CN117518771A - Automatic switching method based on generalized predictive control - Google Patents
Automatic switching method based on generalized predictive control Download PDFInfo
- Publication number
- CN117518771A CN117518771A CN202311678944.XA CN202311678944A CN117518771A CN 117518771 A CN117518771 A CN 117518771A CN 202311678944 A CN202311678944 A CN 202311678944A CN 117518771 A CN117518771 A CN 117518771A
- Authority
- CN
- China
- Prior art keywords
- data
- control
- switching
- prediction
- factors
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012545 processing Methods 0.000 claims description 16
- 230000008859 change Effects 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000005259 measurement Methods 0.000 claims description 12
- 238000002474 experimental method Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 abstract description 7
- 238000004519 manufacturing process Methods 0.000 abstract description 3
- 230000006872 improvement Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 3
- 230000001276 controlling effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001105 regulatory effect Effects 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
- G05B7/00—Arrangements for obtaining smooth engagement or disengagement of automatic control
- G05B7/02—Arrangements for obtaining smooth engagement or disengagement of automatic control electric
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses an automatic switching method based on generalized predictive control, which comprises the steps of firstly, obtaining predictive data, secondly, establishing a regulation and control linear model, thirdly, obtaining predictive switching data, fourthly, generating predictive control switching signals, and fifthly, executing automatic switching regulation and control; according to the invention, through predictive control of multiple influencing factors of the controlled object, full-process automatic synchronous switching is realized, multi-factor synchronous adjustment is satisfied, the situation that the controlled object is changed to have different control results due to overlong head-to-tail interval time caused by manual one-by-one adjustment is avoided, the adjustment precision of the influencing factors on the controlled object after the predictive switching regulation is executed is ensured, and the safe and stable operation of the actual production process is ensured.
Description
Technical Field
The invention relates to the technical field of automatic control, in particular to an automatic switching method based on generalized predictive control.
Background
In the field of automatic control, there is a class of control objects which have the characteristics of large inertia, large time delay, strong noise and the like, for example, a main steam temperature and reheat steam temperature system of a thermal power generating unit all belong to a class of typical thermal objects.
At present, a traditional PID control method is widely adopted for the control objects, and the feedback correction is carried out according to the deviation between a set value and a measured value, so that the control objects belong to post-hoc control.
At present, the manual automatic switching of generalized predictive control realizes PID control and manual control careless switching, but the full automatic detection and adjustment cannot be realized in the actual regulation and control process, the numerical values corresponding to different influence factors are still needed to be manually controlled to adjust the controlled object, the influence factors are needed to be regulated and controlled one by one in the manual control and adjustment process, the time difference exists, the controlled object still has variation in the middle time period from the first influence factor to the last influence factor adjustment process, and the operation of the controlled object cannot be accurately controlled, so the invention provides an automatic switching method based on generalized predictive control to solve the problems in the prior art.
Disclosure of Invention
In view of the above problems, the invention aims to provide an automatic switching method based on generalized predictive control, which realizes full-process automatic synchronous switching through predictive control on various influencing factors of a controlled object, satisfies multi-factor synchronous adjustment, avoids the influence of overlong head-to-tail interval time on the change of the controlled object caused by manual one-by-one adjustment, ensures the adjustment precision of the influencing factors on the controlled object after the execution of predictive switching regulation, and ensures the safe and stable operation of the actual production process.
In order to achieve the purpose of the invention, the invention is realized by the following technical scheme: an automatic switching method based on generalized predictive control comprises the following steps:
firstly, obtaining prediction data, namely detecting and sorting linear and nonlinear data of influence factor changes according to various factors influencing a controlled object, establishing a corresponding change prediction model, and outputting the real-time prediction data through the corresponding prediction model;
step two, building a regulation and control linear model, namely obtaining measurement and calculation data of influences of different factors on a control object through multiple experiments, building an initial data set, and building multiple groups of prediction regulation and control linear models according to the initial data set and based on a deep learning network;
step three, obtaining prediction switching data, taking the real-time prediction data in the step one as input to be imported into a corresponding prediction regulation linear model, and outputting and controlling the prediction switching data by the model;
generating a predictive control switching signal, expressing a controlled object by adopting a CARIMA model, and then carrying control switching predictive data into the CARIMA model for processing and outputting a preside control signal;
and fifthly, executing automatic switching regulation, introducing the output pre-side control signal into an automatic switching system, counting down according to the predicted time length, immediately executing a switching control program after reaching a time point, and performing inversion prediction regulation on different factor variables to complete automatic control.
The further improvement is that: and in the second step, when the measurement and calculation data are obtained, the control object is respectively and independently tested according to different factors, only one variable of the factors to be tested is ensured during testing, other factors are fixed, the influence of different change conditions on the control object is respectively tested, corresponding data are recorded, and then a plurality of groups of data of the single factor are arranged to establish a predictive regulation linear model of the corresponding influence factor.
The further improvement is that: and thirdly, respectively bringing real-time prediction data of different factors into corresponding prediction regulation linear models to obtain control prediction switching data of corresponding influence factors on the controlled object, and then integrating all the control prediction switching data into a data array to be embodied in a data array form.
The further improvement is that: and in the fourth step, the control prediction switching data of different factors are respectively brought into a CARIMA model for iterative processing, the iterative processing results of the different factors are output in the form of regulation and control data, and finally the regulation and control data of the different factors are fused by using a weighted average method to obtain a pre-side control signal.
The switching system of the automatic switching method based on generalized predictive control comprises a multi-factor data acquisition system, a data processing system and an automatic control system, wherein the multi-factor data acquisition system is used for acquiring data of various influencing factors and real-time data of a controlled object and comprises an experimental data acquisition module and a real-time predictive data acquisition module; the data processing system is used for sorting various acquired data, constructing a model and outputting control data, and comprises a data integration module, a model construction module and a control output module; the automatic control system is used for adjusting the control form of the controlled object and automatically predicting the numerical value of various factors influencing the adjustment, and comprises an identification switching module and an adjustment control module.
The further improvement is that: the experimental data acquisition module is used for acquiring measurement and calculation data according to a multi-factor test experiment and sorting the measurement and calculation data to obtain an initial data set, and the real-time prediction data acquisition module is used for acquiring real-time monitoring data of multiple factors and combining a change prediction model to obtain real-time prediction data.
The further improvement is that: the data integration module is used for sorting the acquired various data according to different factor types, the model construction module is used for calling the sorted data to establish various prediction models corresponding to different factors, and the control output module is used for outputting control signals after the prediction data are fused.
The further improvement is that: the identification switching module is used for identifying the output control signal and switching the control form, and the adjustment control module is used for carrying out prediction adjustment of different factors according to the state of the controlled object after switching the control form.
The beneficial effects of the invention are as follows: according to the invention, through predictive control of multiple influencing factors of the controlled object, full-process automatic synchronous switching is realized, multi-factor synchronous adjustment is satisfied, the situation that the controlled object is changed to have different control results due to overlong head-to-tail interval time caused by manual one-by-one adjustment is avoided, the adjustment precision of the influencing factors on the controlled object after the predictive switching regulation is executed is ensured, and the safe and stable operation of the actual production process is ensured.
Drawings
FIG. 1 is a flow chart of a method according to embodiment 1 of the present invention.
Fig. 2 is a system architecture diagram of embodiment 2 of the present invention.
Detailed Description
The present invention will be further described in detail with reference to the following examples, which are only for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
Example 1
According to fig. 1, the embodiment provides an automatic switching method based on generalized predictive control, which comprises the following steps:
firstly, obtaining prediction data, detecting and sorting linear and nonlinear data of influence factor changes according to various factors influencing a controlled object, establishing a corresponding change prediction model, and outputting the real-time prediction data through the corresponding prediction model.
Step two, building a regulation and control linear model, namely obtaining measurement and calculation data of influences of different factors on a control object through multiple experiments, building an initial data set, and building multiple groups of prediction regulation and control linear models according to the initial data set and based on a deep learning network;
when the measurement and calculation data are obtained, the control object is respectively and independently tested according to different factors, only one variable of the factors to be tested is ensured during testing, other factors are fixed, the influence of different change conditions on the control object is respectively tested, corresponding data are recorded, and then a plurality of groups of data of the single factors are arranged to establish a predictive regulation linear model of the corresponding influence factors.
Step three, obtaining prediction switching data, taking the real-time prediction data in the step one as input to be imported into a corresponding prediction regulation linear model, and outputting and controlling the prediction switching data by the model;
and respectively bringing real-time prediction data of different factors into corresponding prediction regulation linear models to obtain control prediction switching data of corresponding influence factors on the controlled object, and then integrating all the control prediction switching data into a data array to be embodied in a data array form.
Generating a predictive control switching signal, expressing a controlled object by adopting a CARIMA model, and then carrying control switching predictive data into the CARIMA model for processing and outputting a preside control signal;
and respectively carrying control prediction switching data of different factors into a CARIMA model for iterative processing, outputting iterative processing results of the different factors in a form of regulation data, and finally fusing the regulation data of the different factors by using a weighted average method to obtain a pre-side control signal.
And fifthly, executing automatic switching regulation, introducing the output pre-side control signal into an automatic switching system, counting down according to the predicted time length, immediately executing a switching control program after reaching a time point, and performing inversion prediction regulation on different factor variables to complete automatic switching regulation.
Predicting an impending change result by using a plurality of influence factors of a controlled object through an established change prediction model, outputting the change result through processing of a regulation linear model to obtain an influence result of a corresponding influence factor, then combining the influence results of the plurality of factors into integral data, and finally combining the integral data with a set operation threshold inversion of the controlled object to obtain respective prediction regulation values of the plurality of influence factors to finish automatic switching regulation;
compared with the traditional generalized predictive control careless switching manual-automatic switching control, the full-automatic switching control is realized, manual adjustment operation is not needed, the automatic switching adjustment can realize multi-factor synchronous control adjustment, and the problem that the controlled object is changed to have different control results due to overlong head-tail interval time caused by manual one-by-one adjustment is avoided, so that the controlled object switching adjustment control precision is low.
Example 2
According to fig. 2, the embodiment provides a switching system of an automatic switching method based on generalized predictive control, which comprises a multi-factor data acquisition system, a data processing system and an automatic control system, wherein the multi-factor data acquisition system is used for acquiring data of multiple influencing factors and real-time data of a controlled object, and comprises an experimental data acquisition module and a real-time predictive data acquisition module; the experiment data acquisition module is used for acquiring measurement and calculation data according to the multi-factor test experiment and sorting the measurement and calculation data to obtain an initial data set, and the real-time prediction data acquisition module is used for acquiring real-time monitoring data recording multiple factors and combining a change prediction model to obtain real-time prediction data.
The data processing system is used for sorting various acquired data, constructing a model and outputting control data, and comprises a data integration module, a model construction module and a control output module; the data integration module is used for sorting the acquired various data according to different factor types, the model construction module is used for calling the sorted data to establish various prediction models corresponding to different factors, and the control output module is used for outputting control signals after the prediction data are fused.
The automatic control system is used for adjusting the control form of the controlled object and automatically predicting the numerical values of various factors influencing the adjustment, and comprises an identification switching module and an adjustment control module; the identification switching module is used for identifying the output control signal and switching the control form, and the adjustment control module is used for carrying out prediction adjustment of different factors according to the state of the controlled object after switching the control form.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. An automatic switching method based on generalized predictive control is characterized by comprising the following steps:
firstly, obtaining prediction data, namely detecting and sorting linear and nonlinear data of influence factor changes according to various factors influencing a controlled object, establishing a corresponding change prediction model, and outputting the real-time prediction data through the corresponding prediction model;
step two, building a regulation and control linear model, namely obtaining measurement and calculation data of influences of different factors on a control object through multiple experiments, building an initial data set, and building multiple groups of prediction regulation and control linear models according to the initial data set and based on a deep learning network;
step three, obtaining prediction switching data, taking the real-time prediction data in the step one as input to be imported into a corresponding prediction regulation linear model, and outputting and controlling the prediction switching data by the model;
generating a predictive control switching signal, expressing a controlled object by adopting a CARIMA model, and then carrying control switching predictive data into the CARIMA model for processing and outputting a preside control signal;
and fifthly, executing automatic switching regulation, introducing the output pre-side control signal into an automatic switching system, counting down according to the predicted time length, immediately executing a switching control program after reaching a time point, and performing inversion prediction regulation on different factor variables to complete automatic control.
2. The automatic switching method based on generalized predictive control according to claim 1, wherein: and in the second step, when the measurement and calculation data are obtained, the control object is respectively and independently tested according to different factors, only one variable of the factors to be tested is ensured during testing, other factors are fixed, the influence of different change conditions on the control object is respectively tested, corresponding data are recorded, and then a plurality of groups of data of the single factor are arranged to establish a predictive regulation linear model of the corresponding influence factor.
3. The automatic switching method based on generalized predictive control according to claim 1, wherein: and thirdly, respectively bringing real-time prediction data of different factors into corresponding prediction regulation linear models to obtain control prediction switching data of corresponding influence factors on the controlled object, and then integrating all the control prediction switching data into a data array to be embodied in a data array form.
4. The automatic switching method based on generalized predictive control according to claim 1, wherein: and in the fourth step, the control prediction switching data of different factors are respectively brought into a CARIMA model for iterative processing, the iterative processing results of the different factors are output in the form of regulation and control data, and finally the regulation and control data of the different factors are fused by using a weighted average method to obtain a pre-side control signal.
5. The switching system of the automatic switching method based on generalized predictive control according to claim 1, wherein: the system comprises a multi-factor data acquisition system, a data processing system and an automatic control system, wherein the multi-factor data acquisition system is used for acquiring data of various influencing factors and real-time data of a controlled object, and comprises an experimental data acquisition module and a real-time prediction data acquisition module; the data processing system is used for sorting various acquired data, constructing a model and outputting control data, and comprises a data integration module, a model construction module and a control output module; the automatic control system is used for adjusting the control form of the controlled object and automatically predicting the numerical value of various factors influencing the adjustment, and comprises an identification switching module and an adjustment control module.
6. The switching system of the automatic switching method based on generalized predictive control according to claim 5, wherein: the experimental data acquisition module is used for acquiring measurement and calculation data according to a multi-factor test experiment and sorting the measurement and calculation data to obtain an initial data set, and the real-time prediction data acquisition module is used for acquiring real-time monitoring data of multiple factors and combining a change prediction model to obtain real-time prediction data.
7. The switching system of the automatic switching method based on generalized predictive control according to claim 5, wherein: the data integration module is used for sorting the acquired various data according to different factor types, the model construction module is used for calling the sorted data to establish various prediction models corresponding to different factors, and the control output module is used for outputting control signals after the prediction data are fused.
8. The switching system of the automatic switching method based on generalized predictive control according to claim 5, wherein: the identification switching module is used for identifying the output control signal and switching the control form, and the adjustment control module is used for carrying out prediction adjustment of different factors according to the state of the controlled object after switching the control form.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311678944.XA CN117518771A (en) | 2023-12-08 | 2023-12-08 | Automatic switching method based on generalized predictive control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311678944.XA CN117518771A (en) | 2023-12-08 | 2023-12-08 | Automatic switching method based on generalized predictive control |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117518771A true CN117518771A (en) | 2024-02-06 |
Family
ID=89756770
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311678944.XA Pending CN117518771A (en) | 2023-12-08 | 2023-12-08 | Automatic switching method based on generalized predictive control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117518771A (en) |
-
2023
- 2023-12-08 CN CN202311678944.XA patent/CN117518771A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112286043B (en) | PID parameter setting method based on controlled object step response characteristic data | |
| US20050149209A1 (en) | Adaptive multivariable process controller using model switching and attribute interpolation | |
| CN108628288B (en) | Performance evaluation method for first-order time-lag combined integral control system | |
| CN109451304B (en) | Batch focusing test method and system for camera modules | |
| CN106227964B (en) | Nonlinear systems with hysteresis parameter identification method based on extended state observer | |
| CN201476905U (en) | Neural network PID temperature controlled thermocouple automatic verification system | |
| CN116089870A (en) | Industrial equipment fault prediction method and device based on meta-learning under small sample condition | |
| CN110850709B (en) | Progressive tuning method for PID parameters | |
| CN110488888B (en) | Resistance heating furnace temperature control method based on adaptive iterative learning | |
| CN117518771A (en) | Automatic switching method based on generalized predictive control | |
| Zhu | System identification for process control: recent experience and outlook | |
| CN116627028B (en) | Control method for crosslinked cable production line | |
| CN111769545B (en) | Load flow evaluation method and device under sequential multiple-break scene | |
| CN107942675A (en) | A kind of Chemical Batch Process stability of control system keeping method | |
| WO2020124934A1 (en) | Servo motor load inertia measurement method | |
| CN107831668B (en) | Method and system suitable for follow-up control self-adaptive detection | |
| CN109725526B (en) | Multivariable semi-adaptive prediction control method | |
| CN106950835A (en) | Succinct Robust Two-Degree-of-Freedom proportional plus integral control method | |
| CN105699043B (en) | A kind of wind tunnel sensors that improve measure stability and the method for precision | |
| CN112115640B (en) | Control valve viscosity detection method based on transfer learning | |
| Fu et al. | Research on fast and intelligent calibration method based on automatic test system | |
| CN117033984B (en) | Semiconductor processing quality prediction method and system combining digital twinning | |
| CN116795065B (en) | Control method and system for unsaturated polyester resin production equipment | |
| CN114924490B (en) | Model collinearity analysis and processing method in model predictive control | |
| CN111624954B (en) | Advanced process control machine learning system for flow type manufacturing industry |
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 |