CN-122018295-A - PLC environmental parameter self-adaptive adjusting system based on group intelligent optimization algorithm

CN122018295ACN 122018295 ACN122018295 ACN 122018295ACN-122018295-A

Abstract

The invention discloses a PLC environment parameter self-adaptive adjusting system based on a group intelligent optimization algorithm, which relates to the technical field of industrial automation control, and comprises the following steps: the PLC control module, the genetic algorithm improvement module, the neural network PID setting module, the performance judging and controlling execution module and the local database are used for globally optimizing the weight and the threshold of the back propagation neural network through the improved genetic algorithm, the back propagation neural network after optimization is used for mapping the environmental parameter deviation, the deviation integral and the derivative into PID control parameters, the PLC is driven to execute closed-loop adjustment after the performance judgment, the environmental parameter control precision and the robustness are improved, the industrial temperature and humidity working conditions with strong time variation and multiple disturbance can be dynamically adapted, the defects of complicated debugging and poor adaptability of the traditional fixed parameter PID are overcome, and the actual requirements of rapid deployment and refined control of an industrial field are met.

Inventors

KONG LING
ZHANG SHUAI
WANG MINGXIN

Assignees

傲拓科技股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260203

Claims (10)

1. The PLC environment parameter self-adaptive adjusting system based on the group intelligent optimization algorithm is characterized by comprising the following modules: the PLC control module is used for calculating the deviation, the deviation integral and the deviation derivative of the environmental parameters according to the actual output value of the acquired environmental parameters; The genetic algorithm improvement module is used for receiving the systematic deviation data and carrying out global optimization on the weight and the threshold value of the back propagation neural network through an improved genetic algorithm; the neural network PID setting module is used for mapping the deviation, the deviation integral and the deviation differential of the calculated environment parameters into three PID control parameters of a proportional constant, an integral time constant and a differential time constant according to the weight and the threshold value of the back propagation neural network obtained by the improved genetic algorithm; the performance judging and controlling executing module is used for judging the PID control parameters and inputting the control values into the PLC temperature and humidity control device to execute the adjusting operation.
2. The adaptive adjustment system for the environmental parameters of the PLC based on the intelligent optimization algorithm of claim 1, wherein the calculating method comprises the following steps: at each sampling period, according to the current sampling time Actual output value of environmental parameter Setting value corresponding to the setting value Calculating the current sampling time The deviation value of (2) is And accumulating the deviation value of the current sampling time and the deviation values of all previous sampling times to obtain a deviation integral term, and dividing the difference value of the current sampling time and the deviation value of the previous sampling time by the sampling period to obtain the deviation integral term.
3. The adaptive adjustment system for the PLC environmental parameters based on the population intelligent optimization algorithm according to claim 2, wherein the global optimization of the weight and the threshold of the back propagation neural network is performed by the improved genetic algorithm, and the adaptive adjustment system specifically comprises the steps of generating an initialized population, calculating the fitness value of each individual in the initialized population, screening the individuals used for propagation in the initialized population, performing cross operation on the individuals screened for propagation, and performing mutation operation based on the set mutation probability.
4. The adaptive adjustment system for the PLC environmental parameters based on the intelligent optimization algorithm of the population according to claim 3, wherein the generation initialization population comprises the following specific generation methods: based on the number of neurons of the input neural layer of the counter-propagating neural network Number of neurons underlying the nerve layer And the number of neurons of the output nerve layer The required optimizing total number for obtaining the weight and the threshold value in the back propagation neural network is ; And the real number coding mode is adopted, the diversity of the initial solution population is enhanced through a Tent mapping strategy in chaotic mapping, and the expression is as follows: wherein Is the first The individual value of the individual(s), Is a mapping coefficient.
5. The adaptive adjustment system for PLC environmental parameters based on a population intelligent optimization algorithm according to claim 3, wherein the calculation method for calculating the fitness value of each individual in the initialized population is as follows: Calculating fitness value of each individual in the initialized population according to fitness calculation function, wherein the fitness calculation function is that , wherein, For the number of samples to be taken, Is the expression of the first in the genetic algorithm The location of the individual, which encodes all the trainable parameters of the back propagation neural network whose input neural layer has the number of neurons Number of neurons underlying the nerve layer And the number of neurons of the output nerve layer The trainable parameters include connection weights between the input layer and the hidden layer Therein, wherein Connection weights between hidden layer and output layer Wherein Threshold of hidden layer neurons Wherein Threshold of output layer neurons Wherein , Represent the first Individual at the first The final training output value in the individual training samples, Represent the first The final expected output value of the individual in the same sample.
6. The adaptive adjustment system for environmental parameters of a PLC based on a population intelligent optimization algorithm according to claim 3, wherein the specific method for screening the individuals used for propagation in the initialized population is as follows: obtaining the sum of fitness values of all the individuals in the population according to the fitness value of each individual in the initialized population as Calculating the probability that each individual in the initialized population is selected for reproduction as And selecting individuals for reproduction from the initialized population by a roulette selection method accordingly.
7. The adaptive adjustment system for the environmental parameters of the PLC based on the intelligent optimization algorithm of the population, according to claim 3, wherein the individuals to be screened for propagation are subjected to the cross operation, and the specific method is as follows: Three individuals with optimal fitness value are selected from the individuals used for propagation by screening the initialized population through a wolf algorithm, and are sequentially defined as 、 And The remaining other individuals are defined as Around three individual update locations, a specific evolutionary process is And Wherein 、 And Respectively represent 、 And And (3) with Is used for the distance of (a), 、、、、 And In order to control the coefficient of the power consumption, Represent the first After a plurality of iterations Is provided in the position of (a), 、 And Respectively represent the first After a plurality of iterations 、 And Is provided in the position of (a), 、 And Respectively represent the influence of the head wolves The direction and distance to be adjusted are required, Represent the first After a plurality of iterations Is a position of (c).
8. The adaptive adjustment system for PLC environmental parameters based on the intelligent optimization algorithm of claim 3, wherein the set mutation probability-based mutation operation is performed by the specific method comprising: For new individuals generated through the cross operation, selecting partial individuals to carry out the mutation operation through the Lewy flight strategy according to the set mutation probability, wherein the position update expression is as follows Wherein Representing the number of current iterations and, Represent the first Individual at the first The location of the number of iterations is, In order for the scaling factor to be a factor, 、 And For controlling parameters, where , , For a preset maximum number of iterations in the genetic algorithm, To at the same time Random numbers uniformly distributed in the interval.
9. The adaptive adjustment system for PLC environmental parameters based on a population intelligent optimization algorithm according to claim 3, wherein the mapping of the deviation, the deviation integral and the deviation derivative of the calculated environmental parameters into three PID control parameters of a proportional constant, an integral time constant and a derivative time constant is as follows: the method comprises the steps of taking a back propagation neural network with optimized weight and threshold value based on an improved genetic algorithm as a mapping model, and taking deviation, deviation integral and deviation differential of environmental parameters as input characteristic vectors to be transmitted to an input layer of the neural network, wherein the input characteristic vectors output a group of corresponding PID control parameters through an activation function of an implicit layer and an activation function of an output layer in the back propagation neural network, and the corresponding PID control parameters respectively correspond to proportionality constants Integration time constant Differential time constant These three PID control parameters.
10. The adaptive adjustment system for the environmental parameters of the PLC based on the intelligent optimization algorithm of claim 9, wherein the specific method for determining the PID control parameters and inputting the control values into the PLC temperature and humidity control device to perform the adjustment operation is as follows: according to each sampling moment Actual output value of environmental parameter Setting value corresponding to the setting value Calculate the performance index as When the performance index of the environmental parameter is smaller than the preset performance threshold, the current PID control parameter is judged to meet the requirement, the back propagation neural network learning is stopped, and the proportionality constant of the required PID control parameter is met Integration time constant Differential time constant Obtaining a control value required to be output by the PID controller through a PID control formula And the control value is calculated Inputting the control signals to corresponding executing mechanisms in the PLC temperature and humidity control device for adjustment; When the performance index of the environmental parameter is larger than or equal to a preset performance threshold, judging that the current PID control parameter does not meet the requirement, and triggering the parameter optimization and setting of the genetic algorithm improvement module and the neural network PID setting module again based on the weight and the threshold of the current counter propagation neural network.

Description

PLC environmental parameter self-adaptive adjusting system based on group intelligent optimization algorithm Technical Field The invention relates to the technical field of industrial automation control, in particular to a PLC environment parameter self-adaptive adjusting system based on a group intelligent optimization algorithm. Background In an automatic control system, a Programmable Logic Controller (PLC) is widely applied to environment parameter adjustment and process control systems of various industrial sites due to stable structure, high reliability and strong capability of adapting to complex industrial environments, and is particularly suitable for real-time monitoring and control of environment parameters such as temperature, humidity and the like. In the above application, the PLC is generally used as a core control unit to implement the collection and processing of various environmental parameters and the linkage control of the executing mechanism. Compared with the prior related scheme, the prior art, such as the patent application disclosed by CN120176263A, CN121246514A and related to the self-adaptive adjustment of environmental parameters, has obvious defects that the prior PLC environmental parameter adjustment mostly adopts fixed parameter PID control, the parameter setting depends on manual experience or repeated debugging, and is suitable for fixed working conditions but difficult to adapt to multi-scene universal equipment, and the problems of long debugging period and low efficiency exist. Although improved methods such as fuzzy PID and the like can be used for online parameter adjustment, manual design fuzzy rules are relied on, universality is poor, theoretical guidance is lacking in parameter selection, control performance is unstable under complex working conditions, and as controlled objects, working conditions and disturbance differences of an industrial field are obvious, problems such as response lag, overshoot increase, precision reduction and the like easily occur in fixed PID control when the environment changes, repeated adjustment is needed under a universal equipment scene, generalized large-scale application is restricted, and the parameters are required to be readjusted for a long time, so that maintenance cost is increased and control consistency is affected. The existing PLC control system is mature, but is difficult to adapt to the time-varying property, nonlinearity and the like of an environment object, and an adaptive control method is required to be introduced to improve the adjustment performance. Disclosure of Invention Aiming at the technical defects, the invention aims to provide a PLC environment parameter self-adaptive adjusting system based on a group intelligent optimization algorithm. In order to solve the technical problems, the invention adopts the following technical scheme that the invention provides a PLC environment parameter self-adaptive adjusting system based on a group intelligent optimization algorithm, which comprises a PLC control module, a control module and a control module, wherein the PLC control module is used for calculating the deviation, the deviation integral and the deviation derivative of the environment parameter according to the actual output value of the acquired environment parameter. And the genetic algorithm improvement module is used for receiving the systematic deviation data and performing global optimization on the weight and the threshold value of the back propagation neural network through an improved genetic algorithm. And the neural network PID setting module is used for mapping the deviation, the deviation integral and the deviation differential of the calculated environment parameters into three PID control parameters, namely a proportional constant, an integral time constant and a differential time constant, according to the weight and the threshold value of the back propagation neural network obtained by the improved genetic algorithm. The performance judging and controlling executing module is used for judging the PID control parameters and inputting the control values into the PLC temperature and humidity control device to execute the adjusting operation. The invention has the beneficial effects that (1) the first part of the invention combines the chaotic mapping strategy, the gray wolf optimization algorithm idea and the Lev flight strategy, improves the traditional genetic algorithm, enhances the population diversity and global searching capability, avoids the problems of premature convergence and local optimization, adopts the improved genetic algorithm, and develops global optimization on the weights of the input layer and the hidden layer, the weights of the hidden layer and the output layer, the hidden layer threshold and the output layer threshold of the back propagation neural network, thereby improving the learning capability and the convergence speed of the neural network. (2) In the second part o