Neural Network PID Controller Research Articles

Adjusting laser power to control the heat generated by nanoparticles at the site of a patient's cells.

Cancer treatment often involves heat therapy, commonly administered alongside chemotherapy and radiation therapy. The authors address the challenges posed by heat treatment methods and introduce effective control techniques. These approaches enable the precise adjustment of laser radiation over time, ensuring the tumour's core temperature attains an acceptable level with a well-defined transient response. In these control strategies, the input is the actual tumour temperature compared to the desired value, while the output governs laser radiation power. Efficient control methods are explored for regulating tumour temperature in the presence of nanoparticles and laser radiation, validated through simulations on a relevant physiological model. Initially, a Proportional-Integral-Derivative (PID) controller serves as the foundational compensator. The PID controller parameters are optimised using a combination of trial and error and the Imperialist Competitive Algorithm (ICA). ICA, known for its swift convergence and reduced computational complexity, proves instrumental in parameter determination. Furthermore, an intelligent controller based on an artificial neural network is integrated with the PID controller and compared against alternative methods. Simulation results underscore the efficacy of the combined neural network-PID controller in achieving precise temperature control. This comprehensive study illuminates promising avenues for enhancing heat therapy's effectiveness in cancer treatment.

Study on Fault Diagnosis Technology for Efficient Swarm Control Operation of Unmanned Surface Vehicles

The purpose of this study is to design a Swarm Control algorithm for the effective mission performance of multiple unmanned surface vehicles (USVs) used for marine research purposes at sea. For this purpose, external force information was utilized for the control of multiple USV swarms using a lead–follow-formation technique. At this time, to efficiently control multiple USVs, the LSTM algorithm was used to learn ocean currents. Then, the predicted ocean currents were used to control USVs, and a study was conducted on behavioral-based control to manage USV formation. In this study, a control system model for several USVs, each equipped with two rear thrusters and a front lateral thruster, was designed. The LSTM algorithm was trained using historical ocean current data to predict the velocity of subsequent ocean currents. These predictions were subsequently utilized as system disturbances to adjust the controller’s thrust. To measure ocean currents at sea as each USV moves, velocity, azimuth, and position data (latitude, longitude) from the GPS units mounted on the USVs were utilized to determine the speed and direction of the hull’s movement. Furthermore, the flow rate was measured using a flow rate sensor on a small USV. The movement and position of the USV were regulated using an Artificial Neural Network-PID (ANN-PID) controller. Subsequently, this study involved a comparative analysis between the results obtained from the designed USV model and those simulated, encompassing the behavioral control rules of the USV swarm and the path traced by the actual USV swarm at sea. The effectiveness of the USV mathematical model and behavior control rules were verified. Through a comparison of the movement paths of the swarm USV with and without the disturbance learning algorithm and the ANN-PID control algorithm applied to the designed simulator, we analyzed the position error and maintenance performance of the swarm formation. Subsequently, we compared the application results.

Research on underwater motion modeling and closed-loop control of bionic undulating fin robot

Aiming at the problems of unclear underwater motion characteristics and poor robustness of bionic undulating fin robots, the underwater motion characteristics of the robot are studied by force analysis and numerical simulation, and the dynamic model is established. Based on the dynamic model, the proportional-integral-derivative controller (PID) and neural network PID simulation model are established for numerical simulation, and the robot's underwater closed-loop motion control experiment is carried out. The accuracy of the dynamic model and the consistency between the numerical simulation and the experimental results can be verified. The results indicate that under the function of the neural network PID controller, the robot can be closer to the target depth, and the fluctuation range could be smaller. As the above characteristics improve, the control accuracy and stability of the robot could also be enhanced.

Optimization of the Semi-Active-Suspension Control of BP Neural Network PID Based on the Sparrow Search Algorithm.

Electric vehicles with hub motors have integrated the motor into the wheel, which increase the unsprung mass of the vehicle, and intensifies the vibration of the underspring components. The motor excitation during driving also intensifies the wheel vibration. The coupling effect between the two makes the performance of electric vehicles deteriorate. The article employed a disc-type permanent-magnet motor as the hub motor, taking into consideration the increase in sprung mass caused by the hub motor and the adverse effects of vertical vibration from motor excitation. Based on random road-surface excitation, and considering the secondary excitation caused by wheel motor drive and vehicle-road coupling, a coupled-dynamics model of a semi-active-suspension vehicle-road system for vertical vehicle motion is investigated under multiple excitations. Using body acceleration, suspension deflection, and dynamic tire load as evaluation indicators, a BP neural network PID controller based on the sparrow search algorithm optimization is proposed for the semi-active-suspension system. Compared with PID control and particle swarm optimization (PSO-BPNN-PID), the research findings indicate that the optimized semi-active suspension significantly improves the ride comfort of hub-motor electric vehicles, and meets the requirements for control performance under different vehicle driving conditions.

Improving Model-Free Control Algorithms Based on Data-Driven and Model-Driven Approaches: A Research Study

Given the challenges associated with accurately modeling complex nonlinear systems with time delays in industrial processes, this paper introduces an advanced model-free control algorithm that combines data-driven and model-driven approaches. Initially, an enhanced algorithm for multi-innovation model-free control, incorporating error feedback, is presented based on the error feedback principle. Subsequently, a novel control strategy is introduced by delving into PID neural network (NN) recognition and control theory, merging PID NN control with multi-innovation feedback control. Through meticulous mathematical derivation, the proposed strategy is proven to ensure system stability. Compared with traditional NN PID controllers, the convergence rate of the proposed scheme is 50 s faster and the steady-state errors are limited to ±1.

Research on Pneumatic Control of a Pressurized Self-Elevating Mat for an Offshore Wind Power Installation Platform.

Efficient deep-water offshore wind power installation platforms with a pressurized self-elevating mat are a new type of equipment used for installing offshore wind turbines. However, the unstable internal pressure of the pressurized self-elevating mat can cause serious harm to the platform. This paper studies the pneumatic control system of the self-elevating mat to improve the precision of its pressure control. According to the pneumatic control system structure of the self-elevating mat, the pneumatic model of the self-elevating mat is established, and a conventional PID controller and fuzzy PID controller are designed and established. It can be seen via Simulink simulation that the fuzzy PID controller has a smaller adjustment time and overshoot, but its anti-interference ability is relatively weak. The membership degree and fuzzy rules of the fuzzy PID controller are optimized using a neural network algorithm, and a fuzzy neural network PID controller based on BP neural network optimization is proposed. The simulation results show that the overshoot of the optimized controller is reduced by 9.71% and the stability time is reduced by 68.9% compared with the fuzzy PID. Finally, the experiment verifies that the fuzzy neural network PID controller has a faster response speed and smaller overshoot, which improves the pressure control accuracy and robustness of the self-elevating mat and provides a scientific basis for the engineering applications of the self-elevating mat.

Actor–critic learning based PID control for robotic manipulators

In this paper, we propose a reinforcement learning structure for auto-tuning PID gains by solving an optimal tracking control problem for robot manipulators. Capitalizing on the actor–critic framework implemented by neural networks, we achieve optimal tracking performance, estimating unknown system dynamics simultaneously. The critic network is used to approximate the cost function, which serves as an indicator of control performance. With feedback from the critic, the actor network learns time-varying PID gains over time to optimize control input, thereby steering the system toward optimal performance. Furthermore, we utilize Lyapunov’s direct method to demonstrate the stability of the closed-loop system. This approach provides an analytical procedure for a stable robot manipulator system to systematically adjust PID gains, bypassing the ad-hoc and painstaking process. The resultant actor–critic PID-like control exhibits stable adaptive and learning capabilities while maintaining a simple structure and inexpensive online computational demands. Numerical simulations underscore the effectiveness and advantages of the proposed actor–critic neural network PID control.

Research on the Multimode Switching Control of Intelligent Suspension Based on Binocular Distance Recognition

As the upgrade of people’s requirements for automotive driving comfort, conventional passive suspensions for cars have fallen short of existing demands due to their nonadjustable damping and stiffness, so semiactive suspensions and active suspensions have gained growing acceptance. Compared with active suspensions, semiactive suspensions offer the advantages of a low manufacturing cost and reliable structure, and thus have become the preferred choice for most vehicles. To optimize the control effect of semiactive suspensions under different working conditions, this paper completed the modeling of magnetorheological semiactive suspension system dynamics and road inputs; then, the design of binocular camera sensing algorithms was performed to obtain the real-time distance of the target using the point cloud ranging function, and the parameters required for suspension control were also obtained. This was followed by the completion of the control-mode-switching rules and the design of the suspension controller. According to the different control objectives, the mode could be divided into the obstacle-road mode, straight-road mode, and curved-road mode. The suspension controller included the BP-PID (neural network PID controller) controller and the force distributor. Finally, the effectiveness of the mode-switching rules and the control method was verified through system simulation and the hardware-in-the-loop test.

Research and Design of Improved Wild Horse Optimizer-Optimized Fuzzy Neural Network PID Control Strategy for EC Regulation of Cotton Field Water and Fertilizer Systems

Xinjiang is the largest cotton-producing region in China, but it faces a severe shortage of water resources. According to relevant studies, the cotton yield does not significantly decrease under appropriate limited water conditions. Therefore, this paper proposes a water and fertilizer integrated control system to achieve water and fertilizer conservation in the process of cotton field cultivation. This paper designs a fuzzy neural network Proportional–Integral–Derivative controller based on the improved Wild Horse Optimizer to address the water and fertilizer integrated control system’s time-varying, lag, and non-linear characteristics. The controller precisely controls fertilizer electrical conductivity (EC) by optimizing parameters through an improved Wild Horse Optimizer for the initial weights from the normalization layer to the output layer, the initial center values of membership functions, and the initial base width of membership functions in the fuzzy neural network. The performance of the controller is validated through MATLAB simulation and experimental tests. The results indicate that, compared with conventional PID controllers and fuzzy PID controllers, this controller exhibits excellent control accuracy and robustness, effectively achieving precise fertilization.

Investigation on active vibration control to improve surface quality in precision milling process

The tool-workpiece vibration in the precision milling process plays a pivotal role in influencing the surface quality. To solve the machining problem coming with the process vibration, the active vibration control model as well as the corresponding platform are developed, and the active vibration control algorithms are applied to reduce the relative vibrations and improve the surface quality. Firstly, the milling vibration reduction and surface quality improvement are modeled based on the active control algorithms and the system dynamic characteristics. Then, applying the different algorithm control strategies, such as PID, Fuzzy PID, BP neural network, and BP neural network PID control, the control effect is simulated and analyzed. Finally, an experimental platform is established to validate the system’s reliability. The efficiency of various active control methods is compared in terms of frequency vibration control and surface finish roughness improvement. The results indicate that under different milling parameters, the four algorithm control strategies exhibit optimal effects of 13.5%, 30.4%, 28.8%, and 40.1% respectively. These findings provide valuable insights into selecting the optimal vibration control method for precision milling.

Conversion Control for Remote Sensing Stable Platforms for Transient and Continuous Disturbances

An airborne electro-optical stabilized platform is a device situated between the aircraft and the imaging components, which serves to isolate external disturbances and maintain imaging axis stability for the imaging components. In light of the impact of transient and continuous attitude changes of the aircraft on the axis-stabilized imaging in visible light unmanned aerial vehicle (UAV) remote sensing missions, a control method combining a proportional-integral (PI) controller and a backpropagation neural network (BPNN) PID conversion control was devised. The specific procedure involved the following steps: firstly, the transfer mechanism of external disturbances between platforms was derived using the state transition matrix through mechanistic modelling. Secondly, the multi-rigid body dynamics equations of the airborne electro-optical platform were established based on Newton’s laws of motion and Euler’s laws. Subsequently, the relationship between the stable platform rotation angle and external disturbances was obtained using Laplace transformation, and an analysis was conducted on the effects of different disturbances on the stable platform. Lastly, conversion control was incorporated into the system model for simulation analysis. The simulation results demonstrated that transient disturbances could be effectively and rapidly isolated by the PI controller, while continuous disturbances exhibited improved performance when handled by the neural network PID controller, thus validating the efficacy of the designed conversion control method.

Leader-Follower UAV formation flight control based on feature modelling

To solve the problems of backstepping error and poor dynamic tracking approach rate in traditional PID neural network control in UAV formation flight control, a Leader-Follower UAV formation flight control method based on feature modelling is proposed,and the pose relationship model between virtual follower and pilot is established by trajectory tracking and pose dynamic fitting. The pose distribution of thefollower is analyzed in the ground coordinate system, and the parameter information of linear velocity and angular velocity control of UAV is obtained, and the backstepping sliding mode formation controller is formed. The variable structure PID neural network controller is used to design the flight control law of UAV formation, and the fast piecewise power approaching factor is introduced into the PID controller to eliminate the chattering of sliding mode control. The simulation results show that this method can ensure the rapidity of UAV formation flight control also show strong anti-jamming ability. Due to the fast piecewise power approach rate, the UAVs can complete the UAV formation reorganization under disturbance and buffeting in a short time, and the trajectory tracking error approaches zero, and it has good anti-buffeting ability.

Research on Two-Stage Semi-Active ISD Suspension Based on Improved Fuzzy Neural Network PID Control.

To better improve the ride comfort and handling stability of vehicles, a new two-stage ISD semi-active suspension structure is designed, which consists of the three elements, including an adjustable damper, spring, and inerter. Meanwhile, a new semi-active ISD suspension control strategy is proposed based on this structure. Firstly, the fuzzy neural network's initial parameters are optimized using the grey wolf optimization algorithm. Then, the fuzzy neural network with the optimal parameters is adjusted to the PID parameters. Finally, a 1/4 2-degree-of-freedom ISD semi-active suspension model is constructed in Matlab/Simulink, and the dynamics simulation is carried out for the three schemes using PID control, fuzzy neural network PID control, and improved fuzzy neural network PID control, respectively. The results show that compared with adopting PID control and fuzzy neural network PID control strategy, the vehicle body acceleration and tire dynamic loads are significantly reduced after using the grey wolf optimized fuzzy neural network PID control strategy, which shows that the control strategy proposed in this paper can significantly improve the vehicle smoothness and the stability of the handling.

Finite-time control based on RBF neural network for quadrotor UAVs with varied mass load

Aiming at the problem of the gradual reduction of the weight and the external wind disturbance affect flight performance of the quadrotor Unmanned Aerial Vehicle (UAV), a dual-loop finite time control strategy based on Radial Basis Function (RBF) neural network is proposed. The UAV model under disturbance is decoupled into position outer loop subsystem and attitude inner loop subsystem. In the outer loop, the changing weight and the external wind disturbance are approximated by using RBF neural network, command filter is used to avoid the “computing explosion” problem in the traditional backstepping method, and the finite-time control method is able to improve the convergence speed of the position. In the inner loop, the cascade RBF neural network PID control which relies on the self-learning of neural network to realize the dynamic tuning of PID parameters is adopted to achieve rapid convergence of the attitude angle. The simulation results show that compared with the traditional backstepping method and cascade PID control, the convergence time is reduced by 31% on average, which verifies the superiority and effectiveness of the proposed control strategy.

Optimizing the initial weights of a PID neural network controller for voltage stabilization of microgrids using a PEO-GA algorithm

This paper proposes an adaptive PID neural network (PIDNN) controller for direct and quadrature voltage control of three-phase inverters for islanded microgrids. A hybrid metaheuristic optimization algorithm is proposed for the initial weight selection of the proposed PIDNN controller using a discrete-time simulation model incorporating the nonlinearity of the insulated gate bipolar transistor (IGBT) or metal oxide semiconductor field effect transistor (MOSFET) switches of the inverter. The proposed hybrid optimization (HO) approach is a combination of population extremal optimization (PEO) and genetic algorithm (GA). It turned out that the proposed HO-PIDNN control scheme excelled the PEO, GA, and particle swarm optimization-based PIDNN controllers in terms of the objective function value, which is composed of the integral time absolute tracking error of the output voltage and a chattering penalty factor. Also, the control system outperformed the model reference adaptive PID control technique from the literature.

Fuzzy neural network PID control design of camellia fruit vibration picking manipulator

Due to the growth characteristics of the flowers and fruits of camellia in the same period, the vibrating camellia fruit picking machine needs to ensure the constant rotational speed of the vibrating hydraulic motor when the picking mechanism is operating, to achieve a constant vibration frequency, to ensure that the camellia fruit can smoothly fall off the branches through vibration. In contrast, the camellia fruit does not fall off. In this regard, this paper deduced the state space equation of the camellia fruit picking machine’s valve-controlled vibrating hydraulic motor system and designed a fuzzy wavelet neural network PID controller (FWNN PID controller) based on the traditional incremental PID control principle. Then the designed vibration picking manipulator control system was simulated under no-load, 5 s load conditions, and load start conditions with MATLAB/Simulink, a general PID controller and a fuzzy RBF neural network PID controller (FRBFNN PID controller) were used to contrast with it. The results show that the general PID controller has a slow response speed and poor robustness, while fuzzy neural network PID controllers (including FWNN PID controller and FRBFNN PID controller) have a fast response speed and strong robustness, which can well meet the requirements of a specific vibration frequency. Finally, a field test was carried out. The results show that the FWNN PID control is better than the FRBFNN PID control. Furthermore, the FWNN PID controller obviously reduced the drop rate of camellia flowers within 6% while ensuring the picking efficiency above 90%, which can well meet the needs of the camellia fruit picking operation.

Fuzzy Neural Network PID Control Used in Individual Blade Control

In order to further reduce the vibration level of helicopters, the active vibration control technology of helicopters has been extensively studied. Among them, individual blade control (IBC) independently applies high-order harmonics to each blade with an actuator, which can improve the aerodynamic environment of the blade and effectively reduce the vibration load of the hub. The rotor structural dynamics model based on the Hamilton energy variation principle and the medium deformation beam theory were established firstly, and the aerodynamic model based on the dynamic inflow model and the Leishman–Beddoes unsteady aerodynamic model were also established. The structural finite element method and the direct numerical integration method were used to calculate the vibration response of the rotor to determine the vibration load of the hub. After these, the steepest descent-golden section combinatorial optimization algorithm was used to find the optimization parameters of IBC. Based on this, the input parameters of fuzzy neural network PID control were determined, and the rotor hub vibration load control simulation was conducted. Under the effect of IBC, the vibration loads of the hub could be reduced by about 60%. The article gives the best control laws of individual harmonic pitch control and their combinations. These results can theoretically be applied to the design of control law to reduce helicopter vibration loads.

Unmanned Bicycle Balance Control Based on Tunicate Swarm Algorithm Optimized BP Neural Network PID

In this study, the authors introduce a novel approach that leverages the tunicate swarm algorithm (TSA) to optimize proportional-integral-derivative (PID) controller based on a back propagation (BP) neural network. The core objective of the approach is to manage and counteract uncertainties and disturbance that may jeopardize the balance and stability of self-driving bicycles in operation. By using the self-learning capabilities of BP neural networks, the controller can dynamically adjust PID parameters in real time. This enables an enhanced robustness and reliability during operation. Further bolstering the efficiency of our controller, the authors use the TSA to optimize the initial weights of a neural network. This effectively mitigates the commonly associated with slow convergence and being entrapped in local minima. Through simulation and experimentation, the findings reveal that the TSA-optimized BP neural network PID controller dramatically improves dynamic performance and robustness. It also proficiently manages changes in the environment such as wind and ground bumps. Therefore, the proposed controller design offers an effective solution to the balancing problem of self-driving bicycles and paves the way for a promising future in designing versatile controllers with broad application potential.

Drying Temperature Precision Control System Based on Improved Neural Network PID Controller and Variable-Temperature Drying Experiment of Cantaloupe Slices.

A drying temperature precision control system was studied to provide technical support for developing and further proving the superiority of the variable-temperature drying process. In this study, an improved neural network (INN) proportional-integral-derivative (PID) controller (INN-PID) was designed. The dynamic performance of the PID, neural network PID (NN-PID) and INN-PID controllers was simulated with unit step signals as an input in MATLAB software. A drying temperature precision control system was set up in an air impingement dryer, and the drying temperature control experiment was carried out to verify the performance of the three controllers. Linear variable-temperature (LVT) and constant-temperature drying experiments of cantaloupe slices were carried out based on the system. Moreover, the experimental results were evaluated comprehensively with the brightness (L value), colour difference (ΔE), vitamin C content, chewiness, drying time and energy consumption (EC) as evaluation indexes. The simulation results show that the INN-PID controller outperforms the other two controllers in terms of control accuracy and regulation time. In the drying temperature control experiment at 50 °C-55 °C, the peak time of the INN-PID controller is 237.37 s, the regulation time is 134.91 s and the maximum overshoot is 4.74%. The INN-PID controller can quickly and effectively regulate the temperature of the inner chamber of the air impingement dryer. Compared with constant-temperature drying, LVT is a more effective drying mode as it ensures the quality of the material and reduces the drying time and EC. The drying temperature precision control system based on the INN-PID controller meets the temperature control requirements of the variable-temperature drying process. This system provides practical and effective technical support for the variable-temperature drying process and lays the foundation for further research. The LVT drying experiments of cantaloupe slices also show that variable-temperature drying is a better process than constant-temperature drying and is worthy of further study to be applied in production.

PID control of evaporation temperature control system based on fuzzy RBF neural network

In this thesis, a fuzzy RBF neural network PID (RBFfnn-pid) control method is designed for temperature deviation concerning the steam curing temperature control system in the steam curing kettle of the aerated concrete block production line. The temperature control system (TCS) models of steam curing are established respectively under the control of fuzzy PID and RBFfnn-pid. Then, the control effect is analyzed by simulation in different situations. The results show that, under this condition of step signal inputting, the RBFfnn-pid control method shortens the rising time by 160 s and reduces the overshoot by 8% compared with the fuzzy PID controlling means. When the system is in a stable state, then the interference signal is added, which in contrast to the controlling means of fuzzy PID, the time for adjusting the RBFfnn-pid control to the set value is shortened by 70 seconds and there is no overshoot. The RBFfnn-pid control method enables the controlling parameters of the steaming temperature control system to be adjusted to the optimum quickly and iteratively, which improves the temperature control accuracy.