Research on PID control system based on genetic algorithm

2011 ◽  
Author(s):  
Dingqun Zhang ◽  
Xinfeng Yang
Keyword(s):  
Genetic Algorithm ◽  
Control System ◽  
Pid Control

Control System Modeling for Automotive Brake Test-Bench Based on Improved PID Algorithm

2012 ◽  
Vol 542-543 ◽  
pp. 1007-1010
Author(s):  
Jia Xi Du ◽  
Hong Shen ◽  
Yuexia Feng
Keyword(s):  
Genetic Algorithm ◽  
Control System ◽  
Pid Control ◽  
Test Bench ◽  
Control Function ◽  
Fitness Function ◽  
System Modeling ◽  
Loop Model ◽  
Deviation Function ◽  
Automotive Brake

Based on PID controller, the closed-loop model of instantaneous torque for automotive brake test-bench was established, and then the instantaneous torque and the deviation function were calculated, furthermore, the genetic algorithm was adopted in order to get a global optimal solution and to optimize the parameters of the PID control system. So that the deviation function can be reduced or improved. By comparing the effect of control function, the causes for error volatility of the PID control system were derived, and the fitness function of genetic algorithm was determined reasonably. This algorithm can improve the reliability and accuracy of the control model effectively, and provide an effective method for testing the merits and integrated performance of automotive brake design.

Optimal analysis and application of the warp tension control system for a rapier loom

2021 ◽  
pp. 004051752110536
Author(s):  
Yanjun Xiao ◽  
Zhenpeng Zhang ◽  
Zhenhao Liu ◽  
Weiling Liu ◽  
Nan Gao ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Control System ◽  
Pid Control ◽  
Performance Optimization ◽  
Experimental Studies ◽  
Tension Control ◽  
Control Performance ◽  
Improved Genetic Algorithm ◽  
Warp Tension ◽  
Tension Control System

Traditional proportional–integral–derivative (PID) control performance optimization is an essential method to improve a loom’s warp tension control performance. This work proposes an improved genetic algorithm optimized PID control scheme to overcome the decline in control performance of the traditional PID control algorithm in a loom’s warp tension control system. Through the decoupling analysis of loom motion mechanism, the establishment of warp tension model and the optimization of fitness evaluation mechanism of genetic algorithm can effectively overcome the problems of local optimal solution and algorithm degradation of genetic algorithm. Simulation experiments were carried out with the traditional PID, the integral separation PID, and the genetic PID in warp tension control. The results show the advantage of the genetic-PID algorithm to control warp tension stability. Ultimately, according to the functional characteristics of the loom mechanism, a tension control platform for experimental studies was established. The test results show that the maximum fluctuation range of warp tension is within [−2, +6] at the test speed of 850 rpm, which meets the requirements of long-term stable and reliable control of warp tension under different weaving conditions.

Advanced design and tests of a new electrical control seeding system with genetic algorithm fuzzy control strategy

2021 ◽  
pp. 1-10
Author(s):  
Sheng Wang ◽  
Yanhong Sun ◽  
Chen Yang ◽  
Yongchang Yu
Keyword(s):  
Genetic Algorithm ◽  
Control System ◽  
Fuzzy Control ◽  
Electric Drive ◽  
Pid Control ◽  
Fuzzy Pid ◽  
Seeding Rate ◽  
Fuzzy Pid Control ◽  
Transmission Method ◽  
Better Than

In the existing soybean breeding and planting machinery, the power source of the metering device adopts the ground wheel transmission method mostly. However, this power transmission method is likely to cause slippage during the planting operation, which will cause problems such as the increase of the missed seeding index and the increase of the coefficient of plant spacing. It is not conducive for scientific researchers to carry out breeding operations. Aiming at this problem, an electronically controlled soybean seeding system is designed, and the power of the seed metering device is derived from the motor. In order to improve the control accuracy of the electronically controlled seeding system, the precise control of the soybean seeding rate is finally realized. The electric drive soybean seeding system adopts closed-loop control, the motor model of the electric drive seeding system is established, and the transfer function of the motor is obtained. PID control based on a genetic algorithm is adopted, and the corresponding parameters are substituted into the control system simulation model established in MATLAB/SIMULINK. Field verification tests have been carried out on the conventional fuzzy PID control system and the electric drive soybean planter of the fuzzy PID control system based on a genetic algorithm. The result showed that the average of the repeat-seeding parameter is 1.30% better than the average of conventional seeding system (1.40%), the average of the miss-seeding parameter is 1.08% better than the average of conventional seeding system (2.09%) and the average of row-spacing variation parameter is 2.79% better than the average of conventional seeding system (2.34%). In conclusion, the new seeding system is robust obviously. Field trial results show that seeding with Genetic Algorithm Fuzzy control is better.

Optimization of the Hydraulic Control System Utilizing BP Neural Network Control Strategy Based on Genetic Algorithm

2013 ◽  
Vol 397-400 ◽  
pp. 1245-1252
Author(s):  
Ying Ying Feng ◽  
Nan Mu Hui ◽  
Zong An Luo ◽  
Dian Hua Zhang
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Control System ◽  
Bp Neural Network ◽  
Pid Control ◽  
Hydraulic System ◽  
Learning Ability ◽  
Hydraulic Control ◽  
Control Effect ◽  
Hydraulic Control System

For the characteristic of the MMS series Thermo-Mechanical Simulator hydraulic control system, using traditional PID control method can not achieve the desired control effect. Basing on genetic algorithm, BP neural network, which has the arbitrary non-linear approximation ability, self-learning ability and generalization ability, has been used into the hydraulic control system to achieve the online adjustment of the weighting coefficients and the adaptive adjustment of PID control parameters. The results of simulation and online tests show that the control effect of hydraulic system has been improved significantly, and the accurate control of hydraulic system hammer displacement has been realized.

The Temperature Control of Electric Furnace Based on PID Genetic Algorithm

2012 ◽  
Vol 490-495 ◽  
pp. 828-834 ◽  
Author(s):  
Di Lu ◽  
Jian Xin Wang ◽  
Jia Feng Li
Keyword(s):  
Genetic Algorithm ◽  
Control System ◽  
Pid Control ◽  
Control Algorithm ◽  
Adaptive Genetic Algorithm ◽  
Quick Response ◽  
Actual Operation ◽  
Furnace Control ◽  
Pure Delay ◽  
Operation Results

The characteristics of Mathematical model for the temperature’s control of resistance-heated furnace are non-linear, strong inertia, time-variant and pure delay. Adaptive genetic algorithm(AGA) was designed by the principle of the traditional PID control system, and dynamically Simulated an industrial furnace control system. Simulation and actual operation results show that using the optimization algorithm has properties of no overshoot, quick response, good robust and the algorithm is simple. It is proved that this control algorithm is a more effective one on improving the temperature’s control of the resistance-heated furnace.

scholarly journals Self-Tuning Two Degree-of-Freedom Proportional–Integral Control System Based on Reinforcement Learning for a Multiple-Input Multiple-Output Industrial Process That Suffers from Spatial Input Coupling

Processes ◽  
2021 ◽  
Vol 9 (3) ◽  
pp. 487
Author(s):  
Fumitake Fujii ◽  
Akinori Kaneishi ◽  
Takafumi Nii ◽  
Ryu’ichiro Maenishi ◽  
Soma Tanaka
Keyword(s):  
Control System ◽  
Reinforcement Learning ◽  
Pid Control ◽  
Multiple Input Multiple Output ◽  
Industrial Process ◽  
Pi Controller ◽  
Multiple Input ◽  
Input Multiple Output ◽  
Self Tuning ◽  
Two Degree Of Freedom

Proportional–integral–derivative (PID) control remains the primary choice for industrial process control problems. However, owing to the increased complexity and precision requirement of current industrial processes, a conventional PID controller may provide only unsatisfactory performance, or the determination of PID gains may become quite difficult. To address these issues, studies have suggested the use of reinforcement learning in combination with PID control laws. The present study aims to extend this idea to the control of a multiple-input multiple-output (MIMO) process that suffers from both physical coupling between inputs and a long input/output lag. We specifically target a thin film production process as an example of such a MIMO process and propose a self-tuning two-degree-of-freedom PI controller for the film thickness control problem. Theoretically, the self-tuning functionality of the proposed control system is based on the actor-critic reinforcement learning algorithm. We also propose a method to compensate for the input coupling. Numerical simulations are conducted under several likely scenarios to demonstrate the enhanced control performance relative to that of a conventional static gain PI controller.

Sign in / Sign up

Export Citation Format

Share Document