The ACA-BP Algorithm Based Controller of PID Neural Network and its Simulation

2012 ◽  
Vol 239-240 ◽  
pp. 1377-1381
Author(s):  
Fang Ding ◽  
Dong Jian Huang
Keyword(s):  
Neural Network ◽  
Pid Controller ◽  
Ant Colony Algorithm ◽  
Setting Time ◽  
Bp Algorithm ◽  
Practical Significance ◽  
Optimal Parameters ◽  
Neuron Network ◽  
Network Weight ◽  
Pid Neural Network

Aiming at the shortages of traditional PID controller, and problems of hardly setting the controller parameters, and the setting time is long, this paragraph gives a design of ACA-BP arithmetic based controller of PID Neural Network. First, uses the Ant Colony algorithm to thickly select the PID neuron network weight parameter. Then adjust parameters online by PID Neural Network and BP algorithm. Finally, we can obtain optimal parameters. The simulation result shows, compared with traditional PID controller, this controller has greatly improved its control performances. This would have some theoretical and practical significance.

Ant Colony Algorithm Based on Improved Neural Network Algorithm and its Application

2014 ◽  
Vol 543-547 ◽  
pp. 2116-2119
Author(s):  
Qing Qing Zhang ◽  
Qian Zhang ◽  
Yue Jiang Feng
Keyword(s):  
Neural Network ◽  
Adaptive Learning ◽  
Ant Colony Algorithm ◽  
Bp Algorithm ◽  
Ant Colony ◽  
Ant Colony System ◽  
Bp Network ◽  
Actual Problem ◽  
Node Number ◽  
Network Learning

This paper mainly to the ant colony algorithm ant colony system (application pseudo-random proportional rules) and add adaptive learning, momentum BP algorithm of these three together was improved, established a hybrid algorithm, to a certain extent overcome the BP algorithm is easy to fall into local minimum value, slow convergence speed, and achieved satisfactory results. Generally speaking, the performance of BP network is composed of two components: the topology of the network and network learning algorithm. The topology of the network design especially hidden node number should be how to choose the number of neurons more reasonable there is no unified theory, the solution actual problem at present is more of the experience and the method of combining the test to determine the optimal number of hidden nodes. This paper mainly discussed the structure of neural network to determine later, network learning process problems.

Research on Pressurizer Pressure Control System Based on BP Neural Network Control of Self-Adjusted PID Parameters

2013 ◽  
Vol 291-294 ◽  
pp. 2416-2423 ◽  
Author(s):  
Guo Duo Zhang ◽  
Xu Hong Yang ◽  
Dong Qing Lu ◽  
Yong Xiao Liu
Keyword(s):  
Neural Network ◽  
Control System ◽  
Bp Neural Network ◽  
Pid Controller ◽  
Nuclear Reactor ◽  
Control Method ◽  
Setting Time ◽  
Pressure Control ◽  
Network Control ◽  
Pressure System

The pressurizer is an important device in nuclear reactor system, and the traditional PID regulator is usually used to control pressure system of pressurizer in modern reactors. However, it is difficult to get precise parameters of traditional PID controller, and the PID control method is relied on the precise mathematical model badly. And the response of PID controller is often shown by the large amount of overshoot and long setting time which are not the desired results. For such a large inertia and complex time-varying control system, the tradition PID controller can not obtain the satisfy control results. A controller based on BP neural network in this paper has a simple structure, and the parameters of PID controller can be tuned on-line by the neural network self-learning characteristics. The computer simulation experiment demonstrates that the BP neural network PID controller performs very well when compared with the tradition PID regulator in minimal overshoot and more quick response.

scholarly journals Prediction of Ammunition Storage Reliability Based on Improved Ant Colony Algorithm and BP Neural Network

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-13 ◽  
Author(s):  
Fang Liu ◽  
Hua Gong ◽  
Ligang Cai ◽  
Ke Xu
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Ant Colony Algorithm ◽  
Data Augmentation ◽  
Storage Period ◽  
Small Sample ◽  
Bp Algorithm ◽  
Ant Colony ◽  
Bp Network ◽  
Data Pretreatment

Storage reliability is an important index of ammunition product quality. It is the core guarantee for the safe use of ammunition and the completion of tasks. In this paper, we develop a prediction model of ammunition storage reliability in the natural storage state where the main affecting factors of ammunition reliability include temperature, humidity, and storage period. A new improved algorithm based on three-stage ant colony optimization (IACO) and BP neural network algorithm is proposed to predict ammunition failure numbers. The reliability of ammunition storage is obtained indirectly by failure numbers. The improved three-stage pheromone updating strategies solve two problems of ant colony algorithm: local minimum and slow convergence. Aiming at the incompleteness of field data, “zero failure” data pretreatment, “inverted hanging” data pretreatment, normalization of data, and small sample data augmentation are carried out. A homogenization sampling method is proposed to extract training and testing samples. Experimental results show that IACO-BP algorithm has better accuracy and stability in ammunition storage reliability prediction than BP network, PSO-BP, and ACO-BP algorithm.

Application of intelligent technologies for modeling of controlled switching systems

2021 ◽  
Author(s):  
D.Y. Openkin ◽  
S.V. Chernomordov
Keyword(s):  
Neural Network ◽  
Numerical Optimization ◽  
Pid Controller ◽  
Optimization Methods ◽  
Practical Significance ◽  
Transport Systems ◽  
Neural Network Modeling ◽  
Switching Systems ◽  
Controlled Switching ◽  
Algorithmic Software

The development of instrumental and methodological support for modeling nonlinear control systems with switching is an urgent problem. Various modifications of numerical optimization methods and artificial intelligence technologies are used to solve this problem. The purpose of this article is to develop algorithmic software for modeling controlled switching systems based on the use of intelligent technologies and numerical optimization methods. Algorithmic software for the synthesis of feedback controls using a PID controller is developed. Intelligent technologies for modeling controlled switching systems are characterized. An algorithm using global parametric optimization methods is proposed for tuning the PID controller. Models of nonlinear dynamic switching systems are studied. An algorithm for finding optimal trajectories based on neural network automata is proposed. The basis for further research is developed, in which it is planned to create a software implementation of the switching algorithm and the neural network algorithm. The practical significance of the results is that the developed algorithmic software will allow analyzing the influence of various parameters on the quality and speed of functioning of intelligent control switching systems. The obtained results can be used in various problems of modeling and global optimization of controlled systems: technical systems with switching modes of operation, transport systems, as well as in problems of neural network modeling and machine learning.

Ant Colony Algorithm and Application in Inspection of Concrete Structure Defects

2012 ◽  
Vol 204-208 ◽  
pp. 3201-3205
Author(s):  
Wei Hua Zheng ◽  
Zong Hua Wang
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Ant Colony Algorithm ◽  
Bp Algorithm ◽  
Ant Colony ◽  
Ant Colony Optimization Algorithm ◽  
Structure Defects ◽  
Network Training ◽  
Network Method ◽  
Network Identification

BP neural network detecting concrete defect, convergence is slower and accuracy is not high. In order to overcome the defect of BP algorithm, using a combination of Ant Colony optimization algorithm and BP neural network method, a mathematical model of Ant Colony neural network was established, enables Ant Colony neural network training, and verify the validity of the method. And concluded: using ant Colony neural network identification of concrete defects, the identification of the location more effective than on size.

Research on Control Strategy of Automatic Control System for Sewage Treatment

2013 ◽  
Vol 791-793 ◽  
pp. 690-693
Author(s):  
Zhang Hong ◽  
Xiao Liang Liu ◽  
Fang Wei
Keyword(s):  
Neural Network ◽  
Control Strategy ◽  
Bp Neural Network ◽  
Pid Control ◽  
Pid Controller ◽  
Treatment Process ◽  
Sewage Treatment ◽  
Bp Algorithm ◽  
Dissolved Oxygen Concentration ◽  
Control Effect

For the characteristics of the sewage treatment process and a combination of BP algorithm and conventional PID control, a PID controller is proposed based on BP neural network to realize the online adjustment of PID controller parameters. This control strategy will be applied to the control of the DO(Dissolved Oxygen) concentration in sewage treatment, and a contrast has been made with conventional PID control effect.

An Advanced Optimization Model of Emerging Energy Priority - Development Fields Based on PS-NN Algorithm

2010 ◽  
Vol 439-440 ◽  
pp. 1030-1036
Author(s):  
Zhi Bin Liu ◽  
Yanna Su ◽  
Zhi Gang Zhang
Keyword(s):  
Neural Network ◽  
Convergence Rate ◽  
Bp Neural Network ◽  
Threshold Value ◽  
Bp Algorithm ◽  
Initial Weight ◽  
Learning Network ◽  
The Neural Network ◽  
Network Weight ◽  
Bp Neural Network Model

The scope of emerging energy is broad, and the development scale and stage of each kind of energy is also irregular. In order to choose the priority development fields of emerging energy, this paper introduces the particle swarm (PS) optimization algorithm into the neural network (NN) training based on an overall situation stochastic optimization thought, establishes the PS-BP neural network model, which optimizes the initial weight value of BP neural network using PS first, then uses the neural network to complete the study of given accuracy. The simulation results indicated that the improved PS-BP algorithm to be able to solve the slow convergence rate and easy to fall into local minimum of learning network weight and the threshold value of conventional BP algorithm effectively, has the quick convergence rate and the high evaluating precision.

An Improved BP Neural Network Algorithm and its Application

2014 ◽  
Vol 543-547 ◽  
pp. 2120-2123 ◽  
Author(s):  
Ming Jun Chen
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Ant Colony Algorithm ◽  
Back Propagation ◽  
Indicator System ◽  
Global Optimum ◽  
Bp Algorithm ◽  
Nonlinear Simulation ◽  
Network Algorithm ◽  
Neural Network Algorithm

Back-propagation (BP) neural network algorithm is currently used most widely and grows fastest for its powful nonlinear simulation capability. However BP neural network is so easy to fall into local minima that it cant find the global optimum which limits its application in many fields. The paper, taking tax innovation teaching evaluation for example, advances a new evaluation algorithm based on improved BP neural network algorithm. Firstly an evaluation indicator system of tax major innovation teaching is designed through analyzing the specific characteristics of innovation teaching requirements. Secondly, in order to overcome the shortages of low convergence speed of original BP neural network algorithm, the paper improves BP algorithm through integrating BP algorithm and ant colony algorithm, ant improving the overall search method of integrated algorithm. Thirdly data from three universities are taken for examples to verify the validity and feasibility of the model and the experimental results show that the model can evaluate university innovation teaching practically.

Research of Genetic Algorithm Controller Based Fuzzy Neural Network in Vacuum Pre-Cooling Freshness-Keeping Machine

2014 ◽  
Vol 926-930 ◽  
pp. 3545-3549
Author(s):  
Ke Liang Zhou ◽  
Qiong Tan ◽  
Jian He
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Pid Controller ◽  
Fuzzy Neural Network ◽  
Fuzzy Controller ◽  
Control Object ◽  
Bp Algorithm ◽  
Control Effect ◽  
Fuzzy Neural ◽  
The Difference

The control object is the temperature of pre-cooling machine, combined the advantage of neural network and genetic algorithm (GA). Adopting GA controller based fuzzy neural network. The controller doing the fuzzy reasoning to the difference of given temperature and sample temperature. GA does the offline training to the Connection weights and Membership function of fuzzy neural network, then uses BP algorithm to do further adjust online for parameters. Simulation result shows that the new controller achieves better control effect compared with traditional PID controller, fuzzy controller.

Sign in / Sign up

Export Citation Format

Share Document