CN112696344B - Intelligent control method for water supply booster pump station - Google Patents
Intelligent control method for water supply booster pump station Download PDFInfo
- Publication number
- CN112696344B CN112696344B CN202011536808.3A CN202011536808A CN112696344B CN 112696344 B CN112696344 B CN 112696344B CN 202011536808 A CN202011536808 A CN 202011536808A CN 112696344 B CN112696344 B CN 112696344B
- Authority
- CN
- China
- Prior art keywords
- water
- data
- water pump
- change curve
- matrix
- 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
-
- 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
Abstract
The invention relates to an intelligent control method of a water supply booster pump station, which comprises the steps of collecting data; preprocessing the acquired data to obtain preprocessed data; carrying out secondary treatment on the instantaneous flow and the effluent pressure data in the preprocessed data by a big data analysis method to obtain secondary treatment data; calculating water pump state data in the preprocessed data through an intelligent algorithm to obtain a water pump state coefficient; generating a water use linear change model according to the secondary processing data and the water pump state coefficient, introducing a water use influence factor coefficient, dynamically adjusting the water use linear change model by optimizing the water use influence factor coefficient, and finally generating a water use change curve; and obtaining a water pump power change curve according to the water use change curve, and then adjusting the water pump power in real time according to the water pump power change curve. The invention realizes the aim of supplying water according to the requirement by intelligently controlling the pump station, thereby effectively saving water resources.
Description
Technical Field
The invention relates to the technical field of water supply control, in particular to an intelligent control method of a water supply booster pump station.
Background
Water is a source of life, a key point of production and an ecological base, and the importance of water is self-evident, but water is not inexhaustible and inexhaustible. Therefore, water conservation is the obligation and obligation that each citizen should have to spend. The method and the device can improve the self water-saving consciousness of citizens, and meanwhile, how to realize the purpose of water saving by technical means is also an important technical bottleneck which needs to be solved seriously.
In the process of resident water supply, a booster pump station in a certain area supplies water for all users in the district by pressurization constantly, so that the basic water demand of people is guaranteed.
At present, water saving technology is different day by day, but research results of the internet are fully applied, the realization of intelligent control on starting and stopping of a water pump for a water supply booster pump station is a research subject of experts, and the aims of saving energy and water can be achieved only by adjusting water supply according to needs through the forward technology.
Disclosure of Invention
The invention aims to solve the technical problem of providing an intelligent control method of a water supply booster pump station, which realizes the aim of supplying water according to needs and effectively saves water resources by intelligently controlling the pump station.
The technical scheme adopted by the invention for solving the technical problems is as follows: the intelligent control method for the water supply booster pump station comprises the following steps:
step (1): collecting instantaneous flow and water outlet pressure data about a water supply pipeline and water pump state data;
step (2): preprocessing the acquired data to obtain preprocessed data;
and (3): carrying out secondary treatment on the instantaneous flow and the effluent pressure data in the preprocessed data by a big data analysis method to obtain secondary treatment data; calculating the water pump state data in the preprocessed data through an intelligent algorithm to obtain a water pump state coefficient delta emax ；
And (4): according to the secondary processing data and the water pump state coefficient delta emax Generating a water use linear change model, introducing a water use influence factor coefficient lambda into the water use linear change model, dynamically adjusting the water use linear change model by optimizing the water use influence factor coefficient lambda, and finally generating a water use change curve;
and (5): and obtaining a water pump power change curve according to the water use change curve, and then adjusting the water pump power in real time according to the water pump power change curve.
In the step (3), the instantaneous flow and the effluent pressure data in the preprocessed data are secondarily processed by a big data analysis method to obtain secondary processed data, which specifically comprises the following steps: and carrying out clustering, segmentation and abnormal value judgment on the instantaneous flow and effluent pressure data in the preprocessed data by adopting a big data analysis method to obtain secondary processed data.
In the step (3), the water pump state data in the preprocessed data is calculated through an intelligent algorithm to obtain a water pump state coefficient delta emax The method specifically comprises the following steps: randomly sampling water pump state data in the preprocessed data to obtain a matrix A, and fuzzifying the matrix A to obtain a matrix A 1 (ii) a By computing said matrix A 1 Obtaining a feature matrix B from the mean, variance and kurtosis of each column; calculating the information entropy w of the characteristic matrix B through an information entropy algorithm;
calculating to obtain a water pump state coefficient delta according to the characteristic matrix B and the information entropy w of the characteristic matrix B emax The formula is as follows:
wherein w is the information entropy of the feature matrix B, and n' is the length of B × w.
In the step (4), the secondary processing data and the water pump state coefficient delta are used emax Generating a water linear change model, and introducing a water influence factor coefficient lambda into the water linear change model, wherein the formula is as follows:
wherein Q is total Is the total flow rate, W i For pump shaft power, H for water pump rated lift, R e Is the resistance coefficient, eta, of the water pump water outlet pipeline i For water pump efficiency, P is the total outlet pressure and n is the number of water pumps.
In the step (4), the water use linear change model is dynamically adjusted by optimizing the water use influence factor coefficient lambda, and finally a water use change curve is generated, specifically: and taking a preset outlet pressure value and the minimum number of running water pumps as constraint conditions, optimizing the water consumption influence factor coefficient lambda by adopting a genetic algorithm, assigning the optimized water consumption influence factor coefficient lambda to the water consumption linear change model, and fitting a water quantity curve through the optimized water consumption linear change model to obtain a water consumption change curve among the water supply flow, the power of each water pump and the number of running water pumps.
The step (5) is specifically as follows: and designing a change relation model between the water pump power and the instantaneous flow according to the water use change curve, obtaining a water pump power change curve according to the change relation model, and finally adjusting the water pump power in real time according to the water pump power change curve.
Advantageous effects
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects: according to the intelligent control method of the water supply booster pump station, the water use linear change model is obtained through a big data analysis technology and an artificial intelligence algorithm, the water use influence factor coefficient is introduced into the water use linear change model, the water use linear change model can be optimized according to actual requirements, the start and stop of the water pump are further intelligently controlled, water supply is adjusted according to needs, intelligent water supply for all users in the jurisdiction is achieved, energy and water can be effectively saved, and the pump station is developed towards the intelligent and green directions.
Drawings
FIG. 1 is a process flow diagram of an embodiment of the present invention;
FIG. 2 is a graph of the change of parameters of the water pump collected in the embodiment of the invention;
FIG. 3 is a schematic of a water flow rate for one day of an embodiment of the present invention;
fig. 4 is a graph showing a change in power of the water pump according to the embodiment of the present invention.
Detailed Description
The invention will be further illustrated with reference to the following specific examples. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and such equivalents may fall within the scope of the present invention as defined in the appended claims.
The embodiment of the invention relates to an intelligent control method of a water supply booster pump station, as shown in figure 1, which is a method flow chart of the embodiment of the invention, taking the booster pump station in a certain area as an example, 6 water pumps are provided, wherein 4 large pumps (using 3 for 1) and 2 small pumps (using 1 for 1) are connected in parallel to a water supply pipeline, and the set water outlet pressure is 0.5Mpa at the moment, and the specific method is as follows:
step (1): the booster pump station equipment is also provided with a corresponding monitoring device for acquiring instantaneous flow data and water outlet pressure data of water flowing in a water supply pipeline; a state monitoring device is installed in each supply pump and used for collecting water pump state data, wherein the water pump state data comprise voltage, current and pump vibration signals.
In the present embodiment, the sampling frequency is set to 0.05Hz, and the instantaneous flow rate, the water discharge pressure data and the water pump state data about the water supply pipeline are collected, for example, at a certain time (9 to 10 am) in a certain day, and the collected data is shown in fig. 2.
Step (2): and preprocessing the acquired data to complete deletion and supplement of the data to obtain preprocessed data.
And (3): carrying out secondary treatment on the instantaneous flow and the effluent pressure data in the preprocessed data by a big data analysis method to obtain secondary treatment data; calculating the water pump state data in the preprocessed data through an intelligent algorithm to obtain a water pump state coefficient delta emax 。
The step (3) is specifically divided into two parts:
a first part: in the step (3), the instantaneous flow and the effluent pressure data in the preprocessed data are secondarily processed by a big data analysis method to obtain secondary processed data, which specifically comprises the following steps: and carrying out clustering, segmentation and abnormal value judgment on the instantaneous flow and effluent pressure data in the preprocessed data by adopting a big data analysis method to obtain secondary processed data.
A second part: in the step (3), water pump state data (mainly pump vibration signals) in the preprocessed data are calculated through an intelligent algorithm to obtain a water pump state coefficient delta emax The method specifically comprises the following steps: the pretreated water pump state data count 360000 points, the water pump state data are randomly sampled into a matrix of 360 x 1000, the matrix is represented by A, and the matrix A is fuzzified to obtain a matrix A 1 Fuzzification operation is realized through membership functionThe formula is:
wherein f (x, sigma, c) is a membership function, e is an exponential function, sigma is a standard deviation of different columns in the matrix A, and c is a mean value of different columns in the matrix A; by computing said matrix A 1 The mean, variance and kurtosis of each column of (a) result in a feature matrix B of 1000 x 3; calculating the information entropy w of the characteristic matrix B through an information entropy algorithm, wherein the formula is as follows:
wherein H (x) is the information entropy result, the calculated H (x) is the information entropy w to be calculated, x is the column of the matrix B, m is the length of each column of the matrix B, p i Taking values of data of each column of the matrix B; calculating to obtain a water pump state coefficient delta according to the characteristic matrix B and the information entropy w of the characteristic matrix B emax The formula is as follows:
where w is the entropy of the feature matrix B and has a length of 3 x 1, n' is the length of B x w, where n has a length of 1000.
And (4): according to the secondary processing data and the water pump state coefficient delta emax And generating a water linear change model taking time as a horizontal coordinate, introducing a water influence factor coefficient lambda into the water linear change model, dynamically adjusting the water linear change model by optimizing the water influence factor coefficient lambda, and finally generating a water change curve chart.
In the step (4), the secondary processing data and the water pump state coefficient delta are used emax Generating a water linear change model, and introducing a water influence factor coefficient lambda into the water linear change model, wherein the formula is as follows:
wherein Q is total Is the total flow, W i For pumping shaft workThe ratio H is the rated lift of the water pump, R e Is the resistance coefficient, eta, of the water pump outlet pipeline i For water pump efficiency, P is the total outlet pressure and n is the number of water pumps.
In the step (4), the water use linear change model is dynamically adjusted by optimizing the water use influence factor coefficient λ, specifically: and (3) taking a preset outlet pressure value and the minimum number of water pumps as constraint conditions, optimizing the water use influence factor coefficient lambda by adopting a genetic algorithm, and assigning the optimized water use influence factor coefficient lambda to the water use linear change model.
After the water use linear variation model is added with the water use influence factor coefficient lambda, the water use linear variation model can be dynamically adjusted according to different time periods, for example, the water supply requirements in summer and winter are different, namely the water use influence factor coefficient lambda corresponding to summer is not suitable for winter, so the water use influence factor coefficient lambda needs to be optimized to enable the water use linear variation model to achieve the optimal value.
Based on the analysis, on the basis that the outlet pressure value tends to a preset value and the minimum number of the water pump operation units are taken as constraint conditions, fitting a water quantity curve through an optimized water linear change model to obtain a water change curve between the water supply flow and each water pump power and the number of the water pump operation units; by a pair of formulas
Making the changes, we obtained:
and is
Under the condition that the flow, the outlet pressure and various rated parameters are known, the relation between the total power and the number of the running water pumps is searched, namely under the condition that the total running power is minimum, the relation between the total flow and the number of the running water pumps is searched, and a water use change curve is further obtained.
And (5): and obtaining a water pump power change curve according to the water use change curve, and adjusting the water pump power in real time according to the water pump power change curve, so as to achieve the aim of saving energy and water in real time.
The step (5) is specifically as follows: and designing a change relation model between the water pump power and the instantaneous flow according to the water use change curve, obtaining a water pump power change curve according to the change relation model, and finally adjusting the water pump power in real time according to the water pump power change curve.
In the present embodiment, the flow rate data (as shown in fig. 3) of one day is obtained, so that the water pump power variation curve shown in fig. 4 is finally obtained, and the power consumption amount at each time is minimum.
Based on the above, four large pumps, which are respectively defined as 1, 2, 3 and 4, can be set to operate in the corresponding working condition mode, each cycle of working condition runs for one circle, the first three pumps are used as main pumps each time, the last pump is used as a standby pump, such as 1/2/3 is the main pump when the cycle working condition is 1 → 2 → 3 → 4, 4 is the standby pump, such as 2/3/4 is the main pump when the cycle working condition is 2 → 3 → 4 → 1, and 1 is the standby pump, so as to operate in the cycle working condition mode; set up two little pumps, all move a week under every operating mode, make a round trip the mutual replacement to avoid the reserve pump because long-time unnecessary, lead to its trouble and damage, finally guarantee the good state operation in succession of pump.
Therefore, the intelligent control method realizes intelligent control on the water supply booster pump station by means of intelligent algorithm, big data analysis and other technical means, adjusts water supply according to requirements, and realizes good effects of saving energy and water.
Claims (4)
1. An intelligent control method for a water supply booster pump station is characterized by comprising the following steps:
step (1): collecting instantaneous flow and water outlet pressure data about a water supply pipeline and water pump state data;
step (2): preprocessing the acquired data to obtain preprocessed data;
and (3): by large numbersCarrying out secondary treatment on the instantaneous flow and the effluent pressure data in the preprocessed data according to an analysis method to obtain secondary treatment data; calculating the water pump state data in the preprocessed data through an intelligent algorithm to obtain a water pump state coefficient delta emax ；
And (4): according to the secondary processing data and the water pump state coefficient delta emax Generating a water use linear change model, introducing a water use influence factor coefficient lambda into the water use linear change model, dynamically adjusting the water use linear change model by optimizing the water use influence factor coefficient lambda, and finally generating a water use change curve;
and (5): obtaining a water pump power change curve according to the water use change curve, and then adjusting the water pump power in real time according to the water pump power change curve;
in the step (3), the water pump state data in the preprocessed data is calculated through an intelligent algorithm to obtain a water pump state coefficient delta emax The method specifically comprises the following steps: randomly sampling water pump state data in the preprocessed data to obtain a matrix A, and performing fuzzification operation on the matrix A to obtain a matrix A 1 (ii) a By calculating said matrix A 1 Obtaining a feature matrix B from the mean, variance and kurtosis of each column; calculating the information entropy w of the characteristic matrix B through an information entropy algorithm;
calculating to obtain a water pump state coefficient delta according to the characteristic matrix B and the information entropy w of the characteristic matrix B emax The formula is as follows:
wherein w is the information entropy of the feature matrix B, and n' is the length of B x w; in the step (4), the secondary processing data and the water pump state coefficient delta are used for processing the water pump state data emax Generating a water linear change model, and introducing a water influence factor coefficient lambda into the water linear change model, wherein the formula is as follows:
wherein Q is total Is the total flow rate, W i For pump shaft power, H for water pump rated lift, R e Is the resistance coefficient, eta, of the water pump outlet pipeline i For water pump efficiency, P is the total outlet pressure and n is the number of water pumps.
2. The intelligent control method for the water supply booster pump station according to claim 1, wherein in the step (3), the instantaneous flow and effluent pressure data in the pre-processing data are secondarily processed by a big data analysis method to obtain secondary processing data, and specifically: and carrying out clustering, segmentation and abnormal value judgment on the instantaneous flow and effluent pressure data in the preprocessed data by adopting a big data analysis method to obtain secondary processed data.
3. The intelligent control method for a water supply booster pump station according to claim 1, wherein in the step (4), the water usage linear variation model is dynamically adjusted by optimizing the water usage influence factor coefficient λ, and finally a water usage variation curve is generated, specifically: and taking a preset outlet pressure value and the minimum number of the water pump running units as constraint conditions, optimizing the water utilization influence factor coefficient lambda by adopting a genetic algorithm, assigning the optimized water utilization influence factor coefficient lambda to the water utilization linear change model, and fitting a water quantity curve through the optimized water utilization linear change model to obtain a water utilization change curve among the water supply flow, the power of each water pump and the number of the water pump running units.
4. The intelligent control method of a water supply booster pump station according to claim 1, characterized in that the step (5) is specifically: and designing a change relation model between the water pump power and the instantaneous flow according to the water use change curve, obtaining a water pump power change curve according to the change relation model, and finally adjusting the water pump power in real time according to the water pump power change curve.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011536808.3A CN112696344B (en) | 2020-12-23 | 2020-12-23 | Intelligent control method for water supply booster pump station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011536808.3A CN112696344B (en) | 2020-12-23 | 2020-12-23 | Intelligent control method for water supply booster pump station |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112696344A CN112696344A (en) | 2021-04-23 |
| CN112696344B true CN112696344B (en) | 2022-09-02 |
Family
ID=75509316
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011536808.3A Active CN112696344B (en) | 2020-12-23 | 2020-12-23 | Intelligent control method for water supply booster pump station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112696344B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN114320866B (en) * | 2022-03-08 | 2022-06-24 | 湖南易净环保科技有限公司 | Centralized management control system for distributed integrated pump station |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1327111A (en) * | 2000-06-01 | 2001-12-19 | 徐景颖 | Energy saving method for water supply engineering |
| CN101705935A (en) * | 2009-11-09 | 2010-05-12 | 江苏大学 | Water pump parallel machine set operation mechanism and control strategy simulation test device |
| 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 |
| CN107563451A (en) * | 2017-09-18 | 2018-01-09 | 河海大学 | Running rate recognizing method under a kind of pumping plant steady state condition |
| CN110163444A (en) * | 2019-05-28 | 2019-08-23 | 河北工程大学 | A kind of water demand prediction method based on GASA-SVR |
| CN110751416A (en) * | 2019-10-29 | 2020-02-04 | 杭州鲁尔物联科技有限公司 | Method, device and equipment for predicting water consumption |
-
2020
- 2020-12-23 CN CN202011536808.3A patent/CN112696344B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1327111A (en) * | 2000-06-01 | 2001-12-19 | 徐景颖 | Energy saving method for water supply engineering |
| CN101705935A (en) * | 2009-11-09 | 2010-05-12 | 江苏大学 | Water pump parallel machine set operation mechanism and control strategy simulation test device |
| 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 |
| CN107563451A (en) * | 2017-09-18 | 2018-01-09 | 河海大学 | Running rate recognizing method under a kind of pumping plant steady state condition |
| CN110163444A (en) * | 2019-05-28 | 2019-08-23 | 河北工程大学 | A kind of water demand prediction method based on GASA-SVR |
| CN110751416A (en) * | 2019-10-29 | 2020-02-04 | 杭州鲁尔物联科技有限公司 | Method, device and equipment for predicting water consumption |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112696344A (en) | 2021-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112696344B (en) | Intelligent control method for water supply booster pump station | |
| CN103195698B (en) | Become the energy-saving control method that in water level water intake pumping station, water pump synchronous speed change regulates | |
| CN107153885B (en) | Real-time power generation plan optimization method considering deep peak shaving of thermal power generating unit | |
| CN106597879A (en) | Sewage treatment elevator pump optimized scheduling method | |
| CN110779182A (en) | Variable-frequency air conditioner compressor frequency control mode directly powered by solar panel | |
| CN102692875A (en) | Method for realizing main steam pressure tracking optimization of steam turbine | |
| CN109274131B (en) | Probability statistics theory-based non-time sequence quantitative evaluation method for new energy consumption capability | |
| CN109546689B (en) | Two-stage unit combined operation control method suitable for large-scale system | |
| CN109002930A (en) | A kind of home energy source Internet of Things Demand Side Response control method neural network based | |
| CN108427459B (en) | Automatic control method for piston type flow regulating valve of multi-water-source annular water supply pipe network | |
| CN106468258A (en) | A kind of compressor bank frequency-changing pressure stabilizing monitoring system | |
| CN111915173A (en) | Screening method for optimal scheduling key factors of small cascade hydropower stations | |
| CN109687428B (en) | Control method of multi-energy complementary distributed energy microgrid operation optimization control system | |
| CN109636001B (en) | Method, system and computer readable medium for adjusting pH value of desulfurization slurry supply system based on big data | |
| CN114925928B (en) | Intelligent dynamic regulation and control underground complex shallow geothermal energy utilization and storage method and system thereof | |
| CN201803430U (en) | Air-conditioning energy-saving controller in subway station | |
| CN115907402A (en) | Method and system for calculating joint guaranteed output of cascade hydropower stations | |
| CN203174694U (en) | Constant-pressure variable frequency water supply control device based on ARM | |
| CN207212646U (en) | A kind of intelligent air compressor energy saver | |
| CN110593355A (en) | Water supply energy consumption reduction method based on pressure control model and PLC | |
| CN113128767B (en) | Method for minimizing load operation cost of agricultural irrigation pump by considering standby income | |
| CN201491335U (en) | Intelligent road lamp power conservation controller | |
| CN110390430A (en) | A kind of frequency conversion type water circulating pump optimizing operation method avoiding frequent start-stop | |
| CN109340094A (en) | A kind of air compressor energy-saving control method based on load | |
| CN113555910B (en) | Energy microgrid system with intelligent hydroelectric energy storage equipment |
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 |