CN117808144A - Intelligent water taking method and system based on time sequence prediction model - Google Patents
Intelligent water taking method and system based on time sequence prediction model Download PDFInfo
- Publication number
- CN117808144A CN117808144A CN202311744249.9A CN202311744249A CN117808144A CN 117808144 A CN117808144 A CN 117808144A CN 202311744249 A CN202311744249 A CN 202311744249A CN 117808144 A CN117808144 A CN 117808144A
- Authority
- CN
- China
- Prior art keywords
- water
- flow
- data
- frequency
- lift
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 246
- 238000000034 method Methods 0.000 title claims abstract description 39
- 239000007788 liquid Substances 0.000 claims abstract description 26
- 238000012544 monitoring process Methods 0.000 claims abstract description 6
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 9
- 230000004931 aggregating effect Effects 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 4
- 238000005265 energy consumption Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 239000010802 sludge Substances 0.000 claims description 2
- 238000012549 training Methods 0.000 abstract description 2
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000008235 industrial water Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The invention provides an intelligent water taking method and system based on a time sequence prediction model, wherein the method comprises the following steps: predicting the water supply amount in a future unit time based on a TimesNet timing prediction model according to the water supply amount data in a plurality of historical unit times; on the basis of the output water supply quantity, calculating a predicted value of the water flow of the inlet plant, and monitoring the running frequency of the current pump set; finding out corresponding power and lift on a flow-power curve and a flow-lift curve according to the flow of the inlet water; and determining the frequency of the water taking pump according to the flow, the power and the lift of the water inlet field, and taking water. According to the invention, training is performed based on historical water quantity data through a TimesNet time sequence prediction model, and information of a plurality of periods is dynamically and adaptively fused, so that accurate prediction is provided for balancing water taking and water supply, thereby effectively controlling the liquid level of a clean water tank and ensuring the running stability of a system.
Description
Technical Field
The invention relates to the field of municipal engineering, in particular to an intelligent water taking method and system based on a time sequence prediction model.
Background
Water supply plants are an indispensable infrastructure of modern society, and water intake systems of water supply plants play a vital role in protecting urban residents and industrial water.
In general, urban water usage varies periodically daily, with fixed water peaks and valleys each day. This periodic pattern is often affected by factors such as lifestyle and industrial production of urban residents. In actual water works, the water supply amount of the water works does not follow the periodic law of peaks and valleys as simply as the conventional mode, for example, the water pumping and storing process of the booster pump station in front of the water works may cause the water supply amount of the water works to appear in the late night. Conventional predictive models have difficulty in effectively coping with such irregularities and multifactorial effects, and more advanced techniques are needed to improve accurate predictions of water supply to meet the demands of urban water supply systems.
Disclosure of Invention
Aiming at the technical problems existing in the prior art, the invention provides an intelligent water taking method and system based on a time sequence prediction model.
According to a first aspect of the present invention, there is provided an intelligent water intake method based on a time sequence prediction model, comprising:
collecting historical data of a water works, and preprocessing the historical data to obtain preprocessed historical data in a plurality of historical unit time;
extracting water supply amount data in a plurality of historical unit time from the historical data, and predicting the water supply amount in a future unit time based on a TimesNet time sequence prediction model;
on the basis of outputting the water supply quantity, calculating an estimated value of the water flow of the inlet plant based on historical data in a plurality of historical unit time and a water balance calculation module, and monitoring the running frequency of the current pump set;
acquiring a flow-power curve and a flow-lift curve of a current pump set, finding corresponding power on the flow-power curve and finding corresponding lift on the flow-lift curve according to the estimated value of the inflow flow;
determining the frequency of a water taking pump according to the flow, the power and the lift of a water inlet field;
and adjusting the operating frequency of the current pump set based on the frequency of the water taking pump so as to take water according to the adjusted operating frequency.
On the basis of the technical scheme, the invention can also make the following improvements.
Optionally, the historical data of the water works comprise water inflow amount, water outflow amount, clean water inflow tank amount, front tank liquid level, clean water tank liquid level and back flush mud discharge intensity, and the real-time operation data of the pump group comprise operation frequency and electric energy consumption data.
Optionally, the preprocessing the historical data includes:
finding out and eliminating abnormal jump values in the historical data set based on a DBSCAN clustering algorithm according to different characteristics;
for the historical data set after the abnormal jump value is removed, the data is complemented by a linear interpolation method;
for water flow data detected by using a flowmeter and liquid level data detected by using a liquid level meter, filtering the water flow data and the liquid level data based on a data smoothing method;
and aggregating the preprocessed discrete historical data into historical data in a plurality of historical unit times.
Optionally, the calculating, based on the historical data in the plurality of historical unit times and based on the water balance calculating module, the estimated value of the water flow rate of the inlet plant includes:
and calculating a predicted value of the water inflow rate of the water works based on the water balance calculation module according to the liquid level of the clean water basin, the warehouse-in flow, the real-time flow of the water inflow field, the real-time flow of the water outflow field, the predicted value of the water outflow plant flow and the back flush mud discharge data.
Optionally, the predicting the water supply amount in the unit time based on the TimesNet timing prediction model includes:
judging whether the predicted water supply amount is larger than the upper limit value of the water supply amount, if so, outputting according to the upper limit value of the water supply amount; if not, outputting according to the actual predicted water supply quantity.
Optionally, the acquiring the flow-power curve and the flow-lift curve of the current pump set includes:
according to delivery parameters and performance curves of the water pump, a flow-lift Q-H curve and a flow-power Q-P curve of the water pump are obtained through fitting;
obtaining flow-lift Q-H curves under different frequencies and flow-power Q-P curves under different frequencies according to the similarity of the water pumps;
and according to the operating frequency of the current pump set, a flow-lift Q-H curve and a flow-power Q-P curve corresponding to the operating frequency of the current pump set are found.
Optionally, the adjusting the operating frequency of the current pump set based on the frequency of the water intake pump includes:
when the frequency of the water taking pump is larger than the upper limit value of the frequency modulation range, the running frequency of the current pump set is adjusted to be the upper limit value of the frequency modulation range;
and when the frequency of the water taking pump is smaller than the upper limit value of the frequency modulation range, adjusting the running frequency of the current pump set to the frequency of the water taking pump.
According to a second aspect of the present invention, there is provided an intelligent water intake system based on a time series prediction model, comprising:
the collecting module is used for collecting historical data of a water works and preprocessing the historical data to obtain preprocessed historical data in a plurality of historical unit time;
the prediction module is used for extracting water supply amount data in a plurality of historical unit time from the historical data and predicting the water supply amount in the future unit time based on the TimesNet time sequence prediction model;
the calculation module is used for calculating an estimated value of the water flow of the water inlet plant based on the historical data in a plurality of historical unit time and the water balance calculation module on the basis of the output water supply quantity, and monitoring the running frequency of the current pump group;
the matching module is used for acquiring a flow-power curve and a flow-lift curve of the current pump set, matching corresponding power on the flow-power curve according to the estimated value of the inflow water flow, and matching corresponding lift on the flow-lift curve;
the determining module is used for determining the frequency of the water taking pump according to the flow, the power and the lift of the water inlet field;
and the adjusting module is used for adjusting the operating frequency of the current pump set based on the frequency of the water taking pump so as to take water according to the adjusted operating frequency.
According to the intelligent water taking method and system based on the time sequence prediction model, training is carried out based on historical water quantity data through the time sNet time sequence prediction model, information of a plurality of periods is dynamically and adaptively fused, accurate prediction is provided for water taking and water supply balance, and therefore the liquid level of a clean water tank is effectively controlled, and the running stability of the system is ensured.
Drawings
FIG. 1 is a flow chart of an intelligent water taking method based on a time sequence prediction model;
FIG. 2 is a flow chart of the whole intelligent water intake method based on a time sequence prediction model;
fig. 3 is a schematic structural diagram of an intelligent water intake system based on a time sequence prediction model.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention. In addition, the technical features of each embodiment or the single embodiment provided by the invention can be combined with each other at will to form a feasible technical scheme, and the combination is not limited by the sequence of steps and/or the structural composition mode, but is necessarily based on the fact that a person of ordinary skill in the art can realize the combination, and when the technical scheme is contradictory or can not realize, the combination of the technical scheme is not considered to exist and is not within the protection scope of the invention claimed.
Fig. 1 is a flowchart of an intelligent water taking method based on a time sequence prediction model, and as shown in fig. 1, the method includes:
step 1, collecting historical data of a water works, and preprocessing the historical data to obtain the preprocessed historical data in a plurality of historical unit time.
It is understood that the data adopted by the invention is the historical data from the water works, and mainly comprises the water inflow amount, the water outflow amount, the clean water inflow tank amount, the front tank liquid level, the clean water tank liquid level and the back flush mud discharging intensity, as well as the current pump set operation data and the current power consumption and energy consumption data.
The collected historical data is preprocessed, and the preprocessing process comprises the following steps:
finding out and eliminating abnormal jump values in the historical data set based on a DBSCAN clustering algorithm according to different characteristics;
for the historical data set after the abnormal jump value is removed, the data is complemented by a linear interpolation method;
for water flow data detected by using a flowmeter and liquid level data detected by using a liquid level meter, filtering the water flow data and the liquid level data based on a data smoothing method;
and aggregating the preprocessed discrete historical data into historical data in a plurality of historical unit times.
It can be understood that the data preprocessing firstly needs to remove the abnormal jump values in the data set, finds and eliminates the obvious abnormal values in the data set through a DBSCAN clustering method, and then logically eliminates jump values which should not appear according to different characteristics and the production reality of water plants. And carrying out data complement on the data set with the abnormal jump value removed by a linear interpolation method. In addition, if measuring noise exists for sensors such as a flowmeter, a liquid level meter and the like, the data can be filtered by adopting a data smoothing technology for the water flow detected by the flowmeter and the liquid level detected by the liquid level meter. Finally, by aggregating the raw data by hour, finer granularity data can be converted into more macroscopic hour-level data for further predictive analysis.
And 2, extracting water supply amount data in a plurality of historical unit time from the historical data, and predicting the water supply amount in the future unit time based on the TimesNet time sequence prediction model.
It is understood that historical water supply amount data is extracted from the preprocessed historical data, and the water supply amount per unit time in the future is predicted based on the TimesNet timing prediction model.
Among them, the prediction of the water supply amount can be regarded as a time-series prediction problem, and accurate estimation by means of a time series model is required. The TimesNet time sequence prediction model is an innovative deep learning model, focuses on processing time sequence data, and provides a powerful tool for time sequence data analysis and prediction. The time sequence prediction model adopts a deep neural network structure, can automatically learn and capture complex relations in time sequence data, and is applicable to different fields and various time sequence application scenes due to a flexible architecture. The TimesNet time sequence prediction model is selected to predict the water supply, and the algorithm thought is mainly to use historical data of the past N hours to predict the water supply change trend of a future period (such as 1 hour).
And 3, calculating an estimated value of the water flow of the inlet plant based on the historical data in a plurality of historical unit time and the water balance calculation module on the basis of the output water supply quantity, and monitoring the running frequency of the current pump set.
It will be appreciated that the above step 2 predicts the water supply amount for a period of time in the future, and the actual water supply amount needs to be outputted based on the predicted water supply amount. As shown in fig. 2, specifically, whether the predicted water supply amount is larger than the upper limit value of the water supply amount is determined, and if so, the predicted water supply amount is outputted according to the upper limit value of the water supply amount; if not, outputting according to the actual predicted water supply quantity.
After the actual water supply amount is determined, the water intake amount is calculated, and the estimated value of the water flow of the water intake factory is calculated according to the historical data, specifically, the estimated value of the water flow of the water intake factory is calculated based on a water balance calculation module according to the liquid level of a clean water tank, the warehouse-in flow, the real-time flow of the water intake farm, the real-time flow of the water outlet farm, the estimated value of the water flow of the water outlet factory and the back flush sludge discharge data, and the current running frequency of the water intake pump set is detected in real time.
And 4, acquiring a flow-power curve and a flow-lift curve of the current pump set, finding corresponding power on the flow-power curve according to the predicted value of the water flow of the inlet plant, and finding corresponding lift on the flow-lift curve.
It can be understood that according to the delivery parameters and the performance curve of the water pump, a water pump flow-lift Q-H curve and a flow-power Q-P curve are obtained through fitting; obtaining flow-lift Q-H curves under different frequencies and flow-power Q-P curves under different frequencies according to the similarity of the water pumps; and according to the operating frequency of the current pump set, a flow-lift Q-H curve and a flow-power Q-P curve corresponding to the operating frequency of the current pump set are found.
And 5, determining the frequency of the water taking pump according to the flow, the power and the lift of the water inlet field.
It can be understood that according to the predicted value of the water flow of the inlet plant, the corresponding lift H and power P are respectively found on the corresponding flow-lift Q-H curve and the corresponding flow-power Q-P curve, and finally, the frequency of the water taking pump is determined according to the optimal curves corresponding to the flow Q, the lift H and the power P.
And 6, adjusting the operating frequency of the current pump set based on the frequency of the water taking pump, and taking water according to the adjusted operating frequency.
It will be appreciated that the so-called water pump frequency, i.e. the frequency at which the pump unit needs to operate, is such that a large incoming water flow is achieved, and that if the water pump frequency is greater than the upper limit of the frequency modulation range, the current pump unit operating frequency is adjusted to the upper limit of the frequency modulation range; and if the frequency of the water taking pump is smaller than the upper limit value of the frequency modulation range, adjusting the running frequency of the current pump set to the frequency of the water taking pump, and taking water with the adjusted running frequency of the current pump set.
Referring to fig. 3, an intelligent water intake system based on a time sequence prediction model according to the present invention includes:
the collection module 301 is configured to collect historical data of a water works, and pre-process the historical data to obtain a plurality of pre-processed historical data in unit time;
a prediction module 302, configured to extract water supply amount data in a plurality of historical unit times from the historical data, and predict a water supply amount in a future unit time based on a TimesNet timing prediction model;
the calculating module 303 is configured to calculate, based on the output water supply amount and based on historical data in a plurality of historical unit times, an estimated value of the water flow rate of the water supply plant based on the water balance calculating module, and monitor the running frequency of the current pump set;
the matching module 304 is configured to obtain a flow-power curve and a flow-lift curve of the current pump set, and match the flow-power curve to corresponding power and the flow-lift curve to corresponding lift according to the estimated value of the inflow water flow;
the determining module 305 is configured to determine a frequency of the water intake pump according to the flow, the power and the lift of the water intake field;
and the adjusting module 306 is configured to adjust the operating frequency of the current pump set based on the frequency of the water intake pump, and take water at the adjusted operating frequency.
It can be understood that the intelligent water intake system based on the time sequence prediction model provided by the invention corresponds to the intelligent water intake method based on the time sequence prediction model provided by the foregoing embodiments, and the relevant technical features of the intelligent water intake system based on the time sequence prediction model can refer to the relevant technical features of the intelligent water intake method based on the time sequence prediction model, which are not described herein.
The intelligent water taking method and system based on the time sequence prediction model provided by the embodiment of the invention have the following advantages:
(1) Water supply amount control: the TimsNet multi-period time sequence prediction model trained by the historical water quantity data provides an advanced water supply quantity prediction function for the water supply system. Based on the water balance principle, the system can accurately predict the future water supply demand and realize the accurate control of water intake. The technical innovation greatly improves the operation efficiency of the water supply system, ensures that the liquid level of the water plant fluctuates in a proper range, and further ensures the stability and reliability of water supply.
(2) Innovations are realized on the long-term and short-term prediction, missing value filling, abnormality detection and other tasks of the TimesNet time sequence prediction model, the performance is excellent in predicting long-term trend, and the performance is excellent in short-term and processing of missing values, abnormality detection and classification tasks, so that more reliable and comprehensive data analysis and processing capability is provided for an intelligent water taking system.
(3) The intelligent water taking method based on the TimesNet time sequence prediction model brings multiple benefits to water supply factories through efficient and accurate data analysis and prediction capability. Including but not limited to:
(3-1) resource optimization: through accurate liquid level control, can realize the optimal utilization to the water resource, the waste is reduced to the maximum extent.
(3-2) running cost reduction: the accurate water supply demand prediction is helpful for reasonably planning the operation of the water supply system, thereby reducing the operation cost.
(3-3) stable water supply: the high-efficiency prediction function of the TimesNet time sequence prediction model ensures that the system can respond rapidly and accurately to the change of the demand on different time scales, and ensures stable water supply service.
In conclusion, the intelligent water taking method based on the TimesNet time sequence prediction model has obvious technical breakthroughs in the aspects of liquid level control, time sequence prediction and data analysis, and provides a reliable solution for stable operation and benefit improvement of a water supply system.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (8)
1. An intelligent water taking method based on a TimesNet time sequence prediction model is characterized by comprising the following steps of:
collecting historical data of a water works, and preprocessing the historical data to obtain preprocessed historical data in a plurality of historical unit time;
extracting water supply amount data in a plurality of historical unit time from the historical data, and predicting the water supply amount in a future unit time based on a TimesNet time sequence prediction model;
on the basis of outputting the water supply quantity, calculating an estimated value of the water flow of the inlet plant based on historical data in a plurality of historical unit time and a water balance calculation module, and monitoring the running frequency of the current pump set;
acquiring a flow-power curve and a flow-lift curve of a current pump set, finding corresponding power on the flow-power curve and finding corresponding lift on the flow-lift curve according to the estimated value of the inflow flow;
determining the frequency of a water taking pump according to the flow, the power and the lift of a water inlet field;
and adjusting the operating frequency of the current pump set based on the frequency of the water taking pump so as to take water according to the adjusted operating frequency.
2. The intelligent water intake method of claim 1, wherein the historical data of the water works comprises water intake quantity, water outlet quantity, clean water intake tank quantity, front tank liquid level, clean water tank liquid level and back flush sludge discharge intensity, and the pump set real-time operation data comprises operation frequency and electric energy consumption data.
3. The intelligent water intake method of claim 2, wherein the preprocessing of the historical data comprises:
finding out and eliminating abnormal jump values in the historical data set based on a DBSCAN clustering algorithm according to different characteristics;
for the historical data set after the abnormal jump value is removed, the data is complemented by a linear interpolation method;
for water flow data detected by using a flowmeter and liquid level data detected by using a liquid level meter, filtering the water flow data and the liquid level data based on a data smoothing method;
and aggregating the preprocessed discrete historical data into historical data in a plurality of historical unit times.
4. The intelligent water intake method according to claim 2, wherein the calculating the estimated value of the water flow rate of the water intake based on the water balance calculation module based on the history data in the plurality of history unit times comprises:
and calculating a predicted value of the water inflow rate of the water works based on the water balance calculation module according to the liquid level of the clean water basin, the warehouse-in flow, the real-time flow of the water inflow field, the real-time flow of the water outflow field, the predicted value of the water outflow plant flow and the back flush mud discharge data.
5. The intelligent water intake method according to claim 1, wherein the predicting the water supply amount per unit time in the future based on the TimesNet timing prediction model, after which comprises:
judging whether the predicted water supply amount is larger than the upper limit value of the water supply amount, if so, outputting according to the upper limit value of the water supply amount; if not, outputting according to the actual predicted water supply quantity.
6. The intelligent water intake method according to claim 1, wherein the obtaining the flow-power curve and the flow-lift curve of the current pump group comprises:
according to delivery parameters and performance curves of the water pump, a flow-lift Q-H curve and a flow-power Q-P curve of the water pump are obtained through fitting;
obtaining flow-lift Q-H curves under different frequencies and flow-power Q-P curves under different frequencies according to the similarity of the water pumps;
and according to the operating frequency of the current pump set, a flow-lift Q-H curve and a flow-power Q-P curve corresponding to the operating frequency of the current pump set are found.
7. The intelligent water intake method according to claim 1, wherein the adjusting the operating frequency of the current pump set based on the frequency of the water intake pump comprises:
when the frequency of the water taking pump is larger than the upper limit value of the frequency modulation range, the running frequency of the current pump set is adjusted to be the upper limit value of the frequency modulation range;
and when the frequency of the water taking pump is smaller than the upper limit value of the frequency modulation range, adjusting the running frequency of the current pump set to the frequency of the water taking pump.
8. An intelligent water intake system based on a TimesNet time sequence prediction model is characterized by comprising:
the collecting module is used for collecting historical data of a water works and preprocessing the historical data to obtain preprocessed historical data in a plurality of historical unit time;
the prediction module is used for extracting water supply amount data in a plurality of historical unit time from the historical data and predicting the water supply amount in the future unit time based on the TimesNet time sequence prediction model;
the calculation module is used for calculating an estimated value of the water flow of the water inlet plant based on the historical data in a plurality of historical unit time and the water balance calculation module on the basis of the output water supply quantity, and monitoring the running frequency of the current pump group;
the matching module is used for acquiring a flow-power curve and a flow-lift curve of the current pump set, matching corresponding power on the flow-power curve according to the estimated value of the inflow water flow, and matching corresponding lift on the flow-lift curve;
the determining module is used for determining the frequency of the water taking pump according to the flow, the power and the lift of the water inlet field;
and the adjusting module is used for adjusting the operating frequency of the current pump set based on the frequency of the water taking pump so as to take water according to the adjusted operating frequency.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311744249.9A CN117808144A (en) | 2023-12-18 | 2023-12-18 | Intelligent water taking method and system based on time sequence prediction model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311744249.9A CN117808144A (en) | 2023-12-18 | 2023-12-18 | Intelligent water taking method and system based on time sequence prediction model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117808144A true CN117808144A (en) | 2024-04-02 |
Family
ID=90421143
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311744249.9A Pending CN117808144A (en) | 2023-12-18 | 2023-12-18 | Intelligent water taking method and system based on time sequence prediction model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117808144A (en) |
-
2023
- 2023-12-18 CN CN202311744249.9A patent/CN117808144A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113236581B (en) | Intelligent parallel pump system and optimal adjustment method | |
| CN116646933A (en) | Big data-based power load scheduling method and system | |
| Wanjiru et al. | Sustainable energy-water management for residential houses with optimal integrated grey and rain water recycling | |
| CN106759834B (en) | A kind of sewage pumping station dynamic control method and system | |
| JP5455724B2 (en) | Operational status monitoring system for water and sewage plants | |
| CN111210152B (en) | Method and device for scheduling drainage system | |
| CN103277291A (en) | Optimal scheduling method for single-stage pump station | |
| KR20210109160A (en) | Sewage Inflow Prediction Method Based on Big Data and AI, and Storage Medium Having the Same | |
| JP5932466B2 (en) | Water distribution operation control device | |
| CN113156817A (en) | Intelligent pump allocation method for pump station | |
| CN114565327B (en) | Wisdom energy management and control system based on thing networking | |
| KR100741691B1 (en) | Water Management System and method for Optimal Operation and Control in Wide-area Waterworks using ubiquitous technology | |
| CN114688010B (en) | Water pump energy-saving consumption-reducing control method | |
| CN110109431A (en) | A kind of die casting machine OEE Information Intelligent Extraction system | |
| CN110837933A (en) | Leakage identification method, device, equipment and storage medium based on neural network | |
| CN117812123A (en) | Valve regulation and control method and system based on Internet of things | |
| JP5193884B2 (en) | Monitoring and control system for water supply facilities | |
| CN117808144A (en) | Intelligent water taking method and system based on time sequence prediction model | |
| CN114542442A (en) | Water treatment lift pump scheduling control method and device, electronic equipment and medium | |
| CN117543589A (en) | Scheduling method of cascade hydropower safety centralized control system | |
| CN116770930A (en) | Integrated sewage discharge system for modularized building | |
| CN110659681B (en) | Time sequence data prediction system and method based on pattern recognition | |
| CN109709993A (en) | Liquid level intelligent control method | |
| CN114221329A (en) | Power grid load management method and system based on big data | |
| CN114396385A (en) | Scheduling control method based on pump station operation |
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 |