A Neural Network Based Reference Modified PID Control with Simple Duration Design for Digitally Controlled DC-DC Converters

This study aims to evaluate the behavior of neural network control method for digitally controlled dc-dc converters when the circuit parameter condition varies from which is in the training of the neural network. Learning based methods, which include the neural network control, are constructed and tuned using the training data to control given plants. They can provide the effective control since they are tuned as the dedicated one, however, they have difficulties when the parameters of components in the plant are changed from original ones, which are used to obtain the training data. Therefore, they may lose the effectivity in control if the the parameters in plant are changed. In the case of controlling dc-dc converters, the circuit parameter condition such as capacitance, reactor and so forth, are varied in the case that the specification of the circuit design is changed. Moreover they are changed by the environmental condition such as temperature, aging degradation and so forth. In this study, we study the effectivity of neural network control method for dc-dc converters when the circuit parameters are changed from the ones which are used in the training. When the circuit parameters are changed from original one, we evaluate that whether the neural network can control without any tuning, such as re-training of the neural network. From evaluation results, we confirm that the neural network control can work effectively even in such situation and it reveals that the neural network control has the robustness against the change of the circuit parameter condition.

Identification and adaptive neural network control of a DC motor system with dead-zone characteristics

The technologic of PID control is very conventional. There is an extensive application in many fields at present. The PID controller is simple in structure, strong in robustness, and can be understood easily. Then neural networks have great capability in solving complex mathematical problems since they have been proven to approximate any continuous function as accurately as possible. Hence, it has received considerable attention in the field of process control. Due to the complication of modern industrial process and the increase of nonlinearity, time-varying and uncertainty of the practical production processes, the conventional PID controller can no longer meet our requirement. This paper introduces the theoretical foundation of the BP neural network and studying algorithm of the neural network briefly, and designs the PID temperature control system and simulation model based on BP neural network. Keywords-PID controller; BP neural network; temperature control system

In the current era, green energy systems like solar PV, wind energy, and battery storage critically rely on DC-DC converters to manage power flow and voltage conversion efficiently, ensuring optimal performance and reliability. Nevertheless, converters face multiple challenges, including efficiency losses, thermal management concerns, and electromagnetic interference, which can impact these green energy systems' overall performance and reliability. To overcome these challenges, it is necessary to utilize advanced control mechanisms, enhance heat management approaches, and optimize component design. Implementing these improvements will improve the effectiveness and durability of DC-DC converters in renewable energy applications. This research aims to analyze the performance characteristics of a three-phase interleaved half-bridge bidirectional (TPHB-Bi) converter. The research objective involves investigating the effectiveness of the proposed controller by rigorously assessing voltage tracking. This is done through comprehensive assessments of start-up procedures and reference voltage variations using MATLAB/Simulink. The study utilizes a neural network controller with an online learning algorithm based on backpropagation to enhance the converter's operational capabilities, ensuring a stable output voltage and improved transient response. The simulation results highlight the significant advantages of the proposed controller over a conventional PID controller. It exhibits a remarkable reduction in overshoot by 5.29%, considerably shorter rise times ranging from 0.01ms to 0.1ms, and faster settling times of 0.025s. The findings have great importance in promoting sustainable energy development and environmental protection. They demonstrate that implementing advanced control strategies for DC-DC converters can result in more efficient and reliable green energy systems.

In this paper, a neural network PID controller with dynamic structure adjustment is proposed for DC-DC switching converters. To improve the efficiency of the controller and reduce its power consumption, the neural network for the proposed controller can change its structure adaptively in transient state according to the variation of voltage error, while it is disabled in steady state. Firstly, the whole voltage error range is divided into four parts to distinguish the location of voltage error. Then, the adaptive structure change mechanism is designed for neural network. Furthermore, a buck DC–DC switching converter using the proposed controller is designed and implemented on the field programmable gate array (FPGA) and printed circuit board (PCB). The experimental results demonstrated that it has similar transient performance in a DC-DC switching converter to that the conventional neural network PID controller, where neural network has the fixed structure. Meanwhile, the proposed controller has less power consumption and higher efficiency in transient state than a conventional neural network PID controller.

A decentralized PID neural network (PIDNN) control scheme was proposed to a quadrotor helicopter subjected to wind disturbance. First, the dynamic model that considered the effect of wind disturbance was established via Newton-Euler formalism. For quadrotor helicopter flying at low altitude in actual situation, it was more susceptible to be influenced by the turbulent wind field. Therefore, the turbulent wind field was generated according to Dryden model and taken into consideration as the disturbance source of quadrotor helicopter. Then, a nested loop control approach was proposed for the stabilization and navigation problems of the quadrotor subjected to wind disturbance. A decentralized PIDNN controller was designed for the inner loop to stabilize the attitude angle. A conventional PID controller was used for the outer loop in order to generate the reference path to inner loop. Moreover, the connective weights of the PIDNN were trained on-line by error back-propagation method. Furthermore, the initial connective weights were identified according to the principle of PID control theory and the appropriate learning rate was selected by discrete Lyapunov theory in order to ensure the stability. Finally, the simulation results demonstrate that the controller can effectively resist external wind disturbances, and presents good stability, maneuverability and robustness.

This paper proposes neural network controllers using a reference model and investigates their characteristics. Since the neural network compensates the incorrectness of the plant such as nonlinearity and uncertainty against the reference model, a conventional controller can be designed based on the known dynamics of the reference model. The neural network controller can be classified into three types in terms of the connection between the neural network controller and the conventional controller. In the D-type controller, the output from the conventional controller inputs to the neural network and the reference model in parallel. In the Y-type controller, the output from the conventional controller inputs to the neural network, the plant and the reference model in parallel. The neural network of both controllers learns the combination of the inverse characteristics of the plant and the forward characteristics of the reference model. In the I-type controller, the output from the conventional controller inputs to the reference model whose output inputs to the neural network. The neural network leams the inverse characteristics of the plant. Simulation results using nonlinear plants show the achievement of the neural controllers and confirm their effectiveness for controlling the nonlinear plants.

In this study, a nonlinear Archimedes wave swing (AWS) energy conversion system was employed to enable the use of irregular sea waves to provide useful electricity. Instead of the conventional PI controllers used in prior research, this study employed fractional-order PID (FOPID) controllers to control the back-to-back configuration of AWS. The aim was to maximize the energy yield from waves and maintain the grid voltage and the capacitor DC link voltage at predetermined values. In this study, six FOPID controllers were used to accomplish the control goals, leading to an array of thirty parameters required to be fine-tuned. In this regard, a hybrid jellyfish search optimizer and particle swarm optimization (HJSPSO) algorithm was adopted to select the optimal control gains. Verification of the performance of the proposed FOPID control system was achieved by comparing the system results to two conventional PID controllers and one FOPID controller. The conventional PID controllers were tuned using a recently presented metaheuristic algorithm called the Coot optimization algorithm (COOT) and the classical particle swarm optimization algorithm (PSO). Moreover, the FOPID was also tuned using the well-known genetic algorithm (GA). The system investigated in this study was subjected to various unsymmetrical and symmetrical fault disturbances. When compared with the standard COOT-PID, PSO-PID, and GA-FOPID controllers, the HJSPSO-FOPID results show a significant improvement in terms of performance and preserving control goals during system instability

In the field of satellite technology and its application, most of the satellite attitude control system uses PID control. However, the conventional PID control has certain limitations in large inertial system, nonlinear system and complex system. In order to overcome these problems, this paper puts forward a novel fuzzy PID controller by using the radial basis function neural network, genetic algorithm and Takagi-Sugeno fuzzy logic. Based on the dynamic model of the satellite attitude, the approach uses the rule from the improved fuzzy PID controller to ensure system stability. And the proposed control system is found to own many excellent performance of faster response speed, higher efficiency and smaller overshoot errors compared with the conventional PID control system. Finally, simulation results and comparative analysis are carried out to demonstrate that the proposed controller applied in the satellite attitude control system can effectively achieve attitude control and improve the response sensitivity. Therefore, it is feasible and effective in practical application to meet the demands of the Euler angles for satellite attitude control.

Due to fast variation of desired variables in vehicle handling problem, design of an accurate applicable economic and considerably quick responsible controller for steering control of such systems has attracted much attention in the literature. The problem becomes more complicated, if the variation of road condition comes into play also. In this study, by combination of a simple PID and an optimized adaptive neural network controller, an arrangement for active front steering control of vehicles in different road frictions is proposed. A general PID controller is picked up and then optimized using the particle swarm optimization algorithm. After that, a neural network is added consecutively and trained by the outputs of PID controller and neural network toolbox of MATLAB software. The proposed controller fulfills both the applicability and efficiency due to dual use of PID and neural network controllers. Simulation results confirm the rightness of suggested controller in active steering control of vehicles even for unpredictable road friction.

Objective: BLDC motor specifically used for high speed applications and needs sophisticated speed control. Conventional controls techniques require more physical involvement for assisting BLDC motor to operate with precise speed value. However, soft tuning based controller may give comparatively better results for that and the same has been elaborated in present paper using neural controller of speed as per requirements.the main objective of this study may be summarized as (i) MATLAB simulink model for BLDC motor incorporated with soft tuned controller and inverter simultaneously, (ii) development of neural controller for BLDC motor control, and (iii) validation of results developed through proposed controller with the available results using PI, PID and fuzzy logic controller. Methods: The speed obtained through simulink model with input supply voltage variations are used as a reference signal for the training and testing purpose of neural controller. With the help of these reference signals, neural control executes and gives optimum values of external parameters such as speed and electromagnetic torque. Result: The study outcome provides dynamic execution of proposed controllerbased on neural network. The proposed controller’s results are validated with the reference results obtained mathematically for the system. The controller efficiency and sensitivity has been checked by MATLAB-Simulink software. Novelty: comparative study for mathematically obtained reference values and neural controller based results are proposed in this paper. The results are validated with the help of Matlab produces tables and figures. Keywords: BLDC Motor; speed control; neural network controller

In this paper, a radial basis function neural network-based (RBFNN) adaptive inverse controller for real-time position tracking control of a two phase hybrid stepper motor in microstep mode is presented. To ensure system's robustness and closed loop stability and to improve the performance of the controller, the RBF based adaptive inverse control is combined with a closed loop PID controller. Experimental results are provided for various types of trajectories, comparing the performance of the proposed controller to the same neuro-controller using feed forward back-propagation neural networks (FFBP) proposed previously by the authors. The results show the superior performance of RBFNN over FFBP neural networks. Also the comparison of neuro controllers with a conventional fixed gain stand-alone PID controller show the improvement of the controller performance from 80% up to 99.7% decrease in the mean squared error (MSE) for different trajectories. Trajectories were tracked with the maximum error of 0.02 up to 0.06 degrees. Also the robustness of the method is confirmed through experimental results comparing neuro-controllers and the conventional PID controller by varying the load's inertia and disturbance torques. For this purpose two methods were examined. First using the same neuro-controllers trained by the initial training data and in the second method, neuro-controllers were adapted by new training data according to the new working conditions.

The traditional manual operation mode has problems such as high manpower cost, low efficiency, low safety, low operating precision, etc. Achieving unmanned intelligent systems in the field of mechanical and electrical engineering has become the key to transforming and upgrading relevant enterprises and improving their overall competitiveness. In this paper, an improved fuzzy PID control system is constructed based on a PLC control system combined with a fuzzy PID intelligence algorithm. It is applied to the pumping motor, coagulation dosing system, and other specific devices for simulation experiments, compared to the conventional PID algorithm, and evaluated the control system in this paper. The fuzzy PID control algorithm of this paper reduces the steady-state adjustment time of the response curve by 30% compared to the conventional PID algorithm, and the overshooting amount is reduced by 25%. With almost no overshoot, the pumping motor that was equipped with this paper’s PID algorithm reached its stable target speed in 0.3 seconds. In addition, this study found that in the coagulation dosing system model incorporating the fuzzy PID algorithm of this paper, when the model is accurate, only 20% of the overshooting amount occurs after the system has been running for some time. The conventional PID algorithm’s 50% overshoot is significantly less than this, and the time it takes to reach a steady state is also 50 minutes earlier than the conventional PID control. When the model is imprecise, fluctuations occur in both conventional PID control and fuzzy PID control, but the amplitude of the fluctuations in fuzzy PID control is relatively small. In conclusion, this paper shows that the fuzzy PID control algorithm in this paper has higher control accuracy, response speed, and stability than the conventional PID control algorithm.

The present paper investigates an advanced control system of the wind energy conversion using an Artificial Neural Network (ANN) controller, which is developed in two modes: the offline mode, required for testing different sets of neural network parameters to find the optimal neural network controller (structure, activation function, and training algorithm), and the online mode where the optimal ANN controller is used in the five-phase PMSG based wind turbine system. The required data to generate the ANN model is obtained from a conventional PI controller. The controller inputs are the error between reference and actual speed (e), and the error change (de = e(k)-e(k-1)). As for the ANN output, it is the decreasing or increasing electromagnetic torque (dTe*). The studied neural network controller has been tested and validated using different wind speed values. Results and analysis are presented, and the contribution has been demonstrated.

DC-DC converters can be found in almost every power electronics device. To improve the efficiency and controller response of a DC-DC converter to dynamical system changes, neural network has been chosen as an alternative to classic methods. However, no prior work has been done in the neural network approach for control of a PSFB (phase-shifted full-bridge) converter yet. In this research, a multi-layer feedforward neural network controller is proposed. The neural network based controller has the advantage of adaptive learning ability, and can work under the situation when the input voltage and load current fluctuate. Levenberg-Marquardt back-propagation training algorithm is used in computer simulation. The neural controller is then implemented on hardware using a DSP (digital signal processor). Satisfactory experimental results are obtained.