CN103336433B - Mixed self-adapting Predictive Control System based on Backstepping and forecast Control Algorithm thereof - Google Patents
Mixed self-adapting Predictive Control System based on Backstepping and forecast Control Algorithm thereof Download PDFInfo
- Publication number
- CN103336433B CN103336433B CN201310145805.0A CN201310145805A CN103336433B CN 103336433 B CN103336433 B CN 103336433B CN 201310145805 A CN201310145805 A CN 201310145805A CN 103336433 B CN103336433 B CN 103336433B
- Authority
- CN
- China
- Prior art keywords
- model
- module
- data
- adaptive
- input
- 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.)
- Active
Links
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention discloses a kind of mixed self-adapting Predictive Control System based on Backstepping and forecast Control Algorithm thereof, this system includes interval Chemical Manufacture object, data acquisition channel, neural network identification module, self-adaptive control module, model library.Intermittently the outfan of Chemical Manufacture object is connected with the input of neural network identification module by data acquisition channel, the outfan of neural network identification module is connected with the input of self-adaptive control module and the input of model library respectively, the outfan of model library is connected with the input of self-adaptive control module, and the outfan of self-adaptive control module is connected by the input of data acquisition channel with interval Chemical Manufacture object.Use hybrid intelligent adaptive prediction control method, both can change according to environmental condition and change the parameter of controller, robust control opposing external disturbance can be carried out again, stable operation and the performance of guarantee system are up to standard, thus reduce energy consumption, reduce cost, the integrated technology of the purpose such as increase economic efficiency.
Description
Technical field
The present invention relates to a kind of interval chemical process Intelligent Hybrid adaptive prediction control system based on Backstepping
And control method, belong to industrial control field.
Background technology
Batch process refers to process to obtain by the processing sequence of regulation in one or more equipment by limited amount material
Obtain the course of processing of finite quantity product.Owing to Batch Process has that flow process is short, equipment simple, small investment, instant effect, is easily changed
The advantages such as kind, are widely used in fine chemistry industry, pesticide chemical and biological medicine production, and application prospect is the most optimistic.Near
Nian Lai, fine chemistry industry production process scale constantly expands, and complex technical process increases, and product quality requires to improve, and environment is protected
Protecting requirement increasingly stricter, meanwhile, raw material and energy scarcity, market is continually changing, and an urgent demand industry energy conservation lowers consumption, it is achieved peace
Entirely, stable, for a long time, at full capacity with optimize run, these propose new challenge to process control.
Owing to batch process has time-varying, the characteristic such as non-linear, owing to actual bath chemical process system is various the most true
The impact of qualitative factor so that designer is difficult to obtain therrmodynamic system object accurate model in relatively wide working range and describes；
Tradition mechanism model method based on matter energy equilibrium equation is on the one hand due to modeling process, model structure and computational methods
Complexity, it is difficult to meet control optimize requirement of real-time, simultaneously because the most specially consider system object run mill continuously
Damage, aging, operating mode deviation, therefore its result of calculation is inevitably and actual operating data exists sizable deviation, reduces
Its practicality；On the other hand, a large amount of on-the-spot test carried out for obtaining the empirical model more pressed close to real system, no
Only need to increase extra-pay, it could even be possible to the normal safety in production of interference.Many process characteristic parameters are difficult to measure, tool
Having multiple operational constraints condition, there is more interference, process is irreversible and is difficult to features such as adopting remedial measures, makes interval mistake
There is the biggest difficulty in the control of journey, therefore in batch production process, various effective Dynamic matrix control plans are applied in research and extension
The most necessary and urgent.
Summary of the invention
For in prior art interval Chemical Processing Systems and control method present in the problems referred to above, the present invention provide
A kind of mixed self-adapting Predictive Control System based on Backstepping and forecast Control Algorithm thereof.
The technical scheme is that
Mixed self-adapting Predictive Control System based on Backstepping, including interval Chemical Manufacture object, data acquisition channel,
Neural network identification module, self-adaptive control module, model library；The outfan of described interval Chemical Manufacture object passes through data acquisition
Collection passage be connected with the input of neural network identification module, the outfan of neural network identification module respectively with Self Adaptive Control
The input of module and the input of model library connect, and the outfan of model library is connected with the input of self-adaptive control module,
The outfan of self-adaptive control module is connected by the input of data acquisition channel with interval Chemical Manufacture object.
Further, described neural network identification module includes neural net model establishing module, model emulation module, model editing
Module；The outfan of described data acquisition channel defeated with the input of model emulation module and neural net model establishing module respectively
Entering end to connect, the outfan of model emulation module is connected with the input of neural net model establishing module；Neural net model establishing module
Outfan be connected with the input of model editing module and the input of model library respectively.
Further, described data acquisition channel includes acquisition module and the data preprocessing module being sequentially connected with.
The forecast Control Algorithm of above-mentioned mixed self-adapting Predictive Control System based on Backstepping, specifically includes following step
Rapid:
(1) process parameter value of data acquisition channel Real-time Collection interval chemical process, carries out data prediction；
(2) data after processing pass to neural network identifier, neural network identifier be modeled, after modeling
Model is through simulation modification；
(3) Intelligent Hybrid adaptive prediction controller reading model parameter, generates and controls parameter, controls actuator and moves
Make；
(4) control algolithm realizes.
Further, described step (1) including: in bottom application DDE technology, OPC technology and API HOOK technology, remotely
Process data switching technology as data source adapter, realizes unified interface, structure for different DCS system platforms similar
Adapter, each adapter uses unified, and message based communications protocol carries out data exchange with one-level central server；One
Data are further encapsulated, are screened, are compressed by level central server again, and require to turn according to the time response of upper layer application
It is dealt into upper level central server, or is supplied directly to the various application that this layer is mounted, genuinely convinced in the most each level
Business device is with the data interaction between the application mounted.
Further, described step (2) including: the modeling of neural network identifier sets up mathematical modulo according to the data obtained
Type, meanwhile, the model that model emulation device utilizes the data obtained to set up neural net model establishing carries out validation verification；Model is compiled
The nonlinear model that neural net model establishing module is set up by volume module according to simulation result is modified；Neural net model establishing module
Model data store is entered in model library.
The invention has the beneficial effects as follows:
The present invention makes full use of the control theory of advanced person, neutral net, system identification, intelligent algorithm etc., to interval chemical industry
Production process realization detects, controls, models, manages, dispatches and decision-making, designs a kind of key for interval chemical process
The modeling of technological parameter and control, for the distinctive control method of cascade system, i.e. based on Backstepping batch production process mixes
Close intelligent adaptive Predictive control design scheme, use this hybrid intelligent adaptive prediction control method, can be according to environmental condition
Change and correspondingly change the parameter of controller, to adapt to the change of its characteristic, robust control opposing external disturbance can be carried out again,
Ensure that stable operation and the performance indications of whole system reach requirement, thus reduce energy consumption, reduce cost, increase economic efficiency
The integrated technology of purpose.
Accompanying drawing explanation
Fig. 1 is the structured flowchart of present invention mixed self-adapting based on Backstepping Predictive Control System；
Fig. 2 is the structured flowchart of the neural network identification module in system of the present invention；
Fig. 3 is the genetic algorithm flow chart of this addition RBF operator.
Detailed description of the invention
Below in conjunction with the accompanying drawings the present invention is described in further detail.
The present invention is directed to interval chemical process, such as propiconazole production process.Propiconazole production process master
Organic synthesis to be passed through obtains, and its synthetic reaction complicated mechanism, control accuracy requires height, controls difficulty big, needs
On the basis of further investigation propiconazole cyclisation, bromination, condensation and the operation characteristic of refining reaction still, process characteristic, extensively
Collect historical data, expertise and rule of operation, determine overall control target and main control variable.
Fig. 1 is the control principle block diagram of present invention mixed self-adapting based on Backstepping Predictive Control System, institute of the present invention
The system of stating includes interval Chemical Manufacture object, data acquisition channel, neural network identification module, self-adaptive control module, model
Storehouse；Intermittently the outfan of Chemical Manufacture object is connected with the input of neural network identification module by data acquisition channel, god
It is connected with the input of self-adaptive control module and the input of model library respectively through the outfan of network identification module, model library
Outfan be connected with the input of self-adaptive control module, the outfan of self-adaptive control module by data acquisition channel with
Intermittently the input of Chemical Manufacture object connects.
The structured flowchart of neural network identification module is as in figure 2 it is shown, include neural net model establishing module, model emulation mould
Block, model editing module；The outfan of described data acquisition channel respectively with input and the neutral net of model emulation module
The input of MBM connects, and the outfan of model emulation module is connected with the input of neural net model establishing module；Neural
The outfan of network modelling module is connected with the input of model editing module and the input of model library respectively.
Data acquisition channel, including the acquisition module being sequentially connected with and data preprocessing module.This module sing on web
The data acquisition switching plane of Service, applied data communications and acquisition technique obtain object and control desired data, handle raw
Produce device parameter and output controls parameter.
Model library, it is considered to the feature that intermittently each workshop section of Chemical Manufacture produces according to certain processing sequence, i.e. forms allusion quotation
The cascade system of type, by temperature, pressure, the motor stirring multivariate such as speed governing, mass flow in whole for PREDICTIVE CONTROL production process
The regulation of parameter, consider simultaneously production process systematic uncertainty can not parametrization time, process model is unknowable, and traditional is pre-
Observing and controlling system has a good control effect at initial operating stage, but passage in time, the factor such as operating condition, production environment occurs
Change, it was predicted that controller performance declines, it is impossible to reach expection benefit.The present invention is directed to interval chemical process unknown-model and
The situation of external disturbance, uses neural network prediction model.
Self-adaptive control module, hybrid intelligent adaptive prediction controller improves systematic function, makes up existing pre-observing and controlling
Device processed changes (i.e. the situation of Unknown Parameters) with working condition and affects control system hydraulic performance decline, and exists outside dry
Disturb, affect system stable operation, thus be unable to reach the defect of expection benefit.
The forecast Control Algorithm of above-mentioned mixed self-adapting Predictive Control System based on Backstepping, specifically includes following step
Rapid:
(1) process parameter value of data acquisition channel Real-time Collection interval chemical process, carries out data prediction；
(2) data after processing pass to neural network identifier, neural network identifier be modeled, after modeling
Model is through simulation modification；
(3) Intelligent Hybrid adaptive prediction controller reading model parameter, generates and controls parameter, controls actuator and moves
Make；
(4) control algolithm realizes.
Step (1) including: A1, in bottom application DDE technology, OPC technology (COM technology) and API HOOK technology, remotely
Process data switching technology, as data source adapter, realizes unified interface, structure class for different DCS system platform developments
As adapter.A2, each adapter use unified, and message based communications protocol carries out data with one-level central server
Exchange.Data are further encapsulated, are screened, are compressed by primary centre server again, and the time according to upper layer application is special
Property etc. require or be forwarded to upper level central server, or be supplied directly to the various application that this layer is mounted.The most every
The central server of one level is with the data interaction between the application mounted, and by using, network penetrance is strong, platform is unrelated, language
Say that unrelated data form based on SOAP, application not only can call the data of central server, moreover it is possible to register extra number
According to processing routine, the control system for isomery provides an opening, unified application collection with applications exchange and shared data
Become environment.
Step (2) including: the data founding mathematical models that B1, the modeling foundation of neural network identification module are obtained, and examines
Considering interval chemical process series production, the output of the most last workshop section is the input quantity of next workshop section, then consider by
Batch process is modeled as typical cascade system.For production process easily by environmental influence, batch process be difficult to model and
Procedure parameter is uncertain, it is contemplated that batch process is regarded as the lower triangle cascade with the combination of linear processes uncertain part
System, utilizes neutral net to have the ability of approximating function, it is considered to the model of neural net model establishing non-linear partial.Meanwhile,
The model that model emulation module utilizes the data obtained to set up neural net model establishing carries out validation verification；B2, model editing
The nonlinear model that neural net model establishing module is set up by module according to simulation result is modified；B3, neural net model establishing mould
Model data store is entered in model library by block.
Step (3) including: C1, Backstepping Controller according to each layer of cascade system modelling, can be simultaneously according to system
Stability analysis, Liapunov function, design adaptive rate, i.e. neutral net weight parameter and estimate.It addition, reduce
The initial estimation error of neutral net weight, advantageously reduces the tracking error of Batch Process control system, and the present invention proposes to use
Genetic Algorithm Optimized Neural Network improves the search efficiency of parameter, adds genetic algorithm flow chart such as Fig. 3 institute of RBF operator
Show.The design of C2, adaptive prediction controller is the feature of cascade structure according to interval chemical process control system model, can
Consider to use Backstepping that complicated nonlinear system is resolved into several subsystems, separately design Li Yapu for each subsystem
Promise husband's function and intermediate virtual controller, whole system can be backed to always with advancing layer by layer, thus it is raw to complete interval chemical industry
Produce the actual adaptive prediction controller of Process Control SystemDesign.Each Virtual ControllerWith actual controllerBag
Include following 4 parts: 1. in order to the neutral net of Parametric System unknown function；2. adaptive line controller；3. supervise
Superintend and direct agency(i.e. switching function), when system produces unusual, is used for temporarily transferring control to the 4. robust controller；4. robust
Controller；The Liapunov type adaptive law that backstepping is mentioned with the C1 in design procedure (3) is used in combination,
Consider controllerAnd adaptive law, make whole system meet desired system dynamically and static performance index.C3, mixing
Adaptive neural network Design of Predictive, the Virtual Controller further above-mentioned steps C2 obtainedAdaptive with actual
Answer controller, use following mixed form to be designed as:,For switching function, native system has
Two kinds of working methods, i.e. step (3) include for adaptive line controllerAnd robust controller.Work as existence
When model parameter is uncertain, select adaptive line controller, uncertain for compensating parameter, and when interference exists
Time, select robust controller, it is used for resisting the external disturbance suffered by system.
Step (4) control algolithm realizes including: system by data collecting system based on DCS and KingView software as upper
The data of position machine software process and display system is constituted, KingView software support DDE technology simultaneously, can be by DDE agreement by group
State king and Matlab carry out data exchange, it is achieved complicated hybrid intelligent adaptive prediction control algolithm.And by substantial amounts of reality
Time simulating, verifying design controller effectiveness, and by part application of result in reality.
The present invention makes full use of the control theory of advanced person, neutral net, system identification, intelligent algorithm etc., to interval chemical industry
Production process realization detects, controls, models, manages, dispatches and decision-making, designs a kind of key for interval chemical process
The modeling of technological parameter and control, for the distinctive control method of cascade system, i.e. based on Backstepping batch production process mixes
Close intelligent adaptive Predictive control design scheme, use this hybrid intelligent adaptive prediction control method, can be according to environmental condition
Change and correspondingly change the parameter of controller, to adapt to the change of its characteristic, robust control opposing external disturbance can be carried out again,
Ensure that stable operation and the performance indications of whole system reach requirement, thus reduce energy consumption, reduce cost, increase economic efficiency
The integrated technology of purpose.Thus the present invention proposes by carrying out simulation study, and part achievement in research is applied to reality
In the interval Chemical Manufacture of border, improve and control quality.
The operation principle of the present invention is by the analysis to interval chemical process, with black-box modeling principle, application
System structure and neural net model establishing algorithm, according to the historical data of interval chemical process, set up interval Chemical Manufacture mistake
The nonlinear model of journey, according to the model set up, design hybrid intelligent adaptive prediction controls, and output controlled quentity controlled variable controls execution machine
Structure action, it is achieved the PREDICTIVE CONTROL to interval chemical process.
Claims (2)
1. the forecast Control Algorithm of mixed self-adapting Predictive Control System based on Backstepping,
Described system includes interval Chemical Manufacture object, data acquisition channel, neural network identification module, self-adaptive controlled molding
Block, model library；The outfan of described interval Chemical Manufacture object is defeated by data acquisition channel and neural network identification module
Enter end to connect, the outfan of neural network identification module respectively with input and the input of model library of self-adaptive control module
Connecting, the outfan of model library is connected with the input of self-adaptive control module, and the outfan of self-adaptive control module is by number
It is connected according to the input of acquisition channel with interval Chemical Manufacture object；Described neural network identification module includes neural net model establishing
Module, model emulation module, model editing module；The outfan of described data acquisition channel defeated with model emulation module respectively
The input entering end and neural net model establishing module connects, and the outfan of model emulation module is defeated with neural net model establishing module
Enter end to connect；The outfan of neural net model establishing module connects with the input of model editing module and the input of model library respectively
Connect；Described data acquisition channel includes acquisition module and the data preprocessing module being sequentially connected with；
Described method specifically includes following steps:
(1) process parameter value of data acquisition channel Real-time Collection interval chemical process, carries out data prediction；
Step (1) including: in bottom application DDE technology, OPC technology and API HOOK technology, remote process Data Interchange Technology
As data source adapter, realizing unified interface for different DCS system platforms, adapter that structure is similar, each is adaptive
Device uses unified, and message based communications protocol carries out data exchange with one-level central server；Primary centre server is again
Data are further encapsulated, screened, compressed, and require to be forwarded to upper level center according to the time response of upper layer application
Server, or it is supplied directly to the various application that this layer is mounted, the central server of the most each level is mounted together
Data interaction between application；
(2) data after processing pass to neural network identifier, neural network identifier be modeled, the model after modeling
Through simulation modification；
Step (2) specifically includes following steps:
The data founding mathematical models that B1, the modeling foundation of neural network identification module are obtained, it is considered to intermittently Chemical Manufacture mistake
Journey series production, the output of the most last workshop section is the input quantity of next workshop section, then considers batch process is modeled as allusion quotation
The cascade system of type；For production process easily by environmental influence, batch process is difficult to model and procedure parameter is uncertain, can
Consider batch process is regarded as the lower triangle cascade system with the combination of linear processes uncertain part, utilize neutral net
There is the ability of approximating function, it is considered to the model of neural net model establishing non-linear partial；Meanwhile, model emulation module utilizes and obtains
The model that neural net model establishing is set up by the data obtained carries out validation verification；
The nonlinear model that neural net model establishing module is set up by B2, model editing module according to simulation result is modified；
Model data store is entered in model library by B3, neural net model establishing module；
(3) Intelligent Hybrid adaptive prediction controller reading model parameter, generates and controls parameter, controls actuator action；
Step (3) specifically includes following steps:
C1, Backstepping Controller according to each layer of cascade system modelling, can be simultaneously according to system stability analysis, Li Yapu
Promise husband's functionDesign adaptive rate, i.e. neutral net weight parameter are estimated；
The design of C2, adaptive prediction controller is the feature of cascade structure according to interval chemical process control system model,
Consider to use Backstepping that complicated nonlinear system is resolved into several subsystems, separately design Li Yapu for each subsystem
Promise husband's function and intermediate virtual controller αi, advance ground to back to whole system layer by layer always, thus complete interval Chemical Manufacture
The actual adaptive prediction controller u design of Process Control System；
C3, mixed self-adapting network response surface device design, Virtual Controller α above-mentioned steps C2 obtained furtheriWith
Actual adaptive controller u, uses following mixed form to be designed as:SiFor switching function,
Native system have that two kinds of working methods, i.e. step (3) include for adaptive line controller αi a,uaWith robust controller αi r,ur；
(4) control algolithm realizes.
The forecast Control Algorithm of mixed self-adapting Predictive Control System based on Backstepping the most according to claim 1, its
It is characterised by: described step (2) including: the modeling of neural network identifier is according to the data founding mathematical models obtained, same
Time, the model that model emulation device utilizes the data obtained to set up neural net model establishing carries out validation verification；Model editing mould
The nonlinear model that neural net model establishing module is set up by block according to simulation result is modified；Neural net model establishing module is by mould
Type data are stored in model library.
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 CN103336433A (en) | 2013-10-02 |
| CN103336433B true 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) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| CN109254531B (en) * | 2017-11-29 | 2021-10-22 | 辽宁石油化工大学 | Method for optimal cost control of a multi-stage batch process with time lag and disturbances |
| CN109634116B (en) * | 2018-09-04 | 2022-03-15 | 贵州大学 | Acceleration self-adaptive stabilizing method of fractional order mechanical centrifugal speed regulator system |
| 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 |
| CN112934142B (en) * | 2021-02-01 | 2023-06-06 | 山东大学 | Homogeneous tubular reactor temperature control method and system based on back-stepping method |
| CN113435067B (en) * | 2021-08-26 | 2022-02-18 | 阿里云计算有限公司 | Data processing system and method |
| CN114326405B (en) * | 2021-12-30 | 2023-04-07 | 哈尔滨工业大学 | Neural network backstepping control method based on error training |
Citations (4)
| 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 |
| 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 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
-
2013
- 2013-04-25 CN CN201310145805.0A patent/CN103336433B/en active Active
Patent Citations (4)
| 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 |
| 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 |
|---|
| 间歇化工反应器的先进控制技术;孙小方等;《化工纵横》;20121130(第11期);第1-5页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103336433A (en) | 2013-10-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103336433B (en) | Mixed self-adapting Predictive Control System based on Backstepping and forecast Control Algorithm thereof | |
| CN103268069B (en) | Based on the adaptive prediction control method of Hammerstein model | |
| Li et al. | Data-driven hybrid petri-net based energy consumption behaviour modelling for digital twin of energy-efficient manufacturing system | |
| Bleicher et al. | Co-simulation environment for optimizing energy efficiency in production systems | |
| Cordeiro et al. | Theoretical proposal of steps for the implementation of the Industry 4.0 concept | |
| Hosseinpour et al. | Importance of simulation in manufacturing | |
| CN105302096B (en) | Intelligent factory scheduling method | |
| Torregrossa et al. | Optimization models to save energy and enlarge the operational life of water pumping systems | |
| US20120239164A1 (en) | Graphical language for optimization and use | |
| Yao et al. | A multi-objective dynamic scheduling approach using multiple attribute decision making in semiconductor manufacturing | |
| CN103440368A (en) | Multi-model dynamic soft measuring modeling method | |
| CN101619850A (en) | Dispatching method and dispatching system based on load online forecasting of thermoelectric power system | |
| CN1694109B (en) | Material data correction method in chemical and oil refinement process | |
| Li et al. | Sustainability Cockpit: An integrated tool for continuous assessment and improvement of sustainability in manufacturing | |
| CN105103059A (en) | System and method for implementing model predictive control in PLC | |
| CN103914594A (en) | Concrete thermodynamic parameter intelligent recognition method based on support vector machine | |
| Omar et al. | A hybrid simulation approach for predicting energy flows in production lines | |
| Cao et al. | Multi-level energy efficiency evaluation for die casting workshop based on fog-cloud computing | |
| Forestier--Coste et al. | Data-fitted second-order macroscopic production models | |
| Hatchett et al. | Real-time distribution system modeling: Development, application, and insights | |
| Pistikopoulos et al. | Towards the integration of process design, control and scheduling: Are we getting closer? | |
| KR20120133362A (en) | Optimized production scheduling system using loading simulation engine with dynamic feedback scheduling algorithm | |
| CN117484545A (en) | Intelligent multifunctional manipulator test platform system and test method | |
| Teslyuk et al. | Methods for the Efficient Energy Management in a Smart Mini Greenhouse. | |
| Zhao et al. | A dynamic process adjustment method based on residual prediction for quality improvement |
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 |
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 |
|
| TR01 | Transfer of patent right |