Method and system for monitoring abnormal use of heating equipment based on multi-source data

Abstract

The invention relates to the technical field of heat supply equipment, in particular to a method and a system for monitoring abnormal use of heat supply equipment based on multi-source data. Comprising the steps of generating a plurality of user points according to a heat supply area, and obtaining a heat supply monitoring packet of each user point according to a preset feedback time node; generating a heat supply abnormal value of each user point according to a preset abnormal evaluation model and all the heat supply monitoring packets; a plurality of risk user points are selected according to all the heat supply abnormal values, and an abnormal behavior diagnosis result is generated according to all the risk user points and a preset heat supply diagnosis model; according to the method, users in a heat supply area are analyzed, a dual evaluation model based on heat supply positions and user behavior habits is constructed, the abnormal heat supply state of each user is recognized in time, so that risk user points are screened, and whether abnormal illegal behaviors exist in each risk user point or not is judged through an established heat supply diagnosis model, so that the risk user points are diagnosed. And the recognition early warning and positioning diagnosis efficiency of the abnormal behavior of the heat supply system user side is improved.

Description

A method and system for monitoring abnormal use of heating equipment based on multi-source data Technical Field

[0001] This application relates to the field of heating equipment technology, and in particular to a method and system for monitoring abnormal use of heating equipment based on multi-source data. Background Technology

[0002] In the operation and management of heating systems, abnormal heating behaviors at the user end are the main cause of energy waste, hydraulic imbalance in the heating network, and economic losses. Such behaviors include unauthorized water release, installation of circulation pumps, and malicious obstruction of heat meters, and are characterized by their high degree of concealment and dispersed distribution.

[0003] Currently, heating companies mainly rely on manual inspections or simple comparisons of heat meter data for monitoring. Manual inspections are inefficient and difficult to verify; while relying solely on heat data cannot effectively distinguish between normal energy-saving behavior and illegal heating use, resulting in a high rate of misjudgment. Existing technologies lack in-depth integration and analysis of multi-dimensional user-side data. For example, they fail to systematically correlate changes in indoor temperature, return water temperature, and flow curves with the total heat supply of the unit and neighborhood heating patterns. When anomalies occur, the system often only detects macroscopic phenomena such as increased total energy consumption, but struggles to accurately pinpoint specific users and their abnormal behaviors, leading to management delays and an inability to promptly stop violations. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for monitoring abnormal use of heating equipment based on multi-source data in order to solve the above-mentioned technical problems, aiming to improve the efficiency of identifying, warning and locating abnormal behavior of heating system users.

[0005] In some embodiments of this application, by analyzing users within the heating area, a dual evaluation model based on heating location and user behavior habits is constructed to promptly identify abnormal heating status of each user, thereby screening risk user points. Furthermore, the established heating diagnostic model is used to determine whether there are any abnormal violations at each risk user point, thereby improving the efficiency of identifying and warning of abnormal behavior at the user end of the heating system.

[0006] In some embodiments of this application, historical data is analyzed to generate various abnormal behaviors to construct an abnormal diagnosis model. The abnormal diagnosis model is then used to analyze the heating monitoring packages of each risk user point to determine the specific abnormal behaviors of each risk user point, enabling early warning and maintenance, and improving the efficiency of locating and diagnosing abnormal behaviors at the user end of the heating system.

[0007] In some embodiments of this application, a method for monitoring abnormal use of heating equipment based on multi-source data is provided, including: generating multiple user points according to the heating area; obtaining heating monitoring packages for each user point according to a preset feedback time node; generating heating anomaly values ​​for each user point according to a preset anomaly assessment model and all heating monitoring packages; selecting multiple risk user points based on all heating anomaly values; and generating abnormal behavior diagnosis results based on all risk user points and a preset heating diagnosis model; wherein, setting multiple user points includes: establishing a user point sequence A, A=(a1,a2…a ... i …a n ), where a i Let be the i-th user point; n is the number of user points.

[0008] In some embodiments of this application, a pre-defined anomaly assessment model is included, comprising: generating multiple user characteristic indicators based on historical monitoring data; setting multiple user categories based on all user characteristic indicators; and establishing a user category sequence B, B=(b1, b2…b…). i …b m ), where b i Let m be the number of user categories, and b be the number of user categories, according to the sequence of user categories B. i Define the target user category; construct an evaluation sub-model for the target user category based on historical monitoring data; set multiple monitoring sub-regions based on the heating area; construct the correlation sub-model for each monitoring sub-region in sequence; generate an anomaly evaluation model based on all correlation sub-models and all evaluation sub-models.

[0009] In some embodiments of this application, multiple risk user points are selected based on all abnormal heating values, including: setting a sequentially according to the user point sequence A. i For the target user point; obtain the user feature package and location parameters of the target user point; set a first-level correlation model based on the location parameters and the anomaly assessment model; set a first-level assessment model based on the user feature package and the anomaly assessment model; obtain the heating monitoring package of the target user point at the current feedback time node; generate the heating anomaly value f of the target user point based on the heating monitoring package; preset the heating anomaly value threshold F1; if f>F1, set the target user point as a risk user point at the current feedback time node; sequentially determine whether each user point is a risk user point at the current feedback time node.

[0010] In some embodiments of this application, generating the heating anomaly value f for the target user point includes: f = g * [ µ i *(s i -s' i ) 2 ];g=U1*[ k iWhere g is the anomaly compensation coefficient; θ1 is the number of thermal monitoring indicators; µ i s is the influencing factor of the i-th thermal monitoring index; i It is a reference value for the i-th thermal monitoring index generated based on the heating monitoring package; s' i To generate the standard reference value for the i-th thermal monitoring index based on the first-level evaluation model; U1 is the preset first conversion coefficient; θ2 is the number of associated user points of the target user point generated according to the first-level correlation model; k i This represents the first-level outlier value of the i-th associated user point at the current feedback time point.

[0011] In some embodiments of this application, a preset heating diagnostic model is included, comprising: setting multiple abnormal behaviors based on historical monitoring data; and establishing an abnormal behavior sequence W, W=(w1, w2…w…). i …w r ), where w i Let r be the i-th abnormal behavior; r is the number of abnormal behaviors; generate diagnostic sub-models for each abnormal behavior in sequence; generate a heating diagnostic model based on all diagnostic sub-models.

[0012] In some embodiments of this application, diagnostic sub-models for each abnormal behavior are generated sequentially, including: setting w sequentially according to the abnormal sub-behavior sequence W. i For the target abnormal behavior; construct a diagnostic sub-model of the target abnormal behavior; obtain the first-level association package of the target abnormal behavior; generate a simulation sub-model of the target abnormal behavior based on the first-level association package; and set b sequentially according to the user behavior category B. i The process involves: identifying the user category to be compensated; generating a secondary association package based on the target abnormal behavior and the user category to be compensated; generating compensation sub-strategies for the target abnormal behavior for the user category to be compensated based on the secondary association package; generating compensation sub-strategies for each user category in sequence; and generating a diagnostic sub-model for the target abnormal behavior based on all compensation sub-strategies and the simulation sub-model.

[0013] In some embodiments of this application, generating abnormal behavior diagnostic results includes: obtaining all risk user points at the current feedback time point; establishing a risk user point sequence A1; A1=(a 11 a 12 …a 1i …a 1n1 ), where a 1i Let n1 be the i-th user risk point at the current feedback time point; n1 is the number of risky user points at the current feedback time point; set a according to the risky user point count sequence A1. 1i The target risk point is defined; w is set sequentially based on the abnormal behavior sequence W. iThe target risk point and the behavior to be compared are used as the comparison behavior. The heating diagnosis model generates a first-level diagnosis model based on the target risk point and the behavior to be compared. A matching evaluation value c is generated based on the first-level diagnosis model. A matching evaluation value threshold C1 is preset. If c > C1, the target risk point generates a first-level warning instruction for the behavior to be compared. The model then determines whether the target risk point generates a first-level warning instruction for each abnormal behavior. The model generates a diagnosis sub-result for the target risk point based on all first-level warning instructions. The model then generates a diagnosis sub-result for each user risk point in turn. Finally, the model generates an abnormal behavior diagnosis result based on all diagnosis sub-results.

[0014] In some embodiments of this application, the generation of the matching evaluation value c includes: c = U2*[ η i *(s 1i -e i *s 2i ) 2 Where, U2 is the preset second conversion coefficient; θ1 is the number of thermal monitoring indicators; η i The weighting coefficient of the i-th thermal monitoring index is set according to the primary diagnostic model; s 1i Let s be the reference value of the i-th thermal monitoring indicator at the current feedback time point for the target risk point; 2i The comparison reference value for the i-th thermal monitoring index is set based on the simulation sub-model in the primary diagnostic model; e i It is the compensation coefficient of the i-th thermal monitoring index set according to the compensator strategy in the first-level diagnostic model.

[0015] In some embodiments of this application, a monitoring system for abnormal use of heating equipment based on multi-source data is provided, comprising: a central control unit for generating multiple user points according to the heating area; a monitoring unit including multiple monitoring sub-modules, wherein the monitoring sub-modules are set at each user point; the monitoring unit is used to collect heating data from each user point and generate heating monitoring packages for each user point; the central control unit includes: a first processing module for obtaining heating monitoring packages for each user point according to a preset feedback time node; the first processing module is further used to generate heating anomaly values ​​for each user point according to a preset anomaly assessment model and all heating monitoring packages; a second processing module for selecting multiple risk user points according to all heating anomaly values ​​and generating abnormal behavior diagnosis results according to all risk user points and a preset heating diagnosis model; and a third processing module for establishing a user point sequence A, A=(a1,a2…a ... i …a n ), where a i Let be the i-th user point; n is the number of user points.

[0016] In some embodiments of this application, the first processing module is further configured to: generate multiple user characteristic indicators based on historical monitoring data; set multiple user categories based on all user characteristic indicators; and establish a user category sequence B, B=(b1, b2…b ... i …b m ), where b i Let m be the number of user categories, and b be the number of user categories, according to the sequence of user categories B. i Define the target user category; construct an evaluation sub-model for the target user category based on historical monitoring data; set multiple monitoring sub-regions based on the heating area; construct the correlation sub-model for each monitoring sub-region in sequence; generate an anomaly evaluation model based on all correlation sub-models and all evaluation sub-models.

[0017] Compared with existing technologies, the present application's embodiment of a method and system for monitoring abnormal use of heating equipment based on multi-source data has the following advantages: by analyzing users within the heating area, a dual evaluation model based on heating location and user behavior habits is constructed to promptly identify abnormal heating status of each user, thereby screening risk user points. Furthermore, the established heating diagnostic model is used to determine whether there are any abnormal violations at each risk user point, thus improving the efficiency of identifying and warning of abnormal behavior at the user end of the heating system.

[0018] By analyzing historical data, various abnormal behaviors are generated to construct an anomaly diagnosis model. The anomaly diagnosis model is then used to analyze the monitoring data of each risk user point to determine the specific abnormal behaviors of each risk user point, enabling early warning and maintenance, and improving the efficiency of locating and diagnosing abnormal behaviors at the user end of the heating system. Attached Figure Description

[0019] Figure 1 is a flowchart illustrating a method for monitoring abnormal use of heating equipment based on multi-source data in a preferred embodiment of this application. Detailed Implementation

[0020] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are used to illustrate this application, but are not intended to limit the scope of this application.

[0021] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0022] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0023] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0024] As shown in Figure 1, a preferred embodiment of this application provides a method for monitoring abnormal use of heating equipment based on multi-source data, comprising: S101; generating multiple user points according to the heating area, and obtaining heating monitoring packages for each user point according to a preset feedback time node; S102; generating heating anomaly values ​​for each user point according to a preset anomaly assessment model and all heating monitoring packages; S103; selecting multiple risk user points based on all heating anomaly values, and generating abnormal behavior diagnosis results based on all risk user points and a preset heating diagnosis model; wherein, setting multiple user points includes: establishing a user point sequence A, A=(a1,a2…a ... i …a n ), where a i Let be the i-th user point; n is the number of user points.

[0025] Specifically, multiple heating users are selected based on the operation and maintenance data of the heating system, and multiple user points are set based on all heating users, where a single user point represents one heating user.

[0026] Specifically, the time interval between adjacent feedback time points can be set based on historical parameters.

[0027] Specifically, the pre-defined anomaly assessment model includes: generating multiple user characteristic indicators based on historical monitoring data; setting multiple user categories based on all user characteristic indicators; and establishing a user category sequence B, B=(b1, b2…b…). i …b m ), where b i Let m be the number of user categories, and b be the number of user categories, according to the sequence of user categories B. iDefine the target user category; construct an evaluation sub-model for the target user category based on historical monitoring data; set multiple monitoring sub-regions based on the heating area; construct the correlation sub-model for each monitoring sub-region in sequence; generate an anomaly evaluation model based on all correlation sub-models and all evaluation sub-models.

[0028] Specifically, user characteristic indicators include, but are not limited to, parameters that affect users' heating habits, such as heating temperature (i.e., the temperature set by the user), heating area (i.e., the user's living area), heating height (i.e., the floor height where the user is located), and outdoor temperature. Multiple value ranges for each user characteristic indicator are generated in sequence, and various user categories are generated based on random combinations of all value ranges.

[0029] Specifically, by analyzing historical monitoring data, various thermal monitoring indicators are generated, including but not limited to: instantaneous flow rate, cumulative flow rate, supply water temperature, return water temperature, valve opening, supply and return water pressure, outdoor temperature, indoor temperature, and other operating parameters related to the heating system. Quantification ensures that the reference values ​​of each thermal monitoring indicator are within the same range.

[0030] Specifically, by generating multiple user categories, users with the same heating habits are aggregated to establish targeted evaluation sub-models for each user category. Each evaluation sub-model includes the standard reference values ​​of each thermal monitoring indicator corresponding to the user category (i.e., the reference values ​​corresponding to the user category when it is in a normal state). When the real-time reference value of the thermal monitoring indicator is greater than the preset safety threshold, it indicates that the user has an abnormal heating state.

[0031] Specifically, by analyzing the location parameters of all users within the heating area, all user points belonging to the same community are set as a monitoring sub-area.

[0032] Specifically, all user points within a single monitoring sub-region are related user points, and a corresponding related sub-model is constructed based on all the relationships within the single monitoring sub-region.

[0033] In a preferred embodiment of this application, multiple risk user points are selected based on all abnormal heating values, including: setting a sequentially according to the user point sequence A. i For the target user point; obtain the user feature package and location parameters of the target user point; set a first-level correlation model based on the location parameters and the anomaly assessment model; set a first-level assessment model based on the user feature package and the anomaly assessment model; obtain the heating monitoring package of the target user point at the current feedback time node; generate the heating anomaly value f of the target user point based on the heating monitoring package; preset the heating anomaly value threshold F1; if f>F1, set the target user point as a risk user point at the current feedback time node; sequentially determine whether each user point is a risk user point at the current feedback time node.

[0034] Specifically, the threshold for abnormal heating values ​​can be set based on historical parameters. When the heating reference value of the target user point is greater than the preset heating standard reference value, it indicates that there is an abnormal heating state at the target user point.

[0035] Specifically, the correlation sub-model corresponding to the monitoring sub-area where the target user point is located is set as the first-level correlation model.

[0036] Specifically, the user category corresponding to the target user point is determined based on the user feature package of the obtained target user point, and the evaluation sub-model corresponding to the user category is set as the first-level evaluation model.

[0037] Specifically, the user feature package contains the parameter values ​​of each user feature indicator for the target user.

[0038] Specifically, generating the heating anomaly value f for the target user point includes: f = g * [ µ i *(s i -s' i ) 2 ];g=U1*[ k i Where g is the anomaly compensation coefficient; θ1 is the number of thermal monitoring indicators; µ i s is the influencing factor of the i-th thermal monitoring index; i It is a reference value for the i-th thermal monitoring index generated based on the heating monitoring package; s' i To generate the standard reference value for the i-th thermal monitoring index based on the first-level evaluation model; U1 is the preset first conversion coefficient; θ2 is the number of associated user points of the target user point generated according to the first-level correlation model; k i This represents the first-level outlier value of the i-th associated user point at the current feedback time point.

[0039] Specifically, by presetting a first conversion coefficient, the anomaly compensation coefficient is made to be within a preset value range, and [ k i The larger the value of ], the smaller the corresponding anomaly compensation coefficient. The mapping relationship between the two can be set based on historical parameters. By setting the anomaly compensation coefficient, the problem of the accuracy of identifying abnormal behavior at the user end caused by the overall heating anomaly interference in some areas due to the operation failure of the heating system can be reduced.

[0040] Specifically, the influence factors of each thermal monitoring index can be set according to their correlation with abnormal heating conditions. The greater the correlation, the larger the value of the corresponding influence factor. The mapping relationship between the two can be set according to historical parameters.

[0041] Specifically, the first-level outliers of each associated user point are those values ​​within that associated user point. µ i *(s i -s' i ) 2 The corresponding value.

[0042] It is understood that in the above embodiments, by analyzing users within the heating area, a dual evaluation model based on heating location and user behavior habits is constructed to identify abnormal heating status of each user in a timely manner, thereby screening risk user points. Furthermore, the established heating diagnosis model is used to determine whether there are any abnormal violations at each risk user point, thereby improving the efficiency of identifying and warning of abnormal behavior at the user end of the heating system.

[0043] In a preferred embodiment of this application, the preset heating diagnostic model includes: setting multiple abnormal behaviors based on historical monitoring data; and establishing an abnormal behavior sequence W, W=(w1, w2…w…). i …w r ), where w i Let r be the i-th abnormal behavior; r is the number of abnormal behaviors; generate diagnostic sub-models for each abnormal behavior in sequence; generate a heating diagnostic model based on all diagnostic sub-models.

[0044] Specifically, by analyzing historical monitoring data, various abnormal behaviors are generated, including but not limited to: discharging hot water, users opening valves, installing circulating pumps, and short-circuiting pipes.

[0045] Specifically, diagnostic sub-models for each abnormal behavior are generated sequentially, including: setting w sequentially according to the abnormal sub-behavior sequence W. i For the target abnormal behavior; construct a diagnostic sub-model of the target abnormal behavior; obtain the first-level association package of the target abnormal behavior; generate a simulation sub-model of the target abnormal behavior based on the first-level association package; and set b sequentially according to the user behavior category B. i The process involves: identifying the user category to be compensated; generating a secondary association package based on the target abnormal behavior and the user category to be compensated; generating compensation sub-strategies for the target abnormal behavior for the user category to be compensated based on the secondary association package; generating compensation sub-strategies for each user category in sequence; and generating a diagnostic sub-model for the target abnormal behavior based on all compensation sub-strategies and the simulation sub-model.

[0046] Specifically, the first-level association package includes all monitoring data corresponding to the target abnormal behavior. By optimizing and analyzing the data in the first-level association package, a corresponding simulation sub-model is constructed. The simulation sub-model includes the comparative reference value of each heating monitoring indicator when the target abnormal behavior occurs (i.e., the average value of all reference values ​​of the heating monitoring indicator in the first-level association package).

[0047] Specifically, the data in the primary association package is further refined according to different user categories. By optimizing and analyzing the refined secondary association packages, compensation sub-strategies for each user category are constructed. The compensation sub-strategies include compensation coefficients for the comparative reference values ​​of various heating monitoring indicators.

[0048] In a preferred embodiment of this application, generating an abnormal behavior diagnosis result includes: obtaining all risk user points at the current feedback time point; establishing a risk user point sequence A1; A1=(a 11 a 12 …a 1i …a 1n1 ), where a 1i Let n1 be the i-th user risk point at the current feedback time point; n1 is the number of risky user points at the current feedback time point; set a according to the risky user point count sequence A1. 1i The target risk point is defined; w is set sequentially based on the abnormal behavior sequence W. i The target risk point and the behavior to be compared are used as the comparison behavior. The heating diagnosis model generates a first-level diagnosis model based on the target risk point and the behavior to be compared. A matching evaluation value c is generated based on the first-level diagnosis model. A matching evaluation value threshold C1 is preset. If c > C1, the target risk point generates a first-level warning instruction for the behavior to be compared. The model then determines whether the target risk point generates a first-level warning instruction for each abnormal behavior. The model generates a diagnosis sub-result for the target risk point based on all first-level warning instructions. The model then generates a diagnosis sub-result for each user risk point in turn. Finally, the model generates an abnormal behavior diagnosis result based on all diagnosis sub-results.

[0049] Specifically, the matching evaluation value threshold can be set based on historical parameters. If the matching evaluation value of the target risk point is greater than the preset matching evaluation value threshold, it indicates that the user corresponding to the target risk point has behavior to be compared, and a corresponding maintenance strategy needs to be generated according to the first-level warning instruction.

[0050] Specifically, the system sequentially identifies various abnormal behaviors of users corresponding to the target risk points and generates diagnostic sub-results for the target risk points based on the identification results.

[0051] Specifically, generating the fit evaluation value c includes: c = U2 * [ η i *(s 1i -e i *s 2i ) 2 Where, U2 is the preset second conversion coefficient; θ1 is the number of thermal monitoring indicators; η i The weighting coefficient of the i-th thermal monitoring index is set according to the primary diagnostic model; s 1i Let s be the reference value of the i-th thermal monitoring indicator at the current feedback time point for the target risk point; 2iThe comparison reference value for the i-th thermal monitoring index is set based on the simulation sub-model in the primary diagnostic model; e i It is the compensation coefficient of the i-th thermal monitoring index set according to the compensator strategy in the first-level diagnostic model.

[0052] Specifically, by presetting a second conversion coefficient, the matching evaluation value is made to fall within a preset value range, and [ η i *(s 1i -e i *s 2i ) 2 The larger the value of ], the smaller the fit evaluation value. The mapping relationship between the two can be set based on historical parameters.

[0053] Specifically, the weighting coefficients of each thermal monitoring indicator can be set according to the degree of correlation between them and the behavior to be compared. The higher the degree of correlation, the larger the corresponding weighting coefficient. The mapping relationship between the two can be set according to historical parameters.

[0054] It is understood that in the above embodiments, by analyzing historical data, various abnormal behaviors are generated to construct an abnormal diagnosis model, and the abnormal diagnosis model is used to analyze the heating monitoring packages of each risk user point to determine the specific abnormal behaviors of each risk user point, so as to provide early warning and maintenance and improve the efficiency of locating and diagnosing abnormal behaviors of the heating system user end.

[0055] Based on any of the above preferred embodiments, another preferred embodiment of a method for monitoring abnormal use of heating equipment based on multi-source data provides a system for monitoring abnormal use of heating equipment based on multi-source data, comprising: a central control unit for generating multiple user points according to the heating area; a monitoring unit including multiple monitoring sub-modules, the monitoring sub-modules being set at each user point; the monitoring unit for collecting heating data from each user point and generating heating monitoring packages for each user point; the central control unit includes: a first processing module for acquiring heating monitoring packages for each user point according to a preset feedback time node; the first processing module is also used to generate heating anomaly values ​​for each user point according to a preset anomaly assessment model and all heating monitoring packages; a second processing module for selecting multiple risk user points according to all heating anomaly values ​​and generating abnormal behavior diagnosis results according to all risk user points and a preset heating diagnosis model; and a third processing module for establishing a user point sequence A, A=(a1,a2…a ... i …a n ), where a i Let be the i-th user point; n is the number of user points.

[0056] In a preferred embodiment of this application, the first processing module is further configured to: generate multiple user characteristic indicators based on historical monitoring data; set multiple user categories based on all user characteristic indicators; and establish a user category sequence B, B=(b1, b2…b ... i …b m ), where b i Let m be the number of user categories, and b be the number of user categories, according to the sequence of user categories B. i Define the target user category; construct an evaluation sub-model for the target user category based on historical monitoring data; set multiple monitoring sub-regions based on the heating area; construct the correlation sub-model for each monitoring sub-region in sequence; generate an anomaly evaluation model based on all correlation sub-models and all evaluation sub-models.

[0057] Based on the first concept of this application, by analyzing users within the heating area, a dual assessment model based on heating location and user behavior habits is constructed to promptly identify abnormal heating status of each user, thereby screening risky user points. Furthermore, the established heating diagnosis model is used to determine whether there are any abnormal or irregular behaviors at each risky user point, thereby improving the efficiency of identifying and warning of abnormal behaviors at the user end of the heating system.

[0058] According to the second concept of this application, by analyzing historical data, an abnormality diagnosis model is generated to construct various abnormal behaviors. The abnormality diagnosis model is then used to analyze the heating monitoring packages of each risk user point to determine the specific abnormal behaviors of each risk user point, so as to provide early warning and maintenance and improve the efficiency of locating and diagnosing abnormal behaviors at the user end of the heating system.

[0059] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and substitutions can be made without departing from the technical principles of this application, and these improvements and substitutions should also be considered within the scope of protection of this application.

Claims

1. A method for monitoring abnormal use of heating equipment based on multi-source data, characterized in that, include: Multiple user points are generated based on the heating area, and heating monitoring packages for each user point are obtained according to preset feedback time nodes. Generate heating anomaly values ​​for each user point based on the preset anomaly assessment model and all heating monitoring packages; Multiple risk user points are selected based on all abnormal heating values. Abnormal behavior diagnostic results are generated based on all risk user points and a pre-set heating diagnostic model. The selection of multiple user points includes establishing a user point sequence A, A=(a1,a2…a…). i …a n ), where a i Let be the i-th user point; n is the number of user points.

2. The method for monitoring abnormal use of heating equipment based on multi-source data as described in claim 1, characterized in that, The pre-defined anomaly assessment model includes: generating multiple user characteristic indicators based on historical monitoring data; setting multiple user categories based on all user characteristic indicators; and establishing a user category sequence B, B=(b1, b2…b…). i …b m ), where b i Let m be the number of user categories, and b be the number of user categories, according to the sequence of user categories B. i Define the target user category; construct an evaluation sub-model for the target user category based on historical monitoring data; set multiple monitoring sub-regions based on the heating area; construct the correlation sub-model for each monitoring sub-region in sequence; generate an anomaly evaluation model based on all correlation sub-models and all evaluation sub-models.

3. The method for monitoring abnormal use of heating equipment based on multi-source data as described in claim 2, characterized in that, Multiple risk user points were selected based on all abnormal heating values, including: setting a according to the user point sequence A. i For the target user point; obtain the user feature package and location parameters of the target user point; set a first-level correlation model based on the location parameters and the anomaly assessment model; set a first-level assessment model based on the user feature package and the anomaly assessment model; obtain the heating monitoring package of the target user point at the current feedback time node; generate the heating anomaly value f of the target user point based on the heating monitoring package; preset the heating anomaly value threshold F1; if f>F1, set the target user point as a risk user point at the current feedback time node; sequentially determine whether each user point is a risk user point at the current feedback time node.

4. The method for monitoring abnormal use of heating equipment based on multi-source data as described in claim 3, characterized in that, Generate the heating anomaly value f for the target user point, including: f = g * [ µ i *(s i -s' i ) 2 ];g=U1*[ k i Where g is the anomaly compensation coefficient; θ1 is the number of thermal monitoring indicators; µ i s is the influencing factor of the i-th thermal monitoring index; i It is a reference value for the i-th thermal monitoring index generated based on the heating monitoring package; s' i To generate the standard reference value for the i-th thermal monitoring index based on the first-level evaluation model; U1 is the preset first conversion coefficient; θ2 is the number of associated user points of the target user point generated according to the first-level correlation model; k i This represents the first-level outlier value of the i-th associated user point at the current feedback time point.

5. The method for monitoring abnormal use of heating equipment based on multi-source data as described in claim 3, characterized in that, The pre-set heating diagnostic model includes: setting various abnormal behaviors based on historical monitoring data; and establishing an abnormal behavior sequence W, W=(w1, w2…w i …w r ), where w i Let r be the i-th abnormal behavior; r is the number of abnormal behaviors; generate diagnostic sub-models for each abnormal behavior in sequence; generate a heating diagnostic model based on all diagnostic sub-models.

6. The method for monitoring abnormal use of heating equipment based on multi-source data as described in claim 5, characterized in that, Diagnostic sub-models for each abnormal behavior are generated sequentially, including: setting w sequentially according to the abnormal sub-behavior sequence W. i For the target abnormal behavior; construct a diagnostic sub-model of the target abnormal behavior; obtain the first-level association package of the target abnormal behavior; generate a simulation sub-model of the target abnormal behavior based on the first-level association package; and set b sequentially according to the user behavior category B. i The process involves: identifying the user category to be compensated; generating a secondary association package based on the target abnormal behavior and the user category to be compensated; generating compensation sub-strategies for the target abnormal behavior for the user category to be compensated based on the secondary association package; generating compensation sub-strategies for each user category in sequence; and generating a diagnostic sub-model for the target abnormal behavior based on all compensation sub-strategies and the simulation sub-model.

7. The method for monitoring abnormal use of heating equipment based on multi-source data as described in claim 6, characterized in that, The generation of abnormal behavior diagnostic results includes: obtaining all risk user points at the current feedback time point; establishing a risk user point sequence A1; A1=(a 11 a 12 …a 1i …a 1n1 ), where a 1i Let n1 be the i-th user risk point at the current feedback time point; n1 is the number of risky user points at the current feedback time point; set a according to the risky user point count sequence A1. 1i The target risk point is defined; w is set sequentially based on the abnormal behavior sequence W. i The target risk point and the behavior to be compared are used as the comparison behavior. The heating diagnosis model generates a first-level diagnosis model based on the target risk point and the behavior to be compared. A matching evaluation value c is generated based on the first-level diagnosis model. A matching evaluation value threshold C1 is preset. If c > C1, the target risk point generates a first-level warning instruction for the behavior to be compared. The model then determines whether the target risk point generates a first-level warning instruction for each abnormal behavior. The model generates a diagnosis sub-result for the target risk point based on all first-level warning instructions. The model then generates a diagnosis sub-result for each user risk point in turn. Finally, the model generates an abnormal behavior diagnosis result based on all diagnosis sub-results.

8. The method for monitoring abnormal use of heating equipment based on multi-source data as described in claim 7, characterized in that, Generate a fit evaluation value c, including: c = U2 * [ η i *(s 1i -e i *s 2i ) 2 Where, U2 is the preset second conversion coefficient; θ1 is the number of thermal monitoring indicators; η i The weighting coefficient of the i-th thermal monitoring index is set according to the primary diagnostic model; s 1i Let s be the reference value of the i-th thermal monitoring indicator at the current feedback time point for the target risk point; 2i The comparison reference value for the i-th thermal monitoring index is set based on the simulation sub-model in the primary diagnostic model; e i It is the compensation coefficient of the i-th thermal monitoring index set according to the compensator strategy in the first-level diagnostic model.

9. A monitoring system for abnormal use of heating equipment based on multi-source data, employing the monitoring method for abnormal use of heating equipment based on multi-source data as described in any one of claims 1-8, characterized in that, include: The central control unit is used to generate multiple user points based on the heating area; The monitoring unit includes multiple monitoring sub-modules, which are located at various user points; The monitoring unit is used to collect heating data from each user point and generate heating monitoring packages for each user point; the central control unit includes: a first processing module, used to acquire heating monitoring packages for each user point according to a preset feedback time node; the first processing module is also used to generate heating anomaly values ​​for each user point according to a preset anomaly assessment model and all heating monitoring packages; a second processing module, used to select multiple risk user points according to all heating anomaly values, and generate abnormal behavior diagnosis results according to all risk user points and a preset heating diagnosis model; a third processing module, used to establish a user point sequence A, A=(a1,a2…a ... i …a n ), where a i Let be the i-th user point; n is the number of user points.

10. The heating equipment abnormal use monitoring system based on multi-source data as described in claim 9, characterized in that, The first processing module is further configured to: generate multiple user characteristic indicators based on historical monitoring data; set multiple user categories based on all user characteristic indicators; and establish a user category sequence B, B=(b1, b2…b ... i …b m ), where b i Let m be the number of user categories, and b be the number of user categories, according to the sequence of user categories B. i Define the target user category; construct an evaluation sub-model for the target user category based on historical monitoring data; set multiple monitoring sub-regions based on the heating area; construct the correlation sub-model for each monitoring sub-region in sequence; generate an anomaly evaluation model based on all correlation sub-models and all evaluation sub-models.

Images