Valve opening degree information determination method and device, storage medium and electronic equipment
Through machine learning models based on historical data training and correction, the optimal valve opening of the heating system is determined, which solves the problem that traditional regulation methods cannot adapt to dynamic changes and achieves more efficient heating management.
Patent Information
- Application Number
- CN202411822455.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-11
- Publication Date
- 2025-03-11
AI Technical Summary
The valve opening control method of the traditional heating second network cannot effectively adapt to the dynamically changing heating demand and environmental conditions, resulting in poor heating quality and excessive energy consumption.
By obtaining historical environment, room temperature, and valve opening information, train and correct machine learning models to determine the optimal valve opening at current environment and preset room temperature.
It realizes dynamic and intelligent control of valve opening, can flexibly adapt to changes in heating demand and environmental conditions, and improves the overall efficiency and user experience of the heating system.
Smart Images
Figure CN119594462A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of heating control, and in particular to a method and device for determining valve opening information, a storage medium and an electronic device. Background Art
[0002] With the continuous expansion of urban scale and the growing demand for energy efficiency, the regulation and optimization of heating systems are facing unprecedented challenges. The secondary heating network, that is, the heat distribution network from the heat source to the user terminal, is a vital component of the heating system. Its regulation efficiency directly affects the heating quality and energy consumption. Traditionally, the valve opening regulation of the secondary heating network mainly relies on the experience of the operator and a set of fixed control parameters. This method can basically meet the heating demand under the condition that the operator is experienced. However, with the increasing complexity of the heating system, the limitations of this method have gradually become apparent:
[0003] Traditional control methods are usually based on a set of fixed control parameters, which makes it difficult to respond to dynamic changes in heating demand and fluctuations in environmental conditions in real time. For example, in severe cold weather, users' demand for heat surges, and fixed parameter control may lead to a mismatch between heat source output and user demand, thus affecting the quality of heating.
[0004] With regard to the problem in the prior art that the valve opening control method cannot effectively adapt to the dynamically changing heating demand and environmental conditions, no effective solution has been proposed yet.
[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 valve opening information, a storage medium and an electronic device, so as to at least solve the problem in the prior art that the valve opening control method cannot effectively adapt to dynamically changing heating demand and environmental conditions.
[0007] According to an embodiment of the present application, a method for determining valve opening information is provided, including: obtaining first historical information and second historical information, wherein the first historical information includes: first historical environmental information, first historical room temperature information and first historical valve opening information, the second historical information includes: second historical environmental information, second historical room temperature information and second historical valve opening information, the time difference between the time corresponding to the first historical information and the current time is a first time difference, the time difference between the time corresponding to the second historical information and the current time is a second time difference, and the first time difference is greater than the second time difference; training a model based on the first historical information to obtain a first model; correcting the first model based on the second historical information to obtain a second model; and when determining the current environmental information and the preset room temperature information, determining the valve opening information corresponding to the current environmental information and the preset room temperature information through the second model.
[0008] In an exemplary embodiment, before training a model based on the first historical information to obtain a first model, the method further includes: preprocessing the first historical information to obtain processed first historical information; adjusting model parameters of the model using the processed first historical environmental information and the processed first historical room temperature information as input and the processed first historical valve opening information as output to obtain a third model; determining a first performance of the third model based on a first test set, and determining whether to train the third model based on the first performance.
[0009] In an exemplary embodiment, determining whether to train the third model based on the first performance includes: when the first performance meets the first preset performance, stopping training the third model and determining the third model to be the first model; when the first performance does not meet the first preset performance, training the third model to obtain a fourth model; determining the second performance of the fourth model based on a second test set, and determining whether to train the fourth model based on the second performance of the fourth model.
[0010] In an exemplary embodiment, before modifying the first model based on the second historical information to obtain the second model, the method further includes: preprocessing the second historical information to obtain processed second historical information, wherein a data format of the processed second historical information is consistent with a data input format of the first model; determining a third performance of the first model based on the second historical information; and determining whether to modify the first model based on the third performance.
[0011] In an exemplary embodiment, determining whether to correct the first model is based on the third performance, including: when the third performance does not meet the second preset performance, determining to correct the first model, and adjusting the model parameters of the first model through the second historical information to obtain the second model; when the third performance meets the second preset performance, determining not to correct the first model, and when determining the current environmental information and the preset room temperature information, determining the valve opening information corresponding to the current environmental information and the preset room temperature information through the first model.
[0012] In an exemplary embodiment, after determining the valve opening information corresponding to the current environmental information and the preset room temperature information through the second model, the method further includes: sending control information to the heat exchange station so that the heat exchange station adjusts the valve opening according to the control information, wherein the control information carries the valve opening information.
[0013] According to another embodiment of the present application, a device for determining valve opening information is provided, including: an acquisition module, used to acquire first historical information and second historical information, wherein the first historical information includes: first historical environmental information, first historical room temperature information and first historical valve opening information, the second historical information includes: second historical environmental information, second historical room temperature information and second historical valve opening information, the time difference between the time corresponding to the first historical information and the current time is a first time difference, the time difference between the time corresponding to the second historical information and the current time is a second time difference, and the first time difference is greater than the second time difference; a first training module, used to train a model based on the first historical information to obtain a first model; a second training module, used to correct the first model based on the second historical information to obtain a second model; a determination module, used to determine the valve opening information corresponding to the current environmental information and the preset room temperature information through the second model when the current environmental information and the preset room temperature information are determined.
[0014] According to another embodiment of the present application, a computer-readable storage medium is provided, 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 running.
[0015] According to another embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
[0016] According to another embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.
[0017] Through the present application, the first historical information and the second historical information are obtained, wherein the first historical information includes: the first historical environment information, the first historical room temperature information and the first historical valve opening information, the second historical information includes: the second historical environment information, the second historical room temperature information and the second historical valve opening information, the time difference between the time corresponding to the first historical information and the current time is the first time difference, the time difference between the time corresponding to the second historical information and the current time is the second time difference, and the first time difference is greater than the second time difference; a model is trained based on the first historical information to obtain a first model; the first model is corrected based on the second historical information to obtain a second model; when the current environment information and the preset room temperature information are determined, the valve opening information corresponding to the current environment information and the preset room temperature information is determined by the second model. In the embodiment of the present application, by integrating historical and recent data, constructing and correcting the prediction model, dynamic and intelligent control of the valve opening is achieved, which effectively solves the problem that the traditional method cannot flexibly adapt to changes in heating demand and environmental conditions, and improves the overall efficiency and user experience of the heating system. 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 computer device of a method for determining valve opening information in an embodiment of the present application;
[0021] Figure 2 is a flow chart of a method for determining valve opening information according to an embodiment of the present application;
[0022] Figure 3 is a system block diagram of the second heating network according to an embodiment of the present application;
[0023] Figure 4 It is a structural block diagram of a step-by-step heating control device based on large model deduction according to an embodiment of the present application;
[0024] Figure 5 is a schematic diagram of data according to an embodiment of the present application;
[0025] Figure 6 It is a structural block diagram of a device for determining valve opening information according to an embodiment of the present application. DETAILED DESCRIPTION
[0026] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.
[0028] The method embodiments provided in the embodiments of the present application can be executed in a computer device or a similar computing device. Taking running on a computer device as an example, Figure 1 1 is a hardware structure block diagram of a computer device for determining valve opening information in an embodiment of the present application. Figure 1 As shown, the computer device 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 MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the above-mentioned computer device may also include a transmission device 106 and an input and 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 above-mentioned computer device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.
[0029] 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 determining the valve opening information 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 may be connected to the computer device 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.
[0030] The transmission device 106 is used to receive or send data via a network. The above-mentioned network specific examples may include a wireless network provided by a communication provider of a computer device. 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.
[0031] In this embodiment, a method for determining valve opening information is provided, which is applied to the above-mentioned computer device. Figure 2 is a flow chart of a method for determining valve opening information according to an embodiment of the present application. Figure 2 As shown, the process includes the following steps:
[0032] Step S202, obtaining first historical information and second historical information, wherein the first historical information includes: first historical environment information, first historical room temperature information and first historical valve opening information, and the second historical information includes: second historical environment information, second historical room temperature information and second historical valve opening information, the time difference between the time corresponding to the first historical information and the current time is a first time difference, the time difference between the time corresponding to the second historical information and the current time is a second time difference, and the first time difference is greater than the second time difference;
[0033] In step S202, two sets of historical information are collected, namely, "first historical information" and "second historical information". These information respectively include historical environmental data, room temperature data and valve opening data, covering the operation records within a certain time range. The time difference between the time corresponding to the "first historical information" and the current time is the "first time difference", and the time difference between the time corresponding to the "second historical information" and the current time is the "second time difference", and the "first time difference" is greater than the "second time difference". It can be understood that the "first historical information" covers a wide range of data over a longer period of time, which is used to construct a comprehensive perspective of the model; while the "second historical information" focuses on recent data, reflecting the recent system status and environmental changes, and providing a basis for real-time correction of the model.
[0034] Step S204, training a model based on the first historical information to obtain a first model;
[0035] After collecting the "first historical information", a machine learning model, namely the "first model", is trained based on this information. The training goal of the model is to learn the complex relationship between the environment, room temperature and valve opening, so as to be able to predict the impact on the valve opening based on historical data and room temperature.
[0036] Step S206, modifying the first model based on the second historical information to obtain a second model;
[0037] After the model is trained, the "second historical information" is used to modify the "first model" to generate the "second model". That is, step S206 uses the feedback of recent data to fine-tune or retrain the model to cope with possible drift or changes in environmental conditions in the heating system. The modified model can improve its prediction accuracy and adaptability in the current or future environment, ensuring that the model can better reflect the recent system status, thereby making more accurate valve opening decisions.
[0038] Step S208: When the current environment information and the preset room temperature information are determined, the valve opening information corresponding to the current environment information and the preset room temperature information is determined by the second model.
[0039] Finally, when the "current environment information" and the user's "preset room temperature information" are determined, the "second model" is used to determine the optimal "valve opening information". This process uses the revised model to dynamically calculate the most appropriate valve opening based on real-time environmental parameters and user room temperature requirements to achieve the best heating effect.
[0040] It should be noted that the second model in the embodiment of the present application can also predict future environmental information based on current environmental information, and calculate valve opening information corresponding to the future environmental information and preset room temperature information.
[0041] Through the above steps, the first historical information and the second historical information are obtained, wherein the first historical information includes: the first historical environment information, the first historical room temperature information and the first historical valve opening information, the second historical information includes: the second historical environment information, the second historical room temperature information and the second historical valve opening information, the time difference between the time corresponding to the first historical information and the current time is the first time difference, the time difference between the time corresponding to the second historical information and the current time is the second time difference, and the first time difference is greater than the second time difference; the model is trained based on the first historical information to obtain the first model; the first model is corrected based on the second historical information to obtain the second model; when the current environment information and the preset room temperature information are determined, the valve opening information corresponding to the current environment information and the preset room temperature information is determined by the second model. In the embodiment of the present application, by integrating historical and recent data, constructing and correcting the prediction model, dynamic and intelligent control of the valve opening is achieved, which effectively solves the problem that the traditional method cannot flexibly adapt to changes in heating demand and environmental conditions, and improves the overall efficiency and user experience of the heating system.
[0042] In an exemplary embodiment, before training a model based on the first historical information to obtain a first model, the method further includes: preprocessing the first historical information to obtain processed first historical information; adjusting model parameters of the model using the processed first historical environmental information and the processed first historical room temperature information as input and the processed first historical valve opening information as output to obtain a third model; determining a first performance of the third model based on a first test set, and determining whether to train the third model based on the first performance.
[0043] In the embodiment of the present application, the original "first historical information" is cleaned, converted, and standardized to eliminate unnecessary data errors and reduce interference factors during model training. Data preprocessing includes but is not limited to missing value filling, outlier detection and processing, data standardization or normalization, feature selection, etc., so that the "first historical information" is converted into "processed first historical information" that is more suitable for model training.
[0044] After data preprocessing, the processed environment and room temperature information are used as input, and the valve opening information is used as output to preliminarily adjust the model parameters to form the "third model". This process is the parameter initialization or tuning stage before model training, which aims to find a set of parameter values so that the model can perform well in the early stages of training. Through preliminary adjustments, the poor results caused by random initialization in the early stages of model training can be avoided, and the efficiency and quality of model training can be improved.
[0045] After the initial adjustment of the parameters, the performance of the "third model" needs to be evaluated to determine whether it has achieved the expected performance indicators. For example, the processed historical data set is divided into a training set and a test set, the training set is used to train the model, and then an independent "first test set" is used to evaluate the generalization ability of the model, that is, the model's ability to predict unseen data. Based on the "first performance" determined by the "first test set", if the model's performance does not meet the preset threshold or standard,
[0046] This performance indicator will be used to determine whether further training or parameter adjustment of the "third model" is required.
[0047] Before training the model based on the first historical information, the training quality and practicality of the model can be effectively improved through data preprocessing, preliminary adjustment of model parameters, model performance evaluation and iterative training decision-making steps, ensuring that the model can better cope with the dynamically changing environment of valve opening control in the heating system and improve the accuracy of prediction and control.
[0048] In an exemplary embodiment, determining whether to train the third model based on the first performance includes: when the first performance meets the first preset performance, stopping training the third model and determining the third model to be the first model; when the first performance does not meet the first preset performance, training the third model to obtain a fourth model; determining the second performance of the fourth model based on a second test set, and determining whether to train the fourth model based on the second performance of the fourth model.
[0049] After the initial adjustment of the model parameters, the performance of the "third model" was evaluated using the "first test set" to determine its "first performance".
[0050] If the "first performance" meets the preset performance standard ("first preset performance"), it is considered that the model has met the basic usage requirements, and the training can be stopped at this time, and the "third model" can be directly determined as the "first model" for subsequent processing. On the contrary, if the "first performance" does not meet the "first preset performance", the "third model" will enter the formal training stage to further improve its performance.
[0051] If the initial validation fails, the “third model” will be trained again. This stage involves multiple training cycles, and the model parameters are continuously adjusted and the model structure is optimized to improve the accuracy and generalization ability of the model.
[0052] In order to evaluate the performance of the trained model, a "second test set" is introduced to test the performance of the "fourth model", that is, to determine its "second performance". The evaluation results of the "second performance" will determine whether the "fourth model" needs to be further trained or adjusted. If the performance meets the requirements, it can be considered that the training process has been successful and the model can be used in actual heating system control; if the performance is still not up to standard, it is necessary to continue training or adopt other strategies for optimization.
[0053] For example, suppose you are developing a machine learning model for valve position control in a heating system.
[0054] After the initial adjustment of the model parameters, the "first test set" containing data from the past year was used to evaluate the initial performance of the model. Assume that the preset performance requires the model's prediction accuracy to reach more than 80%. Through testing, it was found that the prediction accuracy of the model after the initial adjustment (i.e., the "third model") was 75%, which did not meet the preset performance. Therefore, it was decided to enter the formal training phase.
[0055] The "third model" was trained using a large amount of historical data, and the prediction accuracy of the model gradually improved through multiple training cycles. After the last training, the "second test set" containing the data of the last month was used to evaluate the final performance of the model, and the prediction accuracy was 82%. This time, the "second performance" of the "fourth model" reached the preset performance standard, indicating that the training process was successful.
[0056] Since the "second performance" of the "fourth model" meets the requirements, no additional training is required. At this time, the "fourth model" can be determined as the final "first model" for real-time control of the heating system.
[0057] This process not only ensures that the model has a certain basic performance at the beginning of training, but also further optimizes the model through formal training and verification, so that it can more accurately predict the valve opening in actual applications to adapt to changes in heating demand and environmental conditions.
[0058] In an exemplary embodiment, before modifying the first model based on the second historical information to obtain the second model, the method further includes: preprocessing the second historical information to obtain processed second historical information, wherein a data format of the processed second historical information is consistent with a data input format of the first model; determining a third performance of the first model based on the second historical information; and determining whether to modify the first model based on the third performance.
[0059] It should be noted that data preprocessing is an important step before training or correcting any data-driven model. It ensures the quality and consistency of the data and is the basis for the model to accurately predict. In the embodiment of the present application, the "second historical information" is preprocessed mainly to clean the data, fill in missing values, standardize or normalize the data, and ensure that the data format is consistent with the input format of the "first model".
[0060] The performance of the "first model" is evaluated using the "second historical information" to determine its "third performance". This evaluation process is intended to check the performance of the "first model" on recent data, because the "second historical information" contains conditions that are closer to the current environment. The evaluation of the "third performance" includes but is not limited to indicators such as prediction error, accuracy, recall, F1 score, etc., depending on the model's task objectives and specific application areas.
[0061] Based on the evaluation results of the "third performance", decide whether the "first model" needs to be revised. If the model performs well, that is, the "third performance" meets or exceeds the preset performance standards, then there may be no need to further revise the model. However, if the "third performance" does not meet the preset standards, it indicates that the model has prediction bias or insufficient generalization ability when processing the latest data. At this time, the model needs to be revised to obtain the "second model". The revision process includes but is not limited to fine-tuning of model parameters, reselection of features, adjustment of model structure, etc., to improve the model's adaptability to recent data and prediction accuracy.
[0062] For example, suppose that the "first model" is trained on a large amount of past data and is used to predict the valve opening of the heating system. However, due to the rapid changes in conditions such as ambient temperature and user demand, it is necessary to evaluate the performance of the model on recent data. For example, after preprocessing with the "second historical information" of the past week, it was found that the model's prediction of heating demand under extreme weather conditions last week was not accurate enough, that is, the "third performance" was lower than the preset performance index (for example, the prediction error was less than 5%). Based on this evaluation result, it is determined to revise the "first model" by fine-tuning the model parameters so that it can make more accurate predictions when dealing with similar extreme conditions. The revised model (ie, the "second model") passes the test again. If the performance meets or exceeds the preset standard, it can be used for real-time adjustment to improve the response speed and efficiency of the heating system.
[0063] Through the embodiments of the present application, it is possible to ensure that the model not only performs well on long-term series data, but also can flexibly adapt to short-term environmental changes, improve the accuracy of prediction and the precision of control, thereby achieving more efficient heating system management.
[0064] In an exemplary embodiment, determining whether to correct the first model is based on the third performance, including: when the third performance does not meet the second preset performance, determining to correct the first model, and adjusting the model parameters of the first model through the second historical information to obtain the second model; when the third performance meets the second preset performance, determining not to correct the first model, and when determining the current environmental information and the preset room temperature information, determining the valve opening information corresponding to the current environmental information and the preset room temperature information through the first model.
[0065] If the "third performance" reaches or exceeds the "second preset performance", it means that the current configuration of the model can handle the recent heating data well, at least within the preset performance index range. In this case, the "first model" is not modified, but directly used to predict the valve opening of the current heating system.
[0066] On the contrary, if the "third performance" does not reach the "second preset performance", it means that the model has a large error or deficiency when processing recent data. In this case, the "first model" is corrected by adjusting the model parameters in order to further optimize the model performance so that it can more accurately reflect the dynamics of the current heating system, thereby obtaining the "second model".
[0067] In the case of deciding to revise the "first model", the "second historical information" will be used to adjust the model parameters to optimize its performance. This adjustment includes but is not limited to: fine-tuning of parameters, selection of features, optimization of model structure, etc.
[0068] In an exemplary embodiment, after determining the valve opening information corresponding to the current environmental information and the preset room temperature information through the second model, it also includes: sending control information to the heat exchange station so that the heat exchange station adjusts the valve opening according to the control information, wherein the control information carries the valve opening information.
[0069] After the "second model" predicts the optimal "valve opening information" corresponding to the "current environmental information" and the "preset room temperature information", the "valve opening information" predicted by the "second model" is packaged into "control information" in a specific format. This information not only contains the numerical value of the valve opening, but also includes but is not limited to: metadata such as the identification of the target device and the operation timestamp, to ensure that the heat exchange station can accurately identify and execute commands.
[0070] The "control information" is sent to the heat exchange station through a pre-set communication protocol and network (such as a wireless network, wired network or dedicated control network). This communication process needs to ensure the security and real-time nature of the information to avoid data tampering or delay during transmission, which would affect the stable operation of the heating system.
[0071] After the heat exchange station receives the "control information", the control system will decode this information, extract the specific "valve opening information", and convert it into actual operation of the valve (such as adjusting the valve opening through the motor). After the valve opening is adjusted, new environmental data (such as actual room temperature, current external meteorological conditions, etc.) will be collected and compared with the model prediction to form a feedback loop. If it is found that the current room temperature deviates from the preset value, the "second model" can be called again for prediction and new control information can be sent until the room temperature reaches the preset value.
[0072] In order to better understand the process of the method for determining the valve opening information above, the implementation method flow of determining the valve opening information above is described below in combination with an optional embodiment, but it is not used to limit the technical solution of the embodiment of the present application.
[0073] In this embodiment, a method for determining valve opening information is provided. Figure 3 is a system block diagram of the second heating network according to an embodiment of the present application, such as Figure 3 As shown, it includes: a user building (1), a room temperature sensor (2), a control valve (3), and a heat exchange station (4).
[0074] exist Figure 3 In the heating network system, hot water is regulated by the control valve (3) from the heat exchange station (4) and then distributed to each user building (1). The system incorporates environmental adaptability, and its operating efficiency is reflected under different meteorological conditions. The feedback of room temperature effects is different. This process is recorded by the room temperature sensors (2) distributed at the user end, and the room temperature parameters are collected to ensure real-time monitoring and data collection of system performance.
[0075] Figure 4 is a structural block diagram of a step-by-step heating control device based on large model deduction according to an embodiment of the present application, Figure 5 It is a schematic diagram of data according to an embodiment of the present application, wherein the data includes: historical data (equivalent to the first historical information in the embodiment of the present application), recent data (equivalent to the second historical information in the embodiment of the present application) and predicted data, and a heat supply network control device includes: a data collection module (5), a feature extraction module (6), a large model analysis module (7), a large model correction module (8), and a prediction and control module (9).
[0076] The data collection module (5) not only integrates meteorological parameters such as temperature, wind speed, and light, but also collects room temperature parameters and valve opening parameters, which show unique change patterns over time. Subsequently, the feature extraction module (6) conducts in-depth analysis of the long-term historical parameters in the past, identifies and summarizes the characteristics of various parameters changing over time, including the trend of meteorological conditions, the best practices of valve opening under different meteorological conditions, and the response mode of room temperature to valve opening adjustment.
[0077] Based on the feature extraction results, the large model analysis module (7) trains a large model that integrates the complex relationship between room temperature, valve opening and meteorological parameters. This model not only captures the key laws of heating system operation, but also performs strategy deduction to predict the valve opening strategy required to achieve the preset room temperature under specific meteorological conditions.
[0078] The large model calibration module (8) uses the real-time data collected recently to calibrate the accuracy of the large model to ensure that the model can adapt to the changing environment, especially focusing on the accuracy of the valve opening strategy under a given room temperature. After this calibration process, the adaptability and prediction of the large model are improved.
[0079] 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 this 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 described in each embodiment of the present application.
[0080] In this embodiment, a device for determining valve opening information 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 device described in the following embodiments is preferably implemented in software, it is also possible and conceivable to implement it in hardware, or in a combination of software and hardware.
[0081] Figure 6 is a structural block diagram of a device for determining valve opening information according to an embodiment of the present application, such as Figure 6 As shown, the device comprises:
[0082] an acquisition module 62, configured to acquire first historical information and second historical information, wherein the first historical information includes: first historical environment information, first historical room temperature information, and first historical valve opening information, and the second historical information includes: second historical environment information, second historical room temperature information, and second historical valve opening information, the time difference between the time corresponding to the first historical information and the current time is a first time difference, the time difference between the time corresponding to the second historical information and the current time is a second time difference, and the first time difference is greater than the second time difference;
[0083] A first training module 64, configured to train a model based on the first historical information to obtain a first model;
[0084] A second training module 66, configured to modify the first model based on the second historical information to obtain a second model;
[0085] The determination module 68 is used to determine the valve opening information corresponding to the current environment information and the preset room temperature information by using the second model when the current environment information and the preset room temperature information are determined.
[0086] Through the above-mentioned device, the first historical information and the second historical information are obtained, wherein the first historical information includes: the first historical environment information, the first historical room temperature information and the first historical valve opening information, the second historical information includes: the second historical environment information, the second historical room temperature information and the second historical valve opening information, the time difference between the time corresponding to the first historical information and the current time is the first time difference, the time difference between the time corresponding to the second historical information and the current time is the second time difference, and the first time difference is greater than the second time difference; the model is trained based on the first historical information to obtain the first model; the first model is corrected based on the second historical information to obtain the second model; when the current environment information and the preset room temperature information are determined, the valve opening information corresponding to the current environment information and the preset room temperature information is determined by the second model. In the embodiment of the present application, by integrating historical and recent data, constructing and correcting the prediction model, dynamic and intelligent control of the valve opening is achieved, which effectively solves the problem that the traditional method cannot flexibly adapt to changes in heating demand and environmental conditions, and improves the overall efficiency and user experience of the heating system.
[0087] In an exemplary embodiment, a first training module 64 is used to preprocess the first historical information to obtain processed first historical information; adjust the model parameters of the model using the processed first historical environmental information and the processed first historical room temperature information as input and the processed first historical valve opening information as output to obtain a third model; determine a first performance of the third model based on a first test set, and determine whether to train the third model based on the first performance.
[0088] In an exemplary embodiment, the first training module 64 is used to stop training the third model and determine that the third model is the first model when the first performance meets the first preset performance; train the third model to obtain a fourth model when the first performance does not meet the first preset performance; determine the second performance of the fourth model based on the second test set, and determine whether to train the fourth model based on the second performance of the fourth model.
[0089] In an exemplary embodiment, the second training module 66 is used to preprocess the second historical information to obtain processed second historical information, wherein the data format of the processed second historical information is consistent with the data input format of the first model; determine the third performance of the first model based on the second historical information; and determine whether to modify the first model based on the third performance.
[0090] In an exemplary embodiment, the second training module 66 is used to determine that the first model should be corrected when the third performance does not meet the second preset performance, and adjust the model parameters of the first model through the second historical information to obtain the second model; when the third performance meets the second preset performance, determine not to correct the first model, and when the current environmental information and the preset room temperature information are determined, determine the valve opening information corresponding to the current environmental information and the preset room temperature information through the first model.
[0091] In an exemplary embodiment, the device further includes: a sending module, configured to send control information to the heat exchange station so that the heat exchange station adjusts the opening of the valve according to the control information, wherein the control information carries the valve opening information.
[0092] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.
[0093] 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 running.
[0094] Optionally, in this embodiment, the storage medium may be configured to store program codes for executing the following steps:
[0095] S1, obtaining first historical information and second historical information, wherein the first historical information includes: first historical environment information, first historical room temperature information and first historical valve opening information, and the second historical information includes: second historical environment information, second historical room temperature information and second historical valve opening information, the time difference between the time corresponding to the first historical information and the current time is a first time difference, the time difference between the time corresponding to the second historical information and the current time is a second time difference, and the first time difference is greater than the second time difference;
[0096] S2, training a model based on the first historical information to obtain a first model;
[0097] S3, modifying the first model based on the second historical information to obtain a second model;
[0098] S4, when the current environment information and the preset room temperature information are determined, the valve opening information corresponding to the current environment information and the preset room temperature information is determined by the second model.
[0099] 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.
[0100] 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.
[0101] 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.
[0102] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:
[0103] S1, obtaining first historical information and second historical information, wherein the first historical information includes: first historical environment information, first historical room temperature information and first historical valve opening information, and the second historical information includes: second historical environment information, second historical room temperature information and second historical valve opening information, the time difference between the time corresponding to the first historical information and the current time is a first time difference, the time difference between the time corresponding to the second historical information and the current time is a second time difference, and the first time difference is greater than the second time difference;
[0104] S2, training a model based on the first historical information to obtain a first model;
[0105] S3, modifying the first model based on the second historical information to obtain a second model;
[0106] S4, when the current environment information and the preset room temperature information are determined, the valve opening information corresponding to the current environment information and the preset room temperature information is determined by the second model.
[0107] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.
[0108] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.
[0109] An embodiment of the present application also provides a computer program, which includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in any one of the above method embodiments.
[0110] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:
[0111] S1, obtaining first historical information and second historical information, wherein the first historical information includes: first historical environment information, first historical room temperature information and first historical valve opening information, and the second historical information includes: second historical environment information, second historical room temperature information and second historical valve opening information, the time difference between the time corresponding to the first historical information and the current time is a first time difference, the time difference between the time corresponding to the second historical information and the current time is a second time difference, and the first time difference is greater than the second time difference;
[0112] S2, training a model based on the first historical information to obtain a first model;
[0113] S3, modifying the first model based on the second historical information to obtain a second model;
[0114] S4, when the current environment information and the preset room temperature information are determined, the valve opening information corresponding to the current environment information and the preset room temperature information is determined by the second model.
[0115] 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.
[0116] 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.
[0117] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.
Claims
1. A method for determining valve opening information, characterized in that: include: Acquire first historical information and second historical information, wherein the first historical information includes: first historical environmental information, first historical room temperature information and first historical valve opening information, the The second historical information includes: second historical environment information, second historical room temperature information, and second historical valve opening information, the time difference between the time corresponding to the first historical information and the current time is the first time difference, the time difference between the time corresponding to the second historical information and the current time is the second time difference, and the first time difference is greater than the second time difference; Training a model based on the first historical information to obtain a first model; The first model is modified based on the second historical information to obtain a second model; when the current environmental information and the preset room temperature information are determined, the valve opening information corresponding to the current environmental information and the preset room temperature information is determined by the second model.
2. The method according to claim 1, characterized in that Before training a model based on the first historical information to obtain a first model, the method further includes: Preprocessing the first historical information to obtain processed first historical information; adjusting the model parameters of the model using the processed first historical environment information and the processed first historical room temperature information as input and the processed first historical valve opening information as output to obtain a third model; A first performance of the third model is determined based on the first test set, and whether to train the third model is determined according to the first performance.
3. The method according to claim 2, characterized in that Determining whether to train the third model according to the first performance includes: When the first performance meets the first preset performance, stop training the third model and determine that the third model is the first model; When the first performance does not meet the first preset performance, the third model is trained to obtain a fourth model; the second performance of the fourth model is determined based on the second test set, and it is determined whether to train the fourth model according to the second performance of the fourth model.
4. The method according to claim 1, characterized in that: Before modifying the first model based on the second historical information to obtain the second model, the method further includes: Preprocessing the second historical information to obtain processed second historical information, wherein a data format of the processed second historical information is consistent with a data input format of the first model; determining a third performance of the first model based on second historical information; Determine whether to modify the first model according to the third performance.
5. The method according to claim 4, characterized in that Determining whether to modify the first model according to the third performance includes: In a case where the third performance does not meet the second preset performance, determining to correct the first model, and adjusting the model parameters of the first model according to the second historical information to obtain the second model; When the third performance meets the second preset performance, it is determined that the first model is not to be corrected, and when the current environmental information and the preset room temperature information are determined, the valve opening information corresponding to the current environmental information and the preset room temperature information is determined by the first model.
6. The method according to claim 1, characterized in that After determining the valve opening information corresponding to the current environment information and the preset room temperature information through the second model, the method further includes: Control information is sent to the heat exchange station so that the heat exchange station adjusts the opening of the valve according to the control information, wherein the control information carries the valve opening information.
7. A device for determining valve opening information, characterized in that: include: an acquisition module, configured to acquire first historical information and second historical information, wherein the first historical information includes: first historical environment information, first historical room temperature information, and first historical valve opening information, and the second historical information includes: second historical environment information, second historical room temperature information, and second historical valve opening information, the time difference between the time corresponding to the first historical information and the current time is a first time difference, the time difference between the time corresponding to the second historical information and the current time is a second time difference, and the first time difference is greater than the second time difference; A first training module, used for training a model based on the first historical information to obtain a first model; a second training module, configured to modify the first model based on the second historical information to obtain a second model; A determination module is used to determine the valve opening information corresponding to the current environment information and the preset room temperature information through the second model when the current environment information and the preset room temperature information are determined.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the method according to any one of claims 1 to 6 is executed when the program is 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.