Thermal station difference analysis method and system based on AI

Abstract

The invention relates to the technical field of data analysis, in particular to a thermal station difference analysis method and system based on AI, and the method comprises the steps: obtaining a large amount of historical operation data, sampling room temperature and the like of a thermal station, cleaning the data, and removing missing or invalid data. The heat supply parameters related to the health degree, namely the evaluation parameters, are found by analyzing the differences between the values of the heat supply parameters and the reference values when the heating station operates under various conditions. Then, a health degree influence model is constructed based on historical samples of evaluation parameters, so that health degree evaluation is performed on training data, the influence of health degree dimensions on heat supply parameter values is introduced, and the model is trained; and the values of the heat supply parameters are automatically speculated according to the training model, and different heat supply stations are compensated by using the predicted values, that is, the operation parameter compensation can be executed according to the actual conditions of the different heat supply stations. And the problems of unreliability and neglect of health degree influence during manual filling of the heat supply parameters of the heating station are avoided.

Description

Technical Field

[0001] This invention relates to the field of data analysis technology, specifically to an AI-based method and system for analyzing differences in thermal power stations. Background Technology

[0002] With the acceleration of urbanization, the scale of urban centralized heating is constantly expanding. Many large and medium-sized cities have built relatively large heating pipeline systems, covering a large number of residential communities, commercial areas, and public buildings. The coverage rate of centralized heating is generally high in northern cities, effectively improving the comfort of residents' lives in winter, while also contributing to urban energy conservation and emission reduction. For example, in some cities in Northeast and North China, the coverage rate of centralized heating can reach over 80%, basically guaranteeing the heating needs of most users in urban areas.

[0003] As a crucial link connecting heat sources and users, the construction and operation of heating networks are of paramount importance. After years of development, most city heating networks have formed relatively complex ring or branch-like layouts. At the same time, the hydraulic balance regulation of the network system is quite difficult, and uneven heating may occur between different areas and different users; for example, some users may have excessively high indoor temperatures, while others may have insufficient indoor temperatures.

[0004] Because different heating stations serve communities built at different times, with varying insulation structures and different heat dissipation methods for users, different heating station systems require different heating parameters for operation. In the past, deviations in heating station system parameters were mainly filled in manually by heating company operators based on experience, which was time-consuming, labor-intensive, and its accuracy was questionable. Furthermore, the health of the heating station equipment also affects the system's heating parameters; since health is implicit, the parameters filled in by operators often overlooked its impact. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide an AI-based method and system for analyzing the differences in thermal power stations, so as to solve the problems in the background art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] The present invention provides an AI-based method for analyzing the differences between heat stations, comprising the following steps:

[0008] The system acquires basic information about multiple heating stations, historical operating data of multiple heating stations at multiple historical time points, and sampled room temperatures of covered users at multiple historical time points; it also acquires reference values ​​and maintenance records of multiple heating parameters of multiple heating stations. The historical operating data includes values ​​of multiple heating parameters and values ​​of multiple environmental parameters, and the basic information includes unit number, year of construction, year of construction of the heating coverage area, and heating area.

[0009] Based on the sampled room temperature, the historical operating data of multiple heating stations at multiple historical time points are filtered and cleaned to obtain the target operating data of the heating stations under normal operating conditions.

[0010] For each heating station, the differences between the values ​​of various heating parameters in the target operation data and the reference values ​​are calculated. Based on the differences of various heating parameters corresponding to multiple historical time points and the maintenance records, time-series statistical analysis is performed to obtain evaluation parameters related to health. A health impact model is constructed based on the values ​​of the evaluation parameters of multiple heating stations at multiple historical time points. The health impact model represents the correspondence between the health value and the value of the evaluation parameter.

[0011] Preliminary training data is constructed based on basic information of multiple heating stations and target operation data at multiple historical time points. The health of the training data is evaluated based on the health impact model to obtain training data that integrates the health dimension. The artificial neural network is trained based on the training data to obtain a heating parameter prediction model.

[0012] The heating parameters of the heating station are predicted based on the health status impact model and the heating parameter prediction model to obtain the predicted difference value, and the reference value of the heating parameter of the corresponding heating station is compensated based on the predicted difference value.

[0013] In one embodiment of this application, historical operating data of multiple heating stations at multiple historical time points are filtered and cleaned based on the sampled room temperature to obtain target operating data of the heating stations under normal operating conditions, including:

[0014] The sampled room temperature in the historical operating data is compared with the preset normal operating temperature range, and the historical operating data in which the sampled room temperature is within the preset normal operating temperature range is retained to obtain intermediate data;

[0015] For any missing intermediate data, perform linear interpolation to fill in the missing data or delete the missing data to obtain the target running data.

[0016] In one embodiment of this application, calculating the difference between the values ​​of various heating parameters in the target operating data and reference values ​​includes:

[0017] For any heating station, the values ​​of various environmental parameters and various heating parameters corresponding to multiple historical time points are obtained, and the values ​​of various heating parameters corresponding to multiple historical time points are corrected based on a pre-built environmental correction model to obtain the corrected values ​​of various heating parameters corresponding to multiple historical time points under standard environmental conditions. The environmental correction model characterizes the influence ratio of different environmental conditions on the values ​​of heating parameters.

[0018] The difference value is obtained by subtracting the correction value of each heating parameter from the corresponding reference value.

[0019] In one embodiment of this application, the method for constructing the environmental correction model includes:

[0020] Based on the aforementioned basic information, multiple heating stations are clustered to obtain a set of multiple heating stations with similar hardware facilities.

[0021] The maintenance time points of multiple heating stations are extracted from the maintenance records, and multiple operating cycles of multiple heating stations are extracted based on the maintenance time points, with the center time point of each operating cycle as the reference time point.

[0022] The values ​​of various environmental parameters at multiple reference time points for each heating station set are normalized to obtain a sequence of environmental parameters; and the values ​​of various heating parameters at multiple reference time points for each heating station set are normalized to obtain a sequence of heating parameters.

[0023] For any combination of environmental and heating parameters, the time-series correlation coefficients of the corresponding environmental and heating parameter sequences are calculated after binarization based on the intra-series average values. Combinations with time-series correlation coefficients greater than a predetermined correlation coefficient are considered as correlated combinations. The time-series correlation coefficients... The mathematical expression is:

[0024]

[0025] In the formula, This represents the binarized sequence of environmental parameters. This represents the binarized sequence of heating parameters;

[0026] Extract all associated environmental parameters for each heating parameter from the relevant combinations, and construct the relationship between the heating parameter and all associated environmental parameters; then perform multivariate linear fitting on the relationship based on the value of the heating parameter at the reference time point to obtain the relationship between the heating parameter and all associated environmental parameters.

[0027] An environmental correction model is constructed based on the relationships between various heating parameters from multiple heating stations.

[0028] In one embodiment of this application, time-series statistical analysis is performed based on the differences in various heating parameters corresponding to multiple historical time points and the maintenance records to obtain evaluation parameters related to health status, including:

[0029] Extract maintenance time points for multiple heating stations from the maintenance records;

[0030] Based on the maintenance time points, one or more operating cycles for each heating parameter and the difference values ​​of multiple historical time points within the operating cycle are extracted. The two ends of the operating cycle are the maintenance time points, with the first maintenance time point being zero. ;

[0031] For each historical time point within the aforementioned operating cycle Calculate historical time points With the zero point Interval duration The duration sequence was obtained; and based on each heating parameter The difference value is constructed from the difference values ​​at each historical time point within the said operating cycle. Sequence, where, Represent natural numbers;

[0032] The duration sequence and the difference value sequence are normalized respectively to obtain the normalized duration sequence and the normalized difference value sequence;

[0033] Calculate the correlation between the normalized duration sequence and the normalized difference sequence. Heating parameters with a correlation greater than a preset correlation threshold are used as evaluation parameters related to health, wherein the correlation is calculated as follows:

[0034]

[0035] In the formula, Represents the normalized i-th Duration, This represents the average normalized duration in the normalized duration sequence. Represents the normalized i-th One difference value, These are the normalized differences in the normalized difference value sequence.

[0036] In one embodiment of this application, a health impact model is constructed based on the values ​​of evaluation parameters from multiple thermal stations at multiple historical time points, including:

[0037] Based on the aforementioned basic information, multiple heating stations are clustered to obtain a set of multiple heating stations with similar hardware facilities.

[0038] Extract maintenance time points for multiple heating stations from the maintenance records;

[0039] Based on the maintenance time points, multiple operating cycles C are extracted from the maintenance records, and the initial reference values ​​of the evaluation parameters at the first time point of each operating cycle C are extracted. The final reference value of the evaluation parameters at the last time point. ; and the initial reference value based on the environmental correction model. and the aforementioned end reference value Make corrections to obtain the initial correction reference value. and end of correction reference value ,in, Indicates the sequence number of the heating parameter;

[0040] Calculate the first and last differences of the evaluation parameters in each running cycle. , ; Filter out the largest difference and the maximum difference The health of the corresponding runtime cycle is set to 0, while the health of other runtime cycles is set to... for:

[0041]

[0042] In the formula, The difference between the first and last evaluation parameters for the operating cycle C;

[0043] For any set of heating stations, the following relationship is constructed based on multiple evaluation parameters:

[0044]

[0045] In the formula, Indicates the number of evaluation parameters. Indicates the coefficient of the term, Indicates the offset. Indicates health status;

[0046] Initial correction reference values ​​based on multiple operating cycles of the heating station cluster End of correction reference value and health The relationship is fitted with multiple linear equations to obtain the health influence relationship of the current set of heating stations; and a health influence model is constructed based on the health influence relationship of multiple sets of heating stations.

[0047] In one embodiment of this application, the training data is evaluated for health based on the health impact model to obtain training data that integrates health dimensions, including:

[0048] The source heat station for obtaining training data is used to determine the target health influence relationship from the health influence model based on the source heat station.

[0049] Substituting the values ​​of the evaluation parameters in the training data into the target health influence formula, we obtain the health of the source heat station when the training data was generated, and thus obtain preliminary training data that integrates the health dimension.

[0050] The difference between the initial training data and the pre-constructed reference data is calculated to obtain the training data, wherein the reference data is empirical data.

[0051] In one embodiment of this application, an artificial neural network is trained based on the training data to obtain a heating parameter prediction model, including:

[0052] S1, Input the training data into the artificial neural network to obtain the predicted value;

[0053] S2, calculate the loss between the predicted vector and the heating parameter values ​​in the training data based on the loss function, adjust the parameters of the artificial neural network based on the loss, and return to step S1 until a fit is obtained to obtain the heating parameter prediction model.

[0054] In one embodiment of this application, the heating parameters of a heating station are predicted based on the health status impact model and the heating parameter prediction model to obtain predicted difference values, including:

[0055] Obtain the values ​​of various heating parameters and various environmental parameters acquired at the most recent data collection point of the target heating station, and obtain the environmental prediction data of the area where the target heating station is located;

[0056] The values ​​of various heating parameters are corrected based on the environmental correction model to obtain corrected values ​​for various heating parameters;

[0057] The values ​​of the evaluation parameters among various heating parameters are input into the health status impact model to obtain the health status;

[0058] The basic information, health status, and values ​​of various heating parameters and environmental parameters obtained at the most recent collection time of the target heating station are vectorized and input into the heating parameter prediction model to obtain the heating parameter prediction vector.

[0059] This application also provides an AI-based thermal station difference analysis system, including:

[0060] The acquisition module is used to acquire basic information of multiple heating stations, historical operating data of multiple heating stations at multiple historical time points, and sampled room temperature of covered users at multiple historical time points; and to acquire reference values ​​and maintenance records of multiple heating parameters of multiple heating stations. The historical operating data includes values ​​of multiple heating parameters and values ​​of multiple environmental parameters. The basic information includes unit number, year of construction, year of construction of the heating coverage area, and heating area.

[0061] The data cleaning module is used to filter and clean the historical operating data of multiple heating stations at multiple historical time points based on the sampled room temperature, so as to obtain the target operating data of the heating stations under normal operating conditions.

[0062] The health model module is used to calculate the difference between the values ​​of various heating parameters and reference values ​​in the target operating data for each heating station, and to perform time-series statistical analysis based on the difference values ​​of various heating parameters corresponding to multiple historical time points to obtain evaluation parameters related to health. Furthermore, a health impact model is constructed based on the values ​​of the evaluation parameters for multiple heating stations at multiple historical time points, wherein the health impact model characterizes the correspondence between health values ​​and the values ​​of the evaluation parameters.

[0063] The prediction model building module is used to construct preliminary training data based on the basic information of multiple heating stations and the target operation data at multiple historical time points, and to evaluate the health of the training data based on the health impact model to obtain training data that integrates the health dimension; and to train an artificial neural network based on the training data to obtain a heating parameter prediction model.

[0064] The predictive analysis module is used to predict the heating parameters of the heating station based on the health impact model and the heating parameter prediction model, obtain the predicted difference value, and compensate the reference value of the heating parameter of the corresponding heating station based on the predicted difference value.

[0065] The beneficial effects of this invention are as follows: This invention provides an AI-based method and system for analyzing differences in heating station data. It acquires a large amount of historical operating data from heating stations, samples room temperatures, etc., and then cleans the data to remove missing or invalid data. It utilizes the differences between heating parameter values ​​and reference values ​​under various operating conditions of the heating station, and analyzes these differences to find heating parameters related to health status, i.e., evaluation parameters. Then, based on historical samples of the evaluation parameters, a health status impact model is constructed, thereby providing health status evaluation for training data, introducing the influence of the health status dimension on the values ​​of heating parameters, and training the model. Based on the trained model, it automatically predicts the difference values ​​of heating parameters and uses the predicted difference values ​​to compensate for different heating stations. In other words, it can perform operating parameter compensation according to the actual situation of different heating stations. This avoids the problems of unreliability and neglect of the health status impact when manually entering heating station parameters. Attached Figure Description

[0066] The present invention will be further described below with reference to the accompanying drawings and embodiments:

[0067] Figure 1 This is a flowchart illustrating an AI-based heat station difference analysis method in one embodiment of this application;

[0068] Figure 2 This is a data cleaning flowchart of one embodiment of this application;

[0069] Figure 3This is a flowchart illustrating the difference value calculation in one embodiment of this application;

[0070] Figure 4 This is a schematic diagram of the evaluation parameter analysis process in this application;

[0071] Figure 5 This is a flowchart illustrating the method for constructing a health impact model in one embodiment of this application;

[0072] Figure 6 This is a schematic diagram of the heating parameter prediction process in one embodiment of this application;

[0073] Figure 7 This is a structural diagram of an AI-based thermal station difference analysis system shown in one embodiment of this application. Detailed Implementation

[0074] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0075] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the layers related to the present invention and are not drawn according to the actual number, shape and size of the layers in the actual implementation. In the actual implementation, the form, number and proportion of each layer can be arbitrarily changed, and the layer layout may also be more complex.

[0076] Numerous details are explored in the following description to provide a more thorough explanation of embodiments of the invention; however, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details.

[0077] Figure 1 This is a flowchart illustrating an AI-based heat station difference analysis method in one embodiment of this application, as shown below. Figure 1 As shown, the specific process includes:

[0078] S110: Obtain basic information of multiple heating stations, historical operation data of multiple heating stations at multiple historical time points, and sampled room temperature of covered users at multiple historical time points; and obtain reference values ​​and maintenance records of multiple heating parameters of multiple heating stations, wherein the historical operation data includes values ​​of multiple heating parameters and values ​​of multiple environmental parameters;

[0079] Specifically, the basic information of a heating station includes: unit number, year of construction, year of construction of the heating coverage area, and heating area, etc.

[0080] Heating parameters include: primary supply and return temperature and pressure; secondary supply and return temperature and pressure; unit heating area; radiator type; unit primary instantaneous flow rate, instantaneous heat output, cumulative flow rate, and cumulative heat output; feedback opening of electric regulating valve, etc. If the data is incomplete, the minimum data categories should include: unit number, date and time, secondary supply and return temperature, and unit heating area.

[0081] Environmental parameters include: temperature, humidity, and wind speed;

[0082] The sampling room temperature refers to the temperature at the sampling point within the heated residential area, and the temperature is collected at regular intervals.

[0083] For example, the simplest sample of operational data includes {unit number, collection time, secondary supply and return temperature, unit heating area, temperature, humidity, wind speed, and sampled room temperature}.

[0084] S120, Based on the sampled room temperature, the historical operating data of multiple heating stations at multiple historical time points are filtered and cleaned to obtain the target operating data of the heating stations under normal operating conditions;

[0085] Figure 2 This is a data cleaning flowchart of one embodiment of this application, such as... Figure 2 As shown, operational data samples collected at different time points may contain missing or distorted data. Therefore, before using the operational data samples for analysis, data cleaning is required, including:

[0086] S121, compare the sampled room temperature in the historical operation data with the preset normal operating temperature range, and retain the historical operation data where the sampled room temperature is within the preset normal operating temperature range to obtain intermediate data;

[0087] Based on the equipment design parameters or industry standard settings (e.g., 20℃ ≤ sampling room temperature ≤ 30℃), check whether the sampling room temperature of each record in the historical data is within the preset range. Retain data that falls within the range and discard data that does not. This process filters out data that is in the heating phase or abnormal data, retaining only data with normal heating parameters.

[0088] S122: For any missing intermediate data, perform linear interpolation to fill in the missing data or delete the missing data to obtain the target running data.

[0089] For data with fewer than 3 missing items, linear interpolation can be used to supplement the missing items based on data from the two time points before and after the missing items. However, data with more than 3 missing items should be discarded.

[0090] S130, for each heating station, calculate the difference between the values ​​of various heating parameters in the target operation data and the reference values, and perform time-series statistical analysis based on the difference values ​​of various heating parameters corresponding to multiple historical time points and the maintenance records to obtain evaluation parameters related to health; and construct a health impact model based on the values ​​of evaluation parameters of multiple heating stations at multiple historical time points, wherein the health impact model characterizes the correspondence between health values ​​and the values ​​of the evaluation parameters;

[0091] In this application, a decline in the health of heating station equipment (such as heat exchangers, circulating water pumps, valves, etc.) (e.g., scaling, wear, blockage, aging) directly leads to deviations in heating parameters from design reference values. For example, if scale forms on the heat exchange surface, the secondary network supply water temperature will be lower than the design value, resulting in an increased supply and return water temperature difference. Insufficient flow will cause a drop in supply and return water pressure in the primary or secondary network, leading to abnormal temperature differences. Pressure or flow parameters will deviate from the normal range, even causing system imbalance. These deviations (differences) can be considered signals of equipment health status. Through long-term monitoring and data analysis, a quantitative relationship between these differences and health status can be established.

[0092] However, due to the influence of environmental conditions, and because this application involves multiple interferences, an environmental correction model needs to be constructed before calculating the difference values ​​to compensate for the impact of different environmental conditions on heating parameters. The methods for constructing the environmental correction model include:

[0093] (1) Based on the basic information, multiple heating stations are clustered to obtain a set of multiple heating stations with similar hardware facilities;

[0094] First, multiple heating stations are clustered. The goal is to group heating stations with similar hardware facilities and coverage of residential areas to unify basic information conditions.

[0095] In this embodiment, K-means clustering or hierarchical clustering is used to group the features. Before clustering, standardization (such as Z-score standardization) is required. The optimal number of clusters is determined using the silhouette score or the elbow method.

[0096] (2) Extract maintenance time points of multiple heating stations from the maintenance records, and extract multiple operating cycles of multiple heating stations based on the maintenance time points, and take the center time point of each operating cycle as the reference time point;

[0097] Maintenance time points refer to the points in time when maintenance personnel record the maintenance of the main equipment in a heating station. Generally, the equipment in a heating station requires regular maintenance. The table below is a reference schedule for the maintenance cycle of the main equipment in a heating station:

[0098] Table 1. Reference Data Table for Maintenance Cycles of Main Equipment in Heating Stations

[0099] Generally, maintenance personnel will perform maintenance according to the predetermined maintenance cycle. However, since the heating station monitoring system also monitors some heating parameters of the main equipment, maintenance will also be performed if the heating parameter values ​​are abnormal. Therefore, the maintenance time is not completely fixed.

[0100] This application extracts maintenance cycles from any two adjacent maintenance time points, with each maintenance cycle representing the process of equipment health declining from 100% to a certain percentage. To control the impact of health on heating parameters, this application extracts multiple heating parameter values ​​at the center time point of each maintenance cycle as reference values.

[0101] In this application, for the data of each heating station set, the parameters At multiple reference time points The value is represented as .

[0102] (3) Collect multiple environmental parameters at multiple reference time points for each heating station The values ​​are normalized to obtain a series of environmental parameters for various environmental parameters; and the values ​​of various heating parameters at multiple reference time points of each heating station are normalized to obtain a series of heating parameters for various heating parameters.

[0103] This application first uses normalization to eliminate the dimensions of various heating and environmental parameters. The normalization conversion method can be maximum-minimum normalization. Then, the series are aligned using reference time points to calculate the correlation between the two series.

[0104] Furthermore, because data from different heating stations within the same heating station set may overlap in time, for example at a reference time point... There are two parameters For reference values, in this case, the average is calculated and the values ​​are combined.

[0105] For example, for parameters After normalizing the reference values ​​at multiple reference time points, the sequence { is obtained} , ,... };

[0106] (4) For any combination of environmental parameters and heating parameters, the time-series correlation coefficient of the corresponding environmental parameter sequence and heating parameter sequence is calculated after binarization based on the average value within the sequence. Combinations with a time-series correlation coefficient greater than a set correlation coefficient are considered as related combinations. The time-series correlation coefficient... The mathematical expression is:

[0107]

[0108] In the formula, This represents the binarized sequence of environmental parameters. This represents the binarized sequence of heating parameters;

[0109] Because environmental parameter sequences or heating parameter sequences may exhibit significant fluctuations, the Pearson correlation coefficient is not suitable for calculating correlation. Therefore, in this embodiment, time-series correlation analysis is used to determine the correlation. First, the average value of all reference values ​​within the sequence is used to binarize all reference values, for example:

[0110] The original environmental sequence is {0.31, 0.52, ... 0.74}, with an average value of 0.45. The binarized environmental parameter sequence is {0, 0, ... 1}.

[0111] Binarizing the sequence simplifies the value distribution of the sequence. Then, the difference between the binarized heating parameter sequence and the binarized environmental parameter sequence is calculated. The difference sequence reflecting the difference between the two was calculated. Then, the difference sequence was analyzed. The average value of each element in the algorithm is calculated. If the difference is large or small, it indicates a positive or negative correlation. For ease of representation, the absolute value of the average is taken and compared with a threshold (which can be 0.7) to filter out the environmental parameters related to each heating parameter.

[0112] For example, the secondary supply and return temperature is related to temperature, humidity and wind speed.

[0113] (5) Extract all associated environmental parameters of each heating parameter from the relevant combination, and construct the relationship between the heating parameter and all associated environmental parameters of the heating parameter; and perform multivariate linear fitting on the relationship based on the value of the heating parameter corresponding to the reference time point to obtain the relationship between the heating parameter and all associated environmental parameters of the heating parameter.

[0114] After obtaining the correlation judgment results, the correlation needs to be quantified. This application obtains the relationship between heating parameters and related environmental parameters based on multiple linear fitting. The mathematical expression of the relationship is as follows:

[0115]

[0116] In the formula, Indicates the first The coefficient of the term, Indicates the first Item associated environmental parameters, This is the offset;

[0117] Finally, the least squares method or linear regression is used to estimate the coefficients of the relationship. The specific process is based on existing technology and will not be described in detail here.

[0118] (6) Based on the relationship between various heating parameters of multiple heating stations, construct an environmental correction model.

[0119] Environmental correction models can be used to correct parameters under different environmental conditions, thereby unifying the fluctuations in heating parameter values ​​caused by different environmental conditions in the data.

[0120] Figure 3 This is a flowchart of the difference value calculation in one embodiment of this application, as follows: Figure 3 As shown, using the above-mentioned environmental correction model, the differences between the values ​​of various heating parameters and reference values ​​in the target operating data are calculated, including:

[0121] S1301, for any heating station, obtain the values ​​of multiple environmental parameters and multiple heating parameters corresponding to multiple historical time points, and correct the values ​​of multiple heating parameters corresponding to multiple historical time points based on a pre-built environmental correction model to obtain the corrected values ​​of multiple heating parameters corresponding to multiple historical time points under standard environmental conditions. The environmental correction model characterizes the influence ratio of different environmental conditions on the values ​​of heating parameters.

[0122] When correcting the heating parameters of each heating station, the corresponding relationship is found from the environmental correction model. The standard environmental conditions (e.g., temperature 0℃, humidity 40%, wind speed 5m / s) are substituted into the relationship to obtain the correction value.

[0123] S1302, the difference value is obtained by subtracting the correction value of each heating parameter from the corresponding reference value.

[0124] After correction, the difference between the corrected value and the reference value for each heating parameter is calculated to obtain the difference value. The reference value is also a value collected after maintenance under standard environmental conditions.

[0125] Figure 4 This is a schematic diagram of the evaluation parameter analysis process in this application, such as... Figure 4 As shown, after calculating the difference value, the difference value can be used to perform health correlation analysis, specifically including:

[0126] S1311, Extract maintenance time points of multiple heating stations from the maintenance records;

[0127] S1312, based on the maintenance time point, extract one or more operating cycles for each heating parameter and the difference values ​​of multiple historical time points within the operating cycle, wherein the two ends of the operating cycle are maintenance time points, and the maintenance time point at the beginning is zero. ;

[0128] The health status in this application will be reset during each maintenance. For example, when a water pump is running continuously, scale buildup can cause the pump speed to decrease, which in turn can lead to a decrease in water flow. The health status will be restored after maintenance.

[0129] Therefore, it is necessary to break down and analyze the data based on the operating cycle.

[0130] S1313, for each historical time point within the aforementioned operating cycle Calculate historical time points With the zero point Interval duration The duration sequence was obtained; and based on each heating parameter The difference value is constructed from the difference values ​​at each historical time point within the said operating cycle. Sequence, where, Represent natural numbers;

[0131] First, for each heating station, evaluation parameters related to its health status are identified. These parameters change as health status decreases. In this application, health status is assumed to decrease linearly over the operating cycle; therefore, Pearson correlation coefficient analysis is employed. Thus, a sequence of differences in operating time and heating parameters is first constructed.

[0132] S1314, Normalize the duration sequence and the difference value sequence respectively to obtain a normalized duration sequence and a normalized difference value sequence;

[0133] Normalization eliminates dimensions, facilitating subsequent processing. The Pearson correlation coefficient is then used to calculate the correlation.

[0134] S1315, Calculate the correlation between the normalized duration sequence and the normalized difference value sequence. Heating parameters with a correlation greater than a preset correlation threshold are used as evaluation parameters related to health, wherein the correlation is calculated as follows:

[0135]

[0136] In the formula, Represents the normalized i-th Duration, This represents the average normalized duration in the normalized duration sequence. Represents the normalized i-th One difference value, These are the normalized differences in the normalized difference value sequence.

[0137] Figure 5 This is a flowchart of a method for constructing a health impact model according to an embodiment of this application, as shown below. Figure 5 As shown, the methods for constructing the health impact model include:

[0138] S1321, Based on the basic information, multiple heating stations are clustered to obtain a set of multiple heating stations with similar hardware facilities.

[0139] First, multiple heating stations are clustered. The goal is to group heating stations with similar hardware facilities and coverage of residential areas to unify basic information conditions.

[0140] In this embodiment, K-means clustering or hierarchical clustering is used to group the features. Before clustering, standardization (such as Z-score standardization) is required. The optimal number of clusters is determined using the silhouette score or the elbow method.

[0141] S1322, Extract maintenance time points of multiple heating stations from the maintenance records;

[0142] S1323, Based on the maintenance time point, extract multiple operating cycles C from the maintenance record, and extract the initial reference value of the evaluation parameter at the first time point of each operating cycle C. The final reference value of the evaluation parameters at the last time point. ; and the initial reference value based on the environmental correction model, the environmental parameter values ​​at the first time point, and the environmental parameter values ​​at the last time point. and the aforementioned end reference value Make corrections to obtain the initial correction reference value. and end of correction reference value ,in, Indicates the sequence number of the heating parameter;

[0143] An operating cycle C is defined as the period between two consecutive maintenance points. Evaluation parameters include supply and return water temperature, pressure, flow rate, and power consumption. The heating parameter values ​​at the beginning and end of each operating cycle are corrected to avoid interference from different meteorological conditions.

[0144] S1324, Calculate the difference between the beginning and end values ​​of the evaluation parameters in each running cycle. , ; Filter out the largest difference and the maximum difference The health of the corresponding runtime cycle is set to 0, while the health of other runtime cycles is set to... for:

[0145]

[0146] In the formula, The difference between the first and last evaluation parameters for the operating cycle C;

[0147] For any heating parameter, the difference between the initial correction value and the final correction value of the evaluation parameter within each operating cycle C is calculated (e.g., supply and return water temperature difference). ).

[0148] Health score reset to 0 rule: If the difference in a certain period is the largest (e.g., ΔT is the largest), it indicates significant equipment performance degradation, and the health score is set to 0. Health scores for other periods are allocated proportionally based on the difference. .

[0149] S1325, Calculate the relationship based on multiple evaluation parameters for any set of heating stations:

[0150]

[0151] In the formula, Indicates the number of evaluation parameters. Indicates the coefficient of the term, Indicates the offset. For health status.

[0152] This application calculates multiple term coefficients based on multiple linear fitting. and offset The values ​​are obtained to determine the relationship between various evaluation parameters and health status.

[0153] S1326, Initial correction reference value based on multiple operating cycles in the heating station set End of correction reference value and health The relationship is fitted with multiple linear equations to obtain the health influence relationship of the current set of heating stations; and a health influence model is constructed based on the health influence relationship of multiple sets of heating stations.

[0154] Finally, a complete health impact model is constructed based on the relationships between multiple heat stations.

[0155] S140: Based on the basic information of multiple heating stations and the target operation data at multiple historical time points, preliminary training data is constructed, and the health of the training data is evaluated based on the health impact model to obtain training data that integrates the health dimension; and the artificial neural network is trained based on the training data to obtain a heating parameter prediction model.

[0156] After obtaining the health impact model, a health evaluation dimension can be introduced during subsequent training. The process includes:

[0157] S1401, Obtain the source heat station of the training data, and determine the target health influence relationship from the health influence model based on the source heat station;

[0158] S1402, Substitute the values ​​of the evaluation parameters in the training data into the target health influence formula to obtain the health of the source heat station when the training data was generated, and obtain the preliminary training data fused with the health dimension;

[0159] S1403, calculate the difference between the preliminary training data and the pre-constructed reference data to obtain the training data, wherein the reference data is empirical data.

[0160] When constructing a single training dataset, a historical time point is selected, and the basic information of any heating station corresponding to that time point, the values ​​of multiple meteorological parameters, and the health status (obtained based on the health status impact model) are used as training samples. These training samples are essentially variance values, facilitating data reference for subsequent staff. The values ​​of multiple heating parameters serve as labels. All of the above data has undergone vectorization processing.

[0161] Then training can begin, including:

[0162] S1, Input the training data into the artificial neural network to obtain the predicted value;

[0163] The training data is passed through the input layer, hidden layers (potentially multiple layers), and output layer. Each neuron in each layer performs a weighted sum of the inputs and applies an activation function (such as ReLU, Sigmoid, etc.) to generate a predicted value.

[0164] S2, calculate the loss between the predicted value and the heating parameter value in the training data based on the loss function, adjust the parameters of the artificial neural network based on the loss, and return to step S1 until a fit is obtained to obtain the heating parameter prediction model.

[0165] The loss function uses mean squared error (MSE) to measure the difference between the predicted and the true values, and the gradient of the loss function with respect to each parameter is calculated through the backpropagation algorithm.

[0166] S150, based on the health impact model and the heating parameter prediction model, the heating parameters of the heating station are predicted to obtain the predicted difference value, and the reference value of the heating parameter of the corresponding heating station is compensated based on the predicted difference value.

[0167] The compensation value for each heating station is determined based on attributes such as whether it is an energy-efficient building or a non-energy-efficient building, whether it uses wall heating or underfloor heating, and the building's age. Furthermore, during operation, heating administrators can adjust the compensation value based on experience and complaint rates. After multiple adjustments, the compensation value becomes increasingly closer to the actual heat dissipation deviation of each building at each station.

[0168] Figure 6 This is a schematic diagram of the heating parameter prediction process in one embodiment of this application, as shown below. Figure 6 As shown, it includes:

[0169] (1) First, it is necessary to obtain the values ​​of various heating parameters and various environmental parameters obtained by the target heating station at the most recent collection time point, and obtain the environmental prediction data of the area where the target heating station is located;

[0170] (2) Then, the values ​​of various heating parameters are corrected using the environmental correction model and the values ​​of various environmental parameters to obtain the corrected values ​​of various heating parameters; the correction process is as described above and will not be repeated here.

[0171] (3) Input the values ​​of the evaluation parameters among various heating parameters into the health status impact model to obtain the health status;

[0172] (4) Vectorize the basic information, health status, and values ​​of various heating parameters and environmental parameters obtained at the most recent collection time point of the target heating station, and input them into the heating parameter prediction model to obtain the heating parameter prediction vector.

[0173] The basic information of the target heating station, its health status, and the values ​​of various heating parameters and environmental parameters acquired at the most recent data collection point are combined into a vector. This vector is input into the prediction model, and the output vector is the predicted value of the heating parameters. This value can be directly entered into a statistical file for relevant personnel to execute. This solves the problem of errors easily caused by manual data entry.

[0174] This invention discloses an AI-based method for analyzing the differences in heating station data. The method acquires a large amount of historical operational data from heating stations, samples room temperature, etc., and then cleans the data to remove missing or invalid data. It utilizes the differences between heating parameter values ​​and reference values ​​under various operating conditions of the heating station, and analyzes these differences to identify heating parameters related to health status, i.e., evaluation parameters. Then, based on historical samples of the evaluation parameters, a health status impact model is constructed, thereby providing training data for health status evaluation and introducing the influence of the health status dimension on the values ​​of heating parameters. The model is then trained and automatically infers the values ​​of heating parameters based on the trained model. This avoids the problems of unreliability and neglect of the health status impact when manually entering heating station parameters.

[0175] like Figure 7 As shown, this application also provides an AI-based thermal station difference analysis system, including:

[0176] The acquisition module is used to acquire basic information of multiple heating stations, historical operating data of multiple heating stations at multiple historical time points, and sampled room temperature of covered users at multiple historical time points; and to acquire reference values ​​and maintenance records of multiple heating parameters of multiple heating stations. The historical operating data includes values ​​of multiple heating parameters and values ​​of multiple environmental parameters. The basic information includes unit number, year of construction, year of construction of the heating coverage area, and heating area.

[0177] The data cleaning module is used to filter and clean the historical operating data of multiple heating stations at multiple historical time points based on the sampled room temperature, so as to obtain the target operating data of the heating stations under normal operating conditions.

[0178] The health model module is used to calculate the difference between the values ​​of various heating parameters and reference values ​​in the target operating data for each heating station, and to perform time-series statistical analysis based on the difference values ​​of various heating parameters corresponding to multiple historical time points to obtain evaluation parameters related to health. Furthermore, a health impact model is constructed based on the values ​​of the evaluation parameters for multiple heating stations at multiple historical time points, wherein the health impact model characterizes the correspondence between health values ​​and the values ​​of the evaluation parameters.

[0179] The prediction model building module is used to construct preliminary training data based on the basic information of multiple heating stations and the target operation data at multiple historical time points, and to evaluate the health of the training data based on the health impact model to obtain training data that integrates the health dimension; and to train an artificial neural network based on the training data to obtain a heating parameter prediction model.

[0180] The predictive analysis module is used to predict the heating parameters of the heating station based on the health impact model and the heating parameter prediction model, obtain the predicted difference value, and compensate the reference value of the heating parameter of the corresponding heating station based on the predicted difference value.

[0181] This invention discloses an AI-based heating station difference analysis system. This application acquires a large amount of historical operational data from heating stations, samples room temperature, etc., and then cleans the data to remove missing or invalid data. It utilizes the differences between heating parameter values ​​and reference values ​​under various operating conditions of the heating station, and analyzes these differences to identify heating parameters related to health status, i.e., evaluation parameters. Then, based on historical samples of the evaluation parameters, a health status impact model is constructed, thereby using the training data to evaluate health status, introducing the influence of the health status dimension on the values ​​of heating parameters, and training the model. The system automatically predicts the values ​​of heating parameters based on the trained model. This avoids the problems of unreliability and neglect of the health status impact when manually entering heating station parameters.

[0182] This embodiment also provides an electronic terminal, including: a processor and a memory;

[0183] The memory is used to store computer programs, and the processor is used to execute the computer programs stored in the memory to cause the terminal to perform any of the methods in this embodiment.

[0184] As will be understood by those skilled in the art, the computer-readable storage medium described in this embodiment allows for the implementation of all or part of the steps in the above method embodiments by computer program-related hardware. The aforementioned computer program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0185] The electronic terminal provided in this embodiment includes a processor, a memory, a transceiver, and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication between them. The memory is used to store computer programs, the communication interface is used to perform communication, and the processor and the transceiver are used to run the computer programs, so that the electronic terminal performs the steps of the above method.

[0186] In this embodiment, the memory may include random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device.

[0187] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0188] In the above embodiments, although the invention has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. The embodiments of the invention are intended to cover all such substitutions, modifications, and variations falling within the broad scope of the appended claims.

[0189] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. An AI-based heat station difference analysis method, characterized by, The method comprises the following steps: obtaining basic information of a plurality of heat supply stations, historical operation data of the plurality of heat supply stations at a plurality of historical time points, and sample room temperatures of users covered at the plurality of historical time points; and obtaining reference values of a plurality of heat supply parameters of the plurality of heat supply stations and maintenance records, wherein the historical operation data comprises values of a plurality of heat supply parameters and values of a plurality of environmental parameters, and the basic information comprises unit number, construction year, construction year of a heat supply coverage area, and heat supply area; based on the sample room temperatures, filtering and cleaning the historical operation data of the plurality of heat supply stations at the plurality of historical time points to obtain target operation data of the heat supply stations in a normal working state; for each heat supply station, calculating difference values between the values of the plurality of heat supply parameters in the target operation data and reference values, and based on the difference values of the plurality of heat supply parameters corresponding to the plurality of historical time points and the maintenance records, performing time series statistical analysis to obtain evaluation parameters related to health degree; and based on the values of the evaluation parameters of the plurality of heat supply stations at the plurality of historical time points, constructing a health degree influence model, wherein the health degree influence model represents a corresponding relationship between health degree values and the values of the evaluation parameters; based on the basic information of the plurality of heat supply stations and the target operation data at the plurality of historical time points, constructing preliminary training data, and based on the health degree influence model, evaluating the health degree of the training data to obtain training data fused with the health degree dimension; and based on the training data, training an artificial neural network to obtain a heat supply parameter prediction model; based on the health degree influence model and the heat supply parameter prediction model, predicting the heat supply parameters of the heat supply stations to obtain prediction difference values, and based on the prediction difference values, compensating the reference values of the corresponding heat supply stations.

2. The AI-based heat station difference analysis method of claim 1, wherein, based on the sample room temperatures, filtering and cleaning the historical operation data of the plurality of heat supply stations at the plurality of historical time points to obtain target operation data of the heat supply stations in a normal working state, comprising: comparing the sample room temperatures in the historical operation data with a preset normal operation temperature range, and retaining the historical operation data with the sample room temperatures in the preset normal operation temperature range to obtain intermediate data; for the intermediate data with missing values, performing linear interpolation or deletion processing to obtain target operation data. 3.The AI-based heat station difference analysis method of claim 1, wherein, calculating difference values between the values of the plurality of heat supply parameters in the target operation data and reference values, comprising: for any one heat supply station, obtaining values of a plurality of environmental parameters and values of a plurality of heat supply parameters corresponding to a plurality of historical time points, and based on a pre-constructed environmental correction model, correcting the values of the plurality of heat supply parameters corresponding to the plurality of historical time points to obtain correction values of the plurality of heat supply parameters corresponding to the plurality of historical time points under standard environmental conditions, wherein the environmental correction model represents the influence proportion of the heat supply parameter values under different environmental conditions; subtracting the correction value of each heat supply parameter from the corresponding reference value to obtain the difference value.

4. The AI-based heat station difference analysis method of claim 3, wherein, the construction method of the environmental correction model comprises: based on the basic information, clustering the plurality of heat supply stations to obtain a plurality of heat supply station sets with similar hardware facility conditions; extract maintenance time points of the plurality of heat supply stations from the maintenance record, and extract a plurality of operation cycles of the plurality of heat supply stations based on the maintenance time points, and take a central time point of each operation cycle as a reference time point; normalize values of a plurality of environment parameters at a plurality of reference time points of each heat supply station set to obtain environment parameter sequences of the plurality of environment parameters, and normalize values of a plurality of heating parameters at a plurality of reference time points of each heat supply station set to obtain heating parameter sequences of the plurality of heating parameters; For any combination of environmental parameters and heating parameters, the time series correlation coefficient of the corresponding environmental parameter sequence and heating parameter sequence is calculated after binarization based on the average value within the sequence, and combinations with time series correlation coefficients greater than a set correlation coefficient are taken as relevant combinations, wherein the mathematical expression of the time series correlation coefficient is: Mathematical expression: wherein, denotes the sequence of binarized environmental parameters, denotes the sequence of binarized heating parameters; extract all associated environment parameters of each heating parameter from the correlation combination, and construct a relationship between the heating parameter and the all associated environment parameters of the heating parameter; and based on the values of the heating parameters corresponding to the reference time points, perform multivariate linear fitting on the relationship to obtain a relationship between the heating parameter and the all associated environment parameters of the heating parameter; based on the relationship of the plurality of heating parameters of the plurality of heat supply station sets, construct an environment correction model.

5. The AI-based heat station difference analysis method of claim 1, wherein, based on the difference values of the plurality of heating parameters corresponding to the plurality of historical time points and the maintenance record, perform time series statistical analysis to obtain evaluation parameters related to the health degree, including: extract maintenance time points of the plurality of heat supply stations from the maintenance record; intercept one or more running periods of each heating parameter and difference values of multiple historical time points in the running period based on the maintenance time points, wherein both ends of the running period are maintenance time points, and the maintenance time point at the first end is zero ; For each historical time point within the aforementioned operating cycle Calculate historical time points With the zero point Interval duration The duration sequence was obtained; and based on each heating parameter The difference value is constructed from the difference values ​​at each historical time point within the said operating cycle. Sequence, where, Represent natural numbers; respectively normalize the time length sequence and the difference value sequence to obtain a normalized time length sequence and a normalized difference value sequence; calculating a correlation degree of the normalized duration sequence and the normalized difference value sequence and taking the heating parameter with a correlation degree greater than a preset correlation degree threshold as an evaluation parameter related to the health degree, wherein a calculation formula of the correlation degree is: wherein, denotes the normalized time length of the i-th time length, denotes the normalized time length of the i-th time length, denotes the average normalized time length in the sequence of normalized time lengths, denotes the normalized difference value of the i-th difference value, denotes the normalized difference value of the i-th difference value, is the normalized difference value in the sequence of normalized difference values.

6. The AI-based heat station difference analysis method of claim 4, wherein, based on the values of the evaluation parameters of the plurality of heat supply stations at the plurality of historical time points, construct a health degree influence model, including: based on the basic information, cluster the plurality of heat supply stations to obtain a plurality of heat supply station sets with similar hardware facility conditions; extract maintenance time points of the plurality of heat supply stations from the maintenance record; extracting a plurality of running cycles C from the maintenance record based on the maintenance time point, and extracting an initial reference value of the evaluation parameter at a first time point of each running cycle C and an end reference value of the evaluation parameter at a last time point ; and correcting the initial reference value and the end reference value based on the environment correction model to obtain an initial corrected reference value and an end corrected reference value , wherein indicates the serial number of the heat supply parameter; Calculate the first and last difference of evaluation parameters in each running period , ; screen out the maximum difference , and set the health degree of the running period corresponding to the maximum difference to 0, and the health degrees of other running periods : wherein, is the first-to-last difference of the evaluation parameter for the cycle C. calculate, for any one heat supply station set, a relationship based on a plurality of evaluation parameters: wherein, denotes the number of evaluation parameters, denotes the term coefficient, denotes the offset, denotes the healthiness; Initial correction reference values based on a plurality of operating cycles in a heat station set , end correction reference values , and health degree The relationship is subjected to multiple linear fitting to obtain a health degree influence relationship of the current heat station set; and a health degree influence model is constructed based on the health degree influence relationships of a plurality of heat station sets.

7. The AI-based heat station difference analysis method of claim 6, wherein, based on the health degree influence model, evaluate the training data to obtain training data fused with the health degree dimension, including: obtain a source heat supply station of the training data, and determine a target health degree influence relationship from the health degree influence model based on the source heat supply station; substitute the values of the evaluation parameters in the training data into the target health degree influence relationship to obtain the health degree of the source heat supply station when the training data is generated, and obtain preliminary training data fused with the health degree dimension; calculate the difference value between the preliminary training data and the pre-constructed reference data to obtain training data, wherein the reference data is experience data. 8.The AI-based heat station difference analysis method of claim 1, wherein, based on the training data, train an artificial neural network to obtain a heating parameter prediction model, including: S1, input the training data into the artificial neural network to obtain a prediction value; S2, calculate the loss of the prediction value and the heating parameter value in the training data based on a loss function, and adjust the parameters of the artificial neural network based on the loss, and return to step S1 until fitting, to obtain a heating parameter prediction model. 9.The AI-based heat station difference analysis method of claim 4, wherein, based on the health degree influence model and the heating parameter prediction model, predict the heating parameters of the heat supply station to obtain a prediction difference value, including: obtain values of a plurality of heating parameters and a plurality of environment parameters of the target heat supply station at a recent collection time point, and obtain environment prediction data of the region where the target heat supply station is located; The values of the plurality of heating parameters are corrected based on the environment correction model to obtain corrected values of the plurality of heating parameters; The value of the evaluation parameter in the plurality of heating parameters is input into the health degree influence model to obtain the health degree; The basic information of the target heat station, the health degree, the values of the plurality of heating parameters and the plurality of environment parameters obtained at the last acquisition time point are vectorized and input into the heating parameter prediction model to obtain a heating parameter prediction vector.

10. An AI-based heat station difference analysis system, characterized by, Comprise: An acquisition module is configured to acquire basic information of a plurality of heat stations, historical operation data of the plurality of heat stations at a plurality of historical time points, and sample room temperatures of users covered at the plurality of historical time points, and acquire reference values and maintenance records of a plurality of heating parameters of the plurality of heat stations, wherein the historical operation data comprises values of a plurality of heating parameters and values of a plurality of environment parameters, and the basic information comprises unit number, construction year, construction year of a heating coverage area, and heating area; A data cleaning module is configured to filter and clean the historical operation data of the plurality of heat stations at the plurality of historical time points based on the sample room temperatures to obtain target operation data of the heat stations in a normal working state; A health degree model module is configured to, for each heat station, calculate difference values of the values of the plurality of heating parameters in the target operation data and reference values, and perform time series statistical analysis based on the difference values of the plurality of heating parameters corresponding to the plurality of historical time points to obtain evaluation parameters related to the health degree, and construct a health degree influence model based on the values of the evaluation parameters of the plurality of heat stations at the plurality of historical time points, wherein the health degree influence model represents a corresponding relationship between the health degree value and the value of the evaluation parameter; A prediction model construction module is configured to construct preliminary training data based on the basic information of the plurality of heat stations and the target operation data at the plurality of historical time points, perform health degree evaluation on the training data based on the health degree influence model to obtain training data fused with the health degree dimension, and train an artificial neural network based on the training data to obtain a heating parameter prediction model; A prediction analysis module is configured to predict the heating parameters of the heat stations based on the health degree influence model and the heating parameter prediction model to obtain prediction difference values, and compensate for the reference values of the heating parameters of the corresponding heat stations based on the prediction difference values.

Images