CN104235820A - Boiler steam temperature control method based on improved single neuron adaptive PID (proportion integration differentiation) control strategy - Google Patents
Boiler steam temperature control method based on improved single neuron adaptive PID (proportion integration differentiation) control strategy Download PDFInfo
- Publication number
- CN104235820A CN104235820A CN201410511914.4A CN201410511914A CN104235820A CN 104235820 A CN104235820 A CN 104235820A CN 201410511914 A CN201410511914 A CN 201410511914A CN 104235820 A CN104235820 A CN 104235820A
- Authority
- CN
- China
- Prior art keywords
- steam temperature
- pid
- control
- single neuron
- coefficient
- 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.)
- Pending
Links
Abstract
The invention discloses a boiler steam temperature control method based on an improved single neuron adaptive PID (proportion integration differentiation) control strategy. The method comprises the following steps of establishing a overheat steam temperature control model of two stages of boilers, and designing a temperature lowering control system; enabling the auxiliary loop PID control of the temperature lowering control system to combine with a non-supervision Hebb learning rule and a supervision Delta learning rule to realize self learning; combining secondary property indexes to obtain a main loop single neuron adaptive PID control algorithm, and integrating three parameters of a controller into one parameter. The method has the advantages that the self learning of the single neuron is utilized, the change of overheat steam temperature working condition can be adapted by adjusting the control parameters on line, and the common problems of easiness in production of overlarge adjusting amount, large time lag and the like of the overheat steam temperature control system in the practical engineering application are solved.
Description
Technical field
The present invention relates to a kind of Steam Temperature for Boiler control method, be specifically related to a kind of Steam Temperature for Boiler control method based on improved single neuron Adaptive PID Control strategy.
Background technology
Power plant boiler is the complex object of a Non-linear coupling, large time delay, multivariable, many interference, current most domestic power plant boiler Superheated Steam Temperature Control System Applied still adopts PID controller, just many deficiencies are had thus on Control platform, such as exist and regulate not in time, and the problem such as overshoot is excessive.In addition, the research of a lot of overheating steam temperature cascade control system finds that conventional PID controller exists obvious weak point: regulate not in time, overshoot is large.The problems referred to above are caused to be because the parameter of Traditional PID controller is changeless, can only roughly carry out according to the requirement of whole control procedure adjusting of parameter, and overheating steam temperature regulating system has different requirements in each stage of control procedure to parameter.Therefore conventional PID is only adopted to control to be difficult to obtain comparatively satisfied control performance.At present, a lot of scholar proposes many advanced control algorithm strategies for boiler overheating steam temperature control system.But from the actual conditions of power plant, in most circumstances, become when the Mathematical Modeling of steam temperature controlled device is unknown or parameter is, and there is the feature of long time delay and Great inertia, changeless controller parameter is difficult to obtain satisfied control effects, and in fact these parameters need constantly to adjust with the change of operating mode.
Summary of the invention
Goal of the invention of the present invention is to provide a kind of Steam Temperature for Boiler control method based on improved single neuron Adaptive PID Control strategy, utilize mononeuric self-study habit, by on-line tuning controling parameters, to adapt to the change of boiler overheating steam temperature, improve the control characteristic of large time delay, many EVACs, embody stronger robustness and higher stability, there is good Control platform.
To achieve the above object of the invention, the technical solution used in the present invention is: a kind of Steam Temperature for Boiler control method based on improved single neuron Adaptive PID Control strategy, comprises the steps:
1) boiler overheating steam temperature Controlling model is set up: adopt two-stage desuperheating structure, first order attemperator divides left and right to be arranged in low temperature superheater between front screen superheater, on second level attemperator divide left and right to be arranged in steam guiding tube that Late reworking to finishing superheater import connects;
2) attemperation control system, adopts tandem neuron-PID control, wherein,
Inner loop PID controls to combine without supervision Hebb learning rules and has the algorithm of supervision Delta learning rules as follows:
(1)
In formula,
for corresponding to input
weighted value,
for learning rate coefficient, K is neuronic proportionality coefficient, u (k) is controller output, e (k) is systematic error, if r (k) and y (k) represents reference input and the output in k moment respectively, then e (k)=r (k)-y (k).Being input as of neuron PID controller:
(2);
Introduce quadratic performance index function:
(3)
In formula, P, Q are respectively the weighting positive coefficient of output error and controlling increment;
Main ring single neuron self-adaptation PID control algorithm is as follows:
(4)
(5)
Wherein,
,
In formula,
for neuronic weights coefficient,
for the reference value of Intelligent adjustment coefficient,
for adjustment factor,
for learning rate.
Because technique scheme is used, the present invention compared with prior art has following advantages:
1. controller of the present invention makes improvements based on traditional adaptive single neuron controller basis, and being adjusted by three by controling parameters is one, simplifies debug process and control accuracy improves greatly.
2. single neuron PID controller of the present invention, by the learning process of self, on-line tuning controling parameters, can adapt to the working conditions change of overheating steam temperature, solves Superheated Steam Temperature Control System Applied and easily produce the FAQs such as large overshoot, large dead time in practical engineering application.
Accompanying drawing explanation
Fig. 1 is two-stage desuperheating actuator temperature control structure figure of the present invention in embodiment one.
Fig. 2 is the structure chart of improved single neuron Adaptive PID Control algorithm of the present invention in embodiment one.
Fig. 3 is one-level attemperator A side overheating steam temperature cas PID control system diagram in embodiment one.
Fig. 4 is one-level attemperator B side overheating steam temperature cas PID control system diagram in embodiment one.
Fig. 5 is secondary attemperator A side overheating steam temperature cas PID control system diagram in embodiment one.
Fig. 6 is secondary attemperator B side overheating steam temperature cas PID control system diagram in embodiment one.
Fig. 7 is the emulation comparative graph of Traditional PID tandem under random disturbances and neuron algorithm.
Fig. 8 is the emulation comparative graph of Traditional PID tandem under unit step and neuron algorithm.
Fig. 9 is the emulation comparative graph of Traditional PID tandem under characteristics of objects changes and neuron algorithm.
Detailed description of the invention
Below in conjunction with drawings and Examples, the invention will be further described:
Embodiment one: shown in Fig. 1 and 2, a kind of Steam Temperature for Boiler control method based on improved single neuron Adaptive PID Control strategy, comprises the steps:
1) boiler overheating steam temperature Controlling model is set up: adopt two-stage desuperheating structure, first order attemperator divides left and right to be arranged in low temperature superheater between front screen superheater, on second level attemperator divide left and right to be arranged in steam guiding tube that Late reworking to finishing superheater import connects;
2) attemperation control system, adopts tandem neuron-PID control, wherein,
Inner loop PID controls to combine without supervision Hebb learning rules and has the algorithm of supervision Delta learning rules as follows:
(1)
In formula,
for corresponding to input
weighted value,
for learning rate coefficient, K is neuronic proportionality coefficient, u (k) is controller output, e (k) is systematic error, if r (k) and y (k) represents reference input and the output in k moment respectively, then e (k)=r (k)-y (k).Being input as of neuron PID controller:
(2);
Introduce quadratic performance index function:
(3)
In formula, P, Q are respectively the weighting positive coefficient of output error and controlling increment;
Main ring single neuron self-adaptation PID control algorithm is as follows:
(4)
(5)
Wherein,
,
In formula,
for neuronic weights coefficient,
for the reference value of Intelligent adjustment coefficient,
for adjustment factor,
for learning rate.
See shown in Fig. 3 to 6, one-level attemperator A side transfer function model is made to be
, front Folding-Screen A side transfer function model is
, rear screen A side transfer function model is
, secondary attemperator A side transfer function model is
, finishing superheater A side transfer function model is
, one-level attemperator B side transfer function model is
, front Folding-Screen B side transfer function model is
, secondary attemperator B side transfer function model is
, rear screen B side transfer function model is
, finishing superheater B side transfer function model is
.
Shown in Figure 7, the control system quality better of neuron algorithm of the present invention, dynamic property is superior, strong robustness, has good adaptivity.
Shown in Figure 8, the control system quality better of neuron algorithm of the present invention, the overshoot of generation is little, transit time and common pid tandem roughly equal, but the quality of whole process control is more steady.
Shown in Figure 9, the control effects of neuron algorithm of the present invention is steady, and rapidity is relatively good, shows stronger adaptive ability and robustness.
Claims (1)
1., based on a Steam Temperature for Boiler control method for improved single neuron Adaptive PID Control strategy, it is characterized in that, comprise the steps:
1) boiler overheating steam temperature Controlling model is set up: adopt two-stage desuperheating structure, first order attemperator divides left and right to be arranged in low temperature superheater between front screen superheater, on second level attemperator divide left and right to be arranged in steam guiding tube that Late reworking to finishing superheater import connects;
2) attemperation control system, adopts tandem neuron-PID control, wherein,
Inner loop PID controls to combine without supervision Hebb learning rules and has the algorithm of supervision Delta learning rules as follows:
(1)
In formula,
for corresponding to input
weighted value,
for learning rate coefficient, K is neuronic proportionality coefficient, u (k) is controller output, e (k) is systematic error, if r (k) and y (k) represents reference input and the output in k moment respectively, then e (k)=r (k)-y (k), being input as of neuron PID controller:
(2);
Introduce quadratic performance index function:
(3)
In formula, P, Q are respectively the weighting positive coefficient of output error and controlling increment;
Main ring single neuron self-adaptation PID control algorithm is as follows:
(4)
(5)
Wherein,
,
In formula,
for neuronic weights coefficient,
for the reference value of Intelligent adjustment coefficient,
for adjustment factor,
for learning rate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410511914.4A CN104235820A (en) | 2014-09-29 | 2014-09-29 | Boiler steam temperature control method based on improved single neuron adaptive PID (proportion integration differentiation) control strategy |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410511914.4A CN104235820A (en) | 2014-09-29 | 2014-09-29 | Boiler steam temperature control method based on improved single neuron adaptive PID (proportion integration differentiation) control strategy |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104235820A true CN104235820A (en) | 2014-12-24 |
Family
ID=52224420
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410511914.4A Pending CN104235820A (en) | 2014-09-29 | 2014-09-29 | Boiler steam temperature control method based on improved single neuron adaptive PID (proportion integration differentiation) control strategy |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104235820A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108983596A (en) * | 2018-08-08 | 2018-12-11 | 太原理工大学 | ORC system Single Neuron Controller and its control method based on broad sense cross-entropy algorithm |
CN111198498A (en) * | 2020-02-12 | 2020-05-26 | 广东机电职业技术学院 | SiC arc welding power supply control method based on expert system and neuron PID |
CN112506039A (en) * | 2020-11-11 | 2021-03-16 | 珠海格力电器股份有限公司 | Control method and control device for output of electrical equipment and electrical equipment |
CN113641196A (en) * | 2021-08-16 | 2021-11-12 | 何凯 | Application method of SCL (substation configuration language) -language-based single neuron PSD (phase-sensitive detector) algorithm in flash tank pressure control |
CN115963730A (en) * | 2023-03-16 | 2023-04-14 | 广州市景泰科技有限公司 | Selective control method for injection dispensing valve cavity liquid temperature |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4791889A (en) * | 1987-04-02 | 1988-12-20 | The Babcock & Wilcoc Company | Steam temperature control using a modified Smith Predictor |
CN101338892A (en) * | 2008-06-25 | 2009-01-07 | 中国电力科学研究院 | Thermal power unit reheated steam temperature control method |
CN102200272A (en) * | 2011-04-29 | 2011-09-28 | 山西省电力公司电力科学研究院 | Main steam temperature control system for large boiler |
CN103453519A (en) * | 2013-09-26 | 2013-12-18 | 苏州大学 | Configuration design method of switching control system |
-
2014
- 2014-09-29 CN CN201410511914.4A patent/CN104235820A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4791889A (en) * | 1987-04-02 | 1988-12-20 | The Babcock & Wilcoc Company | Steam temperature control using a modified Smith Predictor |
CN101338892A (en) * | 2008-06-25 | 2009-01-07 | 中国电力科学研究院 | Thermal power unit reheated steam temperature control method |
CN102200272A (en) * | 2011-04-29 | 2011-09-28 | 山西省电力公司电力科学研究院 | Main steam temperature control system for large boiler |
CN103453519A (en) * | 2013-09-26 | 2013-12-18 | 苏州大学 | Configuration design method of switching control system |
Non-Patent Citations (1)
Title |
---|
余雷: "基于单神经元自适应PSD控制器的火电厂锅炉过热汽温控制", 《中国优秀硕士学位论文全文数据库》, 28 February 2008 (2008-02-28) * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108983596A (en) * | 2018-08-08 | 2018-12-11 | 太原理工大学 | ORC system Single Neuron Controller and its control method based on broad sense cross-entropy algorithm |
CN111198498A (en) * | 2020-02-12 | 2020-05-26 | 广东机电职业技术学院 | SiC arc welding power supply control method based on expert system and neuron PID |
CN112506039A (en) * | 2020-11-11 | 2021-03-16 | 珠海格力电器股份有限公司 | Control method and control device for output of electrical equipment and electrical equipment |
CN113641196A (en) * | 2021-08-16 | 2021-11-12 | 何凯 | Application method of SCL (substation configuration language) -language-based single neuron PSD (phase-sensitive detector) algorithm in flash tank pressure control |
CN115963730A (en) * | 2023-03-16 | 2023-04-14 | 广州市景泰科技有限公司 | Selective control method for injection dispensing valve cavity liquid temperature |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104235820A (en) | Boiler steam temperature control method based on improved single neuron adaptive PID (proportion integration differentiation) control strategy | |
CN103558757B (en) | Thermoelectricity boiler drum liquid level control method | |
CN102734795B (en) | Self-adapting coal quality change coordinated control method of single-bed circulating fluidized bed without external bed | |
CN101727071A (en) | Concurrent control method of neural network model and quadratic mononeuron PID | |
CN108490790A (en) | A kind of overheating steam temperature active disturbance rejection cascade control method based on multiple-objection optimization | |
CN104102134B (en) | A kind of method realizing reheat steam temperature multivariate predictive coordinated control by performance indications | |
CN104456513B (en) | A kind of thermal power plant Stream temperature estimation optimizing control method | |
CN111637444B (en) | Nuclear power steam generator water level control method based on Q learning | |
CN106154836B (en) | A kind of online dynamic particles group PID optimization method | |
CN101950156A (en) | Adaptive cascade PID control method | |
CN103134046A (en) | Superheated steam temperature two-stage coordination, prediction and control method of thermal power generating unit | |
CN110515304A (en) | Overheating steam temperature PID forecast Control Algorithm based on ARX-Laguerre function model | |
CN110554715A (en) | RBF neural network-based PID control method for hydrolysis process temperature of titanyl sulfate plus seed crystal | |
CN105953207A (en) | High-quality steam temperature control system for power station boiler | |
US20120310375A1 (en) | A nonlinear intelligent pulse-controller | |
CN113835342A (en) | Disturbance rejection prediction control method of superheated steam temperature system | |
CN109062030A (en) | Thermal power unit plant load prediction PID control method based on laguerre function model | |
CN111102559B (en) | Screen type superheater steam temperature control method based on double neural network inverse model | |
CN103453519A (en) | Configuration design method of switching control system | |
CN114428455A (en) | Control method and device of thermal power generating unit control system | |
JP3012716B2 (en) | Process control method and its control device | |
CN108919642B (en) | Optimal setting method for controller parameters of furnace-following machine coordination control system | |
CN106287659A (en) | Reheat steam temperature degree control method and device | |
CN115808876A (en) | Self-adaptive control method and device for engine tail jet pipe actuating mechanism | |
CN104566352A (en) | Circulating fluidized bed boiler primary air fan control method and system adopting instruction regulator |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20141224 |
|
RJ01 | Rejection of invention patent application after publication |