Hydraulic balance adjusting system and method for heat supply pipe network
By using sensors and deep learning technology to calculate the semantic interactive fusion characteristics of temperature and flow in the heating system, intelligently adjusting the speed of the water mixing pump, solving the problem of insufficient hydraulic balance adjustment capability in the heating system during regional expansion and demand growth, and achieving More efficient heating management.
Patent Information
- Application Number
- CN202411405180.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-10
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
When existing heating systems expand regionally and grow heating demand, it is difficult to effectively adjust the hydraulic balance, resulting in uneven hot and cold heat, waste of energy and reduced efficiency.
Using water supply temperature sensor, return water temperature sensor and pipeline flow sensor, data acquisition and processing are carried out through the water mixing flow controller, and using a local interactive fusion network based on deep convolutional neural network and feature fine-grained decoupling to calculate temperature deviation and pipeline The semantic interactive fusion feature of flow, intelligently recommends the speed of the mixing pump to adjust the pipeline flow.
It realizes intelligent adjustment of the heating system, adapts to the balance of the expansion of heating area and regional heating conditions, ensures that remote users can obtain stable heating, and improves the energy efficiency and response capabilities of the system.
Smart Images

Figure CN118912569A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of heating, and in particular to a hydraulic balance regulation system and method for a heating pipe network. Background Art
[0002] Heating systems are an important part of modern buildings and urban infrastructure, which need to maintain a stable supply of heat energy in different seasons and weather conditions. In a heating system, hydraulic balance refers to the balanced distribution of fluid flow conditions in various parts of the system. If the hydraulic balance of the system is disrupted, it may cause some areas to overheat and others to be insufficient, thereby reducing the efficiency of the entire system and the comfort of users. Therefore, achieving good hydraulic balance is essential to improve the overall performance of the heating system.
[0003] However, the original heating system uses a direct supply booster pump. With the expansion of the region and the continuous growth of heating demand, this system may face the problem of insufficient hydraulic balance adjustment capacity. In other words, the original direct supply booster pump form is difficult to provide sufficient adjustability, unable to effectively adapt to the dynamic changes in heating demand, and difficult to adapt to the expansion of heating area and the diversification of user needs, which may lead to uneven heating and cooling, energy waste and reduced efficiency.
[0004] Therefore, an optimized hydraulic balance regulation system for the heating network is desired. Summary of the invention
[0005] This application is made in view of the above problems. One object of this application is to provide a hydraulic balance adjustment system and method for a heating pipe network.
[0006] An embodiment of the present application provides a hydraulic balance regulation system for a heating pipe network, which includes: a water supply temperature sensor, a return water temperature sensor, a pipeline flow sensor and a mixed water flow controller; the water supply temperature sensor is installed in the water supply pipe of the heating pipe network, and is used to collect the water supply temperature; the return water temperature sensor is installed in the return water pipe of the heating pipe network, and is used to collect the return water temperature; the pipeline flow sensor is installed in the mixed water pipe of the mixed water system, and is used to collect the pipeline flow of the mixed water pipe; the mixed water flow controller can be communicatively connected to the water supply temperature sensor, the return water temperature sensor and the pipeline flow sensor, and is used to control the pipeline flow of the mixed water system.
[0007] For example, according to the hydraulic balance regulation system of the heating pipe network of the embodiment of the present application, the mixed water flow controller includes: a water supply and return water temperature acquisition module, which is used to obtain the time series of the water supply temperature and the time series of the return water temperature; a pipeline flow acquisition module, which is used to obtain the time series of the pipeline flow of the mixed water system; a parameter time series feature extraction module, which is used to regularize the time series of the water supply temperature, the time series of the return water temperature and the time series of the pipeline flow according to the time dimension and then pass the time series feature extractor to obtain the water supply temperature time series feature vector, the return water temperature time series feature vector and the pipeline flow time series feature vector; a temperature deviation calculation module, Used to calculate the difference characteristics between the water supply temperature time series feature vector and the return water temperature time series feature vector to obtain the temperature deviation time series feature vector; the temperature deviation-pipeline flow local interaction module is used to fuse the temperature deviation time series feature vector and the pipeline flow time series feature vector through a local interaction fusion network based on feature fine-grained decoupling to obtain the temperature deviation-pipeline flow time series semantic interaction fusion feature vector; the mixing pump speed recommendation module is used to obtain the recommended control value of the mixing pump speed based on the temperature deviation-pipeline flow time series semantic interaction fusion feature vector, and control the pipeline flow of the mixing water system based on the recommended control value of the mixing pump speed.
[0008] For example, according to the hydraulic balance regulation system of the heating pipe network according to the embodiment of the present application, the parameter timing feature extraction module is used to: regularize the time series of the water supply temperature, the time series of the return water temperature and the time series of the pipeline flow according to the time dimension, and then pass them through a timing feature extractor based on a deep convolutional neural network to obtain the water supply temperature timing feature vector, the return water temperature timing feature vector and the pipeline flow timing feature vector.
[0009] For example, according to the hydraulic balance regulation system of the heating pipe network of the embodiment of the present application, the time series feature extractor based on the deep convolutional neural network is a time series feature extractor based on 1D-CNN.
[0010] For example, according to the hydraulic balance regulation system of the heating pipe network according to the embodiment of the present application, the temperature deviation calculation module is used to: calculate the positional difference between the water supply temperature time series characteristic vector and the return water temperature time series characteristic vector to obtain the temperature deviation time series characteristic vector.
[0011] For example, according to the hydraulic balance regulation system of the heating pipe network of the embodiment of the present application, the temperature deviation-pipeline flow local interaction module includes: a feature decoupling unit, which is used to perform feature decoupling on the temperature deviation time series feature vector and the pipeline flow time series feature vector to obtain a sequence of temperature deviation local time series feature vectors and a sequence of pipeline flow local time series feature vectors; a temperature deviation-pipeline flow local time series semantic association interaction unit, which is used to calculate the local semantic association interaction vector between each group of corresponding temperature deviation local time series feature vectors and pipeline flow local time series feature vectors in the sequence of temperature deviation local time series feature vectors and the sequence of pipeline flow local time series feature vectors to obtain a sequence of temperature deviation-pipeline flow local time series semantic association interaction vectors; a temperature deviation-pipeline flow local time series fine-grained attention weight meter A calculation unit is used to calculate the fine-grained attention weights of each temperature deviation-pipeline flow local time series semantic association interaction vector in the sequence of the temperature deviation-pipeline flow local time series semantic association interaction vector to obtain a sequence of temperature deviation-pipeline flow local time series fine-grained attention weights; an inactivation processing unit is used to input the sequence of temperature deviation-pipeline flow local time series fine-grained attention weights into a random inactivation module to obtain a sequence of temperature deviation-pipeline flow local time series fine-grained attention weights after inactivation processing; a weighted sum calculation unit is used to use the sequence of temperature deviation-pipeline flow local time series fine-grained attention weights after inactivation processing as a weight distribution, and calculate the weighted sum of the sequence of temperature deviation-pipeline flow local time series semantic association interaction vectors to obtain the temperature deviation-pipeline flow time series semantic interaction fusion feature vector.
[0012] For example, according to the hydraulic balance regulation system of the heating pipe network of the embodiment of the present application, the temperature deviation-pipeline flow local time series semantic association interaction unit is used to: respectively calculate the position difference, position point multiplication and position addition between the temperature deviation local time series feature vector and the pipe flow local time series feature vector to obtain the temperature deviation-pipeline flow local time series difference vector, the temperature deviation-pipeline flow local time series point product vector and the temperature deviation-pipeline flow local time series sum vector; cascade the temperature deviation-pipeline flow local time series difference vector, the temperature deviation-pipeline flow local time series point product vector and the temperature deviation-pipeline flow local time series sum vector, and perform one-dimensional convolution encoding to obtain a temperature deviation-pipeline flow local time series multi-dimensional fusion vector; perform local window-based maximum pooling processing on the temperature deviation-pipeline flow local time series multi-dimensional fusion vector to obtain the temperature deviation-pipeline flow local time series semantic association interaction vector.
[0013] For example, according to the hydraulic balance regulation system of the heating pipe network of the embodiment of the present application, the temperature deviation-pipeline flow local temporal series fine-grained attention weight calculation unit is used to: multiply each temperature deviation-pipeline flow local temporal series semantic association interaction vector in the sequence of temperature deviation-pipeline flow local temporal series semantic association interaction vectors by the weight matrix, and then add the obtained vector and the bias vector by position to obtain a sequence of temperature deviation-pipeline flow local temporal series semantic association interaction modulation vectors; input the sequence of temperature deviation-pipeline flow local temporal series semantic association interaction modulation vectors into the tanh function for activation processing to obtain a sequence of temperature deviation-pipeline flow local temporal series semantic association interaction activation vectors; multiply each temperature deviation-pipeline flow local temporal series semantic association interaction activation vector in the sequence of temperature deviation-pipeline flow local temporal series semantic association interaction activation vectors by the weight coefficient vector to obtain the sequence of temperature deviation-pipeline flow local temporal series fine-grained attention weights.
[0014] For example, according to the hydraulic balance regulation system of the heating pipe network of the embodiment of the present application, the mixing pump speed recommendation module includes: a mixing pump control unit, which is used to pass the temperature deviation-pipeline flow time series semantic interaction fusion feature vector through a decoder-based mixing pump controller to obtain a recommended control decoding value of the mixing pump speed; a control unit, which is used to control the pipeline flow of the mixing water system based on the recommended control decoding value of the mixing water pump speed.
[0015] The embodiment of the present application also provides a method for regulating the hydraulic balance of a heating network, which comprises: collecting the water supply temperature by means of a water supply temperature sensor installed in the water supply pipe of the heating network; collecting the return water temperature by means of a return water temperature sensor installed in the return water pipe of the heating network; collecting the pipe flow of the mixing water pipe by means of a pipe flow sensor installed in the mixing water pipe of the mixing water system; connecting a mixing water flow controller to the water supply temperature sensor, the return water temperature sensor and the pipe flow sensor in a communicable manner, and controlling the pipe flow of the mixing water system by means of the mixing water flow controller; wherein controlling the pipe flow of the mixing water system by means of the mixing water flow controller comprises: obtaining a time series of the supply water temperature and a time series of the return water temperature; obtaining a time series of the pipe flow of the mixing water system; and connecting the supply water temperature sensor, the return water temperature sensor and the pipe flow sensor to the pipe flow controller. The time series of water temperature, the time series of return water temperature and the time series of pipeline flow are regularized according to the time dimension and then passed through a time series feature extractor to obtain a water supply temperature time series feature vector, a return water temperature time series feature vector and a pipeline flow time series feature vector; the difference feature between the water supply temperature time series feature vector and the return water temperature time series feature vector is calculated to obtain a temperature deviation time series feature vector; the temperature deviation time series feature vector and the pipeline flow time series feature vector are passed through a local interactive fusion network based on feature fine-grained decoupling to obtain a temperature deviation-pipeline flow time series semantic interactive fusion feature vector; based on the temperature deviation-pipeline flow time series semantic interactive fusion feature vector, a recommended control value of the mixing pump speed is obtained, and based on the recommended control value of the mixing pump speed, the pipeline flow of the mixing water system is controlled.
[0016] According to the heating network hydraulic balance regulation system and method of the embodiments of the present application, it can better adapt to the expansion of the heating area, and at the same time can better balance the heating conditions of different areas in the network, ensuring that remote users can also obtain stable heating. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application are briefly introduced below. Obviously, the drawings described below only relate to some embodiments of the present application, and are not intended to limit the present application.
[0018] Figure 1 A structural schematic diagram of a hydraulic balance regulation system for a heating network in an embodiment of the present application is shown.
[0019] Figure 2 A structural schematic diagram of a mixed water flow controller of a hydraulic balance regulation system of a heating network in an embodiment of the present application is shown.
[0020] Figure 3A structural schematic diagram of a temperature deviation-pipeline flow local interaction module of a heating network hydraulic balance regulation system in an embodiment of the present application is shown.
[0021] Figure 4 A structural schematic diagram of a mixing pump speed recommendation module in a heating network hydraulic balance regulation system in an embodiment of the present application is shown.
[0022] Figure 5 A flow chart of a method for adjusting the hydraulic balance of a heating network in an embodiment of the present application is shown. DETAILED DESCRIPTION
[0023] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present application.
[0024] The terms used in this specification are those common terms currently widely used in the art in consideration of the functions of the present application, but these terms may vary according to the intentions of those skilled in the art, precedents, or new technologies in the art. In addition, specific terms may be selected, and in this case, their detailed meanings will be described in the detailed description of the present application. Therefore, the terms used in the specification should not be understood as simple names, but rather as a general description based on the meaning of the terms and the present application.
[0025] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.
[0026] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. At the same time, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.
[0027] In addition, the application architecture diagram in the embodiment of the present application is intended to more clearly illustrate the technical solution in the embodiment of the present application, and does not constitute a limitation on the technical solution provided in the embodiment of the present application. Of course, for other application architectures and business applications, the technical solution provided in the embodiment of the present application is also applicable to similar problems.
[0028] The following is a non-restrictive description of the hydraulic balance regulation system of the heating pipe network provided according to at least one embodiment of the present application through several examples or embodiments. As described below, different features in these specific examples or embodiments can be combined with each other without conflicting with each other to obtain new examples or embodiments, and these new examples or embodiments also fall within the scope of protection of the present application.
[0029] Based on this, the present application proposes an optimized heating network hydraulic balance regulation system 1000, such as Figure 1 As shown, it includes: a water supply temperature sensor 100, a return water temperature sensor 200, a pipeline flow sensor 300 and a mixed water flow controller 400; the water supply temperature sensor 100 is installed in the water supply pipe of the heating network to collect the water supply temperature; the return water temperature sensor 200 is installed in the return water pipe of the heating network to collect the return water temperature; the pipeline flow sensor 300 is installed in the mixed water pipeline of the mixed water system to collect the pipeline flow of the mixed water pipeline; the mixed water flow controller 400 can be communicatively connected to the water supply temperature sensor 100, the return water temperature sensor 200 and the pipeline flow sensor 300, and is used to control the pipeline flow of the mixed water system. In this way, compared with the direct supply booster pump system, the mixed water system has stronger adjustability and responsiveness, can better adapt to the expansion of the heating area, and can better balance the heating conditions of different areas in the pipeline network, ensuring that remote users can also obtain stable heating.
[0030] However, the hydraulic balance regulation in traditional heating systems mainly relies on basic rule matching and operator experience. This method is usually difficult to accurately predict temperature fluctuations and flow requirements, and cannot deeply analyze the complex dynamic characteristics of the system. In addition, due to the lack of rapid processing and intelligent response to real-time data, traditional systems often cannot flexibly adjust the speed of the mixing pump according to the current system status, resulting in the inability to optimize heating performance and respond to changes in the external environment or user needs in a timely manner.
[0031] Correspondingly, in the mixed water flow controller, the technical concept of the present application is to obtain the time series of the water supply temperature and the time series of the return water temperature, and obtain the time series of the pipeline flow of the mixed water system, and use artificial intelligence-based data processing and analysis technology to perform time series feature analysis of the water supply temperature, the return water temperature and the pipeline flow, so as to intelligently recommend the speed value of the mixed water pump according to the semantic interaction fusion characteristics between the temperature deviation time series characteristics calculated between the water supply temperature and the return water temperature and the pipeline flow time series characteristics, and control the pipeline flow of the mixed water system. In this way, the system can collect data in real time, and deeply explore and analyze the complex time series dynamic characteristics between the temperature and flow in the heating system, so as to intelligently recommend the optimal speed value of the mixed water pump to accurately control the flow of the mixed water system, thereby improving the intelligence of the hydraulic balance regulation of the heating pipe network.
[0032] Accordingly, if Figure 2 As shown, the mixed water flow controller 400 includes: a water supply and return water temperature acquisition module 410, which is used to obtain the time series of the water supply temperature and the time series of the return water temperature; a pipeline flow acquisition module 420, which is used to obtain the time series of the pipeline flow of the mixed water system; a parameter time series feature extraction module 430, which is used to regularize the time series of the water supply temperature, the time series of the return water temperature and the time series of the pipeline flow according to the time dimension and then pass the time series feature extractor to obtain the water supply temperature time series feature vector, the return water temperature time series feature vector and the pipeline flow time series feature vector; a temperature deviation calculation module 440, which is used to calculate the water supply temperature. The difference characteristics between the temperature time series feature vector and the return water temperature time series feature vector are used to obtain the temperature deviation time series feature vector; the temperature deviation-pipeline flow local interaction module 450 is used to obtain the temperature deviation-pipeline flow time series semantic interaction fusion feature vector by a local interaction fusion network based on feature fine-grained decoupling; the mixing pump speed recommendation module 460 is used to obtain the recommended control value of the mixing pump speed based on the temperature deviation-pipeline flow time series semantic interaction fusion feature vector, and control the pipeline flow of the mixing water system based on the recommended control value of the mixing pump speed.
[0033] Specifically, in the technical solution of the present application, firstly, the time series of the supply water temperature and the time series of the return water temperature are obtained, and the time series of the pipeline flow of the water mixing system is obtained.
[0034] Next, consider that the time series of the water supply temperature, the time series of the return water temperature and the time series of the pipeline flow rate are constantly changing with the passage of time, and there is a correlation between each time point in the local time dimension. 1D-CNN (One-Dimensional Convolutional Neural Network) is particularly suitable for processing time series data, and can capture local dependencies and patterns in time data to express the time change trend of time data. Therefore, in the technical solution of the present application, the time series of the water supply temperature, the time series of the return water temperature and the time series of the pipeline flow rate are regularized according to the time dimension and then passed through a time series feature extractor based on 1D-CNN to obtain a water supply temperature time series feature vector, a return water temperature time series feature vector and a pipeline flow time series feature vector.
[0035] Correspondingly, the parameter time series feature extraction module 430 is used to: perform data regularization on the time series of the water supply temperature, the time series of the return water temperature, and the time series of the pipeline flow according to the time dimension, and then pass them through a time series feature extractor based on a deep convolutional neural network to obtain the water supply temperature time series feature vector, the return water temperature time series feature vector, and the pipeline flow time series feature vector. The time series feature extractor based on a deep convolutional neural network is a time series feature extractor based on 1D-CNN.
[0036] Then, consider that the main goal of the heating system is to maintain a constant temperature. The difference between the water supply temperature and the return water temperature can directly reflect the heat exchange efficiency of the system, which is crucial for regulating the operation of the mixing water system. Based on this, in the technical solution of the present application, the difference characteristics between the water supply temperature time series characteristic vector and the return water temperature time series characteristic vector are calculated to obtain the temperature deviation time series characteristic vector. That is, by understanding the changing trend of the temperature deviation between the water supply temperature and the return water temperature, the system can intelligently adjust the speed of the mixing water pump to achieve more precise temperature control, thereby improving the energy efficiency of the system. In particular, in a specific embodiment of the present application, the temperature deviation time series characteristic vector can be obtained by calculating the positional difference between the water supply temperature time series characteristic vector and the return water temperature time series characteristic vector.
[0037] Correspondingly, the temperature deviation calculation module 440 is used to calculate the position difference between the supply water temperature time series characteristic vector and the return water temperature time series characteristic vector to obtain the temperature deviation time series characteristic vector.
[0038] Further, considering that there is a local time series mutual correlation dependency between the temperature deviation time series feature vector and the pipeline flow time series feature vector, that is, the temperature deviation and the pipeline flow have a close dynamic correlation in certain specific time periods. Based on this, in the technical solution of the present application, in order to be able to more fine-grainedly perform correlation and interaction analysis on the local time series features between the temperature deviation time series feature vector and the pipeline flow time series feature vector, a local interaction fusion network based on feature fine-grained decoupling is introduced. In particular, the local interaction fusion network based on feature fine-grained decoupling performs dynamic capture by analyzing and capturing the correlation relationship between the local time dimensions of the two. Specifically, first, by performing feature decoupling on the temperature deviation time series feature vector and the pipeline flow time series feature vector, a full-time domain feature vector is decomposed into multiple fine-grained temperature deviation local time series feature vectors and the pipeline flow local time series feature vector containing local time series. Afterwards, the local semantic association between each temperature deviation local time series feature vector and the pipeline flow local time series feature vector is calculated to generate a sequence of temperature deviation-pipeline flow local time series semantic association interaction vectors. In particular, the local semantic association calculates the position difference, position point multiplication and position addition between the two features respectively and concatenates the obtained features, performs one-dimensional convolution coding and performs local maximum pooling processing, which can better reflect the local temporal dependency between temperature deviation and pipeline flow and more accurately describe the local temporal dynamic relationship between the two. Then, the fine-grained attention weight of each temperature deviation-pipeline flow local temporal semantic association interaction vector is calculated. In this way, by assigning corresponding attention weights to each interaction vector, a higher weight can be adaptively assigned to the key local temporal interaction features to highlight their importance, which helps to enhance the model's perception and understanding of the local dynamic relationship between temperature deviation and pipeline flow. Furthermore, the weight is sparsely processed by inputting each fine-grained attention weight into the random dropout module. It should be understood that random dropout will randomly mask some features and retain the most critical and important interaction feature information. Finally, by using the deactivated features as weights to perform weighted summation on the sequence of temperature deviation-pipeline flow local temporal semantic association interaction vectors, the key temporal interaction features can be highlighted, the model's perception of local dynamic relationships can be enhanced, and the temperature deviation-pipeline flow temporal semantic interaction fusion feature vector containing global temporal interaction feature information can be obtained. In this way, compared with global feature fusion, the local interaction fusion network based on feature fine-grained decoupling can focus on the dynamic relationship between temperature deviation and pipeline flow in a specific time period. This local modeling helps to capture instantaneous changes more accurately, thereby improving the responsiveness to real-time control.
[0039] Accordingly, if Figure 3As shown, the temperature deviation-pipeline flow local interaction module 450 includes: a feature decoupling unit 451, which is used to perform feature decoupling on the temperature deviation time series feature vector and the pipeline flow time series feature vector to obtain a sequence of temperature deviation local time series feature vectors and a sequence of pipeline flow local time series feature vectors; a temperature deviation-pipeline flow local time series semantic association interaction unit 452, which is used to calculate the local semantic association interaction vector between each group of corresponding temperature deviation local time series feature vectors and pipeline flow local time series feature vectors in the sequence of temperature deviation local time series feature vectors and the sequence of pipeline flow local time series feature vectors to obtain a sequence of temperature deviation-pipeline flow local time series semantic association interaction vectors; a temperature deviation-pipeline flow local time series fine-grained attention weight calculation unit 453, which is used to calculate the The fine-grained attention weights of each temperature deviation-pipeline flow local time series semantic association interaction vector in the sequence of temperature deviation-pipeline flow local time series semantic association interaction vectors are used to obtain a sequence of temperature deviation-pipeline flow local time series fine-grained attention weights; a deactivation processing unit 454 is used to input the sequence of temperature deviation-pipeline flow local time series fine-grained attention weights into a random deactivation module to obtain a sequence of temperature deviation-pipeline flow local time series fine-grained attention weights after deactivation processing; a weighted sum calculation unit 455 is used to use the sequence of temperature deviation-pipeline flow local time series fine-grained attention weights after deactivation processing as a weight distribution, and calculate the weighted sum of the sequence of temperature deviation-pipeline flow local time series semantic association interaction vectors to obtain the temperature deviation-pipeline flow time series semantic interaction fusion feature vector.
[0040] Among them, the temperature deviation-pipeline flow local time series semantic association interaction unit 452 is used to: respectively calculate the position difference, position dot multiplication and position addition between the temperature deviation local time series feature vector and the pipeline flow local time series feature vector to obtain the temperature deviation-pipeline flow local time series difference vector, the temperature deviation-pipeline flow local time series dot product vector and the temperature deviation-pipeline flow local time series sum vector; cascade the temperature deviation-pipeline flow local time series difference vector, the temperature deviation-pipeline flow local time series dot product vector and the temperature deviation-pipeline flow local time series sum vector, and then perform one-dimensional convolution encoding to obtain the temperature deviation-pipeline flow local time series multi-dimensional fusion vector; perform local window-based maximum pooling processing on the temperature deviation-pipeline flow local time series multi-dimensional fusion vector to obtain the temperature deviation-pipeline flow local time series semantic association interaction vector.
[0041] Among them, the temperature deviation-pipeline flow local temporal series fine-grained attention weight calculation unit 453 is used to: multiply each temperature deviation-pipeline flow local temporal series semantic association interaction vector in the sequence of the temperature deviation-pipeline flow local temporal series semantic association interaction vector by the weight matrix, and then add the obtained vector and the bias vector by position to obtain a sequence of temperature deviation-pipeline flow local temporal series semantic association interaction modulation vectors; input the sequence of temperature deviation-pipeline flow local temporal series semantic association interaction modulation vectors into the tanh function for activation processing to obtain a sequence of temperature deviation-pipeline flow local temporal series semantic association interaction activation vectors; multiply each temperature deviation-pipeline flow local temporal series semantic association interaction activation vector in the sequence of temperature deviation-pipeline flow local temporal series semantic association interaction activation vectors by the weight coefficient vector to obtain a sequence of temperature deviation-pipeline flow local temporal series fine-grained attention weights.
[0042] In one example, the temperature deviation-pipeline flow local interaction module 450 is used to: process the temperature deviation time series feature vector and the pipeline flow time series feature vector through a local interaction fusion network based on feature fine-grained decoupling, using the following interaction fusion formula to obtain the temperature deviation-pipeline flow time series semantic interaction fusion feature vector; wherein the interaction fusion formula is: ;in, and are respectively the temperature deviation time series characteristic vector and the pipeline flow time series characteristic vector, For feature decoupling operations, and are respectively the sequence of the temperature deviation local time series feature vector and the sequence of the pipeline flow local time series feature vector. The local time series characteristic vector of the temperature deviation and the The local time series characteristic vector of the pipeline flow, represents the number of feature vectors in the sequence of the temperature deviation local time series feature vector and the sequence of the pipeline flow local time series feature vector, and They are The temperature deviation local time series feature vector and the pipeline flow local time series feature vector, , and They are position difference, position dot multiplication and position addition respectively. For cascade processing, is a one-dimensional convolutional coding operation, is the maximum pooling operation, is the first in the sequence of the temperature deviation-pipeline flow local temporal semantic association interaction vector Temperature deviation-pipeline flow local time series semantic association interaction vector, is the weight matrix, is the bias vector, is the tanh function, is the weight coefficient vector, is the first in the sequence of the temperature deviation-pipeline flow local time series fine-grained attention weight Temperature deviation-pipeline flow local time series fine-grained attention weight, Indicates deactivation processing, is the first in the sequence of temperature deviation-pipeline flow local time series fine-grained attention weight after the deactivation process Temperature deviation after deactivation processing - fine-grained attention weight of local time series of pipeline flow, It is the temperature deviation-pipeline flow time series semantic interaction fusion feature vector.
[0043] Then, the temperature deviation-pipeline flow time series semantic interaction fusion feature vector is passed through a decoder-based water mixing pump controller to obtain a recommended control decoding value of the water mixing pump speed, and based on the recommended control decoding value of the water mixing pump speed, the pipeline flow of the water mixing system is controlled. That is, the temperature deviation-pipeline flow time series semantic interaction fusion feature vector obtained by local fine-grained interactive fusion of the temperature deviation time series feature vector and the pipeline flow time series feature vector is decoded and processed to intelligently recommend the water mixing pump speed value and control the pipeline flow of the water mixing system. In this way, the system can collect data in real time, and deeply explore and analyze the complex time series dynamic characteristics between temperature and flow in the heating system, so as to intelligently recommend the optimal water mixing pump speed value to accurately control the flow of the water mixing system, thereby improving the intelligence of the hydraulic balance regulation of the heating pipe network.
[0044] Accordingly, if Figure 4 As shown, the mixing water pump speed recommendation module 460 includes: a mixing water pump control unit 461, which is used to pass the temperature deviation-pipeline flow time series semantic interaction fusion feature vector through a decoder-based mixing water pump controller to obtain a recommended control decoding value of the mixing water pump speed; a control unit 462, which is used to control the pipeline flow of the mixing water system based on the recommended control decoding value of the mixing water pump speed.
[0045] In a preferred example, the mixing water pump control unit 461 includes: an optimization subunit, used to optimize the temperature deviation-pipeline flow timing semantic interaction fusion feature vector to obtain an optimized temperature deviation-pipeline flow timing semantic interaction fusion feature vector; a decoding subunit, used to pass the optimized temperature deviation-pipeline flow timing semantic interaction fusion feature vector through the decoder-based mixing water pump controller to obtain a recommended control decoding value of the mixing water pump speed.
[0046] Taking into account that the temperature deviation feature vector and the pipeline flow timing feature vector represent the one-dimensional local timing correlation differential feature of the water supply temperature-return water temperature and the one-dimensional local timing correlation feature of the pipeline flow respectively, therefore, when performing local interactive fusion based on feature fine-grained decoupling, due to the difference in the distribution of timing correlation features caused by the difference in source timing distribution, the temperature deviation-pipeline flow timing semantic interactive fusion feature vector will also have a diversified set expression distribution of timing features based on the fine-grained interactive diversity of feature distribution differences. Therefore, it is expected to improve the overall expression effect of the temperature deviation-pipeline flow timing semantic interactive fusion feature vector based on the diversified set distribution, thereby improving the accuracy of the recommended control decoding value of the mixing water pump speed obtained by the decoder-based mixing water pump controller.
[0047] Based on this, the present application optimizes the temperature deviation-pipeline flow time series semantic interaction fusion feature vector, including the following steps: calculating the sum of the absolute values of each eigenvalue of the temperature deviation-pipeline flow time series semantic interaction fusion feature vector The square root of the sum of squares ,Right now: ;in, The first The eigenvalues at the positions, represents the length of the temperature deviation-pipeline flow time series semantic interaction fusion feature vector, represents the sum of the absolute values of each eigenvalue of the temperature deviation-pipeline flow time series semantic interaction fusion feature vector, Represents the square root of the sum of squares of each eigenvalue of the temperature deviation-pipeline flow time series semantic interaction fusion feature vector.
[0048] Subtract each eigenvalue of the temperature deviation-pipeline flow time series semantic interaction fusion feature vector from After that, take the absolute value and multiply it by the length of the temperature deviation-pipeline flow time series semantic interaction fusion feature vector and The reciprocal of the product is taken to obtain the first temperature deviation-pipeline flow time series semantic interaction fusion intermediate feature vector, and each eigenvalue of the temperature deviation-pipeline flow time series semantic interaction fusion feature vector is subtracted from Then, take the absolute value and multiply it by the length The square root and The reciprocal of the product is taken to obtain the second temperature deviation-pipeline flow time series semantic interaction fusion intermediate feature vector, that is: ;in, The first The eigenvalues at the positions, represents the length of the temperature deviation-pipeline flow time series semantic interaction fusion feature vector, represents the sum of the absolute values of each eigenvalue of the temperature deviation-pipeline flow time series semantic interaction fusion feature vector, represents the square root of the sum of squares of the eigenvalues of the temperature deviation-pipeline flow time series semantic interaction fusion feature vector, The first temperature deviation-pipeline flow time series semantic interaction fusion intermediate feature vector The eigenvalues at the positions, The second temperature deviation-pipeline flow time series semantic interaction fusion intermediate feature vector The feature value at each position.
[0049] Finally, the first temperature deviation-pipeline flow timing semantic interaction fusion intermediate feature vector is subtracted from the dot product of the second temperature deviation-pipeline flow timing semantic interaction fusion intermediate feature vector and the weighted hyperparameter to obtain the optimized temperature deviation-pipeline flow timing semantic interaction fusion feature vector.
[0050] Thus, the difference of the characteristic value of the temperature deviation-pipeline flow time series semantic interaction fusion feature vector relative to the overall feature set of the temperature deviation-pipeline flow time series semantic interaction fusion feature vector is used as the semantic change intensity information, and the phase-like conversion corresponding to the position-based intensity modulation is performed through different and modulation representation forms, so that the aggregation enhancement of the semantic change phase perception can improve the axial aggregation receptive field along the feature aggregation direction by performing the spatial translation operation based on alternating stacking under the feature set scale balance of the temperature deviation-pipeline flow time series semantic interaction fusion feature vector, thereby improving the perception effect of the aggregation semantics of the temperature deviation-pipeline flow time series semantic interaction fusion feature vector on the detail semantic change, so as to improve the overall expression effect of the temperature deviation-pipeline flow time series semantic interaction fusion feature vector, and improve the accuracy of the recommended control decoding value of the mixing pump speed obtained by the mixing pump controller based on the decoder. In this way, the system can collect data in real time, and deeply mine and analyze the complex time series dynamic characteristics between temperature and flow in the heating system, so as to intelligently recommend the optimal mixing pump speed value to accurately control the flow of the mixing system, thereby improving the intelligence of the hydraulic balance regulation of the heating pipe network.
[0051] Based on the above embodiments, see Figure 5 As shown in FIG. 1 , it is a flow chart of a method for adjusting the hydraulic balance of a heating network in an embodiment of the present application. Figure 5 As shown, the hydraulic balance adjustment method for a heating network according to an embodiment of the present application includes the following steps: S510, collecting the water supply temperature through a water supply temperature sensor installed in a water supply pipe of the heating network; S520, collecting the return water temperature through a return water temperature sensor installed in a return water pipe of the heating network; S530, collecting the pipe flow of the mixing water pipe through a pipe flow sensor installed in a mixing water pipe of a mixing water system; S540, communicatively connecting a mixing water flow controller to the water supply temperature sensor, the return water temperature sensor and the pipe flow sensor, and controlling the pipe flow of the mixing water system through the mixing water flow controller.
[0052] Wherein, in step S540, the mixed water flow controller is communicatively connected to the water supply temperature sensor, the return water temperature sensor and the pipeline flow sensor, and the pipeline flow of the mixed water system is controlled by the mixed water flow controller, including: obtaining the time series of the water supply temperature and the time series of the return water temperature; obtaining the time series of the pipeline flow of the mixed water system; regularizing the time series of the water supply temperature, the time series of the return water temperature and the time series of the pipeline flow according to the time dimension, and then obtaining the time series feature vector of the water supply temperature, the time series of the return water temperature and the time series of the pipeline flow through the time series feature extractor to obtain the time series feature vector of the return water temperature and the time series feature vector of the pipeline flow; The invention discloses a method for obtaining a time series feature vector of the water supply temperature and a time series feature vector of the pipeline flow; calculating the difference characteristics between the water supply temperature time series feature vector and the return water temperature time series feature vector to obtain a temperature deviation time series feature vector; passing the temperature deviation time series feature vector and the pipeline flow time series feature vector through a local interactive fusion network based on feature fine-grained decoupling to obtain a temperature deviation-pipeline flow time series semantic interactive fusion feature vector; obtaining a recommended control value of the mixing pump speed based on the temperature deviation-pipeline flow time series semantic interactive fusion feature vector, and controlling the pipeline flow of the mixing water system based on the recommended control value of the mixing pump speed.
[0053] Here, those skilled in the art will appreciate that the specific operations of each step in the above-mentioned heating pipe network hydraulic balance adjustment method have been described in detail above. Figures 1 to 4 The description of the heating pipe network hydraulic balance regulation system 1000 has been introduced in detail, and therefore, its repeated description will be omitted.
[0054] Based on the above embodiments, another exemplary embodiment of an electronic device is also provided in the embodiments of the present application. In some possible implementations, the electronic device in the embodiments of the present application may include a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor can implement the steps of the method for regulating the hydraulic balance of the heating network in the above embodiments when executing the program.
[0055] The embodiment of the present application also provides a computer-readable storage medium, on which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the method for regulating the hydraulic balance of the heating network according to the embodiment of the present application described with reference to the above figures can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may, for example, include a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may, for example, include a read-only memory (ROM), a hard disk, a flash memory, etc.
[0056] The embodiment of the present application also provides a computer program product or a computer program, which includes computer executable instructions, and the computer executable instructions are stored in a computer readable storage medium. The processor of the computer device reads the computer executable instructions from the computer readable storage medium, and the processor executes the computer executable instructions, so that the computer device executes the method for regulating the hydraulic balance of the heating pipe network according to the embodiment of the present application.
[0057] Those skilled in the art will appreciate that the contents disclosed in this application may be subject to various variations and improvements. For example, the various devices or components described above may be implemented by hardware, or by software, firmware, or a combination of some or all of the three.
[0058] In addition, although the present application makes various references to certain units in the system according to embodiments of the present application, any number of different units can be used and run on the client and / or server. The units are only illustrative, and different aspects of the system and method can use different units.
[0059] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of software function modules. The present application is not limited to any particular form of combination of hardware and software.
[0060] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined as such herein.
[0061] The above is an explanation of the present application and should not be considered as limiting thereof. Although several exemplary embodiments of the present application have been described, those skilled in the art will readily appreciate that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present application.
Claims
1. A heating network hydraulic balance regulation system, characterized in that: include: A water supply temperature sensor, a return water temperature sensor, a pipeline flow sensor and a mixed water flow controller; the water supply temperature sensor is installed in the water supply pipe of the heating network to collect the water supply temperature; the return water temperature sensor is installed in the return water pipe of the heating network to collect the return water temperature; the pipeline flow sensor is installed in the mixed water pipe of the mixed water system to collect the pipeline flow of the mixed water pipe; the mixed water flow controller can be communicatively connected to the water supply temperature sensor, the return water temperature sensor and the pipeline flow sensor, and is used to control the pipeline flow of the mixed water system; wherein the mixed water flow controller includes: a water supply and return water temperature acquisition module, which is used to acquire the time series of the water supply temperature and the time series of the return water temperature; a pipeline flow acquisition module, which is used to acquire the time series of the pipeline flow of the mixed water system; a parameter time series feature extraction module, which is used to extract the time series of the water supply temperature, the return water temperature and the pipeline flow sensor; The time series of water temperature and the time series of the pipeline flow are regularized according to the time dimension and then passed through a time series feature extractor to obtain a water supply temperature time series feature vector, a return water temperature time series feature vector and a pipeline flow time series feature vector; a temperature deviation calculation module is used to calculate the difference characteristics between the water supply temperature time series feature vector and the return water temperature time series feature vector to obtain a temperature deviation time series feature vector; a temperature deviation-pipeline flow local interaction module is used to fuse the temperature deviation time series feature vector and the pipeline flow time series feature vector through a local interaction fusion network based on feature fine-grained decoupling to obtain a temperature deviation-pipeline flow time series semantic interaction fusion feature vector; a mixing pump speed recommendation module is used to obtain a recommended control value of the mixing pump speed based on the temperature deviation-pipeline flow time series semantic interaction fusion feature vector, and control the pipeline flow of the mixing water system based on the recommended control value of the mixing pump speed.
2. The heating network hydraulic balance regulation system according to claim 1, characterized in that: The parameter time series feature extraction module is used to: perform data regularization on the time series of the water supply temperature, the time series of the return water temperature and the time series of the pipeline flow according to the time dimension, and then pass them through a time series feature extractor based on a deep convolutional neural network to obtain the water supply temperature time series feature vector, the return water temperature time series feature vector and the pipeline flow time series feature vector.
3. The heating network hydraulic balance regulation system according to claim 2, characterized in that: The temporal feature extractor based on deep convolutional neural network is a temporal feature extractor based on 1D-CNN.
4. The heating network hydraulic balance regulation system according to claim 3, characterized in that: The temperature deviation calculation module is used to calculate the position difference between the water supply temperature time series characteristic vector and the return water temperature time series characteristic vector to obtain the temperature deviation time series characteristic vector.
5. The heating network hydraulic balance regulation system according to claim 4, characterized in that: The temperature deviation-pipeline flow local interaction module includes: a feature decoupling unit, which is used to perform feature decoupling on the temperature deviation time series feature vector and the pipeline flow time series feature vector to obtain a sequence of temperature deviation local time series feature vectors and a sequence of pipeline flow local time series feature vectors; a temperature deviation-pipeline flow local time series semantic association interaction unit, which is used to calculate the local semantic association interaction vector between each group of corresponding temperature deviation local time series feature vectors and pipeline flow local time series feature vectors in the sequence of temperature deviation local time series feature vectors and the sequence of pipeline flow local time series feature vectors to obtain a sequence of temperature deviation-pipeline flow local time series semantic association interaction vectors; a temperature deviation-pipeline flow local time series fine-grained attention weight calculation unit, which is used to calculate the temperature deviation -The fine-grained attention weights of each temperature deviation-pipeline flow local time series semantic association interaction vector in the sequence of pipeline flow local time series semantic association interaction vectors to obtain a sequence of temperature deviation-pipeline flow local time series fine-grained attention weights; an inactivation processing unit, which is used to input the sequence of temperature deviation-pipeline flow local time series fine-grained attention weights into a random inactivation module to obtain a sequence of temperature deviation-pipeline flow local time series fine-grained attention weights after inactivation processing; a weighted sum calculation unit, which is used to use the sequence of temperature deviation-pipeline flow local time series fine-grained attention weights after inactivation processing as a weight distribution, and calculate the weighted sum of the sequence of temperature deviation-pipeline flow local time series semantic association interaction vectors to obtain the temperature deviation-pipeline flow time series semantic interaction fusion feature vector.
6. The heating network hydraulic balance regulation system according to claim 5, characterized in that: The temperature deviation-pipeline flow local time series semantic association interaction unit is used to: respectively calculate the position difference, position point multiplication and position addition between the temperature deviation local time series feature vector and the pipeline flow local time series feature vector to obtain the temperature deviation-pipeline flow local time series difference vector, the temperature deviation-pipeline flow local time series point product vector and the temperature deviation-pipeline flow local time series sum vector; cascade the temperature deviation-pipeline flow local time series difference vector, the temperature deviation-pipeline flow local time series point product vector and the temperature deviation-pipeline flow local time series sum vector, and perform one-dimensional convolution encoding to obtain the temperature deviation-pipeline flow local time series multi-dimensional fusion vector; perform local window-based maximum pooling processing on the temperature deviation-pipeline flow local time series multi-dimensional fusion vector to obtain the temperature deviation-pipeline flow local time series semantic association interaction vector.
7. The heating network hydraulic balance regulation system according to claim 6, characterized in that: The temperature deviation-pipeline flow local temporal sequence fine-grained attention weight calculation unit is used to: multiply each temperature deviation-pipeline flow local temporal sequence semantic association interaction vector in the sequence of the temperature deviation-pipeline flow local temporal sequence semantic association interaction vector by a weight matrix, and then add the obtained vector and the bias vector by position to obtain a sequence of temperature deviation-pipeline flow local temporal sequence semantic association interaction modulation vectors; input the sequence of temperature deviation-pipeline flow local temporal sequence semantic association interaction modulation vectors into a tanh function for activation processing to obtain a sequence of temperature deviation-pipeline flow local temporal sequence semantic association interaction activation vectors; multiply each temperature deviation-pipeline flow local temporal sequence semantic association interaction activation vector in the sequence of temperature deviation-pipeline flow local temporal sequence semantic association interaction activation vectors by a weight coefficient vector to obtain a sequence of temperature deviation-pipeline flow local temporal sequence fine-grained attention weights.
8. The heating network hydraulic balance regulation system according to claim 7, characterized in that: The mixing water pump speed recommendation module includes: a mixing water pump control unit, which is used to pass the temperature deviation-pipeline flow temporal semantic interaction fusion feature vector through a decoder-based mixing water pump controller to obtain a recommended control decoding value of the mixing water pump speed; a control unit, which is used to control the pipeline flow of the mixing water system based on the recommended control decoding value of the mixing water pump speed.
9. A method for regulating the hydraulic balance of a heating network, characterized in that: include: The water supply temperature is collected by a water supply temperature sensor installed in the water supply pipe of the heating network; The return water temperature is collected by a return water temperature sensor installed in the return water pipe of the heating network; the pipe flow rate of the mixing water pipe is collected by a pipe flow sensor installed in the mixing water pipe of the mixing water system; a mixing water flow controller is communicatively connected to the supply water temperature sensor, the return water temperature sensor and the pipe flow sensor, and the pipe flow rate of the mixing water system is controlled by the mixing water flow controller; wherein, controlling the pipe flow rate of the mixing water system by the mixing water flow controller includes: obtaining a time series of the supply water temperature and a time series of the return water temperature; obtaining a time series of the pipe flow rate of the mixing water system; and comparing the time series of the supply water temperature, the time series of the return water temperature and the time series of the pipe flow rate After the sequence is regularized according to the time dimension, it is passed through a time series feature extractor to obtain a water supply temperature time series feature vector, a return water temperature time series feature vector and a pipeline flow time series feature vector; the difference feature between the water supply temperature time series feature vector and the return water temperature time series feature vector is calculated to obtain a temperature deviation time series feature vector; the temperature deviation time series feature vector and the pipeline flow time series feature vector are passed through a local interactive fusion network based on feature fine-grained decoupling to obtain a temperature deviation-pipeline flow time series semantic interactive fusion feature vector; based on the temperature deviation-pipeline flow time series semantic interactive fusion feature vector, a recommended control value of the mixing pump speed is obtained, and based on the recommended control value of the mixing pump speed, the pipeline flow of the mixing water system is controlled.
Citation Information
Patent Citations
Intelligent heat supply network integrated system and control method thereof
CN104048347A
Mixed water direct heat supply operation system
CN106287897A
Heat supply pipe network adjusting method and system
CN106895478A
Classified water mixing pump user unit
CN109506282A
Heat supply pipe network hydraulic regulation and control system and intelligent control and heat supply charging method thereof
CN111578368A
Cited By
Power factor adaptive control method for charging system
CN119209585A
Power factor improvement control method for charging system
CN119209586A
Heat adjusting system and adjusting method of dynamic balance type intelligent heat meter
CN121297096A
Heating and / or cooling apparatus
GB2704437A
Method for regulating coolant flow and system for implementing method for regulating coolant flow
RU2859257C1
