CN113156817B - Intelligent pump allocation method for pump station - Google Patents
Intelligent pump allocation method for pump station Download PDFInfo
- Publication number
- CN113156817B CN113156817B CN202110291013.9A CN202110291013A CN113156817B CN 113156817 B CN113156817 B CN 113156817B CN 202110291013 A CN202110291013 A CN 202110291013A CN 113156817 B CN113156817 B CN 113156817B
- Authority
- CN
- China
- Prior art keywords
- pump
- pump station
- water
- water supply
- characteristic curve
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- 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
Abstract
The invention discloses an intelligent pump allocation method for a pump station, which belongs to the field of intelligent control of water pumps and comprises the following steps: the method comprises the following steps of S1, obtaining water pump performance test data of a pump station, and analyzing according to the water pump performance test data to obtain an optimized operation model of the pump station; s2, acquiring water demand historical data of a water supply area, analyzing according to the water demand historical data of the water supply area, and predicting to obtain the water supply amount of a pump station in the next preset time period; and S3, processing the water supply amount of the pump station and a preset pressure in the next preset time period according to the pump station optimized operation model to obtain an optimized pump allocation scheme. The method establishes the intelligent pump allocation model by taking the lowest operation cost of the secondary pump station as a target function, realizes the coordinated use of multiple pumps on the premise of meeting the urban water demand and lift, enables the water pumps to operate in a high-efficiency working area, reduces energy consumption waste, reduces energy consumption of water purification plants and improves enterprise benefits.
Description
Technical Field
The invention relates to the field of intelligent control of water pumps, in particular to an intelligent pump allocation method for a pump station.
Background
The water purification plant secondary pump station comprises an in-station unit frequency conversion and power frequency unit or a frequency conversion unit, the power consumption of the in-station unit frequency conversion and power frequency unit accounts for more than 95% of the total power consumption of a water supply system, and the operation cost of the pump station generally accounts for 40% -70% of the water control cost or more in the case of a common town water plant.
In the prior art, pumps are mainly allocated in a manual scheduling mode mainly depending on a query table or manual experience so as to ensure the safe operation of a water pump unit. Due to the lack of scientific theoretical guidance, scheduling personnel generally consider less aiming at different external requirements and adopt different water pump collocation to ensure the energy-saving and efficient operation of the unit. Because subjective experience is inaccurate and difficult to quantify, a plurality of water pump units often do not work in a high-efficiency working area in actual operation, the efficiency of the whole unit is low, energy consumption loss to a certain degree is caused, or the water abandoning amount is excessive because the operation scheduling of a pump station is unreasonable, so that the pump station is built with a pump model, the energy consumption is reduced, resources are saved, and the economic benefit and the social benefit of the pump station are improved.
Disclosure of Invention
Aiming at the problems in the prior art, an intelligent pump allocation method for a pump station is provided, and the specific technical scheme is as follows:
the invention provides an intelligent pump allocation method for a pump station, which comprises the following steps:
the method comprises the following steps of S1, obtaining water pump performance test data of a pump station, and analyzing according to the water pump performance test data to obtain an optimized operation model of the pump station;
s2, acquiring water demand historical data of a water supply area, analyzing according to the water demand historical data of the water supply area, and predicting to obtain the water supply amount of a pump station in the next preset time period;
and S3, processing the water supply amount of the pump station and a preset pressure in the next preset time period according to the pump station optimized operation model to obtain an optimized pump allocation scheme.
Preferably, the step S1 specifically includes:
step S11, dividing the collected water pump performance test data to obtain a plurality of data sets corresponding to performance test parameters, wherein the performance test parameters comprise flow, and lift, power and efficiency corresponding to the flow;
step S12, fitting is carried out according to a plurality of data sets to obtain a water pump characteristic curve, wherein the water pump characteristic curve comprises a first characteristic curve used for representing the corresponding relation between the flow and the lift, a second characteristic curve used for representing the corresponding relation between the flow and the power, and a third characteristic curve used for representing the corresponding relation between the flow and the efficiency;
s13, analyzing according to the first characteristic curve, the second characteristic curve and the third characteristic curve of the water pump characteristic curve respectively to obtain corresponding operating condition points and efficient working intervals;
and S14, establishing the pump station optimized operation model, wherein the pump station optimized operation model comprises an objective function and a constraint condition, and the objective function of the pump station optimized operation model is optimized and solved based on the constraint condition of the pump station optimized operation model.
Preferably, in step S14, the objective function is:
wherein the content of the first and second substances,
m represents the number of constant speed pumps in the pump station;
n represents the number of variable frequency pumps in the pump station;
ω i representing the running state of the constant speed pump;
ω j representing the running state of the variable frequency pump;
N i representing the power of the fixed speed pump;
N j representing the power of the variable frequency pump;
f denotes the objective function.
Preferably, the step S2 specifically includes:
step S21, preprocessing the water demand historical data of the water supply area to obtain a time series data set;
s22, dividing the preprocessed time series data set to form a training set, a testing set and a verification set;
step S23, establishing a water supply prediction model, training, testing and verifying the water supply prediction model according to the time sequence data set, and evaluating the trained water supply prediction model;
step S24, collecting water demand data in the previous preset time period of the water supply area when the evaluation result of the water supply prediction model is qualified;
and S25, processing the water demand data in the previous preset time period according to the trained water supply prediction model, and predicting to obtain the average hourly water consumption in the next preset time period.
Preferably, the step S3 specifically includes:
step S31, establishing a decision variable parameter set according to a target function and a constraint condition of the pump station optimized operation model, wherein the decision variable parameter set comprises a water pump rotation speed ratio and a switch state;
step S32, encoding the decision variable parameter set;
step S33, forming a first population and initializing the first population;
step S34, evaluating the fitness of individuals of the first population;
step S35, selecting, recombining, mutating and evolving operations are executed;
s36, evolving the individuals of the first population by using a genetic algorithm to obtain new individuals to form a second population;
step S37, determining whether a preset termination condition is satisfied:
if yes, go to step S38;
if not, returning to the step S34;
and S38, taking the individual with the maximum fitness as the optimized decision variable parameter set and outputting the optimized decision variable parameter set.
Preferably, in step S33, initializing the first population specifically includes:
generating a plurality of feasible solutions in a feasible region according to a coding rule, and initializing the feasible solutions by using a random function method to form the first population.
Preferably, the preset termination condition is the constraint condition;
in step S37, it is determined whether the feasible solution satisfies the constraint condition of the pump station optimized operation model.
Preferably, the preset termination condition is a preset fitness threshold;
in step S37, it is determined whether the fitness corresponding to the individual meets a preset fitness threshold.
Preferably, the preset termination condition is a preset number of iterations;
in step S37, it is determined whether the evolution frequency of the genetic algorithm satisfies a preset iteration frequency.
Preferably, the constraints include an outlet pressure constraint, a total outlet flow constraint, a tone ratio constraint and a flow interval constraint.
The beneficial effects of this technical scheme lie in:
the intelligent pump allocation model is established, the lowest operating cost of a pump station is taken as a target function, and the coordinated use of multiple pumps is realized on the premise of meeting the urban water demand and lift, so that the water pumps operate in an efficient working area, the energy consumption waste is reduced, the energy consumption of a water purification plant is reduced, and the enterprise benefit is improved.
Drawings
FIG. 1 is a schematic flow chart of an intelligent pump allocation method for a pump station in the present invention;
FIG. 2 is a schematic flow chart of step S1 in the present invention;
FIG. 3 is a schematic flow chart of step S2 according to the present invention;
fig. 4 is a schematic flow chart of step S3 in the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive efforts based on the embodiments of the present invention, shall fall within the scope of protection of the present invention.
It should be noted that the embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
The invention is further described with reference to the following drawings and specific examples, which are not intended to be limiting.
The invention provides an intelligent pump station allocation method, which can be used for a secondary pump station of a water purification plant and belongs to the field of intelligent control of water pumps, and as shown in figure 1, the method comprises the following steps:
the method comprises the following steps of S1, obtaining water pump performance test data of a pump station, and analyzing according to the water pump performance test data to obtain an optimized operation model of the pump station;
in step S1, the water pump performance test data is the pump lift, power and efficiency corresponding to different flow rates at the rated rotation speed or a certain rotation speed, wherein the flow rates should be uniformly distributed and should cover the lowest flow rate and the highest flow rate at the rated rotation speed or a certain rotation speed. A model established by collecting multiple groups of data water pump performance test data provides a data analysis original data set, and the data analysis original data set at least comprises 14 groups of data.
In a preferred embodiment, as shown in fig. 2, step S1 specifically includes:
step S11, dividing the collected water pump performance test data to obtain a plurality of data sets corresponding to performance test parameters, wherein the performance test parameters comprise flow, and lift, power and efficiency corresponding to the flow;
in step S11, the water pump performance test data is divided according to different models of the water pumps of the secondary pump station, the water pump performance test data is further divided according to characteristics such as flow, lift, power, efficiency, and the like, and characteristic names and characteristic values are respectively added to a plurality of data sets obtained by the division, wherein the format of the data sets may be csv, SQL, or other formats.
S12, fitting according to the plurality of data sets to obtain a water pump characteristic curve, wherein the water pump characteristic curve comprises a first characteristic curve for representing the corresponding relation between flow and lift, a second characteristic curve for representing the corresponding relation between flow and power, and a third characteristic curve for representing the corresponding relation between flow and efficiency;
in step S12, a characteristic curve of the water pump is fitted to obtain mathematical relations of flow and lift, flow and power, and flow and efficiency, and theoretical analysis and actual measurement of the characteristic curve of the centrifugal pump can obtain that each water pump has its inherent characteristic curve at a rated rotation speed or a certain rotation speed, and the characteristic curve of the water pump reflects the potential working capacity of the water pump of a certain type, and in the operation of a real pump station, the potential working capacity is expressed as instantaneous actual water yield, lift, shaft power, efficiency value, and the like, and the establishment of the characteristic curve of the water pump provides a basis and a reference for the establishment of an optimized operation model of the pump station.
Specifically, the fitting object: a constant speed pump characteristic curve and a variable frequency pump characteristic curve;
characteristic curve: flow-head, flow-power, flow-efficiency;
the fitting method comprises the following steps: a least squares method;
the process of fitting the water pump characteristic curve is as follows:
first, at a flow rate x i (i =1, 2.. Multidot.n) as argument, head y 1i Power y 2i Efficiency y 3i Are respectively dependent variable;
secondly, polynomial functions are respectively established:
flow-head corresponding polynomial function: f. of 1 (x i )＝α 1 x 2 +β 1 x+γ 1 ；
Flow-power corresponding polynomial function: f. of 2 (x i )＝α 2 x 2 +β 2 x+γ 2 ；
Flow-efficiency polynomial function: f. of 3 (x i )＝α 3 x 2 +β 3 x+γ 3 ；
And thirdly, respectively inputting the data in the divided data sets into the polynomial functions, and obtaining each parameter corresponding to each polynomial function according to the principle that the degree of deviation of the predicted value from the true value is minimum (the following formula).
Finally, a first characteristic curve for characterizing the correspondence of flow to head, a second characteristic curve for characterizing the correspondence of flow to power, and a third characteristic curve for characterizing the correspondence of flow to efficiency may be obtained.
Step S13, analyzing according to a first characteristic curve, a second characteristic curve and a third characteristic curve of a water pump characteristic curve respectively to obtain corresponding operating condition points and efficient working intervals;
in step S13, respectively obtaining operating condition points corresponding to the constant speed pumps according to the constant speed pump characteristic curves in the water pump characteristic curves, and analyzing according to the variable frequency pump characteristic curves in the water pump characteristic curves to obtain corresponding efficient operating intervals;
aiming at a constant-speed pump, the actual operation working condition point of a centrifugal pump device is jointly determined by the performance of the pump (a water pump characteristic curve), a pipeline system and boundary conditions (a pipeline characteristic curve), the intersection point M point of the water pump characteristic curve and the pipeline characteristic curve is the working condition point of the constant-speed pump device, when other operation conditions are unchanged, the constant-speed pump device stably works at the point M, the operation efficiency of the pump at the working condition point is the highest, namely if the operation working condition point is required to be adjusted, the water pump characteristic curve or the pipeline characteristic curve can be changed;
aiming at the variable frequency pump, the pump is driven by a motor with adjustable speed, and the working point of the pump device can be further changed by changing the rotating speed of the motor. Compare in the operating mode of constant speed pump, the operating mode of variable frequency pump is under the condition that city water supply pipe network water demand fluctuates gradually, in order to make pump station device running cost optimization, needs to adjust the operating mode point of pump station device, makes the pump station device move at high-efficient workspace.
The flow regulating range of the variable frequency pump is determined in the following way: first speed n 1 The lower flow Q-the first curve corresponding to the lift H, the second rotation speed n 2 According to the law of proportionality, a parabola (also called an equivalent curve) with the origin of coordinates as a vertex under the similar working condition is obtained by a second curve corresponding to the lower flow Q-lift H, namely the first curve corresponding to the flow Q-lift H is H A ＝k A Q 2 The second curve corresponding to the flow Q-head H is H B ＝k B Q 2 The area enclosed by the four curves is the efficient working area of the variable frequency pump, and the flow rate corresponding to the leftmost point and the rightmost point of the efficient working area is the flow regulating range of the variable frequency pump.
And S14, establishing a pump station optimized operation model, wherein the pump station optimized operation model comprises a target function and a constraint condition, and carrying out optimized solution on the target function of the pump station optimized operation model based on the constraint condition of the pump station optimized operation model.
In a preferred embodiment, in step S14, the objective function is:
wherein the content of the first and second substances,
m represents the number of constant speed pumps in the pump station;
n represents the number of variable frequency pumps in the pump station;
ω i representing the running state of the constant speed pump;
ω j representing the running state of the variable frequency pump;
N i representing the power of the constant speed pump;
N j representing the power of the variable frequency pump;
f denotes the objective function.
The constraint conditions comprise outlet pressure constraint, total outlet water flow constraint, frequency modulation speed ratio constraint and flow interval constraint;
the outlet pressure constraint comprises the step of configuring the outlet pressure of each water pump connected in parallel into a set pump station water supply pressure;
the water outlet total flow constraint comprises the step of configuring the sum of the flow of all water pumps of the pump station into a set pump station water supply flow;
the frequency conversion speed regulation ratio constraint comprises that the rotation speed ratio of the frequency conversion pump has a minimum rotation speed ratio and a maximum rotation speed ratio, and the performance of the pump is limited when the rotation speed ratio of the frequency conversion pump exceeds the range;
the flow interval constraint comprises a variable frequency pump high-efficiency flow interval and a constant speed pump high-efficiency flow interval
S2, acquiring water demand historical data of a water supply area, analyzing according to the water demand historical data of the water supply area, and predicting to obtain the water supply amount of a pump station in the next preset time period;
in step S2, the historical data of water demand in the water supply area is historical data of water supply amount at the detection point of the city pipe network and historical data of water consumption amount of the end user of the pipe network. And establishing a machine learning model, analyzing and predicting historical water demand data of a water supply area, and providing accurate input for a pump station optimized operation model.
In a preferred embodiment, as shown in fig. 3, step S2 specifically includes:
step S21, preprocessing the water demand historical data of the water supply area to obtain a time sequence data set, namely converting the water demand historical data of the water supply area into a time sequence data set with input and output supervision learning;
s22, dividing the preprocessed time series data set to form a training set, a testing set and a verification set;
step S23, establishing a water supply prediction model, training, testing and verifying the water supply prediction model according to the time sequence data set, and evaluating the trained water supply prediction model, wherein the model can be evaluated in a mode of evaluating the model in the prior art, and whether the water supply prediction model is qualified or not is evaluated according to the actual pump station requirement;
step S24, when the evaluation result of the water supply prediction model is qualified, collecting water demand data in a previous preset time period of the water supply area, wherein the previous preset time period can be the previous day, the previous N days or a certain day, and the time period can be determined according to the water consumption rule in the water demand historical data, for example, the water consumption condition of the next weekend is predicted according to the water consumption condition of the historical weekend, for example, the water consumption condition of the next corresponding historical holiday is predicted according to the water consumption condition of the historical holiday;
and S25, processing the water demand data in the previous preset time period according to the trained water supply prediction model, predicting to obtain the average hourly water consumption in the next preset time period, namely inputting the historical water demand data of the previous N days into the water supply prediction model, and predicting the average hourly water consumption of 24 hours in the next day.
And S3, processing the water supply amount of the pump station and a preset pressure (namely a set pressure) in the next preset time period according to the pump station optimized operation model to obtain an optimized pump allocation scheme.
In a preferred embodiment, as shown in fig. 4, the processing procedure of step S3 specifically includes the following steps:
step S31, establishing a decision variable parameter set according to a target function and constraint conditions of the pump station optimized operation model, wherein the decision variable parameter set comprises a water pump rotation speed ratio and a switch state;
step S32, coding the parameter set of the decision variable, namely mapping the solution space of the problem to a coding space, wherein the coding mode adopts real number and integer coding;
step S33, forming a first population and initializing the first population;
in a preferred embodiment, the step S33 of initializing the first population specifically includes:
and generating a plurality of feasible solutions in the feasible region according to the coding rule, wherein the initialization method is a random function method, namely, the feasible solutions are initialized by using the random function method to form a first population.
Step S34, evaluating the fitness of individuals of the first population;
the fitness refers to the ability of population individuals to adapt to the environment, the value of the objective function is used as a fitness value, and the minimization convention is followed, namely the larger the objective function value is, the smaller the fitness is.
And establishing a reasonable mapping relation between the objective function and the fitness function to ensure that the fitness value is non-negative and the direction of increasing the fitness is consistent with the optimization direction of the objective function.
And introducing a penalty function when calculating the fitness to solve the optimization problem with complex constraint, namely applying penalty to the non-feasible solution so as to reduce the survival probability of the non-feasible solution individuals which do not meet the constraint condition in the next generation.
Step S35, performing selection, recombination and mutation evolution operations;
the selection refers to a process of selecting the superior individuals from the population according to a certain rule and eliminating the inferior individuals, so that the superior individuals are directly inherited to the next generation or new individuals are generated through recombination and then inherited to the next generation. Wherein the selection operation is established on the basis of fitness evaluation of group individuals.
Recombination is also called crossover, and refers to the operation of replacing and recombining partial structures of two parent individuals to generate a new individual.
The mutation is a process of forming a new chromosome by changing a part of elements in the chromosome, so that the diversity of the population can be improved, and the risk of the evolutionary algorithm falling into the local optimal solution is reduced.
S36, evolving the individuals of the first population by using a genetic algorithm to obtain new individuals to form a second population;
step S37, determining whether a preset termination condition is satisfied:
if yes, go to step S38;
if not, returning to the step S34;
in a preferred embodiment, the preset termination condition is a constraint condition;
in step S37, it is determined whether the feasible solution meets the constraint condition of the pump station optimized operation model, and when a feasible solution meets the condition of a satisfactory solution, that is, the satisfactory solution is found, the genetic algorithm may be terminated.
In a preferred embodiment, the predetermined termination condition is a predetermined fitness threshold;
in step S37, it is determined whether the fitness corresponding to the individual meets a preset fitness threshold, and when the fitness has reached saturation, the evolution continues without generating an approximate solution with better fitness.
In a preferred embodiment, the predetermined termination condition is a predetermined number of iterations;
in step S37, it is determined whether the evolution frequency of the genetic algorithm meets a preset iteration frequency, and the algorithm may be terminated when the evolution reaches a specified population algebra or when a certain amount of occupied resources is reached due to resource limitations consumed by the calculation, such as calculation time, memory occupied by the calculation, and the like.
The evolution operation can be terminated as long as any one of the above-described three termination conditions is satisfied.
And S38, taking the individual with the maximum fitness as an optimized decision variable parameter set and outputting the decision variable parameter set, wherein the decision variable parameter set comprises a rotating speed ratio and an on-off state.
In a preferred embodiment, the constraints include outlet pressure constraints, total outlet flow constraints, tone ratio constraints, and flow interval constraints.
The beneficial effects of this technical scheme lie in:
the intelligent pump allocation model is established, the lowest operating cost of a pump station is taken as a target function, and the coordinated use of multiple pumps is realized on the premise of meeting the urban water demand and lift, so that the water pumps operate in an efficient working area, the energy consumption waste is reduced, the energy consumption of a water purification plant is reduced, and the enterprise benefit is improved.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention.
Claims (9)
1. An intelligent pump allocation method for a pump station is characterized by comprising the following steps:
the method comprises the following steps of S1, obtaining water pump performance test data of a pump station, and analyzing according to the water pump performance test data to obtain a pump station optimized operation model, wherein the pump station optimized operation model comprises a target function and constraint conditions;
s2, acquiring water demand historical data of a water supply area, analyzing according to the water demand historical data of the water supply area, and predicting to obtain the water supply amount of a pump station in the next preset time period;
s3, processing the water supply amount of the pump station and a preset pressure in the next preset time period according to the pump station optimized operation model to obtain an optimized pump allocation scheme;
in step S1, the objective function is:
wherein, the first and the second end of the pipe are connected with each other,
m represents the number of constant speed pumps in the pump station;
n represents the number of variable frequency pumps in the pump station;
ω i representing the running state of the constant speed pump;
ω j representing the running state of the variable frequency pump;
N i representing the power of the fixed speed pump;
N j representing the power of the variable frequency pump;
f represents the objective function.
2. The intelligent pump station matching method according to claim 1, wherein the step S1 specifically comprises:
step S11, dividing the collected water pump performance test data to obtain a plurality of data sets corresponding to performance test parameters, wherein the performance test parameters comprise flow, and lift, power and efficiency corresponding to the flow;
step S12, fitting is carried out according to a plurality of data sets to obtain a water pump characteristic curve, wherein the water pump characteristic curve comprises a first characteristic curve used for representing the corresponding relation between the flow and the lift, a second characteristic curve used for representing the corresponding relation between the flow and the power, and a third characteristic curve used for representing the corresponding relation between the flow and the efficiency;
s13, analyzing according to the first characteristic curve, the second characteristic curve and the third characteristic curve of the water pump characteristic curve respectively to obtain corresponding operating condition points and efficient working intervals;
and S14, establishing the pump station optimized operation model, and carrying out optimized solution on the objective function of the pump station optimized operation model based on the constraint conditions of the pump station optimized operation model.
3. The intelligent pump station matching method according to claim 1, wherein the step S2 specifically comprises:
step S21, preprocessing the water demand historical data of the water supply area to obtain a time series data set;
s22, dividing the preprocessed time series data set to form a training set, a testing set and a verification set;
step S23, establishing a water supply prediction model, training, testing and verifying the water supply prediction model according to the time series data set, and evaluating the trained water supply prediction model;
step S24, when the evaluation result of the water supply prediction model is qualified, collecting water demand data in the previous preset time period of the water supply area;
and S25, processing the water demand data in the previous preset time period according to the trained water supply prediction model, and predicting to obtain the average hour water consumption in the next preset time period.
4. The intelligent pump station allocation method according to claim 1, wherein the step S3 specifically comprises:
step S31, establishing a decision variable parameter set according to a target function and constraint conditions of the pump station optimized operation model, wherein the decision variable parameter set comprises a water pump rotation speed ratio and a switch state;
step S32, encoding the decision variable parameter set;
step S33, forming a first population and initializing the first population;
step S34, evaluating the fitness of the individuals of the first population;
step S35, selecting, recombining, mutating and evolving operations are executed;
s36, evolving the individuals of the first population by using a genetic algorithm to obtain new individuals to form a second population;
step S37, determining whether a preset termination condition is satisfied:
if yes, go to step S38;
if not, returning to the step S34;
and S38, taking the individual with the maximum fitness as the optimized decision variable parameter set and outputting the optimized decision variable parameter set.
5. The pump station intelligent pump allocation method according to claim 4, wherein in the step S33, initializing the first population specifically comprises:
generating a plurality of feasible solutions in a feasible region according to a coding rule, and initializing the feasible solutions by using a random function method to form the first population.
6. The intelligent pump station allocation method according to claim 5, wherein the preset termination condition is the constraint condition;
in step S37, it is determined whether the feasible solution satisfies the constraint condition of the pump station optimized operation model.
7. The intelligent pump station allocation method according to claim 4, wherein the preset termination condition is a preset fitness threshold;
in step S37, it is determined whether the fitness corresponding to the individual meets a preset fitness threshold.
8. The intelligent pump station allocation method according to claim 4, wherein the preset termination condition is a preset number of iterations;
in step S37, it is determined whether the number of evolutionary times of the genetic algorithm satisfies a preset number of iterations.
9. The pump station intelligent pump allocation method according to claim 5, wherein the constraint conditions include an outlet pressure constraint, a total outlet water flow constraint, a frequency modulation ratio constraint and a flow interval constraint.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110291013.9A CN113156817B (en) | 2021-03-18 | 2021-03-18 | Intelligent pump allocation method for pump station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110291013.9A CN113156817B (en) | 2021-03-18 | 2021-03-18 | Intelligent pump allocation method for pump station |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113156817A CN113156817A (en) | 2021-07-23 |
| CN113156817B true CN113156817B (en) | 2022-11-22 |
Family
ID=76887918
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110291013.9A Active CN113156817B (en) | 2021-03-18 | 2021-03-18 | Intelligent pump allocation method for pump station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113156817B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114017302B (en) * | 2021-11-03 | 2022-11-15 | 江苏四联水务科技有限公司 | Dynamic constant liquid level intelligent adjusting method and system for multistage pump station |
| CN114371614A (en) * | 2021-12-20 | 2022-04-19 | 上海西派埃智能化系统有限公司 | Genetic algorithm-based pump station and pump set operation determination method and system |
| CN114623073B (en) * | 2022-02-15 | 2023-07-11 | 国家石油天然气管网集团有限公司 | Sequential decision method for pump starting scheme of liquid pipeline for multi-batch sequential transportation |
| CN115293514B (en) * | 2022-07-08 | 2023-05-12 | 深圳市前海能源科技发展有限公司 | Regional energy supply control method, system and storage medium |
| CN115455812A (en) * | 2022-08-25 | 2022-12-09 | 临涣水务股份有限公司 | Water supply pump station optimization method and system |
| CN116466591B (en) * | 2023-06-13 | 2023-08-29 | 埃睿迪信息技术（北京）有限公司 | Method and device for determining water supply strategy of water supply system |
| CN116596280B (en) * | 2023-07-17 | 2023-10-03 | 青岛国源中创电气自动化工程有限公司 | Cooperative scheduling method for water pump set of sewage treatment plant |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109191018A (en) * | 2018-10-26 | 2019-01-11 | 智恒科技股份有限公司 | A kind of more pump energy saving management methods of water factory |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010051466A1 (en) * | 2008-10-31 | 2010-05-06 | Optimum Energy, Llc | Systems and methods to control energy consumption efficiency |
| CN102629106B (en) * | 2012-04-11 | 2014-10-08 | 广州东芝白云自动化系统有限公司 | Water supply control method and water supply control system |
| CN103062076B (en) * | 2013-01-25 | 2015-12-23 | 北京清控人居环境研究院有限公司 | A kind of urban water plant pump station separate unit characteristic curve of pump rating method |
| CN103277291A (en) * | 2013-06-07 | 2013-09-04 | 上海东方威尔自动化有限公司 | Optimal scheduling method for single-stage pump station |
| CN106354931A (en) * | 2016-08-29 | 2017-01-25 | 上海交通大学 | Pump station optimal scheduling method based on pump characteristic curve update |
| CN107679717A (en) * | 2017-09-15 | 2018-02-09 | 西安博兴自动化科技有限公司 | A kind of management system based on water amount information collection and Group of Pumping Station Optimized Operation |
| CN109214110B (en) * | 2018-09-27 | 2022-12-27 | 中国水利水电科学研究院 | Long-distance water lifting project optimized scheduling method |
| CN110992209A (en) * | 2019-12-17 | 2020-04-10 | 上海威派格智慧水务股份有限公司 | Flow prediction method |
-
2021
- 2021-03-18 CN CN202110291013.9A patent/CN113156817B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109191018A (en) * | 2018-10-26 | 2019-01-11 | 智恒科技股份有限公司 | A kind of more pump energy saving management methods of water factory |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113156817A (en) | 2021-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113156817B (en) | Intelligent pump allocation method for pump station | |
| JP6736112B2 (en) | A short-term practical scheduling method for ultra-large-scale hydropower stations | |
| CN107292766B (en) | Wind power consumption-oriented power system peak regulation means economical evaluation method and system | |
| CN110417048B (en) | Direct-current power grid transmitting and receiving end combined peak regulation optimization method considering source grid load constraint | |
| CN102629106B (en) | Water supply control method and water supply control system | |
| CN110500291B (en) | Multi-pump parallel control method based on genetic algorithm | |
| CN111681130B (en) | Comprehensive energy system optimal scheduling method considering conditional risk value | |
| CN103277291A (en) | Optimal scheduling method for single-stage pump station | |
| CN103761385A (en) | Optimized design method for mult-heat-source annular pipe network | |
| CN109214709B (en) | Method for optimizing distribution of oxygen generation system of iron and steel enterprise | |
| CN113991640B (en) | Thermal power-based multi-energy complementary energy base energy configuration planning method | |
| CN104537445A (en) | Network province two-stage multi-power short-period coordination peak shaving method | |
| CN116466591B (en) | Method and device for determining water supply strategy of water supply system | |
| CN113110056A (en) | Heat supply intelligent decision-making method and intelligent decision-making machine based on artificial intelligence | |
| CN111598348A (en) | Power transmission network uniformity planning optimization method, system, medium and electronic equipment | |
| CN109472716A (en) | A kind of production capacity end power distribution method multifactor based on the considerations of genetic algorithm | |
| CN115712976A (en) | Heat energy and electric load optimization method based on multi-element heat supply unit and related equipment | |
| CN113078647B (en) | Climbing capacity assessment method for flexible power load cluster | |
| KR20220076869A (en) | Forecasting system and method for power consumption | |
| CN112465196A (en) | System load prediction method, device, equipment and storage medium | |
| CN111461449A (en) | Power load prediction method and computer program product | |
| CN117013535B (en) | Water, wind, light and fire complementary capacity configuration method considering ecological scheduling requirements | |
| CN113361763B (en) | Full-time operation optimization method and system for gas transmission pipe network | |
| CN113591283B (en) | Method and device for adjusting operating oxygen amount of gas boiler and computer equipment | |
| CN117254505B (en) | Energy storage power station optimal operation mode decision method and system based on data processing |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An Intelligent Pump Allocation Method for Pumping Stations Effective date of registration: 20230512 Granted publication date: 20221122 Pledgee: Zheshang Bank Limited by Share Ltd. Shanghai branch Pledgor: WPG (SHANGHAI) SMART WATER PUBLIC Co.,Ltd. Registration number: Y2023310000188 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |