CN117469603A - Multi-water-plant water supply system pressure optimal control method based on big data learning - Google Patents
Multi-water-plant water supply system pressure optimal control method based on big data learning Download PDFInfo
- Publication number
- CN117469603A CN117469603A CN202311786341.1A CN202311786341A CN117469603A CN 117469603 A CN117469603 A CN 117469603A CN 202311786341 A CN202311786341 A CN 202311786341A CN 117469603 A CN117469603 A CN 117469603A
- Authority
- CN
- China
- Prior art keywords
- water supply
- area
- analysis
- pipeline
- water
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 236
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000004458 analytical method Methods 0.000 claims abstract description 90
- 238000010586 diagram Methods 0.000 claims abstract description 12
- 238000005457 optimization Methods 0.000 claims abstract description 10
- 238000005516 engineering process Methods 0.000 claims abstract description 6
- 238000012544 monitoring process Methods 0.000 claims abstract description 5
- 238000011156 evaluation Methods 0.000 claims description 24
- 230000005856 abnormality Effects 0.000 claims description 21
- 230000006870 function Effects 0.000 claims description 21
- 238000004088 simulation Methods 0.000 claims description 16
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 238000005265 energy consumption Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 6
- 238000000275 quality assurance Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 230000001105 regulatory effect Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 239000008400 supply water Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D3/00—Arrangements for supervising or controlling working operations
- F17D3/01—Arrangements for supervising or controlling working operations for controlling, signalling, or supervising the conveyance of a product
-
- 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
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
-
- 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
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Automation & Control Theory (AREA)
- Health & Medical Sciences (AREA)
- Mechanical Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Flow Control (AREA)
Abstract
The invention discloses a multi-water-plant water supply system pressure optimization control method based on big data learning, which belongs to the technical field of water supply system pressure, and comprises the following steps: acquiring initial water supply data of a multi-water plant; generating a corresponding initial water supply information diagram according to the initial water supply data; analyzing the water supply areas of each water plant in the initial water supply information diagram based on the initial water supply data to obtain corresponding area analysis results; adjusting the water supply sheet area according to the sheet area analysis result, and forming a corresponding target water supply information diagram based on the adjusted water supply sheet area; establishing a corresponding digital twin model according to the target water supply information graph and the digital twin technology; and carrying out pipeline analysis on each pipeline based on the digital twin model, determining a corresponding adjusting pipeline, carrying out pipeline adjustment on the adjusting pipeline, carrying out water supply monitoring through the digital twin model, identifying the water supply pressure and the flow rate of each pipeline in real time, and carrying out optimization adjustment according to the identified water supply pressure and flow rate.
Description
Technical Field
The invention belongs to the technical field of water supply system pressure, and particularly relates to a multi-water-plant water supply system pressure optimal control method based on big data learning.
Background
With the acceleration of the urban process and the growing population, the demand for urban water supply systems is increasing. In order to meet the urban water supply demand, a plurality of water plants need to work cooperatively to supply water for the city together. However, the conventional multi-water plant water supply system has problems such as unbalanced water supply pressure, low water supply efficiency, and the like. To solve these problems, optimal control of the multi-water plant water supply system is required.
The conventional multi-water plant water supply system has the following problems:
imbalance in water supply pressure: due to the influence of the terrain, water consumption and other factors, the water supply pressure of different areas can be greatly different, so that water supply in some areas is insufficient, and water supply in other areas is excessive. The water supply efficiency is low: due to the influences of factors such as the length, the diameter, the materials and the like of the water supply pipeline, the water flow resistance in the water supply system is high, and the water supply efficiency is low. Coordination between a plurality of water plants cannot be realized: traditional multi-water-plant water supply systems often cannot achieve coordinated cooperation among a plurality of water plants, so that the efficiency and safety of the water supply systems are affected.
Therefore, in order to solve the problems or part of the problems, the invention provides a multi-water-plant water supply system pressure optimization control method based on big data learning.
Disclosure of Invention
In order to solve the problems of the scheme, the invention provides a multi-water-plant water supply system pressure optimization control method based on big data learning.
The aim of the invention can be achieved by the following technical scheme:
as shown in fig. 1, the method for optimizing and controlling the pressure of the water supply system of the multi-water plant based on big data learning comprises the following steps:
step one: acquiring initial water supply data of a multi-water plant; generating a corresponding initial water supply information diagram according to the initial water supply data;
step two: analyzing the water supply sheet areas of each water plant in the initial water supply information map based on the initial water supply data to obtain corresponding sheet area analysis results;
further, the method for analyzing the water supply area of each water plant comprises the following steps:
identifying water supply areas corresponding to all water plants, and dividing the water supply areas into a plurality of unit areas; acquiring historical characteristic data of each unit area according to the initial water supply data, wherein the historical characteristic data comprises a historical supply value, a historical cost value and a historical income value;
determining a comparison area corresponding to the unit area; setting an estimated supply value, an estimated cost value and an estimated income value of each comparison area relative to the unit area;
calculating a unit evaluation value corresponding to each comparison area;
comparing each of the unit evaluation values with a threshold value X2;
when the unit evaluation value smaller than the threshold value X2 is not available, marking the chip area analysis result as qualified chip area analysis;
when the unit evaluation value is smaller than the threshold value X2, the comparison patch area with the smallest unit evaluation value is marked as a regulating patch area, the patch area analysis result is marked as a patch area analysis disqualification, and the corresponding regulating patch area is associated.
Further, the method of calculating the unit evaluation value includes:
according to the formulaCalculating corresponding unit evaluation values;
wherein: QA (quality assurance) i Representing the cell evaluation value; i represents a comparison slice region, i=1, 2, … …, n being a positive integer; GY (GY) 0 Representing a historical supply value; GY (GY) i Representing the estimated supply value of the corresponding comparison area; SC (SC) 0 Representing historical revenue values; SC (SC) i Representing estimated income values of the corresponding comparison areas; CB (CB) 0 Representing a historical cost value; CB (CB) i Representing the estimated cost value of the corresponding comparison slice region; b 1 、b 2 All are proportional coefficients, and the value range is 0<b 1 <1,0<b 2 <1, a step of; exp represents an exponential function with a base of a constant e; h (GY) i ) For the judgment function, the expression isWherein X1 is a threshold value.
Step three: adjusting the water supply sheet area according to the sheet area analysis result, and forming a corresponding target water supply information diagram based on the adjusted water supply sheet area;
step four: establishing a corresponding digital twin model according to the target water supply information graph and the digital twin technology;
step five: performing pipeline analysis on each pipeline based on the digital twin model, determining a corresponding adjusting pipeline, and performing pipeline adjustment on the adjusting pipeline;
further, the method for performing pipeline analysis comprises:
acquiring target requirements of users in each supply area, and simulating according to the target requirements through the digital twin model to acquire corresponding pipeline water supply data;
analyzing the simulated water supply data of the pipelines through a preset abnormality analysis model to obtain abnormal values corresponding to the pipelines; the outliers include 1 and 0;
the pipe having an outlier equal to 1 is marked as an adjusted pipe.
Further, before adjusting the adjusting pipeline, adjusting the water supply requirement of the user corresponding to the adjusting pipeline to obtain a corresponding target reference requirement, and adjusting the adjusting pipeline according to the target reference requirement.
Further, the method for acquiring the target reference requirement comprises the following steps:
identifying a user area corresponding to the adjusting pipeline, acquiring historical user water supply requirements and corresponding user data of the user area, and generating a corresponding user requirement curve and a corresponding user variation curve according to the historical user water supply requirements and the user data;
generating a space analysis curve based on the user demand curve and the user number change curve; fitting the space analysis curve to obtain a corresponding space analysis curve function;
obtaining the number of predicted users corresponding to each unit section in a predicted period, and integrating the number of predicted users into corresponding predicted bottom points; and sequentially carrying the predicted bottom points into a space analysis curve function for correction, and marking the user water supply requirement corresponding to the predicted bottom point with the final sequencing as a target reference requirement.
Further, the method for sequentially bringing each prediction bottom point into the space analysis curve function for correction comprises the following steps:
step SA1: marking the number of the predicted users corresponding to each predicted bottom point as D j Wherein j=1, 2, … …, m is a positive integer;
step SA2: according to formula Dc j =D j -D j-1 Calculating a bottom difference value corresponding to the predicted bottom point, wherein Dc j Is the bottom difference value; d (D) 0 Indicating the number of users at the current time;
step SA3: setting a corresponding bottom difference slope according to the bottom difference value, and marking the bottom difference slope as k j The method comprises the steps of carrying out a first treatment on the surface of the Calculating initial requirements corresponding to the predicted bottom points according to the bottom difference slope, and combining the initial requirements with the predicted bottom points to form initial curve points; marking each initial curve point in a space analysis curve after processing;
step SA4: fitting a new space analysis curve function according to each initial curve point in the space analysis curve, and taking the predicted bottom point after the sequencing into the space analysis curve function for calculation to obtain the corresponding water supply requirement of the user.
Step six: and (3) carrying out water supply monitoring through a digital twin model, identifying the water supply pressure and the water flow rate of each pipeline in real time, and carrying out optimization adjustment according to the identified water supply pressure and the identified water flow rate.
The method for optimally adjusting the water supply pressure and the flow rate according to the identification comprises the following steps:
analyzing the identified water supply pressure and flow rate through a preset abnormality analysis model to obtain corresponding abnormality analysis results, wherein the abnormality analysis results comprise analysis abnormality and analysis normality;
when the abnormal analysis result is that the analysis is normal, not performing corresponding operation;
when the analysis result of the abnormality is analysis abnormality, carrying out simulation adjustment through the digital twin model to obtain a plurality of groups of simulation adjustment modes, evaluating the water supply energy consumption of each simulation adjustment mode, selecting the simulation adjustment mode with the lowest water supply energy consumption as a target adjustment mode, and carrying out water supply adjustment according to the target adjustment mode.
Compared with the prior art, the invention has the beneficial effects that:
by combining the dynamic change conditions of the water supply demands of users in different unit areas in the water supply sheet area, the pipeline is intelligently analyzed and adjusted, so that the problem that the existing pipeline adjustment mode is not accurate enough due to the dynamic change of the water supply demands of users in different unit areas in the water supply sheet area along with the process of urbanization is solved; the adjustment strategy of the pipeline is optimized. Meanwhile, a corresponding digital twin model is established by combining a digital twin technology, and monitoring and adjustment are performed based on the established digital twin model, so that the pipeline pressure optimization is more visual and accurate.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of the method of the present invention.
Description of the embodiments
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the method for optimizing and controlling the pressure of the water supply system of the multi-water plant based on big data learning comprises the following steps:
step one: acquiring detail data of current water supply of multiple water plants, such as water supply areas of each water plant, and related data such as pipeline data, valve data, historical water supply pressure, historical flow rate and the like in the areas; the detail data of the current water supply of the multi-water plant can be counted according to a preset data template; marking the obtained detail data as initial water supply data; generating a corresponding initial water supply information diagram according to the obtained initial water supply data; the initial water supply information map is used for displaying relevant information such as water supply areas, pipelines and the like of each water plant, and the water supply information map with the relevant water supply information map can be used as the initial water supply information map.
Step two: analyzing the water supply areas of each water plant in the initial water supply information diagram based on the initial water supply data, judging whether the water supply areas of each water plant are reasonable or not, and judging whether the area optimization can be carried out or not to obtain a corresponding area analysis result;
the method for analyzing the water supply area of each water plant comprises the following steps:
identifying water supply sheet areas corresponding to all water plants, and dividing the water supply sheet areas into a plurality of unit areas according to the layout and distribution of water supply pipelines; specifically, the unit areas can be divided in various modes, for example, the areas with similar pipe network layout and similar pipe lengths and pipe diameters are divided into the same unit area; dividing a region with similar terrain and similar water consumption into the same unit region; the method can be particularly divided according to actual conditions, for example, different branch pipes can be divided into a unit area, and the dividing condition of the unit area is that the unit area can be divided and adjusted, namely, when the unit area is judged to be unsuitable for the water supply area, the unit area can be adjusted and then is belonged to other water supply areas; the division can also be performed directly by manual means based on their experience.
Acquiring historical characteristic data of each unit area according to the initial water supply data, and carrying out corresponding data statistics on the historical characteristic data according to characteristic items such as supply items, cost items and income items to acquire the historical data of each characteristic item, wherein the historical data of each characteristic item, such as the historical supply data of the unit area, comprises the water supply demand condition of users in the unit area, and can meet the water supply demand of the area; the cost item data is the historical cost data of the water plant for supplying water to the unit area; the income item data is the historical income data of the water plant for supplying water to the unit area, and the income data is the water expenditure of the water users in the unit area; counting supply values, cost values and income values corresponding to historical data of each characteristic item according to month, quarter, year and the like of unit time; the supply value is the average supply demand satisfaction rate in unit time counted according to the historical supply data; the cost value and the income value are respectively corresponding average cost and average income; marked as historical supply values, historical cost values, and historical revenue values.
Determining supply areas adjacent to the supply areas corresponding to the unit areas, marking the supply areas as comparison areas, and predicting predicted supply values, predicted cost values and predicted income values of the comparison areas for the unit areas; estimating corresponding estimated supply values, estimated cost values and estimated income values according to the conditions of the existing pipelines, water plants and the like, wherein the estimated income values are equal to the historical income values by default under the condition that users in the unit areas are unchanged; the prediction is performed according to the historical data under the corresponding conditions, such as the prediction is performed according to the historical data under the basically similar conditions of the distance position of the unit area, the water plant condition and the like.
The general evaluation unit area is a unit area each located at the boundary of the water supply sheet area.
According to the formulaCalculating corresponding unit evaluation values;
wherein: QA (quality assurance) i Representing the cell evaluation value; i represents a comparison slice region, i=1, 2, … …, n being a positive integer; GY (GY) 0 Representing a historical supply value; GY (GY) i Representing the estimated supply value of the corresponding comparison area; SC (SC) 0 Representing historical revenue values; SC (SC) i Representing estimated income values of the corresponding comparison areas; CB (CB) 0 Representing a historical cost value; CB (CB) i Representing the estimated cost value of the corresponding comparison slice region; b 1 、b 2 All are proportional coefficients, and the value range is 0<b 1 <1,0<b 2 <1, a step of; exp represents an exponential function with a base of a constant e; h (GY) i ) For the judgment function, the expression isWherein X1 is a threshold value, and is set according to the standard and specification meeting the water consumption of users.
Whether there is a cell evaluation value smaller than the threshold value X2 is identified, the threshold value X2 is <0, if the cell evaluation value is equal to 0, the cell area is not different even if the cell area is adjusted, and when the optimization conditions such as adjustment cost are considered, the threshold value X2 smaller than 0 is set, and the adjustment critical value in practical application is indicated.
When the unit evaluation value smaller than the threshold value X2 is not available, the chip area analysis result is qualified;
when the unit evaluation value is smaller than the threshold value X2, marking a comparison slice area with the minimum unit evaluation value as a regulating slice area, wherein the slice area analysis result is that the slice area is unqualified and the corresponding regulating slice area; indicating that the cell area subsequently needs to be incorporated into the tab area.
Step three: corresponding water supply sheet area adjustment is carried out according to the obtained sheet area analysis result, a new initial water supply information diagram is generated according to the adjusted water supply sheet area, and the new initial water supply information diagram is marked as a target water supply information diagram;
when the chip area analysis result is that the chip area analysis is qualified, the unit area is not adjusted; otherwise, the corresponding unit area is adjusted to the corresponding adjusting sheet area.
Step four: establishing a corresponding digital twin model according to the target water supply information graph and the digital twin technology;
the relevant data of the water supply network based on the target water supply information map comprises the length, diameter, materials, connection modes and the like of the pipelines, and the information of the position, model, running state and the like of equipment such as a pump station, a valve, a water meter and the like. The data can be obtained by means of field investigation, history file inquiry and the like. And processing and converting the data identified and collected in the target water supply information graph to enable the data to meet the requirements of the digital twin model. For example, positional information of the pipe and the device is converted into three-dimensional coordinates, operational state information of the device is converted into a digital signal, and the like. A suitable digital twinning platform, such as a cloud computing based platform or specialized digital twinning software, is selected for building and managing the corresponding digital twinning model. And constructing a digital twin model on the digital twin platform according to the acquired data and the processing result. This includes building three-dimensional models of pipes and equipment, setting related parameters and attributes, defining connection relationships and operational rules between them, and the like. And verifying and calibrating the established digital twin model to ensure the accuracy and reliability of the model. The output result of the model is checked to be consistent with the actual running condition by a comparison test with the actual water supply network, and if deviation exists, the model needs to be adjusted and optimized.
Step five: carrying out pipeline analysis on each pipeline based on the digital twin model, judging whether the pipeline needs to be adjusted, and carrying out pipeline adjustment according to the obtained pipeline analysis result;
acquiring historical water supply demands of users in each supply area, determining the historical water supply demand with the highest water supply demand according to the acquired historical water supply demand, marking the historical water supply demand as a target demand, simulating according to the acquired target demand through a digital twin model, determining how water needs to be supplied when the target demand is met, and acquiring the water supply pressure and the water flow rate of each pipeline in the state;
corresponding anomaly analysis models are established by acquiring historical pipeline water supply data of a large number of pipelines, the anomaly analysis models are established based on an isolated forest algorithm, and the expression is thatThe method comprises the steps of carrying out a first treatment on the surface of the The input is x, which is the pipeline water supply data corresponding to the water supply pressure and the flow rate, and the output is an abnormal value, and the abnormal value is 1 or 0; determining whether the abnormal conditions of each pipeline occur in the simulation process according to the abnormal analysis model, namely, the water supply pressure, the water flow rate and the like are abnormal at the pipeline and exceed the preset standard; the warning pressure, the warning flow rate and other related data of the pipeline can be determined according to the design standard of each pipeline, such as the diameter, the length, the material and the like of the pipeline;
and marking the pipeline with the abnormal value equal to 1 as an adjusting pipeline, and performing pipeline adjustment on the adjusting pipeline.
And (3) adjusting the pipeline of the adjusting pipeline, namely correspondingly adjusting according to the exceeding item, such as replacing the pipeline meeting the requirements.
In one embodiment, when the current pipelines are not required by analysis, pipeline adjustment is often carried out, but the final adjustment result is greatly different due to different standards in the adjustment process, because the user water supply requirements of different unit areas in the water supply sheet areas are changed along with the process of urban treatment, if the adjustment is directly carried out according to the out-of-standard part, the water supply requirements of users can not be met when the user requirements are increased, if the water supply requirements of fixed coefficients are directly amplified in a traditional way, the amplification is quite easy to be unreasonable, if the water supply requirements of resources are excessively large, the resource waste is caused, and the cost is excessively large, otherwise, the water supply requirements of users are insufficient; therefore, in order to solve the problem, the invention intelligently determines the corresponding target reference requirement in the following way; the method comprises the following steps:
identifying a user area corresponding to the adjusting pipeline, namely a corresponding water supply area; acquiring historical user water supply requirements and corresponding user data of a user area, and generating a corresponding user requirement curve and a corresponding user variation curve according to the acquired historical user water supply requirements and the corresponding user data;
integrating the obtained user demand curve and user number change curve into a space analysis curve, and correspondingly generating according to time, the user number and corresponding historical user water supply demands to form the space analysis curve; forming a plurality of space coordinates after one-to-one correspondence, and generating a corresponding space analysis curve according to the obtained space coordinates; fitting the obtained space analysis curve to obtain a corresponding space analysis curve function;
the number of users in the prediction period of the user area is obtained according to the technology such as big data, and the number of users after the prediction period can be estimated by combining the corresponding city planning, development, population prediction and other modes, and is marked as the number of predicted users; the prediction can be performed by other modes, and a plurality of analysis reports and related prediction methods are provided for the change of the number of users in the region at present, for example, when one region is developed and mature, the number of users in the region cannot be adjusted in a short period of time, and further, the number of users in the region cannot be changed greatly;
forming user quantity data corresponding to different prediction time in a prediction period, and generating a plurality of prediction bottom points according to the unit section; the unit sections are preset time periods, such as a month, a quarter, a year and the like, and are mainly set according to the general change time of the urban user quantity;
and sequentially carrying the predicted bottom points into a space analysis curve function for correction, and obtaining the user water supply requirement corresponding to the last predicted bottom point, and marking the user water supply requirement as a target reference requirement.
The method for carrying each prediction bottom point into the space analysis curve function in turn for correction comprises the following steps:
step SA1: marking the predicted bottom points as j, j=1, 2, … … and m, wherein m is a positive integer, and sorting according to the time sequence; marking the number of the predicted users corresponding to each predicted bottom point as D j ;
Step SA2: according to formula Dc j =D j -D j-1 Calculating a bottom difference value corresponding to the predicted bottom point, wherein Dc j Is the bottom difference value; d (D) 0 The number of users at the current moment is represented, namely the number of users without prediction;
step SA3: setting a corresponding bottom difference slope according to the obtained bottom difference value, and marking the obtained bottom difference slope as k j The method comprises the steps of carrying out a first treatment on the surface of the Calculating initial requirements corresponding to the corresponding predicted bottom points according to the obtained bottom difference slope, and combining the initial requirements with the corresponding predicted bottom points to form initial curve points; marking the obtained initial curve points in a space analysis curve after processing, namely deleting the initial curve points when j=m, namely not inputting the corresponding initial curve points to the final predicted bottom point of the sequencing;
the bottom difference slope is set according to matching, namely a large amount of historical data of the same pipeline is obtained, a corresponding space analysis curve is generated, the curve slope corresponding to the predicted bottom point is matched with the curve slope similar to the curve segment of the same bottom difference value, and the average value of the obtained curve slopes is marked as the bottom difference slope; or firstly identifying curve segments with the same base difference value, identifying the similarity of curve trend of the front segment curve of each curve segment and the predicted base point, taking the curve segment with the similarity within a preset range as a target curve segment, identifying the curve slope of each target curve segment, and calculating the corresponding average value as the base difference slope.
Step SA4: fitting a new space analysis curve function according to each initial curve point in the space analysis curve, and taking the predicted bottom point after the sequencing into the space analysis curve function for calculation to obtain the corresponding water supply requirement of the user.
Step six: and (3) carrying out water supply monitoring through a digital twin model, identifying the water supply pressure and the water flow rate of each pipeline in real time, and carrying out optimization adjustment according to the identified water supply pressure and the identified water flow rate.
The method for optimally adjusting the water supply pressure and the flow rate according to the identification comprises the following steps:
analyzing the identified water supply pressure and flow rate through a preset abnormality analysis model to obtain a corresponding abnormality analysis result, namely, an abnormality value is 1, an abnormality is analyzed, an abnormality value is 0, and the analysis is normal; the anomaly analysis model is established based on the isolated forest algorithm; judging whether the water supply pressure and the flow rate at the pipeline are abnormal;
when the abnormal analysis result is that the analysis is normal, not performing corresponding operation;
when the analysis result of the abnormality is analysis abnormality, performing simulation adjustment through a digital twin model, wherein the basis of the simulation adjustment is to meet the water use requirement of a corresponding user; the method comprises the steps of performing simulation adjustment under the condition that water requirements of corresponding users are met, obtaining a plurality of groups of simulation adjustment modes, evaluating energy consumption data of each simulation adjustment mode, namely performing adjustment according to the simulation adjustment modes, estimating corresponding water supply energy consumption, and currently having a related water supply energy consumption calculation mode, so that calculation can be performed according to the existing mode; the corresponding water supply energy consumption can be calculated by combining the digital twin model;
and selecting the simulation adjustment mode with the lowest water supply energy consumption as a target adjustment mode, and performing water supply adjustment according to the obtained target adjustment mode.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas which are obtained by acquiring a large amount of data and performing software simulation to obtain the closest actual situation, and preset parameters and preset thresholds in the formulas are set by a person skilled in the art according to the actual situation or are obtained by simulating a large amount of data.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (7)
1. The optimal control method for the pressure of the water supply system of the multi-water plant based on big data learning is characterized by comprising the following steps:
step one: acquiring initial water supply data of a multi-water plant; generating a corresponding initial water supply information diagram according to the initial water supply data;
step two: analyzing the water supply sheet areas of each water plant in the initial water supply information map based on the initial water supply data to obtain corresponding sheet area analysis results;
the method for analyzing the water supply area of each water plant comprises the following steps:
identifying water supply areas corresponding to all water plants, and dividing the water supply areas into a plurality of unit areas; acquiring historical characteristic data of each unit area according to the initial water supply data, wherein the historical characteristic data comprises a historical supply value, a historical cost value and a historical income value;
determining a comparison area corresponding to the unit area; setting an estimated supply value, an estimated cost value and an estimated income value of each comparison area relative to the unit area; calculating a unit evaluation value corresponding to each comparison area; comparing each of the unit evaluation values with a threshold value X2;
when the unit evaluation value smaller than the threshold value X2 is not available, marking the chip area analysis result as qualified chip area analysis;
when the unit evaluation value is smaller than the threshold value X2, marking a comparison slice area with the minimum unit evaluation value as an adjustment slice area, marking a slice area analysis result as a slice area analysis disqualification, and associating the adjustment slice area with the corresponding adjustment slice area;
step three: adjusting the water supply sheet area according to the sheet area analysis result, and forming a corresponding target water supply information diagram based on the adjusted water supply sheet area;
step four: establishing a corresponding digital twin model according to the target water supply information graph and the digital twin technology;
step five: performing pipeline analysis on each pipeline based on the digital twin model, determining a corresponding adjusting pipeline, and performing pipeline adjustment on the adjusting pipeline;
step six: and (3) carrying out water supply monitoring through a digital twin model, identifying the water supply pressure and the water flow rate of each pipeline in real time, and carrying out optimization adjustment according to the identified water supply pressure and the identified water flow rate.
2. The optimal control method for the pressure of the water supply system of the multi-water plant based on big data learning according to claim 1, wherein the method for calculating the unit evaluation value comprises the following steps:
according to the formulaCalculating corresponding unit evaluation values;
wherein: QA (quality assurance) i Representing the cell evaluation value; i represents a comparison slice region, i=1, 2, … …, n being a positive integer; GY (GY) 0 Representing a historical supply value; GY (GY) i Representing the estimated supply value of the corresponding comparison area; SC (SC) 0 Representing historical revenue values; SC (SC) i Representing estimated income values of the corresponding comparison areas; CB (CB) 0 Representing a historical cost value; CB (CB) i Representing the estimated cost value of the corresponding comparison slice region; b 1 、b 2 All are proportional coefficients, and the value range is 0<b 1 <1,0<b 2 <1, a step of; exp represents an exponential function with a base of a constant e; h (GY) i ) For the judgment function, the expression isWherein X1 is a threshold value.
3. The optimal control method for the pressure of the water supply system of the multi-water plant based on big data learning according to claim 1, wherein the method for performing pipeline analysis comprises the following steps:
acquiring target requirements of users in each supply area, and simulating according to the target requirements through the digital twin model to acquire corresponding pipeline water supply data;
analyzing the simulated water supply data of the pipelines through a preset abnormality analysis model to obtain abnormal values corresponding to the pipelines; the outliers include 1 and 0;
the pipe having an outlier equal to 1 is marked as an adjusted pipe.
4. The optimal control method for the pressure of the water supply system of the multi-water plant based on big data learning according to claim 3, wherein before the adjustment of the adjusting pipeline is performed, the water supply requirement of a user corresponding to the adjusting pipeline is adjusted, a corresponding target reference requirement is obtained, and the adjustment of the adjusting pipeline is performed according to the target reference requirement.
5. The optimal control method for the pressure of the water supply system of the multi-water plant based on big data learning according to claim 4, wherein the target reference requirement obtaining method comprises the following steps:
identifying a user area corresponding to the adjusting pipeline, acquiring historical user water supply requirements and corresponding user data of the user area, and generating a corresponding user requirement curve and a corresponding user variation curve according to the historical user water supply requirements and the user data;
generating a space analysis curve based on the user demand curve and the user number change curve; fitting the space analysis curve to obtain a corresponding space analysis curve function;
obtaining the number of predicted users corresponding to each unit section in a predicted period, and integrating the number of predicted users into corresponding predicted bottom points; and sequentially carrying the predicted bottom points into a space analysis curve function for correction, and marking the user water supply requirement corresponding to the predicted bottom point with the final sequencing as a target reference requirement.
6. The optimal control method for the pressure of the water supply system of the multi-water plant based on big data learning according to claim 5, wherein the method for sequentially bringing each predicted bottom point into a space analysis curve function for correction comprises the following steps:
step SA1: marking the number of the predicted users corresponding to each predicted bottom point as D j Wherein j=1, 2, … …, m is a positive integer;
step SA2: according to formula Dc j =D j -D j-1 Calculating a bottom difference value corresponding to the predicted bottom point, wherein Dc j Is the bottom difference value; d (D) 0 Indicating the number of users at the current time;
step SA3: setting a corresponding bottom difference slope according to the bottom difference value, and marking the bottom difference slope as k j The method comprises the steps of carrying out a first treatment on the surface of the Calculating initial requirements corresponding to the predicted bottom points according to the bottom difference slope, and combining the initial requirements with the predicted bottom points to form initial curve points; marking each initial curve point in a space analysis curve after processing;
step SA4: fitting a new space analysis curve function according to each initial curve point in the space analysis curve, and taking the predicted bottom point after the sequencing into the space analysis curve function for calculation to obtain the corresponding water supply requirement of the user.
7. The optimal control method for the pressure of the water supply system of the multi-water plant based on big data learning according to claim 1, wherein the optimal adjustment method based on the identified water supply pressure and flow rate comprises the following steps:
analyzing the identified water supply pressure and flow rate through a preset abnormality analysis model to obtain corresponding abnormality analysis results, wherein the abnormality analysis results comprise analysis abnormality and analysis normality;
when the abnormal analysis result is that the analysis is normal, not performing corresponding operation;
when the analysis result of the abnormality is analysis abnormality, carrying out simulation adjustment through the digital twin model to obtain a plurality of groups of simulation adjustment modes, evaluating the water supply energy consumption of each simulation adjustment mode, selecting the simulation adjustment mode with the lowest water supply energy consumption as a target adjustment mode, and carrying out water supply adjustment according to the target adjustment mode.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311786341.1A CN117469603B (en) | 2023-12-25 | 2023-12-25 | Multi-water-plant water supply system pressure optimal control method based on big data learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311786341.1A CN117469603B (en) | 2023-12-25 | 2023-12-25 | Multi-water-plant water supply system pressure optimal control method based on big data learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117469603A true CN117469603A (en) | 2024-01-30 |
CN117469603B CN117469603B (en) | 2024-03-08 |
Family
ID=89633244
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311786341.1A Active CN117469603B (en) | 2023-12-25 | 2023-12-25 | Multi-water-plant water supply system pressure optimal control method based on big data learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117469603B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117906070A (en) * | 2024-03-18 | 2024-04-19 | 深圳市科荣软件股份有限公司 | Pressure regulating method and pressure regulating system of water supply network |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009018564A (en) * | 2007-06-14 | 2009-01-29 | Komori Corp | Liquid transfer member pressing force adjusting method and apparatus of rotary stencil-printing plate liquid-coating machine |
CN102629106A (en) * | 2012-04-11 | 2012-08-08 | 广州东芝白云自动化系统有限公司 | Water supply control method and water supply control system |
US8635051B1 (en) * | 2008-08-28 | 2014-01-21 | Bentley Systems, Incorporated | System and method for pressure-dependent demand optimization for leakage detection |
CN105894130A (en) * | 2016-04-25 | 2016-08-24 | 杭州电子科技大学 | Optimized arrangement method for monitoring points of urban water supply pipe network |
-
2023
- 2023-12-25 CN CN202311786341.1A patent/CN117469603B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009018564A (en) * | 2007-06-14 | 2009-01-29 | Komori Corp | Liquid transfer member pressing force adjusting method and apparatus of rotary stencil-printing plate liquid-coating machine |
US8635051B1 (en) * | 2008-08-28 | 2014-01-21 | Bentley Systems, Incorporated | System and method for pressure-dependent demand optimization for leakage detection |
CN102629106A (en) * | 2012-04-11 | 2012-08-08 | 广州东芝白云自动化系统有限公司 | Water supply control method and water supply control system |
CN105894130A (en) * | 2016-04-25 | 2016-08-24 | 杭州电子科技大学 | Optimized arrangement method for monitoring points of urban water supply pipe network |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117906070A (en) * | 2024-03-18 | 2024-04-19 | 深圳市科荣软件股份有限公司 | Pressure regulating method and pressure regulating system of water supply network |
CN117906070B (en) * | 2024-03-18 | 2024-05-24 | 深圳市科荣软件股份有限公司 | Pressure regulating method and pressure regulating system of water supply network |
Also Published As
Publication number | Publication date |
---|---|
CN117469603B (en) | 2024-03-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109242049B (en) | Water supply pipe network multipoint leakage positioning method and device based on convolutional neural network | |
CN117469603B (en) | Multi-water-plant water supply system pressure optimal control method based on big data learning | |
CN109376925B (en) | Dynamic self-adaptive optimization method for node flow of water supply pipe network | |
CN105678481A (en) | Pipeline health state assessment method based on random forest model | |
CN111369070A (en) | Envelope clustering-based multimode fusion photovoltaic power prediction method | |
CN104461682B (en) | A kind of steel rolling steel plate emulation cutting quality judging system and method | |
CN112308292A (en) | Method for drawing fire risk grade distribution map | |
CN113610381B (en) | Water quality remote real-time monitoring system based on 5G network | |
CN109657962A (en) | A kind of appraisal procedure and system of the volume assets of brand | |
CN114648155A (en) | Source analysis method and emergency response system based on weather typing and weather forecast | |
CN115542236B (en) | Electric energy meter operation error estimation method and device | |
CN108446771A (en) | A method of preventing Sale Forecasting Model over-fitting | |
CN111612149A (en) | Main network line state detection method, system and medium based on decision tree | |
CN112818495A (en) | Novel dynamic correction method for pipeline pressure drop measurement and calculation algorithm parameters | |
CN114548494B (en) | Visual cost data prediction intelligent analysis system | |
CN111242266A (en) | Operation data management system | |
CN113868948A (en) | User-oriented dynamic threshold model training system and method | |
CN117850273A (en) | Digital twin system for controlling carbon emission of building | |
KR102124168B1 (en) | method for selecting optimal location of water pressure gauge for leakage detection in water supply networks | |
CN115330088A (en) | Flood control fine prediction method for small reservoir | |
CN111080115B (en) | Water consumption distribution method and device based on water supply hydraulic model | |
CN114092272A (en) | Intelligent electricity stealing distinguishing method based on dynamic clustering algorithm | |
CN113408764A (en) | Product online technical state management and control system based on digital twins | |
CN109377110B (en) | Evaluation method and system for brand content assets | |
CN105975736B (en) | A kind of renewable energy output power modelling method of probabilistic based on orthogonal series |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |