CN107783423A - Pid parameter automatic setting method and its device based on machine learning - Google Patents
Pid parameter automatic setting method and its device based on machine learning Download PDFInfo
- Publication number
- CN107783423A CN107783423A CN201711007862.7A CN201711007862A CN107783423A CN 107783423 A CN107783423 A CN 107783423A CN 201711007862 A CN201711007862 A CN 201711007862A CN 107783423 A CN107783423 A CN 107783423A
- Authority
- CN
- China
- Prior art keywords
- pid
- parameter
- control parameter
- pid control
- machine learning
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000010801 machine learning Methods 0.000 title claims abstract description 29
- 230000000694 effects Effects 0.000 claims abstract description 33
- 230000007613 environmental effect Effects 0.000 claims abstract description 22
- 230000008569 process Effects 0.000 claims description 14
- 230000010354 integration Effects 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 claims description 7
- 241000208340 Araliaceae Species 0.000 claims description 6
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 6
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 6
- 235000008434 ginseng Nutrition 0.000 claims description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 5
- 230000003321 amplification Effects 0.000 claims description 3
- 230000001174 ascending effect Effects 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 abstract description 9
- 230000010355 oscillation Effects 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 238000004378 air conditioning Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 230000001052 transient effect Effects 0.000 description 3
- 230000004069 differentiation Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001704 evaporation Methods 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 238000005057 refrigeration Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000005494 condensation Effects 0.000 description 1
- 238000009833 condensation Methods 0.000 description 1
- 230000001143 conditioned effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25B—REFRIGERATION MACHINES, PLANTS OR SYSTEMS; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS
- F25B41/00—Fluid-circulation arrangements
- F25B41/30—Expansion means; Dispositions thereof
- F25B41/31—Expansion valves
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B11/00—Automatic controllers
- G05B11/01—Automatic controllers electric
- G05B11/36—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential
- G05B11/42—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential for obtaining a characteristic which is both proportional and time-dependent, e.g. P. I., P. I. D.
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25B—REFRIGERATION MACHINES, PLANTS OR SYSTEMS; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS
- F25B2600/00—Control issues
- F25B2600/25—Control of valves
- F25B2600/2513—Expansion valves
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Automation & Control Theory (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Mechanical Engineering (AREA)
- Thermal Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a kind of pid parameter automatic setting method and its device based on machine learning.Methods described constantly carries out machine learning by equipment, automatically the pid control parameter of electric expansion valve is adjusted, and adjust a set of control parameter respectively under different environmental patterns, realize Auto-matching optimization control parameter under various circumstances, remain optimal operational condition.The parameter includes:The parameters under current environment pattern are detected, are matched from historical data, obtain pid control parameter optimal under the environmental pattern in historical data;Run according to the pid control parameter of acquisition, by judging the quality of control effect, Self-tuning System is carried out, electric expansion valve is run under optimal control effect, the present invention realizes the automatic adjusting of pid control parameter by machine learning, mitigates the workload of commissioning staff significantly;Electric expansion valve Auto-matching optimization control parameter under various circumstances is realized by machine learning, remains optimal operational condition.
Description
Technical field
The present invention relates to household appliances field, more particularly to a kind of pid parameter automatic setting method based on machine learning and
Its device.
Background technology
Electric expansion valve controls the voltage or electric current put on expansion valve using electric signal caused by parameter is conditioned,
And then the purpose of regulation liquid supply rate.Stepless variable capacitance amount refrigeration system refrigeration liquid supply rate adjustable range is wide, it is desirable to regulation reaction
It hurry up, traditional throttling arrangement(Such as heating power expansion valve)It is difficult to well be competent at, and electric expansion valve can meet to require well.
It is in existing air-conditioning system to use electric expansion valve as throttling arrangement more, in order to provide control accuracy and response speed
Degree, PID control(Proportion Integration Differentiation. proportional integral differential controls)Method is in electricity
Application on sub- expansion valve is also more and more ripe.
But the maximum difficult point of PID control be pid parameter adjust, it is necessary to veteran personnel spend a lot of time into
Row engineering test and arameter optimization, and also need to consider different operating modes, difference when selection determines optimal control parameter
The influence of workplace, it is not always all in optimized operation state among real work.
Therefore, a kind of automatic adjusting pid control parameter is designed, it is urgently to solve in the industry control effect is reached optimal method
Technical problem certainly, this method can automatic adjusting pid control parameter, spend a lot of time carry out work without veteran personnel
Journey is tested and arameter optimization.
The content of the invention
The purpose of the present invention is in view of the above-mentioned drawbacks of the prior art, providing a kind of PID ginsengs based on machine learning
Number automatic setting method and its device.
The technical solution adopted by the present invention is to design a kind of pid parameter automatic setting method based on machine learning, this method
Machine learning is constantly carried out by equipment, pid control parameter adjusted automatically, and under different environmental patterns respectively
A set of control parameter is adjusted, Auto-matching optimization control parameter under various circumstances is realized, remains optimal operational condition, institute
The method of stating includes:
The parameters under current environment pattern are detected, is contrasted with the environmental pattern in historical data, obtains the environment mould
The pid control parameter run under formula;
Run under the pid control parameter of acquisition, by the quality of the set pid control parameter control effect, to pid control parameter
Adjusted, control effect is reached optimal.
Preferably, methods described specifically includes:
Parameters under step 1, detection current environment pattern, are matched with the environmental pattern in historical data, if
With success, into step 2, if matching is unsuccessful, into step 3;
Step 2, obtain pid control parameter optimal under the environmental pattern in historical data;
Step 3, acquisition set optimal pid control parameter before dispatching from the factory;
Step 4, the pid control parameter operation according to acquisition, if run under the pid control parameter, its control effect is optimal,
Then run according to the pid control parameter, if running its control effect and non-optimal under the pid control parameter, enter step
Rapid 5;
Step 5, pid control parameter is adjusted, electric expansion valve is run under optimal control effect.
Preferably, the environmental pattern in the step 1 includes preset mode and self-defined pattern, in matching, first to certainly
Defining mode is matched, if can not match, preset mode is matched.
Preferably, when the step 1 is matched from historical data, progress first in the historical data of slave unit local
Match somebody with somebody;If can not be matched in local historical data, matched from the historical data of high in the clouds.
Preferably, the preset mode is by operation phase, compressor load section, environment temperature section, leaving water temperature area
Between, the parameters of degree of superheat set interval are combined and form;The self-defined pattern is on the basis of preset mode, increase
New parameter combination forms.
Preferably, when adjusting proportionally COEFFICIENT K p, time of integration Ti and differential of pid control parameter in the step 5
Between Td order adjusted.
Preferably, the scope control of the Proportional coefficient K p is between 1-5, and each regulation excursion is according to 0.1
Amplification is adjusted from small to large;The time of integration Ti is adjusted from big to small according to T multiple;The derivative time Td
It is adjusted according to T multiple is ascending.
Preferably for the effect adjusted every time, optimal PID control is joined corresponding to renewal if than that will get well in history
Number, does not otherwise update, and until the control effect of the set pid control parameter is optimal, is no longer adjusted and is updated.
Preferably, degree of superheat change and electronic expansion valve opening change and the degree of superheat are passed through in the step 4 and step 5
The curve that setting value is formed judges the quality of control effect;Using attenuation curve method and aritical ratio curve method as judge according to
According to.
The invention also provides a kind of pid parameter Self-tuning System device based on machine learning, described device includes:
Electric expansion valve;
PID controller, it is connected with the electric expansion valve, for detecting each seed ginseng under electric expansion valve working environment pattern
Number;It is connected with cloud server, the parameter of detection is matched in the historical data, obtains in historical data under the parameter
Optimal pid control parameter, the pid control parameter is run, and the control by judging to run under the pid control parameter is imitated
Whether fruit optimal, and pid control parameter is adjusted, meanwhile, by tuning process be better than historical data in control effect should
Set pid control parameter is updated;
Data transmission module, it is connected with PID controller, for the data interaction between cloud server and PID controller;With
And cloud server, and data transmission module wireless connection, for the storage of historical data and the renewal of new data.
Compared with prior art, the present invention at least has the advantages that:The present invention realizes that PID is controlled by machine learning
The automatic adjusting of parameter processed, mitigate the workload of commissioning staff significantly;Realize electric expansion valve in different rings by machine learning
Auto-matching optimization control parameter under border, remains optimal operational condition.
Brief description of the drawings
Fig. 1 is the flow chart of pid parameter automatic setting method of the present invention;
Fig. 2 is the classification chart of environmental pattern of the present invention;
Fig. 3 is the chart of aritical ratio curve method of the present invention;
Fig. 4 is the chart of attenuation curve method of the present invention;
Fig. 5 is the block diagram of pid parameter Self-tuning System device of the present invention.
Embodiment
The present invention will be further described with reference to the accompanying drawings and examples.
As shown in figure 1, the invention discloses a kind of pid parameter automatic setting method based on machine learning, this method passes through
Equipment constantly carries out machine learning, and pid control parameter is adjusted automatically, and is adjusted respectively under different environmental patterns
A set of control parameter, Auto-matching optimization control parameter under various circumstances is realized, remains optimal operational condition, the side
Method includes:
The parameters under current environment pattern are detected, is contrasted with the environmental pattern in historical data, obtains the environment mould
The pid control parameter run under formula;
Run under the pid control parameter of acquisition, by the quality of the set pid control parameter control effect, to pid control parameter
Adjusted, control effect is reached optimal.
Preferably, methods described specifically includes:
Parameters under step 1, detection current environment pattern, are matched with the environmental pattern in historical data, if
With success, into step 2, if matching is unsuccessful, into step 3;
Step 2, obtain pid control parameter optimal under the environmental pattern in historical data;
Step 3, acquisition set optimal pid control parameter before dispatching from the factory;
Step 4, the pid control parameter operation according to acquisition, if run under the pid control parameter, its control effect is optimal,
Then run according to the pid control parameter, if running its control effect and non-optimal under the pid control parameter, enter step
Rapid 5;
Step 5, pid control parameter is adjusted, electric expansion valve is run under optimal control effect.
Current closed-loop automatic control technology is all based on the concept of feedback to reduce uncertainty.The key element of feedback theory
Including three parts:Measure, compare and perform.The actual value of crucially controlled variable is measured, compared with desired value, uses this
Individual deviation carrys out the response of correcting system, performs adjustment control.In engineering in practice, the adjuster control law being most widely used
For ratio, integration, differential control, the regulation of abbreviation PID control, also known as PID.
PID controller is a common backfeed loop part in Industry Control Application, single by proportional unit P, integration
First I and differentiation element D compositions.The basis of PID control is ratio control;Integration control can eliminate steady-state error, but may increase
Overshoot;Differential control can accelerate Great inertia system response speed and weaken overshoot trend.
This it is theoretical and application it is crucial that make correctly measurement and relatively after, how could preferably correcting system.
PID controller is currently still most widely used as the existing last 100 yearses history of PID controller practical earliest
Industrial PID controller.PID controller is easily understood, and the prerequisites such as accurate system model are not required in use, thus is turned into
The PID controller being most widely used.
Specifically, the present invention constantly carries out machine learning, automatically using user's air-conditioning as huge laboratory by equipment
The pid control parameter of electric expansion valve is adjusted, and adjusts a set of control parameter respectively under different environmental patterns,
Auto-matching optimization control parameter under various circumstances is realized, remains optimal operational condition.
Shown in reference picture 2, the environmental pattern in the step 1 includes preset mode and self-defined pattern, in matching, first
Self-defined pattern is matched, if can not match, preset mode matched.
In the present embodiment, when the step 1 is matched from historical data, first in the historical data of slave unit local
Matched;If can not be matched in local historical data, matched from the historical data of high in the clouds.
In the present embodiment, the preset mode is by operation phase, compressor load section, environment temperature section, water outlet
Temperature range, the parameters of degree of superheat set interval are combined and formed;The self-defined pattern is on the basis of preset mode
On, increase new parameter combination and form.
Operation phase includes:Start process, running and shutdown process;Compressor load section is 10%-100%, one
As every 1% be separated into a section;Environment temperature is typically separated into a section every 2 degrees Celsius;Leaving water temperature typically every
3 degrees Celsius are separated into a section;Degree of superheat setting is typically separated into a section every 4 degrees Celsius.
Specifically, the pattern of preset mode is equipment when dispatching from the factory factory settings, the pattern of factory settings is according to a large amount of special
A set of more standard of the formation such as family's opinion, has the pattern of theoretical foundation, in practical operation, user can also be according to oneself
Experience or set a kind of self-defined pattern on its basis, self-defined pattern can increase by one on the basis of preset mode
A little parameters.
When being matched with the environmental pattern in historical data, if user increases by one on the basis of preset mode
A little parameters, form a kind of new self-defined pattern, then preferentially enter self-defined pattern and the environmental pattern in historical data
Row matching, if self-defined pattern can not match with the environmental pattern in historical data, then by preset mode and historical data
In environmental pattern matched.Matching when, it is necessary to pay attention to, first we local database in matched, such as
There is no matching self-defined pattern in fruit local data base, then, we again with cloud server data carry out
Match somebody with somebody.
In the present embodiment, in the step 5 pid control parameter adjust proportionally COEFFICIENT K p, time of integration Ti and
Derivative time Td order is adjusted.
In the present embodiment, the scope control of the Proportional coefficient K p is between 1-5, each regulation excursion according to
0.1 amplification is adjusted from small to large;The time of integration Ti is adjusted from big to small according to T multiple;The differential
Time Td ascending is adjusted according to T multiple.
In the present embodiment, for the effect adjusted every time if than in history will well if optimal PID corresponding to renewal
Control parameter, otherwise do not update, until the control effect of the set pid control parameter is optimal, is no longer adjusted and updated.
In the present embodiment, in the step 4 and step 5 by the degree of superheat change with electronic expansion valve opening change and
The curve that degree of superheat setting value is formed judges the quality of control effect;Using attenuation curve method and aritical ratio curve method as sentencing
Disconnected foundation.
Specifically, compressor, condenser, electric expansion valve, evaporation are possessed using the air-conditioning equipment of electronic expansion valve controls
The parts such as device, blower fan, and electronic expansion valve opening OD, compressor load CC, suction temperature Ts, pressure of inspiration(Pi) can be gathered
The parameters such as Pe, delivery temperature Td, pressure at expulsion Pc, environment temperature Tenv, leaving water temperature Tw, degree of superheat setting value SS and control are set
The controller of received shipment row, also possess the data transmission module of data acquisition and remote monitoring.
Controller can converse evaporating temperature Te and condensation temperature Tc by pressure of inspiration(Pi) Pe and pressure at expulsion Pc, then inhale
Suction superheat control may be selected in gas degree of superheat dTs=Ts-Te, discharge superheat dTd=Td-Tc, herein, user or commissioning staff
System or discharge superheat control, are referred to as degree of superheat SH controls here.
The then degree of superheat(SH)Deviation=degree of superheat measured value-degree of superheat setting value, at k-th of sampling period, control
The aperture variable quantity of electric expansion valve processed is(Unit:%):
Wherein:Kp is proportionality coefficient, and Ti is integration time constant, and Td is derivative time constant, and T is the sampling period, and δ=1/Kp is
Proportional band.(Sampling period T Consideration is more, can be dispatched from the factory and be set by equipment)
Integral coefficient,Differential coefficient.
When control effect judges, changed by degree of superheat change with electronic expansion valve opening whether to judge control effect
In optimal, if it is not, then by adjusting pid control parameter, to change the degree of superheat and electronic expansion valve opening, control is realized
Best results.
Lower PID control ginseng is specifically described below according to critical proportionality range parameter tuning method and attenuation curve parameter tuning method
Number regulation process.
Shown in reference picture 3, its elder generation of critical proportionality range parameter tuning method under simple proportional action (P), by proportional gain by
Step increase (also progressively reduces proportional band), untill self-sustained oscillation occurs in controlled variable.Proportional band now is referred to as facing
Boundary's proportional band, cycle of oscillation are referred to as critical period.Then according to certain formula, calculated by critical proportionality range and critical period
The proportional gain (or proportional band) that should be chosen using f, during PI or F'ILl control algolithms, the again ginseng between timing between the timing of top
Numerical value.
Its operating method is as follows:
A, the time of integration TI of adjuster is placed in maximum(TI=∞), derivative time zero setting(TD=0), proportional band δ is appropriate, balance
Operation a period of time, system is put into automatic running;
B, proportional band δ is gradually reduced, obtains self-sustained oscillation process, write down critical proportionality range δ k and critical period of the oscillation Tk values;
C, according to δ k and Tk values, using empirical equation, the value of adjuster parameters, i.e. δ, TI, TD is calculated;
D, by " adjustment variable of regulator is transferred on calculated value by the last D " of I operation sequence after first P., can be again if satisfied not enough
Further adjustment.
Shown in reference picture 4, attenuation curve parameter tuning method(controller tuning based n attenua-ring
eurvc)One kind of attitude conirol method.First in simple proportional action(P)Lower adjustment proportional gain Kr, makes defeated in step
Attenuation curve form as defined in transient process presentation under people, it is typically to make the ratio between two neighboring cyclic curve amplitude be 4:1 or
LU:1 decay, and measure the cycle of oscillation of transient process only.Then according to certain formula, by the K measured:Calculated with upper value
Using P } PI or P I17 control algolithms when should choose proportional gain, again between timing and rate time parameter value two.
It is descending to adjust proportional band to obtain with attenuation ratio in the case where going out proportional action during its concrete operations(4:1)'s
Transient process, write down proportional band δ s and cycle of oscillation Ts now, rule of thumb formula, obtain corresponding time of integration TI and
TD。
It should be noted that its reaction of attenuation curve method is very fast, 4 are assert:1 attenuation curve and reading Ts are relatively difficult,
Now, usable record, which swings back and forth just to reach to stablize twice, is used as 4:1 attenuation process;In process of production, load variations can shadow
Process characteristic is rung, when load variations change greatly, it is necessary to tuning Regulator parameter value again;If 4:1 decay is too slow, preferably answers
With 10:1 attenuation process.For 10:The step of 1 attenuation curve tuning Regulator parameter with above-mentioned identical, only with meter
It is somewhat different to calculate formula.
As shown in figure 5, the present invention also proposes a kind of pid parameter Self-tuning System device based on machine learning, described device bag
Include:
Electric expansion valve;
PID controller, it is connected with the electric expansion valve, for detecting each seed ginseng under electric expansion valve working environment pattern
Number;It is connected with cloud server, the parameter of detection is matched in the historical data, in acquisition historical data under the parameter most
Good pid control parameter, run the pid control parameter, and the control effect by judging to run under the pid control parameter
It is whether optimal, pid control parameter is adjusted, meanwhile, the set of control effect in historical data will be better than in tuning process
Pid control parameter is updated;
Data transmission module, it is connected with PID controller, for the data interaction between cloud server and PID controller;With
And cloud server, and data transmission module wireless connection, for the storage of historical data and the renewal of new data.
In summary, the present invention realizes the automatic adjusting of pid control parameter by machine learning, mitigates commissioning staff significantly
Workload;Electric expansion valve Auto-matching optimization control parameter under various circumstances is realized by machine learning, remained
Optimal operational condition.
Above-described embodiment is merely to illustrate the embodiment of the present invention.It should be pointed out that for the general of this area
For logical technical staff, without departing from the inventive concept of the premise, some deformations and change can also be made, these deformations and
Change should all belong to protection scope of the present invention.
Claims (10)
1. a kind of pid parameter automatic setting method based on machine learning, it is characterised in that methods described includes:
The parameters under current environment pattern are detected, is contrasted with the environmental pattern in historical data, obtains the environment mould
The pid control parameter run under formula;
Run under the pid control parameter of acquisition, by the quality of the set pid control parameter control effect, to pid control parameter
Adjusted, control effect is reached optimal.
2. the pid parameter automatic setting method according to claim 1 based on machine learning, it is characterised in that methods described
Specifically include:
Parameters under step 1, detection current environment pattern, are matched with the environmental pattern in historical data, if
With success, into step 2, if matching is unsuccessful, into step 3;
Step 2, obtain pid control parameter optimal under the environmental pattern in historical data;
Step 3, acquisition set optimal pid control parameter before dispatching from the factory;
Step 4, the pid control parameter operation according to acquisition, if run under the pid control parameter, its control effect is optimal,
Then run according to the pid control parameter, if running its control effect and non-optimal under the pid control parameter, enter step
Rapid 5;
Step 5, pid control parameter is adjusted, electric expansion valve is run under optimal control effect.
3. the pid parameter automatic setting method according to claim 2 based on machine learning, it is characterised in that the step 1
In environmental pattern include preset mode and self-defined pattern, matching when, first self-defined pattern is matched, if can not
Matching, then match to preset mode.
4. the pid parameter automatic setting method according to claim 3 based on machine learning, it is characterised in that the step 1
When being matched from historical data, matched first in the historical data of slave unit local;If in local historical data
It can not match, then be matched from the historical data of high in the clouds.
5. the pid parameter automatic setting method according to claim 4 based on machine learning, it is characterised in that described default
Pattern by the operation phase, compressor load section, environment temperature section, leaving water temperature section, degree of superheat set interval items
Parameter, which is combined, to be formed;The self-defined pattern increases new parameter combination and formed on the basis of preset mode.
6. the pid parameter automatic setting method according to claim 5 based on machine learning, it is characterised in that the step 5
The order for adjusting proportionally COEFFICIENT K p, time of integration Ti and derivative time Td of middle pid control parameter is adjusted.
7. the pid parameter automatic setting method according to claim 6 based on machine learning, it is characterised in that the ratio
Between 1-5, each regulation excursion is adjusted COEFFICIENT K p scope control from small to large according to 0.1 amplification;Institute
Time of integration Ti is stated to be adjusted from big to small according to T multiple;The derivative time Td according to T the ascending progress of multiple
Regulation.
8. the pid parameter automatic setting method according to claim 7 based on machine learning, it is characterised in that for each
The effect adjusted optimal pid control parameter corresponding to renewal if than that will get well in history, does not otherwise update, until the set
The control effect of pid control parameter is optimal, and is no longer adjusted and is updated.
9. the pid parameter automatic setting method according to claim 8 based on machine learning, it is characterised in that the step 4
Judge to control with the curve formed with electronic expansion valve opening change and degree of superheat setting value by degree of superheat change in step 5
The quality of effect;Basis for estimation is used as using attenuation curve method and aritical ratio curve method.
10. a kind of pid parameter Self-tuning System device based on machine learning, it is characterised in that described device includes:
Electric expansion valve;
PID controller, it is connected with the electric expansion valve, for detecting each seed ginseng under electric expansion valve working environment pattern
Number;It is connected with cloud server, the parameter of detection is matched in the historical data, obtains in historical data under the parameter
Optimal pid control parameter, the pid control parameter is run, and the control by judging to run under the pid control parameter is imitated
Whether fruit optimal, and pid control parameter is adjusted, meanwhile, by tuning process be better than historical data in control effect should
Set pid control parameter is updated;
Data transmission module, it is connected with PID controller, for the data interaction between cloud server and PID controller;With
And cloud server, and data transmission module wireless connection, for the storage of historical data and the renewal of new data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711007862.7A CN107783423B (en) | 2017-10-25 | 2017-10-25 | PID parameter self-tuning method and device based on machine learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711007862.7A CN107783423B (en) | 2017-10-25 | 2017-10-25 | PID parameter self-tuning method and device based on machine learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107783423A true CN107783423A (en) | 2018-03-09 |
CN107783423B CN107783423B (en) | 2020-03-27 |
Family
ID=61435232
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711007862.7A Active CN107783423B (en) | 2017-10-25 | 2017-10-25 | PID parameter self-tuning method and device based on machine learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107783423B (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111684367A (en) * | 2018-03-12 | 2020-09-18 | 欧姆龙株式会社 | Control device, control system, control method, and control program |
CN112286044A (en) * | 2020-10-14 | 2021-01-29 | 珠海格力电器股份有限公司 | PID parameter optimization method and device and related equipment |
CN112353549A (en) * | 2020-10-14 | 2021-02-12 | 深圳中科大唐科技有限公司 | Device and method for improving sleep breathing |
CN112413937A (en) * | 2020-11-23 | 2021-02-26 | 珠海格力电器股份有限公司 | Water chilling unit and electronic expansion valve control method, device and system thereof |
CN112413953A (en) * | 2020-11-17 | 2021-02-26 | 广东芬尼克兹节能设备有限公司 | Electronic expansion valve control method and device of carbon dioxide heat pump |
CN113093521A (en) * | 2021-03-19 | 2021-07-09 | 江苏固德威电源科技股份有限公司 | Dynamic PID control method and dynamic PID controller |
CN113285595A (en) * | 2021-06-09 | 2021-08-20 | 珠海市一微半导体有限公司 | PID parameter setting system and control method of digital power supply based on machine learning |
CN113739389A (en) * | 2021-08-02 | 2021-12-03 | 广东申菱环境系统股份有限公司 | Method and system for setting air conditioner scene mode |
CN113805477A (en) * | 2020-06-12 | 2021-12-17 | 中国石油天然气股份有限公司 | PID (proportion integration differentiation) setting method and device for oil and gas pipeline pressure regulating equipment |
CN114063436A (en) * | 2021-10-09 | 2022-02-18 | 广州大学 | Anti-interference control method, system, equipment and medium for water-surface robot |
CN114237172A (en) * | 2021-11-30 | 2022-03-25 | 浙江大学衢州研究院 | Self-optimization controlled variable selection method and device based on machine learning |
CN114719469A (en) * | 2022-03-24 | 2022-07-08 | 浙江中广电器集团股份有限公司 | Electronic expansion valve opening degree self-adaptive adjusting method based on exhaust temperature control |
CN115186582A (en) * | 2022-07-05 | 2022-10-14 | 科大智能物联技术股份有限公司 | Steel rolling heating furnace control method based on machine learning model |
CN115598967A (en) * | 2022-11-01 | 2023-01-13 | 南栖仙策(南京)科技有限公司(Cn) | Parameter setting model training method, parameter determining method, device, equipment and medium |
US11860589B2 (en) | 2021-01-05 | 2024-01-02 | Honeywell International Inc. | Method and apparatus for tuning a regulatory controller |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS60163101A (en) * | 1984-02-03 | 1985-08-26 | Nissin Electric Co Ltd | Process controller |
CN101930215A (en) * | 2009-06-22 | 2010-12-29 | 费希尔-罗斯蒙特系统公司 | Adaptive controller based on the model parameter of continuous scheduling |
CN102621883A (en) * | 2012-04-01 | 2012-08-01 | 广东电网公司电力科学研究院 | PID (proportion integration differentiation) parameter turning method and PID parameter turning system |
CN102829590A (en) * | 2011-06-17 | 2012-12-19 | 株式会社鹭宫制作所 | Control device of electronic expansion valve |
CN103576553A (en) * | 2013-11-06 | 2014-02-12 | 华北电力大学(保定) | Fractional-order self-adjusting control method for steam temperature of coal-fired boiler |
CN104038139A (en) * | 2014-05-20 | 2014-09-10 | 珠海格力电器股份有限公司 | PG motor control method, system and air conditioner |
CN104633863A (en) * | 2015-02-04 | 2015-05-20 | 无锡市同舟电子实业有限公司 | Central air conditioner control method based on self-tuning discrete PID algorithm |
CN105404149A (en) * | 2015-11-27 | 2016-03-16 | 本钢板材股份有限公司 | Multi-model LF furnace electrode adjusting method based on steel type clearance slag thickness |
CN106325076A (en) * | 2016-11-22 | 2017-01-11 | 东华大学 | Immune optimization innovation control method in stretch ring of production process of polyester staple fiber |
CN107014028A (en) * | 2016-01-28 | 2017-08-04 | 珠海格力电器股份有限公司 | Freeze the control method of water valve |
-
2017
- 2017-10-25 CN CN201711007862.7A patent/CN107783423B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS60163101A (en) * | 1984-02-03 | 1985-08-26 | Nissin Electric Co Ltd | Process controller |
CN101930215A (en) * | 2009-06-22 | 2010-12-29 | 费希尔-罗斯蒙特系统公司 | Adaptive controller based on the model parameter of continuous scheduling |
CN102829590A (en) * | 2011-06-17 | 2012-12-19 | 株式会社鹭宫制作所 | Control device of electronic expansion valve |
CN102621883A (en) * | 2012-04-01 | 2012-08-01 | 广东电网公司电力科学研究院 | PID (proportion integration differentiation) parameter turning method and PID parameter turning system |
CN103576553A (en) * | 2013-11-06 | 2014-02-12 | 华北电力大学(保定) | Fractional-order self-adjusting control method for steam temperature of coal-fired boiler |
CN104038139A (en) * | 2014-05-20 | 2014-09-10 | 珠海格力电器股份有限公司 | PG motor control method, system and air conditioner |
CN104633863A (en) * | 2015-02-04 | 2015-05-20 | 无锡市同舟电子实业有限公司 | Central air conditioner control method based on self-tuning discrete PID algorithm |
CN105404149A (en) * | 2015-11-27 | 2016-03-16 | 本钢板材股份有限公司 | Multi-model LF furnace electrode adjusting method based on steel type clearance slag thickness |
CN107014028A (en) * | 2016-01-28 | 2017-08-04 | 珠海格力电器股份有限公司 | Freeze the control method of water valve |
CN106325076A (en) * | 2016-11-22 | 2017-01-11 | 东华大学 | Immune optimization innovation control method in stretch ring of production process of polyester staple fiber |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11892819B2 (en) | 2018-03-12 | 2024-02-06 | Omron Corporation | Control device, control system, control method, and computer-readable storage medium |
CN111684367A (en) * | 2018-03-12 | 2020-09-18 | 欧姆龙株式会社 | Control device, control system, control method, and control program |
CN111684367B (en) * | 2018-03-12 | 2023-01-17 | 欧姆龙株式会社 | Control device, control system, control method, and computer-readable storage medium |
CN113805477B (en) * | 2020-06-12 | 2024-05-28 | 中国石油天然气股份有限公司 | PID setting method and device for oil and gas pipeline pressure regulating equipment |
CN113805477A (en) * | 2020-06-12 | 2021-12-17 | 中国石油天然气股份有限公司 | PID (proportion integration differentiation) setting method and device for oil and gas pipeline pressure regulating equipment |
CN112286044A (en) * | 2020-10-14 | 2021-01-29 | 珠海格力电器股份有限公司 | PID parameter optimization method and device and related equipment |
CN112353549A (en) * | 2020-10-14 | 2021-02-12 | 深圳中科大唐科技有限公司 | Device and method for improving sleep breathing |
CN112413953A (en) * | 2020-11-17 | 2021-02-26 | 广东芬尼克兹节能设备有限公司 | Electronic expansion valve control method and device of carbon dioxide heat pump |
CN112413953B (en) * | 2020-11-17 | 2022-05-27 | 广东芬尼克兹节能设备有限公司 | Electronic expansion valve control method and device of carbon dioxide heat pump |
CN112413937A (en) * | 2020-11-23 | 2021-02-26 | 珠海格力电器股份有限公司 | Water chilling unit and electronic expansion valve control method, device and system thereof |
CN112413937B (en) * | 2020-11-23 | 2022-05-31 | 珠海格力电器股份有限公司 | Water chilling unit and electronic expansion valve control method, device and system thereof |
US11860589B2 (en) | 2021-01-05 | 2024-01-02 | Honeywell International Inc. | Method and apparatus for tuning a regulatory controller |
CN113093521A (en) * | 2021-03-19 | 2021-07-09 | 江苏固德威电源科技股份有限公司 | Dynamic PID control method and dynamic PID controller |
CN113285595A (en) * | 2021-06-09 | 2021-08-20 | 珠海市一微半导体有限公司 | PID parameter setting system and control method of digital power supply based on machine learning |
CN113739389B (en) * | 2021-08-02 | 2022-09-30 | 广东申菱环境系统股份有限公司 | Method and system for setting air conditioner scene mode |
CN113739389A (en) * | 2021-08-02 | 2021-12-03 | 广东申菱环境系统股份有限公司 | Method and system for setting air conditioner scene mode |
CN114063436B (en) * | 2021-10-09 | 2023-09-26 | 广州大学 | Anti-interference control method, system, equipment and medium for water surface robot |
CN114063436A (en) * | 2021-10-09 | 2022-02-18 | 广州大学 | Anti-interference control method, system, equipment and medium for water-surface robot |
CN114237172A (en) * | 2021-11-30 | 2022-03-25 | 浙江大学衢州研究院 | Self-optimization controlled variable selection method and device based on machine learning |
CN114719469A (en) * | 2022-03-24 | 2022-07-08 | 浙江中广电器集团股份有限公司 | Electronic expansion valve opening degree self-adaptive adjusting method based on exhaust temperature control |
CN114719469B (en) * | 2022-03-24 | 2024-05-17 | 浙江中广电器集团股份有限公司 | Electronic expansion valve opening self-adaptive adjusting method based on exhaust temperature control |
CN115186582A (en) * | 2022-07-05 | 2022-10-14 | 科大智能物联技术股份有限公司 | Steel rolling heating furnace control method based on machine learning model |
CN115598967A (en) * | 2022-11-01 | 2023-01-13 | 南栖仙策(南京)科技有限公司(Cn) | Parameter setting model training method, parameter determining method, device, equipment and medium |
CN115598967B (en) * | 2022-11-01 | 2023-12-08 | 南栖仙策(南京)高新技术有限公司 | Parameter setting model training, parameter determining method, device, equipment and medium |
Also Published As
Publication number | Publication date |
---|---|
CN107783423B (en) | 2020-03-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107783423A (en) | Pid parameter automatic setting method and its device based on machine learning | |
CN101526260B (en) | Variable-frequency air-conditioner control method and control device thereof | |
CN102207320B (en) | Control method of minimum opening of air conditioning expansion valves and air conditioning expansion valves | |
CN108397853B (en) | Air-conditioner set control method and device | |
DK2985563T3 (en) | Apparatus for controlling a cooling system | |
US20190137952A1 (en) | Self-configuring extremum-seeking control system | |
CN106575102B (en) | Adaptive PID Control for industrial turbines | |
CN106440440B (en) | The hot-gas bypass control method and system of screw unit | |
CN104930773B (en) | The control method and device and air-conditioner of electric expansion valve | |
CN104603699A (en) | Temperature administration system | |
CN102032640A (en) | Fuzzy proportion integration differentiation (PID) control method and device for industrial environment high-precision air conditioner | |
CN105241029A (en) | Operation control method for radiation air conditioner | |
US20130186119A1 (en) | Adaptive Control of Vapor Compression System | |
CN106123234B (en) | A method of adjusting outdoor machine of air-conditioner electronic expansion valve | |
CN106227276A (en) | High-and-low temperature humid heat test box temperature accuracy-control system and method | |
US9568897B2 (en) | Controller system for variable parameter and related program product | |
CN101672509A (en) | Air-conditioning control technique with variable air quantity based on enthalpy value control | |
CN103925668A (en) | Direct-current frequency conversion constant-temperature and humidity set achieving condensation heat recovery and heat and humidity separation control method | |
KR20090010888A (en) | Air conditioning control device and air conditioning control method | |
CN108508870A (en) | A kind of method of Drum Water Level Control System for Boiler Performance Evaluation and parameter optimization | |
Li et al. | Model parameter identification of indoor temperature lag characteristic based on hysteresis relay feedback control in VAV systems | |
CN102230466A (en) | System and method for optimally controlling air compressor load | |
CN106871332A (en) | One drag two detachable air conditioner control method and one drag two detachable air conditioner | |
Gurban et al. | Comparison study of PID controller tuning for greenhouse climate with feedback-feedforward linearization and decoupling | |
JP2015102096A (en) | Automated commissioning of gas turbine combustion control system |
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 |