Remote heat larceny early warning system

Abstract

The invention provides a remote heat larceny early warning system, and relates to the technical field of remote early warning, and the system comprises a real-time monitoring module which carries out the dynamic monitoring through a distributed monitoring device; the exception analysis module obtains an anti-disassembly exception index; the abnormity judgment module is used for sending out an anti-disassembly early warning if the anti-disassembly abnormity index reaches a threshold value; the information transmission module activates the distributed standby power supply and transmits the heat larceny monitoring information to the data center; the heat larceny analysis module performs heat larceny analysis on the heat larceny monitoring information; the heat larceny early warning module is used for giving out heat larceny early warning if the heat larceny abnormal index reaches a threshold value; and the emergency intervention module is used for carrying out anti-disassembly heat-stealing emergency intervention on the heat supply pipeline. According to the invention, the technical problem that the accuracy of heat larceny early warning is affected due to insufficient detection of heat larceny behaviors caused by limited heat larceny monitoring area and incomplete anti-tamper monitoring in the prior art can be solved, and the accuracy and efficiency of heat larceny early warning are improved by integrating anti-tamper early warning and heat larceny early warning.

Description

A remote heat theft early warning system Technical Field

[0001] This application relates to the field of remote early warning technology, and in particular to a remote heat theft early warning system. Background Technology

[0002] Currently, urban heating companies primarily rely on on-site inspections by personnel to monitor and inspect unpaid heating users. Consequently, a number of users exploit these loopholes, using and stealing heat without authorization, causing losses to the heating companies. On-site inspections are labor-intensive, lack timeliness, and are difficult to verify, even for obtaining evidence. To address the limitations of manual inspections, numerous heat theft monitoring devices have been introduced. These devices automatically analyze data from the heating system, identify abnormal behavior, and issue real-time warnings. However, these devices typically rely on single or a few monitoring points, which may not cover all critical parts of the pipeline, creating blind spots. If heat theft occurs in these blind spots, it may go undetected and unresponsive. Furthermore, anti-tampering monitoring is also limited. Heat thieves may employ covert methods, such as disguising or removing monitoring equipment, making it difficult to detect abnormal changes or tampering, thus affecting the accuracy of heat theft warnings.

[0003] In summary, existing technologies suffer from technical problems such as insufficient detection of heat theft behavior due to limited monitoring areas and incomplete anti-tampering monitoring, which further affects the accuracy of heat theft warnings. Summary of the Invention

[0004] The purpose of this application is to provide a remote heat theft early warning system to solve the technical problem in the prior art that the limited heat theft monitoring area and incomplete anti-tamper monitoring lead to insufficient detection of heat theft behavior, which further affects the accuracy of heat theft early warning.

[0005] In view of the above problems, this application provides a remote heat theft early warning system, wherein the remote heat theft early warning system includes: a real-time monitoring module, used to dynamically monitor and obtain real-time monitoring information through distributed monitoring devices deployed on the heating pipeline; an anomaly analysis module, used to read predetermined anti-tampering features and perform traversal analysis on the real-time anti-tampering monitoring information in the real-time monitoring information to obtain a real-time anti-tampering anomaly index; an anomaly judgment module, used to issue a first remote anti-tampering early warning if the real-time anti-tampering anomaly index reaches a predetermined anti-tampering threshold; an information transmission module, used to activate a distributed backup power supply based on the first remote anti-tampering early warning and transmit predetermined heat theft monitoring information for a predetermined period to a remote data center in conjunction with a predetermined low-power communication protocol; a heat theft analysis module, used by the remote data center to perform heat theft analysis on the predetermined heat theft monitoring information to obtain a predetermined heat theft anomaly index; a heat theft early warning module, used to issue a first remote heat theft early warning if the predetermined heat theft anomaly index reaches a predetermined heat theft threshold; and an emergency intervention module, used to perform anti-tampering and heat theft emergency intervention on the heating pipeline based on the first remote anti-tampering early warning and the first remote heat theft early warning.

[0006] Optionally, the anti-tamper monitoring assembly unit is used to assemble a distributed anti-tamper monitoring group; the heat theft monitoring assembly unit is used to assemble a distributed heat theft monitoring group; and the monitoring construction unit is used for the distributed anti-tamper monitoring group and the distributed heat theft monitoring group to jointly form the distributed monitoring device; wherein, the distributed anti-tamper monitoring group includes an acceleration sensor, a vibration sensor, and a tilt sensor, and the distributed heat theft monitoring group includes a temperature sensor, a pressure sensor, and a flow sensor.

[0007] Optionally, the feature traversal unit is used to traverse the real-time anti-tamper monitoring information based on the predetermined anti-tamper features to obtain real-time anti-tamper feature parameters; the weighted calculation unit is used to obtain the predetermined weight allocation of the predetermined anti-tamper features and perform weighted calculation in combination with the real-time anti-tamper feature parameters to obtain the real-time anti-tamper anomaly index; wherein, the predetermined weight allocation refers to the standardized result of the predictive ability of each anti-tamper feature in the predetermined anti-tamper features to the real-time anti-tamper anomaly index.

[0008] Optionally, a quantitative analysis subunit is used to introduce a prediction capability quantization function and perform a quantitative analysis of the prediction capability of the first anti-tamper feature on the real-time anti-tamper anomaly index based on the prediction capability quantization function to obtain the first prediction capability; wherein, the first anti-tamper feature refers to any one of the predetermined anti-tamper features, and the predetermined anti-tamper features include acceleration, vibration amplitude and tilt.

[0009] The expression for the predictive ability quantization function is as follows: ;in, This refers to the first anti-tamper feature. The first predictive ability, This refers to the real-time anti-tampering anomaly index. entropy, This refers to the real-time anti-tampering anomaly index. Take the first The probability of each value This refers to the real-time anti-tampering anomaly index. The total number of all possible values. This refers to the first anti-tamper feature. conditional entropy, This refers to the first anti-tamper feature. Value The probability, It refers to The real-time anti-tampering anomaly index under the conditions The entropy; the weight allocation determination subunit is used to obtain the predetermined weight allocation based on the correspondence between the first anti-tamper feature and the first prediction capability.

[0010] Optionally, under the distributed backup power supply, the predetermined low-power communication protocol is combined with the distributed heat theft monitoring group to continuously monitor the heating pipeline during the predetermined time period to obtain the predetermined heat theft monitoring information.

[0011] Optionally, the system includes: a first node extraction unit for extracting a first heat theft monitoring group located at a first node of the heating pipeline within the distributed heat theft monitoring group; a first information matching unit for matching the time sequence of the first monitoring parameter of the first heat theft monitoring group within the predetermined heat theft monitoring information; a first data analysis unit for analyzing the time sequence of the first monitoring parameter through a first data analysis layer of the remote data center to obtain the rate of change of the monitoring parameter; a second node extraction unit for extracting a second heat theft monitoring group located at a second node of the heating pipeline within the distributed heat theft monitoring group, wherein the second node is adjacent to the first node; a second information matching unit for matching the time sequence of the second monitoring parameter of the second heat theft monitoring group within the predetermined heat theft monitoring information; a second collaborative analysis unit for performing collaborative analysis of the time sequence of the first monitoring parameter and the time sequence of the second monitoring parameter through a second data analysis layer of the remote data center to obtain the uniformity of the monitoring parameter and the difference along the monitoring parameter path, respectively; and an anomaly index determination unit for analyzing the rate of change of the monitoring parameter, the uniformity of the monitoring parameter, and the difference along the monitoring parameter path to obtain the predetermined heat theft anomaly index.

[0012] Optionally, the vertical strategy extraction subunit is used to extract the vertical analysis strategy embedded in the first data analysis layer; the vertical analysis subunit is used to analyze the first temperature time series, the first pressure time series, and the first flow time series in the first monitoring parameter time series one by one according to the vertical analysis strategy, and obtain the first temperature change rate, the first pressure change rate, and the first flow change rate, respectively; the change rate composition subunit is used to compose the monitoring parameter change rate from the first temperature change rate, the first pressure change rate, and the first flow change rate.

[0013] Optionally, the time period acquisition subunit is used to acquire any time within the predetermined time period; the first matching subunit is used to sequentially match the first temperature, first pressure, and first flow rate at any time within the first temperature time series, the first pressure time series, and the first flow rate time series; the time series extraction subunit is used to extract the second temperature time series, the second pressure time series, and the second flow rate time series from the second monitoring parameter time series; the second matching subunit is used to sequentially match the second temperature, the second pressure, and the second flow rate at any time within the second temperature time series, the second pressure time series, and the second flow rate time series; the lateral strategy extraction subunit is used to extract the lateral analysis strategy embedded in the second data analysis layer; and the lateral analysis subunit is used to analyze the first temperature, the first pressure, the first flow rate, the second temperature, the second pressure, and the second flow rate according to the lateral analysis strategy to obtain the uniformity of the monitoring parameters and the difference along the monitoring parameters.

[0014] Optionally, a temperature comparison channel is used to compare the first temperature and the second temperature according to the lateral analysis strategy to obtain temperature uniformity and temperature friction difference, respectively; a pressure comparison channel is used to compare the first pressure and the second pressure according to the lateral analysis strategy to obtain pressure uniformity and pressure friction difference, respectively; a flow rate comparison channel is used to compare the first flow rate and the second flow rate according to the lateral analysis strategy to obtain flow rate uniformity and flow rate friction difference, respectively; and a friction difference composition channel is used to compose the monitoring parameter uniformity from the temperature uniformity, the pressure uniformity, and the flow rate uniformity, and to compose the monitoring parameter friction difference from the temperature friction difference, the pressure friction difference, and the flow rate friction difference.

[0015] Optionally, the second analysis unit is used to perform heat theft analysis on the real-time heat theft monitoring information in the real-time monitoring information through the remote data center to obtain the real-time heat theft anomaly index if the real-time anti-tampering anomaly index does not reach the predetermined anti-tampering threshold; the second early warning unit is used to issue a second remote heat theft early warning if the real-time heat theft anomaly index reaches the predetermined heat theft threshold; and the second intervention unit is used to perform heat theft emergency intervention on the heating pipeline according to the second remote heat theft early warning.

[0016] The technical solution provided in this application has at least the following technical effects or advantages: A real-time monitoring module is used to dynamically monitor the heating pipeline using distributed monitoring devices deployed on the pipeline to obtain real-time monitoring information; an anomaly analysis module is used to read predetermined anti-tampering features and perform traversal analysis on the real-time anti-tampering monitoring information in the real-time monitoring information to obtain a real-time anti-tampering anomaly index; an anomaly judgment module is used to issue a first remote anti-tampering warning if the real-time anti-tampering anomaly index reaches a predetermined anti-tampering threshold; an information transmission module is used to activate a distributed backup power supply based on the first remote anti-tampering warning and transmit predetermined heat theft monitoring information for a predetermined period to a remote data center in conjunction with a predetermined low-power communication protocol; a heat theft analysis module is used by the remote data center to perform heat theft analysis on the predetermined heat theft monitoring information to obtain a predetermined heat theft anomaly index; a heat theft warning module is used to issue a first remote heat theft warning if the predetermined heat theft anomaly index reaches a predetermined heat theft threshold; and an emergency intervention module is used to perform anti-tampering and heat theft emergency intervention on the heating pipeline based on the first remote anti-tampering warning and the first remote heat theft warning. In other words, by deploying distributed monitoring devices on the heating pipeline for dynamic monitoring, and combining this with predetermined anti-tampering features to traverse and analyze real-time monitoring data, anti-tampering warnings are issued. Based on the anti-tampering warning, backup power is activated to transmit heat theft monitoring information to a remote data center for heat theft analysis, thereby issuing heat theft warnings. Based on the anti-tampering warning and heat theft warning, emergency intervention for anti-tampering and heat theft is carried out on the heating pipeline, realizing comprehensive real-time monitoring of the heating pipeline and improving the accuracy and efficiency of remote heat theft warnings.

[0017] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0019] Figure 1 is a structural schematic diagram of a remote heat theft early warning system of this application; Figure 2 is a structural schematic diagram of a heat theft analysis module in a remote heat theft early warning system of this application.

[0020] Explanation of reference numerals in the attached diagram: Real-time monitoring module 11, Anomaly analysis module 12, Anomaly judgment module 13, Information transmission module 14, Heat theft analysis module 15, Heat theft early warning module 16, Emergency intervention module 17, First node extraction unit 51, First information matching unit 52, First data analysis unit 53, Second node extraction unit 54, Second information matching unit 55, Second collaborative analysis unit 56, Anomaly index determination unit 57. Detailed Implementation

[0021] This application provides a remote heat theft early warning system, which solves the technical problem in existing technologies where limited heat theft monitoring areas and incomplete anti-tampering monitoring lead to insufficient detection of heat theft behavior, further affecting the accuracy of heat theft early warning. The system utilizes distributed monitoring devices deployed on the heating pipeline for dynamic monitoring. Real-time monitoring data is analyzed in conjunction with predetermined anti-tampering features to generate anti-tampering early warnings. Based on these warnings, a backup power supply is activated to transmit heat theft monitoring information to a remote data center for further analysis, thus generating a heat theft early warning. Emergency intervention for heat theft and tampering prevention is implemented on the heating pipeline based on both the anti-tampering and heat theft warnings. This achieves comprehensive real-time monitoring of the heating pipeline, improving the accuracy and efficiency of remote heat theft early warning.

[0022] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0023] As an example, please refer to Figure 1. This application provides a remote heat theft early warning system, wherein the remote heat theft early warning system includes: a real-time monitoring module 11, used to dynamically monitor through a distributed monitoring device deployed on the heating pipeline to obtain real-time monitoring information.

[0024] Furthermore, the real-time monitoring module 11 in the remote heat theft early warning system is also used for: an anti-tamper monitoring assembly unit for assembling a distributed anti-tamper monitoring group; a heat theft monitoring assembly unit for assembling a distributed heat theft monitoring group; and a monitoring construction unit for the distributed anti-tamper monitoring group and the distributed heat theft monitoring group to jointly form the distributed monitoring device; wherein the distributed anti-tamper monitoring group includes an acceleration sensor, a vibration sensor, and a tilt sensor, and the distributed heat theft monitoring group includes a temperature sensor, a pressure sensor, and a flow sensor.

[0025] Specifically, two separate monitoring groups were established to monitor for tampering and heat theft, respectively, together forming the entire distributed monitoring system. The distributed tampering monitoring group consists of multiple sensors to detect whether the heating equipment has been illegally dismantled, including acceleration sensors, vibration sensors, and tilt sensors. Acceleration sensors detect changes in the acceleration of the pipes when subjected to external forces, promptly identifying whether dismantling tools are applying force. When pipes are illegally manipulated, vibrations are generated; vibration sensors can capture these vibration fluctuations in real time, promptly identifying abnormal vibrations. If the pipes shift or tilt, it may be due to partial dismantling or relocation; by installing tilt sensors, changes in the pipe's tilt angle are sensed in real time, thus determining whether the pipes have been illegally dismantled.

[0026] A distributed heat theft monitoring system consists of multiple sensors to monitor heat theft activities in a heating system, including temperature sensors, pressure sensors, and flow sensors. Temperature sensors measure pipe temperature and can detect abnormal temperature changes. Pressure sensors measure fluid pressure within the pipes and can detect abnormal pressure changes. Flow sensors measure the rate at which fluid flows through the pipes and can detect abnormal flow rate changes. For example, if a temperature sensor detects an abnormal drop in temperature at a point in the pipe, it indicates that heat is being illegally extracted at that point. If heat thieves are extracting heat in certain areas, they may be altering the pipe pressure.

[0027] By combining the anti-tampering monitoring group and the heat theft monitoring group, a unified distributed monitoring device is formed. Through the joint monitoring of multiple sensors, comprehensive monitoring is achieved, ensuring that there are no blind spots and simultaneously identifying tampering and heat theft issues in pipelines.

[0028] Different types of sensors are installed at key nodes of heating pipelines where heating fees have not been paid, forming a distributed monitoring system. Data is simultaneously acquired from different monitoring points, ensuring no blind spots and enabling 24 / 7 monitoring and inspection of the heating pipelines. Through continuous data acquisition, the distributed monitoring system dynamically monitors the pipelines, obtaining real-time monitoring information, including real-time anti-tampering monitoring information and scheduled heat theft monitoring information. Scheduled heat theft monitoring information is obtained by monitoring the heating pipelines during predetermined time periods.

[0029] The anomaly analysis module 12 is used to read the predetermined anti-tamper features and perform a traversal analysis of the real-time anti-tamper monitoring information in the real-time monitoring information to obtain the real-time anti-tamper anomaly index.

[0030] Furthermore, the anomaly analysis module 12 in the remote heat theft early warning system is also used for: a feature traversal unit, used for traversing the real-time anti-tamper monitoring information based on the predetermined anti-tamper features to obtain real-time anti-tamper feature parameters; and a weighted calculation unit, used for obtaining the predetermined weight allocation of the predetermined anti-tamper features and performing weighted calculation in combination with the real-time anti-tamper feature parameters to obtain the real-time anti-tamper anomaly index; wherein, the predetermined weight allocation refers to the standardized result of the predictive ability of each anti-tamper feature in the predetermined anti-tamper features to the real-time anti-tamper anomaly index.

[0031] Specifically, anti-tampering features are pre-defined, which are characteristics that may indicate that the pipeline has been illegally dismantled or damaged, such as changes in acceleration, vibration frequency and amplitude, and tilt angle. Based on the pre-defined anti-tampering features, the real-time anti-tampering monitoring information is traversed, and the real-time monitoring data (such as acceleration, vibration, tilt angle, etc.) are analyzed one by one to extract real-time anti-tampering feature indices, including acceleration parameters, vibration amplitude parameters, and tilt angle parameters.

[0032] The predictive power of each tamper feature in the predetermined tamper features for the real-time tamper anomaly index is quantified using a predictive power quantification function, thus obtaining the weight of each tamper feature. Based on the predetermined weight allocation of the predetermined tamper features, the real-time tamper feature parameters are weighted and calculated to obtain the real-time tamper anomaly index. In short, the weight of each tamper feature is quantified using the predictive power quantification function, each feature parameter in the real-time tamper feature parameters is multiplied by its corresponding weight, and all products are summed to obtain the real-time tamper anomaly index. For example, assuming the current acceleration is 2 m / s². 2 With a vibration amplitude of 5mm and a tilt of 0.5°, the calculated predetermined weights for acceleration, vibration amplitude, and tilt are 0.48, 0.32, and 0.20, respectively. The resulting real-time anti-dismantling anomaly index is 0.96 + 1.6 + 0.1 = 2.66, reflecting the degree of anomaly in the pipeline's anti-dismantling behavior at the current moment.

[0033] Furthermore, the anomaly analysis module 12 in the remote heat theft early warning system is also used for: a quantitative analysis subunit, used for introducing a prediction capability quantification function, and performing a quantitative analysis of the prediction capability of the first anti-tamper feature on the real-time anti-tamper anomaly index based on the prediction capability quantification function, to obtain the first prediction capability; wherein, the first anti-tamper feature refers to any one of the predetermined anti-tamper features, and the predetermined anti-tamper features include acceleration, vibration amplitude and tilt.

[0034] The expression for the predictive ability quantization function is as follows: ;in, This refers to the first anti-tamper feature. The first predictive ability, This refers to the real-time anti-tampering anomaly index. entropy, This refers to the real-time anti-tampering anomaly index. Take the first The probability of each value This refers to the real-time anti-tampering anomaly index. The total number of all possible values. This refers to the first anti-tamper feature. conditional entropy, This refers to the first anti-tamper feature. Value The probability, It refers to The real-time anti-tampering anomaly index under the conditions The entropy; the weight allocation determination subunit is used to obtain the predetermined weight allocation based on the correspondence between the first anti-tamper feature and the first prediction capability.

[0035] Specifically, a predictive ability quantification function is introduced to measure the predictive ability of each anti-tamper feature for the real-time anti-tamper anomaly index, thus obtaining the corresponding predictive ability. Based on the calculation results of the predictive ability quantification function, the weights of each anti-tamper feature are dynamically optimized. Based on the concept of entropy, which represents the uncertainty of information, information gain indicates the degree to which the uncertainty of the prediction result is reduced after introducing a certain feature. Specifically, information gain evaluates the predictive ability of a feature by calculating the difference between the conditional entropy H(Y|X) of the feature anomaly index and the overall entropy H(Y). Entropy is a fundamental concept in information theory, representing the disorder or uncertainty of information. The higher the entropy, the more uncertain the information, and the greater the difficulty of prediction.

[0036] The expression for the predictive power quantization function is: ;in, This refers to the first anti-tamper feature. The first predictive ability is determined by the IG value. The higher the IG value, the more helpful the feature is to the predictive ability, and the greater its corresponding weight. This refers to the real-time anti-tampering anomaly index. The entropy represents the uncertainty of Y when there is no feature information; This refers to the real-time anti-tampering anomaly index. Take the first The probability of each value This refers to the real-time anti-tampering anomaly index. The total number of possible values; This refers to the first anti-tamper feature. The conditional entropy of a target variable Y is the conditional entropy of Y given a feature X. It represents the uncertainty of Y after knowing information about feature X. For example, if the acceleration is known to be a certain value, the entropy of Y may decrease because acceleration can help determine more accurately whether a pipe has been dismantled.

[0037] This refers to the first anti-tamper feature. Value The probability, It refers to The real-time anti-tampering anomaly index under the conditions The entropy, where x is a specific value of X. For example, if X is an acceleration characteristic, then x could be the specific value of acceleration, such as 3 m / s². 2 Based on the predictive power of each feature, the weight of each anti-tamper feature is determined. The weight allocation takes into account the importance of each feature in the prediction. The weight allocation is used to determine sub-units to optimize the final predetermined weight allocation based on the predictive power of each feature, ensuring that the contribution of each feature is reasonable, thereby improving the overall prediction accuracy.

[0038] For each tamper-proof feature (such as acceleration, vibration amplitude, and tilt), its predictive ability for the real-time tamper-proof anomaly index was quantified using a predictive ability quantification function, determining the extent to which each feature could reduce the uncertainty of the real-time tamper-proof anomaly index. Based on these predictive abilities, a weight was assigned to each tamper-proof feature, reflecting its relative importance in the entire prediction process; a larger weight indicates a greater impact of the feature on the prediction result. For example, suppose there are three tamper-proof features: acceleration, vibration amplitude, and tilt, with corresponding IG values ​​of 0.75, 0.5, and 0.3, respectively. The sum of all features is calculated to be 1.55. Assigning weights to each feature, the weight for acceleration is approximately 0.75 / 1.55 ​​= 0.48, the weight for vibration amplitude is approximately 0.5 / 1.55 ​​= 0.32, and the weight for tilt is approximately 0.3 / 1.55 ​​= 0.20.

[0039] By introducing a predictive ability quantification function to quantify the predictive ability of features, and determining the weight of each anti-tamper feature based on the quantitative analysis of predictive ability, the weight is assigned according to the importance of each feature, thereby improving the accuracy and efficiency of the anti-tamper early warning device.

[0040] The anomaly detection module 13 is used to issue a first remote anti-tamper warning if the real-time anti-tamper anomaly index reaches a predetermined anti-tamper threshold.

[0041] Specifically, a key criterion for determining when to trigger a remote early warning is to predefine an anti-tampering threshold based on historical experience, equipment or pipeline safety requirements, and predetermined anti-tampering characteristics. This threshold reflects the maximum risk the facility can withstand; exceeding it means the safety of the equipment or pipeline cannot be guaranteed. When the calculated real-time anti-tampering anomaly index exceeds the predetermined threshold, it indicates abnormal behavior in the pipeline or facility, such as an increased likelihood of dismantling or damage. In this case, an early warning should be triggered to alert monitoring personnel to the anomaly and take intervention measures. For example, if the calculated real-time anti-tampering anomaly index is 2.66, while the predetermined threshold is 2.5, the anomaly index has exceeded the threshold, and an early warning should be triggered.

[0042] The information transmission module 14 is used to activate the distributed backup power supply based on the first remote anti-tamper warning, and transmit the predetermined heat theft monitoring information for a predetermined period to the remote data center in conjunction with a predetermined low-power communication protocol.

[0043] Furthermore, the information transmission module 14 in the remote heat theft early warning system is also used to: under the distributed backup power supply, combine the predetermined low-power communication protocol, and continuously monitor the heating pipeline during the predetermined time period through the distributed heat theft monitoring group to obtain the predetermined heat theft monitoring information.

[0044] Specifically, when an anti-tampering anomaly is detected and the first remote anti-tampering warning is triggered, the distributed backup power supply is activated. The distributed backup power supply is typically provided by high-performance batteries (such as lithium batteries, lead-acid batteries, etc.). Under normal circumstances, the main power supply is the source of power, but if the main power supply is cut off or damaged due to disassembly, the backup power supply will automatically take over, ensuring that the equipment can maintain the basic functions and communication of the distributed monitoring device. The power provided by the backup power supply ensures that the basic functions of the distributed heat theft monitoring group continue, including sensor data acquisition and data transmission, and ensures that alarm signals can be issued.

[0045] With backup power, the distributed heat theft monitoring group continues to operate, monitoring for heat theft in the pipelines and continuously collecting data to generate predetermined heat theft monitoring information. When the equipment is on backup power, a low-power communication protocol is used to extend the operating time of the distributed monitoring device under backup power, ensuring continued communication with the monitoring platform for a period after the backup power is removed. Low-power communication protocols typically feature low power consumption and optimized data transmission, operating at relatively low current, significantly extending the operating time of the distributed monitoring device under backup power. Simultaneously, the transmitted data is compressed and optimized to reduce data volume and ensure transmission efficiency. Once the data is successfully transmitted to the remote data center, the data center analyzes and processes the transmitted heat theft monitoring information, generating relevant reports or alarms regarding heat theft behavior.

[0046] The scheduled time period is a set timeframe, specifically a period after the main power supply is cut off. This period can be set according to actual conditions, typically ranging from a few hours to several days. Continuous monitoring is conducted within this timeframe. Scheduled heat theft monitoring information refers to heat theft data detected during this period, including temperature, flow rate, and pressure. The scheduled low-power communication protocol is a communication method used to extend the device's operating time under backup power, enabling data transmission with extremely low power consumption. The remote data center is a platform for centralized data storage and processing, usually located on a monitoring platform, serving as a platform for remote emergency intervention against tampering and heat theft.

[0047] By combining backup power and low-power communication protocols, the distributed monitoring device can still operate stably and continuously monitor heat theft even in the event of power outages or tampering. It can also transmit relevant information to a remote data center for processing in a timely manner, extending the monitoring time as much as possible until relevant personnel repair the distributed monitoring device.

[0048] The heat theft analysis module 15 is used by the remote data center to perform heat theft analysis on the predetermined heat theft monitoring information to obtain a predetermined heat theft anomaly index.

[0049] Furthermore, as shown in Figure 2, the heat theft analysis module 15 in the remote heat theft early warning system is further configured as follows: a first node extraction unit 51, configured to extract the first heat theft monitoring group deployed at the first node of the heating pipeline in the distributed heat theft monitoring group; a first information matching unit 52, configured to match the first monitoring parameter time sequence of the first heat theft monitoring group in the predetermined heat theft monitoring information; a first data analysis unit 53, configured to analyze the first monitoring parameter time sequence through the first data analysis layer of the remote data center to obtain the rate of change of the monitoring parameters; and a second node extraction unit 54, configured to extract the first monitoring parameter time sequence deployed at the first node of the heating pipeline in the distributed heat theft monitoring group. The second node of the heating pipeline is a second heat theft monitoring group, wherein the second node is adjacent to the first node; a second information matching unit 55 is used to match the second monitoring parameter time series of the second heat theft monitoring group in the predetermined heat theft monitoring information; a second collaborative analysis unit 56 is used to perform collaborative analysis on the first monitoring parameter time series and the second monitoring parameter time series through the second data analysis layer of the remote data center to obtain the monitoring parameter uniformity and the monitoring parameter difference along the path, respectively; an anomaly index determination unit 57 is used to analyze the monitoring parameter change rate, the monitoring parameter uniformity, and the monitoring parameter difference along the path to obtain the predetermined heat theft anomaly index.

[0050] Specifically, a distributed heat theft monitoring group is deployed at multiple nodes of the heating pipeline. A node is randomly selected as the first node, and the first heat theft monitoring group deployed at that first node, including temperature sensors, flow sensors, and pressure sensors, is extracted to monitor heat theft behavior at that location. The time sequence of the first monitoring parameters corresponding to the first monitoring group, including changes in temperature, pressure, and flow rate over time, is matched against predetermined heat theft monitoring information.

[0051] The first data analysis layer is an analysis module within the remote data center, embedding a longitudinal analysis strategy for analyzing time-series data to identify the trends and rates of parameter change. First, it analyzes the first temperature, first pressure, and first flow rate time series of the first monitored parameters one by one to determine the rates of change for the first temperature, first pressure, and first flow rate, thus obtaining the rate of change of the monitored parameters. This rate of change is obtained by dividing the parameter change between two adjacent time points by the time interval.

[0052] Similarly, a second heat theft monitoring group is extracted from the distributed heat theft monitoring group and deployed at the second node of the heating pipeline, i.e., another monitoring location adjacent to the first node. The second monitoring parameter time series of the second heat theft monitoring group is matched with the predetermined heat theft monitoring information. Temperature, pressure, and flow rate at different locations at the same time point are obtained, and the temperature, pressure, and flow rate at the two locations are compared to determine whether heat theft occurs. A collaborative analysis is performed on the time series of the first and second monitoring parameters to compare the parameter differences between different nodes and analyze whether the heat, pressure, and flow rate are uniform across the pipeline nodes. This yields the uniformity of monitoring parameters and the difference along the pipeline. The uniformity of monitoring parameters quantifies the degree of uniformity of monitoring parameters such as temperature, pressure, and flow rate at multiple nodes in the heating pipeline; the difference along the pipeline nodes quantifies the differences in monitoring parameters such as temperature, pressure, and flow rate between different nodes in the pipeline.

[0053] The heat theft anomaly index is obtained by weighting the rate of change, uniformity, and friction difference of the monitored parameters. First, the anomaly index for each parameter is calculated based on its weight, with the rate of change typically having the largest weight, while uniformity and friction difference have smaller weights. For example, the weight of the rate of change is 0.6, and the weights of uniformity and friction difference are 0.2. Then, the anomaly index for each parameter is weighted and summed according to the weights of the influence of other monitored parameters such as temperature, pressure, and flow rate on the anomaly index, resulting in a predetermined heat theft anomaly index. The predetermined heat theft anomaly index is the anomaly index obtained after analyzing heat theft monitoring information for a predetermined time period.

[0054] The first data layer performs longitudinal analysis on each node, analyzing its parameter changes at different time points to determine the timing of heat theft. The second data layer analyzes the parameter changes of multiple nodes at the same time to determine the area where heat theft occurs. By comprehensively analyzing the rate of change, uniformity, and friction loss of monitoring parameters, heat theft is accurately identified, enhancing the reliability of heat theft detection and reducing the possibility of false positives.

[0055] Furthermore, the heat theft analysis module 15 in the remote heat theft early warning system is also used for: a longitudinal strategy extraction subunit, used to extract the longitudinal analysis strategy embedded in the first data analysis layer; a longitudinal analysis subunit, used to analyze the first temperature time series, the first pressure time series, and the first flow time series in the first monitoring parameter time series one by one according to the longitudinal analysis strategy, and obtain the first temperature change rate, the first pressure change rate, and the first flow change rate respectively; and a change rate composition subunit, used to compose the monitoring parameter change rate from the first temperature change rate, the first pressure change rate, and the first flow change rate.

[0056] Specifically, the vertical analysis strategy embedded in the first data analysis layer is extracted. This strategy involves analyzing different types of monitoring parameters (such as temperature, pressure, and flow rate) collected from the same monitoring node (such as the first node) sequentially over time. This allows for a deeper understanding of the changing trends of these parameters over a period of time, thereby extracting the rate of parameter change and further determining whether any anomalies exist. The first temperature time series, first pressure time series, and first flow rate time series in the first monitoring parameter time series represent the time-series data obtained from the temperature sensor, pressure sensor, and flow sensor of the first node, respectively, reflecting the changes of specific parameters over a period of time.

[0057] The rate of temperature change (the amount of temperature change per unit time) is calculated using a temperature time series. For example, if the temperature rises from 50°C to 60°C in 10 minutes, the rate of temperature change is 1°C / minute. Similarly, the rate of pressure change is calculated based on data from a pressure time series. If the pressure rises from 200 Pa to 250 Pa within a certain time period, the rate of pressure change is 5 Pa / minute. The rate of flow rate change is calculated using a flow rate time series, reflecting how quickly the flow rate changes over a period of time.

[0058] For example, the temperature data recorded by the temperature sensor at the first node over one hour is as follows: time 1 is 50℃, time 2 is 51℃, and time 3 is 52℃, so the temperature change rate is 2℃ / h; the pressure data recorded by the pressure sensor is as follows: time 1 is 0.25MPa, time 2 is 0.27MPa, and time 3 is 0.3MPa, so the pressure change rate is 0.05MPa / h; the flow data recorded by the flow sensor is as follows: time 1 is 0.38m... 3 / h, time 2 is 0.4m 3 / h, time 3 is 0.45m 3 If the flow rate changes by 0.07 m / h, then the rate of change of flow is 0.07 m / h. 3 / h.

[0059] The first rate of change in temperature, the first rate of change in pressure, and the first rate of change in flow rate together constitute the rate of change of monitoring parameters, reflecting whether there is abnormal behavior in the pipeline. For example, if the rates of change in temperature, pressure, and flow rate are large within the same time period, it may indicate an anomaly in the heating system at that node, such as heat theft. By using a longitudinal analysis strategy to analyze the rate of change of each monitoring parameter one by one, anomalies can be accurately identified, such as sharp changes in temperature, pressure, and flow rate, which are often signs of heat theft.

[0060] Furthermore, the heat theft analysis module 15 in the remote heat theft early warning system is further configured as follows: a time period acquisition subunit, configured to acquire any time within the predetermined time period; a first matching subunit, configured to sequentially match the first temperature, first pressure, and first flow rate at any given time within the first temperature time series, the first pressure time series, and the first flow rate time series; a time series extraction subunit, configured to extract the second temperature time series, the second pressure time series, and the second flow rate time series from the second monitoring parameter time series; a second matching subunit, configured to sequentially match the second temperature, the second pressure, and the second flow rate at any given time within the second temperature time series, the second pressure time series, and the second flow rate time series; a lateral strategy extraction subunit, configured to extract the lateral analysis strategy embedded in the second data analysis layer; and a lateral analysis subunit, configured to analyze the first temperature, the first pressure, the first flow rate, the second temperature, the second pressure, and the second flow rate according to the lateral analysis strategy to obtain the uniformity of the monitoring parameters and the difference along the monitoring parameters.

[0061] The temperature comparison channel is used to compare the first temperature and the second temperature according to the lateral analysis strategy to obtain temperature uniformity and temperature friction difference, respectively; the pressure comparison channel is used to compare the first pressure and the second pressure according to the lateral analysis strategy to obtain pressure uniformity and pressure friction difference, respectively; the flow rate comparison channel is used to compare the first flow rate and the second flow rate according to the lateral analysis strategy to obtain flow rate uniformity and flow rate friction difference, respectively; the friction difference composition channel is used to compose the monitoring parameter uniformity from the temperature uniformity, the pressure uniformity, and the flow rate uniformity, and to compose the monitoring parameter friction difference from the temperature friction difference, the pressure friction difference, and the flow rate friction difference.

[0062] Specifically, a random time point is selected within a predetermined time period as an arbitrary moment. This moment, a specific point within the selected time period, is used to compare the changes in monitoring data between different nodes (such as the first node and the second node) at the same time point. From the first temperature, first pressure, and first flow rate time series of the first monitoring parameter time series of the first node, the first temperature, first pressure, and first flow rate at any arbitrary moment are extracted; that is, the temperature, pressure, and flow rate data at the first node at that moment. Next, from the second temperature, second pressure, and second flow rate time series of the second monitoring parameter time series, the second temperature, second pressure, and second flow rate at any arbitrary moment are extracted; that is, the temperature, pressure, and flow rate data at the second node at that moment. The first and second temperatures represent temperature data at the same time point at different nodes, and the pressure and flow rates are similarly analyzed.

[0063] The second data analysis layer incorporates a lateral analysis strategy to compare data from different nodes (such as the first and second nodes) and analyze their differences. This lateral analysis strategy primarily compares monitoring data from two or more monitoring nodes to derive indicators regarding uniformity and friction loss. By comparing data such as temperature, pressure, and flow rate between two nodes (e.g., the first and second nodes), it analyzes their trends and differences.

[0064] By comparing the temperature changes of the first and second nodes at the same time point, the uniformity of heat distribution in the heating pipeline can be assessed, thereby determining whether heat theft occurs between these two nodes and pinpointing the specific location of heat theft while monitoring for such activity. Temperature uniformity refers to the degree of temperature difference between different nodes in the heating pipeline. If the temperature differences between nodes are small, it indicates that the heat distribution within the pipeline is relatively uniform, and there are no abnormalities such as excessively high or low temperatures. Conversely, if the temperature differences are large, it may indicate a problem in that area of ​​the pipeline, such as heat theft or heat loss. By calculating the temperature difference between the first and second nodes, the uniformity of temperature changes between these two nodes can be determined. If the temperature difference between the two nodes is very small, the temperature distribution can be considered relatively uniform, indicating that there are no significant abnormalities in the heat distribution of the heating pipeline.

[0065] Temperature friction difference refers to the temperature variation between different locations along a pipe (such as the first and second nodes), reflecting whether there are any abnormalities in the pipe's heat distribution. A large temperature friction difference may indicate heat loss or heat theft. A smaller temperature friction difference indicates a more uniform heat distribution within the pipe; a larger difference suggests potential problems such as heat loss, heat concentration, or heat theft.

[0066] Similarly, comparing the first and second pressures yields pressure uniformity and pressure friction difference. Pressure uniformity refers to whether the pressure change is uniform across all nodes in the heating pipeline. Lower pressure in a certain area of ​​the pipeline may indicate obstructed heat flow or heat theft; smaller pressure differences suggest a more stable fluid state within the pipeline. Pressure friction difference refers to the pressure difference between different locations within the pipeline. A larger pressure friction difference may indicate areas of obstructed fluid flow or pressure changes due to leaks or blockages in certain parts of the pipeline, thus indicating the presence of heat theft. Comparing the first and second flow rates yields flow uniformity and flow friction difference. Flow uniformity refers to whether the flow rate at different nodes in the heating pipeline is the same or similar. Flow non-uniformity may lead to insufficient or excessive heat in certain areas, related to blockages, pipeline damage, or heat theft. Flow friction difference refers to the difference in flow rate at different locations along the pipeline's flow path, reflecting uneven fluid distribution. For example, reduced flow in certain areas may indicate heat theft.

[0067] Temperature uniformity, pressure uniformity, and flow uniformity reflect whether the distribution of temperature, pressure, and flow rate is uniform across different nodes in a heating pipeline. Combining these three parameters forms a monitoring parameter uniformity index. Temperature friction difference, pressure friction difference, and flow friction difference reflect whether the distribution of heat, flow rate, and pressure is balanced across different locations in the heating pipeline. These three parameters also form a monitoring parameter friction difference index. By synthesizing the above analysis results, a comprehensive index of monitoring parameter uniformity and monitoring parameter friction difference is obtained, revealing the state differences between different nodes in the heating pipeline, thereby determining whether any abnormalities or heat theft are occurring.

[0068] The heat theft warning module 16 is used to issue a first remote heat theft warning if the predetermined heat theft anomaly index reaches a predetermined heat theft threshold.

[0069] Specifically, the predetermined heat theft threshold is a pre-set value used as a standard to determine whether heat theft has occurred. It is typically determined based on historical data, industry standards, and the requirements of the specific application. If the predetermined heat theft anomaly index exceeds the predetermined heat theft threshold, an anomaly is considered to exist, and an alarm is triggered. When the predetermined heat theft anomaly index reaches the predetermined heat theft threshold, it indicates that heat theft may have occurred in the pipeline, and a first remote heat theft warning is issued. For example, if the predetermined heat theft threshold is 5, and the actual calculated predetermined heat theft anomaly index is 7, an alarm will be triggered. When the first remote heat theft warning is triggered, the heat theft warning information is sent to the monitoring platform through a remote data center. Administrators can view the warning in real time and conduct further on-site investigations to reduce the impact of heat theft on energy supply and security.

[0070] Emergency intervention module 17 is used to perform emergency intervention for preventing tampering and heat theft in the heating pipeline based on the first remote anti-tampering warning and the first remote heat theft warning.

[0071] Specifically, the first remote anti-tampering warning is an alarm issued when abnormal anti-tampering behavior is detected in the heating pipeline, indicating that the equipment or pipeline may have been maliciously removed or damaged. The first remote heat theft warning is an alarm issued when heat theft behavior is detected in the pipeline (such as illegal heat extraction or tampering with heat metering data), aiming to prevent energy theft and ensure the normal operation of the heating system. When the first remote anti-tampering warning or the first remote heat theft warning is issued, the relevant information is immediately uploaded to the monitoring center, and corresponding alarms are issued to different levels of management personnel according to the warning type and location. For example, the administrator is responsible for overall monitoring and management, including setting warning thresholds and access control; ordinary management personnel are responsible for handling warning information for specific areas or equipment and dispatching on-site inspections as needed; inspectors are responsible for on-site investigations, taking photos and uploading them to the platform for remote management. Each alarm message not only displays the warning type (anti-tampering or heat theft) but also includes alarm count records and alarm classification information, making it convenient for administrators to view historical alarms and their handling process.

[0072] To enhance the timeliness and on-site warning effectiveness of early warnings, anti-tampering and heat theft warnings will trigger on-site sound and light alarm devices. For example, when a pipe is maliciously dismantled or heat theft occurs, an alarm will sound and lights will flash to ensure that staff or those nearby notice the problem promptly. When management personnel receive the warning and inspect the site, they can take photos using their mobile phones or other devices to record the abnormal situation and upload the photos to the monitoring platform for remote monitoring and follow-up by other management personnel.

[0073] Furthermore, the anomaly analysis module 12 in the remote heat theft early warning system is also used for: a second analysis unit, used to perform heat theft analysis on the real-time heat theft monitoring information in the real-time monitoring information through the remote data center to obtain the real-time heat theft anomaly index if the real-time anti-tampering anomaly index does not reach the predetermined anti-tampering threshold; a second early warning unit, used to issue a second remote heat theft early warning if the real-time heat theft anomaly index reaches the predetermined heat theft threshold; and a second intervention unit, used to perform heat theft emergency intervention on the heating pipeline according to the second remote heat theft early warning.

[0074] Specifically, if the real-time anti-tampering anomaly index does not reach the predetermined anti-tampering threshold, it means that no tampering has occurred, and the distributed monitoring device can continue monitoring to obtain real-time monitoring information. The real-time heat theft monitoring information within this real-time monitoring information is then analyzed to obtain the real-time heat theft anomaly index. The specific heat theft analysis here is consistent with the aforementioned analysis of predetermined heat theft monitoring information in a remote data center to obtain a predetermined heat theft anomaly index, and will not be detailed here.

[0075] When the real-time heat theft anomaly index reaches the predetermined heat theft threshold, indicating heat theft activity, a second remote heat theft warning is issued. This warning is sent only to the management personnel's equipment. Management personnel will then implement emergency intervention measures based on the alarm information, including shutting down the heat theft source, repairing tampered equipment, and fixing pipeline leaks. Timely and effective emergency intervention is ensured through on-site inspections, remote control, and real-time data updates. During emergency intervention, the situation is continuously tracked using uploaded monitoring data and warning information, providing further data support to management personnel.

[0076] If the heat theft problem is effectively intervened and resolved, the monitoring data is updated and fed back to the remote data center to complete the incident handling. If the heat theft problem is not effectively intervened, monitoring continues and new alarms are issued as needed to ensure the safe operation of the heating system.

[0077] In summary, the remote heat theft early warning system provided in this application has the following technical effects: A real-time monitoring module is used to dynamically monitor the heating pipeline using distributed monitoring devices deployed on the pipeline to obtain real-time monitoring information; an anomaly analysis module is used to read predetermined anti-tampering features and perform traversal analysis on the real-time anti-tampering monitoring information in the real-time monitoring information to obtain a real-time anti-tampering anomaly index; an anomaly judgment module is used to issue a first remote anti-tampering early warning if the real-time anti-tampering anomaly index reaches a predetermined anti-tampering threshold; an information transmission module is used to activate a distributed backup power supply based on the first remote anti-tampering early warning and transmit predetermined heat theft monitoring information for a predetermined period to a remote data center in conjunction with a predetermined low-power communication protocol; a heat theft analysis module is used by the remote data center to perform heat theft analysis on the predetermined heat theft monitoring information to obtain a predetermined heat theft anomaly index; a heat theft early warning module is used to issue a first remote heat theft early warning if the predetermined heat theft anomaly index reaches a predetermined heat theft threshold; and an emergency intervention module is used to perform anti-tampering and heat theft emergency intervention on the heating pipeline based on the first remote anti-tampering early warning and the first remote heat theft early warning. In other words, by deploying distributed monitoring devices on the heating pipeline for dynamic monitoring, and combining this with predetermined anti-tampering features to traverse and analyze real-time monitoring data, anti-tampering warnings are issued. Based on the anti-tampering warning, backup power is activated to transmit heat theft monitoring information to a remote data center for heat theft analysis, thereby issuing heat theft warnings. Based on the anti-tampering warning and heat theft warning, emergency intervention for anti-tampering and heat theft is carried out on the heating pipeline, realizing comprehensive real-time monitoring of the heating pipeline and improving the accuracy and efficiency of remote heat theft warnings.

[0078] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0079] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A remote heat theft early warning system, characterized in that, include: The real-time monitoring module is used to obtain real-time monitoring information through distributed monitoring devices deployed on the heating pipeline; An anomaly analysis module is used to read predetermined anti-tamper features and perform a traversal analysis of the real-time anti-tamper monitoring information in the real-time monitoring information to obtain a real-time anti-tamper anomaly index. Anomaly detection module is used to issue a first remote anti-tamper warning if the real-time anti-tamper anomaly index reaches a predetermined anti-tamper threshold. The information transmission module is used to activate the distributed backup power supply based on the first remote anti-tamper warning, and transmit the predetermined heat theft monitoring information for a predetermined period to the remote data center in conjunction with a predetermined low-power communication protocol. The heat theft analysis module is used by the remote data center to perform heat theft analysis on the predetermined heat theft monitoring information and obtain a predetermined heat theft anomaly index. The heat theft warning module is used to issue a first remote heat theft warning if the predetermined heat theft anomaly index reaches a predetermined heat theft threshold. The emergency intervention module is used to perform emergency intervention to prevent tampering and heat theft in the heating pipeline based on the first remote anti-tampering warning and the first remote heat theft warning.

2. The remote heat theft early warning system as described in claim 1, characterized in that, The real-time monitoring module includes: an anti-tamper monitoring assembly unit for assembling a distributed anti-tamper monitoring group; a heat theft monitoring assembly unit for assembling a distributed heat theft monitoring group; and a monitoring construction unit for the distributed anti-tamper monitoring group and the distributed heat theft monitoring group to jointly form the distributed monitoring device; wherein the distributed anti-tamper monitoring group includes an acceleration sensor, a vibration sensor, and a tilt sensor, and the distributed heat theft monitoring group includes a temperature sensor, a pressure sensor, and a flow sensor.

3. The remote heat theft early warning system as described in claim 1, characterized in that, The anomaly analysis module includes: a feature traversal unit, used to traverse the real-time anti-tamper monitoring information based on the predetermined anti-tamper features to obtain real-time anti-tamper feature parameters; and a weighted calculation unit, used to obtain the predetermined weight allocation of the predetermined anti-tamper features and perform weighted calculation in combination with the real-time anti-tamper feature parameters to obtain the real-time anti-tamper anomaly index; wherein, the predetermined weight allocation refers to the standardized result of the predictive ability of each anti-tamper feature in the predetermined anti-tamper features to the real-time anti-tamper anomaly index.

4. A remote heat theft early warning system as described in claim 3, characterized in that, The weighted calculation unit includes: a quantization analysis subunit, used to introduce a prediction capability quantization function, and perform quantization analysis on the prediction capability of the first anti-tamper feature to the real-time anti-tamper anomaly index based on the prediction capability quantization function, to obtain the first prediction capability; wherein, the first anti-tamper feature refers to any one of the predetermined anti-tamper features, and the predetermined anti-tamper features include acceleration, vibration amplitude, and tilt angle; wherein, the expression of the prediction capability quantization function is: ;in, This refers to the first anti-tamper feature. The first predictive ability, This refers to the real-time anti-tampering anomaly index. entropy, This refers to the real-time anti-tampering anomaly index. Take the first The probability of each value This refers to the real-time anti-tampering anomaly index. The total number of all possible values. This refers to the first anti-tamper feature. conditional entropy, This refers to the first anti-tamper feature. Value The probability, It refers to The real-time anti-tampering anomaly index under the conditions The entropy; the weight allocation determination subunit is used to obtain the predetermined weight allocation based on the correspondence between the first anti-tamper feature and the first prediction capability.

5. A remote heat theft early warning system as described in claim 2, characterized in that, Under the distributed backup power supply, combined with the predetermined low-power communication protocol, and through the distributed heat theft monitoring group, the predetermined heat theft monitoring information is obtained by continuously monitoring the heating pipeline during the predetermined time period.

6. A remote heat theft early warning system as described in claim 5, characterized in that, The heat theft analysis module is configured to: a first node extraction unit, configured to extract the first heat theft monitoring group deployed at the first node of the heating pipeline in the distributed heat theft monitoring group; and a first information matching unit, configured to match the timing sequence of the first monitoring parameters of the first heat theft monitoring group in the predetermined heat theft monitoring information. A first data analysis unit is used to analyze the time series of the first monitoring parameter through the first data analysis layer of the remote data center to obtain the rate of change of the monitoring parameter; a second node extraction unit is used to extract the second heat theft monitoring group deployed at the second node of the heating pipeline in the distributed heat theft monitoring group, wherein the second node is adjacent to the first node; a second information matching unit is used to match the time series of the second monitoring parameter of the second heat theft monitoring group in the predetermined heat theft monitoring information; a second collaborative analysis unit is used to perform collaborative analysis of the time series of the first monitoring parameter and the time series of the second monitoring parameter through the second data analysis layer of the remote data center to obtain the uniformity of the monitoring parameter and the difference along the monitoring parameter; an anomaly index determination unit is used to analyze the rate of change of the monitoring parameter, the uniformity of the monitoring parameter, and the difference along the monitoring parameter to obtain the predetermined heat theft anomaly index.

7. A remote heat theft early warning system as described in claim 6, characterized in that, The first data analysis unit includes: a vertical strategy extraction subunit, used to extract the vertical analysis strategy embedded in the first data analysis layer; a vertical analysis subunit, used to analyze the first temperature time series, the first pressure time series, and the first flow time series in the first monitoring parameter time series sequentially according to the vertical analysis strategy, and obtain the first temperature change rate, the first pressure change rate, and the first flow change rate, respectively; and a change rate composition subunit, used to compose the monitoring parameter change rate from the first temperature change rate, the first pressure change rate, and the first flow change rate.

8. A remote heat theft early warning system as described in claim 7, characterized in that, The second collaborative analysis unit includes: a time period acquisition subunit, used to acquire any time within the predetermined time period; a first matching subunit, used to sequentially match the first temperature, first pressure, and first flow rate at any given time within the first temperature time series, the first pressure time series, and the first flow rate time series; a time series extraction subunit, used to extract the second temperature time series, the second pressure time series, and the second flow rate time series from the second monitoring parameter time series; a second matching subunit, used to sequentially match the second temperature, the second pressure, and the second flow rate at any given time within the second temperature time series, the second pressure time series, and the second flow rate time series; a lateral strategy extraction subunit, used to extract the lateral analysis strategy embedded in the second data analysis layer; and a lateral analysis subunit, used to analyze the first temperature, the first pressure, the first flow rate, the second temperature, the second pressure, and the second flow rate according to the lateral analysis strategy to obtain the uniformity of the monitoring parameters and the difference along the monitoring parameters.

9. A remote heat theft early warning system as described in claim 8, characterized in that, The lateral analysis subunit includes: a temperature comparison channel, used to compare the first temperature and the second temperature according to the lateral analysis strategy to obtain temperature uniformity and temperature friction difference, respectively; a pressure comparison channel, used to compare the first pressure and the second pressure according to the lateral analysis strategy to obtain pressure uniformity and pressure friction difference, respectively; a flow rate comparison channel, used to compare the first flow rate and the second flow rate according to the lateral analysis strategy to obtain flow rate uniformity and flow rate friction difference, respectively; and a friction difference composition channel, used to compose the monitoring parameter uniformity from the temperature uniformity, the pressure uniformity, and the flow rate uniformity, and to compose the monitoring parameter friction difference from the temperature friction difference, the pressure friction difference, and the flow rate friction difference.

10. A remote heat theft early warning system as described in claim 1, characterized in that, The anomaly analysis module further includes: a second analysis unit, used to perform heat theft analysis on the real-time heat theft monitoring information in the real-time monitoring information through the remote data center to obtain a real-time heat theft anomaly index if the real-time anti-tampering anomaly index does not reach the predetermined anti-tampering threshold; a second early warning unit, used to issue a second remote heat theft early warning if the real-time heat theft anomaly index reaches the predetermined heat theft threshold; and a second intervention unit, used to perform heat theft emergency intervention on the heating pipeline according to the second remote heat theft early warning.

Images