Heating pipe network efficiency digital monitoring method based on internet of things
By constructing a heating stability index and a difference index, and combining sequence segmentation and smoothing algorithms, the operating status of the heating network is monitored in real time. This solves the problems of monitoring lag and error in existing technologies, and enables accurate assessment and early warning of the heating network, thereby improving the stability and efficiency of the heating system.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA NEW ERA INT ENG CORP
- Filing Date
- 2025-10-21
- Publication Date
- 2026-05-22
AI Technical Summary
Existing IoT-based methods for monitoring the efficiency of heating networks suffer from lag and errors, making it difficult to effectively predict heating anomalies and resulting in poor monitoring performance.
By constructing heating stability index, heating difference index, and heating anomaly index, and using flow, pressure, and temperature data, combined with sequence segmentation and smoothing algorithms, real-time monitoring and prediction are achieved to enable accurate assessment and early warning of heating networks.
It has improved the accuracy and predictive ability of heating network monitoring, reduced losses from sudden failures, enabled early warning of heating anomalies, and enhanced the stability and efficiency of the heating system.
Smart Images
Figure CN121346185B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of condition monitoring technology, specifically to a digital monitoring method for the efficiency of heating pipe networks based on the Internet of Things. Background Technology
[0002] In the current context of energy conservation and environmental protection, centralized heating systems are facing multiple pressures: energy saving and emission reduction, efficiency improvement, and ensuring stable heating supply. However, the development of Internet of Things (IoT) technology in recent years has provided technical support for the intelligent upgrading of heating systems. By deploying smart sensors at key nodes in the heating network and transmitting and analyzing data through IoT technology, remote monitoring of the network's operational status can be achieved. Monitoring the network's status can improve the reliability of heating supply.
[0003] Existing methods for monitoring the performance of heating pipe networks using IoT technology typically involve collecting network data from multiple smart sensors, calculating the difference between the data collected by sensors at both ends of the same pipe segment, and comparing this difference with a preset threshold to determine if there are any abnormalities in the network's heating status. However, while this method can monitor the heating status of the network, it remains at a reactive stage, and its monitoring accuracy is affected by the set threshold, exhibiting lag and significant errors, resulting in poor monitoring effectiveness. Summary of the Invention
[0004] To address the aforementioned technical issues, this application provides a digital monitoring method for heating network efficiency based on the Internet of Things (IoT) to resolve existing problems.
[0005] The IoT-based digital monitoring method for heating network efficiency in this application adopts the following technical solution:
[0006] One embodiment of this application provides a method for digital monitoring of heating network efficiency based on the Internet of Things (IoT), the method comprising the following steps:
[0007] Real-time acquisition of flow, pressure, and temperature data at both ends of each pipe in each heat exchange station of the heating network;
[0008] The entire monitoring time is divided into multiple acquisition cycles. Based on the dispersion of the flow difference and pressure difference between the two ends of each pipe in different time periods of the current acquisition cycle, and the similarity between all flow differences and all pressure differences between the two ends of each pipe in the current acquisition cycle, the heating stability index of each pipe in the current acquisition cycle is obtained.
[0009] Based on the differences in initial temperature between each pipe and its neighboring pipes during the current acquisition period, and the differences in heating stability index between each pipe and its neighboring pipes, the heating difference index of each pipe during the current acquisition period is obtained. Combined with the degree of change of the heating difference index of the corresponding pipes in the previous preset number of historical periods, and the heating stability index of each pipe during the current acquisition period, the heating anomaly index of each pipe during the current acquisition period is obtained. Then, the smoothing coefficient of each pipe in the current acquisition period is obtained, and the heating anomaly index of each pipe in the next acquisition period is predicted. Based on the obtained prediction values, it is determined whether each pipe will experience heating anomalies in the next acquisition period.
[0010] Preferably, the formula for calculating the heating stability index of each pipeline in the current collection cycle is: In the formula, This represents the heating stability index of the i-th pipeline in the current data collection cycle. It is the mean of the variances of all subsequences in the pressure difference value sequence of the i-th pipe in the current acquisition period; It is the mean of the variances of all subsequences in the flow difference sequence of the i-th pipe in the current collection period; The cosine similarity between the flow difference sequence and the pressure difference sequence of the i-th pipe in the current acquisition period; This is a preset constant.
[0011] Preferably, the process of obtaining the flow difference sequence and pressure difference sequence of each pipeline in the current acquisition period is as follows: the absolute difference between the flow data and the absolute difference between the pressure data at both ends of each pipeline at each time point are recorded as the flow difference and pressure difference of each pipeline at each time point; the flow difference and pressure difference of each pipeline at all times in the current acquisition period are arranged in chronological order to obtain the flow difference sequence and pressure difference sequence of each pipeline in the current acquisition period.
[0012] Preferably, the subsequences of the pressure difference sequence and flow difference sequence of each pipeline refer to the multiple subsequences obtained by dividing the pressure difference sequence and flow difference sequence of each pipeline separately using a sequence segmentation algorithm.
[0013] Preferably, the method for obtaining the heating difference index of each pipeline in the current collection cycle is as follows:
[0014] Obtain the location of the pipes at both ends of each pipe in each heat exchange station in the heating network, as well as the location of the heat exchange station;
[0015] With the heat exchange station as the center, construct a circle with the maximum value of the Euclidean distance between the positions of the pipes at both ends of each pipe and the position of the heat exchange station as the radius. Pipes whose positions at both ends are within the range of the circle are recorded as the nearest neighbor pipes of the corresponding pipes.
[0016] The average temperature data at both ends of each pipe at the same time is recorded as the temperature of each pipe. The temperatures of each pipe at all times in the current acquisition period are arranged in chronological order to obtain the temperature sequence of each pipe in the current acquisition period.
[0017] The temperature sequence of each pipe in the current acquisition period is divided into multiple subsequences. The mean of the absolute difference between each pipe and the mean temperature of the first subsequence of the temperature sequence of all its neighboring pipes in the current acquisition period is denoted as the pre-adjustment temperature difference degree of each pipe in the current acquisition period.
[0018] Calculate the mean of the absolute differences between the heating stability index of each pipeline and the heating stability index of all its neighboring pipelines.
[0019] The product of the pre-adjustment temperature difference and the mean value is recorded as the heating difference index of each pipeline in the current collection cycle.
[0020] Preferably, the formula for calculating the heating anomaly index of each pipeline in the current acquisition cycle is as follows: In the formula, This represents the heating anomaly index of the i-th pipeline in the current data collection period. This represents the slope difference of the i-th pipe in the current acquisition cycle. Let be the ratio of the heating difference index of the i-th pipeline in the current collection period to the maximum value of the heating difference index of its previous T historical periods, where T is the preset number of periods. Let be the heating stability index of the i-th pipeline in the current data collection period. This is a preset constant.
[0021] Preferably, the method for obtaining the slope difference of each pipeline in the current acquisition cycle is as follows: the heating difference index of each pipeline in the previous T historical cycles of the current acquisition cycle is arranged in chronological order and a straight line is fitted, and the slope of the fitted straight line is recorded as the first slope of each pipeline; the heating difference index of each pipeline in the current acquisition cycle and the previous T historical cycles is arranged in chronological order and a straight line is fitted, and the slope of the fitted straight line is recorded as the second slope of each pipeline, and the absolute difference between the second slope and the first slope of each pipeline is recorded as the slope difference of each pipeline in the current acquisition cycle.
[0022] Preferably, the formula for calculating the smoothing coefficient of each pipe in the current acquisition cycle is as follows: In the formula, Let be the smoothing coefficient for the i-th pipe in the current acquisition cycle. Let be the heating anomaly index of the i-th pipe in the current acquisition cycle, and exp() be an exponential function with the natural constant e as the base.
[0023] Preferably, the specific process of predicting the heating anomaly index of each pipeline in the next acquisition cycle is as follows: the heating anomaly index of each pipeline in the current acquisition cycle and the number of historical cycles before the preset number of cycles is used as the input of the triple exponential smoothing algorithm, and the smoothing coefficient of each pipeline in the current acquisition cycle is used as the smoothing coefficient to output the predicted value of the heating anomaly index of each pipeline in the next acquisition cycle.
[0024] Preferably, the specific process of determining whether each pipeline will experience heating anomalies in the next collection cycle based on the obtained predicted values is as follows: The predicted heating anomaly index values of all pipelines in the heating network in the next collection cycle are taken as 3... The input to the outlier detection algorithm is that if the predicted value of the heating anomaly index for any pipe is above 3... If the signal is outside the range, the pipeline is determined to have a heating abnormality in the next sampling cycle; otherwise, the pipeline is determined to have normal heating performance in the next sampling cycle.
[0025] This application has at least the following beneficial effects:
[0026] This application addresses the problems of lag and error in existing technologies that monitor heating network efficiency solely based on threshold values. It constructs a heating stability index to assess pipeline operational stability based on data differences between the two ends of the pipeline; a heating difference index to reflect the difference in heating effect between a pipeline and its neighboring pipelines, further evaluating heating network efficiency; and a heating anomaly index to reflect the deviation between current and historical data, obtaining a smoothing coefficient for each pipeline in the current acquisition cycle, improving the accuracy of subsequent heating anomaly index predictions for the next acquisition cycle. By assessing the heating status of the heating network using the predicted values for the next acquisition cycle, early warning of pipeline issues can be achieved, reducing losses caused by sudden failures and improving the monitoring effect of heating network efficiency. Attached Figure Description
[0027] To more clearly illustrate the technical solutions and advantages in the embodiments of 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 only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0028] Figure 1 A flowchart illustrating the steps of the IoT-based digital monitoring method for heating network efficiency provided in this application;
[0029] Figure 2 The process for obtaining the smoothing coefficients of each pipeline provided in this application during the current acquisition cycle. Detailed Implementation
[0030] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the IoT-based digital monitoring method for heating network efficiency proposed in this application. 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.
[0031] 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 application pertains.
[0032] The following description, in conjunction with the accompanying drawings, details the specific scheme of the IoT-based digital monitoring method for heating network efficiency provided in this application.
[0033] This application provides an embodiment of an IoT-based digital monitoring method for heating network efficiency. Specifically, the following IoT-based digital monitoring method for heating network efficiency is provided. Please refer to [link / reference]. Figure 1 The method includes the following steps:
[0034] Step 1: Obtain real-time data on flow rate, pressure, and temperature at both ends of each pipe in each heat exchange station of the heating network.
[0035] The heating network is a large distributed system containing multiple heat exchange stations and pipeline branches. This embodiment takes the i-th pipeline within the heating area of a heat exchange station as an example. At both ends of the i-th pipeline, at a distance of m meters (0.5 meters in this embodiment) from the port, flow meters, pressure transmitters, temperature sensors, and GPS locators are installed to collect flow, pressure, temperature, and pipeline location data. All sensors have wireless data transmission capabilities, and the collected data is then transmitted to the central management system of the heat exchange station for processing via IoT technology. Simultaneously, the location data of the heat exchange station is obtained through the GPS locator.
[0036] The absolute differences between the flow rate data and the absolute differences between the pressure data collected at both ends of the i-th pipe at the same time are recorded as the flow rate difference and pressure difference of the i-th pipe at the same time; the average temperature data at both ends of the i-th pipe at the same time is recorded as the temperature of the i-th pipe. In this embodiment, the acquisition interval for flow rate, pressure, and temperature data is 5 seconds, and each hour is considered a acquisition cycle; according to the temporal order of data acquisition, the flow rate difference sequence, pressure difference sequence, and temperature sequence of the i-th pipe in each acquisition cycle are constructed respectively.
[0037] Similarly, the flow rate difference sequence, pressure difference sequence, and temperature sequence of each pipeline within the heating area of the heat exchange station are obtained in each acquisition cycle. Since the locations of the heat exchange station and each pipeline are fixed, this embodiment only collects location data once.
[0038] To eliminate the influence of different dimensions between data, all data except location data are normalized. Normalization methods include Z-score, maximum value normalization, and maximum and minimum value normalization. This embodiment uses maximum and minimum value normalization.
[0039] Step 2: Divide the entire monitoring time into multiple acquisition cycles; based on the dispersion of the flow difference and pressure difference between the two ends of each pipe in different time periods of the current acquisition cycle, and the similarity between all flow differences and all pressure differences between the two ends of each pipe in the current acquisition cycle, obtain the heating stability index of each pipe in the current acquisition cycle.
[0040] Since heating pipes are usually laid underground, they are easily corroded by impurities in the soil. Furthermore, the long-term flow of hot water in the pipe network may cause impurities to accumulate. Therefore, heating pipe networks often face problems such as pipe corrosion and leakage, and local blockages, which in turn affect the heating efficiency of the heating system.
[0041] If the heating network has good heating efficiency and there are no abnormalities such as leaks or blockages, the data collected at both ends of the pipeline through IoT technology should be relatively consistent. However, if there are problems such as poor flow, local blockages, or leaks inside the pipeline, the data at both ends of the pipeline will show obvious differences.
[0042] However, considering that the flow rate of hot water and steam inside the heating network will change with the adjustment of the heating intensity, and that it takes time to travel from one end of the pipeline to the other due to its long length, the adjustment of the heating intensity will also lead to differences in the data collected at both ends of the pipeline, so further analysis is required.
[0043] Since future data needs to be predicted, the latest complete collection period is recorded as the current collection period. We will analyze the data collected by the i-th pipeline within the current collection period as an example.
[0044] If the data difference at both ends of the i-th pipe is caused by heating capacity adjustment, the data difference at both ends of the pipe would be small before the adjustment. During the adjustment, hot water and steam flow from one end to the other. Although there will be differences in the data at both ends of the pipe, the differences will be relatively consistent and stable because the flow rates of hot water and steam are stable after the adjustment. When the hot water and steam reach the other end, the data at both ends of the pipe will be consistent again. Therefore, if the pressure difference or flow rate difference of the i-th pipe is relatively consistent in different time periods, it indicates that the data change of the i-th pipe during this period is very likely caused by heating capacity adjustment.
[0045] The pressure difference sequence and flow difference sequence of the i-th pipeline in the u-th acquisition period are segmented using a sequence segmentation algorithm to obtain multiple subsequences. Then, the dispersion between elements within each segmented subsequence is calculated sequentially. The resulting dispersion can account for the differences caused by heating intensity adjustments, thus accurately reflecting whether there are any abnormalities in the pipeline's heating effect. The larger the value, the greater the change in the pressure difference or flow difference between the two ends of the pipeline, and thus the greater the possibility of abnormalities such as blockage or leakage within the pipeline. The sequence segmentation algorithm is not limited to the BG segmentation algorithm or the MK segmentation algorithm, and the calculation of dispersion is not limited to variance, coefficient of variation, and root mean square error. This embodiment uses the MK sequence segmentation algorithm and variance for processing.
[0046] Furthermore, if the heating efficiency of the heating network is stable and without abnormalities, the flow rate difference and pressure difference at both ends of the pipeline will be small and stable, indicating similarity between the two types of data. However, if abnormalities occur, the similarity between the two types of data will decrease. Therefore, calculating the cosine similarity between the flow rate difference sequence and the pressure difference sequence can reflect whether the changes in the flow rate difference and pressure difference at both ends of the pipeline are similar. The larger the value, the more consistent the changes, and the greater the likelihood of stable heating efficiency in the pipeline.
[0047] As a preferred implementation, the heating stability index of each pipeline in the current acquisition period is obtained based on the dispersion of the flow difference and pressure difference between the two ends of each pipeline in different time periods of the current acquisition period, as well as the similarity between all flow differences and all pressure differences between the two ends of each pipeline in the current acquisition period. This index is used to characterize the heating stability of each pipeline in the current acquisition period.
[0048] In this embodiment, the heating stability index of the i-th pipe in the current collection cycle is denoted as... Its specific expression is: In the formula, This represents the heating stability index of the i-th pipeline in the current data collection cycle. It is the mean of the variances of all subsequences in the pressure difference value sequence of the i-th pipe in the current acquisition period; It is the mean of the variances of all subsequences in the flow difference sequence of the i-th pipe in the current collection period; The cosine similarity between the flow difference sequence and the pressure difference sequence of the i-th pipe in the current acquisition period; As a preset constant, in order to avoid the denominator being 0, its value range is [0.005, 0.01]. The value has little impact on the calculation result and can be ignored. In this embodiment, it is taken as 0.008.
[0049] The heating stability index reflects the heating stability of the i-th pipeline in the current collection cycle. The larger the value, the more consistent the changes in the data difference between the two ends of the pipeline are, indicating that the pipeline is more likely to be operating stably and with good heating efficiency, and the less likely abnormal phenomena will occur.
[0050] Step 3: Based on the difference in initial temperature between each pipe and its neighboring pipes in the current acquisition cycle, and the difference in heating stability index between each pipe and its neighboring pipes, obtain the heating difference index of each pipe in the current acquisition cycle. Combined with the degree of change of the heating difference index of the corresponding pipes in the previous preset number of historical cycles, and the heating stability index of each pipe in the current acquisition cycle, obtain the heating anomaly index of each pipe in the current acquisition cycle. Then, obtain the smoothing coefficient of each pipe in the current acquisition cycle, and predict the heating anomaly index of each pipe in the next acquisition cycle. Based on the obtained prediction value, determine whether each pipe will experience heating anomalies in the next acquisition cycle.
[0051] Furthermore, while the heating network belongs to a centralized heating system, the heating areas of heat exchange stations are large, and the heat transmission distance within the network is long. If the heating efficiency of the network is poor, resulting in uneven heating, it may lead to overheating of pipes near the heat exchange station and insufficient heat in pipes far from the station. This not only wastes energy but also affects the user experience. Therefore, by analyzing the differences between the i-th pipe and other pipes in the current data collection period, the stability of the heating network's heating efficiency can be further evaluated.
[0052] Before the heating intensity is adjusted, all pipelines in the same heating area are operating in a steady state. At this time, if the heating and insulation efficiency of the heating network is good and the heating is uniform, the temperature of all pipelines collected by IoT technology within the distance range between the i-th pipeline and the heat exchange station should be relatively consistent, and the difference will not be too large.
[0053] In the geographic coordinate system, calculate the Euclidean distances between the positions of the i-th pipe at both ends and the position of the heat exchange station, and take the maximum of the two Euclidean distances as the limiting distance between the heat exchange station and the i-th pipe. Construct a circle with the heat exchange station as the center and the limiting distance as the radius, and denote the pipes whose positions at both ends are within the circle as the nearest neighbor pipes of the i-th pipe.
[0054] The temperature sequence of the i-th pipe and all its neighboring pipes in the current acquisition period is segmented by a sequence segmentation algorithm. Then, the first temperature subsequence after segmentation of each temperature sequence is obtained, and the mean of the elements of the first temperature subsequence of each pipe is recorded as the pre-adjustment average temperature of each pipe in the current acquisition period.
[0055] The mean of the absolute differences between the i-th pipe and the average pre-adjustment temperature of all neighboring pipes in the current sampling period is calculated and denoted as the pre-adjustment temperature difference degree of the i-th pipe in the current sampling period. The pre-adjustment temperature difference degree reflects the degree of temperature difference between the i-th pipe and all neighboring pipes before the heating intensity adjustment; the larger the value, the greater the possibility of uneven heating in the heating network or abnormalities in the heating pipes.
[0056] Furthermore, following the calculation method for the heating stability index of the i-th pipe in the current acquisition cycle, the heating stability index of each of its neighboring pipes in the current acquisition cycle is calculated. Then, the mean of the absolute differences between the heating stability index of the i-th pipe and the heating stability indices of all its neighboring pipes is calculated. The obtained mean can reflect whether the i-th pipe will have a significant difference in heating stability with its neighboring pipes in the same acquisition cycle. The larger the value, the greater the difference in heating stability, and the greater the possibility of the i-th pipe having unstable heating.
[0057] As a preferred implementation, the heating difference index of each pipe in the current acquisition cycle is obtained based on the difference between the initial temperature of each pipe and its neighboring pipes in the current acquisition cycle, as well as the difference in the heating stability index between each pipe and its neighboring pipes. This index is used to characterize the possibility of heating anomalies occurring in each pipe in the current acquisition cycle.
[0058] In this embodiment, the heating difference index of the i-th pipe in the current collection cycle is denoted as... Its specific expression is: In the formula, This represents the heating difference index for the i-th pipeline in the current data collection period. This represents the pre-adjustment temperature difference of the i-th pipe in the current acquisition cycle; It is the average of the absolute differences between the heating stability index of the i-th pipe and all its neighboring pipes in the current collection period.
[0059] The heating difference index reflects the difference in heating temperature and heating stability between the i-th pipe and its neighboring pipes in the current collection period. The larger the value, the greater the difference, which indicates that the heating network is more likely to have uneven heating or heating abnormalities in the current collection period, and the heating efficiency may be worse.
[0060] Furthermore, by combining historical data, the heating efficiency of the heating network can be monitored more accurately.
[0061] The heating difference index of the i-th pipe is obtained for the previous T (96 in this embodiment) historical periods in the current sampling period. The heating difference indices of the previous T historical periods (excluding the current sampling period) are arranged in chronological order, and then a linear fit is performed. The slope of the fitted line is recorded as the first slope of the i-th pipe. The first slope can reflect the continuous changing trend of the heating difference index of the i-th pipe in the T historical periods.
[0062] The heating difference index of the current collection period and its T preceding historical periods (including the current collection period) are arranged in chronological order and fitted with a straight line. The slope of the fitted line is denoted as the second slope of the i-th pipe, and the absolute difference between the second slope and the first slope is denoted as the slope difference of the i-th pipe in the current collection period. The slope difference reflects the impact of the heating difference index of the current collection period on the slope of the fitted line after being fitted. The larger the value, the greater the change in the trend of the heating difference index of the current collection period compared with the overall trend. The greater the possibility that the data of the i-th pipe in the current collection period has changed significantly, the less it conforms to the stable characteristics of heating efficiency, and the greater the possibility of anomalies.
[0063] Calculate the ratio of the heating difference index of the i-th pipeline in the current collection period to the maximum value of the heating difference index of its previous T historical periods. The obtained ratio can reflect whether the degree of heating difference of the i-th pipeline in the current collection period far exceeds the historical highest level; the larger the value, the greater the degree of abnormality of the i-th pipeline in the current collection period.
[0064] As a preferred implementation, the heating anomaly index of each pipeline in the current acquisition period is obtained based on the heating stability index and heating difference index of each pipeline in the current acquisition period, as well as the slope difference, and is used to characterize the possibility of heating anomalies in each pipeline in the current acquisition period.
[0065] In this embodiment, the heating anomaly index of the i-th pipe in the current acquisition cycle is denoted as... Its specific expression is: In the formula, This represents the heating anomaly index of the i-th pipeline in the current data collection period. This represents the slope difference of the i-th pipe in the current acquisition cycle. Let be the ratio of the heating difference index of the i-th pipeline in the current collection period to the maximum value of the heating difference index of its previous T historical periods, where T is the preset number of periods. Let be the heating stability index of the i-th pipeline in the current data collection period. This is a preset constant.
[0066] The heating anomaly index reflects the difference between the data of the i-th pipeline in the current collection period and the historical period data. The larger the value, the greater the difference, and thus the greater the possibility that there is a heating anomaly in the i-th pipeline in the current collection period.
[0067] Furthermore, a risk prediction and assessment is performed on the i-th pipeline based on the heating anomaly index to achieve early warning. The triple exponential smoothing algorithm is a classic data prediction algorithm; however, its prediction results are affected by the smoothing coefficient. A larger smoothing coefficient means the algorithm focuses more on predicting based on recent data; a smaller smoothing coefficient means the algorithm focuses more on predicting based on overall data. If the smoothing coefficient is not chosen appropriately, it will directly affect the prediction accuracy.
[0068] Based on the heating anomaly index of the i-th pipe in the current data collection period, the smoothing coefficient of the i-th pipe in the current data collection period is calculated. The specific formula is as follows: In the formula, Let be the smoothing coefficient for the i-th pipe in the current acquisition cycle. Let exp() be the heating anomaly index for the i-th pipe in the current acquisition period, and let exp() be an exponential function with the natural constant e as the base. The process for obtaining the smoothness coefficient of each pipe in the current acquisition period is as follows: Figure 2 As shown.
[0069] when The larger the value, the greater the data difference between the i-th pipe and its neighboring pipes in the current acquisition period, and the greater the difference between the data in the current acquisition period and the historical period data. In this case, it is more necessary to make predictions based on recent data. The smaller the value, the smaller the difference between the data of the i-th pipeline in the current collection period and the historical data, and the more accurate the prediction can be based on the overall data.
[0070] The heating anomaly index of the i-th pipe in the current acquisition period and the previous T historical periods is used as the input to the cubic exponential smoothing algorithm, and the calculated... As a smoothing coefficient, the predicted heating anomaly index value for the i-th pipe in the next acquisition cycle is output. Similarly, the predicted heating anomaly index values for all pipes in the next acquisition cycle can be obtained.
[0071] The predicted heating anomaly index values of all pipelines in the heating network in the next data collection cycle will be used as 3. The input to the outlier detection algorithm is: if the predicted heating anomaly index of the i-th pipe is within 3... If the data is outside the range, it is determined that the i-th pipe will experience abnormalities such as uneven heating or blockage in the next data collection cycle, requiring timely maintenance; otherwise, it is determined that the i-th pipe has normal heating efficiency in the next data collection cycle and no action is required.
[0072] In the same way, the heating efficiency of all pipes in the heating network in the next collection cycle is monitored, so as to provide early warning of heating anomalies and achieve accurate monitoring of the heating network efficiency.
[0073] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments of this specification have been described above. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.
[0074] 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.
[0075] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them; modifications to the technical solutions described in the foregoing embodiments, or equivalent substitutions of some of the technical features, do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.
Claims
1. A digital monitoring method for heating network efficiency based on the Internet of Things, characterized in that, The method includes the following steps: Real-time acquisition of flow, pressure, and temperature data at both ends of each pipe in each heat exchange station of the heating network; The entire monitoring time is divided into multiple acquisition cycles. Based on the dispersion of the flow difference and pressure difference between the two ends of each pipe in different time periods of the current acquisition cycle, and the similarity between all flow differences and all pressure differences between the two ends of each pipe in the current acquisition cycle, the heating stability index of each pipe in the current acquisition cycle is obtained. Based on the differences in initial temperature between each pipe and its neighboring pipes in the current acquisition period, and the differences in heating stability index between each pipe and its neighboring pipes, the heating difference index of each pipe in the current acquisition period is obtained. Combined with the degree of change of the heating difference index of the corresponding pipes in the previous preset number of historical periods, and the heating stability index of each pipe in the current acquisition period, the heating anomaly index of each pipe in the current acquisition period is obtained. Then, the smoothing coefficient of each pipe in the current acquisition period is obtained, and the heating anomaly index of each pipe in the next acquisition period is predicted. Based on the obtained prediction values, it is determined whether each pipe will experience heating anomalies in the next acquisition period. The formula for calculating the heating stability index of each pipeline in the current data collection period is as follows: In the formula, This represents the heating stability index of the i-th pipeline in the current data collection cycle. It is the mean of the variances of all subsequences in the pressure difference value sequence of the i-th pipe in the current acquisition period; It is the mean of the variances of all subsequences in the flow difference sequence of the i-th pipe in the current collection period; The cosine similarity between the flow difference sequence and the pressure difference sequence of the i-th pipe in the current acquisition period; This is a preset constant; The method for obtaining the heating difference index of each pipeline in the current collection period is as follows: Obtain the location of the pipes at both ends of each pipe in each heat exchange station in the heating network, as well as the location of the heat exchange station; With the heat exchange station as the center, construct a circle with the maximum value of the Euclidean distance between the positions of the pipes at both ends of each pipe and the position of the heat exchange station as the radius. Pipes whose positions at both ends are within the range of the circle are recorded as the nearest neighbor pipes of the corresponding pipes. The average temperature data at both ends of each pipe at the same time is recorded as the temperature of each pipe. The temperatures of each pipe at all times in the current acquisition period are arranged in chronological order to obtain the temperature sequence of each pipe in the current acquisition period. The temperature sequence of each pipe in the current acquisition period is divided into multiple subsequences. The mean of the absolute difference between each pipe and the mean temperature of the first subsequence of the temperature sequence of all its neighboring pipes in the current acquisition period is denoted as the pre-adjustment temperature difference degree of each pipe in the current acquisition period. Calculate the mean of the absolute differences between the heating stability index of each pipeline and the heating stability index of all its neighboring pipelines. The product of the pre-adjustment temperature difference and the mean value is recorded as the heating difference index of each pipeline in the current collection cycle; The formula for calculating the heating anomaly index of each pipeline in the current data collection period is as follows: In the formula, This represents the heating anomaly index of the i-th pipeline in the current data collection period. This represents the slope difference of the i-th pipe in the current acquisition cycle. Let be the ratio of the heating difference index of the i-th pipeline in the current collection period to the maximum value of the heating difference index of its previous T historical periods, where T is the preset number of periods. Let be the heating stability index of the i-th pipeline in the current data collection period. This is a preset constant.
2. The method for digital monitoring of heating network efficiency based on the Internet of Things as described in claim 1, characterized in that, The process of obtaining the flow difference sequence and pressure difference sequence of each pipeline in the current acquisition period is as follows: the absolute difference between the flow data and the absolute difference between the pressure data at both ends of each pipeline at each time point are recorded as the flow difference and pressure difference of each pipeline at each time point; the flow difference and pressure difference of each pipeline at all times in the current acquisition period are arranged in chronological order to obtain the flow difference sequence and pressure difference sequence of each pipeline in the current acquisition period.
3. The method for digital monitoring of heating network efficiency based on the Internet of Things as described in claim 2, characterized in that, The subsequences of the pressure difference sequence and flow difference sequence of each pipeline refer to the multiple subsequences obtained by dividing the pressure difference sequence and flow difference sequence of each pipeline separately using a sequence segmentation algorithm.
4. The method for digital monitoring of heating network efficiency based on the Internet of Things as described in claim 1, characterized in that, The method for obtaining the slope difference of each pipeline in the current acquisition period is as follows: the heating difference index of each pipeline in the previous T historical periods of the current acquisition period is arranged in chronological order and a straight line is fitted. The slope of the fitted line is recorded as the first slope of each pipeline. The heating difference index of each pipeline in the current acquisition period and the previous T historical periods is arranged in chronological order and a straight line is fitted. The slope of the fitted line is recorded as the second slope of each pipeline. The absolute difference between the second slope and the first slope of each pipeline is recorded as the slope difference of each pipeline in the current acquisition period.
5. The method for digital monitoring of heating network efficiency based on the Internet of Things as described in claim 1, characterized in that, The formula for calculating the smoothing coefficient of each pipeline in the current acquisition cycle is as follows: In the formula, Let be the smoothing coefficient for the i-th pipe in the current acquisition cycle. Let be the heating anomaly index of the i-th pipe in the current acquisition cycle, and exp() be an exponential function with the natural constant e as the base.
6. The method for digital monitoring of heating network efficiency based on the Internet of Things as described in claim 1, characterized in that, The specific process for predicting the heating anomaly index of each pipeline in the next acquisition cycle is as follows: the heating anomaly index of each pipeline in the current acquisition cycle and the number of historical cycles before the preset number of cycles is used as the input of the triple exponential smoothing algorithm, and the smoothing coefficient of each pipeline in the current acquisition cycle is used as the smoothing coefficient to output the predicted value of the heating anomaly index of each pipeline in the next acquisition cycle.
7. The method for digital monitoring of heating network efficiency based on the Internet of Things as described in claim 1, characterized in that, The specific process for determining whether heating anomalies will occur in each pipeline in the next data collection cycle based on the obtained predicted values is as follows: The predicted heating anomaly index values of all pipelines in the heating network in the next data collection cycle are taken as 3... The input to the outlier detection algorithm is that if the predicted value of the heating anomaly index for any pipe is above 3... If the signal is outside the range, the pipeline is determined to have a heating abnormality in the next sampling cycle; otherwise, the pipeline is determined to have normal heating performance in the next sampling cycle.