Thermal heat supply comprehensive management system based on user behavior analysis
By classifying users in the heating area and dynamically adjusting subsets of heating points, combined with load control and anomaly assessment models, the problem of lagging user-end heat consumption behavior identification and load control in existing heating systems has been solved, achieving efficient operation and maintenance and stability of the heating system.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- 西安沣东华能热力有限公司
- Filing Date
- 2025-11-27
- Publication Date
- 2026-04-14
AI Technical Summary
Existing thermal heating systems are lagging and inefficient in identifying user-side heating behavior and controlling load, failing to effectively identify abnormal behavior and achieve precise load allocation, resulting in energy waste and system instability.
By screening and analyzing users in the heating area to generate multiple user categories, establishing multiple subsets of heating points, and dynamically adjusting heating control parameters according to a preset load control model, combined with an anomaly assessment model for real-time monitoring and diagnosis, the operation and maintenance efficiency and accurate load allocation are improved.
It enables efficient identification and early warning of abnormal heating behavior, improves the operation and maintenance efficiency and stability of the heating system, and ensures the safe operation of the heating system.
Smart Images
Figure CN121860261A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of heating system technology, and in particular to a comprehensive heating management system based on user behavior analysis. Background Technology
[0002] Currently, urban heating systems are gradually shifting from traditional extensive management to refined and intelligent control. However, existing management systems mostly focus on data monitoring and optimization on the supply side, such as heat sources and pipe networks, and have significant shortcomings in comprehensively understanding user heating behavior and accurately controlling load based on this understanding.
[0003] Specifically, traditional systems primarily rely on master meter readings and historical experience for load forecasting and regulation. This extensive load control model is inefficient and lagging because it cannot effectively perceive the real-time heating status of individual users. On the one hand, the system cannot identify abnormal user behaviors such as unauthorized modifications, abnormal window openings, and malicious water release. These behaviors disrupt hydraulic conditions, leading to localized supply-demand imbalances and energy waste, significantly reducing the effectiveness of load control strategies based on the master model. On the other hand, due to the lack of awareness of users' actual needs and abnormal states, the system struggles to achieve the precise load allocation and dynamic adjustment required for "on-demand heating," frequently resulting in overall overheating or localized underheating, thus hindering further improvements in system energy efficiency and stability. Summary of the Invention
[0004] The purpose of this application is to address the aforementioned technical problems by providing a comprehensive heating management system based on user behavior analysis, aiming to improve the operation and maintenance efficiency of the heating system and enhance the efficiency of identifying and issuing early warnings of abnormal heating behaviors.
[0005] In some embodiments of this application, multiple user categories are generated by screening and analyzing users in the heating area, thereby establishing multiple subsets of heating points. The heating control parameters of each subset of heating points in different load scenarios are dynamically adjusted according to a preset load control model, thereby improving the operation and maintenance efficiency and accurate load allocation of the heating system and ensuring the stability of the heating system.
[0006] In some embodiments of this application, by periodically collecting operational monitoring data from each heat source, the perception of real user needs and abnormal states is improved, and by constructing an anomaly assessment model, a dual diagnostic mechanism for the operational status of each heat source is realized, thereby improving the efficiency of identifying and warning of abnormal heating behavior and ensuring the safe operation of the system.
[0007] In some embodiments of this application, a comprehensive heating management system based on user behavior analysis is provided, including: The central control unit is used to set multiple heating points according to the heating area; The operation and maintenance unit includes multiple operation and maintenance substructures, which are located at various heat points; The operation and maintenance unit is used to collect operation monitoring data of each heat source point, and the operation and maintenance unit is also used to control the heating parameters of each heat source point; The operation and maintenance unit is also used to build a historical monitoring database; The simulation unit is used to establish load control models and anomaly assessment models.
[0008] In some embodiments of this application, the central control unit further includes: The first processing module is used to set the primary heating strategy based on the load control model. The user module is used to establish a sequence of heat points A, A=(a1, a2…a…). i …a n ), where a i Let be the i-th heat source; n is the number of heat sources. The user module is also used to set multiple behavioral characteristic indicators; All heat points are aggregated based on all behavioral characteristic indicators, and multiple heat point subsets are generated based on the aggregation results. The user module is also used to establish a subset sequence of heat points W, W=(w1,w2…w…). i …w n1 ), where w i Let n be the i-th heat point subset; n1 is the number of heat point subsets, and n1 <n; The second processing module is used to obtain the operation monitoring data of each heat point user according to the preset feedback time node; The second processing module is also used to determine whether to generate an early warning instruction based on all operational monitoring data and the anomaly assessment model.
[0009] In some embodiments of this application, the simulation unit includes: The first simulation module is used to set multiple load characteristic indicators and set multiple load scenarios based on all load characteristic indicators. Establish a load scenario sequence B, B=(b1, b2…b i …b m ), where b i Let m be the i-th load scenario; m is the number of load scenarios. b is set sequentially according to the load scenario sequence B. i For target load scenarios; The allocation sub-strategy for the target load scenario is set based on the historical monitoring database; Configure the allocation sub-strategies for each load scenario in sequence; The load control model is set according to all allocation sub-strategies.
[0010] In some embodiments of this application, the allocation sub-strategy for the target load scenario is set, including: Generate associated data packets for the target load scenario based on the historical monitoring database; Based on the sequence of heat point subsets W, w is set sequentially. i For the subset to be allocated; Generate the thermal allocation value k of the subset to be allocated in the target load scenario based on the associated data packets; k=[ μ i *s i ]; Where θ1 is the number of evaluation indicators assigned; μ i To allocate the influence factors of the evaluation indicators; s i It is a reference value for the i-th allocation evaluation index of the subset to be allocated in the target load scenario, generated based on the associated data packets; Generate the thermal distribution values of each subset of thermal points in the target load scenario in sequence; The allocation strategy for the target load scenario is generated based on all thermal allocation values.
[0011] In some embodiments of this application, the simulation unit further includes: The second simulation module is used to set multiple heating monitoring indicators; The second simulation module is also used to set wi as the subset to be evaluated according to the thermal point subset sequence W; An evaluation sub-model is set based on the historical monitoring database to evaluate the subset to be evaluated; The evaluation sub-models for each subset of thermal points are set sequentially; An anomaly assessment model is generated based on all assessment sub-models.
[0012] In some embodiments of this application, the first processing module is further configured to: Multiple heating adjustment cycles can be preset; Obtain the load characteristic package and expected total heating flow for the current heating regulation cycle; Establish a primary operating scenario for the current heating cycle based on load characteristic packages; Generate similarity values for the primary operating scenario and each load scenario; The primary allocation strategy for the current heating control cycle is set based on all similar values; The primary heating strategy for the current control cycle is set based on the primary allocation strategy and the expected total heating flow.
[0013] In some embodiments of this application, the second processing module is further configured to: Multiple feedback time points are set within the current heating regulation cycle; Based on the heat point sequence A, ai are sequentially set as target heat points; Obtain operational monitoring data of the target heat map point at the current feedback time point; Generate the operational deviation value c of the target thermal point; c=[ η i *(j i -j 1i ) 2 ]; Where θ2 represents the number of heating monitoring indicators; η i Let j be the influencing factor of the i-th heating monitoring index; i Let j be the real-time reference value of the i-th heating monitoring index at the current feedback time point in the target heat source; 1i It is the expected reference value of the i-th heating monitoring index in the target heat point at the current feedback time node, generated according to the primary heating strategy; The operational deviation values for each thermal point are generated sequentially. Whether to generate an early warning instruction is determined based on all operational deviation values.
[0014] In some embodiments of this application, determining whether to generate a warning instruction based on all operational deviation values includes: Establish a sequence C of operational deviation values at the current feedback time point; C = (c1, c2, ..., c) i …c n ), where c i This represents the operational deviation value of the i-th heat point at the current feedback time point; Preset operating deviation threshold C1; If c i >C1, Set the i-th heat point as a risk heat point at the current feedback time node; Obtain all risk heatmaps; The anomaly assessment model determines whether to generate a Level 1 early warning instruction for each risk heat point.
[0015] In some embodiments of this application, determining whether to generate a first-level early warning instruction for each risk heatmap includes: Select the target risk points sequentially from all risk heatmaps; The assessment sub-model corresponding to the target risk point is set as the first-level assessment model; Obtain operational monitoring data for the target risk points; Based on the primary assessment model and operational monitoring data, generate the abnormal risk value f for the target risk point; f=g*[ η i *(j i -j2i ) 2 ]; Where g is the risk compensation coefficient set based on the operational deviation value of the target risk point; η i Let j be the influencing factor of the i-th heating monitoring index; i Let j be the real-time reference value of the i-th heating monitoring index at the current feedback time point in the target heat source; 2i This is the standard reference value for the i-th heating monitoring indicator set in the first-level assessment model; Preset anomaly risk threshold F1; If f > F1, generate a first-level early warning instruction for the target risk point.
[0016] In some embodiments of this application, determining whether to generate a warning instruction based on all operational deviation values further includes: Generate the heating anomaly value d based on the operational deviation value sequence C; d=e*[ β i *c i ]; Where 'e' is the fluctuation compensation coefficient set based on all load characteristic indicators at the current feedback time point; β i is the influence factor of the i-th heat site; n is the number of heat sites; c i This represents the operational deviation value of the i-th heat point at the current feedback time node; Preset heating anomaly threshold D1; If d > D1, a level 2 early warning instruction is generated at the current feedback time point.
[0017] Compared with existing technologies, the advantages of the thermal heating integrated management system based on user behavior analysis proposed in this application are as follows: By screening and analyzing users in the heating area to generate multiple user categories, several subsets of heating points are established. Based on a pre-set load control model, the heating control parameters of each subset of heating points are dynamically adjusted under different load scenarios. This improves the operational efficiency and accurate load allocation of the heating system, ensuring its stability. By periodically collecting operational monitoring data from various heating points, we can improve our perception of real user needs and abnormal conditions. Furthermore, by constructing an anomaly assessment model, we can achieve a dual diagnostic mechanism for the operational status of each heating point, thereby improving the efficiency of identifying and issuing early warnings of abnormal heating behaviors and ensuring the safe operation of the system. Attached Figure Description
[0018] Figure 1 This is a schematic diagram of the structure of a thermal heating integrated management system based on user behavior analysis in a preferred embodiment of this application. Detailed Implementation
[0019] 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.
[0020] 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.
[0021] 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.
[0022] 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.
[0023] like Figure 1 As shown in the preferred embodiment of this application, a comprehensive heating management system based on user behavior analysis includes: The central control unit is used to set multiple heating points according to the heating area; The operation and maintenance unit includes multiple operation and maintenance substructures, which are located at various heat points. The operation and maintenance unit is used to collect operation monitoring data from each heat source point, and it is also used to control the heating parameters of each heat source point. The operations and maintenance unit is also used to build a historical monitoring database; The simulation unit is used to establish load control models and anomaly assessment models.
[0024] Specifically, multiple heating users are selected in the heating area based on the operation and maintenance data of the heating system, and multiple heating points are set according to all heating users, where each heating point represents a heating user.
[0025] Specifically, a single operation and maintenance substructure includes a monitoring submodule and a control submodule. The monitoring submodule preferably has multiple data acquisition devices that can collect real-time operation monitoring data of the current heat point, and the control submodule preferably has an intelligent valve device that can control the heating flow of the heat point in real time.
[0026] Specifically, the historical monitoring database includes historical operational monitoring data for each heat source.
[0027] Specifically, the central control unit also includes: The first processing module is used to set the primary heating strategy based on the load control model. The user module is used to establish a sequence of heat points A, A=(a1, a2…a…). i …a n ), where a i Let be the i-th heat source; n is the number of heat sources. The user module is also used to set multiple behavioral characteristic indicators; All heat points are aggregated based on all behavioral characteristic indicators, and multiple heat point subsets are generated based on the aggregation results. The user module is also used to establish a subset sequence of heat points W, W=(w1,w2…w…). i …w n1 ), where w i Let n be the i-th heat point subset; n1 is the number of heat point subsets, and n1 <n; The second processing module is used to obtain the operation monitoring data of each heat point user according to the preset feedback time node; The second processing module is also used to determine whether to generate an early warning instruction based on all operational monitoring data and the anomaly assessment model.
[0028] Specifically, behavioral characteristic indicators include, but are not limited to, multiple parameters that affect the real-time heat load of users, such as heating demand time, heating habits (window opening time and frequency), habitual temperature, and periodic load (i.e., the average heat demand of a heat source per unit time). By quantifying each behavioral characteristic indicator, multiple value ranges for each behavioral characteristic indicator are generated. Multiple user categories are constructed based on random combinations of all value ranges. All heat sources are aggregated based on all user categories to generate multiple subsets of heat sources.
[0029] Specifically, the users corresponding to each heat point within a single heat point subset all belong to the same user category.
[0030] Understandably, in the above implementation, multiple user categories are generated by screening and analyzing users in the heating area, thereby establishing multiple subsets of heating points. The heating control parameters of each subset of heating points are dynamically adjusted in different load scenarios according to the preset load control model, thereby improving the operation and maintenance efficiency and accurate load allocation of the heating system and ensuring the stability of the heating system.
[0031] In a preferred embodiment of this application, the simulation unit includes: The first simulation module is used to set multiple load characteristic indicators and set multiple load scenarios based on all load characteristic indicators. Establish a load scenario sequence B, B=(b1, b2…b i …b m ), where b i Let m be the i-th load scenario; m is the number of load scenarios. b is set sequentially according to the load scenario sequence B. i For target load scenarios; The allocation sub-strategy for the target load scenario is set based on the historical monitoring database; Configure the allocation sub-strategies for each load scenario in sequence; The load control model is set according to all allocation sub-strategies.
[0032] Specifically, by filtering and analyzing all data in the historical database, multiple load characteristic indicators are generated. These load characteristic indicators include, but are not limited to, heating operation time, heating system operation fluctuations, expected total load, the difference between the user's expected heating demand and the expected maximum heating capacity of the heating system, and other parameters related to heating flow control. By quantifying each load characteristic indicator, the reference values of each load characteristic indicator are made to be within the same range. Multiple value intervals for each load characteristic indicator are generated sequentially, and multiple load scenarios are constructed based on random combinations of all value intervals.
[0033] Specifically, the allocation sub-strategy for the target load scenario includes: Generate associated data packets for the target load scenario based on the historical monitoring database; Based on the sequence of heat point subsets W, w is set sequentially. i For the subset to be allocated; Generate the thermal allocation value k of the subset to be allocated in the target load scenario based on the associated data packets; k=[ μ i *s i ]; Where θ1 is the number of evaluation indicators assigned; μ i To allocate the influence factors of the evaluation indicators; s iIt is a reference value for the i-th allocation evaluation index of the subset to be allocated in the target load scenario, generated based on the associated data packets; Generate the thermal distribution values of each subset of thermal points in the target load scenario in sequence; The allocation strategy for the target load scenario is generated based on all thermal allocation values.
[0034] Specifically, the allocation evaluation indicators include, but are not limited to, the degree of overlap between the heat point subset and the target load scenario (i.e., the degree of overlap between the user's heating demand time and the heating operation time of the target load scenario; the higher the degree of overlap, the larger the corresponding reference value), the adjustment capability of the subset to be allocated in the target load scenario (i.e., the sensitivity to real-time heating temperature; the greater the sensitivity, the larger the corresponding reference value), and the periodic load of the subset to be allocated (the larger the periodic load, the larger the corresponding reference value). By quantifying each allocation evaluation indicator, the reference values of each allocation evaluation indicator are made to be within the same range.
[0035] Specifically, the influence factors of each allocation evaluation index are set according to their degree of influence on the flow allocation of the heating system. The greater the degree of influence, the larger the value of the influence factor.
[0036] Specifically, the larger the heat allocation value, the greater the flow ratio of the corresponding heat point subset in the target load scenario, and the higher the allocation order of the heating system flow (i.e., when the heating system reduces the flow, it prioritizes reducing the heating flow of the heat point subset with the lower heat allocation value).
[0037] Specifically, the flow ratio of each heat point subset in the target load scenario is the ratio between the heat allocation value and the sum of all heat allocation values. A corresponding allocation sub-strategy is generated based on the flow ratio of each heat point subset.
[0038] It is understood that in the above embodiments, the heating control parameters of each heat point subset in different load scenarios are dynamically adjusted according to the preset load control model, thereby improving the operation and maintenance efficiency and accurate load allocation of the heating system and ensuring the stability of the heating system.
[0039] In a preferred embodiment of this application, the simulation unit further includes: The second simulation module is used to set multiple heating monitoring indicators; The second simulation module is also used to set wi as the subset to be evaluated according to the thermal point subset sequence W; An evaluation sub-model is set based on the historical monitoring database to evaluate the subset to be evaluated; The evaluation sub-models for each subset of thermal points are set sequentially; An anomaly assessment model is generated based on all assessment sub-models.
[0040] Specifically, heating monitoring indicators include, but are not limited to, multiple operating parameters related to the heating system, such as instantaneous flow rate, cumulative flow rate, supply water temperature, return water temperature, valve opening, supply and return water pressure, outdoor temperature, and indoor temperature. Quantification ensures that the reference values for each thermal monitoring indicator are within the same range.
[0041] Specifically, by analyzing the data in the historical monitoring database, standard reference values for each heating monitoring indicator in the subset to be evaluated are generated (i.e., the reference values corresponding to each heating monitoring indicator in the subset to be evaluated when it is in a normal state), and the corresponding evaluation sub-model is constructed based on all the standard reference values.
[0042] In a preferred embodiment of this application, the first processing module is further configured to: Multiple heating adjustment cycles can be preset; Obtain the load characteristic package and expected total heating flow for the current heating regulation cycle; Establish a primary operating scenario for the current heating cycle based on load characteristic packages; Generate similarity values for the primary operating scenario and each load scenario; The primary allocation strategy for the current heating control cycle is set based on all similar values; The primary heating strategy for the current control cycle is set based on the primary allocation strategy and the expected total heating flow.
[0043] Specifically, the load characteristic package includes real-time parameters of various load characteristic indicators acquired within the current heating regulation cycle.
[0044] Specifically, the expected total heating flow is the heating flow that the heating system is expected to provide during the current heating regulation cycle.
[0045] Specifically, similarity values are generated by analyzing the differences between parameters corresponding to various load characteristic indicators in the primary operation scenario and the load scenario. The greater the difference, the smaller the corresponding similarity value. The mapping relationship between the two can be set based on historical parameters.
[0046] Specifically, the allocation sub-strategy corresponding to the load scenario with the maximum value among all similar values is selected as the first-level allocation strategy. Based on the first-level allocation strategy and the expected total heating flow, the expected supply flow corresponding to each heat point subset is set, thereby generating the corresponding first-level heating strategy.
[0047] Specifically, the second processing module is also used for: Multiple feedback time points are set within the current heating regulation cycle; Based on the heat point sequence A, ai are sequentially set as target heat points; Obtain operational monitoring data of the target heat map point at the current feedback time point; Generate the operational deviation value c of the target thermal point; c=[ η i *(j i -j 1i ) 2 ]; Where θ2 represents the number of heating monitoring indicators; η i Let j be the influencing factor of the i-th heating monitoring index; i Let j be the real-time reference value of the i-th heating monitoring index at the current feedback time point in the target heat source; 1i It is the expected reference value of the i-th heating monitoring index in the target heat point at the current feedback time node, generated according to the primary heating strategy; The operational deviation values for each thermal point are generated sequentially. Whether to generate an early warning instruction is determined based on all operational deviation values.
[0048] Specifically, the influence factors of each heating monitoring indicator 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.
[0049] Specifically, determining whether to generate a warning instruction based on all operational deviations also includes: Generate the heating anomaly value d based on the operational deviation value sequence C; d=e*[ β i *c i ]; Where 'e' is the fluctuation compensation coefficient set based on all load characteristic indicators at the current feedback time point; β i is the influence factor of the i-th heat site; n is the number of heat sites; c i This represents the operational deviation value of the i-th heat point at the current feedback time node; Preset heating anomaly threshold D1; If d > D1, a level 2 early warning instruction is generated at the current feedback time point.
[0050] Specifically, the heating anomaly threshold can be set based on historical parameters. If the heating anomaly value at the current feedback time point is greater than the preset heating anomaly threshold, it indicates that there is a serious heat distribution deviation between the current heating system and the user end. The current primary heating strategy needs to be corrected in a timely manner according to the secondary early warning instruction to improve the operation and maintenance efficiency and accurate load distribution of the heating system and ensure the stability of the heating system.
[0051] Specifically, the influence factor of each heat point can be set according to the heat distribution value of its corresponding heat point subset in the load scenario corresponding to the current feedback time node. The larger the heat distribution value, the larger the value of the corresponding influence factor. The mapping relationship between the two can be set according to historical parameters.
[0052] In a preferred embodiment of this application, determining whether to generate a warning instruction based on all operational deviation values includes: Establish a sequence C of operational deviation values at the current feedback time point; C = (c1, c2, ..., c) i …c n ), where c i This represents the operational deviation value of the i-th heat point at the current feedback time point; Preset operating deviation threshold C1; If c i >C1, Set the i-th heat point as a risk heat point at the current feedback time node; Obtain all risk heatmaps; The anomaly assessment model determines whether to generate a Level 1 early warning instruction for each risk heat point.
[0053] Specifically, the operating deviation threshold can be set based on historical parameters. If the operating deviation of the current heat station is greater than the preset operating deviation threshold, it indicates that the current heat station has an abnormal heating state and needs further diagnosis to determine whether the heating abnormality is caused by the operation of the heating system or by the user's violation of regulations.
[0054] Specifically, by screening risky heat points, users with abnormal heating conditions can be quickly located, and through further diagnostic analysis, timely warnings can be issued for user violations.
[0055] Specifically, determining whether to generate a Level 1 warning instruction for each risk heatmap includes: Select the target risk points sequentially from all risk heatmaps; The assessment sub-model corresponding to the target risk point is set as the first-level assessment model; Obtain operational monitoring data for the target risk points; Based on the primary assessment model and operational monitoring data, generate the abnormal risk value f for the target risk point; f=g*[ η i *(j i -j 2i ) 2 ]; Where g is the risk compensation coefficient set based on the operational deviation value of the target risk point; η iLet j be the influencing factor of the i-th heating monitoring index; i Let j be the real-time reference value of the i-th heating monitoring index at the current feedback time point in the target heat source; 2i This is the standard reference value for the i-th heating monitoring indicator set in the first-level assessment model; Preset anomaly risk threshold F1; If f > F1, generate a first-level early warning instruction for the target risk point.
[0056] Specifically, the abnormal risk value threshold can be set based on historical parameters. When the real-time abnormal risk value is greater than the preset abnormal risk value threshold, it indicates that there is user violation at the current risk hotspot, and early warning and maintenance should be carried out according to the first-level warning instruction.
[0057] Specifically, the influence factors of each heating monitoring indicator 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.
[0058] Specifically, whether to generate an alert is determined based on all operational deviation values. It is understandable that in the above embodiments, an abnormal assessment model is constructed to realize a dual diagnostic mechanism for the operating status of each heat point, thereby improving the efficiency of identifying and warning of abnormal heating behavior and ensuring the safe operation of the system.
[0059] According to the first concept of this application, multiple user categories are generated by screening and analyzing users in the heating area, thereby establishing multiple subsets of heating points. The heating control parameters of each subset of heating points in different load scenarios are dynamically adjusted according to a preset load control model, thereby improving the operation and maintenance efficiency and accurate load allocation of the heating system and ensuring the stability of the heating system.
[0060] According to the second concept of this application, by periodically collecting operational monitoring data from various heating points, the perception of real user needs and abnormal states can be improved. Furthermore, by constructing an anomaly assessment model, a dual diagnostic mechanism for the operational status of each heating point can be achieved, thereby improving the efficiency of identifying and warning of abnormal heating behaviors and ensuring the safe operation of the system.
[0061] The above are merely preferred embodiments 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 comprehensive heating management system based on user behavior analysis, characterized in that, include: The central control unit is used to set multiple heating points according to the heating area; The operation and maintenance unit includes multiple operation and maintenance substructures, which are located at various heat points; The operation and maintenance unit is used to collect operation monitoring data of each heat source point, and the operation and maintenance unit is also used to control the heating parameters of each heat source point; The operation and maintenance unit is also used to build a historical monitoring database; The simulation unit is used to establish load control models and anomaly assessment models.
2. The integrated heating management system based on user behavior analysis as described in claim 1, characterized in that, The central control unit also includes: The first processing module is used to set the primary heating strategy based on the load control model. The user module is used to establish a sequence of heat points A, A=(a1, a2…a…). i …a n ), where a i Let be the i-th heat source; n is the number of heat sources. The user module is also used to set multiple behavioral characteristic indicators; All heat points are aggregated based on all behavioral characteristic indicators, and multiple heat point subsets are generated based on the aggregation results. The user module is also used to establish a subset sequence of heat points W, W=(w1,w2…w…). i …w n1 ), where w i Let n be the i-th heat point subset; n1 is the number of heat point subsets, and n1 <n; The second processing module is used to obtain the operation monitoring data of each heat point user according to the preset feedback time node; The second processing module is also used to determine whether to generate an early warning instruction based on all operational monitoring data and the anomaly assessment model.
3. The integrated heating management system based on user behavior analysis as described in claim 2, characterized in that, The simulation unit includes: The first simulation module is used to set multiple load characteristic indicators and set multiple load scenarios based on all load characteristic indicators. Establish a load scenario sequence B, B=(b1, b2…b i …b m ), where b i Let m be the i-th load scenario; m is the number of load scenarios. b is set sequentially according to the load scenario sequence B. i For target load scenarios; The allocation sub-strategy for the target load scenario is set based on the historical monitoring database; Configure the allocation sub-strategies for each load scenario in sequence; The load control model is set according to all allocation sub-strategies.
4. The integrated heating management system based on user behavior analysis as described in claim 3, characterized in that, Define the allocation sub-strategy for the target load scenario, including: Generate associated data packets for the target load scenario based on the historical monitoring database; Based on the sequence of heat point subsets W, w is set sequentially. i For the subset to be allocated; Generate the thermal allocation value k of the subset to be allocated in the target load scenario based on the associated data packets; k=[ m i *s i ]; Where θ1 is the number of evaluation indicators assigned; μ i To allocate the influence factors of the evaluation indicators; s i It is a reference value for the i-th allocation evaluation index of the subset to be allocated in the target load scenario, generated based on the associated data packets; Generate the thermal distribution values of each subset of thermal points in the target load scenario in sequence; The allocation strategy for the target load scenario is generated based on all thermal allocation values.
5. The integrated heating management system based on user behavior analysis as described in claim 4, characterized in that, The simulation unit further includes: The second simulation module is used to set multiple heating monitoring indicators; The second simulation module is also used to set wi as the subset to be evaluated according to the thermal point subset sequence W; An evaluation sub-model is set based on the historical monitoring database to evaluate the subset to be evaluated; The evaluation sub-models for each subset of thermal points are set sequentially; An anomaly assessment model is generated based on all assessment sub-models.
6. The integrated heating management system based on user behavior analysis as described in claim 5, characterized in that, The first processing module is also used for: Multiple heating adjustment cycles can be preset; Obtain the load characteristic package and expected total heating flow for the current heating regulation cycle; Establish a primary operating scenario for the current heating cycle based on load characteristic packages; Generate similarity values for the primary operating scenario and each load scenario; The primary allocation strategy for the current heating control cycle is set based on all similar values; The primary heating strategy for the current control cycle is set based on the primary allocation strategy and the expected total heating flow.
7. The integrated heating management system based on user behavior analysis as described in claim 6, characterized in that, The second processing module is also used for: Multiple feedback time points are set within the current heating regulation cycle; Based on the heat point sequence A, ai are sequentially set as target heat points; Obtain operational monitoring data of the target heat map point at the current feedback time point; Generate the operational deviation value c of the target thermal point; c=[ η i *(j i -j 1i ) 2 ]; Where θ2 represents the number of heating monitoring indicators; η i Let j be the influencing factor of the i-th heating monitoring index; i Let j be the real-time reference value of the i-th heating monitoring index at the current feedback time point in the target heat source; 1i It is the expected reference value of the i-th heating monitoring index in the target heat point at the current feedback time node, generated according to the primary heating strategy; The operational deviation values for each thermal point are generated sequentially. Whether to generate an early warning instruction is determined based on all operational deviation values.
8. The integrated heating management system based on user behavior analysis as described in claim 7, characterized in that, Whether to generate a warning instruction is determined based on all operational deviation values, including: Establish a sequence C of operational deviation values at the current feedback time point; C = (c1, c2, ..., c) i …c n ), where c i This represents the operational deviation value of the i-th heat point at the current feedback time point; Preset operating deviation threshold C1; If c i >C1, Set the i-th heat point as a risk heat point at the current feedback time node; Obtain all risk heatmaps; The anomaly assessment model determines whether to generate a Level 1 early warning instruction for each risk heat point.
9. The integrated heating management system based on user behavior analysis as described in claim 8, characterized in that, Determine whether to generate a Level 1 early warning instruction for each risk heatmap point, including: Select the target risk points sequentially from all risk heatmaps; The assessment sub-model corresponding to the target risk point is set as the first-level assessment model; Obtain operational monitoring data for the target risk points; Based on the primary assessment model and operational monitoring data, generate the abnormal risk value f for the target risk point; f=g*[ or i *(j i -j 2i ) 2 ]; Where g is the risk compensation coefficient set based on the operational deviation value of the target risk point; η i Let j be the influencing factor of the i-th heating monitoring index; i Let j be the real-time reference value of the i-th heating monitoring index at the current feedback time point in the target heat source; 2i This is the standard reference value for the i-th heating monitoring indicator set in the first-level assessment model; Preset anomaly risk threshold F1; If f > F1, generate a first-level early warning instruction for the target risk point.
10. The integrated heating management system based on user behavior analysis as described in claim 9, characterized in that, Determining whether to generate a warning instruction based on all operational deviations also includes: Generate the heating anomaly value d based on the operational deviation value sequence C; d=e*[ b i *c i ]; Where 'e' is the fluctuation compensation coefficient set based on all load characteristic indicators at the current feedback time point; β i is the influence factor of the i-th heat site; n is the number of heat sites; c i This represents the operational deviation value of the i-th heat point at the current feedback time node; Preset heating anomaly threshold D1; If d > D1, a level 2 early warning instruction is generated at the current feedback time point.