An intelligent detection method for leakage of HVAC pipelines

Abstract

The present invention discloses an intelligent detection method for leakage of heating and ventilation pipes, belonging to the technical field of data processing. The method includes: obtaining monitoring data of preset indicators of the heating and ventilation pipes to be detected; setting weights of other data according to the correlation between other data and endpoint data in the monitoring data, and using the other data to fit the endpoint data according to the set weights to achieve constraint optimization of the endpoint data; performing denoising processing on the monitoring data after the constraint optimization of the endpoint data is completed; and realizing intelligent detection of leakage of the heating and ventilation pipes based on the denoised monitoring data. By adopting the solution of the present invention, the accuracy of leakage detection of heating and ventilation pipes can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to an intelligent detection method for leakage of heating and ventilation pipes. Background Art

[0002] Traditional methods for detecting leakage of heating and ventilation pipes often rely on manual inspections or fixed sensors. Such detection methods have problems such as limited detection range, slow response speed, and high false alarm rate, and cannot meet the requirements of remote, real-time, and accurate monitoring. With the development of artificial intelligence and Internet of Things technologies, intelligent detection technologies have been widely applied in the field of leakage monitoring of heating and ventilation pipes. The intelligent detection technology obtains sensor data, processes the data, and intelligently judges whether there is leakage in the heating and ventilation pipes, which can meet the requirements of remote, real-time, and accurate monitoring. However, when collecting pipeline monitoring data through sensors, the collected data often inevitably contains noise, and the existence of noise will cause problems such as false alarms or missed alarms, resulting in a low detection accuracy. Existing denoising algorithms are usually affected by the endpoint effect, and the denoising effect is not ideal. Summary of the Invention

[0003] The present invention provides an intelligent detection method for leakage of heating and ventilation pipes to solve the technical problem that the existing detection methods for leakage of heating and ventilation pipes have low detection accuracy due to the inability to effectively remove noise in the data.

[0004] To solve the above technical problems, the present invention provides the following technical solutions:

[0005] An intelligent detection method for leakage of heating and ventilation pipes, comprising:

[0006] Obtaining monitoring data of preset indicators of the heating and ventilation pipes to be detected;

[0007] Setting the weights of other data according to the correlation between other data and endpoint data in the monitoring data, and using the other data to fit the endpoint data according to the set weights to realize the constraint optimization of the endpoint data;

[0008] Performing denoising processing on the monitoring data after the constraint optimization of the endpoint data;

[0009] Based on the denoised monitoring data, realizing intelligent detection of leakage of heating and ventilation pipes.

[0010] Further, the setting the weights of other data according to the correlation between other data and endpoint data in the monitoring data, and using the other data to fit the endpoint data according to the set weights to realize the constraint optimization of the endpoint data includes:

[0011] Divide the monitoring data into intervals, dividing the monitoring data into multiple data intervals; among them, the endpoint data in the monitoring data is separately divided into an interval, denoted as the endpoint data interval;

[0012] Calculate the correlation between each data interval and the endpoint data interval;

[0013] According to the correlation, screen out the similar data intervals of the endpoint data interval from all data intervals;

[0014] Based on the correlation corresponding to each similar data interval, set the weight of each similar data interval;

[0015] According to the weights of the set similar data intervals, use the data in each similar data interval to fit the data in the endpoint data interval to complete the constraint optimization of the endpoint data.

[0016] Furthermore, the step of dividing the monitoring data into intervals, dividing the monitoring data into multiple data intervals, includes:

[0017] Determine the extreme values in the monitoring data; among them, the extreme values include maximum values and minimum values;

[0018] According to the distribution of the extreme values in the monitoring data, divide the monitoring data into intervals, and divide the data between adjacent extreme values into the same interval, so as to divide the monitoring data into multiple data intervals.

[0019] Furthermore, the calculation formula for calculating the correlation between each data interval and the endpoint data interval is:

[0020]

[0021] Among them, represents the endpoint data interval and the th data interval; represents the average amplitude of the data points in the endpoint data interval ; represents the th data interval in the average amplitude of the data points; represents the maximum amplitude of the data points in the endpoint data interval represents the th data interval in the maximum value of the amplitude of the data points; represents the minimum amplitude of the data points in the endpoint data interval represents the th data interval Indicates the endpoint data interval calculated by the dynamic time warping (DTW) algorithm The DTW value between the th data interval, Indicates the linear normalization function; Indicates a preset hyperparameter with a value greater than 0.

[0022] Furthermore, screening out the similar data intervals of the endpoint data intervals from all data intervals according to the correlation includes:

[0023] Clustering all data intervals through the hierarchical clustering algorithm to obtain multiple clustering clusters;

[0024] Calculating the mean value of the correlation corresponding to the data intervals in each clustering cluster;

[0025] Taking the data intervals in the clustering cluster with the largest mean value as the similar data intervals of the endpoint data intervals.

[0026] Furthermore, the formula for setting the weight of each similar data interval based on the correlation corresponding to each similar data interval is:

[0027]

[0028] Wherein, Indicates the weight of the th similar data interval; Indicates the endpoint data interval and the th similar data interval; Indicates the endpoint data interval and the th similar data interval; Indicates the number of similar data intervals; Indicates the th similar data interval and the Euclidean distance between the midpoint of the endpoint data interval and the midpoint of the

[0029] Furthermore, according to the weights of the set similar data intervals, using the data in each similar data interval to fit the data in the endpoint data interval to complete the constraint optimization of the endpoint data, including:

[0030] Taking the similar data interval with the largest weight as the reference interval, taking the other intervals except the reference interval in all similar data intervals as the fitting intervals, calculating the fitting amplitude of each data point in the endpoint data interval, and fitting the data in the endpoint data interval to complete the constraint optimization of the endpoint data;

[0031] Among them, the calculation formula for the fitting amplitude of each data point in the endpoint data interval is:

[0032]

[0033] Among them, represents the endpoint data interval in the th data point's fitting amplitude; represents the amplitude of the th data point in the reference data interval; represents the weight of the th fitting interval; represents the th in the th data point's amplitude in the fitting interval; represents the number of similar data intervals; represents a preset hyperparameter, and its value is greater than 0.

[0034] Furthermore, the preset index is the pressure value of the HVAC pipeline to be detected.

[0035] Furthermore, the denoising process for the monitoring data after completing the endpoint data constraint optimization includes:

[0036] Using the complementary ensemble empirical mode decomposition (CEEMD) algorithm to denoise the monitoring data after completing the endpoint data constraint optimization.

[0037] Furthermore, the intelligent detection of HVAC pipeline leakage based on the denoised monitoring data includes:

[0038] Comparing the denoised monitoring data with a preset threshold;

[0039] When the denoised monitoring data is less than the preset threshold, it is determined that the HVAC pipeline has leaked.

[0040] The beneficial effects brought by the technical solution provided by the present invention at least include:

[0041] By analyzing the original data, the present invention obtains the correlation of the changes in different data segments in the original data, then sets the weights of the data according to the correlation of the data, and further optimizes the constraints on the endpoint data according to the weights of the data, adds data, so that the endpoint data contains complete maximum and minimum points, so that when fitting the envelope line according to the extreme points, there will be no loss of data points, making its data change more in line with the change of the original data, thus overcoming the influence brought by the endpoint effect, effectively improving the denoising effect of the data, and further effectively improving the accuracy of HVAC pipeline leakage detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0043] Figure 1 It is a schematic flowchart of the execution process of the intelligent detection method for leakage of heating and ventilation pipes provided by the embodiments of the present invention;

[0044] Figure 2 It is a schematic flowchart of the process for optimizing the constraint of endpoint data provided by the embodiments of the present invention. Detailed implementation manners

[0045] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will further describe the embodiments of the present invention in detail with reference to the accompanying drawings.

[0046] This embodiment provides an intelligent detection method for leakage of heating and ventilation pipes. The execution process of this method is as Figure 1 shown and includes the following steps:

[0047] S1. Obtain the monitoring data of the preset indicators of the heating and ventilation pipes to be detected;

[0048] Among them, it should be noted that the main purpose of this embodiment is to analyze the monitoring data of the heating and ventilation pipes to determine whether the heating and ventilation pipes are leaking. For this reason, the pressure of the heating and ventilation pipes is selected as the monitoring index in this embodiment, that is, the pressure is monitored at different points of the pipe network. If an abnormal pressure drop is detected, it indicates that leakage may have occurred. Specifically, in this embodiment, intelligent pressure sensors are arranged at different points on the heating and ventilation pipes to obtain the pressure data at different points on the pipes, and the real-time collected pressure data is transmitted to the data processing system to provide a data basis for subsequent data processing steps.

[0049] S2. Set the weights of other data according to the correlation between other data and endpoint data in the monitoring data. According to the set weights, use other data to fit the endpoint data to achieve the constraint optimization of the endpoint data;

[0050] Among them, it should be noted that when judging whether a pipeline leaks based on monitoring data, since the data collected by sensors contains noise, and the noise will affect the accuracy of data recognition. Therefore, it is necessary to first denoise the obtained data. A major challenge in data denoising is how to retain the important features and information in the signal while removing the noise. Over-denoising may remove important signal details, while insufficient denoising cannot provide clean data. In addition, for a real-time monitoring system, the denoising algorithm needs to be fast enough and have high enough execution efficiency so as not to delay the response time of signal processing and leakage detection. For this reason, the complementary ensemble empirical mode decomposition (CEEMD) algorithm is selected as the denoising algorithm in this embodiment.

[0051] The complementary ensemble empirical mode decomposition (CEEMD) algorithm is a time series analysis method for processing non-linear and non-stationary signals. It is an improved version of the empirical mode decomposition (EMD) algorithm, aiming to overcome the mode mixing problem that may be encountered in the EMD decomposition process. To overcome mode mixing, the CEEMD algorithm adds a set of different white noise signals to the original signal in each iteration. By performing EMD decomposition on the signal ensemble containing random noise, a set of intrinsic mode functions (IMFs) can be obtained. Then, the corresponding IMFs of all the noise-assisted data sets are averaged to eliminate the influence of the noise. However, when decomposing the signal, it is usually affected by the endpoint effect. The endpoint effect refers to the artificially introduced oscillations or inaccurate pseudo-components that may appear at the beginning and end parts of the signal, which is particularly prominent when the signal length is limited. It will lead to an increase in the uncertainty of the edge region of the signal during signal decomposition, affecting the reliability of the analysis of the entire signal.

[0052] In order to overcome the influence brought by the endpoint effect, in this embodiment, by analyzing the original data, the correlation of the changes in different data segments in the original data is obtained, and then the weights of the data are set according to the data correlation, and then the endpoint data is constrained and optimized according to the weights of the data, so as to add data. Specifically, in this embodiment, as Figure 2 shown, the process of constraining and optimizing the endpoint data is as follows:

[0053] S21, divide the monitoring data into intervals, and divide the monitoring data into multiple data intervals; among them, the endpoint data in the monitoring data is separately divided into an interval, denoted as the endpoint data interval;

[0054] Specifically, the interval division method is: determine the extreme values in the monitoring data; among them, the extreme values include maximum values and minimum values; according to the distribution of the extreme values in the monitoring data, divide the monitoring data into intervals, and divide the data between adjacent extreme values into the same interval, so as to divide the monitoring data into multiple data intervals. Since the endpoint data only contains one extreme point, it is a separate data interval, denoted as the endpoint data interval.

[0055] S22, calculate the correlation between each data interval and the endpoint data interval;

[0056] Among them, the calculation formula for the correlation between each data interval and the endpoint data interval is:

[0057]

[0058] Among them, represents the endpoint data interval and the th data interval; represents the average amplitude of the data points in the endpoint data interval ; represents the th average amplitude of the data points in the data interval; represents the maximum amplitude of the data points in the endpoint data interval ; represents the th maximum value of the amplitudes of the data points in the data interval; represents the minimum amplitude of the data points in the endpoint data interval ; represents the th minimum value of the amplitudes of the data points in the data interval; the amplitude refers to the monitored value of the preset index, that is, the pressure value; represents the DTW value between the endpoint data interval and the th data interval calculated by the dynamic time warping (DTW) algorithm, represents the linear normalization function; is a preset hyperparameter, which is a number greater than 0 with a value of 1 or 0.1 or 0.01, etc.

[0059] represents the difference in amplitudes between the endpoint data interval and the th data interval. The greater the difference in the average amplitudes of the two data intervals, the greater the difference in the data change degree of the two data intervals, and thus the smaller the correlation; represents the difference in the maximum values between the endpoint data interval and the th data interval, represents the difference in the maximum values between the endpoint data interval and the The difference in the minimum value of each data interval. The smaller the extreme value difference, the more similar the ranges of the two data intervals are, and the more similar the reasons for data changes in the two data intervals are. At this time, the correlation between the two data intervals is greater. Therefore, the smaller the extreme value difference between the two intervals, the greater the correlation. Represents the endpoint data interval With the DTW value between the data intervals, which represents the difference between the two data intervals. The larger this value, the smaller the correlation.

[0060] S23. According to the correlation, similar data intervals of the endpoint data intervals are screened out from all data intervals;

[0061] Specifically, the screening method for similar data intervals of the endpoint data intervals is as follows: all data intervals are clustered through a hierarchical clustering algorithm to obtain multiple clustering clusters; among them, the number of clustering layers is set to 2; after clustering is completed, the mean value of the correlation corresponding to the data intervals in each clustering cluster is calculated; the data intervals in the clustering cluster with the largest mean value are used as the similar data intervals of the endpoint data intervals.

[0062] S24. Based on the correlation corresponding to each similar data interval, the weight of each similar data interval is set;

[0063] It should be noted that when processing endpoint data, since the endpoint data does not contain complete maximum or minimum points, inaccurate data fitting will occur during decomposition, resulting in errors when decomposing the data. Therefore, to avoid inaccurate denoising caused by the incompleteness of endpoint data, in this embodiment, the endpoint data is filled by analyzing the correlation between the endpoint data and other data intervals, so that the endpoint data contains complete maximum and minimum points, so that data points will not be lost when fitting the envelope line according to the extreme points. For this reason, in this embodiment, the weight of the similar data interval is obtained according to the difference between the similar data interval of the endpoint data interval obtained above and the endpoint data interval. The calculation formula for the weight of the similar data interval is as follows:

[0064]

[0065] Among them, Represents the weight of the th similar data interval; Represents the endpoint data interval and the th similar data interval; Represents the endpoint data interval and the Indicates the number of similar data intervals; Indicates the midpoint of the th similar data interval and the Euclidean distance between the midpoint of the endpoint data interval.

[0066] Indicates the endpoint data interval and the th similar data interval, and the proportion of the correlation between them in the entire data sequence. The larger the ratio, the more similar the data change in the current similar data interval is to the endpoint data. Multiplying by is because the closer the data in the two data intervals are, the more similar the reasons for the data change in the two data intervals may be. Therefore, the smaller the distance, the greater the weight needs to be.

[0067] S25. According to the weights of the set similar data intervals, use the data in each similar data interval to fit the data in the endpoint data interval to complete the constraint optimization of the endpoint data.

[0068] It should be noted that during the process of filling in the data in the endpoint data interval, it is necessary to perform data constraints on the endpoint data interval according to the weights of different similar data intervals, so that the filled data will not be distorted, and the data change in the filled endpoint data interval will be more in line with the change of the original data, so that when performing EMD decomposition on the data, the data can be better fitted. For this reason, the process of constraint optimization of the endpoint data in this embodiment is as follows:

[0069] Take the similar data interval with the largest weight as the reference interval, take all other intervals except the reference interval in all similar data intervals as the fitting intervals, calculate the fitting amplitude of each data point in the endpoint data interval, and fit the data in the endpoint data interval to complete the constraint optimization of the endpoint data;

[0070] Among them, the calculation formula for the fitting amplitude of each data point in the endpoint data interval is:

[0071]

[0072] Among them, indicates the fitting amplitude of the th data point in the endpoint data interval; indicates the amplitude of the th data point in the reference data interval, indicates the th weight of the fitting interval; indicates the th The amplitude of a data point; Indicates the number of similar data intervals.

[0073] Indicates the weight of the th fitting interval multiplied by the amplitude of the th data point in that interval, because the greater the weight, the more similar the interval is to the endpoint data interval. Therefore, when performing data fitting, the contribution degree of the data points in this interval should also be greater; amplitude difference between the th data point in the reference interval and the th data point in the th fitting interval, because in this embodiment, the similar data interval with the greatest similarity degree is used as the reference interval, and then the reference interval is constrained by the similarity between other similar data intervals and the endpoint data interval. Therefore, when fitting the endpoint data interval, it can better conform to the variation law of the original data. So, dividing by is to represent the difference between the reference interval and the corresponding data points of the th fitting interval. The smaller the difference degree, the greater the contribution degree of the

[0074] th fitting interval should be, that is, when performing data fitting, the influence of this fitting interval on the fitting value is greater.

[0075] S3. Denoise the monitored data after completing the endpoint data constraint optimization;

[0076] Specifically, after obtaining the fitting value of each data point in the endpoint data interval according to the above calculation, in this embodiment, the processed monitored data is recorded as the target data, and then the CEEMD algorithm is used to denoise the target data to obtain the denoised data; among them, the CEEMD algorithm is a prior art, so it will not be elaborated here.

[0077] S4. Realize the intelligent detection of the leakage of the HVAC pipeline based on the denoised monitored data;

[0078] Among them, the detection method adopted in this embodiment is: comparing the denoised monitored data with a preset threshold; when the denoised monitored data is less than the preset threshold, it is determined that the HVAC pipeline has leaked. Specifically, this embodiment sets the threshold . When it is monitored that the pressure data of the pipeline is less than

[0079] In summary, this embodiment provides an intelligent detection method for HVAC pipeline leakage. By analyzing the original data, the correlation of changes in different data segments in the original data is obtained. Then, the weights of the data are set according to the data correlation. Furthermore, the endpoint data is constrained and optimized based on the data weights, and data is added to make the endpoint data contain complete maximum and minimum points. Therefore, when fitting the envelope line based on the extreme points, the situation of data point loss will not occur, and the data change is more in line with the change of the original data, thus overcoming the influence brought by the endpoint effect, effectively improving the denoising effect of the data, and further effectively improving the accuracy of HVAC pipeline leakage detection.

[0080] In addition, it should be noted that the present invention can be provided as a method, a device, or a computer program product. Therefore, the embodiments of the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0081] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0082] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including an instruction device, and the instruction device implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks. These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0083] It should also be noted that in this text, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or terminal device including the said element.

[0084] Finally, it should be noted that the above is the preferred embodiment of the present invention. It should be pointed out that although the preferred embodiments of the present invention have been described, for those skilled in the art of this technology, once the basic creative concept of the present invention is known, several improvements and refinements can be made without departing from the principle of the present invention, and these improvements and refinements should also be regarded as the protection scope of the present invention. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

Claims

1. An intelligent detection method for leakage of HVAC pipes, characterized in that, Including: Obtain the monitoring data of the preset indicators of the HVAC pipeline to be detected; Set the weights of other data according to the correlation between other data and endpoint data in the monitoring data. According to the set weights, use other data to fit the endpoint data to achieve the constraint optimization of the endpoint data, including: Divide the monitoring data into intervals, and divide the monitoring data into multiple data intervals; among them, the endpoint data in the monitoring data is separately divided into an interval, denoted as the endpoint data interval; Calculate the correlation between each data interval and the endpoint data interval; According to the correlation, screen out the similar data intervals of the endpoint data interval from all data intervals; Based on the correlation corresponding to each similar data interval, set the weight of each similar data interval; According to the weights of each set similar data interval, use the data in each similar data interval to fit the data in the endpoint data interval to complete the constraint optimization of the endpoint data; Denoise the monitoring data after completing the constraint optimization of the endpoint data; Based on the denoised monitoring data, realize the intelligent detection of HVAC pipeline leakage; The calculation formula for calculating the correlation between each data interval and the endpoint data interval is: Among them, represents the endpoint data interval and the correlation between the th data intervals; represents the average amplitude of the data points in the endpoint data interval represents the average amplitude of the data points in the th data interval; represents the maximum amplitude of the data points in the endpoint data interval ; represents the maximum value of the amplitudes of the data points in the th data interval; represents the minimum amplitude of the data points in the endpoint data interval ; represents the minimum value of the amplitudes of the data points in the th data interval; The amplitude refers to the monitored value of the preset index; represents the DTW value between the endpoint data interval and the th data interval calculated by the dynamic time warping (DTW) algorithm, represents the linear normalization function; represents a preset hyperparameter whose value is greater than 0; According to the weights of each set similar data interval, use the data in each similar data interval to fit the data in the endpoint data interval to complete the constraint optimization of the endpoint data, including: Take the similar data interval with the largest weight as the reference interval, take the other intervals except the reference interval in all similar data intervals as the fitting intervals, calculate the fitting amplitudes of each data point in the endpoint data interval, and fit the data in the endpoint data interval to complete the constraint optimization of the endpoint data; Among them, the calculation formula for the fitting amplitude of each data point in the endpoint data interval is: in, Indicates the endpoint data interval The The fitted amplitude of the data points; Indicates the first The amplitude of the data point; Indicates The weights of the fitting intervals; Indicates The first The amplitude of the data point; Represents the number of similar data intervals; Represents the preset hyperparameter, whose value is greater than 0.

2. The intelligent detection method for leakage of heating and ventilation pipelines according to claim 1, wherein The dividing the monitoring data into intervals and dividing the monitoring data into multiple data intervals includes: Determine the extreme values in the monitoring data; among them, the extreme values include maximum values and minimum values; According to the distribution of the extreme values in the monitoring data, divide the monitoring data into intervals, and divide the data between adjacent extreme values into the same interval, so as to divide the monitoring data into multiple data intervals.

3. The intelligent detection method for leakage of heating and ventilation pipelines according to claim 1, characterized in that, The screening out the similar data intervals of the endpoint data interval from all data intervals according to the correlation includes: Cluster all data intervals through the hierarchical clustering algorithm to obtain multiple clustering clusters; Calculate the mean value of the correlation corresponding to the data intervals in each clustering cluster; Take the data intervals in the clustering cluster with the largest mean value as the similar data intervals of the endpoint data interval.

4. The intelligent detection method for leakage of heating and ventilation pipes according to claim 1, characterized in that, The formula for setting the weight of each similar data interval based on the correlation corresponding to each similar data interval is: Among them, represents the weight of the th similar data interval; represents the correlation between the endpoint data interval and the th similar data interval; represents the correlation between the endpoint data interval and the th similar data interval; represents the number of similar data intervals; represents the Euclidean distance between the midpoint of the th similar data interval and the midpoint of the endpoint data interval .

5. The intelligent detection method for leakage of heating and ventilation pipelines according to claim 1, characterized in that The preset indicator is the pressure value of the HVAC pipeline to be detected.

6. The intelligent detection method for leakage of heating and ventilation pipelines according to claim 5, wherein, The denoising the monitoring data after completing the constraint optimization of the endpoint data includes: Use the complementary ensemble empirical mode decomposition (CEEMD) algorithm to denoise the monitoring data after completing the constraint optimization of the endpoint data.

7. The intelligent detection method for leakage of heating and ventilation pipelines according to claim 6, characterized in that, The realizing the intelligent detection of HVAC pipeline leakage based on the denoised monitoring data includes: Compare the denoised monitoring data with a preset threshold; When the monitored data after denoising is less than the preset threshold, it is determined that there is a leakage in the HVAC pipeline.

Images