CN112215400A - Underground water exploitation excessive early warning method and system - Google Patents
Underground water exploitation excessive early warning method and system Download PDFInfo
- Publication number
- CN112215400A CN112215400A CN202010961209.XA CN202010961209A CN112215400A CN 112215400 A CN112215400 A CN 112215400A CN 202010961209 A CN202010961209 A CN 202010961209A CN 112215400 A CN112215400 A CN 112215400A
- Authority
- CN
- China
- Prior art keywords
- underground water
- data
- exploitation
- hidden layer
- early warning
- 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 61
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012549 training Methods 0.000 claims abstract description 43
- 238000003062 neural network model Methods 0.000 claims abstract description 14
- 230000008569 process Effects 0.000 claims abstract description 11
- 238000005065 mining Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 230000008020 evaporation Effects 0.000 claims description 8
- 238000001704 evaporation Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 7
- 230000007704 transition Effects 0.000 claims 1
- 239000003673 groundwater Substances 0.000 description 14
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
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"
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The invention provides an underground water exploitation excessive early warning method and system, which select a plurality of influence factors related to underground water level, train through an LSTM neural network model, control parameter weights in the training process through a forgetting gate, an input gate and an output gate of the LSTM model, obtain a prediction data set according to the determined parameter weights, predict the underground water level, and give an alarm when a predicted value reaches an underground water level alarm threshold value, thereby realizing the underground water exploitation excessive early warning.
Description
Technical Field
The invention relates to the technical field of underground water, in particular to an underground water exploitation excessive early warning method and system.
Background
The underground water level is taken as an important basis of underground water resource management, has important significance for reasonable development and sustainable utilization of underground water resources, but shows high hysteresis on a time line due to the influence of a series of natural conditions and artificial activities. The traditional early warning method for underground water mining usually adopts a simple linear function to describe the dynamic change characteristics of the underground water mining, and the model construction is carried out by only adopting the underground water level, so that the influence of external conditions is ignored, and the result is often unsatisfactory.
Disclosure of Invention
The invention aims to provide an underground water exploitation excessive early warning method and system, aims to solve the problem that an underground water exploitation early warning model in the prior art is limited to a single influence factor, achieves early warning on underground water exploitation through multiple influence factors, and improves early warning precision.
In order to achieve the technical purpose, the invention provides an underground water exploitation excessive early warning method, which comprises the following operations:
selecting multi-influence factor data related to underground water, and carrying out standardized treatment;
dividing the standardized data into a training set and a prediction set, segmenting the training set, inputting the segmented training set into a hidden layer, training the hidden layer through an LSTM neural network model, and acquiring theoretical output and actual output results;
determining parameter weight according to theoretical output and actual output of the hidden layer to obtain a prediction time sequence set;
and comparing the value concentrated according to the predicted time sequence with a preset underground water level alarm threshold value, and performing underground water mining over-warning when the threshold value is reached.
Preferably, the multiple influence factor data comprise groundwater level observation data, mining volume data, rainfall, evaporation capacity, air temperature and sunshine meteorological data.
Preferably, the normalization process is specifically:
in the formula, x*Is the normalized value, x is the value before normalization,
average value, x, of each variable of the raw dataδIs the standard deviation of each variable in the original data set.
Preferably, the determining the parameter weight according to the theoretical output and the actual output of the hidden layer specifically includes:
in the formula, yiAs theoretical output, piFor actual output, when EmsThe minimum parameter is the determined parameter weight.
The invention also provides an underground water exploitation excessive early warning system, which comprises:
the data selecting module is used for selecting the multi-influence factor data related to the underground water and carrying out standardized processing;
the hidden layer output module is used for dividing the standardized data into a training set and a prediction set, dividing the training set, inputting the divided training set into a hidden layer, training the hidden layer through an LSTM neural network model, and acquiring theoretical output and actual output results;
the prediction set acquisition module is used for determining the parameter weight according to the theoretical output and the actual output of the hidden layer to acquire a prediction time sequence set;
and the threshold comparison module is used for comparing the value concentrated according to the predicted time sequence with a preset underground water level alarm threshold, and carrying out underground water over-exploitation early warning when the threshold is reached.
Preferably, the multiple influence factor data comprise groundwater level observation data, mining volume data, rainfall, evaporation capacity, air temperature and sunshine meteorological data.
Preferably, the normalization process is specifically:
in the formula, x*Is the normalized value, x is the value before normalization,
average value, x, of each variable of the raw dataδIs the standard deviation of each variable in the original data set.
Preferably, the determining the parameter weight according to the theoretical output and the actual output of the hidden layer specifically includes:
in the formula, yiAs theoretical output, piFor actual output, when EmsThe minimum parameter is the determined parameter weight.
The effect provided in the summary of the invention is only the effect of the embodiment, not all the effects of the invention, and one of the above technical solutions has the following advantages or beneficial effects:
compared with the prior art, the method has the advantages that multiple influence factors related to the groundwater level are selected, the LSTM neural network model is used for training, the parameter weight in the training process is controlled through the forgetting gate, the input gate and the output gate of the LSTM model, the prediction data set is obtained according to the determined parameter weight, the groundwater level is predicted, when the predicted value reaches the groundwater level alarm threshold value, an alarm is given, and therefore excessive early warning of groundwater exploitation is achieved.
Drawings
Fig. 1 is a flowchart of an underground water exploitation excessive warning method provided in an embodiment of the present invention;
fig. 2 is a block diagram of an underground water exploitation excessive warning system provided in an embodiment of the present invention.
Detailed Description
In order to clearly explain the technical features of the present invention, the following detailed description of the present invention is provided with reference to the accompanying drawings. The following disclosure provides many different embodiments, or examples, for implementing different features of the invention. To simplify the disclosure of the present invention, the components and arrangements of specific examples are described below. Furthermore, the present invention may repeat reference numerals and/or letters in the various examples. This repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed. It should be noted that the components illustrated in the figures are not necessarily drawn to scale. Descriptions of well-known components and processing techniques and procedures are omitted so as to not unnecessarily limit the invention.
The method and system for warning of excessive underground water exploitation provided by the embodiment of the invention are described in detail below with reference to the accompanying drawings.
As shown in fig. 1, an embodiment of the present invention discloses an underground water exploitation excessive warning method, which includes the following operations:
selecting multi-influence factor data related to underground water, and carrying out standardized treatment;
dividing the standardized data into a training set and a prediction set, segmenting the training set, inputting the segmented training set into a hidden layer, training the hidden layer through an LSTM neural network model, and acquiring theoretical output and actual output results;
determining parameter weight according to theoretical output and actual output of the hidden layer to obtain a prediction time sequence set;
and comparing the value concentrated according to the predicted time sequence with a preset underground water level alarm threshold value, and performing underground water mining over-warning when the threshold value is reached.
According to the embodiment of the invention, the neural network model is adopted to early warn underground water exploitation, multiple influence factors related to underground water are selected, and the multiple influence factors are combined and adjusted at the same time, so that the early warning precision is ensured.
Selecting multiple influence factor data related to groundwater in a period of time in recent years, wherein the multiple influence factor data comprise meteorological data such as groundwater level observation data, mining quantity data, rainfall, evaporation capacity, air temperature, sunshine and the like, and the meteorological data are represented as follows by a data set:
Fn＝(x1,x2,…,xn)
in the formula, xt＝{at,bt,ct,dt,et,ftAnd respectively representing underground water level observation data, mining quantity data, rainfall, evaporation capacity, air temperature and sunlight data corresponding to the time t.
In order to improve the early warning precision and accelerate the convergence speed of the neural network model, the original time sequence variable is subjected to standardization treatment as follows:
in the formula, x*Is the normalized value, x is the value before normalization,
average value, x, of each variable of the raw dataδIs the standard deviation of each variable in the original data set.
And (4) training the data after the standardization processing through a multi-influence factor neural network model. And (3) carrying out segmentation processing on the original data set at an input layer, carrying out weight updating on a hidden layer through an LSTM unit structure, outputting a prediction result and carrying out anti-standardization processing at an output layer, and verifying an error.
Dividing the normalized data into a training set and a test set, which are respectively expressed as follows:
Ftraining＝(x1,x2,…,xm)
FTesting＝(xm+1,xm+2,…,xn)
Segmenting the training set, setting the length L of a segmentation window, and inputting a data set of a hidden layer as follows:
X＝{X1,X2,…,XL}
Xt＝{xt,xt+1,…,xm-L+t-1}
in the formula, X is a data set input to L cells of the hidden layer.
The theoretical output of the hidden layer is:
Y＝{Y1,Y2,…,YL}
Yt＝{yt+1,yt+2,…,ym-L+t}
the actual output of the hidden layer is:
P＝{P1,P2,…,PL}
Pt＝LSTM(Xt,ct-1,ht-1)
in the formula, ct-1Cell state at time t-1, ht-1The LSTM neural network controls the training process through a forgetting gate, an input gate and an output gate for an implicit state at the time of t-1.
The mean square error is taken as a loss calculation formula in the training process, and the following formula is adopted:
in the formula, yiAs theoretical output, piFor actual output, when EmsThe minimum parameter is the determined parameter weight. The parameter weights of the LSTM neural network are continually updated with the goal of minimum loss until the loss is minimal.
Setting the prediction times s, inputting an LSTM network model for training, and outputting a result:
change the time of n +1Inputting the quantity into the model to obtain Pn+2In this way, the prediction time sequence set is obtained as follows:
P*＝{Pn+1,Pn+2,…,Pn+s}
to P*And carrying out denormalization to obtain an actual prediction set.
And setting an underground water level early warning threshold, and when the predicted value reaches the early warning threshold, carrying out underground water development over-warning.
According to the embodiment of the invention, multiple influence factors related to the groundwater level are selected, the LSTM neural network model is used for training, the parameter weight in the training process is controlled through the forgetting gate, the input gate and the output gate of the LSTM model, the prediction data set is obtained according to the determined parameter weight, the groundwater level is predicted, and when the predicted value reaches the groundwater level alarm threshold value, an alarm is given, so that the excessive early warning of groundwater exploitation is realized.
As shown in fig. 2, an embodiment of the present invention further discloses an underground water exploitation excessive warning system, which includes:
the data selecting module is used for selecting the multi-influence factor data related to the underground water and carrying out standardized processing;
the hidden layer output module is used for dividing the standardized data into a training set and a prediction set, dividing the training set, inputting the divided training set into a hidden layer, training the hidden layer through an LSTM neural network model, and acquiring theoretical output and actual output results;
the prediction set acquisition module is used for determining the parameter weight according to the theoretical output and the actual output of the hidden layer to acquire a prediction time sequence set;
and the threshold comparison module is used for comparing the value concentrated according to the predicted time sequence with a preset underground water level alarm threshold, and carrying out underground water over-exploitation early warning when the threshold is reached.
Selecting multiple influence factor data related to groundwater in a period of time in recent years, wherein the multiple influence factor data comprise meteorological data such as groundwater level observation data, mining quantity data, rainfall, evaporation capacity, air temperature, sunshine and the like, and the meteorological data are represented as follows by a data set:
Fn＝(x1,x2,…,xn)
in the formula, xt＝{at,bt,ct,dt,et,ftAnd respectively representing underground water level observation data, mining quantity data, rainfall, evaporation capacity, air temperature and sunlight data corresponding to the time t.
In order to improve the early warning precision and accelerate the convergence speed of the neural network model, the original time sequence variable is subjected to standardization treatment as follows:
in the formula, x*Is the normalized value, x is the value before normalization,
average value, x, of each variable of the raw dataδIs the standard deviation of each variable in the original data set.
And (4) training the data after the standardization processing through a multi-influence factor neural network model. And (3) carrying out segmentation processing on the original data set at an input layer, carrying out weight updating on a hidden layer through an LSTM unit structure, outputting a prediction result and carrying out anti-standardization processing at an output layer, and verifying an error.
Dividing the normalized data into a training set and a test set, which are respectively expressed as follows:
Ftraining＝(x1,x2,…,xm)
FTesting＝(xm+1,xm+2,…,xn)
Segmenting the training set, setting the length L of a segmentation window, and inputting a data set of a hidden layer as follows:
X＝{X1,X2,…,XL}
Xt＝{xt,xt+1,…,xm-L+t-1}
in the formula, X is a data set input to L cells of the hidden layer.
The theoretical output of the hidden layer is:
Y＝{Y1,Y2,…,YL}
Yt＝{yt+1,yt+2,…,ym-L+t}
the actual output of the hidden layer is:
P＝{P1,P2,…,PL}
Pt＝LSTM(Xt,ct-1,ht-1)
in the formula, ct-1Cell state at time t-1, ht-1The LSTM neural network controls the training process through a forgetting gate, an input gate and an output gate for an implicit state at the time of t-1.
The mean square error is taken as a loss calculation formula in the training process, and the following formula is adopted:
in the formula, yiAs theoretical output, piFor actual output, when EmsThe minimum parameter is the determined parameter weight. The parameter weights of the LSTM neural network are continually updated with the goal of minimum loss until the loss is minimal.
Setting the prediction times s, inputting an LSTM network model for training, and outputting a result:
inputting the variable at the moment n +1 into the model to obtain Pn+2In this way, the prediction time sequence set is obtained as follows:
P*＝{Pn+1,Pn+2,…,Pn+s}
to P*Performing anti-standardization to obtainAnd (4) an inter prediction set.
And setting an underground water level early warning threshold, and when the predicted value reaches the early warning threshold, carrying out underground water development over-warning.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. An underground water exploitation excess warning method, characterized in that the method comprises the following operations:
selecting multi-influence factor data related to underground water, and carrying out standardized treatment;
dividing the standardized data into a training set and a prediction set, segmenting the training set, inputting the segmented training set into a hidden layer, training the hidden layer through an LSTM neural network model, and acquiring theoretical output and actual output results;
determining parameter weight according to theoretical output and actual output of the hidden layer to obtain a prediction time sequence set;
and comparing the value concentrated according to the predicted time sequence with a preset underground water level alarm threshold value, and performing underground water mining over-warning when the threshold value is reached.
2. The underground water exploitation excessive early warning method according to claim 1, wherein the multiple influence factor data comprise underground water level observation data, exploitation amount data, rainfall, evaporation capacity, air temperature and sunshine meteorological data.
3. The method for early warning of excessive underground water exploitation according to claim 1, wherein the standardization process specifically comprises:
in the formula, x*For normalized values, x is normalizationThe value of the previous value is,
average value, x, of each variable of the raw dataδIs the standard deviation of each variable in the original data set.
4. The underground water exploitation excessive early warning method according to claim 1, wherein the determining of the parameter weight according to the theoretical output and the actual output of the hidden layer specifically comprises:
in the formula, yiAs theoretical output, piFor actual output, when EmsThe minimum parameter is the determined parameter weight.
5. An underground water exploitation excess warning system, characterized in that the system comprises:
the data selecting module is used for selecting the multi-influence factor data related to the underground water and carrying out standardized processing;
the hidden layer output module is used for dividing the standardized data into a training set and a prediction set, dividing the training set, inputting the divided training set into a hidden layer, training the hidden layer through an LSTM neural network model, and acquiring theoretical output and actual output results;
the prediction set acquisition module is used for determining the parameter weight according to the theoretical output and the actual output of the hidden layer to acquire a prediction time sequence set;
and the threshold comparison module is used for comparing the value concentrated according to the predicted time sequence with a preset underground water level alarm threshold, and carrying out underground water over-exploitation early warning when the threshold is reached.
6. The underground water exploitation transition early warning system according to claim 5, wherein the multiple influence factor data comprises underground water level observation data, exploitation amount data, rainfall, evaporation capacity, air temperature, and sunshine meteorological data.
7. The underground water exploitation excessive warning system according to claim 5, wherein the standardization process specifically comprises:
in the formula, x*Is the normalized value, x is the value before normalization,
average value, x, of each variable of the raw dataδIs the standard deviation of each variable in the original data set.
8. The underground water exploitation excess warning system according to claim 5, wherein the determining of the parameter weight according to the theoretical output and the actual output of the hidden layer specifically comprises:
in the formula, yiAs theoretical output, piFor actual output, when EmsThe minimum parameter is the determined parameter weight.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010961209.XA CN112215400A (en) | 2020-09-14 | 2020-09-14 | Underground water exploitation excessive early warning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010961209.XA CN112215400A (en) | 2020-09-14 | 2020-09-14 | Underground water exploitation excessive early warning method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112215400A true CN112215400A (en) | 2021-01-12 |
Family
ID=74050323
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010961209.XA Pending CN112215400A (en) | 2020-09-14 | 2020-09-14 | Underground water exploitation excessive early warning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112215400A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115271266A (en) * | 2022-09-27 | 2022-11-01 | 山东省地质矿产勘查开发局八〇一水文地质工程地质大队(山东省地矿工程勘察院) | Groundwater level dynamic prediction method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107544904A (en) * | 2017-08-21 | 2018-01-05 | 哈尔滨工程大学 | A kind of prediction model of software reliability based on depth CG LSTM neutral nets |
| CN109214566A (en) * | 2018-08-30 | 2019-01-15 | 华北水利水电大学 | Short-term wind power prediction method based on shot and long term memory network |
| CN110119854A (en) * | 2018-06-28 | 2019-08-13 | 中国人民解放军陆军军事交通学院镇江校区 | Voltage-stablizer water level prediction method based on cost-sensitive LSTM Recognition with Recurrent Neural Network |
| CN111144286A (en) * | 2019-12-25 | 2020-05-12 | 北京工业大学 | Urban PM2.5 concentration prediction method fusing EMD and LSTM |
| CN111222698A (en) * | 2020-01-06 | 2020-06-02 | 重庆邮电大学 | Long-and-short-term memory network-based ponding water level prediction method for Internet of things |
| CN111242344A (en) * | 2019-12-11 | 2020-06-05 | 大连海事大学 | Intelligent water level prediction method based on cyclic neural network and convolutional neural network |
| CN111310968A (en) * | 2019-12-20 | 2020-06-19 | 西安电子科技大学 | LSTM neural network circulation hydrological forecasting method based on mutual information |
-
2020
- 2020-09-14 CN CN202010961209.XA patent/CN112215400A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107544904A (en) * | 2017-08-21 | 2018-01-05 | 哈尔滨工程大学 | A kind of prediction model of software reliability based on depth CG LSTM neutral nets |
| CN110119854A (en) * | 2018-06-28 | 2019-08-13 | 中国人民解放军陆军军事交通学院镇江校区 | Voltage-stablizer water level prediction method based on cost-sensitive LSTM Recognition with Recurrent Neural Network |
| CN109214566A (en) * | 2018-08-30 | 2019-01-15 | 华北水利水电大学 | Short-term wind power prediction method based on shot and long term memory network |
| CN111242344A (en) * | 2019-12-11 | 2020-06-05 | 大连海事大学 | Intelligent water level prediction method based on cyclic neural network and convolutional neural network |
| CN111310968A (en) * | 2019-12-20 | 2020-06-19 | 西安电子科技大学 | LSTM neural network circulation hydrological forecasting method based on mutual information |
| CN111144286A (en) * | 2019-12-25 | 2020-05-12 | 北京工业大学 | Urban PM2.5 concentration prediction method fusing EMD and LSTM |
| CN111222698A (en) * | 2020-01-06 | 2020-06-02 | 重庆邮电大学 | Long-and-short-term memory network-based ponding water level prediction method for Internet of things |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115271266A (en) * | 2022-09-27 | 2022-11-01 | 山东省地质矿产勘查开发局八〇一水文地质工程地质大队(山东省地矿工程勘察院) | Groundwater level dynamic prediction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110298501B (en) | Electrical load prediction method based on long-time and short-time memory neural network | |
| CN109214566B (en) | Wind power short-term prediction method based on long and short-term memory network | |
| CN107944648B (en) | Large ship speed and oil consumption rate prediction method | |
| CN104077632B (en) | A kind of wind electric field power prediction method based on deep neural network | |
| CN111079980B (en) | Optical power prediction method based on self-adaptive classification strategy and hybrid optimization SVR | |
| CN107358318A (en) | Based on GM（1,1）The urban power consumption Forecasting Methodology of model and Grey Markov chain predicting model | |
| CN111695724B (en) | Wind speed prediction method based on hybrid neural network model | |
| CN112130086B (en) | Method and system for predicting remaining life of power battery | |
| CN104573876A (en) | Wind power plant short-period wind speed prediction method based on time sequence long memory model | |
| CN110263984A (en) | Ultra-short term net load prediction technique based on phase space reconfiguration and deep neural network | |
| CN105787594A (en) | Irradiation prediction method based on multivariate time series and regression analysis | |
| CN114462718A (en) | CNN-GRU wind power prediction method based on time sliding window | |
| CN106354940B (en) | Landscape water quality simulation and method for early warning based on the input of WASP water quality model uncertainty | |
| CN113505938A (en) | Ultra-short-term wind power combined prediction method and system | |
| CN114757427A (en) | Autoregressive corrected LSTM intelligent wind power plant ultra-short term power prediction method | |
| CN112182709A (en) | Rapid prediction method for let-down water temperature of large-scale reservoir stop log door layered water taking facility | |
| Syu et al. | Ultra-short-term wind speed forecasting for wind power based on gated recurrent unit | |
| CN112215400A (en) | Underground water exploitation excessive early warning method and system | |
| CN106772354B (en) | Method for tracking target and device based on parallel fuzzy gaussian sum particle filter | |
| CN116757057A (en) | Air quality prediction method based on PSO-GA-LSTM model | |
| CN105447593A (en) | Rapid updating mixing assimilation method based on time lag set | |
| CN109447843B (en) | Photovoltaic output prediction method and device | |
| CN116565840A (en) | High-precision wind speed soft measurement method for wind power prediction of wind power plant | |
| CN113788007A (en) | Layered real-time energy management method and system | |
| CN113435630A (en) | Basin hydrological forecasting method and system with self-adaptive runoff yield mode |
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: 20210112 |
|
| RJ01 | Rejection of invention patent application after publication |