CN117892073A - Irrigation area water metering system and water metering method - Google Patents
Irrigation area water metering system and water metering method Download PDFInfo
- Publication number
- CN117892073A CN117892073A CN202410291082.3A CN202410291082A CN117892073A CN 117892073 A CN117892073 A CN 117892073A CN 202410291082 A CN202410291082 A CN 202410291082A CN 117892073 A CN117892073 A CN 117892073A
- Authority
- CN
- China
- Prior art keywords
- sequence
- water
- water level
- water pressure
- time sequence
- 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.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 511
- 238000003973 irrigation Methods 0.000 title claims abstract description 60
- 230000002262 irrigation Effects 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 46
- 239000013598 vector Substances 0.000 claims abstract description 288
- 230000003993 interaction Effects 0.000 claims abstract description 90
- 230000004927 fusion Effects 0.000 claims abstract description 84
- 238000005728 strengthening Methods 0.000 claims abstract description 54
- 238000012300 Sequence Analysis Methods 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000011176 pooling Methods 0.000 claims description 19
- 238000012937 correction Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000013135 deep learning Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 9
- 230000002452 interceptive effect Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 230000004913 activation Effects 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000012731 temporal analysis Methods 0.000 claims description 3
- 238000000700 time series analysis Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 abstract description 7
- 206010063385 Intellectualisation Diseases 0.000 abstract description 5
- 238000012549 training Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 6
- 238000009826 distribution Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 239000000284 extract Substances 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 239000003621 irrigation water Substances 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000009792 diffusion process Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 238000012271 agricultural production Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Tourism & Hospitality (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A water metering system and a water metering method for irrigation areas are disclosed. Firstly, acquiring water pressure values and water level values at a plurality of preset time points in a preset time period, then, carrying out data preprocessing on the water pressure values and the water level values at the preset time points to obtain a water pressure time sequence input vector and a water level time sequence input vector, then, carrying out time sequence analysis and characteristic interaction on the water pressure time sequence input vector and the water level time sequence input vector to obtain a water pressure-water level interaction fusion strengthening characteristic vector, and finally, determining a water flow value based on the water pressure-water level interaction fusion strengthening characteristic vector. Therefore, the mapping relation between the water pressure and the water flow can be automatically learned from a large amount of water pressure and water level data, so that automation and intellectualization of water metering in the irrigation area are realized.
Description
Technical Field
The application relates to the field of intelligent metering, and more particularly relates to a water metering system and a water metering method for an irrigation area.
Background
The irrigation area refers to an area irrigated by means of manual water diversion, spray irrigation, drip irrigation and the like. Irrigation areas are typically composed of sources of water, channels for water delivery, irrigation facilities, irrigation management organizations, and the like. The construction and management of the irrigation areas have important significance for improving the agricultural production efficiency, protecting water resources and realizing sustainable development.
The irrigation area water consumption metering method can effectively monitor and control the water consumption of the irrigation area, improve the utilization efficiency of water resources, save the water resources and ensure the agricultural production of the irrigation area. However, the conventional water metering method generally relies on manual observation and analysis, and has the disadvantages of low precision and the like. Thus, an optimized method of metering irrigation water is desired.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides a water metering system and a water metering method for a irrigated area, which can automatically learn the mapping relation between the water pressure and the water level data and the water flow by using a deep learning technology, thereby realizing automation and intellectualization of water metering for the irrigated area.
According to one aspect of the present application, there is provided a method of metering water for an irrigation area, comprising:
Acquiring water pressure values and water level values of a plurality of preset time points in a preset time period;
Performing data preprocessing on the water pressure values and the water level values at a plurality of preset time points to obtain a water pressure time sequence input vector and a water level time sequence input vector;
Performing time sequence analysis and characteristic interaction on the water pressure time sequence input vector and the water level time sequence input vector to obtain a water pressure-water level interaction fusion strengthening characteristic vector; and
And determining a water flow value based on the water pressure-water level interaction fusion strengthening characteristic vector.
According to another aspect of the present application, there is provided a irrigation district water metering system comprising:
the data acquisition module is used for acquiring water pressure values and water level values at a plurality of preset time points in a preset time period;
the data preprocessing module is used for preprocessing the data of the water pressure values and the water level values at a plurality of preset time points to obtain a water pressure time sequence input vector and a water level time sequence input vector;
the analysis interaction module is used for carrying out time sequence analysis and characteristic interaction on the water pressure time sequence input vector and the water level time sequence input vector so as to obtain a water pressure-water level interaction fusion strengthening characteristic vector; and
And the flow value analysis module is used for determining a water flow value based on the water pressure-water level interaction fusion strengthening characteristic vector.
Compared with the prior art, the irrigation area water metering system and the irrigation area water metering method provided by the application have the advantages that firstly, the water pressure values and the water level values of a plurality of preset time points in a preset time period are obtained, then, the water pressure values and the water level values of the preset time points are subjected to data preprocessing to obtain a water pressure time sequence input vector and a water level time sequence input vector, then, the water pressure time sequence input vector and the water level time sequence input vector are subjected to time sequence analysis and feature interaction to obtain a water pressure-water level interaction fusion strengthening feature vector, and finally, the water flow value is determined based on the water pressure-water level interaction fusion strengthening feature vector. Therefore, the mapping relation between the water pressure and the water flow can be automatically learned from a large amount of water pressure and water level data, so that automation and intellectualization of water metering in the irrigation area are realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly introduced below, the following drawings not being drawn to scale with respect to actual dimensions, emphasis instead being placed upon illustrating the gist of the present application.
Fig. 1 is a flow chart of a method of metering irrigation water according to an embodiment of the present application.
Fig. 2 is a schematic diagram of an architecture of a method for metering water in an irrigation area according to an embodiment of the application.
Fig. 3 is a flowchart of sub-step S130 of the method of metering irrigation water according to an embodiment of the present application.
Fig. 4 is a flowchart of sub-step S131 of the irrigation area water metering method according to an embodiment of the present application.
Fig. 5 is a flowchart of sub-step S132 of the irrigation area water metering method according to an embodiment of the present application.
Fig. 6 is a block diagram of a irrigation area water metering system according to an embodiment of the present application.
Fig. 7 is an application scenario diagram of the irrigation area water metering method according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are also within the scope of the application.
As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.
A flowchart is used in the present application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Aiming at the technical problems, the technical conception of the application is to automatically learn the mapping relation with the water flow from a large amount of water pressure and water level data by utilizing a deep learning technology, thereby realizing automation and intellectualization of water metering in irrigation areas.
Based on this, fig. 1 is a flowchart of a method of metering irrigation district water according to an embodiment of the present application. Fig. 2 is a schematic diagram of an architecture of a method for metering water in an irrigation area according to an embodiment of the application. As shown in fig. 1 and 2, the irrigation area water metering method according to an embodiment of the present application includes the steps of: s110, acquiring water pressure values and water level values of a plurality of preset time points in a preset time period; s120, carrying out data preprocessing on the water pressure values and the water level values at a plurality of preset time points to obtain a water pressure time sequence input vector and a water level time sequence input vector; s130, carrying out time sequence analysis and characteristic interaction on the water pressure time sequence input vector and the water level time sequence input vector to obtain a water pressure-water level interaction fusion strengthening characteristic vector; and S140, determining a water flow value based on the water pressure-water level interaction fusion strengthening characteristic vector.
It should be appreciated that in step S110, water pressure and water level data for a plurality of predetermined time points over a predetermined period of time are collected and recorded, which data will be used for subsequent processing and analysis. In step S120, the collected water pressure and water level data is preprocessed, which may include operations such as data cleansing, outlier removal, data interpolation or smoothing, etc., to obtain time-series input vectors of the water pressure and water level, which are time-series arranged data sequences for subsequent time-series analysis. In step S130, time sequence analysis and feature interaction are performed on the time sequence input vectors of the water pressure and the water level, where the time sequence analysis may include statistical analysis, frequency domain analysis, time domain analysis, etc. to obtain time related features related to the water pressure and the water level, and the feature interaction refers to combining and interacting the features of the water pressure and the water level to obtain richer information, and these analysis and interaction operations will generate a water pressure-water level interaction fusion strengthening feature vector for use in the next water flow calculation. In step S140, the flow value of the water flow is determined by building a suitable model or algorithm using the previously obtained water pressure-water level interaction fusion enhancement feature vector, which may involve estimating the water flow using techniques such as machine learning, statistical methods, or physical models. In general, these steps constitute a flow path for the irrigation area water metering method, from data collection to feature extraction and final water flow calculation, each step having its specific functions and roles to achieve efficient management and utilization of water resources.
Specifically, in the technical scheme of the application, firstly, water pressure values and water level values of a plurality of preset time points in a preset time period are obtained; and arranging the water pressure values and the water level values of the plurality of preset time points into a water pressure time sequence input vector and a water level time sequence input vector according to the time dimension respectively. In this way, the water pressure and water level values of the time-series discrete distribution are converted into a structured vector representation.
Accordingly, in step S120, the data preprocessing is performed on the water pressure values and the water level values at the plurality of predetermined time points to obtain a water pressure time sequence input vector and a water level time sequence input vector, including: and arranging the water pressure values and the water level values of the plurality of preset time points into the water pressure time sequence input vector and the water level time sequence input vector according to time dimensions respectively.
Then, respectively carrying out vector segmentation on the water pressure time sequence input vector and the water level time sequence input vector to obtain a sequence of water pressure local time sequence input vectors and a sequence of water level local time sequence input vectors; and the sequence of the water pressure local time sequence input vector and the sequence of the water level local time sequence input vector are respectively processed by a time sequence feature extractor based on a one-dimensional convolution layer to obtain the sequence of the water pressure local time sequence feature vector and the sequence of the water level local time sequence feature vector.
Here, it is considered that the water pressure and the change in water level generally have a certain time characteristic, such as instantaneous fluctuation, periodic change, etc., in the process of estimating the flow rate of the water flow in the irrigation area. By segmenting the time sequence input vector, the whole time sequence data can be decomposed into a plurality of local time sequence fragments, so that the follow-up model is guided to pay attention to local features in different time periods, and the time sequence feature extractor can better sense and analyze dynamic changes of water flow.
Further, a characteristic sequence interaction strengthening module is used for processing the sequence of the water pressure local time sequence characteristic vector and the sequence of the water level local time sequence characteristic vector to obtain a water pressure-water level interaction fusion strengthening characteristic vector. The characteristic sequence interaction strengthening module carries out interactive updating on the sequence of the water pressure local time sequence characteristic vectors and the sequence of the water level local time sequence characteristic vectors by constructing a correlation association relationship between each water pressure local time sequence characteristic vector in the sequence of the water pressure local time sequence characteristic vectors and each water level local time sequence characteristic vector in the sequence of the water level local time sequence characteristic vectors, so that internal connection between water pressure time sequence characteristic distribution and water level time sequence characteristic distribution in a local time period is highlighted, and the fused water pressure-water level interaction fusion strengthening characteristic vector can represent the mutual influence relationship between water pressure characteristics and water level characteristics.
Accordingly, in step S130, as shown in fig. 3, performing time sequence analysis and feature interaction on the water pressure time sequence input vector and the water level time sequence input vector to obtain a water pressure-water level interaction fusion strengthening feature vector, including: s131, carrying out local time sequence analysis on the water pressure time sequence input vector and the water level time sequence input vector to obtain a sequence of water pressure local time sequence characteristic vectors and a sequence of water level local time sequence characteristic vectors; and S132, processing the sequence of the water pressure local time sequence characteristic vector and the sequence of the water level local time sequence characteristic vector by using a characteristic sequence interaction strengthening module to obtain the water pressure-water level interaction fusion strengthening characteristic vector.
It should be understood that, in step S131, the local time sequence analysis refers to performing a statistical analysis, a frequency domain analysis or other analysis methods of the local area on the time sequence to extract local features, performing the local time sequence analysis on the water pressure time sequence input vector will obtain a sequence of the water pressure local time sequence feature vectors, and performing the local time sequence analysis on the water level time sequence input vector will obtain a sequence of the water level local time sequence feature vectors. In step S132, the feature sequence interaction strengthening module may use various methods, such as a neural network model, a feature fusion algorithm, etc., to interact and fuse the local time sequence features of the water pressure and the water level, so as to generate a water pressure-water level interaction fusion strengthening feature vector. In summary, S131 and S132 are steps of further processing and analyzing the time sequence input vectors of the water pressure and the water level, step S131 extracts the local time sequence feature vector sequences of the water pressure and the water level through local time sequence analysis, and step S132 processes the feature sequences by using the feature sequence interaction strengthening module to obtain the water pressure-water level interaction fusion strengthening feature vector. The purpose of these steps is to improve the accuracy and reliability of the estimation of the water flow rate by analyzing and fusing the time sequence characteristics of the water pressure and the water level.
Specifically, in step S131, as shown in fig. 4, the local time sequence analysis is performed on the water pressure time sequence input vector and the water level time sequence input vector to obtain a sequence of water pressure local time sequence feature vectors and a sequence of water level local time sequence feature vectors, including: s1311, respectively performing vector segmentation on the water pressure time sequence input vector and the water level time sequence input vector to obtain a sequence of water pressure local time sequence input vectors and a sequence of water level local time sequence input vectors; and S1312, performing feature extraction on the sequence of the water pressure local time sequence input vectors and the sequence of the water level local time sequence input vectors by using a deep learning network model to obtain the sequence of the water pressure local time sequence feature vectors and the sequence of the water level local time sequence feature vectors.
It should be understood that in step S1311, the hydraulic time series input vector and the water level time series input vector are subjected to vector slicing, where the vector slicing is to divide a long time series vector into a sequence of a plurality of shorter local time series input vectors, and the whole time series data can be decomposed into a series of local time series data by slicing, so as to better capture local characteristics and variation trends. In step S1312, the deep learning network model is used to perform feature extraction on the sequence of the water pressure local time series input vectors and the sequence of the water level local time series input vectors, and the deep learning network model can learn and extract abstract feature representations in the input vectors, and by performing feature extraction on each local time series input vector, the sequence of the water pressure local time series feature vectors and the sequence of the water level local time series feature vectors are obtained, and these feature vectors will contain richer and meaningful information for subsequent generation of water pressure-water level interaction fusion strengthening features. In general, S1311 and S1312 are steps of slicing and feature extraction of local time series data of water pressure and water level. These operations help to extract local features and accurately capture the time-series variation patterns of water pressure and water level, providing a more accurate and reliable data base for subsequent feature interactions and water flow calculations.
In one example, in step S1312, the deep learning network model is a one-dimensional convolutional layer based timing feature extractor; the time sequence feature extractor based on the one-dimensional convolution layer comprises an input layer, a one-dimensional convolution layer, an activation layer, a pooling layer and an output layer.
It should be noted that the one-dimensional convolution layer is a common neural network layer in deep learning, and is used for processing data having a time sequence structure, such as time sequence data or signal data. The one-dimensional convolution layer extracts features in the input data by applying a one-dimensional convolution operation. In a one-dimensional convolutional layer, the input data is typically a one-dimensional vector, such as a certain characteristic of time series data or a waveform of a signal. One-dimensional convolution operations scan over the input vector by sliding a small window (convolution kernel) and weight-sum the data within the window at each location. The size and shape of this window is defined by setting the size and shape of the convolution kernel. At each position, the one-dimensional convolution layer multiplies the data in the window by the convolution kernel element by element, and then adds the product results to obtain an output value. By sliding a window across the input vector, a one-dimensional convolution layer can generate a new feature vector in which each element is a local feature at a different location on the input data. One-dimensional convolution layers are typically used with other layers (e.g., activation and pooling layers) to further extract and combine features. The activation layer performs nonlinear transformation on the output of the convolution layer, and introduces nonlinear relation. The pooling layer reduces the dimension of the feature vector and retains important feature information by performing a pooling operation (e.g., maximum pooling or average pooling) on the local region of the convolutional layer output. Finally, the output layer maps the feature vectors subjected to feature extraction to a required output space.
A one-dimensional convolution layer based timing feature extractor utilizes the characteristics of the one-dimensional convolution layer to extract meaningful timing features from the input sequence of water pressure and water level local timing input vectors. Such feature extractors may automatically capture patterns and correlations in the input data by learning the weights of the convolution kernels, thereby improving the accuracy and reliability of the estimation of water flow.
Specifically, feature extraction is performed on the sequence of the water pressure local time sequence input vectors and the sequence of the water level local time sequence input vectors by using a deep learning network model to obtain the sequence of the water pressure local time sequence feature vectors and the sequence of the water level local time sequence feature vectors, and the method comprises the following steps: and respectively passing the sequence of the water pressure local time sequence input vector and the sequence of the water level local time sequence input vector through the time sequence feature extractor based on the one-dimensional convolution layer to obtain the sequence of the water pressure local time sequence feature vector and the sequence of the water level local time sequence feature vector.
Further, in step S131, as shown in fig. 5, the processing the sequence of the water pressure local time series feature vector and the sequence of the water level local time series feature vector by using a feature sequence interaction strengthening module to obtain the water pressure-water level interaction fusion strengthening feature vector includes: s1321, carrying out attention enhancement based on the correlation degree of the sequence of the water pressure local time sequence characteristic vectors and the sequence of the water level local time sequence characteristic vectors to obtain a sequence of attention-enhancing water pressure local time sequence characteristic vectors and a sequence of attention-enhancing water level local time sequence characteristic vectors; s1322, fusing the sequence of the water pressure local time sequence feature vectors and the feature vectors at corresponding positions in the sequence of the attention-enhancing water pressure local time sequence feature vectors to obtain a sequence of water pressure local fusion feature vectors, and fusing the sequence of the water level local time sequence feature vectors and the feature vectors at corresponding positions in the sequence of the attention-enhancing water level local time sequence feature vectors to obtain a sequence of water level local fusion feature vectors; s1323, carrying out maximum value pooling treatment on the sequence of the water pressure local fusion feature vectors to obtain water pressure local fusion maximum value pooling feature vectors, and carrying out maximum value pooling treatment on the sequence of the water level local fusion feature vectors to obtain water level local fusion maximum value pooling feature vectors; and S1324, fusing the water pressure local fusion maximum value pooling feature vector and the water level local fusion maximum value pooling feature vector to obtain the water pressure-water level interaction fusion strengthening feature vector.
Accordingly, in step S140, determining a water flow value based on the water pressure-water level interaction fusion enhancement feature vector includes: correcting the water pressure-water level interaction fusion strengthening characteristic vector to obtain a corrected water pressure-water level interaction fusion strengthening characteristic vector; and passing the corrected water pressure-water level interaction fusion strengthening characteristic vector through a decoder to obtain a decoding value, wherein the decoding value is used for representing a water flow value.
Here, the sequence of the water pressure local time series feature vector and the sequence of the water level local time series feature vector express time series associated features of the water pressure value and the water level value in the global time domain under the local time domain determined by vector slicing, respectively, and therefore, after the sequence of the water pressure local time series feature vector and the sequence of the water level local time series feature vector are processed by using a feature sequence interaction strengthening module, the sequence of the water pressure local time series feature vector and the sequence of the water level local time series feature vector can be fused based on feature sequence interactions between local time series feature sequence distributions in the global time domain, but in order to promote fusion effects of the water pressure-water level interaction fusion strengthening feature vector on the sequence of the water pressure local time series feature vector and the sequence of the water level local time series feature vector while considering local time series interactions in the global time domain, it is desirable to promote mapping effects of the sequence of the water pressure local time series feature vector and the sequence of the water level local time series feature vector to the feature distribution domain of the fused water pressure-water level interaction strengthening feature vector.
Therefore, the application carries out interactive fusion correction on the sequence of the water pressure local time sequence characteristic vector and the sequence of the water level local time sequence characteristic vector.
Correspondingly, correcting the water pressure-water level interaction fusion strengthening characteristic vector to obtain a corrected water pressure-water level interaction fusion strengthening characteristic vector, comprising: performing interactive fusion correction on the sequence of the water pressure local time sequence feature vector and the sequence of the water level local time sequence feature vector to obtain a correction feature vector; and carrying out point multiplication weighting on the correction characteristic vector and the water pressure-water level interaction fusion strengthening characteristic vector to obtain the correction water pressure-water level interaction fusion strengthening characteristic vector.
Specifically, performing interactive fusion correction on the sequence of the water pressure local time sequence feature vector and the sequence of the water level local time sequence feature vector to obtain a correction feature vector, including: performing interactive fusion correction on the sequence of the water pressure local time sequence feature vector and the sequence of the water level local time sequence feature vector by using the following interactive fusion correction formula to obtain the correction feature vector; wherein, the interactive fusion correction is:
wherein is a first feature vector after the sequence cascade of the water pressure local time sequence feature vectors,/> is a second feature vector after the sequence cascade of the water level local time sequence feature vectors,/> and/> are respectively the mean value and standard deviation of feature sets corresponding to the first feature vector/> ,/> and/> are respectively the mean value and standard deviation of feature sets corresponding to the second feature vector/> ,/> represents the position-wise evolution of the feature vector,/> is a logarithm based on 2,/> represents position-wise addition,/> represents position-wise multiplication, and/> represents the correction feature vector.
Here, in order to promote the mapping effect of the sequence of the water pressure local time sequence feature vector and the sequence of the water level local time sequence feature vector to the fusion feature distribution domain under the feature interaction scene, on the basis that the traditional weighted fusion mode has limitation on deducing the semantic space evolution diffusion mode based on feature superposition, the method of combining the low-order superposition fusion mode and the high-order superposition fusion mode of the space is adopted, and the evolution center and the evolution track are simulated through the statistical feature interaction relationship of the sequence of the water pressure local time sequence feature vector and the sequence of the water level local time sequence feature vector, so that the semantic space evolution diffusion under the non-synchronous evolution reconstruction fusion scene is realized under the action of different evolution diffusion speed fields, and the projection effect in the same high-dimensional feature space is effectively promoted. Therefore, the correction feature vector and the water pressure-water level interaction fusion enhancement feature vector are subjected to point multiplication weighting, so that effective feature interaction based on local time domain alignment of the sequence of the water pressure local time sequence feature vector and the sequence of the water level local time sequence feature vector is realized, the expression effect of the water pressure-water level interaction fusion enhancement feature vector is improved, and the accuracy of a decoding value obtained by the water pressure-water level interaction fusion enhancement feature vector through a decoder is improved.
It is worth mentioning that the decoder in deep learning refers to a model component that converts learned feature representations into desired outputs, which generally corresponds to the encoder, which is responsible for converting input data into potential feature representations, which the decoder converts back into the original data or generates the desired outputs. Based on the corrected water pressure-water level interaction fusion enhancement feature vectors, the decoder functions to convert these feature vectors into decoded values representing water flow values, and the decoder may be a neural network model whose structure and parameters are trained to map the feature vectors into a range of water flow values. The design of the decoder may vary depending on the specific task and data characteristics, and common decoders include fully-connected layers, deconvoluted layers, and the like. By inputting the corrected water pressure-water level interaction fusion enhancement feature vector into the decoder, the decoder will reverse-convert the feature to generate a decoded value representing the flow rate value of the water flow, which may be a specific value representing the estimated or predicted result of the water flow. The decoder is a component in the deep learning model for converting the learned feature vectors into the desired output or raw data. Specifically, in step S140, the decoder decodes the corrected water pressure-water level interaction fusion enhancement feature vector into a representation of the water flow value.
Further, in the technical scheme of the application, the irrigation area water metering method further comprises the training steps of: and training the time sequence feature extractor based on the one-dimensional convolution layer, the feature sequence interaction strengthening module and the decoder. It will be appreciated that the training step plays a key role in the method of metering water to the irrigation area. By training the one-dimensional convolution layer based time sequence feature extractor, the feature sequence interaction strengthening module and the decoder, the following objects can be achieved: 1. learning feature representation: through training, the model can learn the characteristic representation of effectively encoding the input data such as water pressure, water level and the like. The training of the one-dimensional convolution layer can capture time sequence modes and correlations in input data, the training of the characteristic sequence interaction strengthening module can improve interaction and expression capacity among characteristics, and the training of the decoder can convert the learned characteristics into decoding results of water flow values. 2. The prediction accuracy is improved: by training, the model can learn the complex relationship between the input features and the water flow. During training, the model adjusts the parameters to minimize the gap between the predicted and actual values by comparison with known water flow values. In this way, the trained model can more accurately predict corresponding water flow values given water pressure and water level. 3. Generalization ability: the training step may increase the generalization ability of the model to enable it to process new, unseen data. By training on a large number of training samples, the model can learn the statistical rules and patterns of the input features, so that accurate predictions can be made when similar inputs are encountered in the future. In summary, the training step is crucial to the implementation of the irrigation area water metering method, and the model can effectively estimate and predict water flow by learning feature representation, improving prediction accuracy and enhancing generalization capability of the model.
In summary, the method for metering water for irrigation areas according to the embodiment of the application is explained, which can automatically learn the mapping relation between the water pressure and the water flow from a large amount of water pressure and water level data, thereby realizing automation and intellectualization of water metering for irrigation areas.
Fig. 6 is a block diagram of a irrigation area water metering system 100 according to an embodiment of the present application. As shown in fig. 6, the irrigation area water metering system 100 according to the embodiment of the present application includes: a data acquisition module 110, configured to acquire water pressure values and water level values at a plurality of predetermined time points within a predetermined time period; the data preprocessing module 120 is configured to perform data preprocessing on the water pressure values and the water level values at the plurality of predetermined time points to obtain a water pressure time sequence input vector and a water level time sequence input vector; the analysis interaction module 130 is configured to perform time sequence analysis and feature interaction on the water pressure time sequence input vector and the water level time sequence input vector to obtain a water pressure-water level interaction fusion strengthening feature vector; and a flow value analysis module 140, configured to determine a flow value based on the water pressure-water level interaction fusion enhancement feature vector.
In one example, in the above-described irrigation district water metering system 100, the data preprocessing module 120 is configured to: and arranging the water pressure values and the water level values of the plurality of preset time points into the water pressure time sequence input vector and the water level time sequence input vector according to time dimensions respectively.
Here, it will be understood by those skilled in the art that the specific functions and operations of the respective modules in the above-described irrigation area water metering system 100 have been described in detail in the above description of the irrigation area water metering method with reference to fig. 1 to 5, and thus, repetitive descriptions thereof will be omitted.
As described above, the irrigation district water metering system 100 according to the embodiment of the present application may be implemented in various wireless terminals, such as a server having an irrigation district water metering algorithm, or the like. In one example, the irrigation district water metering system 100 according to an embodiment of the present application may be integrated into a wireless terminal as a software module and/or hardware module. For example, the irrigation district water metering system 100 may be a software module in the operating system of the wireless terminal, or may be an application developed for the wireless terminal; of course, the irrigation district water metering system 100 may equally be one of a number of hardware modules of the wireless terminal.
Alternatively, in another example, the irrigation district water metering system 100 and the wireless terminal may be separate devices, and the irrigation district water metering system 100 may be connected to the wireless terminal through a wired and/or wireless network and transmit interactive information in a agreed data format.
Fig. 7 is an application scenario diagram of the irrigation area water metering method according to an embodiment of the present application. As shown in fig. 7, in this application scenario, first, water pressure values (e.g., D1 illustrated in fig. 7) and water level values (e.g., D2 illustrated in fig. 7) at a plurality of predetermined time points within a predetermined period of time are acquired, and then, the water pressure values and water level values at the plurality of predetermined time points are input to a server (e.g., S illustrated in fig. 7) where a irrigation area water metering algorithm is deployed, wherein the server is capable of processing the water pressure values and water level values at the plurality of predetermined time points using the irrigation area water metering algorithm to obtain a decoded value representing a water flow rate value.
It should be understood that the irrigation area water metering system is a system for monitoring, controlling the irrigation area water resources. The irrigation area water metering system realizes the functions of automatic collection of irrigation area water metering, real-time image monitoring, remote control of water supply and the like, and achieves the purposes of saving irrigation water and scientifically and efficiently managing the irrigation area. The system plays an important role in ensuring the safe operation of the irrigation area engineering, realizing the optimal allocation of water resources, improving the water use efficiency and ensuring the sustainable development of the irrigation area. In one example, the irrigated area water metering system apparatus includes an IC card motor-pumped well control box, a water level sensor, a flow meter, and the like.
Furthermore, those skilled in the art will appreciate that the various aspects of the application are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The foregoing is illustrative of the present application and is not to be construed as limiting thereof. Although a few exemplary embodiments of this application have been described, those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this application. Accordingly, all such modifications are intended to be included within the scope of this application as defined in the following claims. It is to be understood that the foregoing is illustrative of the present application and is not to be construed as limited to the specific embodiments disclosed, and that modifications to the disclosed embodiments, as well as other embodiments, are intended to be included within the scope of the appended claims. The application is defined by the claims and their equivalents.
Claims (10)
1. A method of metering water for a irrigated area, comprising:
Acquiring water pressure values and water level values of a plurality of preset time points in a preset time period;
Performing data preprocessing on the water pressure values and the water level values at a plurality of preset time points to obtain a water pressure time sequence input vector and a water level time sequence input vector;
Performing time sequence analysis and characteristic interaction on the water pressure time sequence input vector and the water level time sequence input vector to obtain a water pressure-water level interaction fusion strengthening characteristic vector; and
And determining a water flow value based on the water pressure-water level interaction fusion strengthening characteristic vector.
2. A method of metering water for a irrigated area according to claim 1, wherein the data preprocessing of the water pressure values and water level values at the plurality of predetermined time points to obtain a water pressure time series input vector and a water level time series input vector comprises:
And arranging the water pressure values and the water level values of the plurality of preset time points into the water pressure time sequence input vector and the water level time sequence input vector according to time dimensions respectively.
3. The method of claim 2, wherein performing a time series analysis and feature interaction on the water pressure time series input vector and the water level time series input vector to obtain a water pressure-water level interaction fusion enhanced feature vector, comprises:
Carrying out local time sequence analysis on the water pressure time sequence input vector and the water level time sequence input vector to obtain a sequence of water pressure local time sequence characteristic vectors and a sequence of water level local time sequence characteristic vectors; and
And processing the sequence of the water pressure local time sequence feature vectors and the sequence of the water level local time sequence feature vectors by using a feature sequence interaction strengthening module to obtain the water pressure-water level interaction fusion strengthening feature vector.
4. A method of metering water for a irrigated area according to claim 3, wherein performing a local time series analysis on the water pressure time series input vector and the water level time series input vector to obtain a sequence of water pressure local time series feature vectors and a sequence of water level local time series feature vectors comprises:
Vector segmentation is carried out on the water pressure time sequence input vector and the water level time sequence input vector respectively to obtain a sequence of water pressure local time sequence input vectors and a sequence of water level local time sequence input vectors; and
And performing feature extraction on the sequence of the water pressure local time sequence input vectors and the sequence of the water level local time sequence input vectors by using a deep learning network model to obtain the sequence of the water pressure local time sequence feature vectors and the sequence of the water level local time sequence feature vectors.
5. The irrigation district water metering method according to claim 4, wherein the deep learning network model is a time sequence feature extractor based on a one-dimensional convolution layer;
The time sequence feature extractor based on the one-dimensional convolution layer comprises an input layer, a one-dimensional convolution layer, an activation layer, a pooling layer and an output layer.
6. The method according to claim 5, wherein the feature extraction of the sequence of the water pressure local time series input vectors and the sequence of the water level local time series input vectors to obtain the sequence of the water pressure local time series feature vectors and the sequence of the water level local time series feature vectors using a deep learning network model comprises:
And respectively passing the sequence of the water pressure local time sequence input vector and the sequence of the water level local time sequence input vector through the time sequence feature extractor based on the one-dimensional convolution layer to obtain the sequence of the water pressure local time sequence feature vector and the sequence of the water level local time sequence feature vector.
7. The method of claim 6, wherein processing the sequence of water pressure local time series feature vectors and the sequence of water level local time series feature vectors using a feature sequence interaction strengthening module to obtain the water pressure-water level interaction fusion strengthening feature vector comprises:
Performing attention enhancement based on the correlation of the sequence of water pressure local time sequence feature vectors and the sequence of water level local time sequence feature vectors to obtain a sequence of attention enhanced water pressure local time sequence feature vectors and a sequence of attention enhanced water level local time sequence feature vectors;
fusing the sequence of the water pressure local time sequence feature vectors and the feature vectors at corresponding positions in the sequence of the attention-enhancing water pressure local time sequence feature vectors to obtain a sequence of water pressure local fusion feature vectors, and fusing the sequence of the water level local time sequence feature vectors and the feature vectors at corresponding positions in the sequence of the attention-enhancing water level local time sequence feature vectors to obtain a sequence of water level local fusion feature vectors;
performing maximum value pooling treatment on the sequence of the water pressure local fusion feature vectors to obtain water pressure local fusion maximum value pooling feature vectors, and performing maximum value pooling treatment on the sequence of the water level local fusion feature vectors to obtain water level local fusion maximum value pooling feature vectors; and
And fusing the water pressure local fusion maximum value pooling feature vector and the water level local fusion maximum value pooling feature vector to obtain the water pressure-water level interaction fusion strengthening feature vector.
8. The method of claim 7, wherein determining a water flow value based on the water pressure-water level interaction fusion enhancement feature vector comprises:
Correcting the water pressure-water level interaction fusion strengthening characteristic vector to obtain a corrected water pressure-water level interaction fusion strengthening characteristic vector;
And passing the corrected water pressure-water level interaction fusion strengthening characteristic vector through a decoder to obtain a decoding value, wherein the decoding value is used for representing a water flow value.
9. The method of claim 8, wherein correcting the water pressure-water level interaction fusion enhancement feature vector to obtain a corrected water pressure-water level interaction fusion enhancement feature vector comprises:
performing interactive fusion correction on the sequence of the water pressure local time sequence feature vector and the sequence of the water level local time sequence feature vector to obtain a correction feature vector;
and carrying out point multiplication weighting on the correction characteristic vector and the water pressure-water level interaction fusion strengthening characteristic vector to obtain the correction water pressure-water level interaction fusion strengthening characteristic vector.
10. A irrigation district water metering system, comprising:
the data acquisition module is used for acquiring water pressure values and water level values at a plurality of preset time points in a preset time period;
the data preprocessing module is used for preprocessing the data of the water pressure values and the water level values at a plurality of preset time points to obtain a water pressure time sequence input vector and a water level time sequence input vector;
the analysis interaction module is used for carrying out time sequence analysis and characteristic interaction on the water pressure time sequence input vector and the water level time sequence input vector so as to obtain a water pressure-water level interaction fusion strengthening characteristic vector; and
And the flow value analysis module is used for determining a water flow value based on the water pressure-water level interaction fusion strengthening characteristic vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410291082.3A CN117892073B (en) | 2024-03-14 | 2024-03-14 | Irrigation area water metering system and water metering method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410291082.3A CN117892073B (en) | 2024-03-14 | 2024-03-14 | Irrigation area water metering system and water metering method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117892073A true CN117892073A (en) | 2024-04-16 |
| CN117892073B CN117892073B (en) | 2024-05-24 |
Family
ID=90645932
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410291082.3A Active CN117892073B (en) | 2024-03-14 | 2024-03-14 | Irrigation area water metering system and water metering method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117892073B (en) |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110263972A (en) * | 2019-05-15 | 2019-09-20 | 北京航空航天大学 | Product quality prediction technique and device |
| CN110874662A (en) * | 2018-08-29 | 2020-03-10 | 清华大学 | Real-time verification method and system for water consumption in water supply pipe network model |
| US20200098284A1 (en) * | 2018-07-13 | 2020-03-26 | Central China Normal University | Classroom teaching cognitive load measurement system |
| CN211085390U (en) * | 2019-12-25 | 2020-07-24 | 常州农水云服信息科技有限公司 | Water quantity collecting equipment |
| CN115456113A (en) * | 2022-10-25 | 2022-12-09 | 北京邮电大学 | Modulation format identification method based on constellation diagram multi-feature extraction algorithm |
| US20230199005A1 (en) * | 2021-12-17 | 2023-06-22 | Electronics And Telecommunications Research Institute | Method and apparatus for detecting network attack based on fusion feature vector |
| CN116299051A (en) * | 2023-05-19 | 2023-06-23 | 深圳市安科讯电子制造有限公司 | Overcurrent short circuit detection circuit and detection protection system |
| CN116702090A (en) * | 2023-06-19 | 2023-09-05 | 浙江大学 | Multi-mode data fusion and uncertain estimation water level prediction method and system |
| CN116760772A (en) * | 2023-08-21 | 2023-09-15 | 北京中科网芯科技有限公司 | Control system and method for converging flow divider |
| CN117063820A (en) * | 2023-10-16 | 2023-11-17 | 武安市园林绿化管理局 | Intelligent garden monitoring platform based on big data and method thereof |
| CN117222069A (en) * | 2023-10-12 | 2023-12-12 | 深圳市诺文博科技有限公司 | Intelligent control method of illumination driving power supply |
| CN117244678A (en) * | 2023-10-11 | 2023-12-19 | 浙江艾领创矿业科技有限公司 | Intelligent monitoring control system and method for sand mill |
| CN117270082A (en) * | 2023-09-28 | 2023-12-22 | 浙江非线数联科技股份有限公司 | Precipitation prediction system and method based on multi-sensor data fusion |
| CN117308077A (en) * | 2023-10-17 | 2023-12-29 | 浙江嘉诚动能科技股份有限公司 | Water supply control system for evaporator of nuclear power unit of reactor |
| CN117424513A (en) * | 2023-10-26 | 2024-01-19 | 北京华能新锐控制技术有限公司 | Control method and system for realizing constant current control based on belt flow and wheel bucket current |
| CN117485842A (en) * | 2023-11-03 | 2024-02-02 | 北京华能新锐控制技术有限公司 | Method and system for monitoring attitude of wheel bucket cross beam of gate type bucket wheel machine in real time |
| CN117523869A (en) * | 2023-12-22 | 2024-02-06 | 河北思禾电子商务有限公司 | Traffic signal lamp intelligent control system and method based on traffic flow |
| CN117540908A (en) * | 2023-11-07 | 2024-02-09 | 北京佳格天地科技有限公司 | Agricultural resource integration method and system based on big data |
-
2024
- 2024-03-14 CN CN202410291082.3A patent/CN117892073B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200098284A1 (en) * | 2018-07-13 | 2020-03-26 | Central China Normal University | Classroom teaching cognitive load measurement system |
| CN110874662A (en) * | 2018-08-29 | 2020-03-10 | 清华大学 | Real-time verification method and system for water consumption in water supply pipe network model |
| CN110263972A (en) * | 2019-05-15 | 2019-09-20 | 北京航空航天大学 | Product quality prediction technique and device |
| CN211085390U (en) * | 2019-12-25 | 2020-07-24 | 常州农水云服信息科技有限公司 | Water quantity collecting equipment |
| US20230199005A1 (en) * | 2021-12-17 | 2023-06-22 | Electronics And Telecommunications Research Institute | Method and apparatus for detecting network attack based on fusion feature vector |
| CN115456113A (en) * | 2022-10-25 | 2022-12-09 | 北京邮电大学 | Modulation format identification method based on constellation diagram multi-feature extraction algorithm |
| CN116299051A (en) * | 2023-05-19 | 2023-06-23 | 深圳市安科讯电子制造有限公司 | Overcurrent short circuit detection circuit and detection protection system |
| CN116702090A (en) * | 2023-06-19 | 2023-09-05 | 浙江大学 | Multi-mode data fusion and uncertain estimation water level prediction method and system |
| CN116760772A (en) * | 2023-08-21 | 2023-09-15 | 北京中科网芯科技有限公司 | Control system and method for converging flow divider |
| CN117270082A (en) * | 2023-09-28 | 2023-12-22 | 浙江非线数联科技股份有限公司 | Precipitation prediction system and method based on multi-sensor data fusion |
| CN117244678A (en) * | 2023-10-11 | 2023-12-19 | 浙江艾领创矿业科技有限公司 | Intelligent monitoring control system and method for sand mill |
| CN117222069A (en) * | 2023-10-12 | 2023-12-12 | 深圳市诺文博科技有限公司 | Intelligent control method of illumination driving power supply |
| CN117063820A (en) * | 2023-10-16 | 2023-11-17 | 武安市园林绿化管理局 | Intelligent garden monitoring platform based on big data and method thereof |
| CN117308077A (en) * | 2023-10-17 | 2023-12-29 | 浙江嘉诚动能科技股份有限公司 | Water supply control system for evaporator of nuclear power unit of reactor |
| CN117424513A (en) * | 2023-10-26 | 2024-01-19 | 北京华能新锐控制技术有限公司 | Control method and system for realizing constant current control based on belt flow and wheel bucket current |
| CN117485842A (en) * | 2023-11-03 | 2024-02-02 | 北京华能新锐控制技术有限公司 | Method and system for monitoring attitude of wheel bucket cross beam of gate type bucket wheel machine in real time |
| CN117540908A (en) * | 2023-11-07 | 2024-02-09 | 北京佳格天地科技有限公司 | Agricultural resource integration method and system based on big data |
| CN117523869A (en) * | 2023-12-22 | 2024-02-06 | 河北思禾电子商务有限公司 | Traffic signal lamp intelligent control system and method based on traffic flow |
Non-Patent Citations (1)
| Title |
|---|
| 金丰;邵清;: "信号分解与融合神经网络的金融数据预测研究", 小型微型计算机***, no. 06, 29 May 2020 (2020-05-29) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117892073B (en) | 2024-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Grönquist et al. | Deep learning for post-processing ensemble weather forecasts | |
| Fan et al. | Deep learning-based feature engineering methods for improved building energy prediction | |
| Hu et al. | Short-term wind speed prediction using empirical wavelet transform and Gaussian process regression | |
| Hu et al. | A hybrid approach based on the Gaussian process with t-observation model for short-term wind speed forecasts | |
| Chen et al. | Forecasting tourism demand based on empirical mode decomposition and neural network | |
| Fan et al. | A novel deep generative modeling-based data augmentation strategy for improving short-term building energy predictions | |
| CN110210513B (en) | Data classification method and device and terminal equipment | |
| CN112101480A (en) | Multivariate clustering and fused time sequence combined prediction method | |
| Li et al. | Deep spatio-temporal wind power forecasting | |
| CN117041017B (en) | Intelligent operation and maintenance management method and system for data center | |
| CN117270082A (en) | Precipitation prediction system and method based on multi-sensor data fusion | |
| CN116451594B (en) | Training method and device of icing prediction model, prediction method and device and electronic equipment | |
| CN116736703A (en) | Intelligent monitoring system and method for sewage treatment | |
| CN117094451B (en) | Power consumption prediction method, device and terminal | |
| CN117892073B (en) | Irrigation area water metering system and water metering method | |
| CN117875638A (en) | Big data-based power supply demand distribution method and system | |
| CN116737521A (en) | HPC operation power consumption prediction method and system based on self-supervision comparison learning | |
| CN117154680A (en) | Wind power prediction method based on non-stationary transducer model | |
| CN116307206A (en) | Natural gas flow prediction method based on segmented graph convolution and time attention mechanism | |
| CN116341720A (en) | Multi-fan wind speed and direction prediction method based on dynamic graph convolution and transformation | |
| CN115936196A (en) | Monthly rainfall model prediction method based on time sequence convolution network | |
| Widiputra et al. | Dynamic interaction networks versus local trend models for multiple time-series prediction | |
| Darvishi Salookolaei et al. | Application of grey system theory in rainfall estimation | |
| Heghedus et al. | Neural network architectures for electricity consumption forecasting | |
| CN111368408A (en) | Seq2 seq-based data center energy efficiency optimization continuous decision method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |