CN103336433A - Back stepping based mixed adaptive predication control system and predication control method thereof - Google Patents
Back stepping based mixed adaptive predication control system and predication control method thereof Download PDFInfo
- Publication number
- CN103336433A CN103336433A CN2013101458050A CN201310145805A CN103336433A CN 103336433 A CN103336433 A CN 103336433A CN 2013101458050 A CN2013101458050 A CN 2013101458050A CN 201310145805 A CN201310145805 A CN 201310145805A CN 103336433 A CN103336433 A CN 103336433A
- Authority
- CN
- China
- Prior art keywords
- model
- module
- input end
- data
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention discloses a back stepping based mixed adaptive predication control system and a predication control method thereof. The system comprises an intermittent chemical production target, a data collection channel, a neural network identification module, an adaptive control module and a model base, wherein an output end of the intermittent chemical production target is connected with an input end of the neural network identification module through the data collection channel, an output end of the neural network identification module is connected with an input end of the adaptive control module and an input end of the model base, an output end of the model base is connected with an input end of the adaptive control module, and an output end of the adaptive module is connected with an input end of the intermittent chemical production target through the data collection channel. The adopted mixed intelligent adaptive predication control method is a comprehensive technology, which is capable of not only changing parameters of a controller according to variations of environmental conditions, but also carrying out robust control to resist external interferences and ensuring the system to operate stably and the performance to reach the standard, thereby achieving the purposes of decreasing the energy consumption, reducing the cost, improving economic benefits and the like.
Description
Technical field
The present invention relates to a kind of chemical process Intelligent Hybrid adaptive prediction control system and control method thereof at intermittence based on the contragradience method, belong to industrial control field.
Background technology
Batch process refers to limited amount material processing sequence is in accordance with regulations processed to obtain the process of finite quantity product in one or more equipment.Flow process is short, equipment simple because batch production has, small investment, instant effect, be easy to change advantage such as kind, is widely used in during fine chemistry industry, pesticide chemical and biological medicine produce, and application prospect is very optimistic.In the last few years; fine chemistry industry production run scale constantly enlarges; complex technical process increase, product quality require to improve, and environmental protection requirement is more and more stricter; simultaneously; raw material and energy scarcity, market constantly changes, an urgent demand industry energy conservation consumption reduction; realize safety, stable, long-term, at full capacity and optimize operation, these have proposed new challenge to process control.
Because characteristics such as batch process becomes when having, non-linear are because the influence of the actual various uncertain factors of chemical process system at intermittence makes the deviser be difficult to obtain the accurate model of therrmodynamic system object in big working range and describes; Tradition based on the mechanism model method of matter energy balance equation on the one hand because the complicacy of modeling process, model structure and computing method, be difficult to satisfy the real-time requirement that control is optimized, simultaneously because the continuous service wear of special taking into account system object, aging, operating mode do not depart from, so its result of calculation is inevitable and there is sizable deviation in actual operating data, has reduced its practicality; On the other hand, a large amount of site tests for the empirical model that obtains comparatively to press close to real system carries out not only need to increase extra-pay, even might disturb normal safety in production.Many process characteristic difficult parameters are to measure, has multiple operation constraint condition, there is more interference, characteristics such as process is irreversible and be difficult to adopt remedial measures, make the control of batch process have very big difficulty, therefore in batch production process research and extension to use various effective advanced control strategies very necessary and urgent.
Summary of the invention
At the problems referred to above that exist in prior art discontinuous chemical process system and the control method thereof, the invention provides a kind of mixed self-adapting Predictive Control System and forecast Control Algorithm thereof based on the contragradience method.
Technical scheme of the present invention is:
Based on the mixed self-adapting Predictive Control System of contragradience method, comprise intermittently Chemical Manufacture object, data acquisition channel, neural network identification module, self-adaptive control module, model bank; Described intermittence, the output terminal of Chemical Manufacture object was connected by the input end of data acquisition channel with the neural network identification module, the output terminal of neural network identification module is connected with the input end of self-adaptive control module and the input end of model bank respectively, the output terminal of model bank is connected with the input end of self-adaptive control module, and the output terminal of self-adaptive control module is connected with the input end of Chemical Manufacture object intermittently by data acquisition channel.
Further, described neural network identification module comprises neural net model establishing module, model emulation module, model editing module; The output terminal of described data acquisition channel is connected with the input end of model emulation module and the input end of neural net model establishing module respectively, and the output terminal of model emulation module is connected with the input end of neural net model establishing module; The output terminal of neural net model establishing module is connected with the input end of model editing module and the input end of model bank respectively.
Further, described data acquisition channel comprises acquisition module and the data preprocessing module that connects successively.
The forecast Control Algorithm of above-mentioned mixed self-adapting Predictive Control System based on the contragradience method specifically may further comprise the steps:
(1) data acquisition channel is gathered the intermittently process parameter value of chemical process in real time, carries out the data pre-service;
(2) data after the processing pass to neural network identifier, carry out modeling by neural network identifier, and the model after the modeling is through the emulation correction;
(3) Intelligent Hybrid adaptive prediction controller reads model parameter, generates the control parameter, the action of control topworks;
(4) control algolithm realizes.
Further, described step (1) comprising: use DDE technology, OPC technology and API HOOK technology at bottom, the remote process Data Interchange Technology is as data source adapter, realize unified interface, the similar adapter of structure at different DCS system platforms, each adapter adopts unified, and message based communications protocol is carried out exchanges data with the one-level central server; The primary centre server further encapsulates, screens, compresses data again, and require to be forwarded to the upper level central server according to the time response of upper layer application, perhaps directly offer the various application that this layer articulates, the central server of each level is with the data interaction between the application that articulates simultaneously.
Further, described step (2) comprising: the modeling of neural network identifier is set up mathematical model according to the data that obtain, and simultaneously, the model that the data that the utilization of model emulation device obtains are set up neural net model establishing carries out validation verification; The nonlinear model that the model editing module is set up the neural net model establishing module according to simulation result is revised; The neural net model establishing module is gone into model data store in the model bank.
The invention has the beneficial effects as follows:
The present invention takes full advantage of advanced control theory, neural network, System Discrimination, intelligent algorithm etc., chemical process realization at intermittence is detected, control, modeling, management, scheduling and decision-making, design a kind of modeling and control of key process parameter at the chemical process at intermittence, at the distinctive control method of cascade system, namely control design proposal based on the batch production process hybrid intelligent adaptive prediction of contragradience method, adopt this hybrid intelligent adaptive prediction control method, can correspondingly change the parameter of controller according to the environmental baseline change, to adapt to the variation of its characteristic, can carry out robust control opposing external disturbance again, the stable operation and the performance index that guarantee total system reach requirement, thereby minimizing energy consumption, reduce cost the integrated technology of purpose such as increase economic efficiency.
Description of drawings
Fig. 1 is the structured flowchart that the present invention is based on the mixed self-adapting Predictive Control System of contragradience method;
Fig. 2 is the structured flowchart of the neural network identification module in the system of the present invention;
Fig. 3 is the genetic algorithm process flow diagram of this adding RBF operator.
Embodiment
Below in conjunction with accompanying drawing the present invention is described in further detail.
The present invention is directed to intermittently chemical process, as the propiconazole production run.The propiconazole production run mainly obtains by organic synthesis, and its synthetic reaction mechanism complexity, control accuracy requires high, the control difficulty is big, need be on the basis of the operation characteristic of furtheing investigate propiconazole cyclisation, bromination, condensation and refining reaction still, process characteristic, extensively collect historical data, expertise and working specification, determine overall control target and main control variable.
Fig. 1 is the control principle block diagram that the present invention is based on the mixed self-adapting Predictive Control System of contragradience method, and system of the present invention comprises intermittently Chemical Manufacture object, data acquisition channel, neural network identification module, self-adaptive control module, model bank; Intermittently the output terminal of Chemical Manufacture object is connected by the input end of data acquisition channel with the neural network identification module, the output terminal of neural network identification module is connected with the input end of self-adaptive control module and the input end of model bank respectively, the output terminal of model bank is connected with the input end of self-adaptive control module, and the output terminal of self-adaptive control module is connected with the input end of Chemical Manufacture object intermittently by data acquisition channel.
The structured flowchart of neural network identification module comprises neural net model establishing module, model emulation module, model editing module as shown in Figure 2; The output terminal of described data acquisition channel is connected with the input end of model emulation module and the input end of neural net model establishing module respectively, and the output terminal of model emulation module is connected with the input end of neural net model establishing module; The output terminal of neural net model establishing module is connected with the input end of model editing module and the input end of model bank respectively.
Data acquisition channel comprises the acquisition module and the data preprocessing module that connect successively.This module is based on the data acquisition switching plane of Web Service, and applied data communications and acquisition technique obtain object and control desired data, handles process units parameter and output control parameter.
Model bank, consider that intermittently each workshop section of Chemical Manufacture is according to the characteristics of certain processing sequence production, namely form typical cascade system, with temperature in the PREDICTIVE CONTROL whole process of production, pressure, motor stirs speed governing, the adjusting of multivariate parameters such as mass flow, when considering that simultaneously the systematic uncertainty of production run can not parametrization, process model is unknowable, traditional PREDICTIVE CONTROL has good control effect at initial operating stage, but passing in time, operating conditions, factors such as production environment change, the predictive controller performance descends, and can't reach the expection benefit.The present invention is directed to the situation of intermittently chemical process model the unknown and external disturbance, use neural network prediction model.
Self-adaptive control module, hybrid intelligent adaptive prediction controller improves system performance, remedy existing predictive controller and influence the decline of control system performance with working condition change (being the model parameter condition of unknown), and there is an external disturbance, influence system stable operation, thereby can't reach the defective of expection benefit.
The forecast Control Algorithm of above-mentioned mixed self-adapting Predictive Control System based on the contragradience method specifically may further comprise the steps:
(1) data acquisition channel is gathered the intermittently process parameter value of chemical process in real time, carries out the data pre-service;
(2) data after the processing pass to neural network identifier, carry out modeling by neural network identifier, and the model after the modeling is through the emulation correction;
(3) Intelligent Hybrid adaptive prediction controller reads model parameter, generates the control parameter, the action of control topworks;
(4) control algolithm realizes.
Step (1) comprising: A1, use DDE technology, OPC technology (COM technology) and API HOOK technology at bottom, the remote process Data Interchange Technology is as data source adapter, realize unified interface, the similar adapter of structure at different DCS system platform exploitations.A2, each adapter adopt unified, and message based communications protocol is carried out exchanges data with the one-level central server.The primary centre server further encapsulates, screens, compresses data again, and according to requirements such as the time responses of upper layer application or be forwarded to the upper level central server, perhaps directly offers the various application that this layer articulates.The central server of each level is with the data interaction between the application that articulates simultaneously, the network penetrability is strong with adopting, the data layout based on SOAP of platform independence, language independent, use the data that not only can call central server, can also register extra data processor, for the control system of isomery and applications exchange and shared data provide an application integration environment opening, unified.
Step (2) comprising: the modeling of B1, neural network identification module is set up mathematical model according to the data that obtain, consider intermittently chemical process series production, be the input quantity that the output quantity of last workshop section is next workshop section, then consider batch process is modeled as typical cascade system.Be subject to environmental influence at production run, batch process is difficult to modeling and procedure parameter is uncertain, can consider batch process regarded as and have following triangle cascade system linear and that nonlinear uncertain partly makes up, utilize neural network to have the ability of approximating function, consider the model with the neural net model establishing non-linear partial.Simultaneously, the data of model emulation module utilization acquisition are carried out validation verification to the model of neural net model establishing foundation; The nonlinear model that B2, model editing module are set up the neural net model establishing module according to simulation result is revised; B3, neural net model establishing module are gone into model data store in the model bank.
Step (3) comprising: C1, according to the contragradience controller of each layer of cascade system modelling, can be simultaneously according to system stability analysis, and Liapunov function
, the design adaptive rate, namely the neural network weight parameter is estimated.In addition, reduce the initial estimation error of neural network weight, be conducive to reduce the tracking error of batch production control system, the present invention proposes to improve with the genetic algorithm optimization neural network search efficiency of parameter, adds the genetic algorithm process flow diagram of RBF operator as shown in Figure 3.C2, adaptive prediction controller design consideration intermittently chemical process control system model are the characteristics of cascade structure, can consider to use the contragradience method that complicated nonlinear systems is resolved into several subsystems, for each subsystem designs Liapunov function and intermediate virtual controller respectively
, can retreat into total system with advancing layer by layer always, thereby finish the intermittently adaptive prediction controller of the reality of chemical process control system
Design.Each Virtual Controller
With the working control device
Comprise following 4 parts: 1. in order to the neural network of parametrization system unknown function; 2. adaptive line controller
3. supervision is acted on behalf of
(being switching function), system produces when unusual, is used for temporarily transferring control and gives the 4. robust controller; 4. robust controller
The contragradience design method is used in combination with the Liapunov type adaptive law that C1 in the design procedure (3) mentions, and takes all factors into consideration controller
And adaptive law
, make total system meet the desired system dynamically and static performance index.C3, the design of mixed self-adapting neural network prediction controller, the further Virtual Controller that above-mentioned steps C2 is obtained
Adaptive controller with reality
, adopt following mixed form to be designed to:
,
Be switching function, native system has two kinds of working methods, and what namely step (3) comprised is the adaptive line controller
And robust controller
When existing model parameter uncertain, select the adaptive line controller for use
, be used for the compensating parameter uncertainty, and when disturbing when existing, select robust controller for use
, be used for the suffered external disturbance of opposing system.
Step (4) control algolithm realizes comprising: system is by based on the data acquisition system (DAS) of DCS with KingView software handles as the data of upper computer software and display system constitutes, KingView software is supported the DDE technology simultaneously, can KingView and Matlab be carried out exchanges data by the DDE agreement, realize complicated hybrid intelligent adaptive prediction control algolithm.And the validity by a large amount of real-time simulation validation CONTROLLER DESIGN, and with the part application of result in reality.
The present invention takes full advantage of advanced control theory, neural network, System Discrimination, intelligent algorithm etc., chemical process realization at intermittence is detected, control, modeling, management, scheduling and decision-making, design a kind of modeling and control of key process parameter at the chemical process at intermittence, at the distinctive control method of cascade system, namely control design proposal based on the batch production process hybrid intelligent adaptive prediction of contragradience method, adopt this hybrid intelligent adaptive prediction control method, can correspondingly change the parameter of controller according to the environmental baseline change, to adapt to the variation of its characteristic, can carry out robust control opposing external disturbance again, the stable operation and the performance index that guarantee total system reach requirement, thereby minimizing energy consumption, reduce cost the integrated technology of purpose such as increase economic efficiency.Thereby the present invention proposes by carrying out simulation study, and the part Study achievement is applied in the Chemical Manufacture at actual intermittence, and quality is controlled in raising.
Principle of work of the present invention is by the analysis to the chemical process at intermittence, with the black-box modeling principle, application system structure and neural net model establishing algorithm, historical data according to the chemical process at intermittence, set up the intermittently nonlinear model of chemical process, according to the model of setting up, the control of design hybrid intelligent adaptive prediction, the action of output controlled quentity controlled variable control topworks realizes the PREDICTIVE CONTROL to the chemical process at intermittence.
Claims (6)
1. based on the mixed self-adapting Predictive Control System of contragradience method, comprise intermittently Chemical Manufacture object, data acquisition channel, neural network identification module, self-adaptive control module, model bank; Described intermittence, the output terminal of Chemical Manufacture object was connected by the input end of data acquisition channel with the neural network identification module, the output terminal of neural network identification module is connected with the input end of self-adaptive control module and the input end of model bank respectively, the output terminal of model bank is connected with the input end of self-adaptive control module, and the output terminal of self-adaptive control module is connected with the input end of Chemical Manufacture object intermittently by data acquisition channel.
2. the mixed self-adapting Predictive Control System based on the contragradience method according to claim 1, it is characterized in that: described neural network identification module comprises neural net model establishing module, model emulation module, model editing module; The output terminal of described data acquisition channel is connected with the input end of model emulation module and the input end of neural net model establishing module respectively, and the output terminal of model emulation module is connected with the input end of neural net model establishing module; The output terminal of neural net model establishing module is connected with the input end of model editing module and the input end of model bank respectively.
3. the mixed self-adapting Predictive Control System based on the contragradience method according to claim 1 and 2 is characterized in that: described data acquisition channel comprises acquisition module and the data preprocessing module that connects successively.
4. the forecast Control Algorithm of any described mixed self-adapting Predictive Control System based on the contragradience method in the claim 1 to 3 specifically may further comprise the steps:
(1) data acquisition channel is gathered the intermittently process parameter value of chemical process in real time, carries out the data pre-service;
(2) data after the processing pass to neural network identifier, carry out modeling by neural network identifier, and the model after the modeling is through the emulation correction;
(3) Intelligent Hybrid adaptive prediction controller reads model parameter, generates the control parameter, the action of control topworks;
(4) control algolithm realizes.
5. the mixed self-adapting forecast Control Algorithm based on the contragradience method according to claim 4, it is characterized in that: described step (1) comprising: use DDE technology, OPC technology and API HOOK technology at bottom, the remote process Data Interchange Technology is as data source adapter, realize unified interface, the similar adapter of structure at different DCS system platforms, each adapter adopts unified, and message based communications protocol is carried out exchanges data with the one-level central server; The primary centre server further encapsulates, screens, compresses data again, and require to be forwarded to the upper level central server according to the time response of upper layer application, perhaps directly offer the various application that this layer articulates, the central server of each level is with the data interaction between the application that articulates simultaneously.
6. the mixed self-adapting forecast Control Algorithm based on the contragradience method according to claim 4, it is characterized in that: described step (2) comprising: the modeling of neural network identifier is set up mathematical model according to the data that obtain, simultaneously, the data of model emulation device utilization acquisition are carried out validation verification to the model of neural net model establishing foundation; The nonlinear model that the model editing module is set up the neural net model establishing module according to simulation result is revised; The neural net model establishing module is gone into model data store in the model bank.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310145805.0A CN103336433B (en) | 2013-04-25 | 2013-04-25 | Mixed self-adapting Predictive Control System based on Backstepping and forecast Control Algorithm thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310145805.0A CN103336433B (en) | 2013-04-25 | 2013-04-25 | Mixed self-adapting Predictive Control System based on Backstepping and forecast Control Algorithm thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103336433A true CN103336433A (en) | 2013-10-02 |
| CN103336433B CN103336433B (en) | 2016-10-19 |
Family
ID=49244625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310145805.0A Active CN103336433B (en) | 2013-04-25 | 2013-04-25 | Mixed self-adapting Predictive Control System based on Backstepping and forecast Control Algorithm thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103336433B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104122878A (en) * | 2014-08-13 | 2014-10-29 | 黑龙江省科学院自动化研究所 | Industrial energy conservation and emission reduction control device and method |
| CN105231254A (en) * | 2015-09-13 | 2016-01-13 | 常州大学 | Hot-blast air and microwave coupling food drying control system |
| CN107276471A (en) * | 2017-06-16 | 2017-10-20 | 青岛大学 | A kind of asynchronous machine ambiguous location tracking and controlling method based on state constraint |
| CN109254531A (en) * | 2017-11-29 | 2019-01-22 | 辽宁石油化工大学 | The optimal cost control method of multistage batch process with time lag and interference |
| CN109634116A (en) * | 2018-09-04 | 2019-04-16 | 贵州大学 | A kind of acceleration adaptive stabilizing method of fractional order mechanical centrifugal governor system |
| CN111221250A (en) * | 2020-01-14 | 2020-06-02 | 三峡大学 | Nonlinear system with parameter uncertainty and multiple external disturbances and design method thereof |
| CN112934142A (en) * | 2021-02-01 | 2021-06-11 | 山东大学 | Method and system for controlling temperature of homogeneous tubular reactor based on reverse step method |
| CN113435067A (en) * | 2021-08-26 | 2021-09-24 | 阿里云计算有限公司 | Data processing system and method |
| CN114326405A (en) * | 2021-12-30 | 2022-04-12 | 哈尔滨工业大学 | Neural network backstepping control method based on error training |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0453371A1 (en) * | 1990-04-20 | 1991-10-23 | AEROSPATIALE Société Nationale Industrielle | Interactive procedure for producing software source code modelling a complex set of functional modules |
| JP2000235561A (en) * | 1999-02-16 | 2000-08-29 | Nec Corp | Simulation model editor and machine readable recording medium recording program |
| US20030149650A1 (en) * | 2001-09-28 | 2003-08-07 | Yeh Raymond T. | Financial transfer simulation system and method |
| CN101598927A (en) * | 2009-05-15 | 2009-12-09 | 广东工业大学 | A kind of soda carbonization technique control system and control method thereof based on neural network |
| CN102053595A (en) * | 2009-10-30 | 2011-05-11 | 中国石油化工股份有限公司 | Method for controlling cracking depth of cracking furnace in ethylene device |
| CN102255320A (en) * | 2011-07-15 | 2011-11-23 | 广东电网公司电力科学研究院 | Voltage reactive real-time control system of regional power grid and enclosed loop control method thereof |
-
2013
- 2013-04-25 CN CN201310145805.0A patent/CN103336433B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0453371A1 (en) * | 1990-04-20 | 1991-10-23 | AEROSPATIALE Société Nationale Industrielle | Interactive procedure for producing software source code modelling a complex set of functional modules |
| JP2000235561A (en) * | 1999-02-16 | 2000-08-29 | Nec Corp | Simulation model editor and machine readable recording medium recording program |
| US20030149650A1 (en) * | 2001-09-28 | 2003-08-07 | Yeh Raymond T. | Financial transfer simulation system and method |
| CN101598927A (en) * | 2009-05-15 | 2009-12-09 | 广东工业大学 | A kind of soda carbonization technique control system and control method thereof based on neural network |
| CN102053595A (en) * | 2009-10-30 | 2011-05-11 | 中国石油化工股份有限公司 | Method for controlling cracking depth of cracking furnace in ethylene device |
| CN102255320A (en) * | 2011-07-15 | 2011-11-23 | 广东电网公司电力科学研究院 | Voltage reactive real-time control system of regional power grid and enclosed loop control method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 孙小方等: "间歇化工反应器的先进控制技术", 《化工纵横》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104122878A (en) * | 2014-08-13 | 2014-10-29 | 黑龙江省科学院自动化研究所 | Industrial energy conservation and emission reduction control device and method |
| CN104122878B (en) * | 2014-08-13 | 2017-12-22 | 黑龙江省科学院自动化研究所 | The control method of industrial energy saving emission reduction control device |
| CN105231254A (en) * | 2015-09-13 | 2016-01-13 | 常州大学 | Hot-blast air and microwave coupling food drying control system |
| CN107276471A (en) * | 2017-06-16 | 2017-10-20 | 青岛大学 | A kind of asynchronous machine ambiguous location tracking and controlling method based on state constraint |
| CN107276471B (en) * | 2017-06-16 | 2019-06-07 | 青岛大学 | A kind of asynchronous machine ambiguous location tracking and controlling method based on state constraint |
| CN109254531A (en) * | 2017-11-29 | 2019-01-22 | 辽宁石油化工大学 | The optimal cost control method of multistage batch process with time lag and interference |
| CN109634116A (en) * | 2018-09-04 | 2019-04-16 | 贵州大学 | A kind of acceleration adaptive stabilizing method of fractional order mechanical centrifugal governor system |
| CN111221250A (en) * | 2020-01-14 | 2020-06-02 | 三峡大学 | Nonlinear system with parameter uncertainty and multiple external disturbances and design method thereof |
| CN111221250B (en) * | 2020-01-14 | 2022-06-03 | 三峡大学 | Nonlinear system with parameter uncertainty and multiple external disturbances and design method thereof |
| CN112934142A (en) * | 2021-02-01 | 2021-06-11 | 山东大学 | Method and system for controlling temperature of homogeneous tubular reactor based on reverse step method |
| CN113435067A (en) * | 2021-08-26 | 2021-09-24 | 阿里云计算有限公司 | Data processing system and method |
| CN114326405A (en) * | 2021-12-30 | 2022-04-12 | 哈尔滨工业大学 | Neural network backstepping control method based on error training |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103336433B (en) | 2016-10-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103268069B (en) | Based on the adaptive prediction control method of Hammerstein model | |
| CN103336433A (en) | Back stepping based mixed adaptive predication control system and predication control method thereof | |
| CN101619850B (en) | Dispatching method and dispatching system based on load online forecasting of thermoelectric power system | |
| CN102763048B (en) | Using adaptability prediction algorithm and when determine the method and apparatus of using adaptability prediction algorithm in virtual measurement | |
| WO2018137402A1 (en) | Cloud data centre energy-saving scheduling implementation method based on rolling grey prediction model | |
| CN1694109B (en) | Material data correction method in chemical and oil refinement process | |
| Torregrossa et al. | Optimization models to save energy and enlarge the operational life of water pumping systems | |
| CN112365029B (en) | Missing value processing method for air conditioner load prediction and air conditioner load prediction system | |
| CN104102212A (en) | Dispatching method, apparatus and system for gas and steam system in iron and steel enterprises | |
| CN108038040A (en) | Computer cluster performance indicator detection method, electronic equipment and storage medium | |
| CN106991514B (en) | Workshop model creation device and workshop model creation method | |
| Yao et al. | A multi-objective dynamic scheduling approach using multiple attribute decision making in semiconductor manufacturing | |
| CN103279075B (en) | Intermittent chemical production process and control method for same | |
| CN101763083A (en) | An effective industrial process dynamic optimization system and method capable of controlling variable parameterization | |
| CN102601881B (en) | Method for monitoring on-line quality and updating prediction model of rubber hardness | |
| CN109325880A (en) | A kind of Mid-long term load forecasting method based on Verhulst-SVM | |
| CN108197764A (en) | Predict the method and its equipment of electric power enterprise comprehensive energy consumption | |
| CN112308270A (en) | Long-term electricity load prediction method and device and computer implementation system | |
| CN103646670A (en) | Method and device for evaluating performances of storage system | |
| CN101916394A (en) | Knowledge fusion-based online soft measurement method | |
| CN103558756B (en) | The implementation method of single neuron PID controller based on configuration element | |
| CN112836860A (en) | Method and system for determining dynamic yield of fractured well in whole period of yield decreasing stage | |
| He et al. | An Improved Coupling Model of Grey-System and Multivariate Linear Regression for Water Consumption Forecasting. | |
| CN113632132A (en) | Computer-aided energy management method and energy management system | |
| KR20120133362A (en) | Optimized production scheduling system using loading simulation engine with dynamic feedback scheduling algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210311 Address after: Room 407-2-6, building C, Tian'an Digital City, 588 Changwu South Road, Wujin high tech Industrial Development Zone, Changzhou City, Jiangsu Province 213000 Patentee after: CHANGZHOU XIAOGUO INFORMATION SERVICES Co.,Ltd. Address before: Gehu Lake Road Wujin District 213164 Jiangsu city of Changzhou province No. 1 Patentee before: CHANGZHOU University |