Neural Network PID Control Algorithm Research Articles

Study on Early Warning of Karst Collapse Based on the BP Neural Network

In order to comprehensively grasp the dynamics of karst collapse, promote the comprehensive prevention and control level of karst collapse, and prevent secondary disasters caused by lava collapse, this study presents a method of karst collapse early warning based on the BP neural network. This method does not need to set the sliding surface in the finite element calculation model. The stress of the sliding surface is fitted according to the spatial stress relationship of the deep karst layer through the improved BP neural network PID control algorithm and BP neural network algorithm, which avoids the modeling and mesh generation of the complex sliding block and has good accuracy and ease of use. According to the basic theory of the BP neural network, the calculation formulas of multilayer feedforward and error back propagation processes are derived, and the two-dimensional and three-dimensional finite element models of gravity dams without and with sliding blocks are established, respectively. Finally, according to the common formulas of viscoelastic artificial boundary and equivalent load, the two-dimensional and three-dimensional input programs of the karst fluid state are compiled, and a neural network early warning model is obtained. The experimental results show that the process karst state simulated by the algorithm is very close to the actual situation, and the minimum value of antisliding coefficient and its occurrence time can be accurately predicted, with an error range of less than 3%. Conclusion. BP neural network prediction can effectively predict karst collapse, with higher prediction accuracy, and can effectively simulate the actual collapse risk.

Data Collection of Digital Monitoring System for Agricultural Facilities Environment

In order to realize the intelligent control of the agricultural facility greenhouse environment cluster, the paper designs and implements an agricultural facility greenhouse environment cluster monitoring system based on RS485 bus and Modbus protocol. The system consists of on-site data acquisition and control part, remote monitoring centre monitoring software part and communication protocol part. We use the RS485 bus with Modbus protocol to realize the communication between the monitoring centre host and the microcontrollers of each greenhouse. The paper uses the BP neural network PID control algorithm to achieve the intelligent control of the agricultural greenhouse environment. Use Qt software to design a human-computer interaction interface to realize remote control of the greenhouse cluster. The experimental results show that the system can correctly collect the temperature, humidity and light intensity of the agricultural greenhouse environment, and can effectively control the environmental parameters of each greenhouse through the action of the control relay.

Design of an Artificial Muscle Pressure Supply Mode Based on the Connected Structure

This paper proposes an air pressure supply structure for artificial muscles. The main body of the structure comprises a hollow tube, an electromagnet in the outer layer, and a magnetic piston in the inner diameter of the tube. At both ends, a hose interface connects the air inlet of the artificial muscle. Under the action of controlling changes in current, the electromagnet nested in the outer wall causes the movement of the piston by changing the force between the electromagnet and the magnetic piston and by changing the law of air pressure in the tube. Because the inside of the tube is a closed space, the movement of the magnetic piston in the tube causes a change in the volume of the gas at both ends, thus forming pressure differences of different sizes and directions. Therefore, this air supply, with specific oscillatory characteristics, can be used to produce the desired movement of artificial muscles. Through system modeling, theoretical analysis, and simulation experiments of the connected pressure supply structure, we verified that the system has inherent characteristics similar to a spring damping structure. In view of the inherent characteristics of this kind of structure, this paper introduces the trend of input and output changes by considering the deviation value, details how to improve the traditional neural network PID control algorithm, and discusses the intelligent optimization of controller parameters. Simulation results show that the improved control method can effectively overcome the nonlinear and coupling characteristics of the system, and the gas supply structure can provide a continuous pressure supply curve of an arbitrary waveform and a frequency within a certain amplitude range. The designed air supply structure was applied to a quadruped robot, using its oscillating characteristics to generate rhythmic movement. Compared with the traditional pressure control method, the piston was driven to produce reciprocating motion by fully exploiting the energy stored in the compressed gas, so as to reduce the external energy input and reduce the comprehensive energy consumption of the system. In addition, the control algorithm improved in this paper can meet diverse pressure requirements for driving artificial muscles. Moreover, the independent control of leg support force and stiffness can be realized by combining it with the antagonistic joints. This structure can be widely used in the pressure supply of outdoor robot artificial muscle.

Fault Diagnosis of HVAC System Considering LMBP Neural Network Method

Given the complexity of the mathematical model for the HVAC system and the constant changes of multiple external disturbances and working conditions, the application of intelligent control in the HVAC control system to improve the control performance of the HVAC control system has become a research hotspot. The Levenberg-Marquart algorithm (LM algorithm) is studied to address the defects of slow convergence speed and prone to falling into local minimum in the learning process of the BP neural network. To solve the two issues (the choice of the learning rate, and the solution of the inverse matrix) that significantly affect the training time and convergence accuracy, we improved and optimized the LM algorithm using the LU decomposition method and implemented the algorithm through the MATLAB programming language. The LMBP neural network method obtained is applied to the control loop of the HVAC chilled water cycle. The simulation comparison study is performed on its control effect and that of the PID control algorithm and BP neural network PID control algorithm. The research results show that the LMBP neural network method has significantly improved the performance in aspects such as reducing overshoot, accelerating convergence speed and reducing steady-state error, etc.

Motor synchronisation control for multistage hot die forging press feed manipulator based on BP-PID controller

The rapid development of the automotive industry provides a great opportunity for the development of the forging industry. The multistage precision hot die forging is widely used across the world. In order to improve production efficiency, reduce labour costs, and realise the production automation, a multistage hot die forging press feed manipulator is designed in this paper. The mechanical structure is designed firstly. Then the multi-motor synchronisation control problem is also studied. Based on the adjacent cross-coupling control structure, the BP neural network-PID control algorithm is proposed. Simulation and experiment results show that the BP-PID controller has high control accuracy, a fast convergence speed, and can achieve multi-motor synchronous control effectively. The manipulator designed in this paper has a high practical application value.

AMESim simulation and energy control of hydraulic control system for direct drive electro-hydraulic servo die forging hammer

The application of direct drive electro-hydraulic servo system in die forging hammer is studied, and a new type of direct drive electro-hydraulic servo control die forging hammer is proposed. The impact energy of forging hammer is modelled by analytic method, and the relationship between impact energy E and motor speed n is simulated and analysed by Simulink software. The AC permanent magnet synchronous servo motor model and the hydraulic system simulation model are established on AMESim, and the system performance curve, the pump output flow curve and the servo motor speed curve are obtained. A wavelet neural network PID control algorithm is proposed to realise closed-loop control of pressure and speed of direct drive electro-hydraulic servo die forging hammer. A combined simulation model of AMESim and Simulink is built. The hardware-in-the-loop simulation experiment of the control system is designed. The simulation and experimental results verify the correctness of the scheme.

Design and Experimental Analysis on Autonomous Control System of Wave Glider

In order to realize the unattended and autonomous navigation of Wave Glider in the ocean, an autonomous control system is designed, which mainly includes the control circuit part, motor driver part and control algorithm part. System integrates solar energy charging module, wireless communication module, satellite communication module, rudder motor module and data acquisition module etc. In order to improve the intelligence and autonomy, the algorithm of Gaussian earth algorithm, visual tracking algorithm and BP neural network PID control algorithm are used to ensure the navigation accuracy of Wave Glider. To verify the reliability of the system, Wave Glider is tested in the ocean in the aspects of long time running, target points tracking, velocity keeping, and data acquisition. The experiment shows that under normal ocean conditions, Wave Glider can realize the long term autonomous navigation tracking in the ocean, but the speed fluctuates significantly by the current ocean condition; The acquisition of sensor data is normal, stable and reliable, which meets the requirement of long term using in the ocean.

Research of Oil Pump Control Based On Fuzzy Neural Network PID Algorithm

Abstract In view of the fact that oil pumps exist in the more complex mountains and plains, external temperature, humidity, crude oil characteristics and other adverse factors make the oil pumps control system appear the problem of drift, Fuzzy neural network PID algorithm is studied and designed to realize controling the oil pump system in this paper, combined with the advantages of conventional PID control, fuzzy control and neural network control, the composition and structure of the oil pump control system are analyzed, the model structure and algorithm implementation of fuzzy neural network PID control algorithm are designed in detail. The simulation results show that the control algorithm has good adaptability and anti-interference ability.

Plastic Tank Temperature Control System Based on OPC Technology

This paper analyzes the characteristics of the PLC and MATLAB, describes the OPC technology and introduces the system structures and procedures which uses the OPC technology to achieve the exchange of data between PLC and MATLAB system. For example, in the plastic tank temperature control system, it mentions the BP neural network PID control algorithm which is applied to the PLC control system by using the MATLAB intelligent controller. The results show that this control method is simple and the control effect is good, much better than the traditional PID control.

The Research and Simulation of PID Algorithm Optimization for Concrete Mixing

In order to fix the defects of the inaccurate control parameters in concrete intelligent mixing, this paper proposes a concrete mixing parameter control method based on fuzzy neural network PID control algorithm. The control method mainly includes two parts-control parameter calculation and mixing data feedback. According to the control parameter calculation, the proposed method is capable of calculating the control parameters required to control the concrete mixing. The industrial concrete mixing condition can be feedback to the control end via data feedback method. The control parameters can be adjusted according to the feedback data to accurately control the concrete mixing. The experimental results illustrate the proposed algorithm can effectively increase the control accuracy with satisfactory performance.

인공신경망 PID를 이용한 무인항공기 터보제트 엔진 제어

In this paper, controller Propose to prevent compressor surge and improve the transient response of the fuel flow control system of turbojet engine. Turbojet engine controller is designed by applying Artificial Neural Network PID control algorithm and make an inference by applying Artificial Neural Network Error Back Propagation Algorithm. To prevent any surge or a flame out event during the engine acceleration or deceleration, the ANN PID controller effectively controls the fuel flow input of the control system. ANN PID results are used as the fuel flow control inputs to prevent compressor surge and flame-out for turbo-jet engine and the controller is designed to converge to the desired speed quickly and safely. Using MATLAB to perform computer simulations verified the performance of the proposed controller. Response characteristics pursuant to the gain were analyzed by simulation.

고이득 관측기가 적용된 터보제트엔진의 인공신경망 PID 제어기 설계

In this paper, controller propose to prevent compressor surge and improve the transient response of the fuel flow control system of turbojet engine. Turbojet engine controller is designed by applying Artificial Neural Network PID control algorithm and make an inference by applying Levenberg-Marquartdt Error Back Propagation Algorithm. Artificial Neural Network inference results are used as the fuel flow control inputs to prevent compressor surge and flame-out for turbojet engine for UAV. High Gain Observer is used to estimate to compressor rotation speed of turbojet engine. Using MATLAB to perform computer simulations verified the performance of the proposed controller. Response characteristics pursuant to the gain were analyzed by simulation.

Design of Tiltrotor Flight Control System in Conversion Mode Using Improved Neutral Network PID

Considering the high-order, time-varying and nonlinear characteristics of the tiltrotor aircraft in conversion mode, the control requirements and the specific conversion scheme are presented first. An improved back propagation (BP) neural network PID control algorithm is then proposed, utilizing the strong nonlinear mapping characteristics of neural network. In the proposed algorithm, an inertia term is added to the gradient-descent-based weight adjustment formula of the conventional BP neutral network in order to increase the convergence rate and obtain satisfactory control effects. Finally simulation results indicate the effectiveness of the proposed algorihm.

Beer Fermentation Temperature Control Curve Optimization Based on the Fuzzy - Neural Network PID Control Algorithm

An auto-control model is presented to the process of beer fermentation, which has the characteristics such as time-varying, inertia, time-delay and nonlinear. The traditional PID control is difficult to accurately control. This paper according to the beer fermentation of problems puts forward a new control algorithm: fuzzy-neural network PID control algorithm. The fuzzy logistic differential control and intelligent integral control were supplemented into the fuzzy set-point weight tuning, so that the insufficiency of original PID control method was effectively improved. The advantages of this control algorithm are not only constitute a simple, small static error, dynamic response speed but also the ability to learn, etc. Therefore it not only can strengthen robust and intelligence of the system, but also make design simple and easily be required.

The Simulation of Robot Control Based on CMAC Neural Network PID Control Algorithm

According to the problem of nonlinear and uncertainty in robot control, this paper proposes a PID control algorithm based on CMAC neural network model, for the elimination of the influence of uncertainty caused by robot system parameters and external disturbance. The simulation results show that this algorithm can effectively overcome the uncertainties and external disturbance of robot system model, this algorithm has good robustness and stability, its performance is superior to the traditional PID control algorithm.

A Novel Three-phase Rectifier Based on Improved PID Control Algorithm

The three-phase rectifier based on traditional PID control algorithm can improve its harmonic effect, and increase its power factor, but it can’t overcome the problems of selection difficulty of the PID parameters and can realize the online self-turning function of the PID parameters. In order to deal with the questions, the three phase rectifier based on neural network PID control algorithm is designed in this paper. In this paper, the PID parameters of the novel rectifier can realize the function of the online self-turning, which increases the design efficiency and the control accuracy. The simulation results show that the three phase rectifier based on improved PID control algorithm can decrease the harmonic pollution and increase its power factor. DOI: http://dx.doi.org/10.11591/telkomnika.v11i1.1910

Fast Neural Network PID Control Algorithm Based on Multi-Step Predictive Index Function

Based on multi-step predictive index function, a fast neural network PID control algorithm is proposed. The algorithm uses multi-step predictive index function to train the weights of neural network PID controller, thereby, the system has the character of predictive control, and has faster dynamic speed than general neural network PID control.