth pipes. Purpose of the study. To develop an algorithm for calculating the ratio of settings (tasks) required for symmetry for the temperature controllers of the working space of the upper and lower heating zones of continuous furnaces. Materials and methods. The analysis and generalization of literature data on the problem is carried out. A mathematical description of asymmetric heating is proposed, an optimization problem is posed and solved. Results. Algorithm variants provide for the possibility of describing external and internal heat transfer both in linearized and in the original non-linear form. For the case of representation of the heating process by a fully linearized heat conduction equation with a convective form of external heat transfer, the desired result is represented by an analytical formula. This, as is known, makes it possible to trace the influence of the initial process parameters on the optimal ratio of settings. Numerical research shows that observance of the calculated ratio of the settings ensures a satisfactory coincidence of the mass-average temperature trajectories of the upper and lower halves of the slab in the case of asymmetric heating itself (inequality of external heat transfer coefficients). A simplified solution of the problem under consideration is also proposed, when the dynamics of mass-average temperatures of the upper and lower halves of the slab is initially described by a first-order ordinary differential equation obtained from the heat conduction equation by integral temperature averaging over the thickness of the slab. The simplified version also provides, as a rule, practically acceptable proximity of the heating trajectories of the upper and lower halves of the slab and is even more “transparent” as to how the initial data affects the desired result. Conclusion. The use of the optimal ratio of settings allows, for example, when solving problems of optimal process control, to reduce the dimension of the desired control vector by half, which is very important in the development of algorithmic support for automated process control systems for heating furnaces.

Search for optimal control with terminal constraints at petrochemical processes modeling

A method for solving the problem of a petrochemical process optimal control with terminal constraints is considered. The statement of the optimal control problem with constraints on the control parameter and terminal constraints of the equality type is given in a general form. A method for solving this problem based on the penalty method and the artificial immune systems method is described. A computational experiment for a model example is carried out, as a result of which the parameters of the optimal process control and the corresponding optimal trajectories of phase variables are determined. Keywords optimal control, penalty method, artificial immune systems, terminal constraints

Optimal control of a stochastic diffusion process with functional equality and inequality constraints

We consider a problem of optimal control of a multidimensional process specified by Ito stochastic differential equation, in the presence of functional equality and inequality constraints on the phase trajectory, with the control acting on the drift coefficient. Sufficiently general and at the same time constructively verifiable first- and second-order necessary optimality conditions are formulated in terms of variations of functionals.

Artificial Neural Network and Its Application Research Progress in Chemical Process

Most chemical processes, such as distillation, absorption, extraction, and catalytic reactions, are extremely complex processes affected by multiple factors. As a result, the relationships between their input and output variables are non-linear, and it is not easy to optimize or control them using traditional methods. Artificial neural network is a systematic structure composed of multiple neuron models. By simulating many basic functions of the nervous system of living organisms, nonlinear control can be realized without relying on mathematical models, and it is especially suitable for more complex control objects. This article will introduce artificial neural networks' basic principles and development history, and review its application research progress in chemical process control, fault diagnosis, and process optimization.

Separability-based selection of cost-effective control of multistep processes in limited time and money

Modeling as a research method usually consists not in the preparation of proposals and the formation of technical requirements in the created sample, but at the stages of conceptual and technical design, in the development of product samples in systems using them, as well as in various tests. This article discusses optimal control of multi-step processes. Usually, in practice, the problem of constructing models of multistage processes, as a rule, is complicated by the universality, uncertainty and nonlinearity of the simulated objects, complete or partial lack of expert experience and analytical description of dependencies. Mathematical models describing chemical technology consider the partitioning of the state into discrete stages.

Heavy Mineral Sands Mining and Downstream Processing: Value of Mineralogical Monitoring Using XRD

Heavy mineral sands are the source of various commodities such as white titanium dioxide pigment and titanium metal. The three case studies in this paper show the value of X-ray diffraction (XRD) and statistical methods such as data clustering for process optimization and quality control during heavy mineral processing. The potential of XRD as an automatable, reliable tool, useful in the characterization of heavy mineral concentrates, product streams and titania slag is demonstrated. The recent development of ultra-high-speed X-ray detectors and automated quantification allows for ‘on the fly’ quantitative X-ray diffraction analysis and truly interactive process control, especially in the sector of heavy mineral concentration and processing. Apart from the information about the composition of a raw ore, heavy mineral concentrate and the various product streams or titania slag, this paper provides useful information by the quantitative determination of the crystalline phases and the amorphous content. The analysis of the phases can help to optimize the concentration of ores and reduction of ilmenite concentrate. Traditionally, quality control of heavy mineral concentrates and titania slag relies mainly on elemental, chemical, gravimetrical, and magnetic analysis. Since the efficiency of concentration of minerals in the different product streams and reduction depends on the content of the different minerals, and for the latter on the titanium and iron phases such as ilmenite FeTiO3, rutile TiO2, anatase TiO2, or the various titanium oxides with different oxidation stages, fast and direct analysis of the phases is required.

Applying load profiles propagation to machine learning based electrical energy forecasting

Electrical energy generation represents an economical and environmental challenge requiring an optimal control of the production process. An accurate modeling of the electrical energy is essential to develop efficient forecasting systems. To achieve this goal, this paper introduces an innovative load forecasting approach using Load Profiles (LPs). First, the power consumption in Algeria is analyzed to detect the different factors affecting the demand. Then, the fluctuation of the seasonal data is applied through hourly temperature profiles. The LP-based forecasting is performed using three levels (annual, weekly and daily) LP-propagation. Short-term and mid-term load forecasting models were developed using multiple Artificial Intelligence techniques. Among them, a two-dimensional Convolutional Neural Network (CNN) used here for the first time in load forecasting. The resulting prediction accuracies of both the Artificial Intelligence (AI)-based and LP-based models were considerably high, producing (MAPE= 0.80%, RMSE= 75.57MW, Willmott's Index (WI) = 0.99) for the two-dimensional CNN. Compared to (MAPE= 3.86%, RMSE= 372.68 MW, WI= 0.95) for the LP-propagation technique.

Methanol–Water Purification Control Using Multi-Loop PI Controllers Based on Linear Set Point and Disturbance Models

Dimethyl ether (DME), derived from methanol, has been issued as an alternative to diesel and LPG. This study will continue the research of an optimized process control design for DME purification plants, specifically the methanol purification process. This way, water can be separated, and the main product, methanol, can be recycled for DME synthesis. A setpoint-based linear model of a methanol–water purification system has been developed with four controlled variables (CV) with objectives to; maintain a separated liquid water stream in the bottom stage (Stage 30) of the distillation column for methanol–water separation at 11.22%, keep the purified liquid methanol at a condenser at 58.81 °C and 49.96% of level, and the last CV is the cooler in the distillate stream, to keep the purified methanol’s top product at 40.75 °C. To complete the model, a first order plus dead time (FOPDT) disturbance model is created against the inlet temperature and flow rate of the feed, the major cause of disturbances in the industry. Using a traditional proportional integral controller connected to each controlled variable, a multi-loop control system is formed with optimization and compared to the disturbance rejection of multivariable model predictive control (MMPC). The final improvement against the feed temperature and flow for CV1, CV2, CV3, and CV4 is shown by, respectively, Integral Absolute Error (IAE) values of 79.49%, 99.90%, 100%, and 99.99% and Integral Square Error (ISE) values of 97.1%, 100%, 99.99%, and 100%.

Natamycin: a natural preservative for food applications-a review.

The online version contains supplementary material available at 10.1007/s10068-021-00981-1.

A blended empirical shot stream velocity model for improvement of shot peening production

Peening intensity and coverage are vital measurement outputs to quantify the quality of a peening process in the surface enhancement operation of metal parts. In practice, these parameters can only be measured offline upon process completion, which is not suitable for online tracking and operation. Instead, shot stream velocity can be used as a real-time monitoring parameter to bridge operational inputs to the outputs. As such, a robust and accurate shot stream velocity model is needed for real-time tracking. In this study, we propose a blended practical model for shot stream velocity to address the issues. The model is constructed using a regression algorithm based on the blended candidate functions, which are developed from the experimental data and nature of the particle-air flow inside the system. The obtained model is validated against the experimental data for ASR 70 media type for different operating conditions of the inlet airflow pressure and media flowrate. Calculated velocities are in good agreement with the measurements. In addition, the developed model is applied to predict the shot stream velocity for ASR 230 media type, as well as to evaluate the peening intensity and coverage for different media types under different operating conditions. The predicted results are comparable to the measurement data under the same operating conditions. The maximum relative error of the predicted shot stream velocity and measurement velocity is about 5%, while the maximum error in peening intensity is about ±0.0065 mmA. Furthermore, a single-input and single-output model-based control is developed based on the proposed shot stream velocity model. The developed control system is robust, accurate, and reliable. It implies that the developed model can be used to provide the necessary information, as well as to develop the optimal process control system to improve and accelerate the peening processes for cost and time reduction of actual production.