Network Model Predictive Control Research Articles

Chaos-Based NMPC as a Novel MPPT Approach for Organıc Photovoltaıcs

Environmental degradation, alongside the dire consequences of climate change such as the melting of glaciers and rising sea levels, highlight the severe challenges associated with reliance on fossil fuels. As such, the shift towards sustainable and clean renewable energy sources, like photovoltaic systems, is becoming increasingly critical. This paper introduces a novel approach leveraging a chaotic-based nonlinear model predictive control to maximize the power output from organic photovoltaic cells. This method is distinguished by its rapid tracking capabilities and its effectiveness in enhancing the distribution network's performance under fault conditions. Utilizing a feedback-driven recursive control strategy, this approach efficiently predicts and adjusts to the optimal operating state, thereby minimizing its cost function. It comprises two primary phases: estimating the reference point and subsequently adjusting the operating point in alignment with this reference. In this process, the Lagrange function plays a pivotal role in optimizing the estimator's performance, while a chaotic neural network model predictive controller manages the boost converter's operation. Implementing this chaos-based nonlinear model predictive controller has successfully reduced overvoltage incidents by more than 1.3%. Notably, in the absence of such control methods, the penetration of OPV panels leads to voltage fluctuations beyond acceptable limits. The findings demonstrate that, alongside a decrease in network losses, there is an increase in the capacity of distribution feeders and a notable enhancement in the system's overall efficiency.

Neural network predictive control of converter inlet temperature based on event‐triggered mechanism in flue gas acid production

AbstractThe process of smelting non‐ferrous metals results in significant emissions of flue gas that contains sulfur dioxide (SO), which is very harmful to the environment. Through precise control of converter inlet temperature, it is feasible to enhance the conversion ratio of SO and simultaneously mitigate environmental pollution by generating acid from flue gas. Because of the high degree of uncertainty in smelting process, converter inlet temperature is challenging to regulate and controller frequently needs updating. To improve control performance and decrease controller update times, an event‐triggered neural network model predictive control (ETNMPC) strategy is proposed. First, long short‐term memory (LSTM) prediction model and model predictive controller are developed. Second, it is decided whether to update the existing controller by designing an event‐triggered mechanism. Finally, using real data from a copper facility in Jiangxi Province, the temperature control experiment of converter inlet is carried out. Simulation results demonstrate that the proposed ETNMPC outperforms conventional time‐triggered method in terms of control performance, greatly lowers the times of controller updates, and significantly lowers computation costs and communication burden.

Development of a neural network model predictive controller for the fluidized bed biomass gasification process

In this study, an advanced controller for the fluidized bed biomass gasification (FBG) process is proposed. The controller is based on the model predictive control method, utilizing a long short-term memory neural network to accurately predict the controlled variable in the FBG process. Then, employing a gradient-based optimization algorithm, it optimizes the inputs to achieve the desired control objective. The controller specifically aims for temperature regulation in three spatial regions (fluidized bed, freeboard and outlet), using primary air, secondary air, and biomass flow rates as input variables. Open-loop simulations are used to fine-tune the controller's parameters (prediction and control horizon). For unbiased controller testing, a computational fluid dynamics (CFD) model of the FBG process is also developed, which is integrated with the controller in a closed-loop system, simulating real-process feedback for performance evaluation. The proposed controller effectively maintains temperatures (steady state error < 1.5 %) at desired set points (800–900 °C) with a short prediction horizon of 24 time steps, reducing response time to under 5 s, making it suitable for real-time FBG process control.

Model predictive coordinated cooperative control mechanism for multiagent systems based on priority negotiation

Aiming at the control requirements in complex industrial processes and the problem of poor decision-making flexibility of agents in state/output difference-based consensus strategies, a novel model predictive coordinated cooperative control mechanism is proposed using multiagent systems as the computational paradigm. The proposed mechanism considers the global state of the system, the interaction of control actions among agents, the constraints of the process, and energy consumption. According to the proposed coordinated cooperative control mechanism, each agent must accomplish three tasks at each time step. First, each agent proposes its own “winner-takes-all” control scheme and calculates its payoff. Then, adjacent agents determine their own priorities at the current time step according to the payoffs of the “winner-takes-all” scheme by using a designed pairwise game mechanism. Next, each agent, in order of priority, calculates its sequence of actual optimal control input increments by applying the dynamic predictive control approach based on the dynamic model of the system. Finally, the effectiveness of the proposed coordinated cooperative control mechanism is verified by comparing it with the networked coordination-based distributed model predictive control approach and the centralized model predictive control approach based on the temperature control process of heating an alumina ceramic block in a high-power microwave reactor with six microwave sources.

Optimizing power consumption and position control in an electro-hydraulic system with cylinder bypass and NN-MPC

This study introduces an innovative approach to enhance the energy efficiency and position control performance of electro-hydraulic systems, employing a comprehensive comparative analysis. It presents and evaluates three control techniques: Proportional-Integral-Derivative (PID) control, Model Predictive Control (MPC), and Neural Network Model Predictive Control (NN-MPC). These methods are systematically assessed across varying load conditions. Notably, our research unequivocally establishes the exceptional performance of the NN-MPC approach, even when confronted with load variations. Furthermore, the study conducts an exhaustive examination of energy consumption by comparing a conventional system, where a flow control valve is not utilized as a hydraulic cylinder bypass, with a proposed system that employs a fully open Flow Control Valve (FCV). The results underscore the remarkable energy savings achieved, reaching up to 9% at high load levels.

Notice of Violation of IEEE Publication Principles: Sequential Convex Programming for Collaboration of Connected and Automated Vehicles

Notice of Violation of IEEE Publication Principles<BR><BR>"Sequential Convex Programming for Collaboration of Connected and Automated Vehicles," <BR>by Xiaoxue Zhang, Jun Ma, Zilong Cheng, Frank L. Lewis, and Tong Heng Lee, <BR>in IEEE Transactions on Intelligent Vehicles, Early Access <BR><BR>After careful and considered review of the content and authorship of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE’s Publication Principles. <BR><BR>This paper contains significant portions of original text from the paper cited below. The original text was copied without attribution (including appropriate references to the original author(s) and/or paper title) and without permission. <BR><BR>"Networked Model Predictive Control for Vehicle Collision Avoidance" <BR> by Bassam Alrifaee, <BR>in RWTH Aachen University, Dissertation, 04 May 2017 <BR>BR>"Sequential convex programming MPC for dynamic vehicle collision avoidance" <BR>by Bassam Alrifaee, Janis Maczijewski, Dirk Abel, <BR>in the Proceedings of the IEEE Conference on Control Technology and Applications, 2017, pp. 2202-2207 <BR><BR> <br/> This paper investigates the collaboration of multiple connected and automated vehicles (CAVs) in different scenarios. In general, the collaboration of CAVs can be formulated as a nonlinear and nonconvex MPC problem. Most of the existing approaches available for utilization to solve such an optimization problem suffer from the drawback of considerable computational burden, which hinders the practical implementation in real time. This paper proposes the use of SCP, which is a powerful approach to solving the nonlinear and nonconvex MPC problem in real time. To appropriately deploy the methodology, as a first stage, SCP requires linearization and discretization when addressing the nonlinear dynamics of the system model adequately. Based on the linearization and discretization, the original MPC problem can be transformed into a QCQP problem. Besides, SCP also involves convexification to handle the associated nonconvex constraints. Thus, the nonconvex QCQP can be reduced to a quadratic programming (QP) problem that can be solved rather quickly. Therefore, the computational efficiency is suitably improved despite the existence of nonlinear and nonconvex characteristics, whereby the implementation is realized in real time. Furthermore, simulation results in three different scenarios of autonomous driving are presented to validate the effectiveness and efficiency of our proposed approach.

Multiple-input multiple-output Radial Basis Function Neural Network modeling and model predictive control of a biomass boiler

This study presents a model predictive control of a 4 × 3 Multiple-Input Multiple-Output (MIMO) biomass control system that uses radial basis function (RBF) as an activation function to enhance the control performance. The biomass boiler model is developed from the system identification box in MATLAB by collecting measured input and output data from the 31.5 MW Wonji sugar mill and analyzing the data using black box modeling approach. The major goal of this study is to improve the MIMO control performance of a biomass boiler by utilizing Radial Basis Function Neural Network (RBFNN) to increase model accuracy which ultimately enhances the overall control system. Biomass boilers have four inputs and three outputs. The inputs are airflow 1, airflow 2, water flow and stocker speed (the speed of the motor which feeds bagasse or sugarcane pulp) and outputs are temperature, pressure and drum level. The RBFNN model was programmed using MATLAB R2021a software with system identification toolbox. Shorter settling times of 0.286 s, 1.873 s, and 0.637 s, as well as tolerable overshoots of 0.505%, 1.5%, and 15.698% for temperature, pressure, and level respectively, were achieved with the suggested model predictive controller using RBFNN model. However, when utilizing the identical controller and state space model, the settling times are 2.318 s, 5.461 s, and 6.147 s, with overshoots of 4.737%, 8.152%, and 38.194% for the three variables respectively. The suggested method was compared to the model predictive control (MPC) biomass boiler state space model, which can be considered as a model without RBFNN. The simulation results indicate that the RBFNN-based MPC performed better than the state space model-based MPC. This is because, the state space model is always constant, in contrast to the neural network's active monitoring of boiler dynamics.

Synthesis of model predictive control based on neural network for energy consumption enhancement in building

The problem addressed in this work is the enhancement of energy efficiency in buildings, primarily focused on heating control. The paper highlights the importance of addressing this challenge, given that HVAC systems are responsible for over 60% of total energy consumption in buildings, making them the largest energy consumers in both the residential and nonresidential sectors. This paper presents a methodology for developing a model predictive control (MPC) system based on artificial neural network (ANN) models, with the aim of improving the energy efficiency of buildings. This approach involves the creation of a training dataset using dynamic thermal simulation tools, enabling the learning of the ANN model that is responsible for predicting future states within an MPC optimization loop. Additionally, the implementation leverages advanced technologies such as Field-Programmable Gate Arrays (FPGAs), specifically the PYNQ board, Wi-Fi modules, and MQTT communication to enhance scalability, deployment, and adaptability. The study evaluates the proposed Neural Network Model Predictive Control (NNMPC) strategy implemented on the PYNQ, reporting a substantial reduction of 38.53% in heating energy consumption in buildings compared to a basic On/Off control approach for 24-hour simulation. This outcome underscores the solutions significant potential for energy savings in building heating systems.

A novel method of neural network model predictive control integrated process monitoring and applications to hot rolling process

The stable control of product quality when abnormal working conditions occur in the industrial production process is essential to improve product quality and economic efficiency. However, the process industry suffers from multivariate, nonlinear, uncertainty, long time delays and frequent failures, making its modeling and control difficult. In this paper, a novel method of neural network model predictive control integrated process monitoring (PM-NNMPC) is proposed. First, the combination of gated recurrent unit and convolutional neural network (GRU-CNN) is used to extract the features from the time and the space separately to build prediction models for different working conditions of the process. Then, a process monitoring and fault diagnosis method of principal component analysis combined with deep neural network and XGBoost (PCA-DNN-XGBoost) is designed to monitor the working conditions in real-time and diagnose accurately when faults occur. Finally, a new operation control framework integrating process monitoring and fault diagnosis into the model prediction control is designed to solve the problem that equipment operation failure, which makes the product quality fluctuation because of the model mismatch and the system runaway. The experimental results of hot rolling process show that PM-NNMPC can effectively control the system under normal working conditions and in case of the system failure to ensure the stable product quality.

Neural Network Model-Predictive Control for CHB Converters With FPGA Implementation

Finite Control Set Model Predictive Control appears an interesting and effective control technique for Cascaded H-Bridge converters but, because of its computational complexity, becomes impractical when the number of levels of the converter increases. This paper proposes a Neural Network-based approach capable of overcoming the computational burden of conventional predictive control algorithms. The proposed control is then applied to a Cascaded H-Bridge Static Synchronous Compensator using FPGA and tested via hardware in the loop. Results and analysis demonstrate that optimal control of multilevel converters with many levels can be obtained with low computational effort.

Constrained Neural Network Model Predictive Controller Based on Archimedes Optimization Algorithm with Application to Robot Manipulators

Constrained Neural Network Model Predictive Controller Based on Archimedes Optimization Algorithm with Application to Robot Manipulators

An AI framework integrating physics-informed neural network with predictive control for energy-efficient food production in the built environment

Relieving the stress from energy demand is critical for encouraging the application of built environment in agriculture, which is the most energy-intensive food-production sector. In this study, to enhance energy efficiency and crop growth optimization for the built environment, we present a novel artificial intelligence (AI)-based control framework which combines a physics-informed neural network and data-driven robust model predictive control. The physics-informed neural network is constructed for accurately predicting the built environment’s indoor climate and crop states based on control inputs, including controls of temperature, humidity, CO2, irrigation, and fertilization. Data-driven robust model predictive control uses machine learning techniques to account for unpredictable changes in weather conditions to make the best control decisions for actuators. Two examples of the implementation of the proposed AI-based control framework in tomato cultivation environments in Ithaca, New York and Tucson, Arizona are shown to showcase its effectiveness in varying climates. The results show our proposed AI-based control framework can maintain the ideal cultivation environment and, on average, lower cost by 46.4% compared to the conventional control approaches.

A Prediction-Based Approach Realizing Finite-Time Convergence of Networked Control Systems

This paper presents a networked model predictive control (MPC) strategy for the finite-time convergence of networked control systems with two-channel random communication constraints. Network-induced delays and packet dropouts in the backward and forward channels are transformed into the equivalent delays in each channel, which are actively compensated in the controller and actuator, respectively. Future control inputs are obtained by a finite-time MPC strategy, and the upper bound of the convergence time is given by theoretical analysis. Finally, the proposed scheme is verified by the numerical simulation of a mass-spring-damper system.

Development of model predictive controller in avoidance design of Unmanned Aerial Vehicle (UAV)

This research was accomplished by employing already developed mathematical model of a 6DoF UAV in free space through the motion of the 6DoF aircraft (unmanned aerial vehicle) determined by coordinate systems which allow an aircraft’s position and orientation in space to be kept tracked. The discrete method of the model developed for simulation in Simulink was realized with a suitable transfer function. Then, an artificial neural network model predictive adaptive controller that can handle the nonlinearities associated with the UAV was developed based on state space technique and the model predictive controller (MPC) utilizes a neural network model to envisage future plant (aircraft) responses to potential control signals. The developed model predictive controller network was successfully trained offline using Feed-forward Back-propagation algorithm with speed and position as inputs since the underlying objective of this work is to improve the speed and position in order to advance the safety collision distance of the UAV because these parameters are mostly considered in the avoidance maneuver performance. Also, the results reveal that the speed of the generated UAV is approximately the input speed of 75MS–1 during the time the UAV is affecting maneuvering. Significance of the result is that the proposed algorithm is capable of generating collision-free trajectory for different waypoint cases.

Dynamic Obstacle Avoidance for USVs Using Cross-Domain Deep Reinforcement Learning and Neural Network Model Predictive Controller

This work presents a framework that allows Unmanned Surface Vehicles (USVs) to avoid dynamic obstacles through initial training on an Unmanned Ground Vehicle (UGV) and cross-domain retraining on a USV. This is achieved by integrating a Deep Reinforcement Learning (DRL) agent that generates high-level control commands and leveraging a neural network based model predictive controller (NN-MPC) to reach target waypoints and reject disturbances. A Deep Q Network (DQN) utilized in this framework is trained in a ground environment using a Turtlebot robot and retrained in a water environment using the BREAM USV in the Gazebo simulator to avoid dynamic obstacles. The network is then validated in both simulation and real-world tests. The cross-domain learning largely decreases the training time (28%) and increases the obstacle avoidance performance (70 more reward points) compared to pure water domain training. This methodology shows that it is possible to leverage the data-rich and accessible ground environments to train DRL agent in data-poor and difficult-to-access marine environments. This will allow rapid and iterative agent development without further training due to the change in environment or vehicle dynamics.

Neural network MPC for heating section of annealing furnace

Annealing is a process that modifies the properties of steel by heating. An annealing furnace has large thermal inertia due to its size; therefore, research using a model predictive controller (MPC) has been conducted for precise control. An traditional physical model-based MPC requires a dynamic model of the annealing furnace, which necessitates several states and many accurate physical parameters. In addition, predicting the future output of such a high-order dynamic model requires too much time for real-time control. To resolve such issues, the neural network MPC has been proposed on other fields, but the algorithms were not applicable to the large-scale thermal system. Therefore, we propose a novel data-driven neural network MPC and predictive model that uses LSTM layer, which does not require knowledge of the physical parameters, and is applicable to the annealing furnace. Additionally, the proposed neural network MPC is fast enough for real-time control. Simulation scenarios show transient and steady-state performance respectively. The proposed neural network MPC showed high control accuracy and fast speed compared to the previous controllers. The proposed method resolves problems that the conventional MPC have such as the requirement of many physical parameters and computational complexity, enabling real-time predictive control of annealing furnaces to be achieved.

Neural-Network-Based Nonlinear Model Predictive Control of Multiscale Crystallization Process

The purpose of this study was to develop an integrated control strategy for multiscale crystallization processes. An image analysis method using a deep learning neural network is used to measure the fine-scale information of the crystallization process, and the mathematical statistical method is adopted to obtain the mean size of the crystal population. A feedforward neural network is subsequently trained and employed in a nonlinear model predictive control formulation to obtain the optimal profile of the manipulated variable. The effectiveness of the proposed nonlinear model predictive control method is evaluated using alum cooling crystallization experiments. Experimental results demonstrate benefits of the proposed combination of feedforward neural network and nonlinear model predictive control method for the multiscale crystallization process.

Artificial neural network-based model predictive control for optimal operating conditions in proton exchange membrane fuel cells

In the large-scale commercialization of proton exchange membrane fuel cells (PEMFC), efficient control of the dynamic operation requires the consideration of complex nonlinearities in current, temperature, pressure, and membrane hydration. In this study, an artificial neural network (ANN) model was developed and integrated with model predictive control (MPC) to provide optimal conditions for operating the PEMFC system under different current load changes. For this purpose, after modeling a 1.2 kW PEMFC in a MATLAB/Simulink environment, the accuracy of the model was validated within a maximum relative error of 2.30% compared to the experimental data. Next, the power production, temperature, and internal relative humidity of the model were extracted under all feasible operating conditions. The extracted data were used to train the nonlinear autoregressive network with exogenous inputs (NARX), and hyperparameters of neural networks were selected through Bayesian optimization. The NARX model trained with optimal parameters had a mean square error (MSE) of 2.14 × 10−4 and was integrated into the MPC to obtain neural network model predictive control (NNMPC). The developed NNMPC provides the optimal operating temperature and pressure for the PEMFC model at 10-s intervals through iterative simulation of the NARX under Bayesian optimization. To verify the performance of the control system, the developed NNMPC and fixed-setpoint scenario were compared. Each control scenario consisted of three current load profiles: low, medium, and high current. The NNMPC yielded improved system power by maintaining the optimal stack temperature, cathode pressure and membrane hydration for current changes at a low computational cost. The optimized power of the PEMFC system showed an average increase of 10.9% compared to fixed-setpoint condition.

Control of a closed dry grinding circuit with ball mills using predictive control based on neural networks

Closed circuit dry grinding using ball mills is essential in mineral processing industries. This process is characterized by significant dead times, highly coupled variables, limitations by operating ranges and complex modeling, making it difficult for classical controls to obtain fast responses with low overshoot. An alternative to overcome these difficulties is intelligent controls, such as the artificial neural network model predictive control (NNMPC). This study aimed to develop a NNMPC for dry grinding in a closed circuit with a ball mill. Artificial Neural Network represented the multi-input-multi-output system for the model to predict the outputs in the predictive control strategy. Compared to the classical controls and linear model predictive control, the results obtained by the NNMPC were superior with lower errors and better robustness, reaching a reduction of up to 79% and 74.2% for overshoot and settling time, respectively, besides being more efficient in simulations with simultaneous disturbances of the controlled variables.

Multilayer Game Collaborative Optimization Based on Elman Neural Network System Diagnosis in Shared Manufacturing Mode.

With the dynamic sharing of global resources shifted from the independent production of a single enterprise to and the development of collaborative manufacturing, today's manufacturing industry has collaborative production among multiple enterprises. This paper extends the optimization method of the multienterprise dynamic equipment collaborative scheduling system with the dynamic manufacturing network theory approach, combining the neural network system and model predictive control theory to continuously and dynamically diagnose the changes of demand and capacity in the actual production process and design the corresponding multilayer game collaborative optimization robust model according to the uncertainty relationship. The study considers the production characteristics and management needs of multiple enterprises within the manufacturing industry, as well as the optimization of the dynamic equipment collaborative scheduling system, uncertain demand, dynamic equipment matching effectiveness, and equipment failure under the shared manufacturing model, deduces the market capacity demand for manufacturing enterprises by inverse prediction of dynamic market demand through the simple recurrent neural network (Elman network), and then maximizes the idle equipment utilization and load capacity under the shared manufacturing model in model rolling optimization. This paper gives model solutions based on big data analysis and combines improved population intelligence algorithms to determine the dynamic matching of manufacturing resources, product supply and demand paths, and transportation flows. The simulation results show that the application of model predictive control theory to the model of Elman neural network system diagnosis can effectively reduce the adverse effects of the two-way uncertainty environment on the profitability of enterprises. Meanwhile, considering the maximum performance matching of dynamic equipment scheduling and combining with robust optimization methods will reduce the cost loss of manufacturing enterprises in the worst case, and the cost loss reduction can reach 24.73%. The analysis results verify that the method is of great practical significance in the direction of intelligent production collaboration and industrial digital transformation.