CN115963730A - Selective control method for injection dispensing valve cavity liquid temperature - Google Patents
Selective control method for injection dispensing valve cavity liquid temperature Download PDFInfo
- Publication number
- CN115963730A CN115963730A CN202310250316.5A CN202310250316A CN115963730A CN 115963730 A CN115963730 A CN 115963730A CN 202310250316 A CN202310250316 A CN 202310250316A CN 115963730 A CN115963730 A CN 115963730A
- Authority
- CN
- China
- Prior art keywords
- control
- temperature
- coefficient
- pid
- parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention discloses a selective control method of injection dispensing valve cavity liquid temperature, which is composed of an improved single-neuron self-adaptive PID control algorithm, a PID control algorithm optimized by a limit learning machine and a relay self-correction algorithm.
Description
Technical Field
The invention belongs to the field of temperature control algorithms, and particularly relates to a selective control method for the temperature of liquid in a spray dispensing valve cavity.
Background
The dispensing technology is a key technology in the microelectronic packaging industry, along with the development of electronic equipment towards high integration, the performance requirement of the industry on the dispensing technology is increasingly improved, the current dispensing valve tends to high frequency and miniaturization, the working environment of the dispensing valve is increasingly complex, factors such as air flow, room temperature, dispensing frequency, temperature field of the dispensing valve and the like can cause temperature fluctuation, the volume of single liquid drops in the dispensing technology generally reaches the nanoliter (nL) magnitude, the dispensing consistency is directly influenced by the temperature fluctuation of glue solution, and the reduction of the temperature fluctuation of the glue solution has important significance for improving the dispensing performance.
Because the dispensing valve temperature control system has the characteristics of time variation, nonlinearity, pure hysteresis and the like, algorithm research on the dispensing valve temperature control system needs to have optimization and improvement functions, a classical PID control theory is mature and easy to realize, and static errors can be eliminated. The intelligent PID controller is an organic combination of artificial intelligence and classical PID, can exert the characteristics of excellent dynamic response and strong robustness of artificial intelligence control, and also has the advantage of higher steady-state precision of PID control, so that a plurality of students research an advanced control method for combining an artificial intelligence algorithm and the classical PID, but few researches are carried out on the advanced control algorithm of a dispensing valve temperature control system at present, and a selective control method for the liquid temperature of a spraying dispensing valve cavity is urgently needed to solve the problems.
Disclosure of Invention
In view of the above-mentioned limitations of the prior art methods, the present invention is directed to a highway cloud charging system, which solves one or more of the problems of the prior art, and provides at least one of the advantages.
To achieve the above object, according to an aspect of the present invention, there is provided a selective control method of a temperature of a spray dispensing valve chamber liquid, the method comprising the steps of:
the self-correcting relay control method is composed of a single neuron self-adaptive PID control algorithm, an extreme learning machine optimized PID control algorithm and a relay self-correcting algorithm. And determining the current temperature control stage according to the actual cavity liquid temperature of the dispensing valve through a relay self-correction algorithm, and initializing and setting the proportional, integral and differential parameters of the PID controller. In the temperature rapid change control stage, the selective control algorithm selects an improved single-neuron adaptive PID control algorithm through a relay switch to track and control the temperature, so that the system overshoot is reduced, and the response speed is increased. Because the single neuron PID has poor steady-state control effect, in the constant temperature control stage, the selective control algorithm selects the PID control algorithm optimized by the extreme learning machine through the relay switch to control the temperature, and the robustness and the disturbance resistance of the system are improved.
Further, the relay self-correction algorithm comprises the following steps: adopting a system output temperature feedback decision mode to carry out on-off operation on a relay switch to select different control algorithms, adopting a relay feedback mode to carry out initialization automatic correction on parameters of a PID controller, under the condition of each time interval, calculating the parameters of the PID controller by a relay self-correction algorithm and storing the parameters in corresponding addresses of a memory, outputting full power by a temperature control module after receiving a setting command, rapidly controlling the temperature to fall and reach a target value, cooling by full power when the temperature exceeds the set target value, heating by full power when the actual temperature is lower than the set temperature, enabling the system to generate a symmetrical oscillation curve, recording the oscillation curve, and recording the oscillation period after the oscillation is stableAnd an oscillation amplitude A and by means of the oscillation period>And the oscillation amplitude A initiates three parameters of the correction PID controller, which are respectively proportional gain->Integration function->And differentiation action->The calculation method comprises the following steps:
in the formula (I), the compound is shown in the specification,is a period of oscillation, is greater than or equal to>For the amplitude of the input power>Is an intermediate parameter.
Preferably, the relay self-correction algorithm comprises temperature feedback and parameter setting, the temperature feedback takes the difference between the actual cavity fluid temperature and the actual temperature and the set temperature as a feedback variable, and the current temperature control stage is determined through the two feedback variables.
Furthermore, linear quadratic form performance index in optimal control is introduced to calculate a control rule on the basis of the single neuron PID control algorithm, so that control output is optimized, the quadratic form performance index is minimized by modifying the weight coefficient of the single neuron controller, and the temperature self-adaptive PID optimal control can be realized, wherein the linear quadratic form performance index is expressed as,/>The expression of (c) is:
wherein r (k) and y (k) are input temperature value and output temperature value of the control system respectively,for the output variable of the controller, P, Q is the weighting coefficient of the output error and the control increment weighting coefficient, respectively, and the weighting coefficient of the single neuron is updated by the gradient descent method, specifically:
e(k)=r(k)-y(k);
in the formula (I), the compound is shown in the specification,weight coefficient expressed as single neuron, <' > in>Expressed as a learning rate of neurons>Is a constant value, said->() In order to calculate the function partial derivative, e (k) is the error of the control system at the moment k;
the calculated result is: the weight coefficient of the neuron of the controller at any moment, the weight coefficient of every moment can guarantee to make the temperature of the cavity liquid and ideal temperature most similar when the control system outputs the heating device of the action domain, namely guarantee the control effect of the variable temperature stage is optimal through the weight coefficient of the neuron of dynamic renewal, the control error is minimum.
Further, the weighting coefficient of the single neuron is updated by a gradient descent method, the stability of the control system is changed, an intelligent regulation coefficient K capable of automatically regulating the single neuron and a regulation coefficient alpha are set, the regulation coefficient K is a variable, the regulation coefficient alpha is a constant, and the improved single neuron adaptive PID control algorithm specifically comprises the following steps:
in the formula (I), theFor an initial value which automatically adjusts the intelligent regulation factor K for a single neuron, the evaluation of the neuron>、/>、/>Learning rates of the proportional, integral and differential parameters respectively; e (k) is the system error, is greater than or equal to>Is a weighted coefficient of the neuron, is calculated>And &>The weights of the proportional, integral and differential neurons of the PID controller are respectively, m is a set coefficient value, and the value of m is as follows:
parameters at the control ratioIn the calculation, an error value is greater or less>Compared with an input value>In the case of a large phase difference or->Is small in order for the controller to be able to bring the output object close ∑ or ∑ in order to enable the controller to>Then define m =1, otherwiseIf the value of (b) is within a reasonable range, m =0.1 is defined, and the control precision is exchanged by sacrificing the control speed.
Preferably, on the basis of a single neuron PID controller of an unsupervised Hebb learning law with a supervision Delta learning rule, a linear quadratic performance index is introduced to calculate a control rule, and a weighting coefficient of the single neuron is optimized by taking the minimum quadratic performance index as a target, so that the optimal temperature control performance and response speed are achieved.
And further, judging the control stage of the current control system through a relay self-correction algorithm, if the control stage is judged to be the constant temperature control stage at present through the relay self-correction algorithm, selecting a PID (proportion integration differentiation) control algorithm optimized by an extreme learning machine by the control system, and adjusting the parameters of a PID controller in real time on line by using the extreme learning machine according to the temperature of the dispensing valve cavity liquid so as to enhance the adaptability and reduce the overshoot.
Further, the PID control algorithm optimized by the control system selection extreme learning machine is operated in the extreme learning machine, the extreme learning machine is composed of an input layer, a hidden layer and an output layer, the input layer is provided with three neurons, and the error trend is calculatedError amount e (k), and error change rate @>As three inputs of the extreme learning machine, the output layer also has three neurons which respectively correspond to the proportionality coefficient->Integration factor->And a differentiation coefficient>。
Preferably, if the relay self-correction algorithm judges that the current stage is the constant temperature control stage, the control system selects a PID control algorithm optimized by the extreme learning machine, and the specific implementation steps of the algorithm are as follows:
first, training of an extreme learning machine model is performed:
the three input variables of the input layer neurons are:
the three output variables of the output layer are respectively:
furthermore, the parameter optimization design of the PID control algorithm optimized by the extreme learning machine, the trained extreme learning machine model predicts the PID controller parameters in real time, and the proportional coefficient is comparedIntegration factor->And a differentiation coefficient>Carrying out amplification treatment:
to select the optimal parameters, control values for n =3, 2 and 1 are calculated in sequence:
and finally, updating the parameters of the PID controller in real time according to the amplified output parameters, thereby realizing the steady-state control in the constant temperature control stage.
The invention has the beneficial effects that:
1. all parameters of the dispensing valve temperature selective control algorithm provided by the invention are automatically adjusted, the method has high robustness, and the control effect is poor without aging and damage of a controlled object.
2. The invention judges the current temperature control stage through the relay self-correction algorithm so as to self-adaptively select the improved single-neuron PID controller and the optimized PID controller of the extreme learning machine, and adopts the optimal control algorithm of the stage aiming at different temperature control stages, so that the temperature control of the dispensing valve can be more accurate, faster and more stable, and the consistency of the dispensing process is better ensured.
Drawings
The above and other features of the present invention will become more apparent by describing in detail embodiments thereof with reference to the attached drawings in which like reference numerals designate the same or similar elements, it being apparent that the drawings in the following description are merely exemplary of the present invention and other drawings can be obtained by those skilled in the art without inventive effort, wherein:
FIG. 1 is a block diagram of a selective control algorithm for a jetting dispensing valve in accordance with the present invention;
FIG. 2 is a block diagram of an improved single neuron PID control algorithm system proposed by the present invention;
FIG. 3 is a block diagram of a PID control algorithm system for extreme learning machine optimization according to the present invention;
FIG. 4 is a block diagram of a temperature control system according to an embodiment of the present invention;
FIG. 5 is a graph showing the temperature of the chamber fluid in accordance with an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it should be understood that the embodiments described herein are merely illustrative and not restrictive of the present invention.
A method for selectively controlling the temperature of a spray dispensing valve cavity fluid, the method comprising the steps of:
as shown in fig. 1 and 2, the self-correcting relay control method is composed of a single-neuron self-adaptive PID control algorithm, an extreme learning machine optimized PID control algorithm, and a relay self-correcting algorithm. And determining the current temperature control stage according to the actual cavity liquid temperature of the dispensing valve through a relay self-correction algorithm, and initializing and setting the proportional, integral and differential parameters of the PID controller. In the temperature rapid change control stage, the selective control algorithm selects an improved single-neuron adaptive PID control algorithm through a relay switch to track and control the temperature, so that the system overshoot is reduced, and the response speed is increased. Because the single neuron PID steady state control effect is poor, in the constant temperature control stage, the selective control algorithm selects the PID control algorithm optimized by the extreme learning machine through the relay switch to control the temperature, and the robustness and the disturbance resistance of the system are improved.
Further, the relay self-correction algorithm comprises the following steps: adopting a system output temperature feedback decision mode to carry out on-off operation on a relay switch to select different control algorithms, adopting a relay feedback mode to carry out initialization automatic correction on parameters of a PID controller, under the condition of each time interval, calculating the parameters of the PID controller by a relay self-correction algorithm and storing the parameters in corresponding addresses of a memory, outputting full power by a temperature control module after receiving a setting command, rapidly controlling the temperature to fall and reach a target value, cooling by full power when the temperature exceeds the set target value, heating by full power when the actual temperature is lower than the set temperature, enabling the system to generate a symmetrical oscillation curve, recording the oscillation curve, and recording the oscillation period after the oscillation is stableAnd an oscillation amplitude A and is combined over the oscillation period>And the oscillation amplitude A initiates three parameters of the correction PID controller, which are respectively proportional gain->Integrating action>And differentiation action->The calculation method comprises the following steps:
in the formula (I), the compound is shown in the specification,is a period of oscillation, is greater than or equal to>For the amplitude of the input power, is greater or less>Is an intermediate parameter.
Preferably, the relay self-correction algorithm comprises temperature feedback and parameter setting, the temperature feedback takes the difference between the actual cavity fluid temperature and the actual temperature and the set temperature as a feedback variable, and the current temperature control stage is determined through the two feedback variables.
Furthermore, linear quadratic form performance index in optimal control is introduced to calculate a control rule on the basis of the single neuron PID control algorithm, so that control output is optimized, the quadratic form performance index is minimized by modifying the weight coefficient of the single neuron controller, and the temperature self-adaptive PID optimal control can be realized, wherein the linear quadratic form performance index is expressed as,/>The expression of (a) is: />
Wherein r (k) and y (k) are input temperature value and output temperature value of the control system respectively,for the output variables of the controller, P, Q is the output error and control, respectivelyMaking a weighting coefficient of an increment weighting coefficient, and updating the weighting coefficient of a single neuron by a gradient descent method, wherein the method specifically comprises the following steps:
e(k)=r(k)-y(k);
in the formula (I), the compound is shown in the specification,weight coefficient expressed as single neuron, <' > in>Expressed as the learning rate of the neuron, <' >>Is a constant value, said->() In order to calculate the function partial derivative, e (k) is the error of the control system at the moment k;
the calculated result is: the weight coefficient of the neuron at any moment of the controller can ensure that the temperature of the cavity liquid is closest to the ideal temperature when the control system outputs the action domain heating device, namely, the neuron weight coefficient is dynamically updated to ensure the optimal control effect in the temperature changing stage and the minimum control error.
Further, the weighting coefficient of the single neuron is updated by a gradient descent method, the stability of the control system is changed, an intelligent regulation coefficient K capable of automatically regulating the single neuron and a regulation coefficient alpha are set, the regulation coefficient K is a variable, the regulation coefficient alpha is a constant, and the improved single neuron adaptive PID control algorithm specifically comprises the following steps:
in the formula (I), theFor an initial value which automatically adjusts the intelligent regulation factor K for a single neuron, the evaluation of the neuron>、/>、/>Learning rates of the proportional, integral and differential parameters respectively; e (k) is the system error, is greater than or equal to>Is a weighted coefficient of the neuron, is calculated>And &>The weights of the proportional, integral and differential neurons of the PID controller are respectively, m is a set coefficient value, and the value of m is as follows:
parameters at the control ratioIn the calculation, an error value is greater or less>Is compared with the input value->In the event of a large phase difference or +>In order for the controller to be able to bring an output object close to ÷ for>Then m =1 is defined and vice versa>If the value of (b) is within a reasonable range, m =0.1 is defined, and the control precision is exchanged for the control speed.
Preferably, on the basis of a single neuron PID controller of an unsupervised Hebb learning law with a supervision Delta learning rule, a linear quadratic performance index is introduced to calculate a control rule, and a weighting coefficient of the single neuron is optimized by taking the minimum quadratic performance index as a target, so that the optimal temperature control performance and response speed are achieved.
And further, judging the control stage of the current control system through a relay self-correction algorithm, if the control stage is judged to be the constant temperature control stage at present through the relay self-correction algorithm, selecting a PID (proportion integration differentiation) control algorithm optimized by an extreme learning machine by the control system, and adjusting the parameters of a PID controller in real time on line by using the extreme learning machine according to the temperature of the dispensing valve cavity liquid so as to enhance the adaptability and reduce the overshoot.
Further, as shown in fig. 3, the PID control algorithm optimized by the control system selecting the extreme learning machine is operated in the extreme learning machine, and the extreme learning machine is composed of an input layer, a hidden layer and an output layer, wherein the input layer has three neurons, and the error trend is calculatedError amount e (k), and error change rate @>As three inputs of the extreme learning machine, the output layer also has three neurons which respectively correspond to the proportionality coefficient->Integration coefficient>And differential coefficient。
Preferably, if the relay self-correction algorithm judges that the current stage is the constant temperature control stage, the control system selects a PID control algorithm optimized by the extreme learning machine, and the specific implementation steps of the algorithm are as follows:
first, training of an extreme learning machine model is performed:
the three input variables of the input layer neurons are:
the three output variables of the output layer are respectively:
furthermore, the parameter optimization design of the PID control algorithm optimized by the extreme learning machine, the trained extreme learning machine model predicts the PID controller parameters in real time, and the proportional coefficient is comparedIntegration coefficient>And a differential coefficient->Carrying out amplification treatment:
to select the optimal parameters, control values of n =3, 2 and 1 are calculated in sequence:
and finally, updating the parameters of the PID controller in real time according to the amplified output parameters, thereby realizing the steady-state control in the constant temperature control stage.
The temperature control system of the dispensing valve is based on the selective temperature control algorithm disclosed by the invention, the temperature control system takes STM32 as a main control chip, and the temperature of a glue cavity is collected through a platinum resistor to form closed-loop feedback. The system structure block diagram is shown in fig. 4.
In specific implementation, a selective control algorithm (hereinafter referred to as selective PID) and a fuzzy PID program disclosed by the invention are respectively written into the STM32 to carry out a glue solution cavity temperature control experiment, the PC end sends a starting command by using MATLAB, the temperature control system sends glue solution temperature information to the PC in real time through a UART serial port, and a glue solution temperature change curve is drawn according to collected temperature data after the temperature control experiment is completed. The glue temperature curve is shown in figure 5. The target temperature was set at 70 ℃ which is commonly used in dispensing processes. When the temperature of the flow channel is different from the set value by more than 20 ℃, the heating device runs at full power, and when the temperature of the flow channel reaches more than 50 ℃, the controller starts to adjust the heating power.
Comparing the two temperature curves, the two controllers perform almost the same during the set point rise from room temperature due to the more appropriate parameters of the fuzzy PID. The selective PID controller can return to the set point more quickly and without oscillation after a similar external temperature disturbance, while the fuzzy PID is accompanied by small amplitude oscillations after returning to the set temperature and the oscillation amplitude has a tendency to increase. The temperature fluctuation reached 1 ℃ after 480s, while the temperature fluctuation of the selective PID was always stabilized within 0.5 ℃.
Finally, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that various changes, modifications and equivalents may be made therein without departing from the spirit and scope of the invention.
Claims (6)
1. A selective control method for the liquid temperature of an injection dispensing valve cavity is characterized in that an improved single neuron self-adaptive PID control algorithm and an optimized PID control algorithm of an extreme learning machine are selected in a self-adaptive manner according to different temperature control stages through a relay self-correction algorithm, so that optimal control of different temperature control stages is realized;
the relay self-correction algorithm comprises the following steps: adopting a system output temperature feedback decision mode to carry out on-off operation on a relay switch to select different control algorithms, adopting a relay feedback mode to carry out initialization automatic correction on parameters of a PID controller, under the condition of each time interval, calculating the parameters of the PID controller by a relay self-correction algorithm and storing the parameters in corresponding addresses of a memory, outputting full power by a temperature control module after receiving a setting command, rapidly controlling the temperature to fall and reach a target value, cooling by full power when the temperature exceeds the set target value, heating by full power when the actual temperature is lower than the set temperature, enabling the system to generate a symmetrical oscillation curve, recording the oscillation curve, and recording the oscillation period after the oscillation is stableAnd an oscillation amplitude A and by means of the oscillation period>And an oscillation amplitude A three parameters of an initialization correction PID controller, which are respectively proportional gain &>Integration function->And differentiation action->The calculation method comprises the following steps:
2. The selective control method of injection dispensing valve chamber fluid temperature of claim 1, wherein based on the single neuron PID control algorithmThe linear quadratic performance index in the optimal control is introduced to calculate the control rule so as to optimize the control output, the quadratic performance index is minimized by modifying the weight coefficient of the unit neuron controller, the self-adaptive PID optimal control of the temperature can be realized, and the linear quadratic performance index is expressed as,/>The expression of (a) is:
wherein r (k) and y (k) are input temperature value and output temperature value of the control system respectively,for the output variables of the controller, P, Q is the weighting coefficient of the output error and the control increment weighting coefficient, respectively, and the weighting coefficient of the single neuron is updated by a gradient descent method, specifically:
e(k)=r(k)-y(k);
in the formula (I), the compound is shown in the specification,weight coefficient expressed as single neuron, <' > in>Expressed as a learning rate of neurons>Is a constant value, said->() In order to calculate the function partial derivative, e (k) is the error of the control system at the moment k;
3. the selective control method for the injection dispensing valve chamber liquid temperature according to claim 2, characterized in that the stability of the control system is changed by updating the weighting coefficient of a single neuron through a gradient descent method, an intelligent adjustment coefficient K for the single neuron and an adjustment coefficient α which can be automatically adjusted are set, the adjustment coefficient K is a variable, the adjustment coefficient α is a constant, and the improved single neuron adaptive PID control algorithm is specifically:
in the formula (I), theFor an initial value which automatically adjusts the intelligent regulation factor K for a single neuron, the evaluation of the neuron>、/>、/>Learning rates of the proportional, integral and differential parameters respectively; e (k) is the system error, is greater than or equal to>Is a weighted coefficient of the neuron, is calculated>And &>The weights of the proportional, integral and differential neurons of the PID controller are respectively, m is a set coefficient value, and the value of m is as follows:
4. the selective control method for the temperature of the injection dispensing valve cavity liquid according to claim 1, characterized in that the control stage of the current control system is judged through a relay self-correction algorithm, if the relay self-correction algorithm judges that the current control stage is a constant temperature control stage, the control system selects a PID control algorithm optimized by a limit learning machine, and the parameters of a PID controller are adjusted on line in real time by the limit learning machine according to the temperature of the dispensing valve cavity liquid.
5. The method as claimed in claim 4, wherein the PID control algorithm optimized by the control system selects an extreme learning machine to operate in the extreme learning machine, the extreme learning machine is composed of three layers of networks, namely an input layer, a hidden layer and an output layer, wherein the input layer has three neurons, and the error trend is calculated by the three layers of networksError amount e (k), and error change rate @>As three inputs of the extreme learning machine, the output layer also has three neurons which respectively correspond to the proportionality coefficient->Integration factor->And a differential coefficient->。
6. The selective control method for liquid temperature in injection dispensing valve cavity according to claim 4, characterized in that the parameter optimization design of the PID control algorithm optimized by the extreme learning machine is implemented, the trained extreme learning machine model predicts the PID controller parameters in real time, and the proportional coefficient is compared with the proportional coefficientIntegration factor->And a differentiation coefficient>Carrying out amplification treatment: />
To select the optimal parameters, control values of n =3, 2 and 1 are calculated in sequence:
and finally, updating the parameters of the PID controller in real time according to the amplified output parameters, thereby realizing the steady-state control in the constant temperature control stage.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310250316.5A CN115963730B (en) | 2023-03-16 | 2023-03-16 | Selective control method for liquid temperature of injection dispensing valve cavity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310250316.5A CN115963730B (en) | 2023-03-16 | 2023-03-16 | Selective control method for liquid temperature of injection dispensing valve cavity |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115963730A true CN115963730A (en) | 2023-04-14 |
CN115963730B CN115963730B (en) | 2023-06-02 |
Family
ID=85889837
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310250316.5A Active CN115963730B (en) | 2023-03-16 | 2023-03-16 | Selective control method for liquid temperature of injection dispensing valve cavity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115963730B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103576672A (en) * | 2013-10-23 | 2014-02-12 | 北京七星华创电子股份有限公司 | Self-correcting method and device for temperature control system of LPCVD equipment |
CN104235820A (en) * | 2014-09-29 | 2014-12-24 | 苏州大学 | Boiler steam temperature control method based on improved single neuron adaptive PID (proportion integration differentiation) control strategy |
CN104391444A (en) * | 2014-12-10 | 2015-03-04 | 福州大学 | Improved single-neuron PID tuning method based on discrete system |
CN107621837A (en) * | 2017-04-26 | 2018-01-23 | 中南大学 | A kind of Variable power temperature control system and control method for fluid injection valve |
US20180157281A1 (en) * | 2016-12-02 | 2018-06-07 | Inventec (Pudong) Technology Corporation | Method of temperature control and cabinet |
CN113996501A (en) * | 2021-09-27 | 2022-02-01 | 普洛赛斯(苏州)软件科技有限公司 | Glue solution temperature regulating system of intelligent glue dispensing robot |
-
2023
- 2023-03-16 CN CN202310250316.5A patent/CN115963730B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103576672A (en) * | 2013-10-23 | 2014-02-12 | 北京七星华创电子股份有限公司 | Self-correcting method and device for temperature control system of LPCVD equipment |
CN104235820A (en) * | 2014-09-29 | 2014-12-24 | 苏州大学 | Boiler steam temperature control method based on improved single neuron adaptive PID (proportion integration differentiation) control strategy |
CN104391444A (en) * | 2014-12-10 | 2015-03-04 | 福州大学 | Improved single-neuron PID tuning method based on discrete system |
US20180157281A1 (en) * | 2016-12-02 | 2018-06-07 | Inventec (Pudong) Technology Corporation | Method of temperature control and cabinet |
CN107621837A (en) * | 2017-04-26 | 2018-01-23 | 中南大学 | A kind of Variable power temperature control system and control method for fluid injection valve |
CN113996501A (en) * | 2021-09-27 | 2022-02-01 | 普洛赛斯(苏州)软件科技有限公司 | Glue solution temperature regulating system of intelligent glue dispensing robot |
Non-Patent Citations (2)
Title |
---|
周德胜: "神经网络PID在网络控制系统中的设计和仿真", 《中国优秀硕士学位论文全文数据库(电子期刊) 信息科技辑》 * |
邓圭玲 等: "基于模糊 PID 的点胶阀温度控制系统设计", 《传感与微系统》 * |
Also Published As
Publication number | Publication date |
---|---|
CN115963730B (en) | 2023-06-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106647283A (en) | Auto-disturbance rejection position servo system optimization design method based on improved CPSO | |
CN107608209A (en) | The feedforward of piezoelectric ceramic actuator and closed loop composite control method, system | |
CN111766777A (en) | PID controller and PID control method | |
CN105425612A (en) | Preferred method of water turbine adjustment system control parameter | |
CN105114242A (en) | Hydro governor parameter optimization method based on fuzzy self-adaptive DFPSO algorithm | |
CN110531614B (en) | Novel brushless DC motor fuzzy neural network PI controller | |
CN111006843B (en) | Continuous variable speed pressure method of temporary impulse type supersonic wind tunnel | |
CN111413872A (en) | Air cavity pressure rapid active disturbance rejection method based on extended state observer | |
CN104122795A (en) | Novel extremal function index based intelligent self-turning PID (Proportion Integration Differentiation) indoor temperature control algorithm | |
CN109507884B (en) | Air-oxygen mixer pressure control method and device, computer equipment and storage medium | |
CN204595644U (en) | Based on the aluminum-bar heating furnace temperature of combustion automaton of neural network | |
CN117093033A (en) | Resistance heating furnace temperature control system for optimizing PID parameters based on particle swarm optimization | |
Prusty et al. | A novel fuzzy based adaptive control of the four tank system | |
CN113268000B (en) | Soft switching method for multi-model predictive control of aircraft engine | |
CN113885328A (en) | Nuclear power tracking control method based on integral reinforcement learning | |
CN106054616A (en) | Titanium tape reel continuous pickling loop sleeve height control method for fuzzy logic optimizing PID controller parameters | |
CN115963730B (en) | Selective control method for liquid temperature of injection dispensing valve cavity | |
CN108549207A (en) | A kind of method of Adaptive System of Water-Turbine Engine control parameter | |
Lee et al. | A fuzzy controller for an aeroload simulator using phase plane method | |
CN112305912A (en) | Feedforward pressure control method based on reaction kettle parameter self-adjusting fuzzy PID algorithm | |
CN108089442B (en) | PI controller parameter self-tuning method based on prediction function control and fuzzy control | |
CN112748657B (en) | Parameter setting method for rotary inertial navigation active disturbance rejection controller based on adaptive genetic algorithm | |
CN113587120B (en) | Control method of plasma ash melting furnace | |
CN110671260A (en) | Nonlinear generalized predictive control method for regulating system of hydroelectric generating set | |
CN113110065B (en) | Reverse osmosis membrane group pressure optimal control method based on double RBF neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |