CN113406940A - Intelligent drainage grading real-time control method based on model predictive control - Google Patents
Intelligent drainage grading real-time control method based on model predictive control Download PDFInfo
- Publication number
- CN113406940A CN113406940A CN202110858448.7A CN202110858448A CN113406940A CN 113406940 A CN113406940 A CN 113406940A CN 202110858448 A CN202110858448 A CN 202110858448A CN 113406940 A CN113406940 A CN 113406940A
- Authority
- CN
- China
- Prior art keywords
- control
- model
- time
- real
- drainage
- 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 43
- 238000011217 control strategy Methods 0.000 claims abstract description 36
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 34
- 238000005457 optimization Methods 0.000 claims abstract description 31
- 238000004364 calculation method Methods 0.000 claims abstract description 16
- 238000004088 simulation Methods 0.000 claims abstract description 13
- 238000013136 deep learning model Methods 0.000 claims abstract description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 27
- 230000008569 process Effects 0.000 claims description 22
- 239000010865 sewage Substances 0.000 claims description 13
- 230000007246 mechanism Effects 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 5
- 230000008878 coupling Effects 0.000 abstract description 3
- 238000010168 coupling process Methods 0.000 abstract description 3
- 238000005859 coupling reaction Methods 0.000 abstract description 3
- 238000003860 storage Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003449 preventive effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Images
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
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32404—Scada supervisory control and data acquisition
-
- 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]
Abstract
The invention discloses an intelligent drainage grading real-time control method based on model predictive control, which relates to the technical field of drainage grading control and comprises the following steps: the method comprises the steps of building a hydraulic model in advance, calibrating the hydraulic model, carrying out piecewise linearization on the hydraulic model, building a meteorological operation data deep learning model, building a historical meteorological data and drainage system operation data correlation model, calibrating a control strategy, calibrating a control instruction set optimization algorithm and issuing an optimal control instruction set. The invention realizes real-time updating and continuous accurate calculation of the model, and enables a real-time control system to ensure the simulation accuracy of the hydraulic model based on a coupling mode of a linearized control strategy and an optimization algorithm, deeply learn and refine the control strategy of the drainage system through historical data, and find an optimal control instruction group under the control time step length so as to realize real-time control of the drainage system.
Description
Technical Field
The invention relates to the technical field of drainage grading control, in particular to an intelligent drainage grading real-time control method based on model predictive control.
Background
In 2018, the length of a municipal drainage pipe network in China reaches 68.3 kilometers, sewage plants are about 4000 seats, and under the dual pressure of facing water environment and water safety in rainy seasons, how to improve the reliability, elasticity and sustainability of a municipal drainage system is increasingly important for guaranteeing the safety of a municipal water system. The urban drainage system has the characteristics of dynamic property, multiple target property and uncertainty, and from the aspect of basin-oriented treatment, under the multi-target coordination of further reducing combined system overflow pollution, giving full play to the capacity of 'source-process-tail end' of the drainage system and the like, the operation control of the system is increasingly complex and the control difficulty is increasingly increased.
The current dispatching control applied in the urban drainage industry is divided into dispatching control based on experience rules and dispatching control based on target feedback, which belong to post-event compensation control and passive control modes, early prediction control and hierarchical strategy control are not realized, CSO preventive control, urban waterlogging preventive control and sewage plant-storage facility global optimization operation regulation and control cannot be carried out on an urban drainage system, and even if real-time calculation application based on a physical model exists, the time consumption in actual production application is long due to the fact that no physical model and optimization control algorithm are optimized and no dispatching strategy is established, and production operation cannot be actually guided.
An effective solution to the problems in the related art has not been proposed yet.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides an intelligent drainage grading real-time control method based on model predictive control,
the method combines a drainage physical model and a data analysis deep learning model, realizes the high-efficiency operation of the drainage physical model and the data analysis deep learning model through model optimization, solves the automatic generation of a drainage system grading control strategy and the prediction issuing of an optimal real-time control instruction through an optimization algorithm, and realizes the full-automatic real-time control of the drainage system
To overcome the above technical problems of the related art.
The technical scheme of the invention is realized as follows:
an intelligent drainage grading real-time control method based on model predictive control comprises the following steps:
step S1, building a hydraulic model in advance, calibrating the model and carrying out hydraulic model piecewise linearization, wherein the method comprises the steps of screening a core area for simulation and generalizing a complex hydraulic model in a piecewise linearization manner;
step S2, building a meteorological operation data deep learning model, building a historical meteorological data and drainage system operation data correlation model, and calibrating a control strategy;
step S3, calibrating a control instruction set optimizing algorithm, including setting each actuator within the duration of the control range for each control time step of each actuator;
step S4, issuing an optimal control instruction group, receiving the optimal control instruction issued by the optimization algorithm by the executing mechanism, and executing the instruction of the next control time step at the current moment by the executing mechanism;
and step S5, updating the physical model in real time and the process model, including transmitting the operation result of each step of the simulation step length to the process model as a hot start file of the process model.
Further, the meteorological data rainfall hydrological data and the drainage system operation data comprise an waterlogging event, a ponding event, an overflow event, a water quality event and operation data of a sewage plant.
Further, the control strategy includes: the control strategy of dry days and light rain is to ensure the constant water inflow of the sewage plant and maximize the treatment efficiency; the control strategy of heavy rain is to overflow the water body with better water quality preferentially; the control strategy of the rainstorm is to overflow the water body with better water quality preferentially.
Further, the calibration control strategy further comprises the following steps;
calibrating a target function, evaluating the effectiveness of the control rule and determining an optimal control instruction group of the drainage system within a prediction time range;
performing an optimization algorithm to generate an operation instruction group, comprising: and substituting the updated process model into the instruction group and the rainfall prediction data for operation, and evaluating the optimal control instruction group under the current control strategy by an optimization algorithm according to the calculation result.
Further, the optimizing algorithm is represented as:
MIN(Z)＝∑a(b·d(u,x))
wherein, the deviation weight a is a scalar quantity and represents the weight proportion occupied by one type of deviation in the deviation of the whole drainage system, the individual deviation coefficient b represents the weight occupied by the deviation of a calculated value and a target value, the overall deviation coefficient d represents the weight occupied by the absolute average value of the individual deviation, the control instruction group u represents the control instruction under each time step, and the system state x represents the simulation result of the control point under each time step.
Furthermore, the process model updating comprises reading the hot start file to perform prediction operation, and the prediction operation is used as a judgment basis for the optimization algorithm to search the optimal control instruction group.
The invention has the beneficial effects that:
the invention relates to an intelligent drainage grading real-time control method based on model prediction control, which comprises the steps of building a hydraulic model in advance, calibrating the model, carrying out hydraulic model piecewise linearization, building a meteorological operation data deep learning model, building a historical meteorological data and drainage system operation data correlation model, calibrating a control strategy, calibrating a control instruction group optimization algorithm, issuing an optimal control instruction group, receiving an optimal control instruction issued by the optimization algorithm by an executing mechanism, executing the instruction of the next control time step length at the current moment only by the executing mechanism, carrying out physical model real-time updating and process model updating, realizing hydraulic model piecewise linearization, improving the operation efficiency and the calculation speed of model prediction on the premise of ensuring the accuracy, updating the process model in a hot start file manner, realizing the real-time updating of the model, realizing the piecewise linearization of the model, and realizing the control of the water drainage system, Continuous and accurate calculation, and a coupling mode of a control strategy based on linearization and an optimization algorithm ensures that the real-time control system can not only ensure the simulation accuracy of the hydraulic model, but also deeply learn and refine the control strategy of the drainage system through historical data, and can find an optimal control instruction group under the control time step length, thereby realizing the real-time control of the drainage system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for intelligent drainage classification real-time control based on model predictive control according to an embodiment of the invention;
fig. 2 is a scene schematic diagram of an intelligent drainage classification real-time control method based on model predictive control according to an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present invention.
According to the embodiment of the invention, an intelligent drainage grading real-time control method based on model predictive control is provided.
As shown in fig. 1, according to the intelligent drainage classification Real-Time Control method based on model predictive Control in the embodiment of the present invention, a Real-Time Control (RTC) technology dynamically adjusts a Control strategy according to Real-Time monitoring data, intervenes in an auxiliary facility of a drainage pipe network and a sewage treatment plant, so as to maximally submerge and exert storage regulation and treatment capabilities of the drainage facility, thereby providing an intelligent solution for operation of a drainage system.
For the RTC, real-time control (RTC) is an advanced stage of intelligent drainage, and it is generally considered that the real-time control of the drainage system is: in the running process of the drainage system, important process variables (rainfall, liquid level, flow, water quality and the like) are monitored on line, a control strategy is dynamically adjusted according to monitoring data and an on-line model, and real-time intervention is performed on the running of drainage facilities and a sewage treatment plant through control equipment (actuators such as a valve, a water pump and the like), so that the optimal capacity matching of a plant-network, a plant-network and a river is realized, and the optimal control mode of the running efficiency of the whole drainage system is further improved.
In addition, specifically, the method comprises the following steps:
as shown in fig. 2, constructing a hydraulic model and calibrating the model;
and carrying out piecewise linearization on the hydraulic model, wherein the piecewise linearization comprises selecting a core area for simulation, generalizing the complex hydraulic model in a piecewise linearization mode for an area with a complex hydraulic model on the premise of ensuring the reliability of the model, and calculating a part of models by using a piecewise linear equation set in simulation calculation. Therefore, the accuracy of the hydraulic model as a physical model and a process model during operation is ensured, the operation efficiency is greatly improved, and the normal operation of real-time control is ensured.
Building a meteorological operation data deep learning model, building a historical meteorological data and drainage system operation data correlation model, and automatically defining a control strategy through a data deep learning and analysis model system; the meteorological data comprises the hydrological data such as rainfall and the like, and the operation data of the drainage system comprises the operation data of waterlogging events, ponding events, overflow events, water quality events and sewage plants.
Specifically, the control strategy is as follows: the real-time control strategy is a control strategy based on a deep learning model, and generally comprises four scenes of operation of a drainage system: dry weather, light rain, heavy rain, and heavy rain. The control strategy of the dry weather and the light rain is ' no overflow of a plant network ', the constant water inflow of a sewage plant is ensured, the treatment efficiency is maximized ', the control strategy of the heavy rain is ' less overflow of the pipe network, no overflow of the sewage plant and the water body with better preferential overflow water quality ', the control strategy of the heavy rain is ' both overflow of the pipe network and the sewage plant and the water body with better preferential overflow water quality ', and the drainage systems under different meteorological conditions are comprehensively managed. Each set of control strategy corresponds to different control instruction set optimization algorithms.
An objective function: the objective function expression is used for evaluating the effectiveness of the control rule and determining an optimal control instruction set of the drainage system within a prediction time range. The operation indexes concerned by different control strategies are different, for example, dry weather and light rain are concerned about 'stable operation of sewage plants', heavy rain and heavy rain are concerned about overflow amount, overflow times, overflow time, overflow water quality, target water depth of water storage facilities and the like. In each prediction calculation, an optimization algorithm generates an operation instruction group, the updated process model is substituted into the instruction group and the rainfall prediction data for calculation, and finally the optimization algorithm evaluates and selects the optimal control instruction group under the current control strategy according to the calculation result; in order to ensure timeliness of real-time control, the optimization algorithm cannot be endlessly calculated, the system specifies algebra of the genetic algorithm, and does not carry out calculation exceeding the specified algebra, or when the control instruction group is found in advance before the last generation, the optimization algorithm also stops calculation, and the real-time control can be executed most effectively.
Wherein, the optimizing algorithm is expressed as: min (z) ═ Σ a (b · d (u, x)), where deviation weight a is a scalar quantity, representing the proportion of weight that one type of deviation occupies in the entire drainage system deviation, and the sum of all deviation weights should be 1; the individual deviation coefficient b is a one-dimensional vector and represents the weight occupied by the deviation of the calculated value and the target value; the overall deviation coefficient d is a one-dimensional vector and represents the weight occupied by the absolute average value of the individual deviation; the control instruction group u is a two-dimensional vector and represents a control instruction at each time step; the system state x is a two-dimensional vector representing the simulation results for the control points at each time step.
In addition, the optimization algorithm of the calibration control instruction group is as follows: according to the objective function, the system can adopt an optimizer algorithm execution mechanism to comprise equipment and facilities of the drainage system, such as valves, pumps, adjustable weirs and the like, which need to be operated in real time; for each control time step of each actuator, the setting for each actuator is made for the duration of the control range (the time the system is affected by the control command most upstream). The single setting can be a number, such as the opening and closing (0/1) of a pump, or the opening percentage (0-100%) of the valve, the valve opening is quantized to a limited value according to the control precision, and the operation efficiency of real-time control is effectively improved.
In addition, an optimal control instruction group is issued: after the calculation of the optimization algorithm is finished, the execution mechanism receives an optimal control command issued by the optimization algorithm, and only executes the command of the next control time step at the current moment, but not all prediction commands, because only the control commands of the first steps usually have great influence on the prediction result, the problem that the drainage system cannot normally run due to inaccurate prediction of the rear part result is avoided.
In addition, real-time updating of the physical model is performed: the physical model is a real mapping of the drainage system, substitutes the optimal control instruction issued to the executing mechanism and the SCADA data of the drainage system for calculation, ensures that the physical model is updated on line, and transmits the operation result of each step of the simulation step length to the process model as a hot start file of the process model.
In addition, process model updates are performed: in the time step length calculated by each drainage system physical model, at least one process model reads a hot start file for prediction operation, and the hot start file is used as a judgment basis for an optimization algorithm to search an optimal control instruction group.
In summary, according to the technical scheme of the invention, the hydraulic model is built in advance, the calibration model and the hydraulic model are subjected to piecewise linearization, the meteorological operation data deep learning model is built, the historical meteorological data and drainage system operation data correlation model is built, the control strategy is calibrated, the control instruction group optimization algorithm is calibrated, the optimal control instruction group is issued, the execution mechanism receives the optimal control instruction issued by the optimization algorithm, the execution mechanism only executes the instruction of the next control time step at the current moment, the physical model is updated in real time and the process model is updated in real time, the piecewise linearization of the hydraulic model is realized, the operation efficiency and the calculation speed of model prediction are improved on the premise of ensuring the accuracy, the process model is updated in a hot start file manner, and the real-time updating, the segmentation linearization and the optimization of the model are realized, Continuous and accurate calculation, and a coupling mode of a control strategy based on linearization and an optimization algorithm ensures that the real-time control system can not only ensure the simulation accuracy of the hydraulic model, but also deeply learn and refine the control strategy of the drainage system through historical data, and can find an optimal control instruction group under the control time step length, thereby realizing the real-time control of the drainage system.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (6)
1. An intelligent drainage grading real-time control method based on model predictive control is characterized by comprising the following steps:
building a hydraulic model in advance, calibrating the model and carrying out hydraulic model piecewise linearization, wherein the core region is screened for simulation, and the complicated hydraulic model is generalized in a piecewise linearization manner;
building a meteorological operation data deep learning model, building a historical meteorological data and drainage system operation data correlation model, and calibrating a control strategy;
calibrating a control instruction set optimization algorithm, including setting each actuator within the duration of a control range for each control time step of each actuator;
issuing an optimal control instruction group, receiving the issued optimal control instruction from the optimization algorithm by the executing mechanism, and executing the instruction of the next control time step length at the current moment by the executing mechanism;
and (4) updating the physical model in real time and the process model, wherein the step of updating the simulation step length comprises the step of transmitting the operation result of each step to the process model to be used as a hot start file of the process model.
2. The intelligent drainage classification real-time control method based on model predictive control according to claim 1, wherein the meteorological data rainfall hydrological data and the drainage system operation data comprise waterlogging events, ponding events, overflow events, water quality events and sewage plant operation data.
3. The intelligent drainage classification real-time control method based on model predictive control according to claim 2, wherein the control strategy comprises: the control strategy of dry days and light rain is to ensure the constant water inflow of the sewage plant and maximize the treatment efficiency; the control strategy of heavy rain is to overflow the water body with better water quality preferentially; the control strategy of the rainstorm is to overflow the water body with better water quality preferentially.
4. The intelligent drainage classification real-time control method based on model predictive control according to claim 3, wherein the calibration control strategy further comprises the following steps;
calibrating a target function, evaluating the effectiveness of the control rule and determining an optimal control instruction group of the drainage system within a prediction time range;
performing an optimization algorithm to generate an operation instruction group, comprising: and substituting the updated process model into the instruction group and the rainfall prediction data for operation, and evaluating the optimal control instruction group under the current control strategy by an optimization algorithm according to the calculation result.
5. The intelligent drainage classification real-time control method based on model predictive control according to claim 4, characterized in that the optimizing algorithm is expressed as:
MIN(Z)＝∑a(b·d(u,x))
the deviation weight a is a scalar quantity and represents the weight proportion occupied by one type of deviation in the deviation of the whole drainage system, the individual deviation coefficient b represents the weight occupied by the deviation of a calculated value and a target value, the overall deviation coefficient d represents the weight occupied by the absolute average value of the individual deviation, the control instruction group u represents a control instruction under each time step, and the system state x represents the simulation result of a control point under each time step.
6. The intelligent drainage classification real-time control method based on model predictive control as claimed in claim 5, wherein the process model updating comprises reading a hot start file to perform a predictive operation as a judgment basis for an optimization algorithm to search for an optimal control instruction group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110858448.7A CN113406940A (en) | 2021-07-28 | 2021-07-28 | Intelligent drainage grading real-time control method based on model predictive control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110858448.7A CN113406940A (en) | 2021-07-28 | 2021-07-28 | Intelligent drainage grading real-time control method based on model predictive control |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113406940A true CN113406940A (en) | 2021-09-17 |
Family
ID=77687960
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110858448.7A Pending CN113406940A (en) | 2021-07-28 | 2021-07-28 | Intelligent drainage grading real-time control method based on model predictive control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113406940A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1760912A (en) * | 2005-11-11 | 2006-04-19 | 杭州电子科技大学 | Modeling method of uncertain hydraulics model for urban seweage and drainage system |
| CN105139147A (en) * | 2015-09-18 | 2015-12-09 | 北京北变微电网技术有限公司 | Economic scheduling method for micro-grid system |
| CN107958129A (en) * | 2018-01-02 | 2018-04-24 | 清华大学 | Simulate the algorithm of the microcosmic CURRENT DISTRIBUTION of Zinc-oxide piezoresistor |
| CN110570126A (en) * | 2019-09-11 | 2019-12-13 | 福州大学 | Real-time scheduling method of rainwater storage facility based on real-time meteorological information |
| CN111880431A (en) * | 2020-06-19 | 2020-11-03 | 中国市政工程华北设计研究总院有限公司 | Comprehensive urban drainage system joint scheduling real-time simulation control method and system |
| CN112596386A (en) * | 2020-12-14 | 2021-04-02 | 中国市政工程华北设计研究总院有限公司 | Matlab-based urban drainage system simulation control mixed model with mechanism model, concept model and data model |
| CN112799310A (en) * | 2020-12-14 | 2021-05-14 | 中国市政工程华北设计研究总院有限公司 | Method for urban drainage system simulation control mixed model based on mechanism model, concept model and data model of C language |
| CN112989538A (en) * | 2021-03-30 | 2021-06-18 | 清华大学 | Control method and control device for urban drainage system |
-
2021
- 2021-07-28 CN CN202110858448.7A patent/CN113406940A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1760912A (en) * | 2005-11-11 | 2006-04-19 | 杭州电子科技大学 | Modeling method of uncertain hydraulics model for urban seweage and drainage system |
| CN105139147A (en) * | 2015-09-18 | 2015-12-09 | 北京北变微电网技术有限公司 | Economic scheduling method for micro-grid system |
| CN107958129A (en) * | 2018-01-02 | 2018-04-24 | 清华大学 | Simulate the algorithm of the microcosmic CURRENT DISTRIBUTION of Zinc-oxide piezoresistor |
| CN110570126A (en) * | 2019-09-11 | 2019-12-13 | 福州大学 | Real-time scheduling method of rainwater storage facility based on real-time meteorological information |
| CN111880431A (en) * | 2020-06-19 | 2020-11-03 | 中国市政工程华北设计研究总院有限公司 | Comprehensive urban drainage system joint scheduling real-time simulation control method and system |
| CN112596386A (en) * | 2020-12-14 | 2021-04-02 | 中国市政工程华北设计研究总院有限公司 | Matlab-based urban drainage system simulation control mixed model with mechanism model, concept model and data model |
| CN112799310A (en) * | 2020-12-14 | 2021-05-14 | 中国市政工程华北设计研究总院有限公司 | Method for urban drainage system simulation control mixed model based on mechanism model, concept model and data model of C language |
| CN112989538A (en) * | 2021-03-30 | 2021-06-18 | 清华大学 | Control method and control device for urban drainage system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1312629C (en) | Modeling method of uncertain hydraulics model for urban seweage and drainage system | |
| CN102183972B (en) | Method for controlling water level of reservoir of urban drainage system | |
| CN112288164B (en) | Wind power combined prediction method considering spatial correlation and correcting numerical weather forecast | |
| CN108764515A (en) | A kind of reservoir operation Application of risk decision method of Coupled Numerical meteorological model DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM | |
| CN101807045B (en) | Data-based urban sewage pumping station system modeling method | |
| CN112068420A (en) | Real-time control method and device for drainage system | |
| CN113190945B (en) | Urban drainage pipe network optimization method based on online agent model assisted evolution algorithm | |
| CN111880431A (en) | Comprehensive urban drainage system joint scheduling real-time simulation control method and system | |
| CN114792071B (en) | Drainage pump station optimal scheduling method based on machine learning technology | |
| CN112596386A (en) | Matlab-based urban drainage system simulation control mixed model with mechanism model, concept model and data model | |
| CN112799310A (en) | Method for urban drainage system simulation control mixed model based on mechanism model, concept model and data model of C language | |
| CN114357716A (en) | Basin hydrological model parameter dynamic estimation method based on digital twinning technology | |
| CN113050430A (en) | Drainage system control method based on robust reinforcement learning | |
| CN114417631B (en) | Modeling method of infusion area water delivery and distribution system based on observation data | |
| CN114415520B (en) | Full-canal system self-adaptive predictive control method for water networking irrigation areas | |
| CN112113146A (en) | Synchronous self-adaptive check method for roughness coefficient and node water demand of water supply pipe network pipeline | |
| CN115755219A (en) | Flood forecast error real-time correction method and system based on STGCN | |
| CN106200381A (en) | A kind of according to processing the method that water yield control by stages water factory runs | |
| CN113406940A (en) | Intelligent drainage grading real-time control method based on model predictive control | |
| CN104615161A (en) | Liquid level control method of dual-loop water tank based on model prediction | |
| CN115221711B (en) | Accurate calculation method and device for irrigation water consumption suitable for embedded equipment | |
| CN105334730A (en) | Heating furnace oxygen content IGA optimization T-S fuzzy ARX modeling method | |
| KR101859109B1 (en) | Control methods of low impact development facilities using rainfall forecasting | |
| Puig et al. | Optimal predictive control of water transport systems: Arrêt-darré/arros case study | |
| Xie et al. | Irrigation prediction model with BP neural network improved by genetic algorithm in orchards |
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 |