Proportional Integral Differential Controller Research Articles

Longitudinal and Lateral Cooperative Control of Preview Intelligent Vehicles with Stabilization

Aiming at the highly nonlinear and coupled longitudinal and transverse motion control problems of intelligent vehicle path tracking control, a new method of preview MPC path tracking control is proposed by combining visual preview model and model predictive control theory. The method first locally linearizes the nonlinear prediction model and transforms the MPC optimization solution problem into a quadratic programming problem. The longitudinal vehicle speed and the preview distance are then treated as known in each control time domain, an exponential model is applied to characterize the longitudinal vehicle speed, and a transverse angular velocity-center of mass lateral deflection (r-β\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$r-\\beta $$\\end{document}) phase plane plot is applied to characterize the vehicle stability. Finally, proportional integral differential stability controller is designed to improve vehicle stability. Simulation and test results show that: Compared with the MPC tracking control method, the preview MPC control method proposed in this paper can optimize the vehicle tracking performance on different adhesion coefficient road surfaces and improve the tracking accuracy, and this enhancement effect is more obvious at high speeds.

A model-based microfluidic feedback control system for replicating blood pressure and wall shear stress on the inner surface of common carotid artery induced by external counterpulsation

Replicating the hemodynamic signal of endothelial cells (ECs) induced by an external counterpulsation (ECP) using a microfluidic system is crucial for further studying EC mechanobiology associated with ECP theraphy. However, there is currently no suitable method to construct a microfluidic system that can accurately reproduce the hemodynamic signals including blood pressure (BP) and wall shear stress (WSS) on the inner surface of the common carotid artery following ECP intervention. In this study, we propose a model-based approach to build a microfluidic feedback control system (MFCS), which consists of a microfluidic chip and a pump system (PS) to resolve the above issue. An integrated transfer function (TF) model formed by the expression of the input impedance and the proportion integration differentiation (PID) controller is used to design the microfluidic chip and PS. The performance of the proposed MFCS for replicating the hemodynamic signals is evaluated by flow-field analysis, and calcium ion (Ca2+) response experiments are conducted to validate the functionality of the proposed MFCS for investigating mechanobiological mechanisms.

A Positioning and Tracking Performance–Enhanced Composite Control Algorithm for the Macro–Micro Precision Stage

In the macro–micro composite motion process, the macro stage achieves rapid motion in a large workspace, while the micro stage realizes precise positioning within a small displacement. The large-stroke and high-speed motion of the macro stage is influenced by nonlinear friction, overshooting, and vibrations, making it challenging to achieve rapid stabilization within the travel range of the micro stage, thereby impacting equipment operation efficiency. This paper proposes a composite controller structure designed to solve the fast point-to-point positioning of the macro stage driven by a linear motor and enhance the trajectory tracking performance of the stage. The proposed composite control algorithm (CCA) includes velocity feed-forward, gain-scheduled proportional integral differential (PID) control, and a plug-in repetitive control method. By employing a tracking differentiator, velocity feed-forward, and a gain-scheduled PID controller, the control algorithm can realize rapid stabilization and positioning for the macro stage. Through velocity feed-forward, gain-scheduled PID control, and a plug-in repetitive controller, the control algorithm can reduce the trajectory tracking error of the stage. Simulations and experimental studies of point response and sinusoidal trajectory tracking are carried out on a macro–micro stage to verify the effectiveness of the composite controller for the linear motor. The experimental results demonstrate that the proposed composite controller effectively reduces the macro stage’s settling time and overshoot, and improves the accuracy of sinusoidal trajectory tracking, which lays a foundation for submicron positioning accuracy in high-speed macro–micro motion stages.

Research on adaptive hydraulic drive optimization control of concrete mixing tank truck for open-pit mine.

The non-axisymmetric problem caused by the fluid sloshing in the tank of a mining concrete mixing tank truck during driving is affected by the excitation of complex road surfaces. The fluid sloshing is coupled with the dynamics of the vehicle body due to the excitation of the complex road surface. The traditional hydraulic drive proportional integral differential (PID) control method is not effective in dealing with such problems, which can easily lead to accidents such as overturning. To improve the accuracy and stability of the hydraulic drive control system, this paper proposes an optimized particle filter PID adaptive control method based on the elastic firefly (FA) algorithm to accelerate the convergence speed of control parameter optimization, and then analyzes its hydraulic drive control characteristics and structural applications, and discusses step steering and double lane change modes are simulated under filling rates of 1.5 and 2.0, respectively. The experimental results show that compared with traditional PID control, the proposed adaptive control method can significantly reduce the average speed error of hydraulic drive control to 0.03km/h and the maximum speed error to 0.17km/h. It also improves the control tracking performance and stability. The practicality of the adaptive hydraulic drive is verified in the filling rate experiments under step steering and double-lane shifting conditions. It has important reference value for the practical application of hydraulic drive control optimization of mining concrete mixing transport tank trucks.

Research on Heave Compensation System Based on Switched Reluctance Motor

Aiming at the requirements of the marine work platform for real-time control, time-varying speed and the time-varying torque control of the motor-driven active heave compensation device, this paper introduces a composite control strategy based on the switched reluctance motor (SRM)-driven active heave compensation device. As for the compensation error caused by the time lag in the real-time system, the model prediction trajectory algorithm is used to predict the compensation displacement obtained using the dynamic model. The next time, the control parameters are then provided for the SRM control system in advance to reduce the compensation error. The SRM control strategy selects a double closed-loop compound control strategy of Back Propagation (BP) fuzzy neural network Proportion Integration Differentiation (PID) control. Its outer speed loop uses a fuzzy controller to quickly track a wide range of speed changes. The torque inner loop uses BP neural network adaptive PID control. This helps to reduce torque ripple and to ensure that the electromagnetic torque output of the SRM remains stable. Finally, the system feasibility is verified by setting different wave parameters. The simulation results show that the simulation conditions can reach 97.5% and 96.4% under the 3 and 4 wave levels, respectively. The simulation effect is satisfying, which verifies the feasibility of the proposed scheme.

A Deep Reinforcement Learning Approach to Injection Speed Control in Injection Molding Machines with Servomotor-Driven Constant Pump Hydraulic System

The control of the injection speed in hydraulic injection molding machines is critical to product quality and production efficiency. This paper analyzes servomotor-driven constant pump hydraulic systems in injection molding machines to achieve optimal tracking control of the injection speed. We propose an efficient reinforcement learning (RL)-based approach to achieve fast tracking control of the injection speed within predefined time constraints. First, we construct a precise Markov decision process model that defines the state space, action space, and reward function. Then, we establish a tracking strategy using the Deep Deterministic Policy Gradient RL method, which allows the controller to learn optimal policies by interacting with the environment. Careful attention is also paid to the network architecture and the definition of states/actions to ensure the effectiveness of the proposed method. Extensive numerical results validate the proposed approach and demonstrate accurate and efficient tracking of the injection velocity. The controller’s ability to learn and adapt in real time provides a significant advantage over the traditional Proportion Integration Differentiation controller. The proposed method provides a practical solution to the challenge of maintaining accurate control of the injection speed in the manufacturing process.

Control of thermal uniformity in microwave heating process by BPNN and adaptive particle swarm optimization

As China advances its green economy, innovative methods are being employed to enhance energy optimization and conservation within energy-intensive industries. Among these methods, microwave heating stands out due to its superior heating efficiency and lack of pollution. Nonetheless, uniform heating remains a challenge because the microwave absorption capacity of the heated medium varies with changes in heating time and temperature. To address this issue, an Adaptive Particle Swarm Optimization (APSO) neural network microwave system based on the Back Propagation Neural Network (BPNN) is proposed. This system leverages the fundamental principles of Particle Swarm Optimization (PSO), categorizing particle swarms into three types and iterating them through distinct processes to achieve optimal results. An APSO controller is designed based on system identification, adjusting the controller parameters according to the error between the real-time system output and the identification model. The feedback error is used as the fitness function in the PSO algorithm, continuously adjusting the weights and thresholds of the neural network. This intelligent control approach optimizes the microwave oven's input power to minimize the error between the actual temperature output and the identified temperature. The APSO controller is designed based on system identification, with the intelligently controlled microwave heating system adjusting its input power to minimize the error between the identified and actual temperature outputs. Unlike traditional Proportional Integral Differential (PID) and BPNN controllers, this approach calculates the output of the identified model and the error of the actual model, feeding this information back to the controller. The feedback error serves as the fitness function in the PSO algorithm, enabling continuous adjustment of the network's weights and thresholds to regulate the microwave equipment's output power, thereby ensuring the output temperature closely follows the preset temperature curve. Experimental results demonstrate that the actual output value of the system closely aligns with the original preset temperature curve, with a root mean square error of only 0.74. This designed identification and control system effectively achieves the desired outcome.

Research on Satellite Navigation Control of Six‐Crawler Machinery Based on Fuzzy PID Algorithm

ABSTRACTThe six‐crawler driving mechanism plays a crucial role in the operation of large machines such as bucket‐wheel excavators, dumping machines, and mobile crushing stations, as it serves functions like bearing, movement and steering. The driving characteristics of this mechanism directly influence the safety and efficiency of these machinery systems. To enhance the design methodology for multi‐crawler machinery, improve path controllability, and achieve adaptive driving, a satellite navigation control system for six‐crawler machinery was developed based on the principles of real‐time kinematic (RTK) satellite positioning. This system utilizes the distance deviation and heading angle deviation between the actual path and the predetermined path of the six‐crawler machinery as inputs to a fuzzy proportion integration differentiation (fuzzy PID) controller. This controller regulates the deviation angle of the steering crawler and the driving speeds of each track, thereby ensuring precise path tracking control. To evaluate the path tracking control performance under both straight and curved driving conditions, a virtual prototype model of the six‐crawler mechanical system was established, and co‐simulation analysis was conducted. In addition, an experimental platform for path tracking control of six‐crawler machinery was established to validate the efficacy of the satellite navigation system. The actual tracking data obtained from various driving conditions and initial deviations demonstrated that the RTK satellite navigation path tracking control system exhibited excellent control performance.

Hybrid sand cat‐galactic swarm optimization‐based adaptive maximum power point tracking and blade pitch controller for wind energy conversion system

SummaryAs wind energy is sustainable, pollution‐free, easily available, and free of cost, it has become an efficient source of renewable energy for electricity generation. But, the problem with wind energy is that it varies with time, seasons, and location. This makes the Wind Energy Conversion System (WECS) unstable as it frequently needs to match the load demands. The balance in power generation by wind energy is essential since it has to be connected to various grids. So, this unbalanced energy production can affect the stability of the associated power grids as well. It also results in expensive regulatory measures, storage options, and load shedding. So, the stable operation of the WECS is highly essential to adapt it as a trustable source of electricity production. The stable operation of the WECS requires a robust and advanced system for control. Better control of the wind power extracting model is achieved by controlling the Maximum Power Point Tracking (MPPT) and blade pitch. So, an Adaptive MPPT and Blade Pitch Controller (BPC) for the WECS have been developed in this article, with the support of a hybrid optimization algorithm. In order to enhance the working principles of this controller, two effective algorithms such as Sand Cat Swarm Optimization (SCSO) and Galactic Swarm Optimization (GSO) are integrated and named Hybrid Sand Cat Galactic Swarm Optimization (HSC‐GSO). With the help of the recommended HSC‐GSO, the functionality of the controller is enhanced and also at the same time this algorithm helps to optimize the three gains in the Proportional Integral Differential (PID) controller of both MPPT and BPC, respectively. Moreover, with the support of the proposed HSC‐GSO the damping oscillations in the WECS output power and voltage are minimized. In the end, the numerical analysis is conducted for the presented system by comparing it with the traditional techniques. From the overall result analysis, the stability of the recommended adaptive WECS is 97, which is higher than the conventional algorithms such as DHOA, SCSO, GSO, and DA. Thus, it has been proved that the proposed HSC‐GSO algorithm for the parameters optimization in the PID controller of MPPT and the PID controller of BPC attains high robustness, increased steady‐state stability, and efficient transient response than the traditional techniques.

Dynamic analysis of an adiabatic compressed air energy storage system with temperature-regulated in air tanks

In this study, an innovative temperature regulation method is developed to augment the air storage capacity of adiabatic compressed air energy storage. Hot water, produced by recovering waste heat from the discharging process, is injected into these tanks to control the air temperature as needed. The transient-state calculation models have been established for each component, and validation is performed using experimental data obtained from published work. The utilization of proportion integration differentiation control technology enables precise regulation of the air outlet temperature of heat exchangers, achieving a control accuracy of 1K. The operational status of the components has been investigated, and a comparison is made between the performances of the modified and traditional adiabatic compressed air energy storage systems. The comparative analysis results show that the modified system can achieve a notable round trip efficiency of 71.71 %, which is comparable to that of conventional system (71.41 %). The effective air storage density of the modified system is 47.24 kg/m3, which presents a 15.08 % increase compared to traditional system (41.05 kg/m3). The influence of discharge pressure and pressure difference between threshold pressure and discharge pressure is also investigated. It is found that the modified adiabatic compressed air energy storage shows a consistently greater effective air storage density than traditional system, with a minimum increase exceeding 10.52 %.

Analysis and control of an active balance tail for the tilting dual-rotor UAV

PurposeCompared to quad-rotor unmanned aerial vehicle (UAV), the tilting dual-rotor UAV is more prone to instability during exercises and disturbances. The purpose of this paper is using an active balance tail to enhance the hovering stability and motion smoothness of tilting dual-rotor UAV.Design/methodology/approachA balance tail is proposed and integrated into the tilting dual-rotor UAV to enhance hovering stability and motion smoothness. By strategically moving, the balance tail generates additional force and moment, which can promote the rapid stability of the UAV. Subsequently, the control strategy of the UAV is designed, and the influence of the swing of the balance tail at different installation positions with different masses on the dual-rotor UAV is analyzed through simulation. The accompany motion law and the active control, which is based on cascade Proportion Integration Differentiation (PID) control to enhance the hovering stability and motion smoothness of the UAV, are proposed.FindingsThe results demonstrate that active control has obvious adjustment effectiveness when the UAV moves to the target position or makes an emergency stop compared with the results of balance tail no swing and accompany motion.Practical implicationsThe balance tail offers a straightforward means to enhance the motion smoothness of tilting dual-rotor UAV, rendering it safer and more reliable for practical applications.Originality/valueThe novelty of this works comes from the application of an active balance tail to improve the stability and motion smoothness of dual-rotor UAV.

PID Controller Design for an E. coli Fed-Batch Fermentation Process System Using Chaotic Electromagnetic Field Optimization

This paper presents an optimal tuning of a proportional integral differential (PID) controller used to maintain glucose concentration at a desired set point. The PID controller synthesizes an appropriate feed rate profile for an E. coli fed-batch cultivation process. Mathematical models are developed based on dynamic mass balance equations for biomass, substrate, and product concentration of the E. coli BL21(DE3)pPhyt109 fed-batch cultivation for bacterial phytase extracellular production. For model parameter identification and PID tuning, a hybrid metaheuristic technique—chaotic electromagnetic field optimization (CEFO)—is proposed. In the hybridization, a chaotic map is used for the generation of a new electromagnetic particle instead of the electromagnetic field optimization (EFO) search strategy. The CEFO combines the exploitation capability of the EFO algorithm and the exploration power of ten different chaotic maps. The comparison of the results with classical EFO shows the superior behaviour of the designed CEFO. An improvement of 30% of the objective function is achieved by applying CEFO. Based on the obtained mathematical models, 10 PID controllers are tuned. The simulation experiments show that the designed controllers are robust, resulting in a good control system performance. The closed-loop transient responses for the corresponding controllers are similar to the estimated models. The settling time of the control system based on the third PID controller for all estimated models is approximately 9 min and the overshoot is approximately 15%. The proposed CEFO algorithm can be considered an effective methodology for mathematical modelling and achievement of high quality and better performance of the designed closed-loop system for cultivation processes.

Research on Active Disturbance Rejection Control of Small Modular Reactor Once-Through Steam Generator Based on Differential Evolution Optimization Algorithm

The pressure control of once-through steam generator (OTSG) is critical for the operation and safety of small modular reactors. However, the dynamics of the OTSG are quite nonlinear, time varying, and uncertain. Classical control methods face significant challenges in keeping the pressure within acceptable limits in an environment with frequent load variations and multiple sources of external disturbances. In this paper, a robust control strategy based on active disturbance rejection control (ADRC) optimized by the differential evolution (DE) algorithm is proposed to satisfy the requirements of steam pressure control in an optimum and efficient way. First, a lumped parameter model for the OTSG is developed based on the notion of moving boundaries and linearized to introduce a transfer function model for control design purposes. Then a feedforward cascade control system based on an ADRC controller and a proportional integral differential (PID) controller is designed, which mainly consists of a pressure ADRC controller, a feedwater PID controller, and a feedforward compensator. To improve the pressure control performance and parameter tuning efficiency of the OTSG control system, a DE algorithm is applied to optimize the ADRC parameters, and the frequency domain and time domain characteristics are compared with particle swarm optimization and the genetic algorithm. Transient simulation experiments were used to evaluate the control performance at 100%, 50%, and 25% power levels, respectively. Moreover, a performance robustness criterion is proposed to demonstrate the robust stability of the ADRC, and the robustness metric is compared with that of the PID control schemes. The simulation results show that DE-ADRC control strategy has better set point tracking, interference rejection, and robust stability than DE-PID control strategy.

Model-based control strategy with linear parameter-varying state-space model for rack-based cooling data centers

Cooling system energy consumption occupies approximately 40% of the total energy consumption in data centers, and efficient control is crucial for improving cooling efficiency and reducing the operational costs of data centers. This paper introduced a novel economic model predictive control (EMPC) strategy based on a linear parameter-varying state-space model. The primary objective was to maintain the thermal environment of data centers while minimizing the energy consumption of the cooling system. Therein, a linear parameter-varying state-space model was developed based on the parameter identification method to precisely predict the temperature field of the rack-based cooling data center in real-time. The energy management and thermal regulation performance of the EMPC and the proportion integration differentiation (PID) controller were comparatively analyzed through simulation experiments. Moreover, the impacts of the server workload level and optimization time domain on the performance of EMPC were comprehensively investigated. The results show that, the proposed EMPC was able to minimize the energy consumption by optimizing the supplied cold air temperature and airflow rate simultaneously. In comparison with the PID controller, EMPC not only achieves a 9.7% energy saving by preventing server over-cooling but also diminishes server temperature fluctuations, promoting the safe and stable operation of the server. The research shows that the EMPC reveals excellent performance along with all server workload levels. In addition, the length of the prediction horizon has a notable impact and three minutes is suggested for the rack-based cooling system.

Improvement of Dynamic Characteristics of Purpose-Built Vehicles Using Semi-Active Suspension System.

The diversification of mobility into services such as smart stores and conference rooms has accelerated the development of purpose-built vehicles (PBVs)-vehicles designed for specific purposes that utilize an extended electric vehicle chassis and autonomous driving technology. Despite the standards on speed bump dimensions stipulated by the National Land Transportation Act of the Republic of Korea, real-world speed bumps feature varying widths and heights that deviate from these standards. In this study, a velocity equation was derived via regression analysis to achieve the desired dynamic characteristics for a PBV passing over speed bumps with varying shapes through two types of semi-active suspension control: proportional-integral-differential (PID) and linear-quadratic-regulator (LQR). For a cargo-transport PBV, the PID and LQR controllers increased the velocity by 23.74% and 50.74%, respectively, under different speed bump widths and by 19.44% and 38.31%, respectively, under different speed bump heights. Moreover, an analysis of the vibration dose value (VDV), an indicator of ride comfort, revealed that the VDVs calculated using the velocity equation were within an acceptable error range of 10% above the target VDV. These findings provide insights into the speed control required for different types of autonomous PBVs to ensure ride comfort, as well as minimize the driving duration, depending on the specific purpose of the vehicle.

Pengaturan Motor DC Menggunakan Tuning PID Zigler Nichols Sebagai Media Pembelajaran Interaktif;

DC Motor is a direct current that is often used in everyday life that uses speed regulation, the DC Motor rotation will be given a load so we test the Motor rotation value according to the weight of the motor load that is generated after the Motor is activated. To find out the motor rotation and the resulting value after being given a load, we are here using the Arduino Mega component as a microcontroller, the IBT 2 driver as a DCb motor speed controller that has been given a load, the encoder as a copy of the old motor rotation data to the new motor data, the potentiometer as a sensor to find out DC Motor rotation, LCD to display data that has been taken, Arduino Ide as Software. And the control used is PID (proportional integral differential). This PID control system works by processing calculations based on the control variables Kp, Ki, and Kd to achieve conditions according to the expected setpoint..

Self-immunity study of quadrotor UAV based on Modelica system modeling and disturbance feed-forward compensation

For addressing the challenges of decreased attitude and trajectory tracking accuracy and a delayed response in the flight control operations of quadcopter unmanned aerial vehicles (UAVs) under the uncertainties of model parameters and external disturbances, this study leverages the advantages of the non-causal declarative modeling language Modelica in system modeling and simulation. In addition, it incorporates the nonlinear Active Disturbance Rejection Control (ADRC) framework for disturbance observation, estimation, and compensation. A state observer is designed to mitigate the impact of external disturbances and model uncertainties through feed-forward compensation, and stability analysis is conducted. Numerical simulations for hover resistance demonstrate that, compared to the cascade proportional integral differential (PID) control strategy, PID-NLADRC reduces the maximum deviation induced by wind disturbances by ∼50% and shortens the disturbance influence time by around 40%. Simulations for different trajectories, such as planar or spatial, smooth or abrupt changes, indicate that under the PID-NLADRC control strategy, the real-time spatial distance deviation mean is reduced by 69.5%, and the peak time is shortened by 75.7%. Validation through multi-objective applications and physical experiments highlights the advantages of PID-NLADRC in terms of positioning accuracy, rapid tracking, and disturbance suppression, aligning well with the fast, precise, and robust flight control requirements of quadcopter UAVs.

An infrared and visible light video fusion method based on chaos theory and PID control

Differences in the imaging mechanisms of infrared and visible light images lead to differences in the way their visually meaningful gradients are formed. Existing fusion methods use the same feature extractor to extract features from the source video frames, which ignores the differences in the gradients of video frames from different modalities. In this paper, we propose an infrared and visible light video fusion method based on chaos theory and proportional integral differential (PID) control. Firstly, for the Lorentz chaotic system, we give it initial values and parameters, and iterate it to obtain three scrambling sequences, through which the source video frames are scrambled in the rows, columns, and diagonal directions respectively to eliminate their visually meaningful gradients, so that the features extracted are of comparable scales in the same layer, and the fusion process can be carried out in the scale-consistent space. Second, we propose a structure-aware relative total variation feature extraction method (saRTV) for the two-scale decomposition of source video frames, which can transfer more features of source video frames to the detail layer. Then, based on our previous work, this paper introduces PID control to construct a closed-loop control system through transfer function design, controller design and measurement function design. This control system is used to fuse the detail layer, so as to realize the real-time guidance of the source video frames to the fusion process. Experiments on public datasets demonstrate that our method has better performance compared to some state-of-the-art methods.

Modeling and Control of a Two-Axis Stabilized Gimbal Based on Kane Method.

A two-axis stabilizing gimbal is a device that ensures a sensor is working properly on a moving platform. When classical mechanics (Newton-Euler and Lagrange) is employed to model a two-axis stable gimbal, its limitations can complicate the modeling process. To address this issue, a method for establishing a dynamic model for a two-axis stabilizing platform based on the Kane method is proposed in this paper. The Kane method offers the advantage of a simple model structure and computational efficiency. Initially, utilizing a generalized coordinate system, expressions of the generalized velocities, deflection velocities and angular velocities are derived. Subsequently, the generalized active forces and inertial forces acting on the two-axis stabilized gimbal are analyzed. Finally, by combining force and velocity with the Kane equation, the dynamic model of the two-axis stable platform is obtained, demonstrating the validity of the Kane method for establishing the two-axis stable platform model. To ensure the pointing accuracy stability of the two-axis stabilizing platform, a Novel Particle Swarm Optimization Proportion Integration Differentiation (NPSO-PID) controller is designed using the PSO algorithm. It is then simulated in MATLAB/Simulink and compared with a classical PID controller. Simulation results demonstrate that NPSO-PID exhibits superior object tracking performance compared to classical PID controllers and better optimization of control parameters compared to traditional PSO-PID controllers.

Neural network optimizer of proportional-integral-differential controller parameters

Wide application of proportional-integral-differential (PID)-regulator in industry requires constant improvement of methods of its parameters adjustment. The paper deals with the issues of optimization of PID-regulator parameters with the use of neural network technology methods. A methodology for choosing the architecture (structure) of neural network optimizer is proposed, which consists in determining the number of layers, the number of neurons in each layer, as well as the form and type of activation function. Algorithms of neural network training based on the application of the method of minimizing the mismatch between the regulated value and the target value are developed. The method of back propagation of gradients is proposed to select the optimal training rate of neurons of the neural network. The neural network optimizer, which is a superstructure of the linear PID controller, allows increasing the regulation accuracy from 0.23 to 0.09, thus reducing the power consumption from 65% to 53%. The results of the conducted experiments allow us to conclude that the created neural superstructure may well become a prototype of an automatic voltage regulator (AVR)-type industrial controller for tuning the parameters of the PID controller.