CN116502809A - Method for predicting sewage quantity during drainage household based on big position data - Google Patents
Method for predicting sewage quantity during drainage household based on big position data Download PDFInfo
- Publication number
- CN116502809A CN116502809A CN202310765152.XA CN202310765152A CN116502809A CN 116502809 A CN116502809 A CN 116502809A CN 202310765152 A CN202310765152 A CN 202310765152A CN 116502809 A CN116502809 A CN 116502809A
- Authority
- CN
- China
- Prior art keywords
- data
- prediction
- model
- sewage quantity
- sewage
- 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
- 239000010865 sewage Substances 0.000 title claims abstract description 89
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012549 training Methods 0.000 claims abstract description 40
- 238000013528 artificial neural network Methods 0.000 claims abstract description 17
- 230000008859 change Effects 0.000 claims abstract description 8
- 238000012360 testing method Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 15
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 claims description 13
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 13
- 238000003062 neural network model Methods 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 230000001932 seasonal effect Effects 0.000 claims description 2
- 238000012795 verification Methods 0.000 claims description 2
- 230000007246 mechanism Effects 0.000 abstract description 4
- 238000007405 data analysis Methods 0.000 abstract description 3
- 238000005065 mining Methods 0.000 abstract description 2
- 238000011160 research Methods 0.000 description 7
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- Operations Research (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a drainage household sewage quantity prediction method based on position big data; firstly, collecting and establishing a drainage household sewage quantity prediction database, then establishing and training a drainage household sewage quantity BP neural network prediction model, and finally, predicting the drainage household sewage quantity; according to the method, two dimensions are selected from influencing factors and models to optimize the sewage prediction model, sources and generation mechanisms of sewage discharge are fully considered, classification treatment of the sources of sewage discharge is creatively provided, thermal data change based on hundred-degree position big data is used for representing population time change, an advanced data analysis method-BP neural network is used for deeply mining implicit relations among sewage amount data in different time periods, and the sewage amount prediction precision, adaptability and universality are improved.
Description
Technical Field
The invention relates to the technical field of drainage prediction, in particular to a drainage household sewage quantity prediction method based on position big data.
Background
The urban domestic sewage discharge prediction is the basis of urban drainage development planning, and the primary condition for realizing optimal scheduling is to obtain reliable short-term discharge prediction data, so that the discharge amount during urban domestic sewage prediction accurately, scientifically and reasonably provides scientific basis for urban water environment planning decisions such as layout setting and intelligent management of urban drainage systems, construction, operation and maintenance of matched pipe networks and sewage interception systems.
At present, domestic and foreign scholars mainly aim at annual sewage quantity prediction or daily sewage quantity prediction research, and research on relevant influence factors, change characteristics, model selection and the like of the sewage quantity prediction is deficient, so that more accurate prediction cannot be realized, real-time regulation and control requirements of sewage plants cannot be met, and intelligent management processes of a drainage pipe network are limited.
The criticality of the sewage quantity prediction influencing factors and the applicability of the selected model directly influence the accuracy and reliability of the prediction data. The sewage discharge amount-related influence factors can be classified into internal and external influence factors. The internal factors should consider the source and the generation mechanism of sewage discharge, the current research is mostly carried out on urban-level domestic sewage quantity prediction, the prediction research on domestic sewage quantity generation source drainage households is ignored, and the refined utilization of sewage quantity prediction data is difficult to realize. External influence factors mainly comprise climate and social factors 2, wherein the climate factors mainly comprise air temperature, air humidity, and yin-yang conditions, the social factors mainly comprise population, holiday conditions, and the like, and time-varying data based on population are key to predicting sewage quantity. The rise of big data and the application of ArcGIS space analysis technology provide a new thought and research method for human mouth space research. The position big data are often applied to the research in the fields of urban population, people flow change and the like, the hundred-degree thermodynamic diagram is a data product based on the hundred-degree software of the mobile phone with a positioning function, the aggregation degree of population activity space can be reflected dynamically by different colors and brightness, the position, the density and the aggregation degree of the population can be reflected intuitively, and the hundred-degree thermodynamic diagram is an important tool for reflecting population changes. In addition, a prediction model, such as an artificial neural network model, is constructed through data mining, an advanced data analysis method is adopted, hidden relations among sewage quantity data in different time periods are deeply mined, and stability and reliability of the prediction model can be effectively improved.
In summary, how to design a model for predicting sewage quantity when draining a household by using an automatic training mode and analyzing based on big position data, and optimizing a model for predicting sewage by selecting two dimensions from influencing factors and the model, fully considering the source and the generation mechanism of sewage discharge, solving the problems of low accuracy, poor applicability and the like of the existing sewage quantity prediction, and becoming a technical problem to be solved urgently by the personnel in the field.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a drainage household sewage quantity prediction method based on position big data.
A method for predicting sewage quantity in drainage households based on big position data specifically comprises the following steps:
s1, collecting a sewage quantity prediction database when a drainage household is established;
s2, building and training a sewage quantity BP neural network prediction model when a user is drained;
1) Determining the input and output of a BP neural network;
according to factors affecting sewage quantity, using thermal data and time as input vectors, using sewage quantity data of a drainage user as output vectors, and establishing a BP neural network prediction model, wherein the BP neural network prediction model comprises 2 input variables and 1 output variable;
2) Sample data normalization processing;
and carrying out normalization processing on the input and output sample data in the training process, wherein a normalization equation formula is mapmin max, and the formula is as follows:
（1）
wherein: y is normalized sample data, x is original sample data, x max 、x min Maximum and minimum values for the original sample data;
the original sample is dataized into values within the interval [ -1,1] by the above formula;
3) Sample data set partitioning
The dataset was randomly divided into three subsets: training set, verification set and test set, the proportion is 7:1:2; the training set is used for adjusting the connection weight and the deviation through a BP algorithm in the training process; verifying samples for determining the structure of the network and deciding to stop training to avoid overfitting; the test set does not participate in the network training process, but is an independent data set for testing the accuracy of the model;
4) Setting hidden layer node number
Selecting two hidden layers, and setting the number of units of each hidden layer to be 5; the activation function of the hidden layer adopts a tangent S-shaped function tan sig, and the activation function of the output layer adopts a logarithmic S-shaped function log sig; performing inverse normalization when outputting a result to obtain sewage quantity during prediction;
5) Setting training process
Setting iteration times and training accuracy in the BP neural network training process; when the model training set precision reaches a set value or the model iteration number reaches a set value, the model can complete training; setting the model training precision to be 0.001 and the iteration number to be 1500;
6) Model checking
Calculating average absolute percentage error MAPE through a test sample set by the trained BP neural network model to judge the prediction accuracy and reliability degree of the prediction model, wherein the lower the MAPE value is, the lower the prediction error is, the better the model prediction effect is, and the higher the prediction reliability degree is;
（2）
wherein y is i As a result of the fact that the value,n is the number of total predicted values; the checking precision requires that the average absolute percentage error of the test sample is less than 10%, and if the average absolute percentage error is more than or equal to 10%, the step S2 is repeated, and the model is retrained;
s3, sewage quantity prediction during the water drainage of the household.
When the sewage discharge of an actual drainer is monitored, calculating an average absolute percentage error by using a predicted value and an actual value of 24 hours; the MAPE value is utilized to evaluate the performance of the sewage quantity prediction model, when the follow-up prediction data arrives, the training model can be directly called, new prediction data are input, and corresponding sewage quantity prediction data can be obtained; when the average absolute percentage error MAPE of the sewage quantity prediction model is more than or equal to 10%, the sewage discharge behavior change caused by the influence of weather or seasonal variation is judged, the database is required to be updated, the recent sewer thermodynamic data and the sewer actual data are added, and S2 is repeated to retrain the model.
Also, the database in step S1 includes: date, time, type of drain, heat data of drain based on hundred degree position big data, actual data of sewage quantity at drain time and predicted data of sewage quantity at drain time; the types of drainage households are classified into residence, business and administrative offices; and carrying out format conversion on the thermal data acquired from the hundred-degree map through an ArcGIS space analysis technology, and recording the thermal data into a prediction database.
In addition, in the drainage household sewage quantity prediction in the step S3, thermal data acquired from a hundred-degree map are required to be continuously converted and processed by an ArcGIS space analysis technology and then are filled into a prediction database; inputting conditions, time and corresponding thermodynamic data of a drainage user according to the BP neural network model; and predicting the sewage quantity when the user is discharged by using the BP neural network model obtained through S2 training, checking and testing.
The invention has the advantages and technical effects that:
according to the household sewage quantity prediction method based on the position big data, the two dimensions are selected from the influencing factors and the model to optimize the household sewage prediction model, the source and the generation mechanism of sewage discharge are fully considered, the classification treatment of the sewage discharge source is creatively provided, the thermal data change based on the hundred-degree position big data is used for representing the population time change, and the advanced data analysis method-BP neural network is used for deeply mining the implicit relation among sewage quantity data in different time periods, so that the sewage quantity prediction precision, adaptability and universality are improved.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
For a further understanding of the nature, features, and efficacy of the present invention, the following examples are set forth to illustrate, but are not limited to, the invention. The present embodiments are to be considered as illustrative and not restrictive, and the scope of the invention is not to be limited thereto.
Referring to fig. 1, in an embodiment of the present invention, based on the above-mentioned problems existing in the prior art, a method for predicting sewage quantity at the time of a drainage user based on big position data is provided, including:
s1 collecting and building sewage quantity prediction database in drainage households
The database comprises date, time, type of the drainer, thermodynamic data of the drainer based on hundred-degree position big data, actual data of sewage quantity at the time of the drainer and predicted data of sewage quantity at the time of the drainer;
the types of drainage households are classified into residence, business and administrative offices;
and carrying out format conversion on thermal data collected from the hundred-degree map to a certain residential drainage user through an ArcGIS space analysis technology, and recording the thermal data into a prediction database.
S2, building and training a sewage quantity BP neural network prediction model in drainage household
1) Determining BP neural network input/output
The example selects the time sewage quantity of a certain residential type drainer as a prediction object, takes the thermal data and time of the certain residential type drainer as input vectors and takes the time sewage quantity data of the certain residential type drainer as output vectors according to factors influencing the time sewage quantity, and establishes a BP neural network prediction model which comprises 2 input variables and 1 output variable.
2) Sample data normalization
And carrying out normalization processing on the input and output sample data in the training process, wherein a normalization equation formula is mapmin max, and the formula is as follows:
wherein: y is sample data after normalization processing, x is original sample data, xmax and xmin are maximum and minimum values of the original sample data.
The raw samples are dataized by the above formula to values within the [ -1,1] interval.
3) Data set partitioning
The example selects 120 samples of thermodynamic and temporal sewage data of a certain residential type drainer for a certain month and 5 days, and randomly divides the samples into three subsets: training set, validation set and test set, wherein training set 84 samples, validation set 12 samples, test set 24 samples.
4) Setting hidden layer node number
In the embodiment, two hidden layers are selected, and the number of units of each hidden layer is set to be 5;
selecting an activation function, wherein the activation function of an implicit layer of the embodiment adopts a tangent S-shaped function tan sig, and the activation function of an output layer adopts a logarithmic S-shaped function log sig;
and (5) carrying out inverse normalization when outputting the result to obtain the sewage quantity during prediction.
5) Setting training process
The model training accuracy is set to 0.001 and the iteration number is 1500 in this example.
6) Model checking
Substituting the test set samples into a prediction model, calculating to obtain a predicted sewage quantity value when a certain residential type is drained, and calculating average absolute percentage error MAPE of the predicted values and actual values of 24 samples;
the average absolute percentage error MAPE=6.10% <10% of the test set is calculated through the formula (2), the prediction reliability degree and the prediction precision are high, and the model can be used for actual prediction.
S3 sewage quantity prediction in household drainage
The example is to collect the thermal data of a certain residential type drainage family from a hundred-degree map, continuously convert the thermal data by ArcGIS space analysis technology and fill the thermal data into a prediction database; according to the BP neural network model input conditions, inputting 48 samples includes: time and corresponding thermal data of the drain user;
predicting the sewage quantity of a certain residential type drainer for 48 hours by using the BP neural network model obtained through S2 training, checking and testing;
the actual sewage discharge amount of a certain residential type drainer is continuously monitored for 48 hours, MAPE is calculated according to a predicted value and an actual value of 48 hours, the average absolute percentage error MAPE=6.7% of the predicted value of 48 hours, the MAPE value can well evaluate the performance of the sewage amount prediction model at the moment, the model is not required to be updated temporarily and can be used continuously, when the follow-up prediction data arrives, the training model can be directly called, new prediction data are input, and the corresponding sewage amount prediction data at the moment can be obtained.
Finally, the invention adopts the mature products and the mature technical means in the prior art.
It will be understood that modifications and variations will be apparent to those skilled in the art from the foregoing description, and it is intended that all such modifications and variations be included within the scope of the following claims.
Claims (4)
1. The method for predicting the sewage quantity in the drainage process based on the big position data is characterized by comprising the following steps:
s1, collecting a sewage quantity prediction database when a drainage household is established;
s2, building and training a sewage quantity BP neural network prediction model when a user is drained;
1) Determining the input and output of a BP neural network;
according to factors affecting sewage quantity, using thermal data and time as input vectors, using sewage quantity data of a drainage user as output vectors, and establishing a BP neural network prediction model, wherein the BP neural network prediction model comprises 2 input variables and 1 output variable;
2) Sample data normalization processing;
and carrying out normalization processing on the input and output sample data in the training process, wherein a normalization equation formula is mapmin max, and the formula is as follows:
（1）
wherein: y is normalized sample data, x is original sample data, x max 、x min Maximum and minimum values for the original sample data;
the original sample is dataized into values within the interval [ -1,1] by the above formula;
3) Sample data set partitioning
The dataset was randomly divided into three subsets: training set, verification set and test set, the proportion is 7:1:2; the training set is used for adjusting the connection weight and the deviation through a BP algorithm in the training process; verifying samples for determining the structure of the network and deciding to stop training to avoid overfitting; the test set does not participate in the network training process, but is an independent data set for testing the accuracy of the model;
4) Setting hidden layer node number
Selecting two hidden layers, and setting the number of units of each hidden layer to be 5; the activation function of the hidden layer adopts a tangent S-shaped function tan sig, and the activation function of the output layer adopts a logarithmic S-shaped function log sig; performing inverse normalization when outputting a result to obtain sewage quantity during prediction;
5) Setting training process
Setting iteration times and training accuracy in the BP neural network training process; when the model training set precision reaches a set value or the model iteration number reaches a set value, the model can complete training; setting the model training precision to be 0.001 and the iteration number to be 1500;
6) Model checking
Calculating average absolute percentage error MAPE through a test sample set by the trained BP neural network model to judge the prediction accuracy and reliability degree of the prediction model, wherein the lower the MAPE value is, the lower the prediction error is, the better the model prediction effect is, and the higher the prediction reliability degree is;
（2）
wherein y is i As a result of the fact that the value,n is the number of total predicted values; the checking precision requires that the average absolute percentage error of the test sample is less than 10%, and if the average absolute percentage error is more than or equal to 10%, the step S2 is repeated, and the model is retrained;
s3, sewage quantity prediction during the water drainage of the household.
2. The method for predicting the sewage quantity at the time of a water drain based on position big data according to claim 1, wherein the method comprises the following steps: when the sewage discharge amount of an actual drainer is monitored, calculating an average absolute percentage error by using a predicted value and an actual value of 24 hours; the MAPE value is utilized to evaluate the performance of the sewage quantity prediction model, when the follow-up prediction data arrives, the training model can be directly called, new prediction data are input, and corresponding sewage quantity prediction data can be obtained; when the average absolute percentage error MAPE of the sewage quantity prediction model is more than or equal to 10%, the sewage discharge behavior change caused by the influence of weather or seasonal variation is judged, the database is required to be updated, the recent sewer thermodynamic data and the sewer actual data are added, and S2 is repeated to retrain the model.
3. The method for predicting the sewage quantity at the time of a water drain based on position big data according to claim 1, wherein the method comprises the following steps: the database in the step S1 includes: date, time, type of drain, heat data of drain based on hundred degree position big data, actual data of sewage quantity at drain time and predicted data of sewage quantity at drain time; the types of drainage households are classified into residence, business and administrative offices; and carrying out format conversion on the thermal data acquired from the hundred-degree map through an ArcGIS space analysis technology, and recording the thermal data into a prediction database.
4. The method for predicting the sewage quantity at the time of a water drain based on position big data according to claim 1, wherein the method comprises the following steps: in the step S3 of predicting the sewage quantity in the drainage process, the thermodynamic data acquired from the hundred-degree map is required to be continuously converted by the ArcGIS space analysis technology and then is filled into a prediction database; inputting conditions, time and corresponding thermodynamic data of a drainage user according to the BP neural network model; and predicting the sewage quantity when the user is discharged by using the BP neural network model obtained through S2 training, checking and testing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310765152.XA CN116502809A (en) | 2023-06-27 | 2023-06-27 | Method for predicting sewage quantity during drainage household based on big position data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310765152.XA CN116502809A (en) | 2023-06-27 | 2023-06-27 | Method for predicting sewage quantity during drainage household based on big position data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116502809A true CN116502809A (en) | 2023-07-28 |
Family
ID=87316993
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310765152.XA Pending CN116502809A (en) | 2023-06-27 | 2023-06-27 | Method for predicting sewage quantity during drainage household based on big position data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116502809A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101009003A (en) * | 2007-01-09 | 2007-08-01 | 武汉理工大学 | Water quality index prediction method used for municipal wastewater design |
| CN102032935A (en) * | 2010-12-07 | 2011-04-27 | 杭州电子科技大学 | Soft measurement method for sewage pumping station flow of urban drainage converged network |
| CN102592008A (en) * | 2011-12-30 | 2012-07-18 | 华东师范大学 | Municipal drainage pipe network design system and method based on GIS (Geographic Information System) technology |
| CN109948863A (en) * | 2019-03-28 | 2019-06-28 | 杭州电子科技大学 | Drainage pipeline networks inspection shaft liquid level prediction technique based on shot and long term memory models LSTM |
| CN110110890A (en) * | 2019-03-28 | 2019-08-09 | 杭州电子科技大学 | Day wastewater quantity prediction method based on ELMAN neural network |
| CN114330913A (en) * | 2021-12-31 | 2022-04-12 | 北控水务(中国)投资有限公司 | Statistical data-based sewage quantity prediction method and system |
| CN114580703A (en) * | 2021-12-31 | 2022-06-03 | 北控水务(中国)投资有限公司 | Water quantity prediction method and device based on land remote sensing identification time-space change analysis |
-
2023
- 2023-06-27 CN CN202310765152.XA patent/CN116502809A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101009003A (en) * | 2007-01-09 | 2007-08-01 | 武汉理工大学 | Water quality index prediction method used for municipal wastewater design |
| CN102032935A (en) * | 2010-12-07 | 2011-04-27 | 杭州电子科技大学 | Soft measurement method for sewage pumping station flow of urban drainage converged network |
| CN102592008A (en) * | 2011-12-30 | 2012-07-18 | 华东师范大学 | Municipal drainage pipe network design system and method based on GIS (Geographic Information System) technology |
| CN109948863A (en) * | 2019-03-28 | 2019-06-28 | 杭州电子科技大学 | Drainage pipeline networks inspection shaft liquid level prediction technique based on shot and long term memory models LSTM |
| CN110110890A (en) * | 2019-03-28 | 2019-08-09 | 杭州电子科技大学 | Day wastewater quantity prediction method based on ELMAN neural network |
| CN114330913A (en) * | 2021-12-31 | 2022-04-12 | 北控水务(中国)投资有限公司 | Statistical data-based sewage quantity prediction method and system |
| CN114580703A (en) * | 2021-12-31 | 2022-06-03 | 北控水务(中国)投资有限公司 | Water quantity prediction method and device based on land remote sensing identification time-space change analysis |
Non-Patent Citations (5)
| Title |
|---|
| 单甘霖: "《多传感器协同跟踪管理与应用[M]》", vol. 1, 国防工业出版社, pages: 37 - 39 * |
| 张宏伟, 岳琳, 王亮: "城市污水排放量预测模型研究", 中国给水排水, no. 09 * |
| 徐哲;邬玲懿;杨成忠;王建中;薛安克;: "基于BP神经网络的城市污水泵站预测模型", 控制工程, no. 04 * |
| 胡馨月: "《基于信息点数据的城市污水管网时污水量分析与预测》", 工程科技Ⅱ辑, no. 2023, pages 038 - 3155 * |
| 饶世雄;明丹;: "遗传算法―人工神经网络应用于城市污水量预测", 山西建筑, no. 09 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110610280B (en) | Short-term prediction method, model, device and system for power load | |
| CN116646933B (en) | Big data-based power load scheduling method and system | |
| CN106779129A (en) | A kind of Short-Term Load Forecasting Method for considering meteorologic factor | |
| CN110046743A (en) | Energy Consumption of Public Buildings prediction technique and system based on GA-ANN | |
| CN106408223A (en) | Short-term load prediction based on meteorological similar day and error correction | |
| CN110929918A (en) | 10kV feeder line fault prediction method based on CNN and LightGBM | |
| CN111126663B (en) | Short-term power load prediction method | |
| CN113554466A (en) | Short-term power consumption prediction model construction method, prediction method and device | |
| KR102369350B1 (en) | Predicting System of Energy Consumption and Data of Air Conditioning Equipment Using Artificial Neural Network and Method Thereof | |
| CN112149890A (en) | Comprehensive energy load prediction method and system based on user energy label | |
| CN117236199B (en) | Method and system for improving water quality and guaranteeing water safety of river and lake in urban water network area | |
| CN112241607A (en) | Water resource planning method based on simulation and considering climate change | |
| CN108346009A (en) | A kind of power generation configuration method and device based on user model self study | |
| Xue et al. | Prediction of natural gas consumption for city-level DHS based on attention GRU: A case study for a northern chinese city | |
| CN115238854A (en) | Short-term load prediction method based on TCN-LSTM-AM | |
| KR20170106686A (en) | Method and apparatus for predicting home energy usage | |
| CN116485582A (en) | Heat supply optimization regulation and control method and device based on deep learning | |
| CN111144628A (en) | Distributed energy supply type cooling, heating and power load prediction model system and method | |
| CN116502809A (en) | Method for predicting sewage quantity during drainage household based on big position data | |
| CN113837486B (en) | RNN-RBM-based distribution network feeder long-term load prediction method | |
| CN116777027A (en) | Load prediction method and system for abnormal days | |
| CN114048928B (en) | Building short-term load prediction method with high migratability | |
| CN117057516B (en) | Carbon accounting parameter analysis and prediction method based on system dynamics | |
| CN117039855B (en) | Intelligent load prediction method and system for power system | |
| CN114650190B (en) | Energy-saving method, system, terminal equipment and storage medium for data center network |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230728 |