CN116050121A - Water pump characteristic curve parameter optimization method based on gradient algorithm - Google Patents

Water pump characteristic curve parameter optimization method based on gradient algorithm Download PDF

Info

Publication number
CN116050121A
CN116050121A CN202310019105.0A CN202310019105A CN116050121A CN 116050121 A CN116050121 A CN 116050121A CN 202310019105 A CN202310019105 A CN 202310019105A CN 116050121 A CN116050121 A CN 116050121A
Authority
CN
China
Prior art keywords
water pump
parallel
characteristic curve
water
pump
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
Application number
CN202310019105.0A
Other languages
Chinese (zh)
Inventor
王立彪
柳景青
张卫平
张清周
李亚林
秦亚培
吴伟峰
周华珍
郑家骏
张淼佳
厉海东
于俊锋
李秀娟
王江霞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Yuhang Water Holding Group Co ltd
Zhejiang University ZJU
Original Assignee
Hangzhou Yuhang Water Holding Group Co ltd
Zhejiang University ZJU
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hangzhou Yuhang Water Holding Group Co ltd, Zhejiang University ZJU filed Critical Hangzhou Yuhang Water Holding Group Co ltd
Priority to CN202310019105.0A priority Critical patent/CN116050121A/en
Publication of CN116050121A publication Critical patent/CN116050121A/en
Pending legal-status Critical Current

Links

Images

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/08—Fluids
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A20/00—Water conservation; Efficient water supply; Efficient water use

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Control Of Positive-Displacement Pumps (AREA)

Abstract

The invention provides a water pump characteristic curve parameter optimization method based on a gradient algorithm, which comprises the following steps: collecting operation data of water pumps connected in parallel at different periods, wherein the operation data comprise a water pump combination operation scheme, parallel pressure, parallel flow and the like; establishing a water pump characteristic curve parameter optimization model, and determining an objective function; and solving the optimization model based on the gradient descent method to obtain the optimal characteristic curve parameters of each water pump. The invention has the beneficial effects that: the invention has high calculation efficiency and stable and reliable calculation result; the invention does not need to set excessive parameter values, and is convenient to operate; the invention can be carried out under normal water supply conditions without affecting the normal operation of the pipe network.

Description

Water pump characteristic curve parameter optimization method based on gradient algorithm
Technical Field
The invention belongs to the technical field of municipal engineering, and particularly relates to a water pump characteristic curve parameter optimization method based on a gradient algorithm.
Background
The urban water supply system bears the task of conveying the drinking water treated by the water plant to thousands of households, wherein the water pump is used for lifting the pressure of the water supply system and meeting the pressure requirement of users for normal water use. The leakage and energy consumption of a water supply network are the most concerned problems of water supply enterprises, and how to reduce the leakage and the energy consumption of water supply of the network is the focus of the water supply enterprises and researchers under the condition of meeting the normal water consumption of users. A pipe network dynamic hydraulic model is built based on the water supply pipe network basic data and the real-time operation data, and online real-time optimal scheduling is realized for the operation of the water supply pump station, so that the method is the most effective measure for realizing the energy conservation and leakage reduction of the pipe network. Therefore, the accuracy of the characteristic curve parameters of the water pump plays a vital role in the effect of optimizing the scheduling of the real-time combination of the water pump. The characteristic curve of the water pump refers to a functional relation curve of the outlet pressure of the water pump along with the change of flow, and reflects the potential working capacity of the water pump. In order to meet the change of water quantity and water pressure required by different working conditions in an urban water supply network system, a plurality of water pumps are often required to be arranged to work in parallel, and the flow and the pressure of a pump station are regulated through the combination of different water pumps. The characteristic curve of the water pump is the basis for controlling the water pump, and to realize scientific control of the pump station, the characteristic curve of the water pump needs to be accurately mastered, so that the determination of the characteristic curve of each water pump is very important. Therefore, the accurate water pump characteristic curve parameters can improve the efficiency and the accuracy of checking the pipe network model parameters (node flow and pipeline resistance coefficient), ensure that the pipe network model simulation result can better accord with the pipe network actual operation working condition, and provide model precision support for the engineering application effects of follow-up pipe network planning and transformation based on models, pump station optimization scheduling, pipe network partition management, pipe network leakage positioning and the like.
The technical proposal of the prior art is as follows: the existing optimization method of the characteristic curve parameters of the water pump is mainly divided into a water pump independent measurement method and a target optimization algorithm based on an intelligent algorithm: (1) According to the method, only the current water pump to be measured is started by closing other water pumps, the flow and the pressure of the water pump in different water use periods are collected by using a portable electromagnetic flowmeter and a pressure meter, and the optimal characteristic curve parameter value of the water pump is determined by using a nonlinear fitting algorithm in statistics according to the collected flow and pressure data; (2) According to the target optimization algorithm based on the intelligent algorithm, the method does not need to close other water pumps, under the condition that normal operation of a pipe network is not affected, the combination mode, parallel pressure and flow of the water pumps in the pump stations in different periods are recorded, and then the optimal characteristic curve parameters of each water pump in the pump stations are determined by using the intelligent algorithm (for example, a genetic algorithm) according to the collected flow and pressure data.
Disadvantages of the prior art: in practical engineering practice, the two traditional water pump characteristic curve parameter optimization methods have respective limitations.
The water pump independent measurement method is suitable for a water supply system of a single water pump, for example: secondary water supply system, halfway booster pump station, etc. However, at present, a water supply pump station generally adopts a mode of connecting a plurality of water pumps in parallel to supply water, and the characteristic curve parameter of each pump is measured independently, so that other water pumps are required to be turned off. The method influences normal water supply of the pump station, and is easy to cause insufficient water supply or insufficient water supply pressure of a user, so that in the pump station with multiple water pumps connected in parallel, the method determines the optimal characteristic curve parameters of each water pump, has certain difficulty in the implementation process and has low feasibility.
Compared with a water pump independent measurement method, the target optimization algorithm based on the intelligent algorithm does not need to close other water pumps, and does not influence normal water supply of a pump station. The disadvantage of this approach is the uncertainty of the intelligent optimization algorithm, which is determined by the solution mechanism of the algorithm itself. Taking a common genetic algorithm as an example, parameters need to be initialized before solving, and corresponding parameters need to be set, for example: population size, crossover probability, coding probability, real number coding type and other parameter values. The different set values of the parameter values can cause different calculation results, are easy to fall into local optimum, and under the condition of a large number of parallel water pumps, the search space is excessively large (exponentially increases), so that the global optimum solution of the characteristic curve parameters of each water pump is difficult to obtain.
Disclosure of Invention
In view of the above, the present invention aims to provide a gradient algorithm-based optimization method for the characteristic curve parameters of a water pump, so as to solve the bottleneck problem of the above-mentioned optimization method for the characteristic curve parameters of the existing water pump.
In order to achieve the above purpose, the technical scheme of the invention is realized as follows:
a water pump characteristic curve parameter optimization method based on a gradient algorithm comprises the following steps:
s1: collecting operation data of the parallel water pumps at different time periods;
s2: establishing a water pump characteristic curve parameter optimization model;
s3: and solving the water pump characteristic curve parameter optimization model based on the gradient descent method.
Further, the step of collecting the operation data of the parallel water pump at different time periods in the step S1 includes the following steps:
s11: checking whether the pressure gauge and the flowmeter work normally or not, and correcting the pressure gauge and the flowmeter;
s12: according to the water pump installation data, reading the elevation z of the bottom of the water absorbing well 1 Mounting elevation z of pressure gauge behind pump 2 ；
S13: reading data of a pressure gauge, data of a flowmeter and data of a liquid level meter of a water absorbing well after being connected in parallel at different moments i;
s14: the pressure of the parallel water pump at each moment is calculated by equation 1-1.
Further, the formula 1-1 is as follows:
H (i) ＝z 2 -z 1 +h (i) +P (i) equation 1-1
Wherein H is (i) For the pressure of the parallel water pump at time i (i e 1, 2., m), P (i) As data for the post-pump pressure gauge,
Figure BDA0004041760720000041
is the data of the flowmeter, h (i) For the data of the liquid level meter of the water absorbing well, z 1 For the elevation of the bottom of the water-absorbing well, z 2 And installing an elevation for a pressure gauge behind the pump.
Further, the step S2 of establishing the optimization model of the pump characteristic curve parameter includes the following steps:
s21: the method comprises the steps that a pump station is provided with n pumps which are connected in parallel, a pressure gauge and a flowmeter are respectively arranged at an outlet of the pump station, the pressure gauge and the flowmeter record the pressure and the total flow after the water pumps are connected in parallel, and the pressure and the total flow after the water pumps are connected in parallel are respectively measured at different moments of the day;
s22: assuming that m sets of data are measured, the pressure and total flow after water pump paralleling is expressed as:
Figure BDA0004041760720000042
s23: based on the step S21 and the step S22, a characteristic curve of each water pump and a total characteristic curve after n water pumps are connected in parallel are obtained, the expression of the characteristic curve of each water pump is represented by formulas 1-2, and the expression of the total characteristic curve after n water pumps are connected in parallel is represented by formulas 1-3;
s24: optimizing the formula 1-3 to obtain an objective function, wherein the expression of the objective function is the formula 1-4.
Further, in step S21, when the water pumps are operated in parallel, the outlet pressure of each water pump is equal, and the total flow is the sum of the outlet flows of each water pump.
Further, the formulas 1-2 and 1-3 are expressed as follows:
Figure BDA0004041760720000043
/>
Figure BDA0004041760720000044
in the method, in the process of the invention,
Figure BDA0004041760720000051
the total flow after the water pumps are connected in parallel; h is the outlet pressure of the parallel water pump; omega j The relative rotation speed of the water pump j; h is a 0j Is the virtual total lift of the water pump j; r is (r) j ，γ j Is the curve coefficient of the water pump j.
Further, the formulas 1 to 4 are expressed as:
Figure BDA0004041760720000052
wherein m is the number of samples; n is the number of water pumps connected in parallel;
Figure BDA0004041760720000053
for the operation of the pump j corresponding to sample i,
Figure BDA0004041760720000054
q j (H (i) ) Parallel pressure H for sample i water pump (i) The outlet flow of the corresponding water pump j; />
Figure BDA0004041760720000055
And (5) the total flow is connected in parallel for the sample i water pump.
Further, the solving of the water pump characteristic curve parameter optimization model based on the gradient descent method in the step S3 includes the following steps:
s31: determining a cost function, wherein the expression of the cost function is shown as a formula 1-5 and a formula 1-6;
s32: calculating the gradient of the parameter by the formulas 1-7, 1-8, 1-9 and 1-10;
s33: and carrying out gradient iteration solution through the formulas 1-11, 1-12, 1-13 and 1-14 to obtain the optimal parameter value of the characteristic curve of the water pump.
Further, the formulas 1 to 5 and 1 to 6 are expressed as:
Figure BDA0004041760720000056
Figure BDA0004041760720000061
wherein m is the number of samples; n is the number of water pumps connected in parallel;
Figure BDA0004041760720000062
for the operation of the pump j corresponding to sample i,
Figure BDA0004041760720000063
q j (H (i) ) Parallel pressure H for sample i water pump (i) The outlet flow of the corresponding water pump j; />
Figure BDA0004041760720000064
Water pump for sample iTotal flow, omega in parallel j For the relative rotation speed of the water pump j, h 0j Is the virtual total lift of the water pump j; r is (r) j ，γ j Is the curve coefficient of the water pump j.
Further, the formulas 1-7, 1-8, 1-9, and 1-10 are expressed as:
Figure BDA0004041760720000065
/>
Figure BDA0004041760720000066
Figure BDA0004041760720000067
Figure BDA0004041760720000068
wherein q is j (H (i) ) Parallel pressure H for sample i water pump (i) The outlet flow of the corresponding water pump j;
Figure BDA0004041760720000071
for the total flow of the sample i water pump in parallel connection, omega j For the relative rotation speed of the water pump j, h 0j Is the virtual total lift of the water pump j; r is (r) j ，γ j Is the curve coefficient of the water pump j.
Further, the formulas 1 to 11, 1 to 12, 1 to 13, and 1 to 14 are expressed as:
Figure BDA0004041760720000072
Figure BDA0004041760720000073
Figure BDA0004041760720000074
Figure BDA0004041760720000075
wherein q is j (H (i) ) Parallel pressure H for sample i water pump (i) The outlet flow of the corresponding water pump j;
Figure BDA0004041760720000076
for the total flow of the sample i water pump in parallel connection, omega j For the relative rotation speed of the water pump j, h 0j Is the virtual total lift of the water pump j; r is (r) j ，γ j Is the curve coefficient of the water pump j.
Compared with the prior art, the water pump characteristic curve parameter optimization method based on the gradient algorithm has the following advantages:
the water pump characteristic curve parameter optimization method based on the gradient algorithm is high in calculation efficiency and stable and reliable in calculation result; the invention does not need to set excessive parameter values, and is convenient to operate; the invention can be carried out under normal water supply conditions without affecting the normal operation of the pipe network.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a parallel water pump characteristic curve test according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a characteristic curve of a case in which two water pumps are connected in parallel according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a change curve of an objective function value in a case solving process according to an embodiment of the present invention;
fig. 4 is a schematic diagram of two pump characteristic curves after case correction and a characteristic curve after parallel connection according to an embodiment of the present invention.
Detailed Description
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.
In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first", "a second", etc. may explicitly or implicitly include one or more such feature. In the description of the present invention, unless otherwise indicated, the meaning of "a plurality" is two or more.
In the description of the present invention, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art in a specific case.
The invention will be described in detail below with reference to the drawings in connection with embodiments.
As shown in fig. 1 to 4, a gradient algorithm-based optimization method for characteristic curve parameters of a water pump comprises the following steps:
s1: collecting operation data of the parallel water pump at different time intervals according to the steps S11-S14:
s11: checking whether the pressure gauge and the flowmeter work normally or not, and correcting the pressure gauge and the flowmeter;
s12: according to the water pump installation basic data, reading the elevation z of the bottom of the water absorption well 1 Mounting elevation z of pressure gauge behind pump 2 ；
S13: the pump-back pressure gauge data (P) after the parallel connection of different moments i ( i e 1,2, m) are read out (i) ) Flow meter data
Figure BDA0004041760720000091
And the water level meter data of the suction well (depth h) (i) )；
S14, namely: the pressure of the parallel water pump at each moment is calculated, and the specific formula is as follows:
H (i) ＝z 2 -z 1 +h (i) +P (i) equation 1-1
Wherein H is (i) The pressure of the water pump is connected in parallel for time i ( i e 1,2, m).
S2: establishing a water pump characteristic curve parameter optimization model
The pump station is provided with n pumps which are connected in parallel, the outlet of the pump station is respectively provided with a pressure gauge and a flowmeter, the pressure and the total flow after the water pumps are connected in parallel can be recorded, the pressure and the total flow after the water pumps are connected in parallel are respectively measured at different moments of the day, and the pressure and the total flow after the water pumps are connected in parallel can be expressed as follows:
Figure BDA0004041760720000101
a test schematic diagram of the pump station parallel water pump characteristic curve is shown in figure 1. When the water pumps are in parallel connection, the outlet pressure of each water pump is equal, and the total flow is the sum of the outlet flow of each water pump.
The pump station is provided with n water pumps which are operated in parallel, and the characteristic curve of each water pump can be expressed as
Figure BDA0004041760720000102
The total characteristic curve after the parallel connection of n water pumps can be expressed as:
Figure BDA0004041760720000103
in the middle of
Figure BDA0004041760720000104
The total flow after the water pumps are connected in parallel; h is the outlet pressure of the parallel water pump; omega j The relative rotation speed of the water pump j; h is a 0j Is the virtual total lift of the water pump j; r is (r) j ，γ j Is the curve coefficient of the water pump j.
The problem of determining the parallel characteristic curves of n water pumps in the pump station becomes an optimization problem, and the corresponding objective function is as follows:
Figure BDA0004041760720000111
wherein m is the number of samples; n is the number of water pumps connected in parallel;
Figure BDA0004041760720000112
for the operation of the pump j corresponding to sample i,
Figure BDA0004041760720000113
q j (H (i) ) Parallel pressure H for sample i water pump (i) The outlet flow of the corresponding water pump j; />
Figure BDA0004041760720000114
And (5) the total flow is connected in parallel for the sample i water pump.
The parameter to be solved for this optimization problem is ω 1 ,r 1 ,h 01 ,γ 1 ,...,ω n ,r n ,h 0n ,γ n I.e. the characteristic curve coefficient of each water pump.
S3: solving the optimization model based on gradient descent method
S31: a cost function is determined. The optimization problem aims at solving the characteristic curve coefficient of each water pump and meeting the minimization of an objective function. The solution of the optimization problem is carried out by adopting a gradient descent method, and then the cost function is as follows:
Figure BDA0004041760720000115
Figure BDA0004041760720000116
s32: the gradient of the parameter is calculated as follows:
Figure BDA0004041760720000117
/>
Figure BDA0004041760720000121
Figure BDA0004041760720000122
Figure BDA0004041760720000123
s33: and (3) carrying out gradient iteration solution to obtain the optimal parameter value of the characteristic curve of the water pump, wherein the optimal parameter value is as follows:
Figure BDA0004041760720000124
Figure BDA0004041760720000125
Figure BDA0004041760720000126
Figure BDA0004041760720000127
the invention has high calculation efficiency and stable and reliable calculation result; the invention does not need to set excessive parameter values, and is convenient to operate; the invention can be carried out under normal water supply conditions without affecting the normal operation of the pipe network.
Example 1
Two water pumps in a certain pump station work in parallel, and the parallel pressure and the total flow of the two water pumps are respectively measured at different time periods of the day, and the result is shown in figure 2. The known water pump 1 is a constant-speed pump, the water pump 2 is a variable-frequency pump, the rotation speed ratio in the test stage is 0.95, and according to the characteristic curve of the factory water pump, the initial values of two water pump parameters are set as follows: rotation speed ratio w= [1,0.95 ]]The method comprises the steps of carrying out a first treatment on the surface of the Coefficient r= [20,25]The method comprises the steps of carrying out a first treatment on the surface of the Virtual lift h 0 ＝[30,45]The method comprises the steps of carrying out a first treatment on the surface of the Coefficient γ= [1.9,2.0 ]]。
The characteristic curve coefficient of the water pump 1 is calculated to be w=1, r=19.67 and h 0 29.98, γ=1.89, so the pump 1 characteristic curve is h=29.98-19.67Q 1.89 。
The characteristic coefficient of the water pump 2 is w=0.95, r=25.10, h 0 Since =49.94 and γ=2.14, the characteristic curve of the water pump 1 is
Figure BDA0004041760720000131
The change of the objective function in the iterative calculation process is shown in fig. 3, and the characteristic curves of the two water pumps and the characteristic curves after parallel connection are shown in fig. 4.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.

Claims (10)

1. A water pump characteristic curve parameter optimization method based on a gradient algorithm is characterized by comprising the following steps of: the method comprises the following steps:
s1: collecting operation data of the parallel water pumps at different time periods;
s2: establishing a water pump characteristic curve parameter optimization model;
s3: and solving the water pump characteristic curve parameter optimization model based on the gradient descent method.
2. The method for optimizing the characteristic curve parameters of the water pump based on the gradient algorithm according to claim 1, wherein the method comprises the following steps: the step S1 of collecting the operation data of the parallel water pump at different time intervals comprises the following steps:
s11: checking whether the pressure gauge and the flowmeter work normally or not, and correcting the pressure gauge and the flowmeter;
s12: according to the water pump installation data, reading the elevation z of the bottom of the water absorbing well 1 Mounting elevation z of pressure gauge behind pump 2 ；
S13: reading data of a pressure gauge, data of a flowmeter and data of a liquid level meter of a water absorbing well after being connected in parallel at different moments i;
s14: the pressure of the parallel water pump at each moment is calculated by equation 1-1.
3. The method for optimizing the characteristic curve parameters of the water pump based on the gradient algorithm according to claim 2, wherein the method comprises the following steps: the formula 1-1 is as follows:
H (i) ＝z 2 -z 1 +h (i) +P (i) equation 1-1
Wherein H is (i) For the pressure of the parallel water pump at time i (i e 1, 2., m), P (i) As data for the post-pump pressure gauge,
Figure FDA0004041760710000011
is the data of the flowmeter, h (i) For the data of the liquid level meter of the water absorbing well, z 1 For the elevation of the bottom of the water-absorbing well, z 2 And installing an elevation for a pressure gauge behind the pump.
4. The method for optimizing the characteristic curve parameters of the water pump based on the gradient algorithm according to claim 1, wherein the method comprises the following steps: the step S2 of establishing the water pump characteristic curve parameter optimization model comprises the following steps:
s21: the method comprises the steps that a pump station is provided with n pumps which are connected in parallel, a pressure gauge and a flowmeter are respectively arranged at an outlet of the pump station, the pressure gauge and the flowmeter record the pressure and the total flow after the water pumps are connected in parallel, and the pressure and the total flow after the water pumps are connected in parallel are respectively measured at different moments of the day;
s22: assuming that m sets of data are measured, the pressure and total flow after water pump paralleling is expressed as:
Figure FDA0004041760710000021
H (i) ，(i＝1,2,…,m)；
s23: based on the step S21 and the step S22, a characteristic curve of each water pump and a total characteristic curve after n water pumps are connected in parallel are obtained, the expression of the characteristic curve of each water pump is represented by formulas 1-2, and the expression of the total characteristic curve after n water pumps are connected in parallel is represented by formulas 1-3;
s24: optimizing the formulas 1-3 to obtain an objective function, wherein the expression of the objective function is shown as formulas 1-4;
in step S21, when the water pumps are operated in parallel, the outlet pressure of each water pump is equal, and the total flow is the sum of the outlet flows of each water pump.
5. The gradient algorithm-based water pump characteristic curve parameter optimization method as claimed in claim 4, wherein the method comprises the following steps: the formulas 1-2 and 1-3 are expressed as follows:
Figure FDA0004041760710000022
Figure FDA0004041760710000031
in the method, in the process of the invention,
Figure FDA0004041760710000032
the total flow after the water pumps are connected in parallel; h is the outlet pressure of the parallel water pump; omega j The relative rotation speed of the water pump j; h is a 0j Is the virtual total lift of the water pump j; r is (r) j ，γ j Is the curve coefficient of the water pump j.
6. The gradient algorithm-based water pump characteristic curve parameter optimization method as claimed in claim 4, wherein the method comprises the following steps: the formulas 1-4 are expressed as:
Figure FDA0004041760710000033
wherein m is the number of samples; n is the number of water pumps connected in parallel;
Figure FDA0004041760710000034
for the operation of the pump j corresponding to sample i,
Figure FDA0004041760710000035
q j (H (i) ) Parallel pressure H for sample i water pump (i) The outlet flow of the corresponding water pump j; />
Figure FDA0004041760710000036
And (5) the total flow is connected in parallel for the sample i water pump.
7. The method for optimizing the characteristic curve parameters of the water pump based on the gradient algorithm according to claim 1, wherein the method comprises the following steps: the solution to the water pump characteristic curve parameter optimization model based on the gradient descent method in the step S3 comprises the following steps:
s31: determining a cost function, wherein the expression of the cost function is shown as a formula 1-5 and a formula 1-6;
s32: calculating the gradient of the parameter by the formulas 1-7, 1-8, 1-9 and 1-10;
s33: and carrying out gradient iteration solution through the formulas 1-11, 1-12, 1-13 and 1-14 to obtain the optimal parameter value of the characteristic curve of the water pump.
8. The gradient algorithm-based optimization method for the characteristic curve parameters of the water pump according to claim 7, wherein the method comprises the following steps of: the formulas 1-5 and 1-6 are expressed as:
Figure FDA0004041760710000041
Figure FDA0004041760710000042
wherein m is the number of samples; n is the number of water pumps connected in parallel;
Figure FDA0004041760710000043
for the operation of the pump j corresponding to sample i,
Figure FDA0004041760710000044
q j (H (i) ) Parallel pressure H for sample i water pump (i) The outlet flow of the corresponding water pump j; />
Figure FDA0004041760710000045
For the total flow of the sample i water pump in parallel connection, omega j For the relative rotation speed of the water pump j, h 0j Is the virtual total lift of the water pump j; r is (r) j ，γ j Is the curve coefficient of the water pump j.
9. The gradient algorithm-based optimization method for the characteristic curve parameters of the water pump according to claim 7, wherein the method comprises the following steps of: the formulas 1-7, 1-8, 1-9 and 1-10 are expressed as follows:
Figure FDA0004041760710000046
/>
Figure FDA0004041760710000051
Figure FDA0004041760710000052
Figure FDA0004041760710000053
wherein q is j (H (i) ) Parallel pressure H for sample i water pump (i) The outlet flow of the corresponding water pump j;
Figure FDA0004041760710000054
for the total flow of the sample i water pump in parallel connection, omega j For the relative rotation speed of the water pump j, h 0j Is the virtual total lift of the water pump j; r is (r) j ，γ j Is the curve coefficient of the water pump j.
10. The gradient algorithm-based optimization method for the characteristic curve parameters of the water pump according to claim 7, wherein the method comprises the following steps of: the formulas 1-11, 1-12, 1-13, and 1-14 are expressed as:
Figure FDA0004041760710000055
Figure FDA0004041760710000056
Figure FDA0004041760710000057
Figure FDA0004041760710000061
wherein q is j (H (i) ) Parallel pressure H for sample i water pump (i) The outlet flow of the corresponding water pump j;
Figure FDA0004041760710000062
for the total flow of the sample i water pump in parallel connection, omega j For the relative rotation speed of the water pump j, h 0j Is the virtual total lift of the water pump j; r is (r) j ，γ j Is the curve coefficient of the water pump j. />
CN202310019105.0A 2023-01-06 2023-01-06 Water pump characteristic curve parameter optimization method based on gradient algorithm Pending CN116050121A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310019105.0A CN116050121A (en) 2023-01-06 2023-01-06 Water pump characteristic curve parameter optimization method based on gradient algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310019105.0A CN116050121A (en) 2023-01-06 2023-01-06 Water pump characteristic curve parameter optimization method based on gradient algorithm

Publications (1)

Publication Number Publication Date
CN116050121A true CN116050121A (en) 2023-05-02

Family

ID=86126977

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310019105.0A Pending CN116050121A (en) 2023-01-06 2023-01-06 Water pump characteristic curve parameter optimization method based on gradient algorithm

Country Status (1)

Country Link
CN (1) CN116050121A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117041303A (en) * 2023-10-09 2023-11-10 睿兴科技(天津)有限公司 Data transmission method and system for intelligent diagnosis of water pump

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117041303A (en) * 2023-10-09 2023-11-10 睿兴科技(天津)有限公司 Data transmission method and system for intelligent diagnosis of water pump
CN117041303B (en) * 2023-10-09 2023-12-15 睿兴科技(天津)有限公司 Data transmission method and system for intelligent diagnosis of water pump

Similar Documents

Publication Publication Date Title
CN102541015B (en) Intelligent energy efficiency control system and method
CN101247045B (en) Electric voltage safety monitoring method based on voltage stabilization field in partition load space
CN116050121A (en) Water pump characteristic curve parameter optimization method based on gradient algorithm
CN111306612B (en) Secondary network regulation and control method and system for heat exchange station
CN101858095A (en) Processing method and device for providing auxiliary dispatching data of water supply network
CN110056781A (en) Water supply network flow monitoring point optimization placement method
CN105928056B (en) Boiler group control system based on water admixing device
CN104964719A (en) Household electronic water meter flow metering method based on BP neural network
CN106228276B (en) Water resource optimization configuration method for single pump station-single reservoir system for directly supplementing channels under insufficient irrigation condition
WO2021238170A1 (en) Method and system for calculation and transaction of binary water rights
CN110443418A (en) Urban water consumption prediction technique based on GA-BP neural network
CN108266792A (en) It is a kind of to build the quick calculation method for representing temperature
CN101916313A (en) Function optimization method for city water-supply pipe network
CN110414712A (en) Serve the water supply network Optimal Operation Model method for building up of control leakage loss
CN112596386A (en) Matlab-based urban drainage system simulation control mixed model with mechanism model, concept model and data model
CN110969342B (en) Method for balancing small-reservoir-capacity hydroelectric generation safety and flood control risk management and control
CN114134955B (en) Ad hoc network and pressure management system and water pressure management method of self-powered water supply network
CN108959754A (en) A kind of calculation method of river ecological minimum flow
CN113847644B (en) Secondary net valve opening control method and system
CN113651402B (en) Water treatment chlorination control method and device
CN113626959B (en) Sewage pipe network hydraulic model building method based on three-dimensional geographic information
CN207365324U (en) A kind of big data intelligent air condition equipment with household metering
CN114330156A (en) Channel flow measurement method based on scale effect of central cylindrical rectangular groove
CN112711229B (en) Intelligent optimization energy-saving system based on multi-correlation factor energy consumption prediction
CN203823884U (en) Heat metering management system for heating based on hydraulic power balance

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