Intelligent monitoring method and system for abnormal building energy consumption

Abstract

The present disclosure provides an intelligent monitoring method and system for abnormal building energy consumption, which relates to the field of data processing technology. The method includes: collecting the indoor temperature of each user unit in the target building and the water supply temperature and return water temperature of the heating system; determining the temperature standard value of the indoor temperature based on the heating intensity, and determining the abnormal heating interval of each user unit based on the temperature standard value and the indoor temperature; determining the temperature deviation discreteness and the similarity of the temperature change trend of each abnormal heating interval based on the indoor temperature of each user unit in the abnormal heating interval; determining the window opening interference value based on the supply water temperature, return water temperature and indoor temperature; determining the confidence level of the abnormal heating system based on the temperature deviation discreteness, the similarity of the temperature change trend and the window opening interference value; judging whether the heating system is abnormal based on the confidence level, and handling the abnormal situation when an abnormality occurs. The present disclosure can more effectively realize the monitoring of abnormal conditions in the heating system.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an intelligent monitoring method and system for abnormal building energy consumption. Background Art

[0002] With the continuous growth of global energy demand and the gradual increase in environmental awareness, building energy consumption is receiving increasing attention. Heating energy consumption accounts for a significant proportion of building energy consumption, especially in winter in cold regions, where it can reach as much as 40%-60% of total building energy consumption. Therefore, accurately monitoring and analyzing heating energy consumption is crucial for improving building energy efficiency, reducing energy waste, and achieving energy conservation and emission reduction.

[0003] In related technologies, threshold judgment methods or statistical analysis methods are usually used to monitor and analyze heating energy consumption, which have the following problems: focusing on the energy consumption data itself, ignoring the significant impact of user behavior interference factors such as window opening and living habits on temperature, resulting in a high false alarm rate; it is difficult to detect gradual anomalies such as pipe blockage and circulation pump failure, and it mainly relies on manual inspections, which is inefficient and leads to lags in anomaly detection; ignoring the correlation between user unit temperature data, and being unable to distinguish between system failures and anomalies caused by local user behavior. Summary of the Invention

[0004] To address the problems of related technologies, such as insufficient consideration of user behavior interference, lag in anomaly detection, and insufficient analysis of the correlation between user unit temperature data, the present invention provides an intelligent monitoring method for building energy consumption anomalies. The technical solution adopted is as follows:

[0005] Collecting the indoor temperature of each user unit in the target building and monitoring the supply water temperature and return water temperature of the heating system of the target building;

[0006] determining a standard temperature value of the indoor temperature based on the heating intensity of the heating system, and determining an abnormal heating interval of each user unit based on the standard temperature value and the indoor temperature of each user unit;

[0007] determining, based on the indoor temperature of each user unit in the abnormal heating interval, a temperature deviation dispersion of each abnormal heating interval and a similarity of a temperature change trend of each user unit;

[0008] determining a window opening interference value based on the supply water temperature, the return water temperature, and the indoor temperature within the abnormal heating interval;

[0009] Determining a confidence level that an abnormality has occurred in the heating system based on the temperature deviation dispersion, the similarity of the temperature change trend, and the window opening interference value;

[0010] It is determined whether an abnormality occurs in the heating system based on the confidence level, and when it is determined that an abnormality occurs in the heating system, the abnormality is processed.

[0011] Correspondingly, the present invention also provides an intelligent monitoring system for abnormal building energy consumption, which specifically includes:

[0012] A sensor module is used to collect the indoor temperature of each user unit in the target building and monitor the supply water temperature and return water temperature of the heating system of the target building;

[0013] a data processing module, configured to determine a standard temperature value of the indoor temperature based on the heating intensity of the heating system, and determine an abnormal heating interval of each user unit based on the standard temperature value and the indoor temperature of each user unit;

[0014] an analysis module for determining, based on the indoor temperature of each user unit in the abnormal heating interval, a temperature deviation dispersion of each abnormal heating interval and a similarity of a temperature change trend of each user unit;

[0015] The analysis module is further configured to determine a window opening interference value based on the supply water temperature, the return water temperature, and the indoor temperature within the abnormal heating interval;

[0016] The analysis module is further configured to determine a confidence level that an abnormality has occurred in the heating system based on the temperature deviation dispersion, the similarity of the temperature change trend, and the window opening interference value;

[0017] a determination module, configured to determine whether an abnormality occurs in the heating system based on the confidence level;

[0018] The processing module is used to process the abnormal situation when it is determined that the heating system has an abnormality.

[0019] The present invention may have some or all of the following beneficial effects:

[0020] In the intelligent monitoring method for abnormal building energy consumption provided by the present invention, the indoor temperature of each user unit in the target building is collected, and the water supply temperature and return water temperature of the heating system of the target building are monitored; the temperature standard value of the indoor temperature is determined based on the heating intensity of the heating system, and the abnormal heating interval of each user unit is determined based on the temperature standard value and the indoor temperature of each user unit; based on the indoor temperature of each user unit in the abnormal heating interval, the temperature deviation discreteness of each abnormal heating interval and the similarity of the temperature change trend of each user unit are determined; based on the supply water temperature, return water temperature and the indoor temperature in the abnormal heating interval, the window opening interference value is determined; based on the temperature deviation discreteness, the similarity of the temperature change trend and the window opening interference value, the confidence level of the abnormality of the heating system is determined; based on the temperature deviation discreteness, the similarity of the temperature change trend and the window opening interference value, whether the heating system is abnormal is judged based on the confidence level, and when it is judged that the heating system is abnormal, the abnormal situation is handled. The present invention collects the indoor temperature of the user unit and the supply and return water temperature of the heating system, and determines the abnormal heating interval based on the indoor temperature and the temperature standard value under the current heating intensity, so that the temperature deviation discreteness of each abnormal heating interval and the similarity of the temperature change trend of each user unit can be determined based on the indoor temperature of each user unit, and the window interference value can be determined based on the supply water temperature, return water temperature and the indoor temperature in the abnormal heating interval. Furthermore, the confidence level of the abnormality of the heating system can be determined based on the temperature deviation discreteness, the similarity of the temperature change trend and the window interference value. Since the confidence level comprehensively considers the temperature deviation discreteness, the similarity of the temperature change trend and the window interference value, the influence of the user behavior interference factor on the temperature can be eliminated through the above-mentioned window interference value. The correlation relationship between the temperature data of each user unit is considered through the above-mentioned similarity of the temperature change trend, which helps to distinguish between system failures and abnormalities caused by local user behavior. Accurate monitoring of heating system abnormalities is achieved through multi-dimensional data analysis.

[0021] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 A flow chart of a method for intelligently monitoring abnormal building energy consumption according to an exemplary embodiment of the present disclosure is shown;

[0024] Figure 2A schematic diagram showing a normal temperature fluctuation range and a temperature data curve of a certain user unit in the intelligent monitoring method for abnormal building energy consumption according to an exemplary embodiment of the present disclosure is shown;

[0025] Figure 3 A schematic diagram of a user unit temperature data curve showing the delayed relationship between the start / end time of an abnormal interval and the heating distance in the intelligent monitoring method for abnormal building energy consumption according to an exemplary embodiment of the present disclosure is shown;

[0026] Figure 4 A schematic diagram of an intelligent monitoring system for abnormal building energy consumption according to an exemplary embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0027] To further illustrate the technical means and effectiveness of the present invention in achieving its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of the intelligent monitoring method for abnormal building energy consumption proposed by the present invention. In the following description, different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0028] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0029] The specific scheme of the intelligent monitoring method for abnormal building energy consumption provided by the present invention is described in detail below with reference to the accompanying drawings.

[0030] See also Figure 1 , which shows a method flow chart of an intelligent monitoring method for abnormal building energy consumption provided by an embodiment of the present invention, such as Figure 1 As shown, the intelligent monitoring method for abnormal building energy consumption specifically includes the following steps:

[0031] S110: Collecting the indoor temperature of each user unit in the target building and monitoring the water supply temperature and return water temperature of the heating system of the target building;

[0032] S120: determining a standard temperature value of the indoor temperature based on the heating intensity of the heating system, and determining an abnormal heating interval of each user unit based on the standard temperature value and the indoor temperature of each user unit;

[0033] S130: Based on the indoor temperature of each user unit in the abnormal heating interval, determining the temperature deviation dispersion of each abnormal heating interval and the similarity of the temperature change trend of each user unit;

[0034] S140: Determine a window opening interference value based on the supply water temperature, the return water temperature, and the indoor temperature within the abnormal heating range;

[0035] S150: Determining the confidence level of the abnormality in the heating system based on the temperature deviation dispersion, the similarity of the temperature change trend, and the window opening interference value;

[0036] S160: Determine whether an abnormality occurs in the heating system based on the confidence level, and handle the abnormality when it is determined that an abnormality occurs in the heating system.

[0037] The present invention collects the indoor temperature of the user unit and the supply and return water temperature of the heating system, and determines the abnormal heating interval based on the indoor temperature and the temperature standard value under the current heating intensity, so that the temperature deviation discreteness of each abnormal heating interval and the similarity of the temperature change trend of each user unit can be determined based on the indoor temperature of each user unit, and the window interference value can be determined based on the supply water temperature, return water temperature and the indoor temperature in the abnormal heating interval. Furthermore, the confidence level of the abnormality of the heating system can be determined based on the temperature deviation discreteness, the similarity of the temperature change trend and the window interference value. Since the confidence level comprehensively considers the temperature deviation discreteness, the similarity of the temperature change trend and the window interference value, the influence of the user behavior interference factor on the temperature can be eliminated through the above-mentioned window interference value. The correlation relationship between the temperature data of each user unit is considered through the above-mentioned similarity of the temperature change trend, which helps to distinguish between system failures and abnormalities caused by local user behavior. Accurate monitoring of heating system abnormalities is achieved through multi-dimensional data analysis.

[0038] The following describes in detail the steps of the intelligent monitoring method for abnormal building energy consumption:

[0039] In step S110 , the indoor temperature of each user unit in the target building is collected, and the supply water temperature and return water temperature of the heating system of the target building are monitored.

[0040] In the embodiment of the present application, the target building can be any building whose heating system is monitored for abnormalities using the intelligent monitoring method for abnormal building energy consumption provided by the embodiment of the present application. For example, the target building can be an office building, a residential apartment building, or a teaching building.

[0041] In the embodiment of the present application, the user unit can be a house in the target building for users to live, work, or study. Taking the teaching building as an example, each classroom in the teaching building can be regarded as a user unit.

[0042] In the embodiment of the present application, the above-mentioned indoor temperature refers to the air temperature value measured by temperature sensors and other equipment in the internal space environment of the above-mentioned user unit. It is an important physical quantity for measuring the indoor thermal environment and is used to reflect the degree of hotness or coldness of the indoor air. During the building heating process, heat is transferred from the heating equipment to the indoor space through heat conduction, convection and radiation, etc., so that the indoor temperature rises. When the heating system operates normally, the indoor temperature will rise according to a certain rule and remain within a relatively stable range. According to Newton's law of cooling, the heat dissipation rate of an object is proportional to the temperature difference between the object and the surrounding environment. In an indoor environment, if the heating equipment continues to provide stable heat, the indoor temperature should be maintained in a reasonable range, and the heating and cooling processes have a certain degree of predictability. Therefore, in the embodiment of the present application, it is possible to judge whether the heating system of the target building is abnormal based on the change in the indoor temperature.

[0043] For example, collecting the indoor temperature of each user unit in the target building can be achieved by installing indoor temperature sensors in the user units of the target building. These distributed indoor temperature sensors collect data in real time at regular intervals (for example, every five minutes), ensuring that the collected temperature data is accurate and complete, covering temperature conditions at different times of the day. It is important to note that these temperature sensors must be placed in a location that accurately reflects the average indoor temperature and avoid proximity to heat or cold sources.

[0044] In the embodiments of this application, the heating system refers to an equipment system that provides heat to the target building to maintain a constant indoor temperature within the target building's user units, creating a comfortable indoor thermal environment. The heating system primarily consists of three components: a heat source, heat transfer piping, and heat dissipation equipment. The heat source is the core component of the heating system, responsible for generating heat energy and providing a heat source for the entire system. The heat transfer piping connects the heat source and heat dissipation equipment, transporting the heat medium (hot water or steam) generated by the heat source to the various heat dissipation equipment. The heat dissipation equipment dissipates the heat carried by the heat transfer equipment into the indoor space, raising the indoor temperature and achieving the purpose of heating.

[0045] In the above heating system, the supply water temperature refers to the temperature of the hot water output from the heat source and transported to the heat dissipation device through the heat medium transport pipeline. The return water temperature refers to the temperature of the hot water after being dissipated by the heat dissipation device and then returned to the heat source.

[0046] Exemplarily, the above-mentioned monitoring of the water supply temperature and return water temperature of the heating system of the target building can be achieved by the following method: installing temperature sensors on the water supply pipes and return water pipes of the above-mentioned heating system, and monitoring the water supply temperature and return water temperature at fixed time intervals through the temperature sensors to understand the heat transfer situation.

[0047] In the embodiment of the present application, the collected temperature data may also be preprocessed to ensure the data quality of the collected temperature data. Specifically, an indoor temperature sensor is installed in the user unit, and a temperature sensor is installed in the water supply and return pipes. After collecting temperature data at a fixed interval (e.g., every 5 minutes), the above-mentioned data preprocessing includes: (1) data cleaning: eliminating abnormal values ​​caused by sensor failure or signal interference; (2) data interpolation: using linear interpolation or spline interpolation to fill in missing data to ensure data continuity.

[0048] In step S120 , a temperature standard value of the indoor temperature is determined based on the heating intensity of the heating system, and an abnormal heating interval of each user unit is determined based on the temperature standard value and the indoor temperature of each user unit.

[0049] In the embodiments of this application, the heating intensity generally refers to the amount of heat received by the heated space per unit time, per unit area, or per unit volume. It reflects the speed and amount of heat transferred to the indoor space by the heating system and is an important indicator of the heating system's ability to provide heat to the target building. The standard temperature value refers to the temperature value that the indoor temperature of the user unit should reach at the current heating intensity.

[0050] In the embodiments of the present application, the abnormal heating interval refers to an interval in which heating anomalies occur. For example, the abnormal heating interval can be represented by a temperature change curve, with time as the horizontal axis, the value interval representing the time interval in which the temperature data anomaly occurs, and temperature as the vertical axis, representing the temperature data corresponding to each monitoring time within the abnormal time interval.

[0051] In the embodiments of the present application, since the heating system's design determines its heating capacity and operating parameters based on certain indoor and outdoor temperature parameters, building heat load, and other conditions, the indoor temperature should fluctuate within the designed range when the heating system is operating normally. In other words, if a user unit experiences the aforementioned abnormal heating interval, it indicates that the actual operation of the heating system may not conform to the designed operating conditions. This condition may be caused by a malfunction in a heating system component, such as a clogged radiator or a malfunctioning circulation pump, resulting in poor heating performance or excessive heating, which in turn causes abnormal heating energy consumption.

[0052] In an embodiment of the present application, the above-mentioned determination of the abnormal heating interval of each user unit based on the temperature standard value and the indoor temperature of each user unit can be implemented as follows: determine the normal temperature fluctuation range based on the temperature standard value; for each user unit, if the indoor temperature exceeds the normal temperature fluctuation range at the first target number of consecutive monitoring moments, then when the indoor temperature is within the normal temperature fluctuation range at the second target number of consecutive monitoring moments, the first monitoring moment in the first target number is used as the starting moment, and the last monitoring moment before the second target number is used as the ending moment to determine the abnormal heating interval of the user unit. For example, the normal temperature fluctuation range determined by the above method can be as follows: Figure 2 As shown, Figure 2 The horizontal axis of the coordinate system is time, the vertical axis is temperature, and the temperature data range between the two horizontal lines parallel to the horizontal axis in the coordinate system is the normal temperature fluctuation range mentioned above. In addition, if Figure 2 As shown in FIG, when abnormal heating energy consumption occurs, the indoor temperature data of the user unit usually does not return to the normal range immediately. In actual monitoring, it usually presents a state of continuously decreasing and then stabilizing to a certain low data value.

[0053] Specifically, the above-mentioned determination of the normal temperature fluctuation range based on the temperature standard value is implemented as follows: Assuming that under the current heating intensity, the above-mentioned temperature standard value is , we can determine that the normal temperature fluctuation range is ,in, It is the standard deviation of the indoor temperature of a user unit within a day under standard heating.

[0054] After determining the above-mentioned normal temperature fluctuation range, the abnormal heating interval of each user unit can be determined based on the normal temperature fluctuation range. Taking the above-mentioned first target number and second target number both taking values ​​of 3 as an example, for the indoor temperature data of any user unit, if the indoor temperature exceeds the above-mentioned normal temperature fluctuation range for three consecutive monitoring moments, then starting from the first monitoring moment exceeding the normal temperature fluctuation range, until the indoor temperature is within the normal temperature fluctuation range for three consecutive monitoring moments, the first monitoring moment exceeding the normal temperature fluctuation range is taken as the starting moment, and the last monitoring moment exceeding the normal temperature fluctuation range before the indoor temperature is within the normal temperature fluctuation range for three consecutive monitoring moments is taken as the ending moment, to obtain the time interval of abnormal heating and the temperature curve within the time interval. Specifically, taking the above-mentioned normal temperature fluctuation range of (25 degrees Celsius, 31 degrees Celsius) as an example, for the 14 monitoring moments with temperature data of (26, 26, 23, 28, 23, 21, 21, 23, 23, 26, 23, 27, 28, 30) as an example, the time interval from the 5th monitoring moment to the 11th monitoring moment is the time interval when abnormal heating occurs, and the temperature data values ​​corresponding to this time interval are (23, 21, 21, 23, 23, 26, 23).

[0055] In step S130 , based on the indoor temperature of each user unit in the abnormal heating interval, the temperature deviation dispersion of each abnormal heating interval and the similarity of the temperature change trend of each user unit are determined.

[0056] In the embodiment of the present application, the temperature deviation dispersion is a statistic used to measure the degree of dispersion or fluctuation of a set of temperature data, reflecting the degree of dispersion of the temperature data relative to the average value. When determining whether an abnormality has occurred in the heating system, the accuracy of abnormality monitoring of the heating system can be improved by considering the temperature deviation dispersion of each user unit in the abnormal heating interval. Specifically, the smaller the difference in the temperature deviation dispersion of each user unit in the abnormal heating interval, the higher the possibility of an abnormality in the heating system. During the complete process of a certain heating abnormality and its repair operation, the temperature deviation dispersion of the abnormal heating interval corresponding to the user unit should show a trend of gradually increasing and then decreasing.

[0057] The embodiment of the present application can determine the temperature deviation dispersion of the current abnormal heating interval based on the fluctuation of the temperature data in the above-mentioned abnormal heating interval. Exemplarily, the above-mentioned determination of the temperature deviation dispersion of each abnormal heating interval based on the indoor temperature of each user unit in the abnormal heating interval can be achieved as follows: determine the minimum value of the indoor temperature in the abnormal heating interval and the number of temperature data points; calculate the sum of the first difference between adjacent indoor temperatures in the abnormal heating interval, and the second difference between the temperature standard value and the minimum value of the indoor temperature in the abnormal heating interval; determine the temperature deviation dispersion based on the sum of the first difference, the second difference and the number of temperature data points of the indoor temperature in the abnormal heating interval. Specifically, the temperature deviation dispersion can be determined by the following formula:

[0058]

[0059] in, Indicates the standard temperature value of the indoor temperature of the user unit corresponding to the current heating intensity; Indicates the minimum value of temperature data in the current abnormal heating range; Indicates the number of data points in the current abnormal heating interval (i.e., the time-temperature data points in the temperature curve corresponding to the current abnormal heating interval); 、 In the current abnormal heating range 、 Temperature data.

[0060] In the above formula, the above The larger the value, the lower the temperature data in the current abnormal heating interval, the greater the drop in the indoor temperature of the user unit in the abnormal situation, and the more likely the current state is a late abnormal state with a low stability level. In this case, the temperature data deviates more significantly from the normal range, so the temperature deviation dispersion is higher. It is used to measure the temperature drop intensity of the current abnormal heating interval. The greater the temperature difference between two adjacent temperature data points, the faster the indoor temperature of the user unit drops. The larger the value of is, the more likely it is that when the temperature of adjacent temperature data points rises within the abnormal heating interval, it means that the current state may be a fault repair or a short-term temperature recovery. Therefore, when a temperature recovery occurs, If it is a negative number, the sum will gradually decrease, which is the process of decreasing the dispersion of temperature deviation; and when the same temperature difference occurs, the fewer the number of data points in the abnormal heating interval, the more significant the fluctuation of the current abnormal heating interval, that is, the greater the dispersion of temperature deviation.

[0061] In the embodiment of the present application, the similarity of the temperature change trend is used to measure the similarity of the temperature change trend of each user unit in the abnormal heating interval.

[0062] In an actual heating system, once an abnormality in the heating system's energy consumption occurs, this abnormality often spreads rapidly, like a chain reaction, to all user units covered by the heating system, triggering a comprehensive heating anomaly. Since each user unit is under the same heating system, the indoor temperature data fluctuations between user units show significant similarity, and the similarity of the temperature change trends mentioned above is used to measure this similarity. In addition, user interference behaviors such as leaving windows open for a long time can also cause a large amount of indoor heat to be lost. The resulting abnormal heating interval has no impact on other user units. In this case, the similarity of the temperature change fluctuations between the abnormal heating intervals of this user unit and other user units is also low. Therefore, when determining whether an abnormality has occurred in the heating system, the similarity of the temperature change trends of the above-mentioned user units must be considered. The higher the similarity of the temperature change trends, the greater the possibility of an abnormality in the heating system.

[0063] In an embodiment of the present application, the similarity of the temperature data change trends between all user units at the current moment can be analyzed based on the indoor temperature data change trends of the abnormal heating intervals between user units. For example, the similarity of the temperature change trends of each user unit based on the indoor temperature of each user unit in the abnormal heating interval can be determined as follows: based on the dynamic time warping algorithm, the dynamic time warping distance values ​​between the abnormal heating intervals are determined and summed; the total number of user units in the target building and the number of user units corresponding to the abnormal heating intervals are determined; the similarity of the temperature change trends is determined based on the total number of user units in the target building, the number of user units corresponding to the abnormal heating intervals, and the sum of the dynamic time warping distance values. Specifically, the similarity of the temperature change trends can be determined by the following formula:

[0064]

[0065] in, Indicates the number of all user units; Indicates the number of user units corresponding to the abnormal heating interval up to the current monitoring time; Indicates the DTW distance value between the indoor temperature data curves corresponding to two abnormal heating intervals.

[0066] In the above formula, the above The smaller the value, the more user units there are in abnormal heating intervals, and the greater the possibility of abnormal heating system conditions. The larger the value; (that is, the sum of the above-mentioned dynamic time warping distance values) represents the sum of the DTW distance values ​​of the temperature data between all abnormal heating intervals, reflecting the correlation between the abnormal heating intervals of all user units at the current monitoring moment. The smaller the sum value, the higher the correlation of the abnormal heating intervals of the user units.

[0067] In the embodiments of the present application, the Dynamic Time Warping (DTW) algorithm is a method for calculating the similarity between two time series. Its core concept is to find an optimal matching method by nonlinearly stretching and compressing the two time series on the time axis, so that the sum of the distances between the two series is minimized. The Dynamic Time Warping distance value is a numerical indicator derived from the Dynamic Time Warping algorithm to measure the similarity between two time series.

[0068] In step S140 , a window opening interference value is determined based on the supply water temperature, the return water temperature, and the indoor temperature in the abnormal heating interval.

[0069] In this embodiment of the present application, the window-opening interference value is used to characterize the impact of indoor temperature changes caused by a user opening a window on abnormal heating system monitoring. In other words, during actual heating operation, users opening windows for ventilation can also cause abnormal heating intervals, while the heating system continues to heat the user's unit normally. Therefore, the window-opening interference value is used to characterize the interference this user behavior has on monitoring.

[0070] In the embodiment of the present application, compared with the abnormal situation of the heating system, the indoor temperature drop caused by the user's window opening behavior is relatively small and the drop rate is also slow. When the heating system is abnormal (such as the heating pipe is broken or blocked), the heating equipment will continue to supply heat. In order to compensate for the heat loss in the user unit room, the heating system will carry more heat when supplying hot water. At the same time, the heat absorbed from the user unit room will be reduced, which will lead to a significant change in the supply and return water temperature difference. When the user frequently opens the window, the supply and return water temperature shows a relatively stable gradual trend. Therefore, the present application can combine the changes in the supply and return water temperature difference and the trend of temperature data changes in the abnormal heating interval to analyze the degree of interference of the user's window opening behavior on the monitoring of the abnormal heating interval, so as to more accurately analyze the abnormal conditions of the heating system.

[0071] Exemplarily, the above-mentioned determination of the window opening interference value based on the supply water temperature, return water temperature and indoor temperature in the abnormal heating interval can be implemented as follows: determine the supply and return water temperature difference of the user unit based on the supply water temperature and return water temperature; determine the slopes corresponding to all adjacent indoor temperatures in the abnormal heating interval and sum them; determine the minimum value of the indoor temperature in the abnormal heating interval, and calculate the difference between the temperature standard value and the minimum value of the indoor temperature in the abnormal heating interval; determine the window opening interference value based on the supply and return water temperature difference, the sum of the slopes corresponding to all adjacent indoor temperatures, and the difference between the temperature standard value and the minimum value of the indoor temperature in the abnormal heating interval. Specifically, the window opening interference value can be determined by the following formula:

[0072]

[0073] in, Indicates the supply and return water temperature difference of the user unit; It represents the sum of the slopes of all two adjacent temperature data points in the current abnormal heating interval; Indicates the minimum value of the temperature data within the current abnormal heating range; Indicates the standard temperature value of the indoor temperature of the user unit corresponding to the current heating intensity.

[0074] In the above formula, the above supply and return water temperature difference The larger the value, the more likely it is that the abnormal heating interval is caused by an abnormality in the heating system, and the less interference the user's window-opening behavior has. In the current abnormal heating interval, the indoor temperature of the user unit drops more slowly (the smaller the slope between two adjacent temperature data points, that is, the above The larger the value is), the more likely it is that the current abnormal heating interval is the temperature drop caused by the user opening the window; the above The smaller the value of , the smaller the temperature drop in the current abnormal heating interval, the more likely it is to correspond to a small temperature change caused by the user's window opening behavior, and the greater the degree of window opening interference in the user unit.

[0075] In step S150 , the confidence level of the abnormality in the heating system is determined based on the temperature deviation dispersion, the similarity of the temperature change trend, and the window interference value.

[0076] In actual heating scenarios, taking a centralized heating system that relies on water circulation to transport heat as an example, hot water usually flows through each user unit in sequence along a certain pipeline route. User units that are closer to the heat source will be affected first, while user units that are farther away will be delayed in the start time of the abnormal heating interval due to the order in which the water flows arrive. Similarly, when the heating system returns to normal, user units that are closer to the heat source will also recover first, and user units that are farther away will recover later, resulting in a sequence in the end time of the abnormal heating interval. Figure 3As shown, Figure 3 Taking the temperature data curves of two user units as an example, the starting time of the abnormal heating intervals of the two user units can be seen.

[0077] In an embodiment of the present application, the distance between the above-mentioned user unit and the heat source of the heating system can be represented by the heating distance. Since the start and end time of the abnormal heating interval are consistent with the order in which the user units are heated, the heating distance can also be used as a basis for reflecting the abnormal energy consumption of the heating system.

[0078] In an embodiment of the present application, considering the influence of the heating distance on the start and end times of the abnormal heating interval, when calculating the confidence level of the abnormality of the above-mentioned heating system, it is necessary to select an interval corresponding to the abnormal heating interval of the current user unit from the abnormal heating intervals of other user units for analysis, so as to consider the correspondence of the start time of the abnormal heating interval in the analysis process of abnormal monitoring of the heating system. Exemplarily, the process of selecting the corresponding interval can be implemented as follows: for each user unit, the time length of the abnormal heating interval of the user unit is determined based on the start and end times of the abnormal heating interval; within the abnormal heating interval of the first user unit, an interval of the same length as the time length of the abnormal heating interval of the current unit is selected as the target abnormal heating interval of the first user unit; wherein the heating distance of the above-mentioned first user unit is smaller than that of the current user unit.

[0079] Specifically, for a user unit's abnormal heating interval at the current moment, when determining the corresponding abnormal heating interval for the previous user unit (i.e., the first user unit mentioned above) that is closer to the heat source in terms of heating distance than the user unit, the portion of time equal to the user unit's abnormal heating interval is selected as the corresponding interval in the abnormal heating intervals of the remaining user units with a heating distance closer to the user unit. Similarly, for all user units with a heating distance closer to the user unit, the corresponding interval is determined according to this rule. The closer the temperature deviation dispersion of the user unit's abnormal heating interval at the current moment is to that of all its corresponding intervals, the more indicative of an abnormal heating system condition.

[0080] For example, the above-mentioned determination of the confidence level of an abnormal heating system based on the temperature deviation dispersion, the similarity of the temperature change trend, and the windowing interference value can be implemented as follows: for each user unit, the difference between the temperature deviation dispersion of the user unit's abnormal heating interval and the temperature deviation dispersion of the corresponding target abnormal heating interval is calculated and summed; the confidence level is determined based on the sum of the temperature deviation dispersion differences, the similarity of the temperature change trend, and the windowing interference value. Specifically, the confidence level can be determined using the following formula:

[0081]

[0082] in, Indicates the similarity of the temperature change trends among all user units (i.e., the similarity of the above temperature change trends); Indicates the possible degree of windowing interference of the user unit (i.e. the above-mentioned windowing interference value); Indicates the number of user units corresponding to the abnormal heating interval ending at the current monitoring moment; They respectively represent the temperature deviation dispersion of the abnormal heating intervals of the x-th user unit and the y-th user unit at the current monitoring moment.

[0083] In the above formula, the above It means that for each user unit with abnormal heating interval at the moment, the sum of the differences in temperature deviation dispersion between it and all the user units with the previous heating distance (that is, the first user unit mentioned above) is calculated. The smaller the sum, the greater the possibility that the change in the temperature deviation dispersion of the user unit at the current monitoring moment has the law of abnormal heating distribution, and the similarity of the temperature change trend is higher. The larger the value of , the higher the confidence level of the abnormality in the heating system obtained by the above calculation.

[0084] In step S160, it is determined based on the confidence level whether an abnormality occurs in the heating system, and when it is determined that an abnormality occurs in the heating system, the abnormality is processed.

[0085] In an embodiment of the present application, the above-mentioned confidence-based judgment of whether an abnormality occurs in the heating system can be implemented as follows: a two-dimensional coordinate system is established with time as the vertical axis and the user units with the above-mentioned heating distances from near to far as the horizontal axis; the starting time of the abnormal heating interval of each user unit is marked in the two-dimensional coordinate system to obtain a starting time curve, and the starting time curve is fitted with a least squares method to obtain a first fitting curve of the starting time curve; the ending time of the abnormal heating interval of each user unit is marked in the two-dimensional coordinate system to obtain an ending time curve, and the ending time curve is fitted with a least squares method to obtain a second fitting curve of the ending time curve; based on the first fitting curve, the second fitting curve and the confidence level, it is judged whether an abnormality occurs in the heating system.

[0086] Specifically, determining the start time curve and its corresponding first fitting curve, and determining the end time curve and its second fitting curve are implemented as follows: A heating distance sequence corresponding to all user units in the target building is obtained, and a two-dimensional coordinate system is constructed with the user units from closest to furthest heating distance as the horizontal axis and the time as the vertical axis. The start time and end time of each user unit's abnormal heating interval are marked in the two-dimensional coordinate system to obtain the start time curve and end time curve for all user units' abnormal heating intervals. If a user unit does not have an abnormal heating interval, no data point is marked in the two-dimensional coordinate system. A least squares linear fit is performed on the start time curve and end time curve for all user units' abnormal heating intervals, and the fitting residual is obtained. The smaller the fitting residual, the better the least squares linear fit. Assuming that the slopes of the fitting curves for the start time curve and the end time curve are both positive, the smaller the fitting variance, the more likely the user unit's affected time is related to the heating distance, and thus the greater the likelihood that the user unit's abnormal heating interval is caused by a heating system abnormality.

[0087] Furthermore, the above-mentioned determination of whether an abnormality occurs in the heating system based on the first fitting curve, the second fitting curve and the confidence level can be implemented as follows: determine the slopes of the first fitting curve and the second fitting curve; when the slopes of the first fitting curve and the second fitting curve are both positive and the confidence level is greater than a preset threshold, determine that an abnormality occurs in the heating system. Taking the above-mentioned preset threshold of 0.75 as an example, the slopes of the fitting curves of the starting time curve and the ending time curve are both positive, and the above-mentioned confidence level is greater than a preset threshold. When the value of is greater than the preset threshold value of 0.75, it is determined that an abnormality has occurred in the heating system at the current monitoring moment.

[0088] In the embodiment of the present application, after determining that the heating system has an abnormality, the abnormal situation can also be handled. For example, the process of handling the abnormality of the heating system can be achieved in the following ways: confirming and recording the abnormal situation, reviewing the various data used in the above-mentioned process of determining the abnormal energy consumption of the heating system to ensure that the misjudgment is not caused by data errors or sensor failures; recording in detail the time when the abnormality occurred, the range of user units involved, the relevant data of the abnormal heating interval and the current energy consumption data; investigating and locating the cause of the abnormality, arranging professional personnel to inspect the key parts of the heating system, and combining historical and real-time data to deeply analyze the root cause of the energy consumption abnormality; implementing treatment measures, Carry out emergency repairs for problems found during inspections, and adjust operating parameters based on data analysis results. If the anomaly is caused by unreasonable heat usage by users, it is necessary to communicate with the users in a timely manner and provide correct heat usage guidance; evaluate the effectiveness of anomaly handling results, continuously monitor energy consumption data and compare it with the data before the anomaly occurred, collect user feedback, and summarize the lessons learned in the anomaly handling process; optimize the heating system anomaly monitoring system to improve the accuracy of anomaly identification and early warning capabilities. In addition, the monitoring information can be enriched by adding monitoring indicators. By establishing a knowledge base, the monitoring system can automatically give processing suggestions when an anomaly occurs, thereby realizing continuous and intelligent monitoring of energy consumption anomalies in the heating system.

[0089] The present invention collects the indoor temperature of the user unit and the supply and return water temperature of the heating system, and determines the abnormal heating interval based on the indoor temperature and the temperature standard value under the current heating intensity. Therefore, the temperature deviation discreteness of each abnormal heating interval and the similarity of the temperature change trend of each user unit can be determined based on the indoor temperature of each user unit. The window opening interference value can be determined based on the supply water temperature, return water temperature and the indoor temperature within the abnormal heating interval. Furthermore, the confidence level of the abnormality of the heating system can be determined based on the temperature deviation discreteness, the similarity of the temperature change trend and the window opening interference value. Based on the confidence level, it is determined whether the heating system is abnormal, and when an abnormality occurs, the abnormality is handled. In summary, the present invention identifies the abnormal heating interval based on the normal temperature fluctuation range of the user unit, greatly improving the accuracy of abnormality monitoring. When analyzing the confidence level of the abnormal heating energy consumption, not only the data change trend of the abnormal heating interval is considered, but also the similarity of the temperature data change trend between all user units and the interference caused by user window opening are comprehensively considered, effectively eliminating false alarms caused by user behavior or other non-system failure factors. When it is determined that an abnormal situation occurs in the heating system, the operation and maintenance personnel can take targeted measures in a timely manner, reducing the system failure time and ensuring efficient and stable operation of the system.

[0090] The above mainly introduces the solution provided by the embodiment of the present invention from the perspective of method. In order to realize the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0091] The embodiment of the present disclosure provides an intelligent monitoring system for abnormal building energy consumption. Figure 4 As shown, the intelligent monitoring system 400 for abnormal building energy consumption may include a sensor module 410, a data processing module 420, an analysis module 430, a determination module 440, and a processing module 450, wherein:

[0092] The sensor module 410 is used to collect the indoor temperature of each user unit in the target building and monitor the supply water temperature and return water temperature of the heating system of the target building;

[0093] The data processing module 420 is configured to determine a standard temperature value of the indoor temperature based on the heating intensity of the heating system, and determine an abnormal heating interval of each user unit based on the standard temperature value and the indoor temperature of each user unit;

[0094] An analysis module 430 is configured to determine, based on the indoor temperature of each user unit in the abnormal heating interval, a temperature deviation dispersion of each abnormal heating interval and a similarity of temperature change trends of each user unit;

[0095] The analysis module 430 is further configured to determine a window opening interference value based on the supply water temperature, the return water temperature, and the indoor temperature within the abnormal heating interval;

[0096] The analysis module 430 is further configured to determine the confidence level of the abnormality in the heating system based on the temperature deviation dispersion, the similarity of the temperature change trend, and the window opening interference value;

[0097] A determination module 440 is configured to determine whether an abnormality occurs in the heating system based on the confidence level;

[0098] The processing module 450 is used to process the abnormal situation when it is determined that the heating system has an abnormality.

[0099] In an embodiment of the present application, the above-mentioned data processing module is specifically used to: determine the normal temperature fluctuation range based on the temperature standard value; for each user unit, if the indoor temperature exceeds the normal temperature fluctuation range at a first target number of consecutive monitoring moments, then when the indoor temperature is within the normal temperature fluctuation range at a second target number of consecutive monitoring moments, the first monitoring moment in the first target number is used as the starting moment, and the last monitoring moment before the second target number is used as the end moment to determine the abnormal heating interval of the user unit.

[0100] In an embodiment of the present application, the above-mentioned analysis module is specifically used to: determine the minimum value of the indoor temperature and the number of temperature data points in the abnormal heating interval; calculate the sum of the first differences between adjacent indoor temperatures in the abnormal heating interval, and the second difference between the temperature standard value and the minimum value of the indoor temperature in the abnormal heating interval; determine the temperature deviation discreteness based on the sum of the first difference, the second difference and the number of temperature data points of the indoor temperature in the abnormal heating interval.

[0101] In an embodiment of the present application, the above-mentioned analysis module is specifically used to: determine the dynamic time warping distance values ​​between each abnormal heating interval based on the dynamic time warping algorithm and sum them up; determine the total number of user units in the target building and the number of user units corresponding to the abnormal heating intervals; determine the similarity of temperature change trends based on the total number of user units in the target building, the number of user units corresponding to the abnormal heating intervals and the sum of the dynamic time warping distance values.

[0102] In an embodiment of the present application, the above-mentioned analysis module is specifically used to: determine the supply and return water temperature difference of the user unit based on the supply water temperature and the return water temperature; determine the slopes corresponding to all adjacent indoor temperatures in the abnormal heating interval and sum them; determine the minimum value of the indoor temperature in the abnormal heating interval, and calculate the difference between the temperature standard value and the minimum value of the indoor temperature in the abnormal heating interval; determine the window opening interference value based on the supply and return water temperature difference, the sum of the slopes corresponding to all adjacent indoor temperatures, and the difference between the temperature standard value and the minimum value of the indoor temperature in the abnormal heating interval.

[0103] In an embodiment of the present application, the above-mentioned analysis module is specifically used for: for each user unit, determining the time length of the abnormal heating interval of the user unit based on the start time and end time of the abnormal heating interval; selecting an interval of equal length to the above-mentioned time length within the abnormal heating interval of the first user unit as the target abnormal heating interval of the first user unit; wherein the heating distance of the first user unit is smaller than that of the user unit, and the above-mentioned heating distance is the distance between the user unit and the heating system. In an embodiment of the present application, the above-mentioned analysis module is specifically used for: for each user unit, calculating the difference between the temperature deviation discreteness of the abnormal heating interval of the user unit and the temperature deviation discreteness of each corresponding target abnormal heating interval and summing them; determining the above-mentioned confidence based on the sum of the difference in temperature deviation discreteness, the similarity of temperature change trends and the windowing interference value.

[0104] In an embodiment of the present application, the above-mentioned determination module is specifically used to: establish a two-dimensional coordinate system with time as the vertical axis and user units with heating distances from near to far as the horizontal axis; mark the starting time of the abnormal heating interval of each user unit in the two-dimensional coordinate system to obtain a starting time curve, and perform least squares linear fitting on the starting time curve to obtain a first fitting curve of the starting time curve; mark the ending time of the abnormal heating interval of each user unit in the two-dimensional coordinate system to obtain an ending time curve, and perform least squares linear fitting on the ending time curve to obtain a second fitting curve of the ending time curve; judge whether the heating system is abnormal based on the first fitting curve, the second fitting curve and the confidence level.

[0105] In an embodiment of the present application, the above-mentioned processing module is specifically used to: determine the slopes of the first fitting curve and the second fitting curve; when the slopes of the first fitting curve and the second fitting curve are both positive values ​​and the above-mentioned confidence value is greater than a preset threshold, it is judged that an abnormality has occurred in the heating system.

[0106] In embodiments of the present invention, the intelligent monitoring system for abnormal building energy consumption can be divided into functional modules based on the above-described method example. For example, each functional module can be divided into corresponding functional modules, or two or more functions can be integrated into a single processing module. The above-mentioned integrated modules can be implemented in the form of hardware or software functional modules. It should be noted that the module division in the embodiments of the present invention is illustrative and only represents a logical functional division. In actual implementation, other division methods may be used.

[0107] In addition, the specific implementation details of the above-mentioned intelligent monitoring system for abnormal building energy consumption have been described in detail in the corresponding position of the intelligent monitoring method for abnormal building energy consumption, so they will not be repeated here.

[0108] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0109] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. An intelligent monitoring method for abnormal building energy consumption, characterized in that: The method comprises: Collecting the indoor temperature of each user unit in the target building and monitoring the supply water temperature and return water temperature of the heating system of the target building; determining a standard temperature value of the indoor temperature based on the heating intensity of the heating system, and determining an abnormal heating interval of each user unit based on the standard temperature value and the indoor temperature of each user unit; determining, based on the indoor temperature of each user unit in the abnormal heating interval, a temperature deviation dispersion of each abnormal heating interval and a similarity of a temperature change trend of each user unit; determining a window opening interference value based on the supply water temperature, the return water temperature, and the indoor temperature within the abnormal heating interval; Determining a confidence level that an abnormality has occurred in the heating system based on the temperature deviation dispersion, the similarity of the temperature change trend, and the window opening interference value; determining whether an abnormality occurs in the heating system based on the confidence level, and handling the abnormality when it is determined that an abnormality occurs in the heating system; Determining a window opening interference value based on the supply water temperature, the return water temperature, and the indoor temperature within the abnormal heating interval includes: Determining a supply and return water temperature difference of the user unit based on the supply water temperature and the return water temperature; Determine the slopes corresponding to all adjacent indoor temperatures in the abnormal heating interval and sum them; determining a minimum value of the indoor temperature within the abnormal heating interval, and calculating a difference between the temperature standard value and the minimum value of the indoor temperature within the abnormal heating interval; The window opening interference value is determined based on the supply and return water temperature difference, the sum of the slopes corresponding to all adjacent indoor temperatures, and the difference between the temperature standard value and the minimum value of the indoor temperature in the abnormal heating interval.

2. The intelligent monitoring method for abnormal building energy consumption according to claim 1, characterized in that: The determining of the abnormal heating interval of each user unit based on the temperature standard value and the indoor temperature of each user unit includes: determining a normal temperature fluctuation range based on the temperature standard value; For each user unit, if the indoor temperature exceeds the normal temperature fluctuation range at a first target number of consecutive monitoring moments, then when the indoor temperature is within the normal temperature fluctuation range at a second target number of consecutive monitoring moments, the first monitoring moment in the first target number is taken as the starting moment, and the last monitoring moment before the second target number is taken as the ending moment to determine the abnormal heating interval of the user unit.

3. The intelligent monitoring method for abnormal building energy consumption according to claim 1, characterized in that: The determining, based on the indoor temperature of each user unit within the abnormal heating interval, the temperature deviation dispersion of each abnormal heating interval includes: determining the minimum value of the indoor temperature and the number of temperature data points within the abnormal heating interval; calculating a sum of first differences between adjacent indoor temperatures in the abnormal heating interval, and a second difference between the temperature standard value and the minimum indoor temperature in the abnormal heating interval; The temperature deviation dispersion is determined based on the sum of the first difference, the second difference, and the number of temperature data points of the indoor temperature in the abnormal heating interval.

4. The intelligent monitoring method for abnormal building energy consumption according to claim 1, characterized in that: The determining, based on the indoor temperature of each user unit in the abnormal heating interval, the similarity of the temperature change trend of each user unit includes: Determine the dynamic time warping distance values ​​between each of the abnormal heating intervals based on a dynamic time warping algorithm and sum them up; Determining the total number of the user units in the target building and the number of the user units corresponding to the abnormal heating interval; The similarity of the temperature change trend is determined based on the total number of the user units in the target building, the number of the user units corresponding to the abnormal heating interval, and the sum of the dynamic time warping distance values.

5. The intelligent monitoring method for abnormal building energy consumption according to claim 2, characterized in that: After determining the abnormal heating interval of the user unit by taking the first monitoring moment of the first target number as the starting moment and the last monitoring moment before the second target number as the ending moment, the method further includes: For each user unit, determining a duration of the abnormal heating interval of the user unit based on the start time and the end time; An interval of equal length to the time length is selected within the abnormal heating interval of the first user unit as the target abnormal heating interval of the first user unit; wherein the heating distance of the first user unit is smaller than that of the user unit, and the heating distance is the distance from the heating system.

6. The intelligent monitoring method for abnormal building energy consumption according to claim 5, characterized in that: The determining of the confidence level of the abnormality of the heating system based on the temperature deviation dispersion, the similarity of the temperature change trend, and the window interference value includes: For each user unit, calculating the difference between the temperature deviation dispersion of the abnormal heating interval of the user unit and the temperature deviation dispersion of each corresponding target abnormal heating interval and summing the differences; The confidence level is determined based on the sum of the differences in the temperature deviation dispersions, the similarity of the temperature change trends, and the windowed interference value.

7. The intelligent monitoring method for abnormal building energy consumption according to claim 5, characterized in that: The determining whether an abnormality occurs in the heating system based on the confidence level includes: A two-dimensional coordinate system is established with time as the vertical axis and the user units of the heating distance from near to far as the horizontal axis; Marking the starting time of the abnormal heating interval of each user unit in the two-dimensional coordinate system to obtain a starting time curve, and performing least squares linear fitting on the starting time curve to obtain a first fitting curve of the starting time curve; Marking the end time of the abnormal heating interval of each user unit in the two-dimensional coordinate system to obtain an end time curve, and performing least squares linear fitting on the end time curve to obtain a second fitting curve of the end time curve; Whether an abnormality occurs in the heating system is determined based on the first fitting curve, the second fitting curve, and the confidence level.

8. The intelligent monitoring method for abnormal building energy consumption according to claim 7, characterized in that: The determining whether an abnormality occurs in the heating system based on the first fitting curve, the second fitting curve, and the confidence level includes: determining the slopes of the first fitting curve and the second fitting curve; When the slopes of the first fitting curve and the second fitting curve are both positive, and the confidence value is greater than a preset threshold, it is determined that an abnormality occurs in the heating system.

9. An intelligent monitoring system for abnormal building energy consumption, characterized in that: The system comprises: A sensor module is used to collect the indoor temperature of each user unit in the target building and monitor the supply water temperature and return water temperature of the heating system of the target building; a data processing module, configured to determine a standard temperature value of the indoor temperature based on the heating intensity of the heating system, and determine an abnormal heating interval of each user unit based on the standard temperature value and the indoor temperature of each user unit; an analysis module for determining, based on the indoor temperature of each user unit in the abnormal heating interval, a temperature deviation dispersion of each abnormal heating interval and a similarity of a temperature change trend of each user unit; The analysis module is further configured to determine a window opening interference value based on the supply water temperature, the return water temperature, and the indoor temperature within the abnormal heating interval; The analysis module is further configured to determine a confidence level that an abnormality has occurred in the heating system based on the temperature deviation dispersion, the similarity of the temperature change trend, and the window opening interference value; a determination module, configured to determine whether an abnormality occurs in the heating system based on the confidence level; A processing module, configured to process the abnormality when it is determined that the heating system has an abnormality; Determining a window opening interference value based on the supply water temperature, the return water temperature, and the indoor temperature within the abnormal heating interval includes: Determining a supply and return water temperature difference of the user unit based on the supply water temperature and the return water temperature; Determine the slopes corresponding to all adjacent indoor temperatures in the abnormal heating interval and sum them; determining a minimum value of the indoor temperature within the abnormal heating interval, and calculating a difference between the temperature standard value and the minimum value of the indoor temperature within the abnormal heating interval; The window opening interference value is determined based on the supply and return water temperature difference, the sum of the slopes corresponding to all adjacent indoor temperatures, and the difference between the temperature standard value and the minimum value of the indoor temperature in the abnormal heating interval.

Images