CN117073055A - Hydraulic balance control system and method thereof - Google Patents

Hydraulic balance control system and method thereof Download PDF

Info

Publication number
CN117073055A
CN117073055A CN202310837294.2A CN202310837294A CN117073055A CN 117073055 A CN117073055 A CN 117073055A CN 202310837294 A CN202310837294 A CN 202310837294A CN 117073055 A CN117073055 A CN 117073055A
Authority
CN
China
Prior art keywords
vector
pressure
feature
temperature
input
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
Application number
CN202310837294.2A
Other languages
Chinese (zh)
Inventor
华少雷
杨圣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui Huayuan Hvac Energy Saving Technology Co ltd
Original Assignee
Anhui Huayuan Hvac Energy Saving Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Anhui Huayuan Hvac Energy Saving Technology Co ltd filed Critical Anhui Huayuan Hvac Energy Saving Technology Co ltd
Priority to CN202310837294.2A priority Critical patent/CN117073055A/en
Publication of CN117073055A publication Critical patent/CN117073055A/en
Pending legal-status Critical Current

Links

Classifications

    • 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
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24D—DOMESTIC- OR SPACE-HEATING SYSTEMS, e.g. CENTRAL HEATING SYSTEMS; DOMESTIC HOT-WATER SUPPLY SYSTEMS; ELEMENTS OR COMPONENTS THEREFOR
    • F24D19/00—Details
    • F24D19/10—Arrangement or mounting of control or safety devices
    • F24D19/1006—Arrangement or mounting of control or safety devices for water heating systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • 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
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24D—DOMESTIC- OR SPACE-HEATING SYSTEMS, e.g. CENTRAL HEATING SYSTEMS; DOMESTIC HOT-WATER SUPPLY SYSTEMS; ELEMENTS OR COMPONENTS THEREFOR
    • F24D2220/00—Components of central heating installations excluding heat sources
    • F24D2220/04—Sensors
    • F24D2220/042—Temperature sensors
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24D—DOMESTIC- OR SPACE-HEATING SYSTEMS, e.g. CENTRAL HEATING SYSTEMS; DOMESTIC HOT-WATER SUPPLY SYSTEMS; ELEMENTS OR COMPONENTS THEREFOR
    • F24D2220/00—Components of central heating installations excluding heat sources
    • F24D2220/04—Sensors
    • F24D2220/044—Flow sensors
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24D—DOMESTIC- OR SPACE-HEATING SYSTEMS, e.g. CENTRAL HEATING SYSTEMS; DOMESTIC HOT-WATER SUPPLY SYSTEMS; ELEMENTS OR COMPONENTS THEREFOR
    • F24D2220/00—Components of central heating installations excluding heat sources
    • F24D2220/04—Sensors
    • F24D2220/046—Pressure sensors

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Software Systems (AREA)
  • Thermal Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • Feedback Control In General (AREA)

Abstract

The application relates to the technical field of intelligent control, and particularly discloses a hydraulic balance control system and a hydraulic balance control method.

Description

Hydraulic balance control system and method thereof
Technical Field
The application relates to the technical field of intelligent control, in particular to a hydraulic balance control system and a hydraulic balance control method.
Background
The hydraulic balance refers to the process of achieving an equilibrium state between the flow and the pressure of an inlet and an outlet of a hydraulic system and the flow and the pressure of each point in the system. The current hydraulic balance technology mainly relates to the aspects of flow calculation, head loss calculation, pump station scheduling control and the like.
However, due to the limitation of the self-equipment, the pressure of the water supply is often insufficient, or the circulating water exceeds the value set by the original system, so that the pressure of the water pump is insufficient, or the pressure in the water pump is reduced, and the phenomenon of hydraulic imbalance in the heating system is generated.
Thus, an optimized hydraulic balance control scheme 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 hydraulic balance control system and a hydraulic balance control method, wherein the system comprises the steps of firstly collecting temperature values, water flow values and pressure values at a plurality of preset time points, then using a deep neural network model based on deep learning as a feature extractor, and carrying out feature extraction through a multi-scale domain feature extraction module and a convolution neural network model to balance the pressure of a water supply system so as to achieve hydraulic balance, thereby effectively improving the stability and reliability of the water supply system.
According to one aspect of the present application, there is provided a hydraulic balance control system including:
the data acquisition module is used for acquiring temperature values, water flow values and pressure values at a plurality of preset time points in a preset time period;
the data association module is used for respectively arranging the temperature values and the water flow values of the plurality of preset time points into a temperature input vector and a water flow input vector according to the time dimension and then calculating a temperature flow association input matrix between the temperature input vector and the water flow input vector;
The pressure characteristic vector extraction module is used for respectively arranging the pressure values of the plurality of preset time points into the pressure input vector according to the time dimension, and obtaining a pressure characteristic vector through the multi-scale neighborhood characteristic extraction module;
the correlation characteristic coding module is used for enabling the temperature flow correlation input matrix to pass through a convolutional neural network model serving as a filter to obtain a temperature flow correlation characteristic vector;
the fusion feature module is used for fusing the temperature flow associated feature vector and the pressure feature vector to obtain a fusion feature vector; and
and the result generation module is used for passing the fusion feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating that the pressure value of the water conservancy system should be increased or decreased.
In the hydraulic balance control system, the data association module is configured to: and calculating the product between the transpose vector of the temperature input vector and the water flow input vector to obtain the temperature flow correlation input matrix.
In the hydraulic balance control system, the pressure feature vector extraction module includes: a first scale feature extraction unit, configured to input the pressure input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first scale pressure feature vector, where the first convolution layer has a first one-dimensional convolution kernel with a first length; a second scale feature extraction unit configured to input the pressure input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale pressure feature vector, where the second convolution layer has a second one-dimensional convolution kernel of a second length, and the first length is different from the second length; and the fusion unit is used for cascading the first scale pressure characteristic vector and the second scale pressure characteristic vector by using a cascading layer of the multi-scale neighborhood characteristic extraction module so as to obtain the pressure characteristic vector.
In the hydraulic balance control system, the first scale feature extraction unit is configured to: performing one-dimensional convolution encoding on the pressure input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module according to the following first convolution formula to obtain a first-scale pressure feature vector; wherein the first convolution formula is:
wherein a is the width of the first one-dimensional convolution kernel in the X direction, F (a) is a parameter vector of the first one-dimensional convolution kernel, G (X-a) is a local vector matrix operated with the first convolution kernel function, w is the size of the first one-dimensional convolution kernel, X represents the pressure input vector, and Cov (X) is one-dimensional convolution encoding of the pressure input vector.
In the hydraulic balance control system, the second scale feature extraction unit is configured to: performing one-dimensional convolution encoding on the pressure input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module according to the following second convolution formula to obtain a second-scale pressure feature vector; wherein the second convolution formula is:
wherein b is the width of the second one-dimensional convolution kernel in the X direction, F (b) is a parameter vector of the second one-dimensional convolution kernel, G (X-b) is a local vector matrix calculated by a second convolution kernel function, m is the size of the second one-dimensional convolution kernel, X represents the pressure input vector, and Cov (X) is one-dimensional convolution encoding of the pressure input vector.
In the hydraulic balance control system, the associated feature encoding module is configured to: each layer using the convolutional neural network model is performed in forward transfer of the layer: carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling each feature matrix along the channel dimension of the convolution feature map to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the convolutional neural network model is the temperature flow correlation characteristic vector, and the input of the first layer of the convolutional neural network model is the temperature flow correlation input matrix.
In the hydraulic balance control system, the fusion feature module includes: the sparse coding unit is used for performing sparse coding on the temperature flow associated feature vector and the pressure feature vector to obtain a first sparse feature vector and a second sparse feature vector; a first divergence calculating unit, configured to calculate a first JS divergence of the first sparse feature vector relative to the second sparse feature vector; a second divergence calculating unit, configured to calculate a second JS divergence of the second sparse feature vector relative to the first sparse feature vector; the normalization unit is used for performing normalization processing on the first JS dispersion and the second JS dispersion to obtain normalized first JS dispersion and normalized second JS dispersion; and a weight applying unit, configured to fuse the first sparse feature vector and the second sparse feature vector with the normalized first JS divergence and the normalized second JS divergence as weights, to obtain a fused feature vector.
According to another aspect of the present application, there is provided a hydraulic balance control method including:
acquiring temperature values, water flow values and pressure values at a plurality of preset time points in a preset time period;
after arranging the temperature values and the water flow values of the plurality of preset time points into a temperature input vector and a water flow input vector according to a time dimension respectively, calculating a temperature flow correlation input matrix between the temperature input vector and the water flow input vector;
the pressure values of the plurality of preset time points are respectively arranged into the pressure input vector according to the time dimension, and then the pressure characteristic vector is obtained through a multi-scale neighborhood characteristic extraction module;
the temperature flow correlation input matrix is passed through a convolutional neural network model serving as a filter to obtain a temperature flow correlation characteristic vector;
fusing the temperature flow associated feature vector and the pressure feature vector to obtain a fused feature vector; and
and the fusion characteristic vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the pressure value of the water conservancy system should be increased or decreased.
In the hydraulic balance control method, after arranging the temperature values and the water flow values at the plurality of predetermined time points into a temperature input vector and a water flow input vector according to a time dimension, calculating a temperature flow correlation input matrix between the temperature input vector and the water flow input vector, including: and calculating the product between the transpose vector of the temperature input vector and the water flow input vector to obtain the temperature flow correlation input matrix.
In the hydraulic balance control method, after arranging the pressure values of the plurality of predetermined time points into the pressure input vector according to a time dimension, obtaining a pressure feature vector through a multi-scale neighborhood feature extraction module, including: inputting the pressure input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first-scale pressure feature vector, wherein the first convolution layer has a first one-dimensional convolution kernel with a first length; inputting the pressure input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale pressure feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel of a second length, and the first length is different from the second length; and cascading the first scale pressure feature vector and the second scale pressure feature vector by using a cascading layer of the multi-scale neighborhood feature extraction module to obtain the pressure feature vector.
In the hydraulic balance control method, the pressure input vector is input into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first scale pressure feature vector, wherein the first convolution layer has a first one-dimensional convolution kernel with a first length and is used for: performing one-dimensional convolution encoding on the pressure input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module according to the following first convolution formula to obtain a first-scale pressure feature vector; wherein the first convolution formula is:
Wherein a is the width of the first one-dimensional convolution kernel in the X direction, F (a) is a parameter vector of the first one-dimensional convolution kernel, G (X-a) is a local vector matrix operated with the first convolution kernel function, w is the size of the first one-dimensional convolution kernel, X represents the pressure input vector, and Cov (X) is one-dimensional convolution encoding of the pressure input vector.
In the hydraulic balance control method, the pressure input vector is input into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale pressure feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length and is used for: performing one-dimensional convolution encoding on the pressure input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module according to the following second convolution formula to obtain a second-scale pressure feature vector; wherein the second convolution formula is:
wherein b is the width of the second one-dimensional convolution kernel in the X direction, F (b) is a parameter vector of the second one-dimensional convolution kernel, G (X-b) is a local vector matrix calculated by a second convolution kernel function, m is the size of the second one-dimensional convolution kernel, X represents the pressure input vector, and Cov (X) is one-dimensional convolution encoding of the pressure input vector.
In the hydraulic balance control method, the step of obtaining the temperature flow correlation eigenvector by passing the temperature flow correlation input matrix through a convolutional neural network model serving as a filter includes: each layer using the first convolutional neural network model is performed in forward transfer of the layer; carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling each feature matrix along the channel dimension of the convolution feature map to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the first convolutional neural network model is the temperature flow correlation feature vector, and the input of the first layer of the first convolutional neural network model is the temperature flow correlation input matrix.
In the hydraulic balance control method, fusing the temperature flow related feature vector and the pressure feature vector to obtain a fused feature vector includes: the sparse coding unit is used for performing sparse coding on the temperature flow associated feature vector and the pressure feature vector to obtain a first sparse feature vector and a second sparse feature vector; a first divergence calculating unit, configured to calculate a first JS divergence of the first sparse feature vector relative to the second sparse feature vector; a second divergence calculating unit, configured to calculate a second JS divergence of the second sparse feature vector relative to the first sparse feature vector; the normalization unit is used for performing normalization processing on the first JS dispersion and the second JS dispersion to obtain normalized first JS dispersion and normalized second JS dispersion; and a weight applying unit, configured to fuse the first sparse feature vector and the second sparse feature vector with the normalized first JS divergence and the normalized second JS divergence as weights, to obtain a fused feature vector.
Compared with the prior art, the hydraulic balance control system and the hydraulic balance control method provided by the application have the advantages that the temperature value, the water flow value and the pressure value at a plurality of preset time points are firstly collected, then the deep neural network model based on deep learning is used as the feature extractor, and the multi-scale domain feature extraction module and the convolutional neural network model are used for carrying out feature extraction, so that the pressure of the water supply system is balanced, the hydraulic balance is achieved, and the stability and the reliability of the water supply system are effectively improved.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
FIG. 1 is a block diagram schematic of a hydraulic balance control system according to an embodiment of the present application.
Fig. 2 is a block diagram of a hydraulic balance control system and a method thereof according to an embodiment of the present application.
Fig. 3 is a flow chart of a hydraulic balance control method according to an embodiment of the present application.
Fig. 4 is a schematic diagram of a hydraulic balance control method architecture according to an embodiment of the present application.
Fig. 5 is a block diagram of an electronic device according to an embodiment of the application.
Detailed Description
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.
Scene overview
As described above, the hydraulic balance in the water conservancy system is a precondition of normal water supply, but the hydraulic imbalance is caused due to the unbalanced water supply pressure caused by the temperature and water flow change in the water conservancy system, so that the water supply system cannot work normally, and the water supply of equipment is affected. It is therefore desirable to have an optimized hydraulic balance control scheme that balances the pressure of the water supply system by a combination of temperature, water flow and pressure.
Specifically, in the application scene of the application, considering that parameters such as temperature, water flow and pressure in the water supply system have influence on the water supply system, the states of the water supply system at different time points can have larger difference, such as different time periods of morning, noon, evening and the like, and are influenced by external factors such as seasons, weather and the like, the precision and stability of data acquisition can be improved by acquiring data at a plurality of preset time points, the influence of abnormal and error data is reduced, the water supply system can be comprehensively monitored and analyzed, and a corresponding model is established to realize automatic adjustment. Therefore, in the technical scheme of the application, the pressure of the water supply system is balanced through the combined action of temperature, water flow and pressure, so that the hydraulic balance is achieved.
In recent years, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. In addition, deep learning and neural networks have also shown levels approaching and even exceeding humans in the fields of image classification, object detection, semantic segmentation, text translation, and the like.
Specifically, in the technical scheme of the present application, first, temperature values, water flow rate values, and pressure values at a plurality of predetermined time points in a time period are acquired. And then, arranging the temperature values and the water flow values at the plurality of preset time points into a temperature input vector and a water flow input vector according to a time dimension, and calculating a temperature flow correlation input matrix between the temperature input vector and the water flow input vector. Considering that the temperature and the water flow are very important parameters in the water supply system, the change trend and the interaction relationship between the temperature and the water flow can reflect the real-time state of the water supply system, and certain correlation exists between the temperature and the water flow, for example, the water flow is changed due to the temperature rise. Temperature and water flow are one of the main factors affecting the water supply pressure, and the correlation characteristics between them can be used to predict future pressure changes. Therefore, by calculating the temperature flow rate association input matrix, the association between the temperature and the water flow rate can be established, and the change trend and the interaction relationship between the temperature and the water flow rate at different time points can be reflected, so that the state and the characteristic of the water supply system can be more comprehensively and accurately captured.
Then, it is considered that the pressure value in the water supply system changes with the lapse of time. The pressure trend may be different at different time scales, such as sudden changes in a short period and slow trends in a long period. Furthermore, the method based on multi-scale neighborhood feature extraction can abstract pressure data with different granularities, in this way, the original pressure data can be converted into higher-level features, so that the model can learn the general rule in the data more easily, and the generalization capability of the model is improved. In practice, pressure data in the water supply may be subject to various disturbances and noise, such as sensor errors, equipment malfunctions, etc. Through multi-scale extraction, the interference and noise can be offset to a certain extent, and the robustness of the model is improved. Therefore, after the pressure values of the plurality of preset time points are respectively arranged into the pressure input vector according to the time dimension, the pressure feature vector is obtained through the multi-scale neighborhood feature extraction module, so as to capture the pressure change trend under different time scales and improve the feature expression capability.
Next, considering that the temperature and flow associated input matrix tends to have larger dimensions and scales, using a traditional fully connected neural network tends to create problems of parameter explosion and computational resource waste. And when the convolutional neural network processes large-scale data, the calculation cost can be effectively reduced, and the training efficiency and the prediction speed of the model are improved. That is, parameters such as temperature and water flow rate have a certain spatial local correlation in time sequence. The convolutional neural network can extract local features through convolution operation, so that the correlation is better captured, and the expression capacity of the model is further improved. Therefore, the temperature and flow correlation input matrix is used as a convolutional neural network model of a filter to obtain a temperature and flow correlation feature vector, so that the correlation between the temperature and the water flow can be effectively captured, the risk of overfitting is reduced, the calculation efficiency is improved, and the expression capacity and performance of the model are further optimized by combining other deep learning technologies.
And then, fusing the temperature flow associated feature vector and the pressure feature vector to obtain a fused feature vector, and passing the fused feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating that the pressure value of the water conservancy system should be increased or decreased, and the temperature flow associated feature vector and the pressure feature vector both contain the change trend and the correlation of different parameters in the water supply system. There may be some potential correlation between the temperature flow correlation feature vector and the pressure feature vector, such as the effect of temperature and water flow variations on the water supply pressure, etc. The characteristic information can be fused together through the fusion vector, so that the state and the characteristics of the water supply system are more comprehensively described, the information among different characteristics can be synthesized, the characteristic association is established, the characteristic dimension is reduced, and the more accurate and reliable water supply system adjustment is realized.
In particular, in the technical solution of the present application, when the temperature and flow related feature vector and the pressure feature vector are fused, because the two feature vectors provide partially similar information, this may cause a certain degree of data redundancy. In addition, these factors can also lead to data noise due to errors, noise, and uncertainty in data acquisition and processing. If the temperature flow related feature vector and the pressure feature vector are directly fused by cascading, the influence of noise and redundant information is reduced, the feature fusion effect is reduced, the information loss in the feature fusion process is increased, and the quality and the credibility of the data after feature fusion are reduced.
Based on this, in the technical scheme of the application, fusing the temperature flow related feature vector and the pressure feature vector to obtain a fused feature vector includes: sparse coding is carried out on the temperature flow associated feature vector and the pressure feature vector so as to obtain a first sparse feature vector and a second sparse feature vector; calculating a first JS divergence of the first sparse feature vector relative to the second sparse feature vector; calculating a second JS divergence of the second sparse feature vector relative to the first sparse feature vector; normalizing the first JS divergence and the second JS divergence to obtain normalized first JS divergence and normalized second JS divergence; and fusing the first sparse feature vector and the second sparse feature vector by taking the normalized first JS divergence and the normalized second JS divergence as weights to obtain a fused feature vector.
The feature distribution fusion algorithm utilizes the sparse coding idea to effectively capture the structure and mode information between two feature distributions without being influenced by noise and redundant information, so that the feature fusion effect is improved, in such a way, the information loss in the feature fusion process can be effectively reduced, the important information in the original feature distribution is reserved, the data quality and the reliability after feature fusion are improved, meanwhile, the data dimension after feature fusion can be effectively reduced, the data redundancy and the noise are reduced, the data expression capability after feature fusion is effectively enhanced, more implicit information and potential rules are extracted, the capability and the level of data mining and knowledge discovery are improved, and the accuracy of the classification result obtained by the classifier through the fused feature vector is improved.
Based on this, the present application provides a hydraulic balance control system, comprising: the data acquisition module is used for acquiring temperature values, water flow values and pressure values at a plurality of preset time points in a preset time period; the data association module is used for respectively arranging the temperature values and the water flow values of the plurality of preset time points into a temperature input vector and a water flow input vector according to the time dimension and then calculating a temperature flow association input matrix between the temperature input vector and the water flow input vector; the pressure characteristic vector extraction module is used for respectively arranging the pressure values of the plurality of preset time points into the pressure input vector according to the time dimension, and obtaining a pressure characteristic vector through the multi-scale neighborhood characteristic extraction module; the correlation characteristic coding module is used for enabling the temperature flow correlation input matrix to pass through a convolutional neural network model serving as a filter to obtain a temperature flow correlation characteristic vector; the fusion feature module is used for fusing the temperature flow associated feature vector and the pressure feature vector to obtain a fusion feature vector; and the result generation module is used for passing the fusion feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating that the pressure value of the water conservancy system should be increased or decreased.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Exemplary System
FIG. 1 is a block diagram schematic of a hydraulic balance control system according to an embodiment of the present application. As shown in fig. 1, the hydraulic balance control system 100 according to the embodiment of the present application includes: a data acquisition module 110, configured to acquire temperature values, water flow values, and pressure values at a plurality of predetermined time points within a predetermined time period; the data correlation module 120 is configured to arrange the temperature values and the water flow values at the plurality of predetermined time points into a temperature input vector and a water flow input vector according to a time dimension, and then calculate a temperature flow correlation input matrix between the temperature input vector and the water flow input vector; the pressure feature vector extraction module 130 is configured to arrange the pressure values of the plurality of predetermined time points into the pressure input vectors according to a time dimension, and then obtain pressure feature vectors through the multi-scale neighborhood feature extraction module; the correlation feature encoding module 140 is configured to pass the temperature and flow correlation input matrix through a convolutional neural network model serving as a filter to obtain a temperature and flow correlation feature vector; the fusion feature module 150 is configured to fuse the temperature flow related feature vector and the pressure feature vector to obtain a fusion feature vector; and a result generation module 160, configured to pass the fusion feature vector through a classifier to obtain a classification result, where the classification result is used to indicate that the pressure value of the hydraulic system should be increased or decreased.
In the embodiment of the present application, the data acquisition module 110 is configured to acquire temperature values, water flow values, and pressure values at a plurality of predetermined time points within a predetermined time period. Considering that parameters such as temperature, water flow and pressure in the water supply system have influence on the water supply system, the states of the water supply system at different time points can have larger difference, such as different time periods of morning, noon, evening and the like, and are influenced by external factors such as seasons, weather and the like, the accuracy and stability of data acquisition can be improved by acquiring data at a plurality of preset time points, the influence of abnormal and error data is reduced, the water supply system can be comprehensively monitored and analyzed, and a corresponding model is established to realize automatic adjustment.
In this embodiment of the present application, the data association module 120 is configured to arrange the temperature values and the water flow values at the plurality of predetermined time points into a temperature input vector and a water flow input vector according to a time dimension, and then calculate a temperature flow association input matrix between the temperature input vector and the water flow input vector. Considering that the temperature and the water flow are very important parameters in the water supply system, the change trend and the interaction relationship between the temperature and the water flow can reflect the real-time state of the water supply system, and certain correlation exists between the temperature and the water flow, for example, the water flow is changed due to the temperature rise. Temperature and water flow are one of the main factors affecting the water supply pressure, and the correlation characteristics between them can be used to predict future pressure changes. Therefore, by calculating the temperature flow rate association input matrix, the association between the temperature and the water flow rate can be established, and the change trend and the interaction relationship between the temperature and the water flow rate at different time points can be reflected, so that the state and the characteristic of the water supply system can be more comprehensively and accurately captured.
In a specific embodiment of the present application, the data correlation module calculates a product between a transpose vector of the temperature input vector and the water flow input vector to obtain the temperature flow correlation input matrix.
In the embodiment of the present application, the pressure feature vector extraction module 130 is configured to arrange the pressure values at the plurality of predetermined time points into the pressure input vector according to a time dimension, and then obtain a pressure feature vector through a multi-scale neighborhood feature extraction module. Taking into account that the pressure value in the water supply changes over time. The pressure trend may be different at different time scales, such as sudden changes in a short period and slow trends in a long period. Furthermore, the method based on multi-scale neighborhood feature extraction can abstract pressure data with different granularities, in this way, the original pressure data can be converted into higher-level features, so that the model can learn the general rule in the data more easily, and the generalization capability of the model is improved. In practice, pressure data in the water supply may be subject to various disturbances and noise, such as sensor errors, equipment malfunctions, etc. Through multi-scale extraction, the interference and noise can be offset to a certain extent, and the robustness of the model is improved. Therefore, after the pressure values of the plurality of preset time points are respectively arranged into the pressure input vector according to the time dimension, the pressure feature vector is obtained through the multi-scale neighborhood feature extraction module, so as to capture the pressure change trend under different time scales and improve the feature expression capability.
Fig. 2 is a block diagram of a hydraulic balance control system and a method thereof according to an embodiment of the present application. In a specific embodiment of the present application, the pressure feature vector extraction module 130 includes: a first scale feature extraction unit 131, configured to input the pressure input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first scale pressure feature vector, where the first convolution layer has a first one-dimensional convolution kernel with a first length; a second scale feature extraction unit 132 configured to input the pressure input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale pressure feature vector, where the second convolution layer has a second one-dimensional convolution kernel of a second length, and the first length is different from the second length; and a fusion unit 133, configured to concatenate the first scale pressure feature vector and the second scale pressure feature vector using a concatenation layer of the multi-scale neighborhood feature extraction module to obtain the pressure feature vector.
In a specific embodiment of the present application, the first scale feature extraction unit is configured to: performing one-dimensional convolution encoding on the pressure input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module according to the following first convolution formula to obtain a first-scale pressure feature vector; wherein the first convolution formula is:
Wherein a is the width of the first one-dimensional convolution kernel in the X direction, F (a) is a parameter vector of the first one-dimensional convolution kernel, G (X-a) is a local vector matrix operated with the first convolution kernel function, w is the size of the first one-dimensional convolution kernel, X represents the pressure input vector, and Cov (X) is one-dimensional convolution encoding of the pressure input vector.
In a specific embodiment of the present application, the second scale feature extraction unit is configured to: performing one-dimensional convolution encoding on the pressure input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module according to the following second convolution formula to obtain a second-scale pressure feature vector; wherein the second convolution formula is:
wherein b is the width of the second one-dimensional convolution kernel in the X direction, F (b) is a parameter vector of the second one-dimensional convolution kernel, G (X-b) is a local vector matrix calculated by a second convolution kernel function, m is the size of the second one-dimensional convolution kernel, X represents the pressure input vector, and Cov (X) is one-dimensional convolution encoding of the pressure input vector.
In the embodiment of the present application, the correlation feature encoding module 140 is configured to pass the temperature and flow correlation input matrix through a convolutional neural network model serving as a filter to obtain a temperature and flow correlation feature vector. Considering that the temperature and flow associated input matrix tends to have larger dimension and scale, the traditional fully-connected neural network is easy to generate problems of parameter explosion and calculation resource waste. And when the convolutional neural network processes large-scale data, the calculation cost can be effectively reduced, and the training efficiency and the prediction speed of the model are improved. That is, parameters such as temperature and water flow rate have a certain spatial local correlation in time sequence. The convolutional neural network can extract local features through convolution operation, so that the correlation is better captured, and the expression capacity of the model is further improved. Therefore, the temperature and flow correlation input matrix is used as a convolutional neural network model of a filter to obtain a temperature and flow correlation feature vector, so that the correlation between the temperature and the water flow can be effectively captured, the risk of overfitting is reduced, the calculation efficiency is improved, and the expression capacity and performance of the model are further optimized by combining other deep learning technologies.
In a specific embodiment of the present application, the associated feature encoding module includes: each layer using the convolutional neural network model is performed in forward transfer of the layer respectively; carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling each feature matrix along the channel dimension of the convolution feature map to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the convolutional neural network model is the temperature flow correlation characteristic vector, and the input of the first layer of the convolutional neural network model is the temperature flow correlation input matrix.
In the embodiment of the present application, the fusion feature module 150 is configured to fuse the temperature flow related feature vector and the pressure feature vector to obtain a fusion feature vector. And the temperature and flow related characteristic vector and the pressure characteristic vector both comprise the variation trend and the correlation of different parameters in the water supply system. There may be some potential correlation between the temperature flow correlation feature vector and the pressure feature vector, such as the effect of temperature and water flow variations on the water supply pressure, etc. The characteristic information can be fused together through the fusion vector, so that the state and the characteristics of the water supply system are more comprehensively described, the information among different characteristics can be synthesized, the characteristic association is established, the characteristic dimension is reduced, and the more accurate and reliable water supply system adjustment is realized.
In particular, in the technical solution of the present application, when the temperature and flow related feature vector and the pressure feature vector are fused, because the two feature vectors provide partially similar information, this may cause a certain degree of data redundancy. In addition, these factors can also lead to data noise due to errors, noise, and uncertainty in data acquisition and processing. If the temperature flow related feature vector and the pressure feature vector are directly fused by cascading, the influence of noise and redundant information is reduced, the feature fusion effect is reduced, the information loss in the feature fusion process is increased, and the quality and the credibility of the data after feature fusion are reduced.
In a specific embodiment of the present application, the fusion feature module includes: the sparse coding unit is used for performing sparse coding on the temperature flow associated feature vector and the pressure feature vector to obtain a first sparse feature vector and a second sparse feature vector; a first divergence calculating unit, configured to calculate a first JS divergence of the first sparse feature vector relative to the second sparse feature vector; a second divergence calculating unit, configured to calculate a second JS divergence of the second sparse feature vector relative to the first sparse feature vector; the normalization unit is used for performing normalization processing on the first JS dispersion and the second JS dispersion to obtain normalized first JS dispersion and normalized second JS dispersion; and a weight applying unit, configured to fuse the first sparse feature vector and the second sparse feature vector with the normalized first JS divergence and the normalized second JS divergence as weights, to obtain a fused feature vector.
The feature distribution fusion algorithm utilizes the sparse coding idea to effectively capture the structure and mode information between two feature distributions without being influenced by noise and redundant information, so that the feature fusion effect is improved, in such a way, the information loss in the feature fusion process can be effectively reduced, the important information in the original feature distribution is reserved, the data quality and the reliability after feature fusion are improved, meanwhile, the data dimension after feature fusion can be effectively reduced, the data redundancy and the noise are reduced, the data expression capability after feature fusion is effectively enhanced, more implicit information and potential rules are extracted, the capability and the level of data mining and knowledge discovery are improved, and the accuracy of the classification result obtained by the classifier through the fused feature vector is improved.
In one embodiment of the application, the temperature flow associated feature vector and the pressure feature vector are subjected to sparse coding based on a dictionary learning technology to obtain a first sparse feature vector and a second sparse feature vector. It will be appreciated that the main idea of dictionary learning-based techniques is to learn a sparse representation so that the original feature vectors can be described with a small number of non-zero weights, and that these weights are calculated based on a pre-defined dictionary. Specifically, sparse coding is performed on the temperature flow associated feature vector and the pressure feature vector based on a dictionary learning technology to obtain a first sparse feature vector and a second sparse feature vector, including: a sparse encoder is defined that is capable of receiving a feature vector and outputting a sparse code of the received feature vector. The code satisfies the following condition: the received feature vector is composed of a small number of non-zero values corresponding to base vectors in a dictionary defined in advance. A dictionary learning module is built, the input of which is a set of training feature vectors and the output of which is a set of basis vectors, which form a dictionary. The goal of dictionary learning is to minimize reconstruction errors, i.e., reconstruct the original feature vectors with the basis vectors in the dictionary such that the reconstruction errors are minimized. Given a training set, training is performed by using a sparse encoder and a dictionary learning module. In the training process, the original feature vector is transmitted to a sparse encoder to obtain sparse codes. The sparse coding and the basis vectors in the dictionary are then input into the decoder, minimizing the reconstruction error. This process is repeated until the model converges. For a new feature vector to be encoded, a sparse encoder and a dictionary which are trained are used for calculating the sparse code related to the new feature vector.
In this embodiment of the present application, the management result generating module 160 is configured to pass the fused feature vector through a classifier to obtain a classification result, where the classification result is used to indicate that the pressure value of the hydraulic system should be increased or decreased.
In summary, according to the hydraulic balance control system provided by the embodiment of the application, the temperature values, the water flow values and the pressure values of a plurality of preset time points are collected first, then, a deep neural network model based on deep learning is used as a feature extractor, and the feature extraction is performed through a multi-scale domain feature extraction module and a convolution neural network model, so that the pressure of the water supply system is balanced, and the hydraulic balance is achieved, so that the stability and the reliability of the water supply system are effectively improved.
Exemplary method
Fig. 3 is a flow chart of a hydraulic balance control method according to an embodiment of the present application. As shown in fig. 3, the hydraulic balance control method according to the embodiment of the present application includes: s110, acquiring temperature values, water flow values and pressure values at a plurality of preset time points in a preset time period; s120, after arranging the temperature values and the water flow values of the plurality of preset time points into a temperature input vector and a water flow input vector according to a time dimension, calculating a temperature flow correlation input matrix between the temperature input vector and the water flow input vector; s130, after the pressure values of the plurality of preset time points are respectively arranged into the pressure input vectors according to the time dimension, obtaining pressure feature vectors through a multi-scale neighborhood feature extraction module; s140, the temperature flow correlation input matrix is passed through a convolutional neural network model serving as a filter to obtain a temperature flow correlation feature vector; s150, fusing the temperature flow related feature vector and the pressure feature vector to obtain a fused feature vector; and S160, passing the fusion feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating that the pressure value of the water conservancy system should be increased or decreased.
Fig. 4 is a schematic diagram of a hydraulic balance control method architecture according to an embodiment of the present application. As shown in fig. 4, in the embodiment of the present application, first, temperature values, water flow rate values, and pressure values at a plurality of predetermined time points within a predetermined period of time are acquired. And then, arranging the temperature values and the water flow values of the plurality of preset time points into a temperature input vector and a water flow input vector according to a time dimension, and calculating a temperature flow correlation input matrix between the temperature input vector and the water flow input vector. And meanwhile, after the pressure values of the plurality of preset time points are respectively arranged into the pressure input vector according to the time dimension, obtaining a pressure characteristic vector through a multi-scale neighborhood characteristic extraction module. And then, the temperature flow correlation input matrix is passed through a convolutional neural network model serving as a filter to obtain a temperature flow correlation characteristic vector. Finally, fusing the temperature flow associated feature vector and the pressure feature vector to obtain a fused feature vector; and passing the fusion feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating that the pressure value of the water conservancy system should be increased or decreased.
In step S120, after the temperature values and the water flow values at the predetermined time points are respectively arranged into a temperature input vector and a water flow input vector according to the time dimension, a temperature flow correlation input matrix between the temperature input vector and the water flow input vector is calculated. Comprising the following steps: and calculating the product between the transpose vector of the temperature input vector and the water flow input vector to obtain the temperature flow correlation input matrix.
In step S130, after arranging the pressure values of the plurality of predetermined time points into the pressure input vector according to a time dimension, a multi-scale neighborhood feature extraction module is used to obtain a pressure feature vector, which includes: inputting the pressure input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first-scale pressure feature vector, wherein the first convolution layer has a first one-dimensional convolution kernel with a first length; inputting the pressure input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale pressure feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel of a second length, and the first length is different from the second length; and cascading the first scale pressure feature vector and the second scale pressure feature vector by using a cascading layer of the multi-scale neighborhood feature extraction module to obtain the pressure feature vector.
Specifically, in the embodiment of the present application, the pressure input vector is input to a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first scale pressure feature vector, where the first convolution layer has a first one-dimensional convolution kernel with a first length for: performing one-dimensional convolution encoding on the pressure input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module according to the following first convolution formula to obtain a first-scale pressure feature vector; wherein the first convolution formula is:
wherein a is the width of the first one-dimensional convolution kernel in the X direction, F (a) is a parameter vector of the first one-dimensional convolution kernel, G (X-a) is a local vector matrix operated with the first convolution kernel function, w is the size of the first one-dimensional convolution kernel, X represents the pressure input vector, and Cov (X) is one-dimensional convolution encoding of the pressure input vector.
Specifically, in an embodiment of the present application, inputting the pressure input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second-scale pressure feature vector, where the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length, and includes: performing one-dimensional convolution encoding on the pressure input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module according to the following second convolution formula to obtain a second-scale pressure feature vector; wherein the second convolution formula is:
Wherein b is the width of the second one-dimensional convolution kernel in the X direction, F (b) is a parameter vector of the second one-dimensional convolution kernel, G (X-b) is a local vector matrix calculated by a second convolution kernel function, m is the size of the second one-dimensional convolution kernel, X represents the pressure input vector, and Cov (X) is one-dimensional convolution encoding of the pressure input vector.
Here, it will be understood by those skilled in the art that the specific operations of the respective steps in the above hydraulic balance control method have been described in detail in the above description of the hydraulic balance control system with reference to fig. 1 to 2, and thus, repetitive descriptions thereof will be omitted.
Exemplary electronic device
Next, a block diagram of an electronic device according to an embodiment of the present application is described with reference to fig. 5. Fig. 5 is a block diagram of an electronic device according to an embodiment of the application. As shown in fig. 5, the electronic device 10 includes one or more processors 11 and a memory 12.
The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer readable storage medium that can be executed by the processor 11 to perform the functions in the hydraulic balance control method of the various embodiments of the present application described above and/or other desired functions. Various contents such as a temperature value, a water flow value, and a pressure value may also be stored in the computer-readable storage medium.
In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown).
The input means 13 may comprise, for example, a keyboard, a mouse, etc.
The output device 14 may output various information including the classification result and the like to the outside. The output means 14 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.
Of course, only some of the components of the electronic device 10 that are relevant to the present application are shown in fig. 5 for simplicity, components such as buses, input/output interfaces, etc. are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer readable storage Medium
In addition to the methods and apparatus described above, embodiments of the application may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform steps in the functions of the hydraulic balance control method according to various embodiments of the application described in the "exemplary methods" section of this specification.
The computer program product may write program code for performing operations of embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present application may also be a computer-readable storage medium, on which computer program instructions are stored, which, when being executed by a processor, cause the processor to perform steps in the functions of the hydraulic balance control method according to the various embodiments of the present application described in the "exemplary method" section above in this specification.
The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Claims (10)

1. A hydraulic balance control system, comprising:
the data acquisition module is used for acquiring temperature values, water flow values and pressure values at a plurality of preset time points in a preset time period;
the data association module is used for respectively arranging the temperature values and the water flow values of the plurality of preset time points into a temperature input vector and a water flow input vector according to the time dimension and then calculating a temperature flow association input matrix between the temperature input vector and the water flow input vector;
the pressure characteristic vector extraction module is used for respectively arranging the pressure values of the plurality of preset time points into the pressure input vector according to the time dimension, and obtaining a pressure characteristic vector through the multi-scale neighborhood characteristic extraction module;
the correlation characteristic coding module is used for enabling the temperature flow correlation input matrix to pass through a convolutional neural network model serving as a filter to obtain a temperature flow correlation characteristic vector;
the fusion feature module is used for fusing the temperature flow associated feature vector and the pressure feature vector to obtain a fusion feature vector; and
and the result generation module is used for passing the fusion feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating that the pressure value of the water conservancy system should be increased or decreased.
2. The hydraulic balance control system of claim 1, wherein the data correlation module is configured to: and calculating the product between the transpose vector of the temperature input vector and the water flow input vector to obtain the temperature flow correlation input matrix.
3. The hydraulic balance control system of claim 2, wherein the pressure feature vector extraction module comprises:
a first scale feature extraction unit, configured to input the pressure input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first scale pressure feature vector, where the first convolution layer has a first one-dimensional convolution kernel with a first length;
a second scale feature extraction unit configured to input the pressure input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale pressure feature vector, where the second convolution layer has a second one-dimensional convolution kernel of a second length, and the first length is different from the second length; and
and the fusion unit is used for cascading the first scale pressure characteristic vector and the second scale pressure characteristic vector by using a cascading layer of the multi-scale neighborhood characteristic extraction module so as to obtain the pressure characteristic vector.
4. The hydraulic balance control system according to claim 3, wherein the first scale feature extraction unit is configured to: performing one-dimensional convolution encoding on the pressure input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module according to the following first convolution formula to obtain a first-scale pressure feature vector;
wherein the first convolution formula is:
wherein a is the width of the first one-dimensional convolution kernel in the X direction, F (a) is a parameter vector of the first one-dimensional convolution kernel, G (X-a) is a local vector matrix operated with the first convolution kernel function, w is the size of the first one-dimensional convolution kernel, X represents the pressure input vector, and Cov (X) is one-dimensional convolution encoding of the pressure input vector.
5. The hydraulic balance control system according to claim 4, wherein the second scale feature extraction unit is configured to: performing one-dimensional convolution encoding on the pressure input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module according to the following second convolution formula to obtain a second-scale pressure feature vector;
wherein the second convolution formula is:
wherein b is the width of the second one-dimensional convolution kernel in the X direction, F (b) is a parameter vector of the second one-dimensional convolution kernel, G (X-b) is a local vector matrix calculated by a second convolution kernel function, m is the size of the second one-dimensional convolution kernel, X represents the pressure input vector, and Cov (X) is one-dimensional convolution encoding of the pressure input vector.
6. The hydraulic balance control system of claim 5, wherein the associated feature encoding module is configured to:
each layer using the convolutional neural network model is performed in forward transfer of the layer respectively;
carrying out convolution processing on input data to obtain a convolution characteristic diagram;
pooling each feature matrix along the channel dimension of the convolution feature map to obtain a pooled feature map; and
non-linear activation is carried out on the pooled feature map so as to obtain an activated feature map;
the output of the last layer of the convolutional neural network model is the temperature flow correlation characteristic vector, and the input of the first layer of the convolutional neural network model is the temperature flow correlation input matrix.
7. The hydraulic balance control system of claim 6 wherein the fusion characterization module comprises:
the sparse coding unit is used for performing sparse coding on the temperature flow associated feature vector and the pressure feature vector to obtain a first sparse feature vector and a second sparse feature vector;
a first divergence calculating unit, configured to calculate a first JS divergence of the first sparse feature vector relative to the second sparse feature vector;
A second divergence calculating unit, configured to calculate a second JS divergence of the second sparse feature vector relative to the first sparse feature vector;
the normalization unit is used for performing normalization processing on the first JS dispersion and the second JS dispersion to obtain normalized first JS dispersion and normalized second JS dispersion; and
and the weight applying unit is used for fusing the first sparse feature vector and the second sparse feature vector by taking the normalized first JS divergence and the normalized second JS divergence as weights so as to obtain a fused feature vector.
8. A hydraulic balance control method, comprising:
acquiring temperature values, water flow values and pressure values at a plurality of preset time points in a preset time period;
after arranging the temperature values and the water flow values of the plurality of preset time points into a temperature input vector and a water flow input vector according to a time dimension respectively, calculating a temperature flow correlation input matrix between the temperature input vector and the water flow input vector;
the pressure values of the plurality of preset time points are respectively arranged into the pressure input vector according to the time dimension, and then the pressure characteristic vector is obtained through a multi-scale neighborhood characteristic extraction module;
The temperature flow correlation input matrix is passed through a convolutional neural network model serving as a filter to obtain a temperature flow correlation characteristic vector;
fusing the temperature flow associated feature vector and the pressure feature vector to obtain a fused feature vector; and
and the fusion characteristic vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the pressure value of the water conservancy system should be increased or decreased.
9. The hydraulic balance control method according to claim 8, wherein after the temperature values and the water flow values at the plurality of predetermined time points are arranged into a temperature input vector and a water flow input vector in a time dimension, respectively, calculating a temperature flow correlation input matrix between the temperature input vector and the water flow input vector, comprises: and calculating the product between the transpose vector of the temperature input vector and the water flow input vector to obtain the temperature flow correlation input matrix.
10. The hydraulic balance control method according to claim 9, wherein the step of obtaining the pressure feature vector by the multi-scale neighborhood feature extraction module after arranging the pressure values of the plurality of predetermined time points into the pressure input vector according to the time dimension, respectively, comprises:
Inputting the pressure input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first-scale pressure feature vector, wherein the first convolution layer has a first one-dimensional convolution kernel with a first length;
inputting the pressure input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale pressure feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel of a second length, and the first length is different from the second length; and
and cascading the first scale pressure feature vector and the second scale pressure feature vector by using a cascading layer of the multi-scale neighborhood feature extraction module to obtain the pressure feature vector.
CN202310837294.2A 2023-07-08 2023-07-08 Hydraulic balance control system and method thereof Pending CN117073055A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310837294.2A CN117073055A (en) 2023-07-08 2023-07-08 Hydraulic balance control system and method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310837294.2A CN117073055A (en) 2023-07-08 2023-07-08 Hydraulic balance control system and method thereof

Publications (1)

Publication Number Publication Date
CN117073055A true CN117073055A (en) 2023-11-17

Family

ID=88716024

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310837294.2A Pending CN117073055A (en) 2023-07-08 2023-07-08 Hydraulic balance control system and method thereof

Country Status (1)

Country Link
CN (1) CN117073055A (en)

Similar Documents

Publication Publication Date Title
CN115796173A (en) Data processing method and system for supervision submission requirements
CN115759658B (en) Enterprise energy consumption data management system suitable for smart city
CN114724386B (en) Short-time traffic flow prediction method and system under intelligent traffic and electronic equipment
CN116245513B (en) Automatic operation and maintenance system and method based on rule base
CN115456789B (en) Abnormal transaction detection method and system based on transaction pattern recognition
CN116247824B (en) Control method and system for power equipment
CN115859437A (en) Jacket underwater stress detection system based on distributed optical fiber sensing system
CN116308754B (en) Bank credit risk early warning system and method thereof
CN115471216B (en) Data management method of intelligent laboratory management platform
CN117058622A (en) Intelligent monitoring system and method for sewage treatment equipment
CN117041017A (en) Intelligent operation and maintenance management method and system for data center
CN115878330A (en) Thread operation control method and system
CN115324843A (en) Wind generating set fault diagnosis system and method based on monitoring data
CN117612053A (en) Asphalt waterproof coiled material processing and preparing system and method thereof
CN116844088A (en) Online dust remover control system and method thereof
CN117268760A (en) Bearing state monitoring system and method
CN115205788A (en) Food material quality monitoring system
CN117421655A (en) Industrial Internet data stream anomaly detection method and system
CN112766810A (en) Neural network training method for intelligent comprehensive overall quality evaluation
CN116467485B (en) Video image retrieval construction system and method thereof
CN116404212B (en) Capacity equalization control method and system for zinc-iron flow battery system
CN116821831A (en) Intelligent electric power inspection system and method thereof
CN117073055A (en) Hydraulic balance control system and method thereof
CN116385733A (en) High-precision positioning system and method for bucket wheel machine
CN116124448A (en) Fault diagnosis system and method for wind power gear box

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