Water heating pipeline maintenance detection method and system

Abstract

The invention relates to the technical field of image data processing, in particular to a water heating pipeline maintenance detection method and system.The method comprises the steps that firstly, pipeline time sequence image data, pipeline feature image data, pipeline thermal imaging image data and pipeline common imaging data of an area, needing to be detected, in a floor heating water pipe in a building are collected; constructing a water heating pipeline image data set; secondly, identifying the water heating pipeline image data set by constructing a water heating pipeline abnormal state detection model to obtain a pipeline deformation abnormal coefficient, a pipeline texture abnormal coefficient and a pipeline temperature abnormal coefficient; and finally, according to the pipeline deformation abnormal coefficient, the pipeline texture abnormal coefficient and the pipeline temperature abnormal coefficient, generating a water heating pipeline abnormal coefficient through multi-modal data fusion. And the water heating pipeline is maintained according to the abnormal coefficient of the water heating pipeline, so that the maintenance efficiency of the water heating pipeline is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and in particular to a water heating pipeline maintenance detection method and system. Background Art

[0002] As an important part of the modern building heating system, the operating status of water and heating pipes has a vital impact on the heating effect and safety of the building. Due to factors such as long-term operation, changes in the external environment and material aging, water and heating pipes are prone to deformation, texture damage and temperature abnormalities. If these problems are not detected and maintained in time, they may lead to serious consequences such as reduced heating efficiency, water leakage and even pipe bursts, threatening building safety and increasing maintenance costs. Therefore, real-time monitoring and abnormality detection of the operating status of water and heating pipes has become an important research direction in the maintenance of building heating systems.

[0003] Existing plumbing pipe inspection methods mainly rely on manual inspection or single sensor measurement, such as manually observing changes in the pipe surface and using thermal imaging equipment to monitor temperature distribution. However, these methods have defects such as low detection accuracy, insufficient efficiency, and limited coverage, making it difficult to fully and accurately reflect the actual health status of the pipe. At the same time, due to the diversity and complexity of pipe surface texture changes, deformation characteristics, and temperature distribution, a single data source or detection technology is difficult to meet the needs of comprehensive evaluation.

[0004] Therefore, a water heating pipeline maintenance detection method and system are proposed. Summary of the invention

[0005] The object of the present invention is to provide a plumbing pipe maintenance and detection method and system. First, the pipe time-series image data, pipe feature image data, pipe thermal imaging image data and pipe general imaging data of the area to be detected in the heating water pipe in the building are collected to construct a plumbing pipe image data set; secondly, the plumbing pipe image data set is identified by constructing a plumbing pipe abnormal state detection model to obtain the pipe deformation abnormality coefficient, pipe texture abnormality coefficient and pipe temperature abnormality coefficient; finally, according to the pipe deformation abnormality coefficient, the pipe texture abnormality coefficient and the pipe temperature abnormality coefficient, the plumbing pipe abnormality coefficient is generated through multimodal data fusion; based on the plumbing pipe abnormality coefficient, the plumbing pipe is maintained.

[0006] To achieve the above object, the present invention provides the following technical solutions: Collect pipeline time-series image data, pipeline feature image data, pipeline thermal imaging image data and pipeline general imaging data of the area to be inspected in the heating water pipes in the building, and build a water heating pipe image data set; Constructing a plumbing pipe abnormal state detection model to identify the plumbing pipe image data set, and obtaining a pipe deformation abnormality coefficient, a pipe texture abnormality coefficient, and a pipe temperature abnormality coefficient; The pipeline deformation anomaly coefficient is obtained by identifying the pipeline time series image data through a local outlier factor algorithm; The pipeline texture anomaly coefficient is obtained by identifying the pipeline feature image data using a texture feature analysis method; The pipeline temperature anomaly coefficient is obtained by identifying the pipeline thermal imaging image data and the pipeline ordinary imaging data through data fusion technology; According to the pipeline deformation anomaly coefficient, the pipeline texture anomaly coefficient and the pipeline temperature anomaly coefficient, a water heating pipeline anomaly coefficient is generated through multimodal data fusion; the formula for the multimodal data fusion is: ; in, is the abnormal coefficient of water and heating pipes, is the weight of pipeline deformation anomaly coefficient, is the pipeline deformation anomaly coefficient, is the pipeline texture anomaly coefficient weight, is the pipeline texture anomaly coefficient, is the pipe temperature anomaly coefficient weight, is the pipeline temperature anomaly coefficient, ; The plumbing pipes are maintained according to the plumbing pipe abnormality coefficient.

[0007] Preferably, a historical image dataset of water and heating pipes is obtained to construct a water and heating pipe abnormal state detection model; The water heating pipeline abnormal state detection model includes a pipeline deformation abnormality module, a pipeline texture abnormality module and a pipeline temperature abnormality module; The pipeline deformation anomaly module obtains the deformation anomaly of the water heating pipeline in the detection area by identifying the pipeline time series image data in the water heating pipeline image data set; The pipeline texture anomaly module obtains the pipeline texture anomaly area by identifying the pipeline feature image data in the water heating pipeline image data set; The pipeline temperature anomaly module obtains pipeline temperature anomaly by identifying pipeline thermal imaging image data and pipeline common imaging data in the water heating pipeline image data set.

[0008] Preferably, the pipeline deformation anomaly module includes a first image preprocessing layer, a first feature extraction layer, an outlier factor calculation layer, an anomaly detection layer and a result output layer; The first image preprocessing layer generates preprocessed first pipeline time series image data by graying, denoising and aligning the pipeline time series image data; The first feature extraction layer constructs a first pipeline feature vector by extracting edge strength, local gradient change and structural similarity of each frame of image from the first pipeline time series image data; The outlier factor calculation layer analyzes the first pipeline time series image data using a local outlier factor algorithm based on the first pipeline feature vector to obtain a local outlier factor; The anomaly detection layer analyzes the local outlier factor and the local outlier factor threshold, identifies abnormal feature points and clusters and marks them as abnormal areas; The result output layer calculates and obtains the pipeline deformation anomaly coefficient by identifying the abnormal area.

[0009] Preferably, the pipeline texture anomaly module includes a second image preprocessing layer, a second feature extraction layer, an abnormal texture detection layer and a texture output layer; The second image preprocessing layer performs denoising, image segmentation and grayscale normalization on the pipeline characteristic image data to obtain first pipeline characteristic image data; The second feature extraction layer extracts local texture features, global texture features and detail texture features from the first pipeline feature image data to form a second pipeline feature; The abnormal texture detection layer classifies texture features through a support vector machine classification model to obtain the distribution characteristics of texture abnormal areas; The texture output layer identifies the distribution characteristics of the texture abnormality area and calculates and obtains the pipeline texture abnormality coefficient.

[0010] Preferably, the pipeline temperature anomaly module includes a third image preprocessing layer, a multimodal image registration layer, a feature extraction and fusion layer, and a temperature anomaly detection layer; The third image preprocessing layer performs denoising, contrast enhancement and normalization on the pipeline thermal imaging image data and the pipeline ordinary imaging data respectively, so as to obtain a preprocessed first thermal imaging image and a first ordinary imaging image; The multimodal image registration layer performs feature point matching on the preprocessed thermal imaging image and the ordinary imaging image to generate a multimodal image; The feature extraction and fusion layer extracts temperature gradient features from the thermal imaging image in the multimodal image, extracts geometric edge features from the common imaging image in the multimodal image, and generates a multimodal feature vector; The temperature anomaly detection layer performs analysis based on the multimodal feature vector and the standard pipeline multimodal feature vector to calculate and generate a pipeline temperature anomaly coefficient.

[0011] Preferably, the specific calculation formula of the pipeline deformation abnormal coefficient is: ; in, is the pipeline deformation anomaly coefficient, is the total number of abnormal feature points, Abnormal feature points The local outlier factor of is the preset local outlier factor threshold, Abnormal feature points The gradient strength, is the gradient strength of all abnormal feature points, Abnormal feature points The weight of The specific calculation formula of the pipeline texture anomaly coefficient is: ; in, is the pipeline texture anomaly coefficient, is the number of abnormal texture areas, For the The weight of local texture feature value in abnormal texture area, For the The local texture feature values ​​of abnormal texture areas, For the The global texture eigenvalue weight of the abnormal texture area, For the The global texture feature value of the abnormal texture area, For the The detail texture feature value weights of abnormal texture areas, For the Detailed texture feature values ​​of abnormal texture areas, is the confidence coefficient of the abnormal area of ​​pipeline texture; ; The specific calculation formula of the pipeline temperature anomaly coefficient is: ; in, is the pipeline temperature anomaly coefficient, is the number of detected temperature zones, For the The temperature gradient deviation value weight of each detection area, For the The actual measured temperature gradient of the detection area, For the The temperature gradient of the standard pipeline in the detection area, For the The geometric edge deviation weight of the detection area, For the The total number of edge points in the detection area, For the In the detection area The detection value of edge points, For the In the detection area The standard value of edge points, is the confidence coefficient of abnormal pipeline temperature area, .

[0012] A water and heating pipeline maintenance and detection system, comprising: A data acquisition unit collects pipeline time-series image data, pipeline feature image data, pipeline thermal imaging image data and pipeline general imaging data of the area to be inspected in the heating water pipes in the building, and constructs a water heating pipe image data set; A related abnormality coefficient acquisition unit is used to construct a plumbing pipe abnormal state detection model to identify the plumbing pipe image data set, and obtain a pipe deformation abnormality coefficient, a pipe texture abnormality coefficient, and a pipe temperature abnormality coefficient; The water heating pipeline abnormality coefficient acquisition unit generates the water heating pipeline abnormality coefficient through multimodal data fusion according to the pipeline deformation abnormality coefficient, the pipeline texture abnormality coefficient and the pipeline temperature abnormality coefficient; the formula of the multimodal data fusion is: ; in, is the abnormal coefficient of water and heating pipes, is the weight of pipeline deformation anomaly coefficient, is the pipeline deformation anomaly coefficient, is the pipeline texture anomaly coefficient weight, is the pipeline texture anomaly coefficient, is the pipe temperature anomaly coefficient weight, is the pipeline temperature anomaly coefficient, ; The plumbing pipes are maintained according to the plumbing pipe abnormality coefficient.

[0013] Preferably, the pipeline deformation anomaly coefficient is obtained by identifying the pipeline time series image data through a local outlier factor algorithm; The pipeline texture anomaly coefficient is obtained by identifying the pipeline feature image data using a texture feature analysis method; The pipeline temperature anomaly coefficient is obtained by identifying the pipeline thermal imaging image data and the pipeline ordinary imaging data through data fusion technology.

[0014] Preferably, the water heating pipeline abnormal state detection model includes a pipeline deformation abnormality module, a pipeline texture abnormality module and a pipeline temperature abnormality module; The pipeline deformation anomaly module obtains the deformation anomaly of the water heating pipeline in the detection area by identifying the pipeline time series image data in the water heating pipeline image data set; The pipeline texture anomaly module obtains the pipeline texture anomaly area by identifying the pipeline feature image data in the water heating pipeline image data set; The pipeline temperature anomaly module obtains pipeline temperature anomaly by identifying pipeline thermal imaging image data and pipeline common imaging data in the water heating pipeline image data set.

[0015] Preferably, the pipeline deformation anomaly module includes a first image preprocessing layer, a first feature extraction layer, an outlier factor calculation layer, an anomaly detection layer and a result output layer; The pipeline texture anomaly module includes a second image preprocessing layer, a second feature extraction layer, an abnormal texture detection layer and a texture output layer; The pipeline temperature anomaly module includes a third image preprocessing layer, a multimodal image registration layer, a feature extraction and fusion layer, and a temperature anomaly detection layer.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention constructs a water and heating pipeline abnormal state detection model, obtains the abnormal state of the water and heating pipeline by analyzing the deformation characteristics, texture characteristics and temperature anomalies of the water and heating pipeline; locates the abnormal deformation area of ​​the pipeline by identifying the deformation characteristics of the pipeline time series image data; effectively identifies the abnormal texture characteristics of the pipeline surface by texture analysis of the pipeline feature image data; quantitatively detects the temperature distribution anomaly of the pipeline by combining the multimodal registration and fusion of thermal imaging image data and ordinary imaging data; and improves the safety and maintenance efficiency of water and heating pipeline operation by adapting to different environments and detection requirements through multimodal data fusion technology.

[0017] 2. The pipeline deformation anomaly module of the present invention realizes accurate detection through multi-level processing. The pipeline time series image data preprocessing layer effectively reduces image noise and aligns images to improve image data quality; extracts key edge and gradient features from the preprocessed time series images to ensure the comprehensiveness of deformation features; the outlier factor calculation layer combines the local outlier factor algorithm to quantify abnormal feature points; finally, through clustering and regional labeling, the deformation anomaly is located and quantified, thereby improving the accuracy and reliability of deformation anomaly detection and providing a scientific basis for pipeline maintenance.

[0018] 3. The pipeline texture anomaly module of the present invention ensures that the data is clear and stable by denoising, image segmentation and grayscale normalization of the pipeline feature image data; enhances the accuracy of anomaly detection by extracting local, global and detailed texture features of the processed pipeline feature image; classifies the texture features using the support vector machine classification model to achieve accurate identification of abnormal areas; further, by quantifying the characteristics of the abnormal area, the texture anomaly coefficient is calculated, thereby improving the comprehensiveness and accuracy of texture anomaly detection.

[0019] 4. The pipeline temperature anomaly module of the present invention ensures image quality by denoising, contrast enhancement and normalization of pipeline thermal imaging and ordinary imaging data; the multimodal image registration layer fuses multi-source data to improve the matching accuracy of pipeline temperature features; the feature extraction and fusion layer fully extracts temperature gradients and geometric edge features to achieve multimodal feature vector construction; the temperature anomaly detection layer accurately calculates the temperature anomaly coefficient through multimodal feature analysis, thereby improving the accuracy and robustness of pipeline temperature anomaly detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of a flow chart of a water and heating pipeline maintenance and detection method provided by the present invention; Figure 2 A schematic diagram of the structure of a water and heating pipeline maintenance and detection system provided by the present invention; Figure 3 A schematic diagram of the structure of a water and heating pipeline abnormal state detection model provided by an embodiment of the present invention; Figure 4 A schematic diagram of an abnormal state of a water heating pipeline provided by an embodiment of the present invention.

[0021] In the picture: 1. Abnormal deformation of the plumbing pipe; 2. Abnormal texture of the plumbing pipe. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] See also Figure 1 The present invention provides a water heating pipeline maintenance and detection method, and the technical solution is as follows: Arrange industrial cameras around plumbing pipes to obtain pipe images; Reference Figure 1S10 in which pipe time-series image data, pipe feature image data, pipe thermal imaging image data and pipe general imaging data of the area to be inspected in the heating water pipes in the building are collected to construct a water heating pipe image data set; Reference Figure 1 In S20, a water heating pipe abnormal state detection model is constructed to identify the water heating pipe image data set to obtain a pipe deformation abnormality coefficient, a pipe texture abnormality coefficient, and a pipe temperature abnormality coefficient; Furthermore, a historical image dataset of water and heating pipes is obtained to construct a water and heating pipe abnormal state detection model; The abnormal state detection model of the water heating pipeline includes a pipeline deformation abnormality module, a pipeline texture abnormality module and a pipeline temperature abnormality module. Figure 3 ; The pipeline deformation anomaly module obtains the deformation anomaly of the plumbing pipeline in the detection area by identifying the pipeline time-series image data in the plumbing pipeline image data set; Figure 4 ,The water and heating pipe deformation anomaly 1 is analyzed and identified through the pipeline time series image data; The pipeline texture anomaly module obtains the pipeline texture anomaly area by identifying the pipeline feature image data in the water heating pipeline image data set; Figure 4 ,The water and heating pipe texture anomaly 2 is identified through the pipe feature image; The pipeline temperature anomaly module obtains pipeline temperature anomaly by identifying pipeline thermal imaging image data and pipeline common imaging data in the water heating pipeline image data set.

[0024] In this embodiment, the industrial camera obtains the pipeline time-series image data, pipeline feature image data, pipeline thermal imaging image data and pipeline general imaging data of the water and heating pipeline, and analyzes the water and heating pipeline image data through the water and heating pipeline abnormal state detection model. In addition, this embodiment also uses two other models to analyze the water and heating pipeline image data, each model is repeated 3 times, and the accuracy of the abnormal area of ​​the water and heating pipeline is calculated. The specific results are shown in Table 1.

[0025] Model 1 is the abnormal state detection model for water heating pipes proposed by the present invention; Model 2 is based on Model 1 without adding temperature anomaly recognition; Model 3 is based on Model 1 and only analyzes texture anomalies. It can be seen from Table 1 that the abnormal state detection model for water heating pipes provided in this embodiment can effectively improve the safety of water heating pipes.

[0026] Table 1 Comparison of the accuracy of pipeline abnormal areas of different models

[0027] In this embodiment, by constructing a water and heating pipeline abnormal state detection model, multi-dimensional accurate recognition of pipeline deformation, texture and temperature anomalies is achieved. The pipeline deformation anomaly module captures deformation features based on time series images, the pipeline texture anomaly module extracts texture features to locate abnormal areas, and the pipeline temperature anomaly module integrates thermal imaging and ordinary imaging data to detect temperature anomalies. Multi-module collaboration improves detection accuracy and efficiency, and provides reliable support for early warning and maintenance decisions of pipeline abnormalities.

[0028] Further, the pipeline deformation anomaly module includes a first image preprocessing layer, a first feature extraction layer, an outlier factor calculation layer, an anomaly detection layer and a result output layer; The first image preprocessing layer generates preprocessed first pipeline time series image data by graying, denoising and aligning the pipeline time series image data; The first feature extraction layer constructs a first pipeline feature vector by extracting edge strength, local gradient change and structural similarity of each frame of image from the first pipeline time series image data; The outlier factor calculation layer analyzes the first pipeline time series image data using a local outlier factor algorithm based on the first pipeline feature vector to obtain a local outlier factor; The local outlier factor calculation formula is: ; in, For feature points The local outlier factor of is the feature point, For feature points of Neighbor set, For feature points The local reachable density of For feature points The local reachable density of For feature points The number of all neighbors of For feature points With feature points The reachable distance, is the maximum value function, For feature points With feature points The Euclidean distance of For feature points To its The distance to the nearest neighbor; The anomaly detection layer analyzes the local outlier factor and the local outlier factor threshold, identifies abnormal feature points and clusters and marks them as abnormal areas; When the local outlier factor is greater than the local outlier factor threshold, the feature point at this time is taken as an abnormal feature point; the local outlier factor threshold is obtained by training historical water and heating pipeline data; The result output layer calculates and obtains the pipeline deformation anomaly coefficient by identifying the abnormal area.

[0029] In this embodiment, the pipeline deformation anomaly module is used to accurately detect the pipeline deformation features, graying, denoising and alignment processing are used to improve the image quality, and the feature vector is constructed by combining edge strength, local gradient change and structural similarity. The local outlier factor algorithm is used to accurately calculate the abnormal feature points and cluster the abnormal areas. The threshold is trained by historical data to improve the detection sensitivity and adaptability, so as to efficiently generate the pipeline deformation anomaly coefficient, providing a scientific basis for early warning and maintenance of deformation faults.

[0030] Further, the pipeline texture anomaly module includes a second image preprocessing layer, a second feature extraction layer, an abnormal texture detection layer and a texture output layer; The second image preprocessing layer performs denoising, image segmentation and grayscale normalization on the pipeline characteristic image data to obtain first pipeline characteristic image data; The second feature extraction layer extracts local texture features, global texture features and detail texture features from the first pipeline feature image data to form a second pipeline feature; The local texture features are extracted by local binary patterns, and the local texture patterns around each pixel are extracted to reflect the roughness of the local area; the global texture features are extracted by gray-level co-occurrence matrix, and the co-occurrence relationship of pixel gray levels in the image is calculated to extract texture features such as contrast, correlation, and entropy; the detail texture features are extracted by multi-resolution wavelet transform, and the image is decomposed into frequency components of different scales to extract detail texture features; The abnormal texture detection layer classifies texture features through a support vector machine classification model to obtain the distribution characteristics of texture abnormal areas; The texture output layer identifies the distribution characteristics of the texture abnormality area and calculates and obtains the pipeline texture abnormality coefficient.

[0031] In this embodiment, the present invention realizes comprehensive detection of pipeline texture features through the pipeline texture anomaly module, and uses denoising, image segmentation and grayscale normalization to improve data quality. The local, global and detail texture features are extracted by combining local binary patterns, grayscale co-occurrence matrix and multi-resolution wavelet transform, and the support vector machine classification model accurately identifies the texture anomaly area. Through classification analysis and anomaly coefficient calculation, the pipeline texture anomaly is accurately located, providing a reliable basis for pipeline status assessment and maintenance, and significantly improving detection accuracy and efficiency.

[0032] Further, the pipeline temperature anomaly module includes a third image preprocessing layer, a multimodal image registration layer, a feature extraction and fusion layer, and a temperature anomaly detection layer; The third image preprocessing layer performs denoising, contrast enhancement and normalization on the pipeline thermal imaging image data and the pipeline ordinary imaging data respectively, so as to obtain a preprocessed first thermal imaging image and a first ordinary imaging image; The multimodal image registration layer performs feature point matching on the preprocessed thermal imaging image and the ordinary imaging image to generate a multimodal image; The feature extraction and fusion layer extracts temperature gradient features from the thermal imaging image in the multimodal image, extracts geometric edge features from the common imaging image in the multimodal image, and generates a multimodal feature vector; The temperature anomaly detection layer performs analysis based on the multimodal feature vector and the standard pipeline multimodal feature vector to calculate and generate a pipeline temperature anomaly coefficient.

[0033] In this embodiment, the present invention realizes accurate detection of water heating pipe temperature anomalies through the pipe temperature anomaly module, and uses the multimodal fusion technology of thermal imaging and ordinary imaging data, combined with denoising, contrast enhancement and normalization processing to improve image quality. The multi-dimensionality and high precision of anomaly detection are ensured by extracting and fusing temperature gradient features and geometric edge features. The temperature anomaly detection layer effectively compares the actual and standard multimodal feature vectors, calculates the pipe temperature anomaly coefficient, provides a scientific basis for pipe heat loss assessment and maintenance strategies, and greatly improves detection reliability and accuracy.

[0034] Furthermore, the specific calculation formula of the pipeline deformation abnormal coefficient is: ; in, is the pipeline deformation anomaly coefficient, is the total number of abnormal feature points, Abnormal feature points The local outlier factor of is the preset local outlier factor threshold, Abnormal feature points The gradient strength, is the gradient strength of all abnormal feature points, Abnormal feature points The weight of The specific calculation formula of the pipeline texture anomaly coefficient is: ; in, is the pipeline texture anomaly coefficient, is the number of abnormal texture areas, For the The weight of local texture feature value in abnormal texture area, For the The local texture feature values ​​of abnormal texture areas, For the The global texture eigenvalue weight of the abnormal texture area, For the The global texture feature value of the abnormal texture area, For the The detail texture feature value weights of abnormal texture areas, For the Detailed texture feature values ​​of abnormal texture areas, is the confidence coefficient of the abnormal area of ​​pipeline texture; ; The specific calculation formula of the pipeline temperature anomaly coefficient is: ; in, is the pipeline temperature anomaly coefficient, is the number of detected temperature zones, For the The temperature gradient deviation value weight of each detection area, For the The actual measured temperature gradient of the detection area, For the The temperature gradient of the standard pipeline in the detection area, For the The geometric edge deviation weight of the detection area, For the The total number of edge points in the detection area, For the In the detection area The detection value of edge points, For the In the detection area The standard value of edge points, is the confidence coefficient of abnormal pipeline temperature area, .

[0035] In this embodiment, the pipe deformation anomaly coefficient, pipe texture anomaly coefficient and pipe temperature anomaly coefficient are calculated by specific formulas to achieve quantitative evaluation of the abnormal state of the water and heating pipe. The deformation anomaly coefficient combines the outlier factor and gradient strength to improve the deformation detection accuracy; the texture anomaly coefficient integrates multi-dimensional texture features and confidence coefficients to enhance the texture anomaly positioning capability; the temperature anomaly coefficient is based on the temperature gradient and geometric edge deviation to accurately reflect the characteristics of the temperature anomaly area.

[0036] Reference Figure 1In S30, a water heating pipeline abnormality coefficient is generated through multimodal data fusion according to the pipeline deformation abnormality coefficient, the pipeline texture abnormality coefficient and the pipeline temperature abnormality coefficient; the formula for the multimodal data fusion is: ; in, is the abnormal coefficient of water and heating pipes, is the weight of pipeline deformation anomaly coefficient, is the pipeline deformation anomaly coefficient, is the pipeline texture anomaly coefficient weight, is the pipeline texture anomaly coefficient, is the pipe temperature anomaly coefficient weight, is the pipe temperature anomaly coefficient, ; Data refer to Table 2; When the water heating pipe abnormal coefficient When the abnormal coefficient of the water and heating pipeline is greater than 0.5, the abnormal area and abnormal type are obtained in time by analyzing the abnormal coefficient of pipeline deformation, pipeline texture and pipeline temperature; Table 2 Water and heating pipeline abnormal data fusion table

[0037] The plumbing pipes are maintained according to the plumbing pipe abnormality coefficient.

[0038] Through the abnormal state detection model of plumbing pipes and multimodal data fusion technology, accurate assessment of pipe deformation, texture and temperature anomalies is achieved, and a comprehensive plumbing pipe anomaly coefficient is generated. The deformation anomaly coefficient combines the outlier factor and gradient strength to improve deformation recognition capability; the texture anomaly coefficient enhances texture anomaly positioning through comprehensive analysis of local, global and detailed texture features; the temperature anomaly coefficient integrates thermal imaging and ordinary imaging features to accurately reflect the characteristics of temperature anomaly areas. Finally, through the multimodal data fusion formula, each anomaly coefficient is weighted and integrated to provide comprehensive and scientific anomaly assessment results, providing strong support for efficient maintenance and accurate detection of plumbing pipes.

[0039] Embodiment 2 In a water and heating pipe system, the long-term operation of the pipe may be affected by the external environment and the internal medium, resulting in deformation, abnormal texture and abnormal temperature, etc. These problems directly affect the service life and safety of the pipe. In view of the above problems, the present invention provides a water and heating pipe maintenance detection system to efficiently and accurately identify pipe abnormalities.

[0040] The present invention provides a water heating pipeline maintenance and detection method, which is applied to a water heating pipeline maintenance and detection system. The specific method flow chart and system structure diagram refer to Figure 1 and Figure 2 ,The weights in the present invention are all obtained by machine learning training of historical data of water and heating pipes.

[0041] As an embodiment of the present invention, refer to Figure 1 S10 in the figure is applied to a data acquisition unit of a water and heating pipe maintenance and detection system. The data acquisition unit constructs a water and heating pipe image data set by collecting pipe time-series image data, pipe feature image data, pipe thermal imaging image data and pipe general imaging data of the area to be detected in the heating water pipes in the building.

[0042] Reference Figure 1 S20 in the embodiment is applied to a related abnormality coefficient acquisition unit of a water and heating pipe maintenance and detection system. The related abnormality coefficient acquisition unit identifies the water and heating pipe image data set by constructing a water and heating pipe abnormal state detection model to obtain the pipe deformation abnormality coefficient, pipe texture abnormality coefficient and pipe temperature abnormality coefficient.

[0043] Furthermore, a historical image dataset of water and heating pipes is obtained to construct a water and heating pipe abnormal state detection model; The water heating pipeline abnormal state detection model includes a pipeline deformation abnormality module, a pipeline texture abnormality module and a pipeline temperature abnormality module; The pipeline deformation anomaly module obtains the deformation anomaly of the water heating pipeline in the detection area by identifying the pipeline time series image data in the water heating pipeline image data set; The pipeline texture anomaly module obtains the pipeline texture anomaly area by identifying the pipeline feature image data in the water heating pipeline image data set; The pipeline temperature anomaly module obtains pipeline temperature anomaly by identifying pipeline thermal imaging image data and pipeline common imaging data in the water heating pipeline image data set.

[0044] Further, the pipeline deformation anomaly module includes a first image preprocessing layer, a first feature extraction layer, an outlier factor calculation layer, an anomaly detection layer and a result output layer; The first image preprocessing layer generates preprocessed first pipeline time series image data by graying, denoising and aligning the pipeline time series image data; The first feature extraction layer constructs a first pipeline feature vector by extracting edge strength, local gradient change and structural similarity of each frame of image from the first pipeline time series image data; The outlier factor calculation layer analyzes the first pipeline time series image data using a local outlier factor algorithm based on the first pipeline feature vector to obtain a local outlier factor; The anomaly detection layer analyzes the local outlier factor and the local outlier factor threshold, identifies abnormal feature points and clusters and marks them as abnormal areas; The result output layer calculates and obtains the pipeline deformation anomaly coefficient by identifying the abnormal area.

[0045] The pipeline deformation is dynamically monitored using a time series analysis algorithm. The time-related characteristics of the pipeline deformation are extracted through this analysis, including but not limited to the curvature, sagging and deformation rate of the pipeline, and the structural changes of the pipeline are evaluated based on these characteristics. The severity of the pipeline deformation is judged based on the deformation rate, curvature and deformation amplitude. Larger curvature and higher deformation rate may cause the pipeline structure to face greater pressure and a higher risk of failure.

[0046] Further, the pipeline texture anomaly module includes a second image preprocessing layer, a second feature extraction layer, an abnormal texture detection layer and a texture output layer; The second image preprocessing layer performs denoising, image segmentation and grayscale normalization on the pipeline characteristic image data to obtain first pipeline characteristic image data; The second feature extraction layer extracts local texture features, global texture features and detail texture features from the first pipeline feature image data to form a second pipeline feature; The abnormal texture detection layer classifies texture features through a support vector machine classification model to obtain the distribution characteristics of texture abnormal areas; The texture output layer identifies the distribution characteristics of the texture abnormality area and calculates and obtains the pipeline texture abnormality coefficient.

[0047] By analyzing the texture features of the pipeline image, information such as the roughness, crack width, crack length, color change, edge sharpness, and texture granularity of the pipeline surface is extracted. The texture feature analysis method automatically identifies the corroded area of ​​the pipeline based on the texture distribution of the image and quantifies the degree of corrosion. The severity of corrosion is evaluated based on the granularity of the texture features, crack width, and length. Areas with wider and longer cracks and smaller texture granularity may indicate more severe corrosion and a higher risk of failure of the pipeline.

[0048] Further, the pipeline temperature anomaly module includes a third image preprocessing layer, a multimodal image registration layer, a feature extraction and fusion layer, and a temperature anomaly detection layer; The third image preprocessing layer performs denoising, contrast enhancement and normalization on the pipeline thermal imaging image data and the pipeline ordinary imaging data respectively, so as to obtain a preprocessed first thermal imaging image and a first ordinary imaging image; The multimodal image registration layer performs feature point matching on the preprocessed thermal imaging image and the ordinary imaging image to generate a multimodal image; The feature extraction and fusion layer extracts temperature gradient features from the thermal imaging image in the multimodal image, extracts geometric edge features from the common imaging image in the multimodal image, and generates a multimodal feature vector; The temperature anomaly detection layer performs analysis based on the multimodal feature vector and the standard pipeline multimodal feature vector to calculate and generate a pipeline temperature anomaly coefficient.

[0049] Combining thermal imaging and conventional imaging image data, the leaking area of ​​the pipeline is detected through data fusion technology. Thermal imaging images are used to detect areas with abnormal temperature distribution, and conventional imaging images are used to eliminate interference from external environmental factors and accurately locate the location of the leak. By analyzing the temperature change amplitude of thermal imaging images and the signs of water stains in conventional images, the size of the leaking area and the degree of temperature change are related to the severity of the leak. Areas with large temperature changes and large leaking areas may indicate more serious leaking problems.

[0050] Furthermore, the specific calculation formula of the pipeline deformation abnormal coefficient is: ; in, is the pipeline deformation anomaly coefficient, is the total number of abnormal feature points, Abnormal feature points The local outlier factor of is the preset local outlier factor threshold, Abnormal feature points The gradient strength, is the gradient strength of all abnormal feature points, Abnormal feature points The weight of The specific calculation formula of the pipeline texture anomaly coefficient is: ; in, is the pipeline texture anomaly coefficient, is the number of abnormal texture areas, For the The weight of local texture feature value in abnormal texture area, For the The local texture feature values ​​of abnormal texture areas, For the The global texture eigenvalue weight of the abnormal texture area, For the The global texture feature value of the abnormal texture area, For the The detail texture feature value weights of abnormal texture areas, For the Detailed texture feature values ​​of abnormal texture areas, is the confidence coefficient of the abnormal area of ​​pipeline texture; ; The specific calculation formula of the pipeline temperature anomaly coefficient is: ; in, is the pipe temperature anomaly coefficient, is the number of detected temperature zones, For the The temperature gradient deviation value weight of each detection area, For the The actual measured temperature gradient of the detection area, For the The temperature gradient of the standard pipeline in the detection area, For the The geometric edge deviation weight of the detection area, For the The total number of edge points in the detection area, For the In the detection area The detection value of edge points, For the In the detection area The standard value of edge points, is the confidence coefficient of abnormal pipeline temperature area, .

[0051] Reference Figure 1 S30 in the embodiment is applied to a water-heating pipe abnormality coefficient acquisition unit of a water-heating pipe maintenance and detection system. The water-heating pipe abnormality coefficient acquisition unit generates the water-heating pipe abnormality coefficient by multimodal data fusion according to the pipe deformation abnormality coefficient, the pipe texture abnormality coefficient and the pipe temperature abnormality coefficient.

[0052] The formula for multimodal data fusion is: ; in, is the abnormal coefficient of water and heating pipes, is the weight of pipeline deformation anomaly coefficient, is the pipeline deformation anomaly coefficient, is the pipeline texture anomaly coefficient weight, is the pipeline texture anomaly coefficient, is the pipe temperature anomaly coefficient weight, is the pipe temperature anomaly coefficient, ; Data refer to Table 3; Table 3 Water and heating pipe abnormal data table

[0053] The plumbing pipes are maintained according to the plumbing pipe abnormality coefficient.

[0054] The present invention provides a plumbing pipe maintenance and detection system that uses a plumbing pipe abnormal state detection model and a multimodal data fusion method to comprehensively analyze deformation, texture and temperature anomalies to generate a plumbing pipe anomaly coefficient. The deformation anomaly coefficient is based on the outlier factor and gradient strength to accurately identify pipe deformation problems; the texture anomaly coefficient integrates local, global and detailed texture features to accurately locate abnormal areas; the temperature anomaly coefficient combines thermal imaging and ordinary imaging features to fully reflect temperature change characteristics. The multimodal data fusion formula weights and integrates each anomaly coefficient to provide a scientific and comprehensive pipeline anomaly assessment result, providing a reliable basis for plumbing pipe maintenance and fault detection, and improving detection efficiency and maintenance accuracy.

[0055] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A water and heating pipeline maintenance and detection method, comprising: Collect pipeline time-series image data, pipeline feature image data, pipeline thermal imaging image data and pipeline general imaging data in the plumbing pipeline inspection area in the building to build a plumbing pipeline image data set; Constructing a plumbing pipe abnormal state detection model to identify the plumbing pipe image data set, and obtaining a pipe deformation abnormality coefficient, a pipe texture abnormality coefficient, and a pipe temperature abnormality coefficient; The pipeline deformation anomaly coefficient is obtained by identifying the pipeline time series image data through a local outlier factor algorithm; The pipeline texture anomaly coefficient is obtained by identifying the second pipeline feature of the pipeline feature image data; The pipeline temperature anomaly coefficient is obtained by identifying the multimodal feature vector of the multimodal image; According to the pipeline deformation anomaly coefficient, the pipeline texture anomaly coefficient and the pipeline temperature anomaly coefficient, a water heating pipeline anomaly coefficient is generated through multimodal data fusion; the formula for the multimodal data fusion is: ； in, is the abnormal coefficient of water and heating pipes, is the weight of pipeline deformation anomaly coefficient, is the pipeline deformation anomaly coefficient, is the pipeline texture anomaly coefficient weight, is the pipeline texture anomaly coefficient, is the pipe temperature anomaly coefficient weight, is the pipeline temperature anomaly coefficient, ; The plumbing pipes are maintained according to the plumbing pipe abnormality coefficient.

2. A water heating pipeline maintenance and detection method according to claim 1, characterized in that: Obtain historical image datasets of plumbing pipes and build a plumbing pipe abnormal state detection model; The water heating pipeline abnormal state detection model includes a pipeline deformation abnormality module, a pipeline texture abnormality module and a pipeline temperature abnormality module; The pipeline deformation anomaly module obtains the deformation anomaly of the water heating pipeline in the detection area by identifying the pipeline time series image data of the water heating pipeline image data set; The pipeline texture anomaly module obtains the pipeline texture anomaly area by identifying the pipeline feature image data of the water heating pipeline image data set; The pipeline temperature anomaly module obtains pipeline temperature anomaly by identifying pipeline thermal imaging image data and pipeline common imaging data in the water heating pipeline image data set.

3. A water heating pipeline maintenance and detection method according to claim 2, characterized in that: The pipeline deformation anomaly module includes a first image preprocessing layer, a first feature extraction layer, an outlier factor calculation layer, an anomaly detection layer and a result output layer; The first image preprocessing layer generates preprocessed first pipeline time series image data by graying, denoising and aligning the pipeline time series image data; The first feature extraction layer constructs a first pipeline feature vector by extracting edge strength, local gradient change and structural similarity of each frame of image from the first pipeline time series image data; The outlier factor calculation layer analyzes the first pipeline time series image data using a local outlier factor algorithm based on the first pipeline feature vector to obtain a local outlier factor; The anomaly detection layer analyzes the local outlier factor and the local outlier factor threshold, identifies abnormal feature points and clusters and marks them as abnormal areas; The result output layer calculates and obtains the pipeline deformation anomaly coefficient by identifying the abnormal area.

4. A water heating pipeline maintenance and detection method according to claim 2, characterized in that: The pipeline texture anomaly module includes a second image preprocessing layer, a second feature extraction layer, an abnormal texture detection layer and a texture output layer; The second image preprocessing layer performs denoising, image segmentation and grayscale normalization on the pipeline characteristic image data to obtain first pipeline characteristic image data; The second feature extraction layer extracts local texture features, global texture features and detail texture features from the first pipeline feature image data to form a second pipeline feature; The abnormal texture detection layer classifies texture features through a support vector machine classification model to obtain the distribution characteristics of texture abnormal areas; The texture output layer identifies the distribution characteristics of the texture abnormality area and calculates and obtains the pipeline texture abnormality coefficient.

5. A water heating pipeline maintenance and detection method according to claim 2, characterized in that: The pipeline temperature anomaly module includes a third image preprocessing layer, a multimodal image registration layer, a feature extraction and fusion layer, and a temperature anomaly detection layer; The third image preprocessing layer performs denoising, contrast enhancement and normalization on the pipeline thermal imaging image data and the pipeline ordinary imaging data respectively, so as to obtain a preprocessed first thermal imaging image and a first ordinary imaging image; The multimodal image registration layer performs feature point matching on the preprocessed thermal imaging image and the ordinary imaging image to generate a multimodal image; The feature extraction and fusion layer extracts temperature gradient features from the thermal imaging image in the multimodal image, extracts geometric edge features from the common imaging image in the multimodal image, and generates a multimodal feature vector; The temperature anomaly detection layer performs analysis based on the multimodal feature vector and the standard pipeline multimodal feature vector to calculate and generate a pipeline temperature anomaly coefficient.

6. A water heating pipeline maintenance and detection method according to claim 1, characterized in that: The specific calculation formula of the pipeline deformation abnormal coefficient is: ； in, is the pipeline deformation anomaly coefficient, is the total number of abnormal feature points, Abnormal feature points The local outlier factor of is the preset local outlier factor threshold, Abnormal feature points The gradient strength, is the gradient strength of all abnormal feature points, Abnormal feature points The weight of The specific calculation formula of the pipeline texture anomaly coefficient is: ； in, is the pipeline texture anomaly coefficient, is the number of abnormal texture areas, For the The weight of local texture feature value in abnormal texture area, For the The local texture feature values ​​of abnormal texture areas, For the The global texture eigenvalue weight of the abnormal texture area, For the The global texture feature value of the abnormal texture area, For the The detail texture feature value weight of the abnormal texture area, For the Detailed texture feature values ​​of abnormal texture areas, is the confidence coefficient of the abnormal area of ​​pipeline texture; ; The specific calculation formula of the pipeline temperature anomaly coefficient is: ； in, is the pipeline temperature anomaly coefficient, is the number of detected temperature zones, For the The temperature gradient deviation value weight of each detection area, For the The actual measured temperature gradient of the detection area, For the The temperature gradient of the standard pipeline in the detection area, For the The geometric edge deviation weight of the detection area, For the The total number of edge points in the detection area, For the In the detection area The detection value of edge points, For the In the detection area The standard value of edge points, is the confidence coefficient of abnormal pipeline temperature area, .

7. A water and heating pipeline maintenance and detection system, characterized in that: include: A data acquisition unit collects pipeline time-series image data, pipeline feature image data, pipeline thermal imaging image data and pipeline general imaging data of the area to be inspected in the heating water pipes in the building, and constructs a water heating pipe image data set; A related abnormality coefficient acquisition unit is used to construct a plumbing pipe abnormal state detection model to identify the plumbing pipe image data set, and obtain a pipe deformation abnormality coefficient, a pipe texture abnormality coefficient, and a pipe temperature abnormality coefficient; The water heating pipeline abnormality coefficient acquisition unit generates the water heating pipeline abnormality coefficient through multimodal data fusion according to the pipeline deformation abnormality coefficient, the pipeline texture abnormality coefficient and the pipeline temperature abnormality coefficient; the formula of the multimodal data fusion is: ； in, is the abnormal coefficient of water and heating pipes, is the weight of pipeline deformation anomaly coefficient, is the pipeline deformation anomaly coefficient, is the pipeline texture anomaly coefficient weight, is the pipeline texture anomaly coefficient, is the pipe temperature anomaly coefficient weight, is the pipeline temperature anomaly coefficient, ; The plumbing pipes are maintained according to the plumbing pipe abnormality coefficient.

8. A water and heating pipeline maintenance and detection system according to claim 7, characterized in that: The pipeline deformation anomaly coefficient is obtained by identifying the pipeline time series image data through a local outlier factor algorithm; The pipeline texture anomaly coefficient is obtained by identifying the pipeline feature image data using a texture feature analysis method; The pipeline temperature anomaly coefficient is obtained by identifying the pipeline thermal imaging image data and the pipeline ordinary imaging data through data fusion technology.

9. A water and heating pipeline maintenance and detection system according to claim 7, characterized in that: The water heating pipeline abnormal state detection model includes a pipeline deformation abnormality module, a pipeline texture abnormality module and a pipeline temperature abnormality module; The pipeline deformation anomaly module obtains the deformation anomaly of the water heating pipeline in the detection area by identifying the pipeline time series image data in the water heating pipeline image data set; The pipeline texture anomaly module obtains the pipeline texture anomaly area by identifying the pipeline feature image data in the water heating pipeline image data set; The pipeline temperature anomaly module obtains pipeline temperature anomaly by identifying pipeline thermal imaging image data and pipeline common imaging data in the water heating pipeline image data set.

10. A water and heating pipeline maintenance and detection system according to claim 7, characterized in that: The pipeline deformation anomaly module includes a first image preprocessing layer, a first feature extraction layer, an outlier factor calculation layer, an anomaly detection layer and a result output layer; The pipeline texture anomaly module includes a second image preprocessing layer, a second feature extraction layer, an abnormal texture detection layer and a texture output layer; The pipeline temperature anomaly module includes a third image preprocessing layer, a multimodal image registration layer, a feature extraction and fusion layer, and a temperature anomaly detection layer.

Images