CN111105065A - Rural water supply system and method based on machine learning - Google Patents
Rural water supply system and method based on machine learning Download PDFInfo
- Publication number
- CN111105065A CN111105065A CN201910918895.XA CN201910918895A CN111105065A CN 111105065 A CN111105065 A CN 111105065A CN 201910918895 A CN201910918895 A CN 201910918895A CN 111105065 A CN111105065 A CN 111105065A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- water supply
- training
- rural
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- E—FIXED CONSTRUCTIONS
- E03—WATER SUPPLY; SEWERAGE
- E03B—INSTALLATIONS OR METHODS FOR OBTAINING, COLLECTING, OR DISTRIBUTING WATER
- E03B1/00—Methods or layout of installations for water supply
- E03B1/02—Methods or layout of installations for water supply for public or like main supply for industrial use
-
- E—FIXED CONSTRUCTIONS
- E03—WATER SUPPLY; SEWERAGE
- E03B—INSTALLATIONS OR METHODS FOR OBTAINING, COLLECTING, OR DISTRIBUTING WATER
- E03B7/00—Water main or service pipe systems
- E03B7/07—Arrangement of devices, e.g. filters, flow controls, measuring devices, siphons, valves, in the pipe systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses a rural water supply system and a water supply method based on machine learning, which comprises a data importing module, a data monitoring and collecting module, a data storage module, a data preprocessing module, a data training module, a data prediction module, a data verification module and an interface service module, wherein the electrical output ends of the data importing module and the data monitoring and collecting module are connected with the electrical input end of the data preprocessing module, a great amount of rural historical water supply data, water consumption data, water supply data and real-time monitoring data are obtained as training data for machine learning, the relation among historical water supply, historical water supply and historical water consumption is researched by utilizing a machine learning technology, the rural water supply, water supply and water consumption are predicted based on the historical data and the real-time monitoring data by utilizing a deep neural network algorithm and a water balance algorithm, and the monthly water supply distribution of rural areas is carried out, the water supply guarantee rate in rural areas is improved.
Description
Technical Field
The invention relates to the technical field of rural water supply, in particular to a rural water supply system and a rural water supply method based on machine learning.
Background
The prediction of the rural water consumption and the water supply capacity is beneficial to reasonably planning the water supply capacity of a rural water supply system, reasonably guiding and adjusting water, reasonably distributing water, reasonably planning the water yield of each water plant in the rural water supply system and reducing the water supply cost to the maximum extent. At present, the country also proposes a water-saving society, water resources are relatively deficient in northwest regions, and reasonable water supply and distribution is beneficial to saving water resources, so that the water supply capacity, water consumption and water supply quantity of a rural water supply system are predicted, the reasonable utilization and distribution of the water resources are an important way for solving the problems of low guarantee rate of the rural water resources and construction of the water-saving society, and the rural water supply system and the water supply method based on machine learning are provided for the purpose.
Disclosure of Invention
The invention aims to provide a rural water supply system and a water supply method based on machine learning, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: the utility model provides a rural water supply system based on machine learning, includes leading-in data module, data monitoring acquisition module, data storage module, data preprocessing module, data training module, data prediction module, data verification module, interface service module, its characterized in that: the electrical output ends of the imported data module and the data monitoring and collecting module are connected with the electrical input end of the data preprocessing module, the electrical output end of the data preprocessing module is connected with the electrical input end of the data storage module, the electrical output end of the data storage module is electrically connected with the electrical input end of the data training module, the electrical output end of the data training module is electrically connected with the electrical input end of the data prediction module, the electrical output end of the data prediction module is connected with the electrical input end of the data verification module, the electrical output end of the data verification module is connected with the electrical input end of the interface service module, and the output ends of the data prediction module and the data verification module are electrically connected with the data training module;
the import data module is used for importing the data of the historical water consumption, the water supply amount and the water consumption amount in the rural area;
the data monitoring and collecting module is used for collecting monthly actual water supply data, actual water use data and actual rainfall data in a rural water supply system;
the data storage module is used for storing the preprocessed data in a classified manner so as to facilitate subsequent calculation and calling;
the data preprocessing module is used for preprocessing the acquired data and eliminating invalid and unreasonable data;
the data training module is used for taking historical data away from the current time period as a training sample, taking actual monitoring and collecting data away from the current time period as a test sample, and realizing machine learning training based on a BP neural network algorithm;
the data prediction module is used for predicting data such as water supply amount and the like from the current time period based on training and learning of historical data;
and the data verification module is used for carrying out error analysis by utilizing actual acquired data and predicted data which are far away from the current time period to determine an optimal model.
Preferably, the data prediction module and the data verification module are used for feeding error analysis back to the training model and adjusting the model connection weight and the threshold value.
Preferably, the data training module includes a training sample, a test sample, and a network node, where the training sample is connected to the test sample, and the test sample is connected to the network node.
Preferably, the interface service module is configured to forward data, and perform data packing and parsing.
The invention also provides a rural water supply method based on machine learning, which comprises the following steps:
the method comprises the following steps: acquiring rural historical water supply, water consumption and water inflow data, importing the historical data into a system through an import data module, preprocessing the data and storing the preprocessed data in a data storage module;
step two: the method comprises the steps of collecting data such as the latest water supply amount, the actual water consumption amount and the actual rainfall amount of a rural water supply system, preprocessing the data, storing the preprocessed data in a data storage module, and updating system data information in time;
step three: the data preprocessing module processes and corrects the obtained data, judges the validity of the data, and rejects unreasonable data and invalid data according to a judgment rule set by a system;
step four: the data training module is used for classifying and calling water supply data, water consumption data and precipitation data from the data storage module;
step five: inputting a time period in which the water consumption and the water supply amount need to be predicted, and predicting the water consumption and the water supply amount in the time period through an optimized BP neural network;
step six: and (3) carrying out reasonable water distribution on the water supply quantity in the rural water supply system according to the actual water supply capacity of the water supply system and by combining a water quantity balance equation.
Preferably, in the third step, the data is corrected by using feature normalization, where the feature normalization equation is:
preferably, the fourth step includes performing machine learning training by using various types of data as samples, and the specific training steps are as follows:
s1, dividing the sample data into training samples and verification samples according to the time sequence; 80% of training samples, 20% of validation samples;
s2, predicting the water quantity based on the BP neural algorithm;
s3, training a multilayer network node to form a BP neural network by using a BP neural algorithm;
s4, using the divided training sample training model, carrying out error analysis on the output result and the target result, and then carrying out inverse pushing to correct the connection weight and the threshold of the BP neural network to obtain the connection weight and the threshold which enable the BP neural model prediction value to be continuously optimized;
and S5, evaluating the BP neural network by using the divided verification samples, and determining an optimal BP neural network model.
Preferably, in S5, if the training sample error is decreased but the verification sample error is increased, the training is stopped, and the connection weight and the threshold value with the minimum verification sample error are selected and returned to determine the optimal BP neural network model.
Preferably, the multi-layer network node in S3 includes an input layer, a hidden layer and an output layer, and the input layer accepts data input; the hidden layer and the output layer contain functional neurons, which are capable of performing functional processing on information.
Preferably, 80% of the training samples in S1 are monthly water consumption, water supply and water supply data before 3 years, and the 20% validation samples are monthly water consumption, water supply and water supply data from the previous 3 years to the current time period
Compared with the prior art, the invention has the beneficial effects that:
firstly, the system can acquire data of real-time water supply, water consumption, real-time water inflow (real-time rainfall condition) and the like in the rural area based on a rural drinking water safety information management platform.
The invention can predict the water supply, water supply and water consumption of rural areas based on the historical data and the real-time monitoring data by acquiring a large amount of rural historical water supply data, water use data, incoming water data and real-time monitoring data as training data for machine learning, researching the relation among historical incoming water, historical water supply and historical water consumption by using a machine learning technology, and realizing the water supply, incoming water and water consumption of rural areas based on the historical data and the real-time monitoring data by using a deep neural network algorithm and a water balance algorithm to distribute the water supply of rural areas every month, thereby improving the guarantee rate of rural water supply.
Drawings
FIG. 1 is a block diagram of a machine learning based rural water supply system of the present invention;
FIG. 2 is a flow chart of the BP neural network-based machine learning model of the present invention;
FIG. 3 is a flow chart of a rural water supply method based on machine learning of the present invention;
FIG. 4 is a flow chart of the rural water supply distribution method based on water balance of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Examples
Referring to fig. 1-4, the present invention provides a technical solution: a rural water supply system based on machine learning comprises a lead-in data module, a data monitoring and collecting module, a data storage module, a data preprocessing module, a data training module, a data predicting module, a data verifying module and an interface service module, wherein the electrical output ends of the lead-in data module and the data monitoring and collecting module are connected with the electrical input end of the data preprocessing module, the electrical output end of the data preprocessing module is connected with the electrical input end of the data storage module, the electrical output end of the data storage module is electrically connected with the electrical input end of the data training module, the electrical output end of the data training module is electrically connected with the electrical input end of the data predicting module, the electrical output end of the data predicting module is connected with the electrical input end of the data verifying module, and the electrical output end of the data verifying module is connected with the electrical input end of the interface service module, the output ends of the data prediction module and the data verification module are electrically connected with the data training module;
the import data module is used for importing the data of the historical water consumption, the water supply amount and the water consumption amount in the rural area;
the data monitoring and collecting module is used for collecting monthly actual water supply data, actual water use data and actual rainfall data in a rural water supply system;
the data storage module is used for storing the preprocessed data in a classified manner so as to facilitate subsequent calculation and calling;
the data preprocessing module is used for preprocessing the acquired data and eliminating invalid and unreasonable data;
the data training module is used for taking historical data before 3 years from the current time interval as a training sample, taking actual monitoring acquisition data which is near 3 years from the current time interval as a test sample, and realizing machine learning training based on a BP neural network algorithm;
the data prediction module is used for predicting data such as water supply amount in 3 years near the current time period based on training and learning of historical data;
and the data verification module is used for carrying out error analysis by utilizing actual acquired data and predicted data which are close to 3 years away from the current time period to determine an optimal model and provide technical support for reasonably carrying out rural water supply distribution.
When the invention is implemented, the concrete steps are as follows: and the data prediction module and the data verification module are used for feeding error analysis back to the training model and adjusting the model connection weight and the threshold value.
When the invention is implemented, the concrete steps are as follows: the data training module comprises a training sample, a testing sample and a network node, wherein the training sample is connected with the testing sample, the testing sample is connected with the network node, the training sample takes monthly water consumption, water supply and water inflow before 3 years as input samples, and takes monthly water consumption, water supply and water inflow after 1 year as target samples; the test sample uses 3 years of monthly water consumption, water supply and water inflow as input samples, and uses 1 year of monthly water consumption, water supply and water inflow as comparison samples, and the network node is provided with 3 input units, a hidden layer is provided with 1 layer with 12 neural units and 3 output units.
When the invention is implemented, the concrete steps are as follows: the interface service module is used for forwarding data and packaging and analyzing the data.
The invention also provides a rural water supply method based on machine learning, which comprises the following steps,
the method comprises the following steps: acquiring rural historical water supply, water consumption and water inflow data, importing the historical data into a system through an import data module, preprocessing the data and storing the preprocessed data in a data storage module;
step two: the method comprises the steps of collecting data such as the latest water supply amount, the actual water consumption amount and the actual rainfall amount of a rural water supply system, preprocessing the data, storing the preprocessed data in a data storage module, and updating system data information in time;
step three: the data preprocessing module processes and corrects the obtained data, judges the validity of the data, and rejects unreasonable data and invalid data according to a judgment rule set by a system;
step four: the data training module is used for classifying and calling water supply data, water consumption data and precipitation data from the data storage module;
step five: inputting a time period in which the water consumption and the water supply amount need to be predicted, and predicting the water consumption and the water supply amount in the time period through an optimized BP neural network;
step six: and (3) carrying out reasonable water distribution on the water supply quantity in the rural water supply system according to the actual water supply capacity of the water supply system and by combining a water quantity balance equation.
When the invention is implemented, the concrete steps are as follows: and correcting the data by adopting characteristic normalization in the third step, wherein the characteristic normalization equation is as follows:
in the formula: x is the number ofiThe monthly water consumption data/water supply data/water coming data of the past year; x is the number ofminThe minimum water consumption data/minimum water supply data of the past year; x is the number ofmaxThe data is the maximum water consumption data/maximum water supply data; x'iIs the processed input value.
When the invention is implemented, the concrete steps are as follows: step four, taking various data before 3 years as samples to perform machine learning training, wherein the specific training steps are as follows:
s1, dividing the sample data into training samples and verification samples according to the time sequence; 80% of training samples, 20% of validation samples;
s2, predicting the water quantity based on the BP neural algorithm;
s3, training a multilayer network node to form a BP neural network by using a BP neural algorithm;
s4, using the divided training sample training model, carrying out error analysis on the output result and the target result, and then carrying out inverse pushing to correct the connection weight and the threshold of the BP neural network to obtain the connection weight and the threshold which enable the BP neural model prediction value to be continuously optimized;
and S5, evaluating the BP neural network by using the divided verification samples, and determining an optimal BP neural network model.
In the specific embodiment, 80% of the training samples in S1 are monthly water consumption, water supply and water supply data before 3 years, and 20% of the verification samples are monthly water consumption, water supply and water supply data from the previous 3 years to the current time period.
In a specific embodiment, the multilayer network node in S3 includes an input layer, a hidden layer, and an output layer, where the input layer accepts external data input, has only an input function, and cannot perform function processing on information; the hidden layer and the output layer comprise functional neurons and can perform function processing on information. Training a model by using divided training samples, wherein the training is divided into positive feedback and negative feedback; carrying out error analysis on the output result and the target result, and then carrying out reverse-pushing correction on the connection weight and the threshold of the neural network to obtain the connection weight and the threshold which enable the BP neural model to be continuously optimized;
the multi-layer network node is specifically represented as: an input node: x is the number ofiAnd implicit node: y isjAnd an output node: h islThe network weight between the input node and the hidden node is wjiThe network weight of the hidden node and the output node is bljThe bias of the input layer to the hidden layer is θjThe bias from the hidden layer to the output layer is σl. Wherein i is the number of input nodes; j is the number of hidden layer nodes; l is the number of output nodes, k is the number of learning samples,the excitation function is f (x), f (x) is Sigmoid function in form
When the desired output of the output node is tlThen, the model calculation steps are as follows:
input of the input node: x is the number ofi
Output of implicit node:
in the formula: w is ajiThe connection weight from the input layer to the hidden layer; thetajNode threshold values for hidden layer nodes.
Output of the output node:
in the formula: bjlThe connection weight from the hidden layer to the output layer; sigmalIs the node threshold of the output layer node.
Modification formula of output layer (implicit node to output node):
desired output of output node: t is tl
And (3) error control: all sample errors:
in the formula:
error for one sample; p is the number of samples.
Error correction formula: deltal＝(tl-hl)hl(1-hl)
Weight correction: blj(k+1)＝blj(k)+ηδlyj
Threshold value correction: sigmal(k+1)＝σl(k)+ηδl
Modified formula of hidden node layer (input node to hidden node):
error formula:
weight correction: w is aji(k+1)＝wji(k)+η'δj'xi
Threshold value correction: thetaj(k+1)＝θj(k)+η'δj'；
Aiming at the sixth step: according to the actual water supply capacity of the water supply system, reasonable water distribution is carried out on the water supply quantity in the rural water supply system by combining a water quantity balance equation, wherein the water quantity balance equation is as follows: wAmount of water supply＝WAmount of water used+WLoss of power
Wherein WAmount of water supplyFor actual water supply, WAmount of water usedW is the actual water consumptionLoss of powerWater and pipeline water loss for production;
when W'Amount of water supply＞W'Amount of water usedThen WAmount of water supply＝ηW′Amount of water used，WDiversion volume＝0
When W'Amount of water supply＜W'Amount of water usedWhen W isDiversion volume＝ηW′Amount of water used-W'Amount of water supply，WAmount of water supply＝WDiversion volume+W'Amount of water supply
W'Amount of water supplyPredicting the amount of water that can be provided by the water supply system; w'Amount of water usedη is an empirical coefficient set to take account of the lost water in the pipeline, WDiversion volumeIn order to require the amount of water to be recalled from other areas.
When the system is used, data such as water supply quantity, water consumption quantity, real-time rainfall and the like of a rural water supply system are collected through front-end monitoring equipment; the rural water supply system based on machine learning comprises a lead-in data module, a data monitoring and collecting module, a data storage module, a data preprocessing module, a data training module, a data prediction and verification module and an interface service module. Importing the data of the historical water consumption, the water supply quantity and the water consumption quantity in the rural areas through an importing data module; acquiring monthly actual water supply data, actual water use data and actual rainfall data in a rural water supply system through a data acquisition monitoring module; the data preprocessing module preprocesses the acquired data and eliminates invalid and unreasonable data; the data storage module stores the preprocessed data in a classified manner, so that subsequent calculation and calling are facilitated; the data training module takes historical data before 3 years as training samples, takes actual monitoring and collecting data of nearly 3 years as inspection samples, and realizes machine learning training based on a BP neural network algorithm; the data prediction module predicts the water supply amount and other data of the last 3 years based on the training and learning of historical data; the data verification module performs error analysis by using actual collected data and predicted data of nearly 3 years to determine an optimal model, and provides technical support for reasonably distributing water supply in rural areas.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. The utility model provides a rural water supply system based on machine learning, includes leading-in data module, data monitoring acquisition module, data storage module, data preprocessing module, data training module, data prediction module, data verification module, interface service module, its characterized in that: the electrical output ends of the imported data module and the data monitoring and collecting module are connected with the electrical input end of the data preprocessing module, the electrical output end of the data preprocessing module is connected with the electrical input end of the data storage module, the electrical output end of the data storage module is electrically connected with the electrical input end of the data training module, the electrical output end of the data training module is electrically connected with the electrical input end of the data prediction module, the electrical output end of the data prediction module is connected with the electrical input end of the data verification module, the electrical output end of the data verification module is connected with the electrical input end of the interface service module, and the output ends of the data prediction module and the data verification module are electrically connected with the data training module;
the import data module is used for importing the data of the historical water consumption, the water supply amount and the water consumption amount in the rural area;
the data monitoring and collecting module is used for collecting monthly actual water supply data, actual water use data and actual rainfall data in a rural water supply system;
the data storage module is used for storing the preprocessed data in a classified manner so as to facilitate subsequent calculation and calling;
the data preprocessing module is used for preprocessing the acquired data and eliminating invalid and unreasonable data;
the data training module is used for taking historical data away from the current time period as a training sample, taking actual monitoring and collecting data away from the current time period as a test sample, and realizing machine learning training based on a BP neural network algorithm;
the data prediction module is used for predicting data such as water supply amount and the like from the current time period based on training and learning of historical data;
and the data verification module is used for carrying out error analysis by utilizing actual acquired data and predicted data which are far away from the current time period to determine an optimal model.
2. The rural water supply system based on machine learning of claim 1, characterized in that: and the data prediction module and the data verification module are used for feeding error analysis back to the training model and adjusting the model connection weight and the threshold value.
3. The rural water supply system based on machine learning of claim 1, characterized in that: the data training module comprises a training sample, a testing sample and a network node, wherein the training sample is connected with the testing sample, and the testing sample is connected with the network node.
4. The rural water supply system based on machine learning of claim 1, characterized in that: the interface service module is used for forwarding data and packaging and analyzing the data.
5. A rural water supply method based on machine learning according to any one of claims 1-4, characterized by comprising the following steps:
the method comprises the following steps: acquiring rural historical water supply, water consumption and water inflow data, importing the historical data into a system through an import data module, preprocessing the data and storing the preprocessed data in a data storage module;
step two: the method comprises the steps of collecting data such as the latest water supply amount, the actual water consumption amount and the actual rainfall amount of a rural water supply system, preprocessing the data, storing the preprocessed data in a data storage module, and updating system data information in time;
step three: the data preprocessing module processes and corrects the obtained data, judges the validity of the data, and rejects unreasonable data and invalid data according to a judgment rule set by a system;
step four: the data training module is used for classifying and calling water supply data, water consumption data and precipitation data from the data storage module;
step five: inputting a time period in which the water consumption and the water supply amount need to be predicted, and predicting the water consumption and the water supply amount in the time period through an optimized BP neural network;
step six: and (3) carrying out reasonable water distribution on the water supply quantity in the rural water supply system according to the actual water supply capacity of the water supply system and by combining a water quantity balance equation.
6. The rural water supply method based on machine learning according to claim 5, characterized in that: and correcting the data by adopting characteristic normalization in the third step, wherein the characteristic normalization equation is as follows:
7. the rural water supply method based on machine learning according to claim 5, characterized in that: the fourth step comprises the step of performing machine learning training by taking various types of data as samples, wherein the specific training steps are as follows:
s1, dividing the sample data into training samples and verification samples according to the time sequence; 80% of training samples, 20% of validation samples;
s2, predicting the water quantity based on the BP neural algorithm;
s3, training a multilayer network node to form a BP neural network by using a BP neural algorithm;
s4, using the divided training sample training model, carrying out error analysis on the output result and the target result, and then carrying out inverse pushing to correct the connection weight and the threshold of the BP neural network to obtain the connection weight and the threshold which enable the BP neural model prediction value to be continuously optimized;
and S5, evaluating the BP neural network by using the divided verification samples, and determining an optimal BP neural network model.
8. The rural water supply method based on machine learning according to claim 7, characterized in that: and in the step S5, if the training sample error is reduced but the verification sample error is increased, stopping training, and selecting the connection weight and the threshold value with the minimum verification sample error for returning, so as to determine the optimal BP neural network model.
9. The rural water supply method based on machine learning according to claim 7, characterized in that:
the multi-layer network node in the S3 comprises an input layer, a hidden layer and an output layer, wherein the input layer accepts data input; the hidden layer and the output layer contain functional neurons, which are capable of performing functional processing on information.
10. The rural water supply method based on machine learning according to claim 7, characterized in that: 80% of the training samples in the S1 are monthly water consumption, water supply and water supply data before 3 years, and the 20% verification samples are monthly water consumption, water supply and water supply data from the previous 3 years to the current time period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910918895.XA CN111105065A (en) | 2019-09-26 | 2019-09-26 | Rural water supply system and method based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910918895.XA CN111105065A (en) | 2019-09-26 | 2019-09-26 | Rural water supply system and method based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111105065A true CN111105065A (en) | 2020-05-05 |
Family
ID=70421259
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910918895.XA Pending CN111105065A (en) | 2019-09-26 | 2019-09-26 | Rural water supply system and method based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111105065A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111681131A (en) * | 2020-06-16 | 2020-09-18 | 浙江和达科技股份有限公司 | Water resource management method and management system based on artificial intelligence |
| CN112529368A (en) * | 2020-11-20 | 2021-03-19 | 成都赛零信息技术开发有限公司 | Intelligent water use plan generation method for water supply network and intelligent water use plan using method |
| CN112982297A (en) * | 2021-04-19 | 2021-06-18 | 四川省水利科学研究院 | System for realizing slope ecological protection based on convolutional neural network |
| CN113240314A (en) * | 2021-05-28 | 2021-08-10 | 浙江机电职业技术学院 | Secondary water supply peak shifting scheduling system |
| CN113250271A (en) * | 2021-06-17 | 2021-08-13 | 武汉科迪智能环境股份有限公司 | Equipment control method and device, water supply system and storage medium |
| WO2021258635A1 (en) * | 2020-06-24 | 2021-12-30 | 山东建筑大学 | Water usage pattern-based user profiling method and system |
| CN114477329A (en) * | 2022-02-22 | 2022-05-13 | 江苏舜维环境工程有限公司 | Integrated water treatment device for cement plant |
| CN116562600A (en) * | 2023-07-11 | 2023-08-08 | 中关村科学城城市大脑股份有限公司 | Water supply control method, device, electronic equipment and computer readable medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150347922A1 (en) * | 2014-05-30 | 2015-12-03 | International Business Machines Corporation | Multi-model blending |
| CN105956690A (en) * | 2016-04-25 | 2016-09-21 | 广州东芝白云自动化系统有限公司 | Water supply prediction method and water supply prediction system |
| CN110009161A (en) * | 2019-04-15 | 2019-07-12 | 成都四方伟业软件股份有限公司 | Water supply forecast method and device |
-
2019
- 2019-09-26 CN CN201910918895.XA patent/CN111105065A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150347922A1 (en) * | 2014-05-30 | 2015-12-03 | International Business Machines Corporation | Multi-model blending |
| CN105956690A (en) * | 2016-04-25 | 2016-09-21 | 广州东芝白云自动化系统有限公司 | Water supply prediction method and water supply prediction system |
| CN110009161A (en) * | 2019-04-15 | 2019-07-12 | 成都四方伟业软件股份有限公司 | Water supply forecast method and device |
Non-Patent Citations (2)
| Title |
|---|
| 单金林,戴雄奇,李江涛: "利用BP网络建立预测城市用水量模型" * |
| 金建华,史义雄,史永刚: "基于BP神经网络构建城市时需水量预测模型" * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111681131A (en) * | 2020-06-16 | 2020-09-18 | 浙江和达科技股份有限公司 | Water resource management method and management system based on artificial intelligence |
| WO2021258635A1 (en) * | 2020-06-24 | 2021-12-30 | 山东建筑大学 | Water usage pattern-based user profiling method and system |
| CN112529368A (en) * | 2020-11-20 | 2021-03-19 | 成都赛零信息技术开发有限公司 | Intelligent water use plan generation method for water supply network and intelligent water use plan using method |
| CN112982297A (en) * | 2021-04-19 | 2021-06-18 | 四川省水利科学研究院 | System for realizing slope ecological protection based on convolutional neural network |
| CN112982297B (en) * | 2021-04-19 | 2021-07-13 | 四川省水利科学研究院 | System for realizing slope ecological protection based on convolutional neural network |
| CN113240314A (en) * | 2021-05-28 | 2021-08-10 | 浙江机电职业技术学院 | Secondary water supply peak shifting scheduling system |
| CN113250271A (en) * | 2021-06-17 | 2021-08-13 | 武汉科迪智能环境股份有限公司 | Equipment control method and device, water supply system and storage medium |
| CN114477329A (en) * | 2022-02-22 | 2022-05-13 | 江苏舜维环境工程有限公司 | Integrated water treatment device for cement plant |
| CN114477329B (en) * | 2022-02-22 | 2023-01-06 | 江苏舜维环境工程有限公司 | Cement plant integrates water treatment facilities |
| CN116562600A (en) * | 2023-07-11 | 2023-08-08 | 中关村科学城城市大脑股份有限公司 | Water supply control method, device, electronic equipment and computer readable medium |
| CN116562600B (en) * | 2023-07-11 | 2023-09-19 | 中关村科学城城市大脑股份有限公司 | Water supply control method, device, electronic equipment and computer readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111105065A (en) | Rural water supply system and method based on machine learning | |
| CN111199016B (en) | Daily load curve clustering method for improving K-means based on DTW | |
| Nie et al. | Network traffic prediction based on deep belief network in wireless mesh backbone networks | |
| CN106022521B (en) | Short-term load prediction method of distributed BP neural network based on Hadoop architecture | |
| CN112131783B (en) | Power distribution station area big data-based household transformer topology relation identification method | |
| CN111210093B (en) | Daily water consumption prediction method based on big data | |
| CN106682763B (en) | Power load optimization prediction method for large amount of sample data | |
| CN111369070A (en) | Envelope clustering-based multimode fusion photovoltaic power prediction method | |
| Dong et al. | Applying the ensemble artificial neural network-based hybrid data-driven model to daily total load forecasting | |
| CN114841476B (en) | Urban rainwater resource utilization space-time dynamic allocation and transaction method and system | |
| CN111008726B (en) | Class picture conversion method in power load prediction | |
| CN112734128A (en) | 7-day power load peak value prediction method based on optimized RBF | |
| CN113361195B (en) | Power distribution network line ultra-short term load prediction method based on LSTM and similar days | |
| CN114358213A (en) | Error ablation processing method, system and medium for nonlinear time series data prediction | |
| CN114330934A (en) | Model parameter self-adaptive GRU new energy short-term power generation power prediction method | |
| CN112348290A (en) | River water quality prediction method, device, storage medium and equipment | |
| CN110880044B (en) | Markov chain-based load prediction method | |
| CN114971090A (en) | Electric heating load prediction method, system, equipment and medium | |
| CN110390440B (en) | Clustering and deep neural network-based intelligent ammeter user aggregate load prediction method | |
| CN115081597A (en) | Method, system, equipment and medium for performing carbon check by using electricity based on machine learning | |
| CN109214610A (en) | A kind of saturation Methods of electric load forecasting based on shot and long term Memory Neural Networks | |
| CN113723791A (en) | Urban water supply analysis method and device based on salt avoidance and fresh storage | |
| CN111697560B (en) | Method and system for predicting load of power system based on LSTM | |
| CN106650060B (en) | Photovoltaic cell internal resistance attenuation coefficient prediction method | |
| CN107818678A (en) | Real-time online modification method and device for power information acquisition system |
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 |