CN116702611A - Pump unit optimization method based on genetic algorithm - Google Patents
Pump unit optimization method based on genetic algorithm Download PDFInfo
- Publication number
- CN116702611A CN116702611A CN202310676886.0A CN202310676886A CN116702611A CN 116702611 A CN116702611 A CN 116702611A CN 202310676886 A CN202310676886 A CN 202310676886A CN 116702611 A CN116702611 A CN 116702611A
- Authority
- CN
- China
- Prior art keywords
- pump
- water
- genetic algorithm
- water pump
- pump set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 58
- 230000002068 genetic effect Effects 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims abstract description 31
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 197
- 238000009826 distribution Methods 0.000 claims abstract description 28
- 230000006870 function Effects 0.000 claims abstract description 22
- 238000011056 performance test Methods 0.000 claims abstract description 17
- 238000004519 manufacturing process Methods 0.000 claims abstract description 12
- 230000008569 process Effects 0.000 claims abstract description 4
- 230000007246 mechanism Effects 0.000 claims description 20
- 230000035772 mutation Effects 0.000 claims description 8
- 108090000623 proteins and genes Proteins 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 230000001133 acceleration Effects 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 239000007788 liquid Substances 0.000 claims description 3
- 238000005265 energy consumption Methods 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 8
- 230000005611 electricity Effects 0.000 description 6
- 238000013461 design Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000007620 mathematical function Methods 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000004141 dimensional analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000008303 genetic mechanism Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The application discloses a pump set optimization method based on a genetic algorithm, and belongs to the technical field of pump set optimization; comprising the following steps: step S1, collecting performance test report data and actual production data of each water pump in a water supply pump room, and analyzing to obtain a pump set optimization model, wherein the pump set optimization model comprises constraint conditions and fitness functions; step S2, applying the pump set optimization model to a water distribution unit; step S3, constructing an algorithm framework of a genetic algorithm according to the problem to be optimized and the fitness function; and S4, the pump set optimization model processes the water outlet flow and the water outlet pressure of the water distribution unit, and carries out genetic algorithm iteration to obtain an optimized pump set combination. The beneficial effects of the technical scheme are as follows: the aim of minimum energy consumption is to realize the adjustment and use of the fixed-frequency or variable-frequency pump, save energy and reduce consumption, and prolong the service life of the water pump.
Description
Technical Field
The application relates to the technical field of pump set optimization, in particular to a pump set optimization method based on a genetic algorithm.
Background
The pump set of the water supply pump room of the water works generally comprises a fixed-frequency pump set of the water pump and a variable-frequency pump set of the water pump, and the collocation of the pump set mainly depends on manual experience or a self-control equipment table checking method for a long time.
In the prior art, the traditional pump distribution combination mainly depends on a query table or manual experience, so that the power consumption of a water distribution unit of a water delivery pump room is too high, the water pump deviates from a high-efficiency interval for a long time, and the water supply is unstable, thereby influencing the service life.
Disclosure of Invention
The application aims to provide a pump set optimization method based on a genetic algorithm, which solves the technical problems;
a genetic algorithm-based pump set optimization method, comprising:
step S1, collecting performance test report data and actual production data of each water pump in a water supply pump room, and analyzing to obtain a pump set optimization model, wherein the pump set optimization model comprises constraint conditions and fitness functions;
step S2, applying the pump set optimization model to a water distribution unit;
step S3, constructing an algorithm framework of a genetic algorithm according to the problem to be optimized and the fitness function;
and S4, the pump set optimization model processes the water outlet flow and the water outlet pressure of the water distribution unit, and carries out genetic algorithm iteration to obtain an optimized pump set combination.
Preferably, after step S4, the efficiency of each water pump in the optimized pump set assembly is predicted according to the optimized pump set assembly, the predicted power consumption is estimated according to a mechanism formula, and compared with the actual power consumption, the power consumption is analyzed to obtain the saved power consumption.
Preferably, the mechanism formula is:
wherein W represents power consumption, and the unit is kW.h;
ρ represents the liquid density in 1.0×10 3 kg/m 3 ；
g represents the acceleration of gravity in 9.8m/s 2 ；
Q represents flow, in m 3 /s；
H represents the lift, and the unit is m;
η 1 representing the efficiency value of the water pump;
η 2 representing a motor efficiency value;
t represents time in h.
Preferably, step S1 comprises:
step S11, analyzing performance test report data and actual production data of each water pump, and fitting the flow of each water pump and the mechanism relation of the lift, power and efficiency corresponding to the flow;
step S12, calculating to obtain a corresponding water pump efficiency interval according to the flow rate of each water pump and the mechanism relation of the lift, power and efficiency corresponding to the flow rate, wherein the water pump efficiency interval is a range of 10% of rated power of each water pump;
and S13, establishing the pump set optimization model, and carrying out optimization solution on the fitness function based on the constraint condition of the pump set optimization model.
Preferably, the pump group optimization model in step S2 is applied to the water distribution unit according to model boundary conditions;
the model boundary conditions are:
the power consumption of the water distribution unit is more than 380 kW.h/km 3 ·Mpa；
The number of the water pump fixed-frequency pump sets or the water pump variable-frequency pump sets in the actual environment of the pump room is more than or equal to three;
each water pump is provided with a performance test report.
Preferably, the problem of optimization in step S3 is: under the condition of meeting the water demand, the water pump works in an efficiency interval and the power consumption is minimized;
the fitness function is as follows: the sum of the power of each water pump is expressed as follows:
wherein n represents the total number of internal frequency conversion pumps in the water plant, m represents the total number of frequency conversion pumps in the water plant, c i Indicating the state of the constant frequency pump c j Representing the state of the variable frequency pump, and 1 and 0 representing the on state and the off state, N i Represents the power of the constant frequency pump, N j Representing the power of the variable frequency pump.
Preferably, step S3 includes:
step S31, a plurality of initial solutions are randomly generated according to the constraint conditions and the fitness function;
step S32, coding the initial solution to obtain an initial population;
step S33, performing crossover operation and mutation operation on the initialized population to obtain crossover offspring and mutation offspring;
step S34, decoding the crossed offspring and the variant offspring, and calculating the corresponding fitness function to obtain a selected population;
and step S35, judging whether the selected population reaches a termination condition, if not, executing step S33, and if so, generating and outputting an optimal solution, wherein the genetic algorithm is ended.
Preferably, each of the initial solutions in step S31 contains a set of genes, which are binary strings or real numbers or characters.
Preferably, the constraint condition in step S31 is the water outlet flow and the water outlet pressure corresponding to the water pump efficiency interval of each water pump.
Preferably, the termination condition in step S35 is a set number of iterations or a target fitness value.
The beneficial effects of the application are as follows: by adopting the technical scheme, the aim of minimum energy consumption is achieved, the regulation and the use of the fixed-frequency or variable-frequency pump are realized, the energy is saved, the consumption is reduced, and the service life of the water pump is prolonged.
Drawings
FIG. 1 is a step diagram of a pump stack optimization method in a preferred embodiment of the present application;
FIG. 2 is a step diagram of step S1 in a preferred embodiment of the present application;
FIG. 3 is a step diagram of step S3 in a preferred embodiment of the present application;
FIG. 4 is a flow chart of an iteration of the evolutionary algorithm in a preferred embodiment of the application;
FIG. 5 is a daily unit electricity and water consumption distribution line diagram in a preferred embodiment of the present application;
FIG. 6 is a bar graph of daily unit electricity and water consumption in accordance with a preferred embodiment of the present application;
fig. 7 is a plot of water and electricity consumption per hour in accordance with a preferred embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other.
The application is further described below with reference to the drawings and specific examples, which are not intended to be limiting.
A genetic algorithm-based pump set optimization method, as shown in fig. 1, comprises the following steps:
step S1, collecting performance test report data and actual production data of each water pump in a water supply pump room, and analyzing to obtain a pump set optimization model, wherein the pump set optimization model comprises constraint conditions and fitness functions;
step S2, applying the pump set optimization model to a water distribution unit;
step S3, constructing an algorithm framework of a genetic algorithm according to the problem to be optimized and the fitness function;
and S4, the pump set optimization model processes the water outlet flow and the water outlet pressure of the water distribution unit, and carries out genetic algorithm iteration to obtain an optimized pump set combination.
Specifically, the application provides a genetic algorithm-based pump set optimization method, which is used in the field of pump set optimization, and takes actual water demand of a water supply area as model input to prevent unstable pressure of a pipe network caused by excessive or insufficient water supply of a pump station; the dependence of the artificial experience is reduced, the pump set is scientifically and reasonably combined and matched, the operation time and the start-stop times are balanced, and the water supply safety and stability are ensured.
Further specifically, the water plant data collection relies on a performance test report of each water pump in a water delivery pump house, a mechanism formula of flow, lift, efficiency and power of each water pump under different frequencies is fitted, a high-efficiency interval of each water pump is calculated as a constraint condition, and a time period is divided by design parameters of a water plant pump station and flow and lift requirements of historical actual production data; constructing an algorithm framework of a genetic algorithm, configuring the flow and the lift after the first step of time division as input, setting corresponding constraint conditions, setting search mechanisms such as crossing and mutation parameters, iteration stopping conditions and the like; the historical data is fed into the model, genetic algorithm iteration is carried out, model parameters are debugged, so that the optimal effect of the model is guaranteed, and the optimal pump set combination with different water supply requirements in each time period is generated through searching of the global optimal of the model.
In a preferred embodiment, after step S4, the efficiency of each water pump in the optimized pump set is predicted according to the optimized pump set combination, the predicted power consumption is estimated according to the mechanism formula, and compared with the actual power consumption, and the power consumption is analyzed to obtain the saved power consumption.
Specifically, the efficiency of each water pump in the pump group combination is predicted, the predicted power consumption is estimated according to a mechanism formula, and compared with the actual power consumption, the power consumption is saved through multidimensional analysis, and the actual economic value brought by a water supply plant is obtained.
In a preferred embodiment, the mechanism formula is:
wherein W represents power consumption, and the unit is kW.h;
ρ represents the liquid density in 1.0×10 3 kg/m 3 ；
g represents the acceleration of gravity in 9.8m/s 2 ；
Q represents flow, in m 3 /s；
H represents the lift, and the unit is m;
η 1 representing the efficiency value of the water pump;
η 2 representing a motor efficiency value;
t represents time in h.
In a preferred embodiment, as shown in fig. 2, step S1 includes:
step S11, analyzing performance test report data and actual production data of each water pump, and fitting the flow of each water pump and the mechanism relation of the lift, power and efficiency corresponding to the flow;
step S12, calculating to obtain a corresponding water pump efficiency interval according to the flow rate of each water pump and the mechanism relation of the lift, power and efficiency corresponding to the flow rate, wherein the water pump efficiency interval is a range of 10% of rated power of each water pump;
and S13, establishing a pump set optimization model, and carrying out optimization solution on the fitness function based on constraint conditions of the pump set optimization model.
Specifically, the performance test report of each water pump in the water delivery pump house is carefully analyzed and understood, the mechanism relation between the flow and the lift, the power and the efficiency of each water pump is fitted according to the data on the performance test report, a corresponding mathematical function formula is established, and the mechanism relation between the flow and the lift, the power and the efficiency of the variable frequency pump at different frequencies is calculated according to a similar law; the water pump efficiency interval is a water pump high-efficiency interval, the definition of the water pump high-efficiency interval is that each water pump is within 10% of rated power, and the flow range corresponding to each water pump high-efficiency interval is calculated and used as a constraint condition after a model is built; the historical data of actual production of the water plant is subjected to multidimensional analysis unit water distribution power consumption and flow and lift change trends in different time periods, wherein the multidimensional analysis unit water distribution power consumption can reflect the actual efficiency level of a water delivery pump room of the water plant, a pump distribution model can be guided to optimize the direction, the flow and lift change trend in different time periods is divided into a plurality of time periods according to the historical data, different pump group combinations are started in different time periods to respond to large water use trend changes, and the time periods can be used for responding to small water use trend changes through adjustment of control frequency.
In a preferred embodiment, the pump group optimization model in step S2 is applied to the water distribution unit according to model boundary conditions;
the model boundary conditions are:
the power consumption of the water distribution unit is more than 380 kW.h/km 3 ·Mpa；
The number of the water pump fixed-frequency pump sets or the water pump variable-frequency pump sets in the actual environment of the pump room is more than or equal to three;
each water pump is provided with a performance test report.
Specifically, in order to fully show the difference between the model and the manual experience debugging, whether the pump set model is judged according to the conditions of the water distribution unit electricity consumption multidimensional analysis, the actual environment of the pump house and the like.
More specifically, the multi-dimensional analysis of the unit water distribution and electricity consumption is carried out when the unit water distribution and electricity consumption of a water delivery pump room of a water plant is more than 380 kW.h/km 3 The efficiency of the water delivery pump house of the water plant is considered to be low, and the optimization space is large; the water pump room water pump fixed or variable frequency pump combination of the water plant is not less than 3, and a plurality of pump combinations can be matched; thirdly, each water pump needs to be provided with a performance test report for fitting the mechanism relation of key index flow and lift, efficiency and power.
In a preferred embodiment, the problem of optimization in step S3 is: under the condition of meeting the water demand, the water pump works in an efficiency interval and the power consumption is minimized;
the fitness function is: the sum of the power of each water pump is expressed as follows:
wherein n represents the total number of internal frequency conversion pumps in the water plant, m represents the total number of frequency conversion pumps in the water plant, c i Indicating the state of the constant frequency pump c j Representing the state of the variable frequency pump, and 1 and 0 representing the on state and the off state, N i Represents the power of the constant frequency pump, N j Representing the power of the variable frequency pump.
In a preferred embodiment, as shown in fig. 3 and 4, step S3 includes:
step S31, randomly generating a plurality of initial solutions according to constraint conditions and fitness functions;
step S32, coding the initial solution to obtain an initialized population;
step S33, performing cross operation and mutation operation on the initialized population to obtain cross offspring and mutation offspring;
step S34, decoding the crossed offspring and the variant offspring, and calculating the corresponding fitness function to obtain a selected population;
and step S35, judging whether the selected population reaches a termination condition, if not, executing step S33, and if so, generating and outputting an optimized solution, wherein the genetic algorithm is ended.
Specifically, before designing a genetic algorithm, a problem of explicit optimization and a fitness function need to be explicitly optimized, then, a population needs to be initialized, that is, a certain number of initial solutions are randomly generated, each solution is composed of a group of genes, the genes can be binary strings, real numbers, characters and the like, then, a selection operation is performed, a certain number of individuals are selected from the current population as the parents of the next-generation population, and the selection principle is that the higher the fitness is, the higher the probability that the individuals are selected is, so as to screen excellent solutions. Then, cross-pairing is carried out on the parent individuals, paired genes are randomly exchanged, new individuals are generated, the purpose of the cross-pairing is to increase diversity of the population, the algorithm is prevented from falling into a local optimal solution, finally, mutation operation is carried out, random gene change is carried out on the next generation individuals, new solutions are generated, the diversity of the population is further increased, the steps can be circularly carried out until the set stopping condition is reached, for example, the maximum iteration number is reached or a target fitness value is reached, and the like, through the algorithm design and the iterative operation, the genetic algorithm can find excellent solutions, and particularly in complex nonlinear optimization problems, the genetic algorithm can find a good solution.
In a preferred embodiment, each initial solution in step S31 contains a set of genes, either binary strings or real numbers or characters.
In a preferred embodiment, the constraint condition in step S31 is the water outlet flow and the water outlet pressure corresponding to the water pump efficiency interval of each water pump.
In a preferred embodiment, the termination condition in step S35 is a set number of iterations or target fitness value.
In one embodiment, the production data information of a water plant is shown in the following table, and the water plant provides data such as 6 months of water supply, water outlet pressure, power consumption, performance test reports of water pumps in a water pump room, and the like, and evaluates the value benefits brought by the optimal operation model of the intelligent pump set by combining the actual production requirements of the water plant (limiting conditions such as pump cutting times in one day).
The data required by the intelligent pump distribution method of the water delivery pump house based on the genetic algorithm comprises data of indexes such as performance test reports of each water pump in the water delivery pump house, pump station scheduling data (pump station flow and pressure), real-time water outlet flow of a water plant, real-time water outlet pressure of the water plant, real-time start-stop state of the water pump, real-time start-up frequency of the water pump and the like.
The intelligent water supply pump room pump distribution method based on the genetic algorithm can be used for judging whether two boundary conditions are optimal or not, and fig. 5, 6 and 7 are unit water distribution power consumption analysis of the water plant in the example, and the unit water distribution power consumption analysis exceeds 380 Kw.h/km 3.mpa from each dimension. Secondly, the total number of the water supply pump house stator and the variable frequency pumps is not less than 3, at least one variable frequency pump is arranged, and the boundary condition is set so as to highlight that the model can adapt to more complex pump house environments to meet different water supply demands, and more pump group collocation schemes can be provided.
The following table shows the current situation of the pump house of the water plant:
| water pump numbering | Water pump model | Rated flow rate | Rated lift | Rotational speed | Frequency conversion/power frequency |
| 1 | KP2427-5/6 | 4063 | 40 | 995 | Variable frequency |
| 2 | KP2427-5/6 | 4063 | 40 | 995 | Variable frequency |
| 3 | 800X500CW10GM | 5700 | 30 | 740 | Variable frequency |
| 4 | KP2427-5/6 | 4063 | 40 | 995 | Variable frequency |
| 5 | 800X500CW10GM | 5700 | 30 | 740 | Variable frequency |
| 6 | KP1220-9/0 | 1200 | 25 | 985 | Variable frequency |
The application background of the example is a nonlinear complex optimization problem with discrete variables (water pump parallel operation state) and continuous variables (water pump speed ratio) and equality constraint and inequality constraint, if a traditional gradient optimization method is adopted to solve the problem, the problem that a genetic algorithm is a search algorithm based on natural selection and population genetic mechanism has no special requirement on search space is considered, only the optimized problem is computable, and the method has the remarkable characteristics of strong robustness and high efficiency and practicability, so the example adopts a genetic algorithm to solve the intelligent scheduling problem of a water pump room.
According to half-year data, an intelligent pump set optimal model is adopted, power consumption and actual power consumption generated by a predicted pump set are compared, economic analysis is carried out, for reducing the start-stop times of the pump set in 1 day, the data distribution of water outlet flow and water outlet pressure of a water plant for 24 hours in 1 day is synthesized, 1 day is divided into 4 time periods according to water supply requirements, different working pump sets are matched between the time periods to meet large fluctuation of water consumption requirements, and the frequency of the working pump sets is adjusted in the time periods to meet small fluctuation of the water consumption requirements.
The flow pressure considered in the time period is the average value of the actual water demand, the time period is matched with a pump set for combination, the start and stop times are reduced, a scheme is maintained in the time period, the frequency is changed every hour, and the prediction scheme is as follows:
according to the optimal pump set scheme corresponding to each produced time period, the efficiency of each water pump in the pump set combination is predicted, the power consumption is estimated according to a mechanism formula, the power consumption is compared with the actual power consumption, the multidimensional analysis is performed to obtain the saved power consumption, and the economic value is quantized.
| Line label | Summation term: total actual power consumption in the barrel | Summation term: estimating total power consumption in barrel | Percentage of | Saving electric quantity |
| 2022-09 | 366152 | 330369 | 90.23％ | 9.77％ |
| 2022-10 | 611129 | 418592 | 68.49％ | 31.51％ |
| 2022-11 | 353573 | 305527 | 86.41％ | 13.59％ |
| 2022-12 | 428289 | 382831 | 89.39％ | 10.61％ |
| 2023-01 | 359437 | 338336 | 94.13％ | 5.87％ |
| 2023-02 | 332479 | 331581 | 99.73％ | 0.27％ |
| 2023-03 | 354809 | 341453 | 96.24％ | 3.76％ |
| Totals to | 2805868 | 2448688 | 87.27％ | 12.73％ |
In summary, the application provides a pump group optimization method based on a genetic algorithm, which comprises the following technical directions of data mining, genetic algorithm and machine learning, and aims at the service characteristics of a water delivery pump house of a water plant, so as to complete the development and design of a mechanism model genetic algorithm model, and predict corresponding pump group combinations including key indexes such as start-stop state, frequency, efficiency and distributed flow of a pump by utilizing the algorithm model to different water supply demands in historical data, thereby assisting the operation of the water plant and improving the fine management level; the intelligent pump group optimizing operation model is used for helping the water plant to solve the problems of high energy consumption, high residence time, excessive dependence on artificial experience and the like, and the solution of optimal water pump collocation combination is recommended through real-time operation data analysis, so that the water pump can always operate in a high-efficiency performance interval and can be in seamless connection with an intelligent water plant management platform to realize the aims of energy conservation and consumption reduction and improve the fine management level; the method comprises the steps of taking actual production data of a water delivery pump house of a water plant as a core, establishing a mathematical function relation between flow, lift, power and efficiency around a performance test report of each water pump of the water delivery pump house, taking historical data of the water plant as input, feeding the historical data into a genetic algorithm, taking an efficient section of the water pump and water supply requirements to be met as constraint conditions, taking the power sum of each water pump as an fitness function, globally optimizing, generating a pump set combination which meets the water supply requirements and enables the total power to be minimum, completing development and design of an intelligent pump set model, evaluating the space saving with actual power consumption, and improving economic benefits of the water plant; the method can be widely applied to water supply pump rooms of domestic waterworks, can realize direct down control of model results to equipment, brings considerable economic benefits, and improves the level of fine management.
The foregoing description is only illustrative of the preferred embodiments of the present application and is not to be construed as limiting the scope of the application, and it will be appreciated by those skilled in the art that equivalent substitutions and obvious variations may be made using the description and illustrations of the present application, and are intended to be included within the scope of the present application.
Claims (10)
1. A genetic algorithm-based pump set optimization method, comprising:
step S1, collecting performance test report data and actual production data of each water pump in a water supply pump room, and analyzing to obtain a pump set optimization model, wherein the pump set optimization model comprises constraint conditions and fitness functions;
step S2, applying the pump set optimization model to a water distribution unit;
step S3, constructing an algorithm framework of a genetic algorithm according to the problem to be optimized and the fitness function;
and S4, the pump set optimization model processes the water outlet flow and the water outlet pressure of the water distribution unit, and carries out genetic algorithm iteration to obtain an optimized pump set combination.
2. The genetic algorithm-based pump stack optimization method according to claim 1, wherein after step S4, the efficiency of each water pump in the optimized pump stack assembly is predicted according to the optimized pump stack assembly, the predicted power consumption is estimated according to a mechanism formula, and compared with the actual power consumption, the power consumption is analyzed to obtain the saved power consumption.
3. The genetic algorithm-based pump assembly optimization method of claim 2, wherein the mechanism formula is:
wherein W represents power consumption, and the unit is kW.h;
ρ represents the liquid density in 1.0×10 3 kg/m 3 ；
g represents the acceleration of gravity in 9.8m/s 2 ；
Q represents flow, in m 3 /s；
H represents the lift, and the unit is m;
η 1 representing the efficiency value of the water pump;
η 2 representing a motor efficiency value;
t represents time in h.
4. The genetic algorithm-based pump set optimization method according to claim 1, wherein step S1 comprises:
step S11, analyzing performance test report data and actual production data of each water pump, and fitting the flow of each water pump and the mechanism relation of the lift, power and efficiency corresponding to the flow;
step S12, calculating to obtain a corresponding water pump efficiency interval according to the flow rate of each water pump and the mechanism relation of the lift, power and efficiency corresponding to the flow rate, wherein the water pump efficiency interval is a range of 10% of rated power of each water pump;
and S13, establishing the pump set optimization model, and carrying out optimization solution on the fitness function based on the constraint condition of the pump set optimization model.
5. The genetic algorithm-based pump stack optimization method according to claim 1, wherein the pump stack optimization model in step S2 is applied to the water distribution unit according to model boundary conditions;
the model boundary conditions are:
the power consumption of the water distribution unit is more than 380 kW.h/km 3 ·Mpa；
The number of the water pump fixed-frequency pump sets or the water pump variable-frequency pump sets in the actual environment of the pump room is more than or equal to three;
each water pump is provided with a performance test report.
6. The genetic algorithm-based pump assembly optimization method according to claim 1, wherein the problem of optimization in step S3 is: under the condition of meeting the water demand, the water pump works in an efficiency interval and the power consumption is minimized;
the fitness function is as follows: the sum of the power of each water pump is expressed as follows:
wherein n represents the total number of internal frequency conversion pumps in the water plant, m represents the total number of frequency conversion pumps in the water plant, c i Indicating the state of the constant frequency pump c j Representing the status of the variable frequency pump and using 1 and 0Indicating the on state and the off state, N i Represents the power of the constant frequency pump, N j Representing the power of the variable frequency pump.
7. The genetic algorithm-based pump set optimization method according to claim 1, wherein step S3 comprises:
step S31, a plurality of initial solutions are randomly generated according to the constraint conditions and the fitness function;
step S32, coding the initial solution to obtain an initial population;
step S33, performing crossover operation and mutation operation on the initialized population to obtain crossover offspring and mutation offspring;
step S34, decoding the crossed offspring and the variant offspring, and calculating the corresponding fitness function to obtain a selected population;
and step S35, judging whether the selected population reaches a termination condition, if not, executing step S33, and if so, generating and outputting an optimal solution, wherein the genetic algorithm is ended.
8. The genetic algorithm-based pump set optimization method of claim 7, wherein each of the initial solutions in step S31 contains a set of genes, the genes being binary strings or real numbers or characters.
9. The genetic algorithm-based pump stack optimization method according to claim 7, wherein the constraint condition in the step S31 is a water outlet flow rate and a water outlet pressure corresponding to a water pump efficiency interval of each water pump.
10. The method of claim 7, wherein the termination condition in step S35 is a set number of iterations or a target fitness value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310676886.0A CN116702611A (en) | 2023-06-08 | 2023-06-08 | Pump unit optimization method based on genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310676886.0A CN116702611A (en) | 2023-06-08 | 2023-06-08 | Pump unit optimization method based on genetic algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116702611A true CN116702611A (en) | 2023-09-05 |
Family
ID=87835261
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310676886.0A Pending CN116702611A (en) | 2023-06-08 | 2023-06-08 | Pump unit optimization method based on genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116702611A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117519054A (en) * | 2023-12-11 | 2024-02-06 | 广州智业节能科技有限公司 | High-efficient cold station control system |
| CN117519054B (en) * | 2023-12-11 | 2024-06-11 | 广州智业节能科技有限公司 | High-efficient cold station control system |
-
2023
- 2023-06-08 CN CN202310676886.0A patent/CN116702611A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117519054A (en) * | 2023-12-11 | 2024-02-06 | 广州智业节能科技有限公司 | High-efficient cold station control system |
| CN117519054B (en) * | 2023-12-11 | 2024-06-11 | 广州智业节能科技有限公司 | High-efficient cold station control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107153885B (en) | Real-time power generation plan optimization method considering deep peak shaving of thermal power generating unit | |
| CN109636043B (en) | Adaptive optimization method and system for power generation dispatching of cascade hydropower system | |
| CN107578288B (en) | Non-invasive load decomposition method considering user power consumption mode difference | |
| CN113156817B (en) | Intelligent pump allocation method for pump station | |
| CN102780235B (en) | Pumped storage power station dispatching method on basis of genetic algorithm | |
| CN105156327A (en) | Energy-saving control method for compressed air industrial screw-type air compressor group control system | |
| CN106786764A (en) | A kind of utilization hydrogen generating system wind-powered electricity generation of dissolving abandons the hydrogen manufacturing capacity configuration optimizing method of wind | |
| CN111767677A (en) | GA algorithm-based cascade pump station group lift optimal distribution method | |
| CN112018756A (en) | Day-ahead robust coordinated optimization scheduling method for gas-electricity combined system | |
| CN110729721B (en) | Global spare capacity calculation method for power system | |
| CN116702611A (en) | Pump unit optimization method based on genetic algorithm | |
| CN112418732A (en) | Multi-energy hub-containing comprehensive energy system planning method and system based on maximum flow and minimum cut theorem | |
| Coelho et al. | Analysis of diverse optimisation algorithms for pump scheduling in water supply systems | |
| CN110380407B (en) | Power distribution network operation optimization method considering agricultural electric irrigation and drainage loads | |
| CN105552941B (en) | A kind of distributed generation resource peak capacity optimization method | |
| CN114123175B (en) | Distributed control method for power distribution network considering generalized demand side resource alliance characteristics | |
| CN111915088B (en) | Optimized control method for reducing energy consumption of pump set | |
| CN112068439B (en) | Family energy management optimization method based on renewable energy sharing model | |
| CN110189231B (en) | Method for determining optimal power supply scheme of power grid based on improved genetic algorithm | |
| CN114021851A (en) | Multistage correlation section quota adaptability assessment and optimization calculation method | |
| CN114243737A (en) | Pumped storage power station capacity benefit calculation method based on production operation simulation | |
| CN111027782B (en) | Building secondary water supply optimal scheduling method and device based on centerless genetic algorithm | |
| Fan et al. | A Dynamic Multi-Stage Planning Method for Integrated Energy Systems considering Development Stages | |
| Salvini et al. | A memetic computing approach for unit commitment with energy storage systems | |
| Marcelino et al. | Application of evolutionary multiobjective algorithms for solving the problem of energy dispatch in hydroelectric power plants |
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 |