A heat network metering data supervision method and system

Abstract

The present application relates to the technical field of data processing, in particular to a kind of heat supply network metering data supervision method and system, the method comprises: obtaining the heat supply system heat network metering data in predetermined time period;According to average and standard deviation, determine data normal range, determine the heat data that exceeds data normal range as initial abnormal heat data;According to the heat data and outdoor temperature data of each time in predetermined time period, determine the first predicted heat data of any one time in predetermined time period;According to the change quantity between the heat data of the target time corresponding to initial abnormal heat data in predetermined time period and the last time adjacent to target time and the change quantity between first predicted heat data, determine the assignment of initial abnormal heat data;In the case where assignment is greater than first threshold, determine initial abnormal heat data as actual abnormal heat data.Such, the present application improves monitoring accuracy, and improves the failure detection rate in heat supply system.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, specifically to a method and system for monitoring heating network metering data. Background Technology

[0002] Heat network metering data refers to the data on heat, temperature, pressure, flow, and other related parameters collected in a centralized heating system through various sensors, metering instruments, and other equipment installed at heat sources, heat exchange stations, pipelines, and user terminals. It is used to monitor and control the operating status of the heating system, assess energy usage, optimize heating strategies, and improve energy efficiency.

[0003] In some scenarios, monitoring heating network metering data is crucial for assessing the operational status of the heating system. Numerous factors can cause anomalies in heat data, such as sensor malfunctions, pipe leaks, and damage. Furthermore, sudden changes in environmental factors can affect heating demand, leading to momentary fluctuations in heat data. However, these fluctuations caused by environmental factors do not necessarily indicate a fault in the heating system. When monitoring heat data, threshold methods and time series analysis are commonly used for anomaly detection. This can easily lead to misclassifying normal heat data influenced by environmental factors as abnormal. Consequently, the accuracy of heat monitoring in heating network metering data is low, resulting in a low fault detection rate in the heating system. Summary of the Invention

[0004] To address the technical problems of low accuracy in heat monitoring and low fault detection rate in heating systems, this invention aims to provide a method and system for monitoring heating network metering data. The specific technical solution adopted is as follows:

[0005] In a first aspect, embodiments of the present invention provide a method for monitoring heating network metering data, comprising: acquiring heating network metering data of a heating system within a predetermined time period, the heating network metering data including heat data and outdoor temperature data corresponding to the heat data; calculating the average value and standard deviation of the heat data within the predetermined time period, and determining the normal range of the data based on the average value and standard deviation, and determining heat data exceeding the normal range as initial abnormal heat data; determining first predicted heat data at any time within the predetermined time period based on the heat data and outdoor temperature data at each time point within the predetermined time period; determining the value of the initial abnormal heat data based on the change in heat data between the target time point corresponding to the initial abnormal heat data and the previous time point adjacent to the target time point, and the change between the first predicted heat data; and determining the initial abnormal heat data as actual abnormal heat data if the assigned value is greater than a first threshold.

[0006] Optionally, obtaining the heating network metering data of the heating system within a predetermined time period includes: obtaining the supply water temperature of the supply water pipe, the return water temperature of the return water pipe, the first flow rate in the supply water pipe, and the specific heat capacity of water in the heating system; calculating the absolute value of the first difference between the supply water temperature and the return water temperature; and determining the product of the first flow rate, the specific heat capacity, and the absolute value of the first difference as the heat data.

[0007] Optionally, determining the first predicted heat data for any given moment within the predetermined time period based on the heat data and outdoor temperature data at each moment within the predetermined time period includes: determining the second predicted heat data for any given moment within the predetermined time period based on the heat data at the first moment within the predetermined time period and the change in the heat data at the first moment within the predetermined time period; determining the predicted outdoor temperature for any given moment within the predetermined time period based on the outdoor temperature data at the first moment within the predetermined time period and the change in the outdoor temperature data at the first moment within the predetermined time period; determining the second ratio between the change in heat data and the change in outdoor temperature data at any given moment within the predetermined time period using the first ratio between the second predicted heat data and the predicted outdoor temperature at the first moment within the predetermined time period and the change in the ratio between the change in the second predicted heat data and the change in the predicted outdoor temperature at adjacent moments; and determining the first predicted heat data for any given moment within the predetermined time period based on the heat data at the moment preceding any given moment within the predetermined time period, the second ratio at any given moment, and the change in the predicted outdoor temperature between any given moment and the moment preceding any given moment.

[0008] Optionally, determining the second predicted heat data at any time within the predetermined time period based on the heat data at the first moment within the predetermined time period and the change in the heat data at the first moment within the predetermined time period includes: calculating the reciprocal of the sorted value at any time within the predetermined time period, and calculating the first product of the reciprocal and the change in the heat data at the first moment; determining the first sum between the first product and the heat data at the first moment as the second predicted heat data at any time within the predetermined time period.

[0009] Optionally, determining the predicted outdoor temperature at any point within the predetermined time period based on the outdoor temperature data at the first moment within the predetermined time period and the change in the outdoor temperature data at the first moment within the predetermined time period includes: calculating the reciprocal of the first difference between the sorted value at any moment within the predetermined time period and the predetermined value, and the second product between the reciprocal of the first difference and the change in the outdoor temperature data at the first moment; determining the second sum between the second product and the outdoor temperature data at the first moment as the predicted outdoor temperature at any moment within the predetermined time period.

[0010] Optionally, determining the second ratio between the change in heat data and the change in outdoor temperature at any given moment within the predetermined time period, using the first ratio between the second predicted heat data and the predicted outdoor temperature at the first moment within the predetermined time period, and the change in the ratio between the change in the second predicted heat data and the change in the predicted outdoor temperature at adjacent moments, includes: calculating the reciprocal of the second difference between the sorted value and the predetermined value at any given moment within the predetermined time period, and the third product of the reciprocal of the second difference and the change in the ratio between the change in the second predicted heat data and the change in the predicted outdoor temperature at adjacent moments; and determining the third sum of the second predicted heat data at the first moment within the predetermined time period and the third product as the second ratio.

[0011] Optionally, determining the first predicted heat data for any given moment within the predetermined time period, based on the heat data of a moment before any given moment within the predetermined time period, the second ratio of any given moment, and the change in predicted outdoor temperature between any given moment and the moment before any given moment, includes: calculating the fourth product between the second ratio of any given moment and the change in predicted outdoor temperature between any given moment and the moment before any given moment; and determining the fourth sum between the fourth product and the heat data of a moment before any given moment within the predetermined time period as the first predicted heat data for any given moment within the predetermined time period.

[0012] Optionally, determining the assignment of the initial abnormal heat data based on the change in heat data between the target time and the previous time adjacent to the target time, and the change in the first predicted heat data within the predetermined time period, includes: calculating the absolute value of the third difference between the change in heat data between the target time and the previous time adjacent to the target time, and the change in the first predicted heat data; normalizing the absolute value of the third difference to obtain the assignment of the initial abnormal heat data.

[0013] Optionally, after determining that the initial abnormal heat data is actual abnormal heat data when the assigned value is greater than the first threshold, the method further includes: clustering each actual abnormal heat data to obtain multiple first clusters; merging the first clusters according to the distance between the centers of the first clusters to obtain second clusters; using the center of the second cluster as the second threshold; and determining that the real-time heat data is abnormal and issuing an alarm when the real-time heat data of the heating system is greater than the second threshold.

[0014] In a second aspect, embodiments of the present invention provide a heating network metering data monitoring system, comprising: a processor and a memory; wherein the memory is used to store a computer program that can run on the processor; the processor is used to execute the program stored in the memory to implement the steps of the heating network metering data monitoring method mentioned in the first aspect.

[0015] The present invention has the following beneficial effects: First, it acquires the heating network metering data of the heating system within a predetermined time period, including heat data and corresponding outdoor temperature data; then, it calculates the average value and standard deviation of the heat data within the predetermined time period, and determines the normal range of the data based on the average value and standard deviation; second, it identifies heat data exceeding the normal range as initial abnormal heat data; then, it determines the first predicted heat data for any time within the predetermined time period based on the heat data and outdoor temperature data at each moment within the predetermined time period; and it determines the value of the initial abnormal heat data based on the change in heat data between the target time corresponding to the initial abnormal heat data and the previous time adjacent to the target time, as well as the change between the first predicted heat data; finally, if the assigned value is greater than a first threshold, it determines the initial abnormal heat data as actual abnormal heat data.

[0016] Thus, embodiments of the present invention can utilize the relationship between heat data and outdoor temperature data in the heating system to locate abnormal heat data and identify abnormal changes in heat data caused by temperature drops due to abnormal weather. Specifically, it first preliminarily identifies abnormal heat data that is outside the normal range. Then, based on the correspondence between heat data and outdoor temperature, it predicts the heat data for each moment. The preliminarily identified abnormal heat data is assigned a value based on the predicted heat data and the preliminarily identified abnormal heat data. If this value is greater than a first threshold, the initial abnormal heat data is determined to be genuine abnormal heat data, and not abnormal heat data caused by temperature changes in the external environment. Therefore, by using the technical solution provided by embodiments of the present invention, the monitoring accuracy and fault detection rate in the heating system are improved when monitoring heat in the heating network metering data. Attached Figure Description

[0017] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention 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 only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating a method for monitoring heating network metering data, provided as an embodiment of the present invention;

[0019] Figure 2 A schematic diagram of the curves showing the change of outdoor temperature data and corresponding heat data over time, provided as an embodiment of the present invention;

[0020] Figure 3 This is a schematic diagram of the structure of a heating network metering data monitoring system provided in one embodiment of the present invention. Detailed Implementation

[0021] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a heating network metering data monitoring method and system proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0023] The following description, in conjunction with the accompanying drawings, details the specific scheme of a heating network metering data monitoring method and system provided by the present invention.

[0024] Example 1:

[0025] Please see Figure 1 The flowchart illustrates a heating network metering data monitoring method according to an embodiment of the present invention, including:

[0026] S101, Obtain the heating network metering data of the heating system within a predetermined time period.

[0027] The heating network metering data includes heat data and the corresponding outdoor temperature data.

[0028] Specifically, embodiments of the present invention include obtaining historical heat data for the same time period over multiple days within a predetermined time period, and historical outdoor temperature data corresponding to the historical heat data from a relevant database. It also includes obtaining real-time heat data for the predetermined time period and outdoor temperature data corresponding to the real-time heat data. For the historical heat data and historical outdoor temperature data for the same time period over these days, the average of the historical heat data and historical outdoor temperature data for each time period is calculated as the historical data for each time period.

[0029] For real-time heat data and outdoor temperature data, real-time heat data and outdoor temperature data within a predetermined time period can be obtained. The predetermined time period can be determined based on actual conditions; in this embodiment, it is 24 hours. Then, the 24 hours are divided into multiple time points, with each point having a 1-second interval. In this embodiment, a series of sensors and data acquisition devices are typically used to collect various parameters in the heating system. These include the supply water temperature in the supply pipes, the return water temperature in the return pipes, and the water flow rate in the supply pipes. This embodiment acquires the temperature data of the supply pipes in a residential area for a certain period, as well as the corresponding return water temperature data at the same moment. Since the pipes in residential areas are relatively short, and the distance from the supply pipes to the return pipes of large users is limited, the instantaneous difference between the supply and return water temperatures can basically reflect the heating status, and the delay error is negligible. Therefore, this embodiment uses a Kalman filter algorithm to dynamically smooth the supply and return water temperatures to obtain denoised supply and return water temperatures. For each heat data point, there is a corresponding time point. In this embodiment of the invention, the time point corresponding to the heat data is obtained, and real-time outdoor temperature data is obtained from the network meteorological platform based on the time point. The obtained outdoor temperature data is then fitted with a polynomial curve using SG filtering to smooth the noise and obtain the denoised outdoor temperature data.

[0030] In acquiring heat data of a heating system, as an optional embodiment of the present invention, acquiring heat network metering data of the heating system within a predetermined time period includes: firstly, acquiring the supply water temperature of the supply water pipe, the return water temperature of the return water pipe, the first flow rate in the supply water pipe, and the specific heat capacity of the water in the heating system; then, calculating the absolute value of the first difference between the supply water temperature and the return water temperature; and finally, determining the product of the first flow rate, the specific heat capacity, and the absolute value of the first difference as the heat data.

[0031] Specifically, the first flow rate in the water supply pipeline refers to the water flow rate in the pipeline, and the supply and return water temperatures can be measured using temperature sensors. This embodiment of the invention uses the following formula to calculate the heat data:

[0032] Q 实际 =C×M×|T in -T out |

[0033] In the above formula, T in T represents the water supply temperature at any given time in the water supply pipeline. out Let Q be the return water temperature at any given time in the return water pipe. Let M be the initial flow rate in the supply water pipe at any given time. 实际 This is used to calculate heat data in real time. C represents the specific heat capacity of water.

[0034] S102, calculate the average value and standard deviation of the heat data within the predetermined time period, and determine the normal range of the data based on the average value and standard deviation, and identify the heat data that exceeds the normal range as the initial abnormal heat data.

[0035] Specifically, anomalies in the heating system can directly or indirectly affect heat data. For example, sensor malfunctions, pipe leaks, and damage can directly cause a sudden spike in the acquired heat data, exceeding normal levels. Conversely, equipment shutdowns and sensor failures can lead to a sudden and significant drop in data. These anomalies can all cause abnormal peaks or lows in heat data. Therefore, this embodiment of the invention determines the normal range of heat data based on the characteristics of abnormal heat data, such as peaks or troughs.

[0036] Furthermore, after acquiring the heat data within a predetermined time period, the average value and standard deviation of the heat data within that time period are calculated. In this embodiment of the invention, the normal range of heat data is determined to be [a-3b, a+3b], where a-3b represents the lower limit of the normal range, a+3b represents the upper limit of the normal range, a represents the average value of the heat data within the predetermined time period, and b represents the standard deviation of the heat data within the predetermined time period. If the heat data at a certain point in time is not within this normal range, it indicates that the heat data may be abnormal, and it is taken as initial abnormal heat data. According to the method provided in this embodiment of the invention, all real-time heat data within the acquired predetermined time period are judged to obtain all suspected abnormal initial abnormal heat data.

[0037] S103, determine the first predicted heat data for any time within the predetermined time period based on the heat data and outdoor temperature data at each time point within the predetermined time period.

[0038] Specifically, in this embodiment of the invention, abnormal heat data is represented by peaks or troughs. Initial abnormal heat data is extracted and located. By analyzing residents' heat data during a specific time of day within the residential area, it is found that residents' use of the heating system exhibits significant variations throughout the day. Therefore, based on this situation, this embodiment of the invention further filters the heat data by establishing a trend of heat data changes during a specific time of day under normal conditions. First, the heat data for a specific time of day is analyzed, revealing certain variation characteristics. A curve is plotted using the obtained heat data under normal conditions for a specific time of day. Analysis of the data variation characteristics shows that these characteristics are mainly influenced by residents' usage habits. Specifically, during periods of high activity in the room, air circulation is greater, leading to faster heat loss, and frequent opening of windows and doors also contributes to heat loss. Therefore, this embodiment of the invention determines the predicted heat data for any given moment within a predetermined time period based on heat data at various times within that time period and outdoor temperature data.

[0039] Furthermore, in determining the first predicted heat data at any given moment within a predetermined time period, as an optional embodiment of the present invention, firstly, based on the heat data at the first moment within the predetermined time period and the change in the heat data at the first moment within the predetermined time period, the second predicted heat data at any given moment within the predetermined time period is determined; then, based on the outdoor temperature data at the first moment within the predetermined time period and the change in the outdoor temperature data at the first moment within the predetermined time period, the predicted outdoor temperature at any given moment within the predetermined time period is determined; next, using the first ratio of the second predicted heat data at the first moment within the predetermined time period to the predicted outdoor temperature and the change in the ratio between the change in the second predicted heat data at adjacent moments and the change in the predicted outdoor temperature, the second ratio is determined; finally, based on the heat data at the moment preceding any given moment within the predetermined time period, the second ratio at any given moment, and the change in the predicted outdoor temperature between any given moment and the moment preceding any given moment, the first predicted heat data at any given moment within the predetermined time period is determined.

[0040] Specifically, the change in heat data at the first moment can be the difference between the heat data at a moment before the predetermined time period and the heat data at the first moment within the predetermined time period. Furthermore, the moments within the predetermined time period are ordered chronologically, i.e., by time of day, namely the first moment, the second moment, and so on up to the nth moment.

[0041] Furthermore, in determining the second predicted heat data at any time within a predetermined time period, as an optional embodiment of the present invention, the reciprocal of the sorting value at any time within the predetermined time period is first calculated, and the first product of the reciprocal and the change in heat data at the first time period is calculated; then, the first sum between the first product and the heat data at the first time period is determined to be the second predicted heat data at any time within the predetermined time period.

[0042] Specifically, embodiments of the present invention can use the following formula to calculate the second predicted heat data at any time within a predetermined time period:

[0043]

[0044] In the formula for calculating the second predicted heat data, Q(t) n ) 历史 This represents the value of the predicted heat data at the nth time point within the predetermined time period, i.e., the second predicted heat data. Q(t1) represents the value of the historical heat data at the 1st time point within the predetermined time period. ΔQ(t1) represents the change in the historical heat data at the 1st time point within the predetermined time period. This represents the correlation between the change in historical heat data at time n within the extracted predetermined time period and the change in historical heat data at time 1. This represents the change in historical heat data at time n within a predetermined time period. The logic of this formula is to represent the value of the historical heat data at time n within the predetermined time period as the sum of the value of the historical heat data at time 1 and the change in the historical heat data at time n.

[0045] In the formula for calculating the predicted heat data value at time n, n represents the nth time. The larger n is, the greater the time interval between time n and time 1, meaning the greater the distance between the data at the two times. Since heat data is time-series data that changes over time, it can be further explained that the smaller the influence of the change in historical heat data at time n within the predetermined time period on the change in historical heat data at time 1 within the predetermined time period, the smaller the correlation between the two changes. Therefore, n and the correlation assignment are negatively correlated. To ensure the rationality of the calculation relationship between the correlation assignment and the predicted heat, the reciprocal of n is used as the correlation assignment between the two. The smaller n is, the lower the correlation value. The larger the value, the greater the correlation value.

[0046] Furthermore, the method described in this embodiment of the invention represents the daily variation trend of heat data within a day using the daily variation characteristics of heat data. Abnormal heat data is located by comparing the difference between the original change in heat data and the predicted change in heat data. Although this eliminates interference from the inherent variation characteristics of the heat data itself, it is difficult to rule out the interference caused by temperature fluctuations due to weather conditions. Analysis reveals that drastic changes in external ambient temperature within a short period, such as cold waves or sudden temperature increases, directly affect the building's heat demand. For every degree the outdoor temperature drops, the heat data increases by a corresponding amount, and as time increases, the correlation between the change in outdoor temperature and the initial change becomes increasingly weaker. Figure 2 As shown, Figure 2 This is a schematic diagram illustrating the change of outdoor temperature data and corresponding heat data over time, as provided in one embodiment of the present invention. From... Figure 2 It can be seen that whenever the outdoor temperature decreases, the heat data increases, and when the outdoor temperature rises, the heat data decreases. Therefore, it can be concluded that there is heat exchange between indoor and outdoor temperatures. Since the rise and fall of the outdoor temperature causes changes in the indoor temperature, it in turn affects the changes in the heat data. That is, the changes in heat data and outdoor temperature data are synchronized. Specifically, a decrease in outdoor temperature by a certain degree will result in a corresponding increase in the heat data.

[0047] Furthermore, in determining the predicted outdoor temperature at any given moment within a predetermined time period, as an optional embodiment of the present invention, the reciprocal of the first difference between the sorted value at any given moment within the predetermined time period and the predetermined value is first calculated, as well as the second product between the reciprocal of the first difference and the change in the outdoor temperature data at the first moment; then, the second sum between the second product and the outdoor temperature data at the first moment is determined to be the predicted outdoor temperature at any given moment within the predetermined time period.

[0048] Specifically, in this embodiment of the invention, the predetermined value can be determined according to the actual situation, and in this embodiment, the value is 1. Specifically, this embodiment of the invention uses the following formula to calculate the predicted outdoor temperature at any time within a predetermined time period.

[0049]

[0050] In the formula for predicting outdoor temperature, T 外，m This represents the outdoor temperature data at the m-th time within the predicted time period, i.e., the predicted outdoor temperature. T 外，1 This represents the outdoor temperature data at the first moment within a predetermined time period. ΔT 外，1This indicates the change in outdoor temperature data at the first moment within a predetermined time period. This represents the correlation between the change in outdoor temperature data at time m and the change in outdoor temperature data at time 1. In this embodiment of the invention, the logic of this formula is to express the outdoor temperature data at time m within a predetermined time period as the sum of the changes in outdoor temperature data at time 1 and time m within the predetermined time period.

[0051] Furthermore, for every degree the outdoor temperature decreases, the heat data increases by a corresponding amount. Moreover, as time increases, the ratio of the change in outdoor temperature to the change in heat data at the same time point exhibits a decreasing correlation with the initial ratio over time. Specifically, the ratio of the change in outdoor temperature to the change in heat data at the same time point is calculated using... Indicated by ΔQ m This represents the change in heat data at time m within a predetermined time period. ΔT m This represents the change in outdoor temperature data at time m within a predetermined time period, i.e., ΔT. m Based on the predicted outdoor temperature T at time m in the above embodiments of the present invention 外，m The predicted outdoor temperature T at time m-1 外，m-1 The difference is obtained by subtraction, i.e., ΔT m =T 外，m -T 外，m-1 B m This represents the second ratio between the change in heat data at time m within a predetermined time period and the change in outdoor temperature data.

[0052] Furthermore, in this embodiment of the invention, the second ratio is quantified in the following way: first, the reciprocal of the second difference between the sorted value at any time within a predetermined time period and the predetermined value is calculated, and the third product is calculated between the reciprocal of the second difference and the change in the ratio between the change in the second predicted heat data and the change in the predicted outdoor temperature at adjacent times; then, the third sum between the second predicted heat data at the first time within the predetermined time period and the third product is determined to be the second ratio.

[0053] Specifically, the second ratio is expressed by the following formula in the embodiments of the present invention:

[0054]

[0055] In the formula for calculating the second ratio, B mThis represents the ratio between the change in heat data at time m within a predetermined time period and the change in outdoor temperature data. B1 represents the ratio between the change in heat data at time 1 and the change in outdoor temperature data. ΔB2 represents the difference between the ratio between the ratio between the change in heat data at time 2 and the ratio between the ratio between the change in heat data at time 1 and the change in outdoor temperature data. The correlation assignment is given to the change in the ratio between the change in heat data at time m and the change in outdoor temperature data, and the change in the ratio between the change in heat data at time 1 and the change in outdoor temperature data.

[0056] It should be noted that the calculation principle of m in the formula for predicting outdoor temperature and the second ratio is the same as that of n in the formula for predicting the second heat data. Therefore, the calculation principle of m will not be analyzed again here.

[0057] Furthermore, when performing anomaly analysis on heat data, analyzing heat data alone would include changes in heat data caused by changes in outdoor temperature. However, the method described in this embodiment of the invention uses the change characteristics between outdoor temperature data and heat data to represent the relationship between them as a ratio. Therefore, based on this ratio, the predicted heat data at a certain moment within a predetermined time period is updated. In one optional embodiment of the invention, firstly, based on the heat data at a moment before any moment within the predetermined time period, the second ratio at any moment, and the change in predicted outdoor temperature between any moment and the moment before any moment, the first predicted heat data at any moment within the predetermined time period is determined by: then calculating the fourth product between the second ratio at any moment and the change in predicted outdoor temperature between any moment and the moment before any moment; finally, determining the fourth sum between the fourth product and the heat data at the moment before any moment within the predetermined time period as the first predicted heat data at any moment within the predetermined time period.

[0058] Specifically, in this embodiment of the invention, the first predicted heat data at any given moment within a predetermined time period is calculated using the following formula:

[0059] Q 历史，m =Q m-1 +B m ×ΔT m

[0060] In the above formula, Q 历史，m Q represents the first predicted heat data at the m-th time point within a predetermined time period. m-1This is the value of the heat data at the (m-1)th time point within the predetermined time period. B m This represents the ratio between the change in heat data at time m within a predetermined time period and the change in outdoor temperature data. ΔT m Based on the predicted outdoor temperature T at time m in the above embodiments of the present invention 外，m The predicted outdoor temperature T at time m-1 外，m-1 The difference is obtained by subtraction, i.e., ΔT m =T 外，m -T 外，m-1 The logic of this formula is that, taking into account the influence of outdoor temperature changes, the historical value of the heat data at the m-th moment within a predetermined time period is expressed as the sum of the historical value of the heat data at the (m-1)-th moment within the predetermined time period and the change in the heat data at the m-th moment.

[0061] S104, determine the value of the initial abnormal heat data based on the change in heat data between the target time and the previous time adjacent to the target time and the change between the first predicted heat data within the predetermined time period.

[0062] Specifically, in this embodiment of the invention, the difference between the actual real-time heat data and the first predicted heat data predicted in the above embodiment is used to represent the difference between the actual heat data and the original heat data, thereby reflecting the degree of abnormality of the actual heat data. In determining the initial value of the abnormal heat data, as an optional embodiment of the invention, the absolute value of a third difference between the change in heat data between the target time and the previous time adjacent to the target time, and the change in the first predicted heat data, is first calculated; then, the absolute value of the third difference is normalized to obtain the initial value of the abnormal heat data.

[0063] Specifically, taking the target time as the t-th time as an example, this embodiment of the invention uses the following formula to calculate the initial abnormal heat data assignment:

[0064] f t =norm|ΔQ 实际，t '-ΔQ 历史，t '|

[0065] In the above formula, f t This indicates the initial abnormal heat data at time t, representing the magnitude of the abnormal heat data. ΔQ 实际，t ' represents the change in heat data at time t compared to the heat data at the previous time t. ΔQ 历史，t This represents the change in heat data at time t compared to the heat data at the previous time, predicted using the relationship feature. |ΔQ 实际，t '-ΔQ历史，t '| represents the difference between the changes in these two heat data points, and norm indicates the difference between |ΔQ and |ΔQ|. 实际，t '-ΔQ 历史，t Normalize | if |ΔQ 实际，t '-ΔQ 历史，t The larger | is, the more f t The larger the value, the greater the value assigned to indicate that the heat data is abnormal.

[0066] S105, if the assigned value is greater than the first threshold, the initial abnormal heat data is determined to be the actual abnormal heat data.

[0067] Specifically, the first threshold can be determined according to the actual situation; in this embodiment of the invention, it is set to 0.8. When the initial abnormal heat data is assigned the value f... t If the value is greater than 0.8, then the heat data can be considered as actual abnormal heat data.

[0068] This invention utilizes the relationship between heat data and outdoor temperature data in a heating system to locate abnormal heat data and identify abnormal changes in heat data caused by temperature drops due to weather anomalies. Specifically, it first preliminarily identifies abnormal heat data that is outside the normal range. Then, based on the correspondence between heat data and outdoor temperature, it predicts the heat data for each time period. The preliminarily identified abnormal heat data is then assigned a value based on the predicted heat data and the preliminarily identified abnormal heat data. If this value is greater than a first threshold, the initial abnormal heat data is determined to be genuine abnormal heat data, rather than abnormal heat data caused by temperature changes in the external environment. Thus, by employing the technical solution provided by this invention, the accuracy of heat monitoring in heating network metering data is improved, and the fault detection rate in the heating system is increased.

[0069] Furthermore, a heat data threshold can be determined based on actual abnormal heat data to determine whether the real-time heat data is abnormal. As an optional embodiment of the invention, the actual abnormal heat data are clustered to obtain multiple first clusters; the first clusters are merged according to the distance between their centers to obtain second clusters; the center of the second cluster is used as a second threshold; when the real-time heat data of the heating system exceeds the second threshold, the real-time heat data is determined to be abnormal and an alarm is issued.

[0070] Specifically, when merging the first clusters according to the distance between their centers, the two clusters containing the closest centers can be merged to obtain the second cluster center, which can be the average of the two cluster centers. If the real-time heat data in the heating system exceeds this second threshold, the real-time heat data is determined to be abnormal, and an alarm is issued to remind maintenance personnel to inspect and repair it.

[0071] Example 2:

[0072] Corresponding to the heating network metering data monitoring method provided in the above embodiments, based on the same technical concept, this embodiment of the invention also provides a heating network metering data monitoring system, which is used to execute the above-described heating network metering data monitoring method. Figure 3 This is a schematic diagram of the structure of a heating network metering data monitoring system according to an embodiment of the present invention, as shown below. Figure 3 As shown. The heating network metering data monitoring system can vary significantly due to differences in configuration or performance. It may include one or more processors 301 and memory 302. The memory 302 stores computer programs that can run on the processor 301. The processor 301 executes the programs stored in the memory 302 to achieve the above... Figure 1 The various steps in the method embodiment are described. The memory 302 can be temporary or persistent storage. The application program stored in the memory 302 may include one or more modules (not shown in the figures), each module may include a series of computer-executable instructions for the heating network metering data monitoring system.

[0073] Furthermore, the processor 301 can be configured to communicate with the memory 302 and execute a series of computer-executable instructions stored in the memory 302 on the heating network metering data monitoring system. The heating network metering data monitoring system may also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input / output interfaces 305, and one or more keyboards 306.

[0074] Specifically, in this embodiment, the heating network metering data monitoring system includes a processor, a communication interface, a memory, and a communication bus; wherein, the processor, communication interface, and memory communicate with each other via the bus; the memory stores computer programs; and the processor executes the programs stored in the memory to achieve the above... Figure 1 The various steps in the method embodiments are the same as those in the above method embodiments, and have the same beneficial effects. To avoid repetition, the embodiments of the present invention will not be described again here.

[0075] It should be noted that the heating network metering data monitoring system provided in this embodiment of the invention and the heating network metering data monitoring method provided in this embodiment of the invention are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned heating network metering data monitoring method, and has the same or similar beneficial effects. Repeated parts will not be described again.

[0076] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0077] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for monitoring heating network metering data, characterized in that, The method for monitoring heating network metering data includes: Obtain heating network metering data of the heating system within a predetermined time period, wherein the heating network metering data includes heat data and outdoor temperature data corresponding to the heat data; Calculate the average value and standard deviation of the calorie data within the predetermined time period, and determine the normal range of the data based on the average value and the standard deviation. Determine the calorie data that exceeds the normal range as the initial abnormal calorie data. The first predicted heat data for any time within the predetermined time period is determined based on the heat data and outdoor temperature data at each time point within the predetermined time period. The value of the initial abnormal heat data is determined based on the change in heat data between the target time corresponding to the initial abnormal heat data and the previous time adjacent to the target time within the predetermined time period, as well as the change between the first predicted heat data. If the assigned value is greater than the first threshold, the initial abnormal heat data is determined to be actual abnormal heat data; The step of determining the first predicted heat data for any given moment within the predetermined time period based on the heat data and outdoor temperature data at each moment within the predetermined time period includes: Based on the heat data at the first moment within the predetermined time period and the change in the heat data at the first moment within the predetermined time period, determine the second predicted heat data at any moment within the predetermined time period, including: Calculate the reciprocal of the sort value at any given moment within the predetermined time period, and calculate the first product of the reciprocal and the change in the heat data at the first moment; The first sum between the first product and the heat data at the first moment is determined to be the second predicted heat data at any moment within the predetermined time period; Based on the outdoor temperature data at the first moment within the predetermined time period and the change in the outdoor temperature data at the first moment within the predetermined time period, the predicted outdoor temperature at any moment within the predetermined time period is determined. Using the first ratio of the second predicted heat data to the predicted outdoor temperature at the first moment within the predetermined time period, and the change in the ratio between the change in the second predicted heat data and the change in the predicted outdoor temperature at adjacent moments, a second ratio between the change in heat data and the change in outdoor temperature data at any moment within the predetermined time period is determined. Based on the heat data of a time preceding any time within the predetermined time period, the second ratio of that time, and the change in predicted outdoor temperature between that time and the time preceding that time, the first predicted heat data for any time within the predetermined time period is determined, including: Calculate the second ratio at any given time and the fourth product between the predicted change in outdoor temperature at any given time and the time preceding the given time; The fourth sum between the fourth product and the heat data at a time before any time within the predetermined time period is determined to be the first predicted heat data at any time within the predetermined time period; The step of determining the value of the initial abnormal heat data based on the change in heat data between the target time corresponding to the initial abnormal heat data and the previous time adjacent to the target time within the predetermined time period, and the change between the first predicted heat data, includes: Calculate the absolute value of a third difference between the change in heat data between the target time and the previous time adjacent to the target time and the change in the first predicted heat data; The absolute value of the third difference is normalized, and the normalized value is used as the initial abnormal heat data.

2. The heating network metering data monitoring method according to claim 1, characterized in that, The acquisition of heating network metering data of the heating system within the predetermined time period includes: The water supply temperature of the water supply pipe, the return water temperature of the return water pipe, the first flow rate in the water supply pipe, and the specific heat capacity of water in the heating system are obtained. Calculate the absolute value of the first difference between the supply water temperature and the return water temperature; The product of the first flow rate, the specific heat capacity, and the absolute value of the first difference is determined as the heat data.

3. The method for monitoring heating network metering data according to claim 1, characterized in that, Determining the predicted outdoor temperature at any point within the predetermined time period based on the outdoor temperature data at the first moment within the predetermined time period and the change in the outdoor temperature data at the first moment within the predetermined time period includes: Calculate the reciprocal of the first difference between the sorted value at any time within the predetermined time period and the predetermined value, and the second product between the reciprocal of the first difference and the change in the outdoor temperature data at the first time. The second sum between the second product and the outdoor temperature data at the first moment is determined to be the predicted outdoor temperature at any moment within the predetermined time period.

4. The heating network metering data monitoring method according to claim 1, characterized in that, The step of determining the second ratio between the change in heat data and the change in outdoor temperature at any point within the predetermined time period by using the first ratio of the second predicted heat data to the first predicted outdoor temperature at the first moment within the predetermined time period, and the change in the ratio between the change in the second predicted heat data and the change in the predicted outdoor temperature at adjacent moments, includes: Calculate the reciprocal of the second difference between the sorted value at any time within the predetermined time period and the predetermined value, and the third product between the reciprocal of the second difference and the change in the ratio between the change in the second predicted heat data and the change in the predicted outdoor temperature at adjacent times; The third sum between the second predicted heat data at the first moment within the predetermined time period and the third product is determined to be the second ratio.

5. The heating network metering data monitoring method according to claim 1, characterized in that, After determining that the initial abnormal heat data is actual abnormal heat data when the assigned value is greater than the first threshold, the method further includes: The actual abnormal heat data are clustered to obtain multiple first clusters; The first clusters are merged according to the distance between the centers of the first clusters of each first cluster to obtain the second cluster; The second cluster center of the second cluster is used as the second threshold. When the real-time heat data of the heating system exceeds the second threshold, the real-time heat data is determined to be abnormal and an alarm is issued.

6. A heating network metering data monitoring system, characterized in that, The heating network metering data monitoring system includes a processor and a memory; wherein the memory is used to store computer programs that can run on the processor; the processor is used to execute the programs stored in the memory to implement the steps of the heating network metering data monitoring method as described in any one of claims 1-5.

Images