CN117348614A - Intelligent reservoir dispatching system - Google Patents
Intelligent reservoir dispatching system Download PDFInfo
- Publication number
- CN117348614A CN117348614A CN202311378925.5A CN202311378925A CN117348614A CN 117348614 A CN117348614 A CN 117348614A CN 202311378925 A CN202311378925 A CN 202311378925A CN 117348614 A CN117348614 A CN 117348614A
- Authority
- CN
- China
- Prior art keywords
- reservoir
- curve
- level height
- identification
- water level
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 408
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000006243 chemical reaction Methods 0.000 claims abstract description 28
- 238000012544 monitoring process Methods 0.000 claims abstract description 24
- 230000008859 change Effects 0.000 claims description 36
- 238000005070 sampling Methods 0.000 claims description 25
- 238000013519 translation Methods 0.000 claims description 21
- 230000001105 regulatory effect Effects 0.000 claims description 10
- 238000013480 data collection Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 5
- 238000006467 substitution reaction Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000004393 prognosis Methods 0.000 claims 1
- 238000009825 accumulation Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003973 irrigation Methods 0.000 description 2
- 230000002262 irrigation Effects 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009372 pisciculture Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D9/00—Level control, e.g. controlling quantity of material stored in vessel
- G05D9/12—Level control, e.g. controlling quantity of material stored in vessel characterised by the use of electric means
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses an intelligent reservoir dispatching system, which relates to the technical field of air conditioners and comprises the following components: establishing a regulation and control prejudging model, establishing a regulation and control reaction model and establishing a flow velocity compensation model; the method comprises the steps of monitoring the water level height in the reservoir and the water level height outside the reservoir in real time, and monitoring the water source quality in the reservoir and the water source quality outside the reservoir in real time; the central controller predicts a predicted value of the water level height in the reservoir and a predicted value of the water source quality in the reservoir after one minute according to the regulation and control pre-judging model, and sets the parameters of the dispatching system by using a regulation and control reaction model; the actual water outlet speed is monitored in real time, parameters of the dispatching system are adjusted according to the flow rate compensation model, the output power of the dispatching system is changed, and the actual water outlet speed is adjusted to a flow rate preset value. By arranging the model building module, the real-time monitoring module, the parameter regulation and control module and the flow rate compensation module, no delay exists, and the adjustment of the water source in the reservoir is not needed to wait.
Description
Technical Field
The invention relates to the technical field of water conservancy, in particular to an intelligent reservoir dispatching system.
Background
Reservoirs, commonly referred to as "hydraulic engineering structures for flood control and water storage and regulation, can be utilized for irrigation, power generation, flood control and fish farming. "it means an artificial lake formed by constructing a dam at the slit of a mountain ditch or river. After the reservoir is built, the effects of flood control, water storage irrigation, water supply, power generation, fish culture and the like can be achieved. Sometimes natural lakes are also called reservoirs. Reservoir sizes are generally divided into small, medium and large sizes according to reservoir capacity.
However, the existing scheduling system has delay in regulation and control, namely, real-time water sources are scheduled, a small period of time is required to be spent, so that the water sources in the reservoirs can reach target values, the water sources in the reservoirs cannot be predicted according to the current water sources in the reservoirs, the water sources in the reservoirs are adjusted in advance, in addition, the water outlet speed of a filter screen of a water outlet is slower and slower due to accumulation of sundries, and the actual output flow rate of the scheduling system is smaller than the flow rate set by parameters, so that scheduling errors occur.
Disclosure of Invention
In order to solve the technical problem, the intelligent reservoir dispatching system is provided, the problem that the existing dispatching system is delayed in regulation and control, namely, real-time water sources are dispatched, a short period of time is required to be required to enable the water sources in the reservoirs to reach target values, the water sources in the reservoirs cannot be predicted according to the current water sources in the reservoirs, the water sources in the reservoirs cannot be adjusted in advance, in addition, the water outlet speed of a filter screen of a water outlet is slower and slower due to accumulation of sundries, and the actual output flow speed of the dispatching system is smaller than the flow speed of parameter setting, so that errors occur in dispatching is solved.
In order to achieve the above purpose, the invention adopts the following technical scheme:
an intelligent reservoir dispatching system, comprising:
the model building module builds a regulation and control pre-judging model, collects data to obtain a regulation and control reaction database, stores predicted values of different water level heights in the reservoir, predicted values of water source quality in the reservoir, predicted values of water level height outside the reservoir, predicted values of water source quality outside the reservoir, target values of water level height in the reservoir and target values of water source quality in the reservoir, builds a regulation and control reaction model according to the regulation and control reaction database, and builds a flow rate compensation model;
the real-time monitoring module is used for monitoring the water level height in the reservoir and the water level height outside the reservoir in real time, collecting monitoring data of the water level height in the reservoir and the water level height outside the reservoir, monitoring the water source quality in the reservoir and the water source quality outside the reservoir in real time, and collecting monitoring data of the water source quality in the reservoir and the water source quality outside the reservoir;
the parameter regulation and control module drives the central controller to predict a predicted value of the water level height in the reservoir and a predicted value of the water source quality in the reservoir after one minute according to the regulation and control pre-judgment model, predicts a predicted value of the water level height outside the reservoir and a predicted value of the water source quality outside the reservoir after one minute, uses a regulation and control reaction model according to the predicted value and a set target value after one minute, sets a dispatching system parameter, corrects the water level height of the water source entering the reservoir and the water source quality value, and the dispatching system parameter comprises a flow speed preset value, a water level height correction value and a water source quality correction value;
the flow rate compensation module is used for monitoring the actual water outlet speed in real time at the water outlet position of the filter screen, adjusting parameters of the dispatching system according to the flow rate compensation model, changing the output power of the dispatching system and adjusting the actual water outlet speed to a flow rate preset value.
Preferably, the establishing the regulation and control prejudging model includes the following steps:
the regulation and control prejudging model comprises a water level height prejudging model and a water source quality prejudging model;
the water level height pre-judging model comprises a reservoir inner water level height prediction model and a reservoir outer water level height prediction model;
the method for establishing the prediction model of the water level height in the reservoir comprises the following steps:
at least one continuous change curve of the water level height in the big data collection reservoir along with the time change is summarized, and all the continuous change curves are a first water level height curve;
uniformly dividing the first water level height curve with the time length of 2 minutes to obtain at least one first water level height identification curve;
taking the previous minute image of the water level height identification curve I as an identification judgment curve I, and taking the next minute image of the water level height identification curve I as an identification prediction curve I;
equidistant taking at least one identification point I on the identification judgment curve I;
fitting the first identification prediction curve by using a translation fitting method to obtain a fitting function F (x) of the first identification prediction curve;
at least one first identification point is arranged in sequence, a corresponding relation is established with the fitting function F (x), and the first identification point and the fitting function F (x) are called together during calling;
forming a reservoir water level height prediction model by the plurality of groups of first identification points and the fitting function F (x);
the method for establishing the reservoir external water level height prediction model comprises the following steps of:
at least one continuous change curve of the external water level height of the big data collection reservoir along with the time change is summarized, and all the continuous change curves are summarized to be a water level height curve II;
uniformly dividing the second water level height curve by the time length of 2 minutes to obtain at least one second water level height identification curve;
taking the previous minute image of the water level height identification curve II as an identification judgment curve II, and taking the next minute image of the water level height identification curve II as an identification prediction curve II;
equidistant taking at least one identification point II on the identification judgment curve II;
fitting the second identification prediction curve by using a translation fitting method to obtain a fitting function G (x) of the second identification prediction curve;
at least one second identification point is arranged in sequence, a corresponding relation is established with the fitting function G (x), and the second identification point and the fitting function G (x) are called together during calling;
the second groups of identification points and the fitting function G (x) form a reservoir external water level height prediction model;
the water source quality pre-judging model comprises a water source quality model in a reservoir and a water source quality model outside the reservoir;
the method for establishing the water source quality model in the reservoir comprises the following steps:
at least one continuous change curve of water source quality in the big data collection reservoir along with time change is summarized, and all the continuous change curves are a water source quality curve V;
uniformly dividing a water source quality curve five by the time length of 2 minutes to obtain at least one water source quality identification curve five;
taking the previous minute image of the water source quality identification curve five as an identification judgment curve five, and taking the next minute image of the water source quality identification curve five as an identification prediction curve five;
equidistant taking at least one identification point five on the identification judgment curve five;
fitting the identification prediction curve five by using a translation fitting method to obtain a fitting function J (x) of the identification prediction curve five;
at least one identification point five is arranged in sequence, a corresponding relation is established with the fitting function J (x), and the identification point five and the fitting function J (x) are called together during calling;
forming a water source quality prediction model in the reservoir by the plurality of groups of identification points V and the fitting function J (x);
the method for establishing the quality model of the water source outside the reservoir comprises the following steps:
collecting at least one continuous change curve of the quality of the water source outside the reservoir along with the time change, and summarizing all the continuous change curves into a water source quality curve six;
uniformly dividing a water source quality curve six by the time length of 2 minutes to obtain at least one water source quality identification curve six;
taking the previous minute image of the water source quality identification curve six as an identification judgment curve six, and taking the next minute image of the water source quality identification curve six as an identification prediction curve six;
equidistant taking at least one identification point six on the identification judgment curve six;
fitting the identification prediction curve six by using a translation fitting method to obtain a fitting function K (x) of the identification prediction curve six;
at least one identification point six is arranged in sequence, a corresponding relation is established with the fitting function K (x), and the identification point six and the fitting function K (x) are called together during calling;
and the plurality of groups of identification points six and the fitting function K (x) form a reservoir external water source quality prediction model.
Preferably, the translation fitting method is specifically as follows:
equally spaced n points on the curve, the coordinates of the n points being (a i ，y i ) I is 1 to n;
a transverse translation curve which is satisfied with a after translation n =1, to obtain the coordinates of new n points (x i ，y i )；
Let the fitting function of the translated curve be L (x) =kx+b,
substitution into all (x i ，y i )，
Thus, the values of k and b are obtained, and L (x) is obtained by substituting L (x) =kx+b.
Preferably, after one minute of prediction, the predicted value of the water level height in the reservoir and the predicted value of the water source quality in the reservoir include the following steps:
acquiring the water level height in the reservoir in real time for one minute, and generating a real-time water level height curve in the reservoir;
taking at least one point on a water level height curve in the real-time reservoir as a first sampling point at equal intervals, and calculating the deviation degree of a first sampling point row and a first identification point row;
selecting a first identification point with the minimum deviation degree, and calling a fitting function F (x) corresponding to the first identification point;
inputting 1 into F (x) to obtain a predicted value of the water level height in the reservoir after one minute;
acquiring the quality of a water source in a reservoir in real time for one minute, and generating a real-time water source quality curve in the reservoir;
taking at least one point on a water source quality curve in the real-time reservoir as a sampling point five at equal intervals, and calculating the deviation degree of a point column of the sampling point five and a point column of the identification point five;
selecting an identification point five with the minimum deviation degree, and calling a fitting function J (x) corresponding to the identification point five;
inputting 1 into J (x) to obtain a predicted value of the water source quality in the reservoir after one minute;
after predicting one minute, the predicted value of the height of the water level outside the reservoir and the predicted value of the quality of the water source outside the reservoir comprise the following steps:
acquiring the real-time one-minute outside water level height of the reservoir, and generating a real-time outside water level height curve of the reservoir;
taking at least one point on the outer water level height curve of the real-time reservoir as a second sampling point at equal intervals, and calculating the deviation degree of a second sampling point column and a second identification point column;
selecting a second identification point with the minimum deviation degree, and calling a fitting function G (x) corresponding to the second identification point;
inputting 1 into G (x) to obtain a predicted value of the water level height outside the reservoir after one minute;
acquiring the quality of the reservoir external water source in one minute in real time, and generating a real-time reservoir external water source quality curve;
taking at least one point on the real-time reservoir external water source quality curve as a sampling point six at equal intervals, and calculating the deviation degree of a point column of the sampling point six and a point column of the identification point six;
selecting a recognition point six with the minimum deviation degree, and calling a fitting function K (x) corresponding to the recognition point six;
inputting 1 into K (x) to obtain a predicted value of the quality of the water source outside the reservoir after one minute.
Preferably, the establishing the regulation response model includes the following steps:
acquiring a predicted value of the water level height in a reservoir and a predicted value of the water source quality in the reservoir;
acquiring a predicted value of the height of the water level outside the reservoir and a predicted value of the quality of the water source outside the reservoir;
acquiring a target value of the water level height in a reservoir and a target value of the water source quality in the reservoir;
summarizing to obtain a predicted value and a target value array;
testing to obtain the dispatching system parameters which are satisfied with: in one minute, regulating the water level height in the reservoir and the water source quality in the reservoir to target values of the water level height in the reservoir and the water source quality in the reservoir;
recording parameters of a dispatching system, and matching the parameters with predicted values of the water level height in the reservoir, the predicted values of the water source quality in the reservoir, the predicted values of the water level height outside the reservoir, the predicted values of the water source quality outside the reservoir, target values of the water level height in the reservoir and target values of the water source quality in the reservoir to form a predicted array;
traversing data stored in a regulation reaction database, obtaining at least one predicted value and a value of a target value array, obtaining at least one corresponding scheduling system parameter, and pairing to obtain at least one predicted array;
and summarizing at least one prediction array to obtain a regulation and control reaction model.
Preferably, the setting the scheduling system parameter using the regulation reaction model includes the following steps:
acquiring the water level height in the reservoir, the water level height outside the reservoir, the water source quality in the reservoir and the water source quality outside the reservoir in real time;
according to the regulation and control pre-judging model, obtaining a predicted value of the water level height in the reservoir, a predicted value of the water source quality in the reservoir, a predicted value of the water level height outside the reservoir and a predicted value of the water source quality outside the reservoir after one minute;
acquiring a target value of the water level height in the reservoir and the water source quality in the reservoir after one minute;
and in the regulation reaction model, finding out the dispatching system parameters under the same conditions, and allocating according to the dispatching system parameters.
Preferably, the establishing the flow rate compensation model includes the following steps:
acquiring actual water outlet speed and flow velocity preset values at the filter screen;
adjusting the output power of the dispatching system, and recording the output power of the dispatching system when the actual water outlet speed reaches a preset flow speed value;
the actual water outlet speed, the output power and the preset flow speed value form an array;
and (3) adjusting the actual water outlet speed and the preset flow velocity value to obtain at least one array, and summarizing to form a flow velocity compensation model.
Compared with the prior art, the invention has the beneficial effects that:
the model establishment module, the real-time monitoring module, the parameter regulation and control module and the flow rate compensation module are arranged to predict the water source data after one minute, and when parameters are currently input, the water source data after one minute are regulated, so that the water source in the reservoir can keep a target value.
Drawings
FIG. 1 is a schematic flow diagram of an intelligent reservoir dispatching system of the present invention;
FIG. 2 is a schematic flow chart of a model for establishing regulation and control prejudgment according to the present invention;
FIG. 3 is a schematic flow chart of predicted values of water level height in a reservoir and predicted values of water source quality in the reservoir after one minute of prediction according to the invention;
FIG. 4 is a schematic flow chart of the process for establishing a regulation reaction model according to the present invention;
FIG. 5 is a schematic diagram of a flow chart for setting parameters of a dispatching system by using a regulation and control reaction model;
FIG. 6 is a flow chart of the flow rate compensation model building method of the invention.
Detailed Description
The following description is presented to enable one of ordinary skill in the art to make and use the invention. The preferred embodiments in the following description are by way of example only and other obvious variations will occur to those skilled in the art.
Referring to fig. 1, an intelligent reservoir dispatching system includes:
the model building module builds a regulation and control pre-judging model, collects data to obtain a regulation and control reaction database, stores predicted values of different water level heights in the reservoir, predicted values of water source quality in the reservoir, predicted values of water level height outside the reservoir, predicted values of water source quality outside the reservoir, target values of water level height in the reservoir and target values of water source quality in the reservoir, builds a regulation and control reaction model according to the regulation and control reaction database, and builds a flow rate compensation model;
the real-time monitoring module is used for monitoring the water level height in the reservoir and the water level height outside the reservoir in real time, collecting monitoring data of the water level height in the reservoir and the water level height outside the reservoir, monitoring the water source quality in the reservoir and the water source quality outside the reservoir in real time, and collecting monitoring data of the water source quality in the reservoir and the water source quality outside the reservoir;
the parameter regulation and control module drives the central controller to predict a predicted value of the water level height in the reservoir and a predicted value of the water source quality in the reservoir after one minute according to the regulation and control pre-judgment model, predicts a predicted value of the water level height outside the reservoir and a predicted value of the water source quality outside the reservoir after one minute, uses a regulation and control reaction model according to the predicted value and a set target value after one minute, sets a dispatching system parameter, corrects the water level height of the water source entering the reservoir and the water source quality value, and the dispatching system parameter comprises a flow speed preset value, a water level height correction value and a water source quality correction value;
at the water outlet of the filter screen, the actual water outlet speed is monitored in real time, the parameters of a dispatching system are adjusted according to a flow rate compensation model, the output power of the dispatching system is changed, and the actual water outlet speed is adjusted to a flow rate preset value;
the target value is set in the dispatching system as the target of system control, and parameter setting is carried out according to the predicted value after one minute, when the dispatching system operates after one minute, all index values in the reservoir reach the target value at the moment, so that waiting is not needed, the dispatching system continues to predict all index values in the reservoir of the next minute, and the method is adopted to continue to carry out advanced adjustment, so that delay of adjustment can be avoided.
Referring to fig. 2, the establishment of the regulation pre-judgment model includes the steps of:
the regulation and control prejudging model comprises a water level height prejudging model and a water source quality prejudging model;
the water level height pre-judging model comprises a reservoir inner water level height prediction model and a reservoir outer water level height prediction model;
the method for establishing the prediction model of the water level height in the reservoir comprises the following steps:
at least one continuous change curve of the water level height in the big data collection reservoir along with the time change is summarized, and all the continuous change curves are a first water level height curve;
uniformly dividing the first water level height curve with the time length of 2 minutes to obtain at least one first water level height identification curve;
taking the previous minute image of the water level height identification curve I as an identification judgment curve I, and taking the next minute image of the water level height identification curve I as an identification prediction curve I;
equidistant taking at least one identification point I on the identification judgment curve I;
fitting the first identification prediction curve by using a translation fitting method to obtain a fitting function F (x) of the first identification prediction curve;
at least one first identification point is arranged in sequence, a corresponding relation is established with the fitting function F (x), and the first identification point and the fitting function F (x) are called together during calling;
forming a reservoir water level height prediction model by the plurality of groups of first identification points and the fitting function F (x);
the method for establishing the reservoir external water level height prediction model comprises the following steps of:
at least one continuous change curve of the external water level height of the big data collection reservoir along with the time change is summarized, and all the continuous change curves are summarized to be a water level height curve II;
uniformly dividing the second water level height curve by the time length of 2 minutes to obtain at least one second water level height identification curve;
taking the previous minute image of the water level height identification curve II as an identification judgment curve II, and taking the next minute image of the water level height identification curve II as an identification prediction curve II;
equidistant taking at least one identification point II on the identification judgment curve II;
fitting the second identification prediction curve by using a translation fitting method to obtain a fitting function G (x) of the second identification prediction curve;
at least one second identification point is arranged in sequence, a corresponding relation is established with the fitting function G (x), and the second identification point and the fitting function G (x) are called together during calling;
the second groups of identification points and the fitting function G (x) form a reservoir external water level height prediction model;
the water source quality pre-judging model comprises a water source quality model in a reservoir and a water source quality model outside the reservoir;
the method for establishing the water source quality model in the reservoir comprises the following steps:
at least one continuous change curve of water source quality in the big data collection reservoir along with time change is summarized, and all the continuous change curves are a water source quality curve V;
uniformly dividing a water source quality curve five by the time length of 2 minutes to obtain at least one water source quality identification curve five;
taking the previous minute image of the water source quality identification curve five as an identification judgment curve five, and taking the next minute image of the water source quality identification curve five as an identification prediction curve five;
equidistant taking at least one identification point five on the identification judgment curve five;
fitting the identification prediction curve five by using a translation fitting method to obtain a fitting function J (x) of the identification prediction curve five;
at least one identification point five is arranged in sequence, a corresponding relation is established with the fitting function J (x), and the identification point five and the fitting function J (x) are called together during calling;
forming a water source quality prediction model in the reservoir by the plurality of groups of identification points V and the fitting function J (x);
the method for establishing the quality model of the water source outside the reservoir comprises the following steps:
collecting at least one continuous change curve of the quality of the water source outside the reservoir along with the time change, and summarizing all the continuous change curves into a water source quality curve six;
uniformly dividing a water source quality curve six by the time length of 2 minutes to obtain at least one water source quality identification curve six;
taking the previous minute image of the water source quality identification curve six as an identification judgment curve six, and taking the next minute image of the water source quality identification curve six as an identification prediction curve six;
equidistant taking at least one identification point six on the identification judgment curve six;
fitting the identification prediction curve six by using a translation fitting method to obtain a fitting function K (x) of the identification prediction curve six;
at least one identification point six is arranged in sequence, a corresponding relation is established with the fitting function K (x), and the identification point six and the fitting function K (x) are called together during calling;
and the plurality of groups of identification points six and the fitting function K (x) form a reservoir external water source quality prediction model.
The translation fitting method is specifically as follows:
equally spaced n points on the curve, the coordinates of the n points being (a i ，y i ) I is 1 to n;
a transverse translation curve which is satisfied with a after translation n =1, to obtain the coordinates of new n points (x i ，y i )；
Let the fitting function of the translated curve be L (x) =kx+b,
substitution into all (x i ，y i )，
Thus, the values of k and b are obtained, and L (x) is obtained by substituting L (x) =kx+b.
Referring to fig. 3, after predicting one minute, the predicted value of the water level height in the reservoir and the predicted value of the water source quality in the reservoir include the steps of:
acquiring the water level height in the reservoir in real time for one minute, and generating a real-time water level height curve in the reservoir;
taking at least one point on a water level height curve in the real-time reservoir as a first sampling point at equal intervals, and calculating the deviation degree of a first sampling point row and a first identification point row;
the degree of deviation is calculated as follows:
the point column of the sampling point one is (b i ，c i ) The point column identifying the point one is (d i ，e i ) I is 1 to n; degree of deviation
Selecting a first identification point with the minimum deviation degree, and calling a fitting function F (x) corresponding to the first identification point;
inputting 1 into F (x) to obtain a predicted value of the water level height in the reservoir after one minute;
acquiring the quality of a water source in a reservoir in real time for one minute, and generating a real-time water source quality curve in the reservoir;
taking at least one point on a water source quality curve in the real-time reservoir as a sampling point five at equal intervals, and calculating the deviation degree of a point column of the sampling point five and a point column of the identification point five;
selecting an identification point five with the minimum deviation degree, and calling a fitting function J (x) corresponding to the identification point five;
inputting 1 into J (x) to obtain a predicted value of the water source quality in the reservoir after one minute;
after predicting one minute, the predicted value of the height of the water level outside the reservoir and the predicted value of the quality of the water source outside the reservoir comprise the following steps:
acquiring the real-time one-minute outside water level height of the reservoir, and generating a real-time outside water level height curve of the reservoir;
taking at least one point on the outer water level height curve of the real-time reservoir as a second sampling point at equal intervals, and calculating the deviation degree of a second sampling point column and a second identification point column;
selecting a second identification point with the minimum deviation degree, and calling a fitting function G (x) corresponding to the second identification point;
inputting 1 into G (x) to obtain a predicted value of the water level height outside the reservoir after one minute;
acquiring the quality of the reservoir external water source in one minute in real time, and generating a real-time reservoir external water source quality curve;
taking at least one point on the real-time reservoir external water source quality curve as a sampling point six at equal intervals, and calculating the deviation degree of a point column of the sampling point six and a point column of the identification point six;
selecting a recognition point six with the minimum deviation degree, and calling a fitting function K (x) corresponding to the recognition point six;
inputting 1 into K (x) to obtain a predicted value of the quality of the water source outside the reservoir after one minute.
Referring to fig. 4, the construction of the regulation response model includes the steps of:
acquiring a predicted value of the water level height in a reservoir and a predicted value of the water source quality in the reservoir;
acquiring a predicted value of the height of the water level outside the reservoir and a predicted value of the quality of the water source outside the reservoir;
acquiring a target value of the water level height in a reservoir and a target value of the water source quality in the reservoir;
summarizing to obtain a predicted value and a target value array;
testing to obtain the dispatching system parameters which are satisfied with: in one minute, regulating the water level height in the reservoir and the water source quality in the reservoir to target values of the water level height in the reservoir and the water source quality in the reservoir;
recording parameters of a dispatching system, and matching the parameters with predicted values of the water level height in the reservoir, the predicted values of the water source quality in the reservoir, the predicted values of the water level height outside the reservoir, the predicted values of the water source quality outside the reservoir, target values of the water level height in the reservoir and target values of the water source quality in the reservoir to form a predicted array;
traversing data stored in a regulation reaction database, obtaining at least one predicted value and a value of a target value array, obtaining at least one corresponding scheduling system parameter, and pairing to obtain at least one predicted array;
summarizing at least one prediction array to obtain a regulation and control reaction model;
the predicted value of the height of the water level outside the reservoir and the predicted value of the quality of the water source outside the reservoir are considered because the scheduled water source is obtained from the outside, so that the predicted value of the height of the water level outside the reservoir and the predicted value of the quality of the water source outside the reservoir are needed to be known, and the parameters of the scheduling system can be adjusted by combining the predicted values.
Referring to FIG. 5, using the regulatory response model, setting the scheduling system parameters includes the steps of:
acquiring the water level height in the reservoir, the water level height outside the reservoir, the water source quality in the reservoir and the water source quality outside the reservoir in real time;
according to the regulation and control pre-judging model, obtaining a predicted value of the water level height in the reservoir, a predicted value of the water source quality in the reservoir, a predicted value of the water level height outside the reservoir and a predicted value of the water source quality outside the reservoir after one minute;
acquiring a target value of the water level height in the reservoir and the water source quality in the reservoir after one minute;
and in the regulation reaction model, finding out the dispatching system parameters under the same conditions, and allocating according to the dispatching system parameters.
Referring to fig. 6, the flow rate compensation model is constructed by the steps of:
acquiring actual water outlet speed and flow velocity preset values at the filter screen;
adjusting the output power of the dispatching system, and recording the output power of the dispatching system when the actual water outlet speed reaches a preset flow speed value;
the actual water outlet speed, the output power and the preset flow speed value form an array;
adjusting the actual water outlet speed and the flow speed preset value to obtain at least one array, and summarizing to form a flow speed compensation model;
the flow rate compensation is to enable the actual water outlet speed to reach a flow rate preset value, otherwise, the flow rate is smaller than the flow rate preset value due to sundry blockage of the filter screen, and errors occur in scheduling;
the actual water outlet speed is regulated to a preset flow speed value as follows:
and at the water outlet position of the filter screen, the actual water outlet speed is monitored in real time, meanwhile, a flow speed preset value is obtained, the output power of the flow speed compensation model under the same condition is called, the dispatching system is adjusted to the output power, the actual water outlet speed at the water outlet position of the filter screen is adjusted to the flow speed preset value, and the dispatching system can dispatch the water in the reservoir according to the set parameters.
The working process of the self-adaptive adjustment control system of the scheduling system is as follows:
step one: the model building module builds a regulation and control prejudging model, a regulation and control reaction model and a flow rate compensation model;
step two: the real-time monitoring module monitors the water level height in the reservoir, the water level height outside the reservoir, the water source quality in the reservoir and the water source quality outside the reservoir in real time, and obtains the numerical value for monitoring the water level height in the reservoir, the water level height outside the reservoir, the water source quality inside the reservoir and the water source quality outside the reservoir in real time;
step three: the parameter regulation and control module predicts a predicted value of the water level height in the reservoir and a predicted value of the water source quality in the reservoir after one minute according to the regulation and control prejudgement model established by the model establishment module, and sets the parameters of the dispatching system by using a regulation and control reaction model according to the predicted value and a target value after one minute;
step four: the flow rate compensation module monitors the actual water outlet speed at the water outlet position of the filter screen in real time, changes the output power of the dispatching system according to the preset flow rate value set in the dispatching system parameter, and adjusts the actual water outlet speed to the preset flow rate value.
In summary, the invention has the advantages that: the model establishment module, the real-time monitoring module, the parameter regulation and control module and the flow rate compensation module are arranged to predict the water source data after one minute, and when parameters are currently input, the water source data after one minute are regulated, so that the water source in the reservoir can keep a target value.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made therein without departing from the spirit and scope of the invention, which is defined by the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. An intelligent reservoir dispatching system, comprising:
the model building module builds a regulation and control pre-judging model, collects data to obtain a regulation and control reaction database, stores predicted values of different water level heights in the reservoir, predicted values of water source quality in the reservoir, predicted values of water level height outside the reservoir, predicted values of water source quality outside the reservoir, target values of water level height in the reservoir and target values of water source quality in the reservoir, builds a regulation and control reaction model according to the regulation and control reaction database, and builds a flow rate compensation model;
the real-time monitoring module is used for monitoring the water level height in the reservoir and the water level height outside the reservoir in real time, collecting monitoring data of the water level height in the reservoir and the water level height outside the reservoir, monitoring the water source quality in the reservoir and the water source quality outside the reservoir in real time, and collecting monitoring data of the water source quality in the reservoir and the water source quality outside the reservoir;
the parameter regulation and control module drives the central controller to predict a predicted value of the water level height in the reservoir and a predicted value of the water source quality in the reservoir after one minute according to the regulation and control pre-judgment model, predicts a predicted value of the water level height outside the reservoir and a predicted value of the water source quality outside the reservoir after one minute, uses a regulation and control reaction model according to the predicted value and a set target value after one minute, sets a dispatching system parameter, corrects the water level height of the water source entering the reservoir and the water source quality value, and the dispatching system parameter comprises a flow speed preset value, a water level height correction value and a water source quality correction value;
the flow rate compensation module is used for monitoring the actual water outlet speed in real time at the water outlet position of the filter screen, adjusting parameters of the dispatching system according to the flow rate compensation model, changing the output power of the dispatching system and adjusting the actual water outlet speed to a flow rate preset value.
2. An intelligent reservoir dispatching system according to claim 1, wherein said establishing a regulatory prognosis model comprises the steps of:
the regulation and control prejudging model comprises a water level height prejudging model and a water source quality prejudging model;
the water level height pre-judging model comprises a reservoir inner water level height prediction model and a reservoir outer water level height prediction model;
the method for establishing the prediction model of the water level height in the reservoir comprises the following steps:
at least one continuous change curve of the water level height in the big data collection reservoir along with the time change is summarized, and all the continuous change curves are a first water level height curve;
uniformly dividing the first water level height curve with the time length of 2 minutes to obtain at least one first water level height identification curve;
taking the previous minute image of the water level height identification curve I as an identification judgment curve I, and taking the next minute image of the water level height identification curve I as an identification prediction curve I;
equidistant taking at least one identification point I on the identification judgment curve I;
fitting the first identification prediction curve by using a translation fitting method to obtain a fitting function F (x) of the first identification prediction curve;
at least one first identification point is arranged in sequence, a corresponding relation is established with the fitting function F (x), and the first identification point and the fitting function F (x) are called together during calling;
forming a reservoir water level height prediction model by the plurality of groups of first identification points and the fitting function F (x);
the method for establishing the reservoir external water level height prediction model comprises the following steps of:
at least one continuous change curve of the external water level height of the big data collection reservoir along with the time change is summarized, and all the continuous change curves are summarized to be a water level height curve II;
uniformly dividing the second water level height curve by the time length of 2 minutes to obtain at least one second water level height identification curve;
taking the previous minute image of the water level height identification curve II as an identification judgment curve II, and taking the next minute image of the water level height identification curve II as an identification prediction curve II;
equidistant taking at least one identification point II on the identification judgment curve II;
fitting the second identification prediction curve by using a translation fitting method to obtain a fitting function G (x) of the second identification prediction curve;
at least one second identification point is arranged in sequence, a corresponding relation is established with the fitting function G (x), and the second identification point and the fitting function G (x) are called together during calling;
the second groups of identification points and the fitting function G (x) form a reservoir external water level height prediction model;
the water source quality pre-judging model comprises a water source quality model in a reservoir and a water source quality model outside the reservoir;
the method for establishing the water source quality model in the reservoir comprises the following steps:
at least one continuous change curve of water source quality in the big data collection reservoir along with time change is summarized, and all the continuous change curves are a water source quality curve V;
uniformly dividing a water source quality curve five by the time length of 2 minutes to obtain at least one water source quality identification curve five;
taking the previous minute image of the water source quality identification curve five as an identification judgment curve five, and taking the next minute image of the water source quality identification curve five as an identification prediction curve five;
equidistant taking at least one identification point five on the identification judgment curve five;
fitting the identification prediction curve five by using a translation fitting method to obtain a fitting function J (x) of the identification prediction curve five;
at least one identification point five is arranged in sequence, a corresponding relation is established with the fitting function J (x), and the identification point five and the fitting function J (x) are called together during calling;
forming a water source quality prediction model in the reservoir by the plurality of groups of identification points V and the fitting function J (x);
the method for establishing the quality model of the water source outside the reservoir comprises the following steps:
collecting at least one continuous change curve of the quality of the water source outside the reservoir along with the time change, and summarizing all the continuous change curves into a water source quality curve six;
uniformly dividing a water source quality curve six by the time length of 2 minutes to obtain at least one water source quality identification curve six;
taking the previous minute image of the water source quality identification curve six as an identification judgment curve six, and taking the next minute image of the water source quality identification curve six as an identification prediction curve six;
equidistant taking at least one identification point six on the identification judgment curve six;
fitting the identification prediction curve six by using a translation fitting method to obtain a fitting function K (x) of the identification prediction curve six;
at least one identification point six is arranged in sequence, a corresponding relation is established with the fitting function K (x), and the identification point six and the fitting function K (x) are called together during calling;
and the plurality of groups of identification points six and the fitting function K (x) form a reservoir external water source quality prediction model.
3. An intelligent reservoir dispatching system according to claim 2, wherein the translation fitting method is specifically as follows:
equally spaced n points on the curve, the coordinates of the n points being (a i ，y i ) I is 1 to n;
a transverse translation curve which is satisfied with a after translation n =1, to obtain the coordinates of new n points (x i ，y i )；
Let the fitting function of the translated curve be L (x) =kx+b,
substitution into all (x i ，y i )，
Thus, the values of k and b are obtained, and L (x) is obtained by substituting L (x) =kx+b.
4. An intelligent reservoir dispatching system according to claim 3, wherein the predicted value of the water level height in the reservoir and the predicted value of the water source quality in the reservoir after one minute are predicted, comprises the steps of:
acquiring the water level height in the reservoir in real time for one minute, and generating a real-time water level height curve in the reservoir;
taking at least one point on a water level height curve in the real-time reservoir as a first sampling point at equal intervals, and calculating the deviation degree of a first sampling point row and a first identification point row;
selecting a first identification point with the minimum deviation degree, and calling a fitting function F (x) corresponding to the first identification point;
inputting 1 into F (x) to obtain a predicted value of the water level height in the reservoir after one minute;
acquiring the quality of a water source in a reservoir in real time for one minute, and generating a real-time water source quality curve in the reservoir;
taking at least one point on a water source quality curve in the real-time reservoir as a sampling point five at equal intervals, and calculating the deviation degree of a point column of the sampling point five and a point column of the identification point five;
selecting an identification point five with the minimum deviation degree, and calling a fitting function J (x) corresponding to the identification point five;
inputting 1 into J (x) to obtain a predicted value of the water source quality in the reservoir after one minute;
after predicting one minute, the predicted value of the height of the water level outside the reservoir and the predicted value of the quality of the water source outside the reservoir comprise the following steps:
acquiring the real-time one-minute outside water level height of the reservoir, and generating a real-time outside water level height curve of the reservoir;
taking at least one point on the outer water level height curve of the real-time reservoir as a second sampling point at equal intervals, and calculating the deviation degree of a second sampling point column and a second identification point column;
selecting a second identification point with the minimum deviation degree, and calling a fitting function G (x) corresponding to the second identification point;
inputting 1 into G (x) to obtain a predicted value of the water level height outside the reservoir after one minute;
acquiring the quality of the reservoir external water source in one minute in real time, and generating a real-time reservoir external water source quality curve;
taking at least one point on the real-time reservoir external water source quality curve as a sampling point six at equal intervals, and calculating the deviation degree of a point column of the sampling point six and a point column of the identification point six;
selecting a recognition point six with the minimum deviation degree, and calling a fitting function K (x) corresponding to the recognition point six;
inputting 1 into K (x) to obtain a predicted value of the quality of the water source outside the reservoir after one minute.
5. An intelligent reservoir dispatching system according to claim 4, wherein said building of a regulatory response model comprises the steps of:
acquiring a predicted value of the water level height in a reservoir and a predicted value of the water source quality in the reservoir;
acquiring a predicted value of the height of the water level outside the reservoir and a predicted value of the quality of the water source outside the reservoir;
acquiring a target value of the water level height in a reservoir and a target value of the water source quality in the reservoir;
summarizing to obtain a predicted value and a target value array;
testing to obtain the dispatching system parameters which are satisfied with: in one minute, regulating the water level height in the reservoir and the water source quality in the reservoir to target values of the water level height in the reservoir and the water source quality in the reservoir;
recording parameters of a dispatching system, and matching the parameters with predicted values of the water level height in the reservoir, the predicted values of the water source quality in the reservoir, the predicted values of the water level height outside the reservoir, the predicted values of the water source quality outside the reservoir, target values of the water level height in the reservoir and target values of the water source quality in the reservoir to form a predicted array;
traversing data stored in a regulation reaction database, obtaining at least one predicted value and a value of a target value array, obtaining at least one corresponding scheduling system parameter, and pairing to obtain at least one predicted array;
and summarizing at least one prediction array to obtain a regulation and control reaction model.
6. The intelligent reservoir dispatching system of claim 5, wherein the setting of dispatching system parameters using a regulatory response model comprises the steps of:
acquiring the water level height in the reservoir, the water level height outside the reservoir, the water source quality in the reservoir and the water source quality outside the reservoir in real time;
according to the regulation and control pre-judging model, obtaining a predicted value of the water level height in the reservoir, a predicted value of the water source quality in the reservoir, a predicted value of the water level height outside the reservoir and a predicted value of the water source quality outside the reservoir after one minute;
acquiring a target value of the water level height in the reservoir and the water source quality in the reservoir after one minute;
and in the regulation reaction model, finding out the dispatching system parameters under the same conditions, and allocating according to the dispatching system parameters.
7. An intelligent reservoir dispatching system according to claim 6, wherein said establishing a flow rate compensation model comprises the steps of:
acquiring actual water outlet speed and flow velocity preset values at the filter screen;
adjusting the output power of the dispatching system, and recording the output power of the dispatching system when the actual water outlet speed reaches a preset flow speed value;
the actual water outlet speed, the output power and the preset flow speed value form an array;
and (3) adjusting the actual water outlet speed and the preset flow velocity value to obtain at least one array, and summarizing to form a flow velocity compensation model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311378925.5A CN117348614A (en) | 2023-10-24 | 2023-10-24 | Intelligent reservoir dispatching system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311378925.5A CN117348614A (en) | 2023-10-24 | 2023-10-24 | Intelligent reservoir dispatching system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117348614A true CN117348614A (en) | 2024-01-05 |
Family
ID=89370756
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311378925.5A Pending CN117348614A (en) | 2023-10-24 | 2023-10-24 | Intelligent reservoir dispatching system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117348614A (en) |
-
2023
- 2023-10-24 CN CN202311378925.5A patent/CN117348614A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111320272A (en) | Multi-condition controlled automatic back-flushing device for denitrification biological filter and operation method thereof | |
| US20190320626A1 (en) | Oxygenation Device for Aquaculture Tank Group and Control Method | |
| CN114565327B (en) | Wisdom energy management and control system based on thing networking | |
| CN110989698A (en) | Pump station gate opening control method | |
| CN115407735A (en) | Plant factory management system based on digital twins | |
| CN105389614B (en) | A kind of implementation method of neutral net self refresh process | |
| CN117348614A (en) | Intelligent reservoir dispatching system | |
| CN112759133B (en) | Water balance automatic control method, system, device and medium for sewage treatment plant | |
| CN115198047B (en) | Hot blast stove combustion monitoring system and method based on big data analysis | |
| KR20180078420A (en) | Enery saving system for marinenursery facilities based on Internet of Things(IoT) | |
| CN215012263U (en) | Three-dimensional greening irrigation system | |
| CN115903698A (en) | Advanced control system and control method for diphenyl carbonate synthesis device by ester exchange method | |
| CN115759804A (en) | Method for analyzing health state of filter in real time | |
| CN114610084A (en) | Gate control method, electronic device and gate | |
| CN1060490A (en) | The observation of catalytic cracking reaction depth and control method | |
| CN117250870B (en) | Reclaimed water recycling control system based on data information processing | |
| CN110673664A (en) | Optimized control method for liquid level of salt melting barrel | |
| CN1155758C (en) | Method based on intermediate water channel for determing impurity concentration and water supply network | |
| CN109816182B (en) | Progressive splitting optimization method for injection and production dynamic regulation and control of water-flooding oil reservoir | |
| CN116200813B (en) | Crystal growth equipment control method and system | |
| CN113104988B (en) | Uniform water distribution system for long-distance subsurface flow wetland channel | |
| CN117472108A (en) | Automatic slurry supply intelligent control method based on pH predicted value | |
| CN118160676B (en) | Automatic oxygenation device and method for aquaculture | |
| CN108385597B (en) | Series channel control method based on multi-channel pond storage capacity balance | |
| Ranjan et al. | Design of an ON/OFF mist duty cycle in mist bioreactors for the growth of hairy roots |
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 |