Method and device for determining opening degree of valve, storage medium, electronic device and computer program product

Abstract

The invention discloses a method and device for determining the opening degree of a valve, a storage medium, an electronic device and a computer program product, and relates to the field of computers.The method for determining the opening degree of the valve comprises the steps that N target thermal load values are determined, the ith target thermal load value in the N target thermal load values is used for indicating the total amount of heat which needs to be received from the outside by the ith unit building when the indoor temperature of the ith unit building in the N unit buildings is maintained at the target temperature; n unit operation models are determined; the electric adjusting valve of the ith unit building is used for adjusting the flow of liquid flowing through the heat distribution pipeline of the ith unit building; through the N unit operation models, N sets of data are determined according to the N target heat load values and the target water supply temperature, and the ith set of data in the N sets of data comprises the target valve opening degree and the target water return temperature of an electric adjusting valve of the ith unit building; the water supply temperature of the N unit buildings is the target water supply temperature.

Description

Technical Field

[0001] The present application relates to the field of computers, and more specifically, to a method and device for determining a valve opening, a storage medium, an electronic device, and a computer program product. Background Art

[0002] As a basic livelihood guarantee project in my country, heating is related to the vital interests of the people. In recent years, complaints due to substandard heating quality have been common, which has also brought huge challenges to relevant heating practitioners. How to achieve high-efficiency energy utilization of heating systems and reduce operating energy consumption has become a topic worthy of in-depth exploration.

[0003] Taking the heat exchange station as an example, the current monitoring system mainly monitors operating parameters, and the operation control method is mainly feedback control combined with manual experience adjustment. The control object is mostly the heat exchange station level, and feedback control mostly uses climate compensation prediction method, lacking technology and system for precise control on demand. Since feedback control is a process of continuous iteration, comparison, and control, it has the inherent characteristic of response delay. Therefore, the system cannot accurately provide heat on demand. Due to the above characteristics of the existing secondary heating system and the limited energy of the heat exchange station staff, many heat exchange stations basically do not make real-time adjustments at the unit building level, resulting in limited control optimization and energy-saving potential.

[0004] With regard to the problem in related technologies that the heating system cannot be controlled to provide precise heating to unit buildings according to the actual needs of the unit buildings, no effective solution has been proposed so far.

[0005] Therefore, it is necessary to improve the related technology to overcome the above-mentioned defects in the related technology. Summary of the invention

[0006] The embodiments of the present application provide a method and device for determining a valve opening, a storage medium, an electronic device, and a computer program product to at least solve the problem of being unable to control a heating system to accurately heat a unit building according to the actual needs of the unit building.

[0007] According to one aspect of an embodiment of the present application, a method for determining a valve opening is provided, comprising: determining N target heat load values, wherein the i-th target heat load value among the N target heat load values ​​is used to indicate the total amount of heat that the i-th unit building needs to receive from the outside when the indoor temperature of the i-th unit building among the N unit buildings is maintained at the target temperature, N is an integer greater than or equal to 2, and i is an integer greater than or equal to 1 and less than or equal to N; and determining N unit operation models, wherein the i-th unit operation model is used to reflect the water supply temperature, The relationship between the return water temperature and the valve opening of the electric regulating valve and the heat load value of the i-th unit building; the electric regulating valve of the i-th unit building is used to adjust the flow rate of the liquid flowing through the thermal pipeline of the i-th unit building; through the N unit operation model, N groups of data are determined according to the N target heat load values ​​and the target water supply temperature, wherein the i-th group of data in the N groups of data includes the target valve opening and the target return water temperature of the electric regulating valve of the i-th unit building; the water supply temperature of the N unit buildings is the target water supply temperature.

[0008] In an exemplary embodiment, determining N target heat load values ​​includes: determining the ith target heat load value in the following manner to determine the N target heat load values: predicting the predicted heat load value of the ith unit building at the next moment of the historical time series according to the time series data corresponding to the ith unit building in the historical time series through the heat load prediction model of the ith unit building, wherein the time series data includes target data corresponding to each historical moment in the historical time series, and the target data includes: water supply temperature, return water temperature, flow rate of liquid flowing through the thermal pipeline of the ith unit building, and indoor temperature; correcting the predicted heat load value according to the average indoor temperature corresponding to the time series data and the target temperature to obtain the ith target heat load value.

[0009] In an exemplary embodiment, the predicted heat load value is corrected according to the average indoor temperature and the target temperature corresponding to the time series data to obtain the i-th target heat load value, including: dividing the target temperature by the average indoor temperature to obtain a first value; multiplying the first value by the predicted heat load value to obtain the i-th target heat load value.

[0010] In an exemplary embodiment, the method further includes: acquiring first training data, wherein the first training data includes multiple groups of first data, wherein each group of the multiple groups of first data includes: time series data corresponding to the i-th unit building in the sample historical time series, and the predicted heat load value of the i-th unit building at the next moment of the sample historical time series; training a general LSTM model based on the training data until the general LSTM model meets preset conditions, and determining the general LSTM model that meets the preset conditions as the heat load prediction model of the i-th unit building.

[0011] In an exemplary embodiment, the preset conditions include: the mean square error MAE value of the general LSTM model is less than a first preset threshold, and the goodness of fit R2 value of the general LSTM model is greater than a second preset threshold.

[0012] In an exemplary embodiment, the method further includes: obtaining the i-th unit operation model by: acquiring second training data, wherein the second training data includes multiple groups of second data, wherein each group of the multiple groups of second data includes: sample data, and the heat load value of the i-th unit building corresponding to the sample data, and the sample data includes: the water supply temperature, the return water temperature and the valve opening of the electric regulating valve of the i-th unit building; training the general recurrent neural network model based on the second training data until the general recurrent neural network model meets the convergence condition, and determining the general recurrent neural network model that meets the convergence condition as the i-th unit operation model.

[0013] According to another aspect of an embodiment of the present application, a device for determining a valve opening is further provided, comprising: a first determination module, for determining N target heat load values, wherein the i-th target heat load value among the N target heat load values ​​is used to indicate the total amount of heat that the i-th unit building needs to receive from the outside when the indoor temperature of the i-th unit building among the N unit buildings is maintained at the target temperature, N is an integer greater than or equal to 2, and i is an integer greater than or equal to 1 and less than or equal to N; a second determination module, for determining N unit operation models, wherein the i-th unit operation model is used to reflect the i-th unit building the relationship between the water supply temperature, the return water temperature and the valve opening of the electric regulating valve and the heat load value of the i-th unit building; the electric regulating valve of the i-th unit building is used to adjust the flow rate of the liquid flowing through the thermal pipeline of the i-th unit building; a third determination module is used to determine N groups of data according to the N target heat load values ​​and the target water supply temperature through the N unit operation model, wherein the i-th group of data in the N groups of data includes the target valve opening and target return water temperature of the electric regulating valve of the i-th unit building; the water supply temperature of the N unit buildings is the target water supply temperature.

[0014] According to another aspect of the embodiment of the present application, a computer-readable storage medium is further provided, wherein the computer-readable storage medium includes a stored program, wherein the program is configured to execute the above-mentioned method for determining the valve opening when running.

[0015] According to another aspect of the embodiment of the present application, there is also provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, wherein the processor is configured to execute the above-mentioned method for determining the valve opening through the computer program.

[0016] According to another aspect of the embodiment of the present application, a computer program product is also provided, including a computer program, and the computer program performs the above-mentioned method for determining the valve opening when executed by a processor.

[0017] This application confirms the total amount of heat that the unit building needs to receive from the outside to maintain the indoor temperature at the target temperature and the unit operation model used to reflect the relationship between the unit building's water supply temperature, return water temperature, and the valve opening of the electric regulating valve and the heat load value, thereby using the unit operation model to confirm the valve opening of the electric regulating valve and the target return water temperature according to the confirmed total amount of heat and the target water supply temperature. Since the valve opening and return water temperature are determined by the model based on the actual amount of heat required to maintain the indoor temperature of the unit building, the heating efficiency of the heating system and the accuracy of the heating parameters are improved, thereby solving the problem of being unable to control the heating system to accurately heat the unit building according to the actual needs of the unit building. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0020] Figure 1 It is a hardware structure block diagram of a mobile terminal of a method for determining a valve opening according to an embodiment of the present application;

[0021] Figure 2 is a flow chart of a method for determining a valve opening according to an embodiment of the present application;

[0022] Figure 3 It is a structural block diagram of a device for determining a valve opening according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 11 is a hardware structure block diagram of a mobile terminal of a method for determining a valve opening according to an embodiment of the present application. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor (MP) or a programmable logic device (FPGA)) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0026] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for detecting pneumatic imbalance in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0027] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0028] In order to solve the above problem, a method for determining a valve opening is provided in this embodiment. The execution subject is a valve opening determination system, including but not limited to being applied to the above mobile terminal. Figure 2is a flow chart of a method for determining a valve opening according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps S202 to S206:

[0029] Step S202: determining N target heat load values, wherein the i-th target heat load value among the N target heat load values ​​is used to indicate the total amount of heat that the i-th unit building needs to receive from the outside when the indoor temperature of the i-th unit building among the N unit buildings is maintained at the target temperature, N is an integer greater than or equal to 2, and i is an integer greater than or equal to 1 and less than or equal to N;

[0030] Optionally, the valve opening determination system first needs to determine the target heat load value of each of the N unit buildings. This step uses the Long Short-Term Memory (LSTM) model to predict the heat demand of each unit at the target room temperature by analyzing historical data and current environmental conditions (such as outdoor temperature, humidity, etc.). These predicted values ​​are then used in the subsequent optimization and adjustment process to ensure that each unit receives appropriate heat supply according to its actual needs.

[0031] Step S204: determining N unit operation models, wherein the i-th unit operation model is used to reflect the relationship between the water supply temperature, return water temperature and valve opening of the electric regulating valve of the i-th unit building and the heat load value of the i-th unit building; the electric regulating valve of the i-th unit building is used to adjust the flow rate of the liquid flowing through the thermal pipeline of the i-th unit building;

[0032] Optionally, the operation model of the N unit buildings describes the relationship between the supply water temperature, return water temperature, and the opening of the electric regulating valve and the heat load value of the unit building. By using a recurrent neural network (RNN) model to establish the unit operation model, the valve opening determination system can learn the relationship between these parameters, and even when the supply water temperature is consistent, it can predict the change of heat load of each unit caused by different valve openings.

[0033] Step S206: running the model through the N units, determining N groups of data according to the N target heat load values ​​and the target water supply temperature, wherein the i-th group of data in the N groups of data includes the target valve opening and target return water temperature of the electric regulating valve of the i-th unit building; the water supply temperature of the N unit buildings is the target water supply temperature.

[0034] Optionally, step S206 uses N units to run the model, combines N target heat load values ​​and target water supply temperatures, and calculates the target valve opening and target return water temperature of the electric regulating valve required for each unit building. This process is directly obtained through the calculation of the model without manual participation, ensuring the accuracy and timeliness of the adjustment parameters.

[0035] It should be noted that the system can automatically calculate the valve opening and return water temperature of each unit, realize automatic adjustment of the heating system, reduce manual intervention and improve operational efficiency. In addition, although the water supply temperature of all units is the same, by adjusting the opening of different valves and return water temperature, differentiated heating can be achieved for each unit, better meeting the heat demand of different units and improving overall energy efficiency.

[0036] It should be noted that the above steps achieve accurate prediction and automatic adjustment of the heating system by introducing advanced data analysis models. It can not only provide personalized services according to the specific needs of each unit, but also significantly improve the system's energy utilization efficiency and user comfort, and reduce the operating cost and environmental impact of the heating system.

[0037] The above steps confirm the total amount of heat that the unit building needs to receive from the outside to maintain the indoor temperature at the target temperature and the unit operation model used to reflect the relationship between the unit building's water supply temperature, return water temperature, and the valve opening of the electric regulating valve and the heat load value, thereby using the unit operation model to confirm the valve opening of the electric regulating valve and the target return water temperature according to the confirmed total amount of heat and the target water supply temperature. Since the valve opening and return water temperature are determined by the model based on the actual amount of heat required to maintain the indoor temperature of the unit building, the heating efficiency of the heating system and the accuracy of the heating parameters are improved, thereby solving the problem of being unable to control the heating system to accurately heat the unit building according to the actual needs of the unit building.

[0038] In an exemplary embodiment, determining N target heat load values ​​may be achieved by the following steps: determining the i-th target heat load value by the following steps S11-S12 to determine the N target heat load values:

[0039] Step S11: using the heat load prediction model of the i-th unit building, predicting the predicted heat load value of the i-th unit building at the next moment of the historical time series according to the time series data corresponding to the i-th unit building in the historical time series, wherein the time series data includes target data corresponding to each historical moment in the historical time series, and the target data includes: water supply temperature, return water temperature, flow rate of liquid flowing through the thermal pipeline of the i-th unit building, and indoor temperature;

[0040] Optionally, the heat load prediction model is a LSTM model.

[0041] It should be noted that the LSTM model is a special recurrent neural network (RNN) architecture. By introducing memory units and gating mechanisms (input gate, forget gate, and output gate), it can effectively learn and utilize long-term dependency information, and is particularly suitable for processing sequence data.

[0042] Optionally, in this step, the system uses the heat load prediction model for the i-th unit building to analyze the time series data in the historical time series to predict the heat load demand of the unit building at the next moment. The time series data includes multiple parameters at historical moments, such as supply water temperature, return water temperature, liquid flow through the thermal pipes of the unit building, and indoor temperature. Due to its advantages in processing time series data, the LSTM model can capture the pattern of changes in these parameters over time, thereby making more accurate predictions.

[0043] Optionally, for example, the temperature sensor, pressure sensor, resident room temperature and other data at the thermal inlet of the i-th unit building unit are read once every 10 minutes. In order to avoid the interference of distorted data and missing data on modeling, the acquired historical data are preprocessed, and the K-means clustering algorithm is used to determine the outliers and use the previous and next means to replace and fill them. Data that is missing for 6 consecutive hours is directly deleted, and data that obviously violates common sense is directly deleted, such as secondary heating is lower than the return temperature.

[0044] Alternatively, assume that the target data of the i-th unit building at four moments in the historical time series are obtained, and the five moments are t 1 , t 2 , t 3 , t 4 , then the heat load prediction model will predict t 5 The predicted heat load value of the i-th unit building at time t 5 and t 4 The time interval is equal to t 4 and t 3 The time interval is equal to t 3 and t 2 The time interval is equal to t 2 and t 1 time interval.

[0045] It should be noted that predicting future heat loads based on historical data allows the heating system to prepare in advance to avoid insufficient or excessive heating. In addition, relying on data prediction rather than manual experience reduces the uncertainty of human factors and makes decision-making more scientific and reasonable.

[0046] Step S12: Correcting the predicted heat load value according to the average indoor temperature corresponding to the time series data and the target temperature to obtain the i-th target heat load value.

[0047] It should be noted that the predicted heat load value is not the final target heat load value. The system needs to make corrections based on the average indoor temperature corresponding to the time series data and the preset target temperature (the temperature that the unit building wants to reach indoors). This is because the predicted value may be affected by changes in external environmental conditions and deviate from actual demand. By comparing the average indoor temperature with the target temperature, the system can adjust the heat load value to ensure that the indoor temperature can be stabilized within a more accurate target range.

[0048] It should be noted that through correction, the heat supply can be accurately matched to user needs, resource waste can be avoided, and energy efficiency can be improved. The corrected heat load value is closer to the actual needs of users, and can maintain the indoor temperature within the target range, thereby improving living comfort.

[0049] It should be noted that, through step S12, the system can dynamically adjust the heat load demand according to the actual indoor temperature, thereby improving the adaptability to environmental changes.

[0050] It should be noted that the above steps combine advanced data analysis models with the correction mechanism of actual needs, which can achieve accurate prediction and fine-tuning of the heat load demand of each unit building in the heating system. This model not only improves the energy efficiency and user satisfaction of the system, but also responds to changes in the environment and user needs in real time, and realizes intelligent and automated management of the heating system. Through data-driven methods, operating costs are reduced, energy waste is reduced, and there is also a positive contribution to environmental protection.

[0051] In an exemplary embodiment, the predicted heat load value is corrected according to the average indoor temperature corresponding to the time series data and the target temperature to obtain the i-th target heat load value, which can be achieved by the following steps S21-S22:

[0052] Step S21: Divide the target temperature by the average indoor temperature to obtain a first value;

[0053] Optionally, the system divides the preset target temperature by the average indoor temperature calculated from historical data to obtain a first value. This first value actually reflects the proportional relationship between the indoor temperature and the target temperature expected by the user, that is, the difference between the indoor temperature and the target temperature. If the average indoor temperature is lower than the target temperature, the first value will be greater than 1, which means that the heat load needs to be increased to increase the temperature; conversely, if the average indoor temperature is higher than the target temperature, the first value will be less than 1, which means that the heat load needs to be reduced to lower the temperature.

[0054] It should be noted that by calculating the first value, the concept of proportional control is introduced, so that the system can automatically adjust the heat load according to the difference between the actual temperature and the target temperature, thereby improving the accuracy of the adjustment.

[0055] Step S22: multiplying the first value by the predicted heat load value to obtain the i-th target heat load value.

[0056] Optionally, the following formula is used to correct the predicted value to obtain the i-th target heat load value that better meets the actual demand. In this way, the system can dynamically adjust the predicted heat load value to ensure that the heating amount can be increased or decreased according to the actual demand of the room temperature, so as to achieve the target temperature:

[0057]

[0058] Among them, P f is the i-th target heat load value, P is the predicted heat load value, is the first value, T target is the target temperature, T in is the average indoor temperature.

[0059] It should be noted that the corrected target heat load value can more accurately match the actual heat demand of each unit, reduce overheating or underheating, and improve user comfort. By adjusting the heat load value on demand, energy waste caused by excessive heating is avoided, energy optimization configuration is achieved, and the overall energy efficiency of the system is improved. Moreover, this process is completely completed automatically by the system without manual intervention, which improves the convenience of operation and the degree of automation of the system.

[0060] It should be noted that through the above steps, the system can automatically adjust the heat load demand of each unit according to the difference between the real-time monitored indoor temperature and the preset target temperature, thus realizing the precise and automatic distribution of heat load. This heat load correction mechanism based on real-time feedback and proportional control not only improves user satisfaction and living comfort, but also significantly improves the energy efficiency of the system and reduces unnecessary energy consumption. It is an important step in the intelligent upgrade of the heating system.

[0061] In an exemplary embodiment, the method further comprises the following steps S31-S32:

[0062] Step S31: Acquire first training data, wherein the first training data includes multiple groups of first data, wherein each group of the multiple groups of first data includes: time series data corresponding to the i-th unit building in the sample historical time series, and the predicted heat load value of the i-th unit building at the next moment of the sample historical time series;

[0063] Optionally, each set of first data records the operating parameters of the i-th unit building at the corresponding moment of the sample historical time series and the heat load value at the current moment, as well as the predicted heat load value at the next moment. The time series data includes parameters such as supply water temperature, return water temperature, valve opening, etc., while the heat load value is calculated based on actual measurement or user feedback (such as indoor temperature).

[0064] It should be noted that each set of data collected reflects the characteristics of a specific unit building and helps to generate a personalized prediction model that can accurately reflect the changes in the unit's thermal demand.

[0065] Step S32: training the general LSTM model based on the training data until the general LSTM model meets preset conditions, and determining the general LSTM model that meets the preset conditions as the heat load prediction model of the i-th unit building.

[0066] In an exemplary embodiment, the preset conditions include: the mean square error MAE value of the general LSTM model is less than a first preset threshold, and the goodness of fit R2 value of the general LSTM model is greater than a second preset threshold.

[0067] It should be noted that the Mean Absolute Error (MAE) and the R2 value are two key indicators for evaluating the difference between the heat load value predicted by the model and the actual heat load value. The MAE measures the absolute size of the prediction error, and the R2 value reflects the ability of the model to explain the variability of the data.

[0068] Optionally, the maximum number of iterations when training the model is 100 times, and the heat load prediction result is evaluated by the mean square error MAE and the goodness of fit R2. The smaller the MAE value is and the closer the R2 is to 1, the better the heat load prediction result is.

[0069] Optionally, once the MAE value of the model is lower than the first preset threshold and the R2 value is higher than the second preset threshold, it indicates that the model has high accuracy and good fitting effect in predicting the heat load. At this time, the model is considered to be trained and is determined as the heat load prediction model for the i-th unit building.

[0070] It should be noted that by setting the thresholds of MAE and R2 values, it is ensured that the model has sufficiently high accuracy and explanatory power when predicting heat load, so that it can be reliably used in actual heating regulation. The model can more effectively guide heat load regulation, reduce unnecessary energy consumption, and improve the operating efficiency of the entire heating system.

[0071] It should be noted that, through the above steps, this embodiment can generate a high-precision heat load prediction model for a specific unit building, which can predict future heat load demand based on historical data, and then guide the automatic adjustment of the heating system. This not only improves the intelligence level of the heating system, but also effectively optimizes energy distribution, reduces operating costs, and ensures the user's comfortable experience, demonstrating the advancement and practicality of data-driven modern heating control systems.

[0072] In an exemplary embodiment, the method further comprises the following steps: obtaining the i-th unit operation model through the following steps S41-S42:

[0073] Step S41: acquiring second training data, wherein the second training data includes a plurality of groups of second data, wherein each group of the plurality of groups of second data includes: sample data, and a heat load value of the i-th unit building corresponding to the sample data, wherein the sample data includes: a water supply temperature, a return water temperature, and a valve opening of an electric regulating valve of the i-th unit building;

[0074] It should be noted that the second training data consists of multiple sets of second data, each set of data includes the operating parameters of the i-th unit building at a specific time point (such as supply water temperature, return water temperature and valve opening), and the heat load value at the corresponding time point. These data are intended to capture the operating status of the heating system under different conditions, and the relationship between these status and the heat load of the unit building.

[0075] It should be noted that by collecting sample data including operating parameters and heat load, it is possible to analyze and understand the dynamic relationship between the two, providing a basis for model training.

[0076] Step S42: training the general recurrent neural network model based on the second training data until the general recurrent neural network model meets the convergence condition, and determining the general recurrent neural network model that meets the convergence condition as the i-th unit operation model.

[0077] Optionally, the RNN model is used to establish the unit operation model P f =f(t g , t h , k), where P f is the heat load value, t g is the unit water supply temperature, t h is the unit return water temperature, k is the valve opening. The operation models P of different units in the same heat exchange station are established in sequence. f1 , P f2 ,…,P fn (n is the number of units).

[0078] Optionally, the training process will continue until the model meets the convergence condition, that is, the performance indicators of the model (such as the loss function) no longer change significantly after multiple training cycles, indicating that the model has learned the patterns in the data and reached the optimal state. Once the model meets the convergence condition, it will be determined as the running model for the i-th unit building.

[0079] It should be noted that through the above training process, the model can capture the unique correlation between the operating parameters of a specific unit building and the heat load, realize the establishment of a personalized operation model, ensure that the model converges during the training process, and help improve the accuracy and stability of the model in predicting the relationship between the operating parameters of the heating system and the heat load.

[0080] It should be noted that, through the above steps, this embodiment can construct a high-precision operation model for the i-th unit building. The model is based on a recurrent neural network and can effectively understand and predict the heat load of the heating system under different operating parameters. This not only improves the intelligence level of the heating system, but also can accurately control the heat supply and reduce energy waste by adjusting the water supply temperature, return water temperature and valve opening in real time, while optimizing the indoor temperature and improving user comfort, demonstrating the efficiency and intelligence of modern heating control systems.

[0081] Obviously, the above-described embodiments are only embodiments of a part of the present invention, rather than all embodiments. In order to better understand the above method, the above process is described below in conjunction with embodiments, but it is not intended to limit the technical solutions of the embodiments of the present invention, specifically:

[0082] Step 1: Establish unit load prediction model;

[0083] The electric regulating valves, temperature and pressure sensors, and residents' room temperatures at the thermal entrances of the community unit building units are read every 10 minutes. In order to avoid the interference of distorted data and missing data on modeling, the acquired historical data are preprocessed, and the K-means clustering algorithm is used to determine outliers and use the previous and next means to replace and fill in. If the data is missing for 6 consecutive hours, it will be deleted directly. If the data obviously violates common sense, it will be deleted directly, such as the secondary heating is lower than the return temperature.

[0084] The unit load prediction model P is established using the LSTM model. The maximum number of iterations when training the model is 100. The mean square error MAE and goodness of fit R2 are used to evaluate the heat load prediction results. The smaller the MAE value and the closer the R2 is to 1, the better the heat load prediction result.

[0085] Step 2: Establish unit operation model;

[0086] The calculation results of the heat load prediction model are modified based on the mean value of the unit room temperature, namely:

[0087]

[0088] Among them, P f is the i-th target heat load value, P is the predicted heat load value, is the first value, T target is the target temperature, T in is the average indoor temperature.

[0089] Use RNN model to establish unit operation model P f =f(t g , t h , k), where P f is the heat load value, t g is the unit water supply temperature, t h is the unit return water temperature, k is the valve opening. The operation models P of different units in the same heat exchange station are established in sequence. f1 , P f2 ,…,P fn (n is the number of units).

[0090] Step 3: Calculate unit operation adjustment parameters;

[0091] Based on the unit operation model, it can be seen that the water supply temperature at the inlet of each unit is basically the same. That is, for n unit models, if their heat load results and water supply temperature values ​​are known, their valve opening values ​​and return water temperature values ​​can be obtained, and their valve opening values ​​are the target values ​​that need to be adjusted.

[0092] It should be noted that the present invention establishes a unit-level regulation method for the heating system through a large household data analysis model. First, a unit-level heat load prediction model is established based on LSTM, and correction is made based on the difference between the actual room temperature and the target room temperature. Then, the RNN model is used to establish a relationship model between the unit heat load and the operating parameters. When the difference between the unit water supply temperatures is ignored, the unit valve opening value can be determined based on the RNN model, and the target regulation value can be directly calculated, and no manual participation is required in the whole process.

[0093] It should be noted that the present application also has the following advantages: 1. The control target is set based on the user's room temperature data to achieve the established target value. The room temperature data of each household in the building is involved in the correction of the load forecast result, which can ensure the stability of the user's room temperature, improve the heating comfort, and reduce user complaints of overcooling and overheating; 2. The unit model establishment process does not require the participation of flow data, but directly replaces the flow data with the valve opening value. There is no need to separately analyze the relationship between the valve opening and the flow data. By mining the data value, the model is simplified and the analysis efficiency is improved; 3. The establishment of the load forecast model and the unit model does not adopt mechanism modeling to avoid obstacles caused by the lack of information such as structural data. The adopted data analysis model can fully mine the valuable information in the chaotic data, and the model is more practical.

[0094] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0095] In this embodiment, a device for determining the valve opening is also provided, which is used to implement the above embodiments and preferred implementations, and will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0096] Figure 3 : is a structural block diagram of a device for determining a valve opening according to an embodiment of the present application, the device comprising:

[0097] The first determination module 302 is used to determine N target heat load values, wherein the i-th target heat load value among the N target heat load values ​​is used to indicate the total amount of heat that the i-th unit building needs to receive from the outside when the indoor temperature of the i-th unit building among the N unit buildings is maintained at the target temperature, N is an integer greater than or equal to 2, and i is an integer greater than or equal to 1 and less than or equal to N;

[0098] The second determination module is used to determine N unit operation models, wherein the i-th unit operation model is used to reflect the relationship between the water supply temperature, return water temperature and valve opening of the electric regulating valve of the i-th unit building and the heat load value of the i-th unit building; the electric regulating valve of the i-th unit building is used to adjust the flow rate of the liquid flowing through the thermal pipeline of the i-th unit building;

[0099] The third determination module is used to determine N groups of data according to the N target heat load values ​​and the target water supply temperature by running the model through the N units, wherein the i-th group of data among the N groups of data includes the target valve opening and target return water temperature of the electric regulating valve of the i-th unit building; and the water supply temperatures of the N unit buildings are all the target water supply temperatures.

[0100] The above device confirms the total amount of heat that the unit building needs to receive from the outside to maintain the indoor temperature at the target temperature and the unit operation model used to reflect the relationship between the unit building's water supply temperature, return water temperature and valve opening of the electric regulating valve and the heat load value, thereby using the unit operation model to confirm the valve opening of the electric regulating valve and the target return water temperature according to the confirmed total amount of heat and the target water supply temperature. Since the valve opening and return water temperature are determined by the model based on the actual amount of heat required to maintain the indoor temperature of the unit building, the heating efficiency of the heating system and the accuracy of the heating parameters are improved, thereby solving the problem of being unable to control the heating system to accurately heat the unit building according to the actual needs of the unit building.

[0101] In an exemplary embodiment, the first determination module 302 is further used to determine the ith target heat load value in the following manner to determine the N target heat load values: using the heat load prediction model of the ith unit building, predicting the predicted heat load value of the ith unit building at the next moment of the historical time series according to the time series data corresponding to the ith unit building in the historical time series, wherein the time series data includes target data corresponding to each historical moment in the historical time series, and the target data includes: water supply temperature, return water temperature, flow rate of liquid flowing through the thermal pipeline of the ith unit building, and indoor temperature; correcting the predicted heat load value according to the average indoor temperature corresponding to the time series data and the target temperature to obtain the ith target heat load value.

[0102] In an exemplary embodiment, the first determination module 302 is further configured to divide the target temperature by the average indoor temperature to obtain a first value; and multiply the first value by the predicted heat load value to obtain the i-th target heat load value.

[0103] In an exemplary embodiment, the above-mentioned device also includes: a first training module, used to obtain first training data, wherein the first training data includes multiple groups of first data, wherein each group of data in the multiple groups of first data includes: the time series data corresponding to the i-th unit building in the sample historical time series, and the predicted heat load value of the i-th unit building at the next moment of the sample historical time series; training the general LSTM model based on the training data until the general LSTM model meets the preset conditions, and determining the general LSTM model that meets the preset conditions as the heat load prediction model of the i-th unit building.

[0104] In an exemplary embodiment, the preset conditions include: the mean square error MAE value of the general LSTM model is less than a first preset threshold, and the goodness of fit R2 value of the general LSTM model is greater than a second preset threshold.

[0105] In an exemplary embodiment, the above-mentioned device also includes: a second training module, which is used to obtain the i-th unit operation model in the following manner: obtaining second training data, wherein the second training data includes multiple groups of second data, wherein each group of the multiple groups of second data includes: sample data, and the heat load value of the i-th unit building corresponding to the sample data, and the sample data includes: the water supply temperature, the return water temperature and the valve opening of the electric regulating valve of the i-th unit building; based on the second training data, the general recurrent neural network model is trained until the general recurrent neural network model meets the convergence condition, and the general recurrent neural network model that meets the convergence condition is determined as the i-th unit operation model.

[0106] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when run.

[0107] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0108] S1, determining N target heat load values, wherein the i-th target heat load value among the N target heat load values ​​is used to indicate the total amount of heat that the i-th unit building needs to receive from the outside when the indoor temperature of the i-th unit building among the N unit buildings is maintained at the target temperature, N is an integer greater than or equal to 2, and i is an integer greater than or equal to 1 and less than or equal to N;

[0109] S2, determining N unit operation models, wherein the i-th unit operation model is used to reflect the relationship between the water supply temperature, return water temperature and valve opening of the electric regulating valve of the i-th unit building and the heat load value of the i-th unit building; the electric regulating valve of the i-th unit building is used to adjust the flow rate of the liquid flowing through the thermal pipeline of the i-th unit building;

[0110] S3, determining N groups of data according to the N target heat load values ​​and the target water supply temperature through the N unit operation models, wherein the i-th group of data in the N groups of data includes the target valve opening and target return water temperature of the electric regulating valve of the i-th unit building; and the water supply temperatures of the N unit buildings are all the target water supply temperatures.

[0111] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0112] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0113] An embodiment of the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps in any one of the above method embodiments are performed.

[0114] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0115] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0116] S1, determining N target heat load values, wherein the i-th target heat load value among the N target heat load values ​​is used to indicate the total amount of heat that the i-th unit building needs to receive from the outside when the indoor temperature of the i-th unit building among the N unit buildings is maintained at the target temperature, N is an integer greater than or equal to 2, and i is an integer greater than or equal to 1 and less than or equal to N;

[0117] S2, determining N unit operation models, wherein the i-th unit operation model is used to reflect the relationship between the water supply temperature, return water temperature and valve opening of the electric regulating valve of the i-th unit building and the heat load value of the i-th unit building; the electric regulating valve of the i-th unit building is used to adjust the flow rate of the liquid flowing through the thermal pipeline of the i-th unit building;

[0118] S3, determining N groups of data according to the N target heat load values ​​and the target water supply temperature through the N unit operation models, wherein the i-th group of data in the N groups of data includes the target valve opening and target return water temperature of the electric regulating valve of the i-th unit building; and the water supply temperatures of the N unit buildings are all the target water supply temperatures.

[0119] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0120] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0121] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0122] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining valve opening, characterized in that: include: Determine N target heat load values, wherein the i-th target heat load value among the N target heat load values ​​is used to indicate the total amount of heat that the i-th unit building needs to receive from the outside when the indoor temperature of the i-th unit building among the N unit buildings is maintained at the target temperature, and N is an integer greater than or equal to 2. i is an integer greater than or equal to 1 and less than or equal to N; and Determine N unit operation models, wherein the i-th unit operation model is used to reflect the relationship between the water supply temperature, return water temperature and valve opening of the electric regulating valve of the i-th unit building and the heat load value of the i-th unit building; the electric regulating valve of the i-th unit building is used to adjust the flow rate of the liquid flowing through the thermal pipeline of the i-th unit building; By running the N unit models, N groups of data are determined according to the N target heat load values ​​and the target water supply temperatures, wherein the i-th group of data among the N groups of data includes the target valve opening and target return water temperature of the electric regulating valve of the i-th unit building; and the water supply temperatures of the N unit buildings are all the target water supply temperatures.

2. The method according to claim 1, characterized in that Determine N target heat load values, including: The i-th target heat load value is determined in the following manner to determine the N target heat load values: Using the heat load prediction model of the i-th unit building, predicting the predicted heat load value of the i-th unit building at the next moment of the historical time series according to the time series data corresponding to the i-th unit building in the historical time series, wherein the time series data includes target data corresponding to each historical moment in the historical time series, and the target data includes: water supply temperature, return water temperature, flow rate of liquid flowing through the thermal pipeline of the i-th unit building, and indoor temperature; The predicted heat load value is corrected according to the average indoor temperature corresponding to the time series data and the target temperature to obtain the i-th target heat load value.

3. The method according to claim 2, characterized in that The predicted heat load value is corrected according to the average indoor temperature corresponding to the time series data and the target temperature to obtain the i-th target heat load value, including: Dividing the target temperature by the average indoor temperature to obtain a first value; The first value is multiplied by the predicted heat load value to obtain the i-th target heat load value.

4. The method according to claim 2, characterized in that: The method further comprises: Acquire first training data, wherein the first training data includes multiple groups of first data, wherein each group of data in the multiple groups of first data includes: time series data corresponding to the i-th unit building in the sample historical time series, and a predicted heat load value of the i-th unit building at the next moment of the sample historical time series; The general LSTM model is trained based on the training data until the general LSTM model meets the preset conditions, and the general LSTM model that meets the preset conditions is determined as the heat load prediction model of the i-th unit building.

5. The method according to claim 4, characterized in that The preset conditions include: the mean square error MAE value of the general LSTM model is less than a first preset threshold, and the goodness of fit R2 value of the general LSTM model is greater than a second preset threshold.

6. The method according to claim 1, characterized in that The method further comprises: The i-th unit operation model is obtained by: Acquire second training data, wherein the second training data includes multiple groups of second data, wherein each group of the multiple groups of second data includes: sample data, and a heat load value of the i-th unit building corresponding to the sample data, wherein the sample data includes: a water supply temperature, a return water temperature, and a valve opening of an electric regulating valve of the i-th unit building; The universal recurrent neural network model is trained based on the second training data until the universal recurrent neural network model meets a convergence condition, and the universal recurrent neural network model that meets the convergence condition is determined as the i-th unit operation model.

7. A device for determining valve opening, characterized in that: include: The first determination module is used to determine N target heat load values, wherein the i-th target heat load value among the N target heat load values ​​is used to indicate the total amount of heat that the i-th unit building needs to receive from the outside when the indoor temperature of the i-th unit building among the N unit buildings is maintained at the target temperature. N is an integer greater than or equal to 2, i is an integer greater than or equal to 1 and less than or equal to N; The second determination module is used to determine N unit operation models, wherein the i-th unit operation model is used to reflect the relationship between the water supply temperature, return water temperature and valve opening of the electric regulating valve of the i-th unit building and the heat load value of the i-th unit building; the electric regulating valve of the i-th unit building is used to adjust the flow rate of the liquid flowing through the thermal pipeline of the i-th unit building; A third determination module is used to determine N groups of data according to the N target heat load values ​​and the target water supply temperature by running the model through the N units, wherein the i-th group of data in the N groups of data includes the target valve opening and the target return water temperature of the electric regulating valve of the i-th unit building; The water supply temperatures of the N unit buildings are all the target water supply temperatures.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 6 when executed.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 6 through the computer program.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images