Heat exchange station temperature control method, device, computer equipment and storage medium

Abstract

The present application relates to a method, device, computer equipment and storage medium for controlling the temperature of a heat exchange station. The method analyzes the acquired target data (meteorological data, heat exchange station heating data and indoor temperature data) through a room temperature prediction model, predicts the indoor temperature (predicted room temperature) when the current heating temperature (heating) is adopted, and judges whether the difference between the predicted room temperature and the target room temperature meets the corresponding adjustment conditions. If not, the temperature output at the current moment is directly adopted. Otherwise, the corresponding adjustment is performed according to the temperature adjustment strategy set by the prediction, minimizing the difference between the predicted room temperature and the target room temperature after adjustment. Automatic temperature compensation is achieved by automatic detection, and resources can be effectively saved. Avoid the problem of unreasonable compensation and waste of resources due to insufficient experience of the compensation personnel during manual compensation.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, computer equipment and storage medium for controlling the temperature of a heat exchange station. Background Art

[0002] The heating problem in winter is closely related to people's lives. At present, in northern cities, the centralized heating system is one of the infrastructures. The heating system consists of three parts: heat source, heating pipeline network, and heat users (buildings). Among them, the primary supply and return water and the secondary supply and return water are not connected, and the two exchange heat through the heat exchange station. The heat of the secondary water supply is transferred to the heat user through the radiator and then becomes secondary return water. The core goal of heating is to keep the heat supply and heat dissipation in a balanced state at all times, so as to maintain a suitable indoor temperature. In order to maintain a suitable indoor temperature, a room temperature climate compensator is usually required to supplement the room temperature. The traditional room temperature climate compensator adjusts the compensation curve through manual assistance, and everyone's experience is different. People with poor experience cannot accurately judge whether temperature adjustment is needed. If adjustment is made when it is not necessary, it will lead to waste of resources. Summary of the invention

[0003] In order to solve the above technical problems, the present application provides a heat exchange station temperature control method, device, computer equipment and storage medium.

[0004] The present application provides a heat exchange station temperature control method, comprising:

[0005] Obtain the target data at the current moment, the target data includes the heating data of the heat exchange station, the indoor temperature data and the meteorological data, and the heating data includes the temperature supply;

[0006] Input the target data into the room temperature prediction model and output the predicted room temperature at the current moment;

[0007] Calculate the difference between the predicted room temperature and the target room temperature;

[0008] When the difference value is greater than the first threshold value and less than the second threshold value, the temperature data to be adjusted is obtained, an adjustment instruction is generated according to the temperature data to be adjusted and the temperature supply, and the adjustment instruction is executed.

[0009] In one embodiment, the room temperature prediction model includes a heating sub-model, a cooling sub-model and a prediction sub-model, the target data includes heating data and cooling data, and the inputting of the target data into the room temperature prediction model and outputting the predicted room temperature at the current moment includes: inputting the heating data into the heating sub-model and outputting multiple implicit variables of the heating sub-model; inputting the cooling data into the cooling sub-model and outputting multiple implicit variables of the cooling sub-model; inputting the multiple implicit variables of the cooling sub-model and the heating sub-model into the prediction sub-model and outputting the predicted room temperature at the current moment.

[0010] In one embodiment, the heating data of the heat exchange station also includes reheating, the difference between the supply temperature and the reheating, and the product of the difference and the flow rate; the indoor temperature data includes room temperature and humidity; the meteorological data includes outdoor temperature, outdoor humidity, wind direction, wind speed, light and weather; the heating data includes the supply temperature, the reheating, the difference between the supply temperature and the reheating, the product of the difference and the flow rate and light, the outdoor temperature, the outdoor humidity, the wind direction, the wind speed, the weather, the room temperature and the humidity.

[0011] In one of the embodiments, the heating sub-model and the cooling sub-model are both fully connected networks, and the activation function of the prediction sub-model is a Sigmoid function.

[0012] In one embodiment, the indoor temperature data includes room temperature. Before obtaining the target data at the current moment, it also includes: receiving initial temperature data collected by each sensor, each sensor is distributed in a different house; constructing an initial matrix according to the distribution of house types, each matrix element in the initial matrix corresponds to a house, and some houses are equipped with the sensor; updating the initial matrix according to the initial temperature data collected by each sensor to obtain a first matrix; using a filling algorithm of non-negative matrix decomposition to fill the matrix elements of the first matrix to obtain a target matrix, each matrix element of the target matrix is ​​the room temperature in the indoor temperature data.

[0013] In one of the embodiments, when the difference value is smaller than the first threshold value, the heat exchange station directly outputs the supply temperature.

[0014] In one of the embodiments, when the difference value is greater than the second threshold value, the heat exchange station directly outputs the supply temperature.

[0015] The present application provides a heat exchange station temperature control device, comprising:

[0016] A data acquisition module is used to acquire target data at the current moment, wherein the target data includes heating data of the heat exchange station, indoor temperature data and meteorological data, and the heating data includes temperature supply;

[0017] A room temperature prediction module, used to input the target data into a room temperature prediction model and output the predicted room temperature at the current moment;

[0018] A difference value calculation module, used to calculate the difference value between the predicted room temperature and the target room temperature;

[0019] The temperature control module is used to obtain the temperature data to be adjusted when the difference value is greater than a first threshold value and less than a second threshold value, generate an adjustment instruction according to the temperature data to be adjusted and the temperature supply, and execute the adjustment instruction.

[0020] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0021] Obtain the target data at the current moment, the target data includes the heating data of the heat exchange station, the indoor temperature data and the meteorological data, and the heating data includes the temperature supply;

[0022] Input the target data into the room temperature prediction model and output the predicted room temperature at the current moment;

[0023] Calculate the difference between the predicted room temperature and the target room temperature;

[0024] When the difference value is greater than the first threshold value and less than the second threshold value, the temperature data to be adjusted is obtained, an adjustment instruction is generated according to the temperature data to be adjusted and the temperature supply, and the adjustment instruction is executed.

[0025] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0026] Obtain the target data at the current moment, the target data includes the heating data of the heat exchange station, the indoor temperature data and the meteorological data, the heating data includes the heating, and the indoor temperature data includes the room temperature;

[0027] Input the target data into the room temperature prediction model and output the predicted room temperature at the current moment;

[0028] Calculate the difference between the predicted room temperature and the target room temperature;

[0029] When the difference value is greater than the first threshold value and less than the second threshold value, the temperature data to be adjusted is obtained, an adjustment instruction is generated according to the temperature data to be adjusted and the temperature supply, and the adjustment instruction is executed.

[0030] The above-mentioned heat exchange station temperature control method, device, computer equipment and storage medium, the method includes: obtaining the target data at the current moment, the target data includes the heating data of the heat exchange station, the indoor temperature data and the meteorological data, the heating data includes the temperature supply, and the indoor temperature data includes the room temperature; inputting the target data into the room temperature prediction model, and outputting the predicted room temperature at the current moment; calculating the difference between the predicted room temperature and the target room temperature; when the difference is greater than the first threshold value and less than the second threshold value, obtaining the temperature data to be adjusted, generating the adjustment instruction according to the temperature data to be adjusted and the temperature supply, and executing the adjustment instruction. The obtained target data (meteorological data, heat exchange station heating data and indoor temperature data) are analyzed by the room temperature prediction model, and the indoor temperature (predicted room temperature) when the current heating temperature (temperature supply) is adopted is predicted, and it is judged whether the difference between the predicted room temperature and the target room temperature meets the corresponding adjustment condition. If not, the heat exchange station directly adopts the temperature supply at the current moment for output, otherwise, the corresponding adjustment is performed according to the temperature supply adjustment strategy set by the prediction, and the difference between the predicted room temperature and the target room temperature after adjustment is minimized. Automatic temperature compensation is achieved by automatic detection, and resources can be effectively saved. Avoid problems such as unreasonable compensation and waste of resources due to lack of experience of compensation personnel when making manual compensation. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0032] In order to more clearly illustrate the embodiments of the present invention 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.

[0033] Figure 1 This is an application environment diagram of a heat exchange station temperature control method in one embodiment;

[0034] Figure 2 It is a schematic flow chart of a method for controlling the temperature of a heat exchange station in one embodiment;

[0035] Figure 3 A schematic diagram of temperature prediction of an indoor prediction model in one embodiment;

[0036] Figure 4 is a schematic diagram of a method for controlling the temperature of a heat exchange station in one embodiment;

[0037] Figure 5 is a structural block diagram of a temperature control device for a heat exchange station in one embodiment;

[0038] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, 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 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 making creative work are within the scope of protection of this application.

[0040] Figure 1 FIG. 1 is an application environment diagram of a heat exchange station temperature control method in an embodiment. Figure 1 The heat exchange station temperature control method is applied to a heating system. The heating system includes a sensor 110 and a heat exchange station control terminal 120. The sensor 110 and the heat exchange station control terminal 120 are connected via a network. The sensor 110 can be a temperature sensor 111 and a humidity sensor 112. The heat exchange station control terminal 120 can be a desktop terminal or a mobile terminal, and the mobile terminal can be at least one of a mobile phone, a tablet computer, a laptop computer, etc.

[0041] like Figure 2 As shown, in one embodiment, a method for controlling the temperature of a heat exchange station is provided. This embodiment mainly applies the method to the above Figure 1 The heat exchange station control terminal 120 in FIG. Figure 2 , the heat exchange station temperature control method specifically includes the following steps:

[0042] Step S201, obtaining the target data at the current moment.

[0043] In this specific embodiment, the target data includes heating data of the heat exchange station, indoor temperature data and meteorological data, and the heating data includes temperature supply.

[0044] Specifically, the primary water supply and return network of the heating system affects the secondary water supply and return network through heat exchange, and the heat exchange station is used to control the temperature of the secondary water outlet. The secondary water supply and return network refers to the network that directly provides heat to the building, so the indoor temperature is basically only affected by the secondary water supply and return network. The target data includes the heating data of the heat exchange station, the indoor temperature data and the meteorological data. Among them, the heating data of the heat exchange station includes heating, return temperature, the difference between heating and return temperature, and the product of the difference and the flow rate. Indoor temperature data includes room temperature and humidity. Meteorological data includes outdoor temperature, outdoor humidity, wind direction, wind speed, light and weather. Among them, temperature-related data such as indoor temperature, outdoor temperature, heating and return temperature are collected through temperature sensors. Humidity (indoor humidity and outdoor humidity) is collected through humidity sensors.

[0045] In one embodiment, the meteorological data can be directly obtained from the local meteorological data released by the meteorological platform. Directly using the data of the meteorological platform for outdoor data can reduce the cost of laying hardware equipment.

[0046] In one embodiment, the initial heating data of the heat exchange station, the initial temperature data in the room, and the initial meteorological data in the meteorological platform are collected by the sensor at the current moment. Feature extraction is performed on the initial data (initial heating data, initial temperature data, and initial meteorological data) to obtain target data. Feature extraction is performed on the collected original data and the obtained meteorological data to avoid the problem of unavailability of the original data. Feature extraction of the data can also integrate and analyze the directly collected data, making the data more comprehensive.

[0047] In one embodiment, sensors are not distributed in every house, so when collecting indoor temperature, only the room temperature of some houses is collected, and the room temperature of other houses is supplemented by the collected room temperature of the house. The room temperature supplementation method can be supplemented by local mean, matrix decomposition, etc. The specific supplementation method can be customized.

[0048] Step S202, input target data to the room temperature prediction model, and output the predicted room temperature at the current moment.

[0049] Specifically, the room temperature prediction model is a neural network model, which may include one independent feature extraction module or multiple independent feature extraction modules. When multiple independent feature extraction modules are included, each feature extraction module outputs corresponding features, and finally the features output by each independent feature extraction module are fused to output the predicted indoor temperature, that is, the predicted room temperature at the current moment.

[0050] In one embodiment, the room temperature prediction module includes a heating sub-model, a cooling sub-model and a prediction sub-model, and the target data includes heating data and cooling data. Step S202: input the heating data to the heating sub-model, and output multiple implicit variables of the heating sub-model; input the cooling data to the cooling sub-model, and output multiple implicit variables of the cooling sub-model; input the multiple implicit variables of the cooling sub-model and the heating sub-model into the prediction sub-model, and output the predicted room temperature at the current moment.

[0051] Specifically, the heating sub-model is used to extract heating features, that is, by analyzing the heating data, multiple heating features (multiple implicit variables of the heating sub-model) are obtained. The heat dissipation sub-model is used to analyze the heat dissipation data and output the corresponding multiple heat dissipation features (multiple implicit variables of the heat dissipation sub-model). The prediction sub-model is used to receive the output features of the heating sub-model and the heat dissipation sub-model, and predict the indoor temperature based on the received features. The model structures of the heating sub-model and the heat dissipation sub-model can be the same or different. If the model structures of the heating sub-model and the heat dissipation sub-model are both fully connected networks, the number of network layers of the heating sub-model and the heat dissipation sub-model can be the same or different. The activation function of the prediction sub-model can be relu and sigmoid.

[0052] In one embodiment, the heating sub-model and the cooling sub-model are both fully connected networks, such as the heating sub-model and the cooling sub-model are both 3- or 4-layer fully connected networks.

[0053] In one embodiment, in order to improve the generalization of the room temperature prediction model, a dropout algorithm is used in the hidden layer of the network. The hidden layer refers to the network layer other than the input layer and the output layer. The input layer is used to receive data, and the output layer is used to output the prediction result. The dropout algorithm is used to stop the neurons in the hidden layer from working with a certain probability.

[0054] Step S203, calculating the difference between the predicted room temperature and the target room temperature.

[0055] Step S204, when the difference value is greater than the first threshold value and less than the second threshold value, obtain the temperature data to be adjusted, generate an adjustment instruction according to the temperature data to be adjusted and the temperature supply, and execute the adjustment instruction.

[0056] Specifically, the target room temperature refers to a predefined room temperature, which is a temperature that is more suitable for human habitation. The difference value refers to the difference between the predicted room temperature and the target room temperature or the absolute value, etc., which represents the difference. The first threshold and the second threshold are both custom temperature thresholds. The first threshold is less than the second threshold, and the threshold interval between the first threshold and the second threshold is defined as the first interval. The difference value is in the first interval, that is, the difference value is greater than the first threshold and less than the second threshold, indicating that the difference between the predicted room temperature and the target room temperature is large, and the heating temperature of the heat exchange station needs to be adjusted. The temperature data to be adjusted is the pre-set temperature data. For example, it can be adjusted according to 0.1°C or 0.2°C. The adjustment direction is determined according to the difference between the predicted room temperature and the target room temperature. If the target room temperature is higher than the predicted room temperature, the heating temperature is lowered, otherwise the heating temperature is increased.

[0057] In one embodiment, when the difference value is less than a first threshold, the heat exchange station directly outputs the supply temperature.

[0058] Specifically, if the difference value is less than the first threshold, it means that the predicted indoor temperature is substantially consistent with the target room temperature, and no compensation is required, and the temperature at the current moment can be directly output.

[0059] In one embodiment, when the difference value is greater than a second threshold, the heat exchange station directly outputs the supply temperature.

[0060] Specifically, if the difference value is greater than the second threshold, it means that the difference between the room temperature and the adjusted temperature is too large. If the temperature adjustment is too large, the stability of the heating pipe network cannot be guaranteed. Therefore, when the difference is large, the temperature corresponding to the current moment is directly used as the output temperature of the heat exchange station.

[0061] The temperature control method of the heat exchange station includes: obtaining the target data at the current moment, the target data includes the heating data of the heat exchange station, the indoor temperature data and the meteorological data, the heating data includes the heating, and the indoor temperature data includes the room temperature; inputting the target data into the room temperature prediction model, and outputting the predicted room temperature at the current moment; calculating the difference between the predicted room temperature and the target room temperature; when the difference is greater than the first threshold value and less than the second threshold value, obtaining the temperature data to be adjusted, generating the adjustment instruction according to the temperature data to be adjusted and the heating, and executing the adjustment instruction. The obtained target data is analyzed by the room temperature prediction model, and the indoor temperature (predicted room temperature) when the current heating temperature (heating) is adopted is predicted, and it is judged whether the difference between the predicted room temperature and the target room temperature meets the corresponding adjustment condition. If not, the temperature output at the current moment is directly adopted. Otherwise, the corresponding adjustment is performed according to the temperature adjustment strategy set by the prediction, and the difference between the predicted room temperature and the target room temperature after adjustment is minimized. Automatic temperature compensation is realized by automatic detection, and resources can be effectively saved. Avoid the problem of unreasonable compensation and waste of resources due to insufficient experience of compensation personnel during manual compensation.

[0062] In one embodiment, before obtaining the target data at the current moment, it also includes: receiving initial temperature data collected by each sensor, each sensor is distributed in a different house; constructing an initial matrix according to the distribution of house types, each matrix element in the initial matrix corresponds to a house, and some houses are equipped with sensors; updating the initial matrix according to the initial temperature data collected by each sensor to obtain a first matrix; using a filling algorithm of non-negative matrix decomposition to fill the matrix elements of the first matrix to obtain a target matrix, and each matrix element of the target matrix is ​​the room temperature in the indoor temperature data.

[0063] Specifically, in order to save the cost of hardware resources, when laying indoor sensors, only part of the houses are laid with temperature sensors, and the corresponding temperature data, i.e., initial temperature data, is collected by the temperature sensors laid in part of the houses. The house may refer to a single room or multiple rooms corresponding to each house type. The house type distribution refers to the house type distribution of each floor to which the house belongs. The initial matrix is ​​constructed according to the house type distribution, such as 7 / 8 floors and four directions, and the initial matrix is ​​a 4*7 / 4*8 matrix. The house type distribution is not necessarily divided according to the four directions, and the matrix can be constructed according to the actual house type distribution so that each house corresponds to an element in the initial matrix. The filling algorithm of non-negative matrix decomposition refers to a method of decomposing a non-negative matrix, and then restoring the matrix according to the decomposed matrix. For example, a 4*8 matrix can be decomposed into two matrices of 4*6 and 6*8, and the two matrices of 4*6 and 6*8 are used for restoration to obtain the target matrix. Similarly, it can also be decomposed into multiple matrices, such as decomposing into three matrices of 4*4, 4*5 and 5*8. And so on, it can also be decomposed into more matrices. The decomposed matrix may be further decomposed, for example, into two matrices of 4*6 and 6*8, and then the 6*8 matrix may be further decomposed to obtain two matrices of 6*5 and 5*8.

[0064] In a specific embodiment, refer to Table 1, which is a table of collected indoor original temperature data. For example, a building includes 8 floors, each floor has four apartment types, and each apartment type faces east, south, west and north respectively. Among them, the houses on the first and third floors facing north are laid with temperature sensors, the houses on the second and eighth floors facing south are laid with temperature sensors, the houses on the fourth and seventh floors facing east are laid with temperature sensors, and the houses on the fifth and sixth floors facing west are laid with temperature sensors. Among them, "?" means that there is no room temperature data for the house, and the number represents the room temperature (℃).

[0065] Table 1 Indoor original temperature data table

[0066]

[0067] The method of non-negative matrix decomposition is used to fill in the missing matrix elements in Table 1 to obtain the target matrix. That is, by performing matrix decomposition on the matrix composed of the data in Table 1, the matrix elements of the decomposed matrix are determined by the matrix elements with specific values ​​in the matrix, and the decomposed matrix is ​​used for matrix restoration to complete the missing matrix elements. The indoor temperature data of all houses can provide real-time feedback on the heating situation. It is very necessary to obtain the temperature data of each house, and it is costly to lay corresponding sensors in each house. Temperature sensors are laid in some houses, and the temperature data of rooms without temperature sensors are completed according to the temperature data collected by sensors in some houses. That is, the missing matrix elements in the matrix are completed by the method of non-negative matrix decomposition, saving the cost of laying temperature sensors. And the temperature data of the house can be restored more accurately by the method of non-negative matrix decomposition.

[0068] In one embodiment, referring to Figure 3 , the room temperature prediction model includes a heating sub-model, a cooling sub-model and a prediction sub-model. The input features of the heating sub-model are heating features, and the input features of the cooling sub-network are cooling features. The heating sub-model inputs data related to heating, such as heating, temperature recovery, the difference between heating and temperature recovery, the product of the temperature recovery difference and flow, and light data, and then uses a 3-layer fully connected network for further learning. Among them, the activation function of the heating sub-model is Relu. The cooling sub-model inputs features related to cooling, such as outdoor temperature, outdoor humidity, wind direction, wind speed, weather, relevant time, room temperature, humidity and other data, and uses a 3-layer fully connected network for further learning. The results of the heating sub-model and the cooling sub-model are spliced ​​together, and the Sigmoid function of the prediction sub-network is used to predict the indoor temperature at the next moment (predicted room temperature). At the end of the model, the dropout algorithm is used to increase the generalization of the model.

[0069] By characterizing the influence of multiple factors, the room temperature prediction model can predict the room temperature at the next moment. On this basis, considering the feedback of the current room temperature, the heating temperature can be optimized based on the target direction solution method. Assuming that the target average indoor temperature of all houses in the community is set to 21°, the optimization goal is to minimize the difference between the average indoor temperature (predicted room temperature) and the target indoor temperature. The solution method based on the target direction is as follows Figure 4 shown.

[0070] Set the temperature to the heating temperature at the current moment, and predict the indoor temperature prediction result at the next moment through the room temperature prediction model. If the difference between the predicted room temperature and the target room temperature is less than 0.3℃ (the first threshold), it is considered to meet the set requirements, and the current heating temperature is directly output. If the difference in room temperature is greater than 0.3°, it is necessary to determine whether the difference in the change of the heating temperature is greater than 2° (the second threshold, the single adjustment limit) (to ensure the stability of the heating pipe network, the single adjustment cannot be too large). If it is greater, it is directly output (the heat exchange station directly outputs the temperature at the current moment). On the contrary, the heating temperature is continuously adjusted up and down with a minimum adjustable accuracy of 0.1°, and the above process is repeated. With the help of this progressive optimization adjustment, the output is achieved until the conditions are met. It should be noted that the direction of the up and down adjustment of the heating temperature comes from the difference between the predicted room temperature and the set room temperature. If the predicted room temperature is lower than 21°, the heating temperature is increased; vice versa. This method can reduce the consumption of heating energy in the heat exchange station.

[0071] By combining the real-time indoor temperature data collected remotely by the Internet of Things, the heating temperature is controlled based on the prediction of the indoor temperature, thereby achieving precise control of the indoor temperature, saving energy consumption of the heating system, and improving living comfort.

[0072] Figure 2 FIG. 1 is a flow chart of a method for controlling the temperature of a heat exchange station in an embodiment. It should be understood that although Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0073] In one embodiment, Figure 5 As shown, a heat exchange station temperature control device 200 is provided, comprising:

[0074] The data acquisition module 201 is used to acquire the target data at the current moment, the target data includes the heating data of the heat exchange station, the indoor temperature data and the meteorological data, and the heating data includes the temperature supply;

[0075] The room temperature prediction module 202 is used to input the target data into the room temperature prediction model and output the predicted room temperature at the current moment;

[0076] The difference value calculation module 203 is used to calculate the difference value between the predicted room temperature and the target room temperature;

[0077] The temperature control module 204 is used to obtain the temperature data to be adjusted when the difference value is greater than the first threshold value and less than the second threshold value, generate an adjustment instruction according to the temperature data to be adjusted and the temperature supply, and execute the adjustment instruction.

[0078] In one embodiment, the room temperature prediction model includes a heating sub-model, a heat dissipation sub-model and a prediction sub-model.

[0079] The room temperature prediction module 202 is used to input heating data into the heating sub-model and output multiple implicit variables of the heating sub-model; input heat dissipation data into the heat dissipation sub-model and output multiple implicit variables of the heat dissipation sub-model; input multiple implicit variables of the heat dissipation sub-model and the heating sub-model into the prediction sub-model and output the predicted room temperature at the current moment.

[0080] In one embodiment, the heating data of the heat exchange station also includes reheating, the difference between supply heating and reheating, and the product of the difference and flow rate. The indoor temperature data includes room temperature and humidity. The meteorological data includes outdoor temperature, outdoor humidity, wind direction, wind speed, light and weather. The heating data includes supply heating, reheating, the difference between supply heating and reheating, the product of the difference and flow rate and light, outdoor temperature, outdoor humidity, wind direction, wind speed, weather, room temperature and humidity.

[0081] In one embodiment, the heating sub-model and the cooling sub-model are both fully connected networks, and the activation function of the prediction sub-model is the Sigmoid function.

[0082] In one embodiment, the heat exchange station temperature control device 200 further includes:

[0083] The initial data receiving module is used to receive the initial temperature data collected by each sensor, each sensor is distributed in a different house;

[0084] The matrix initialization module is used to construct an initial matrix according to the distribution of house types. Each matrix element in the initial matrix corresponds to a house, and some houses are equipped with sensors.

[0085] A matrix updating module, used for updating the initial matrix according to the initial temperature data collected by each sensor to obtain a first matrix;

[0086] The matrix filling module is used to fill the matrix elements of the first matrix using a filling algorithm of non-negative matrix decomposition to obtain a target matrix, wherein each matrix element of the target matrix is ​​the room temperature in the indoor temperature data.

[0087] In one embodiment, the heat exchange station temperature control device 200 further includes:

[0088] The temperature output module is used to enable the heat exchange station to directly output the temperature when the difference value is less than the first threshold value.

[0089] In one embodiment, the heat exchange station temperature control device 200 further includes:

[0090] The temperature output module is also used to enable the heat exchange station to directly output the temperature when the difference value is greater than the second threshold value.

[0091] Figure 6 The internal structure diagram of a computer device in one embodiment is shown. The computer device may specifically be Figure 1 The terminal 110 (or server 120) in FIG. Figure 6 As shown, the computer device includes a processor, a memory, a network interface, an input device and a display screen connected via a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program, which, when executed by the processor, enables the processor to implement the heat exchange station temperature control method. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to execute the heat exchange station temperature control method. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0092] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0093] In one embodiment, the heat exchange station temperature control device provided in the present application can be implemented in the form of a computer program. The computer program can be Figure 6 The computer device shown in the figure is run. The memory of the computer device can store various program modules constituting the temperature control device of the heat exchange station, for example, Figure 5 The data acquisition module 201, room temperature prediction module 202, difference value calculation module 203 and temperature control module 204 are shown. The computer program composed of various program modules enables the processor to execute the steps of the heat exchange station temperature control method of each embodiment of the present application described in this specification.

[0094] For example, Figure 6 The computer device shown can be Figure 5The data acquisition module 201 in the heat exchange station temperature control device 200 shown in the figure acquires the target data at the current moment, and the target data includes the heating data of the heat exchange station, the indoor temperature data and the meteorological data, the heating data includes the temperature supply, and the indoor temperature data includes the room temperature. The computer device can input the target data into the room temperature prediction model through the room temperature prediction module 202, and output the predicted room temperature at the current moment. The computer device can calculate the difference between the predicted room temperature and the target room temperature through the difference value calculation module 203. The computer device can acquire the temperature data to be adjusted through the temperature control module 204 when the difference value is greater than the first threshold and less than the second threshold, generate the adjustment instruction according to the temperature data to be adjusted and the temperature supply, and execute the adjustment instruction.

[0095] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps in any embodiment of the above-mentioned heat exchange station temperature control method are implemented.

[0096] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in any embodiment of the above-mentioned heat exchange station temperature control method are performed.

[0097] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0098] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0099] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for controlling the temperature of a heat exchange station, characterized in that: The method comprises: Acquire the target data at the current moment, wherein the target data includes the heating data of the heat exchange station, the indoor temperature data and the meteorological data, and the heating data includes the temperature supply; Input the target data into a room temperature prediction model, and output the predicted room temperature at the current moment; wherein the room temperature prediction model is a neural network model; Calculating the difference between the predicted room temperature and the target room temperature; When the difference value is greater than a first threshold value and less than a second threshold value, obtaining temperature data to be adjusted, generating an adjustment instruction according to the temperature data to be adjusted and the temperature supply, and executing the adjustment instruction; The indoor temperature data includes the room temperature. Before acquiring the target data at the current moment, the method further includes: Receiving initial temperature data collected by each sensor, each of the sensors being distributed in a different house; Constructing an initial matrix according to the distribution of house types, wherein each matrix element in the initial matrix corresponds to a house, and some houses are provided with the sensors; Update the initial matrix according to the initial temperature data collected by each of the sensors to obtain a first matrix; The matrix elements of the first matrix are filled in by using a filling algorithm of non-negative matrix decomposition to obtain a target matrix, wherein each matrix element of the target matrix is ​​the room temperature in the indoor temperature data.

2. The method according to claim 1, characterized in that The room temperature prediction model includes a heating sub-model, a heat dissipation sub-model and a prediction sub-model, the target data includes heating data and heat dissipation data, and the target data is input into the room temperature prediction model to output the predicted room temperature at the current moment, including: Inputting the heating data into the heating sub-model, and outputting a plurality of implicit variables of the heating sub-model; Inputting the heat dissipation data into the heat dissipation sub-model, and outputting a plurality of implicit variables of the heat dissipation sub-model; The multiple implicit variables of the heat dissipation sub-model and the heating sub-model are input into the prediction sub-model, and the predicted room temperature at the current moment is output.

3. The method according to claim 2, characterized in that The heating data of the heat exchange station also includes the return temperature, the difference between the supply temperature and the return temperature, and the product of the difference and the flow rate; the indoor temperature data includes the room temperature and humidity; the meteorological data includes the outdoor temperature, outdoor humidity, wind direction, wind speed, light and weather; the heat dissipation data includes the outdoor temperature, the outdoor humidity, the wind direction, the wind speed, the weather, the room temperature and the humidity.

4. The method according to claim 2, characterized in that: The heating sub-model and the heat dissipation sub-model are both fully connected networks, and the activation function of the prediction sub-model is the Sigmoid function.

5. The method according to claim 1, characterized in that The method further comprises: When the difference value is smaller than the first threshold value, the heat exchange station directly outputs the supply temperature.

6. The method according to claim 1, characterized in that The method further comprises: When the difference value is greater than the second threshold, the heat exchange station is enabled to directly output the supply temperature.

7. A temperature control device for a heat exchange station, characterized in that: The device comprises: A data acquisition module is used to acquire target data at the current moment, wherein the target data includes heating data of the heat exchange station, indoor temperature data and meteorological data, and the heating data includes temperature supply; A room temperature prediction module, used to input the target data into a room temperature prediction model, and output the predicted room temperature at the current moment; wherein the room temperature prediction model is a neural network model; A difference value calculation module, used to calculate the difference value between the predicted room temperature and the target room temperature; a temperature control module, configured to obtain the temperature data to be adjusted when the difference value is greater than a first threshold value and less than a second threshold value, generate an adjustment instruction according to the temperature data to be adjusted and the temperature supply, and execute the adjustment instruction; The indoor temperature data includes the room temperature. Before obtaining the target data at the current moment, the method further includes: Receiving initial temperature data collected by each sensor, each of the sensors being distributed in a different house; Constructing an initial matrix according to the distribution of house types, wherein each matrix element in the initial matrix corresponds to a house, and some houses are provided with the sensors; Update the initial matrix according to the initial temperature data collected by each of the sensors to obtain a first matrix; The matrix elements of the first matrix are filled in by using a filling algorithm of non-negative matrix decomposition to obtain a target matrix, wherein each matrix element of the target matrix is ​​the room temperature in the indoor temperature data.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images