Non-contact building exterior wall surface layer quality detection system and method

Abstract

The invention discloses a non-contact building exterior wall surface layer quality detection system and method, and relates to the technical field of building detection.External environment state data are collected in real time through multiple environment monitoring devices, an external environment state data set is generated through preprocessing, an external environment influence coefficient Xwh is obtained after calculation, and when the external environment influence coefficient Xwh exceeds a threshold value, the external environment influence coefficient Xwh is judged to be the same as the threshold value; a surface layer quality detection instruction is sent out, then a facing layer surface image and a heat insulation layer distribution heat map are obtained through shooting equipment, after uniform division and feature extraction, obtained related damage data information and related heat bridge distribution data information are associated with an external environment influence coefficient Xwh, and a surface layer quality evaluation index Zmc is calculated. The method comprises the following steps: detecting the quality of the building exterior wall surface layer, comparing the quality of the building exterior wall surface layer with a quality evaluation threshold value P, judging whether the surface layer quality detection is qualified, and generating a corresponding detection report, so that non-contact and automatic quality detection and evaluation of the building exterior wall surface layer are realized in general.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of building detection, in particular to a non-contact building outer wall surface layer quality detection system and method. BACKGROUND

[0002] With the continuous development of building technology, the construction industry has grown significantly worldwide, and the safety and comfort of buildings directly affect the health and quality of life of residents and users, so building quality management has gradually become an important issue in the industry. During the use of buildings, the outer wall surface layer is a key part directly exposed to the external environment, and its quality condition determines the durability, energy efficiency and aesthetics of the building to a great extent, therefore, the quality detection of the building outer wall surface layer is particularly important.

[0003] Traditional outer wall surface layer quality detection methods rely on manual inspection and contact detection equipment, the detection process is usually tedious and easily affected by human factors, and at the same time, it will interfere with and damage the building outer wall surface layer itself. With the progress of technology, non-contact quality detection technology is gradually applied as an innovative means, but in actual application, it still faces many challenges and deficiencies. First of all, it lacks consideration of the influence of external environmental factors on the quality of the building outer wall surface layer, and it is also limited to the detection of surface defects of the surface layer. In addition, it also fails to combine big data analysis and intelligent algorithms well, and lacks in-depth analysis of the damage of the surface layer and the thermal bridge effect of the insulation layer. Therefore, there is an urgent need for a method that can integrate external environmental factors, use high-precision image acquisition technology, and combine intelligent algorithms to detect and comprehensively evaluate the quality of the outer wall surface layer, improve the accuracy and intelligent level of building outer wall surface layer quality detection. SUMMARY

[0004] In view of the deficiencies of the prior art, the present application provides a non-contact building outer wall surface layer quality detection system and method, which solves the problems in the background art.

[0005] To achieve the above purpose, the present application realizes the following technical scheme: a non-contact building outer wall surface layer quality detection system, comprising an external environment monitoring module, an external environment analysis module, a surface layer detection module, a quality comprehensive evaluation module and a feedback module;

[0006] The external environment monitoring module is used to monitor the external environment state of the building outer wall surface layer in real time by using a plurality of environment monitoring devices, and obtain an external environment state data set;

[0007] The external environment analysis module is used to construct an external environment influence coefficient Xwh according to the external environment state data set, and if the external environment influence coefficient Xwh exceeds a threshold value, a surface layer quality detection instruction is issued to the outside;

[0008] The surface layer detection module is used to take pictures of the building exterior wall surface layer according to the shooting equipment set on the front of the building exterior wall after receiving the surface layer quality detection instruction, and generate surface images of the decorative layer and thermal distribution maps of the insulation layer respectively. After uniform division and feature extraction, relevant damage data information and relevant thermal bridge distribution data information are obtained respectively.

[0009] The comprehensive quality assessment module is used to analyze relevant damage data and thermal bridge distribution data, and combine them with the external environmental influence coefficient Xwh to fit and obtain the surface layer quality assessment index Zmc.

[0010] The feedback module is used to pre-set the quality assessment threshold P and compare it with the surface layer quality assessment index Zmc to comprehensively determine whether the current building exterior wall surface layer quality inspection is qualified and generate a corresponding inspection report.

[0011] Preferably, the external environment monitoring module includes a monitoring unit and a preprocessing unit;

[0012] The monitoring unit is used to deploy multiple environmental monitoring devices on the external environment where the building's exterior wall surface is located to monitor the external environment status in real time and obtain an external environment status data set. The external environment status data set includes temperature (Twd), humidity (Ssd), and light intensity (Ggz) at each monitoring time point within the monitoring period, wherein the monitoring period is one day and night. The environmental monitoring devices include temperature sensors, humidity sensors, and optical sensors.

[0013] The preprocessing unit is used to preprocess relevant data information in the external environment state dataset. Preprocessing includes noise removal, missing value imputation, and data smoothing. Missing value imputation methods include mean imputation, median imputation, interpolation imputation, and regression imputation.

[0014] Preferably, the external environment analysis module includes an analysis unit and an early warning unit;

[0015] The analysis unit is used to extract features from the acquired set of external environmental state data, and, combined with a statistical mean-calculation algorithm, to obtain the minimum temperature value Twd within the monitoring period. min Maximum temperature Twd max Average humidity and average light intensity By the minimum temperature Twd min and maximum temperature Twd max Correlate the data and obtain the temperature difference value ΔTwd during the monitoring period. The temperature difference value ΔTwd is obtained using the following formula:

[0016] ΔTwd=Twd max -Twdmin ;

[0017] According to the external environment state data set, an external environment influence coefficient Xwh is constructed, and the external environment influence coefficient Xwh is obtained through the following formula:

[0018]

[0019] In the formula, ΔTwd represents a temperature difference value, represents a humidity average value, represents an average value of light intensity, wherein α1, α2 and α3 respectively represent weight values of the temperature difference value ΔTwd, the humidity average value and the average value of light intensity , and A represents a first correction constant.

[0020] Preferably, the early warning unit is configured to compare and analyze the external environment influence coefficient Xwh with a preset threshold value, so as to determine whether the current external environment has an influence on the quality of the building outer wall surface layer. The specific comparison content is as follows:

[0021] If the external environment influence coefficient Xwh exceeds the threshold value, it is determined that the current external environment has an influence on the quality of the building outer wall surface layer. At this time, a surface layer quality detection instruction is sent out to the outside, and the surface layer quality is further analyzed.

[0022] If the external environment influence coefficient Xwh does not exceed the threshold value, it is determined that the current external environment has no influence on the quality of the building outer wall surface layer. At this time, no additional surface layer quality detection instruction is sent out.

[0023] Preferably, the surface layer detection module comprises a detection unit and an extraction unit.

[0024] The detection unit is configured to, after receiving the surface layer quality detection instruction, set a visible light high-definition camera and an infrared thermal imaging shooting device on the front of the building outer wall, and combine with an automatic control technology, dynamically adjust the shooting distance, angle and focal length according to the shape and size characteristics of the building outer wall surface layer, capture and shoot the surface state of the facing layer and the distribution of the thermal insulation layer of the building outer wall surface layer by orthographic projection, so as to obtain the surface image of the facing layer and the distribution thermal image of the thermal insulation layer, respectively; based on the wavelet denoising technology, remove the noise of the obtained surface image of the facing layer and the distribution thermal image of the thermal insulation layer, and adjust the brightness distribution and contrast of the surface image of the facing layer and the distribution thermal image of the thermal insulation layer through the gamma correction image enhancement technology.

[0025] The distribution thermal image of the thermal insulation layer is evenly divided into a plurality of thermal image detection regions, and the plurality of thermal image detection regions of the distribution thermal image of the thermal insulation layer are respectively marked as a first thermal image detection region T1, a second thermal image detection region T2, a third thermal image detection region T3,..., and an mth thermal image detection region Tm.

[0026] The extraction unit is configured to identify and detect relevant damage data information of the surface of the facing layer, including the bulging area Sgq, the crack length Lcd, the pit area Skd and the peeling area Sqp, by using the surface image of the facing layer; and identify and detect relevant thermal bridge distribution data information of the distribution of the thermal insulation layer, including the thermal bridge area Rmj and the thermal bridge change rate Vbh of each thermal map detection area, by using the distribution thermal map of the thermal insulation layer.

[0027] Preferably, the quality comprehensive evaluation module comprises a damage analysis unit, a thermal bridge prediction unit and a comprehensive evaluation unit.

[0028] The damage analysis unit is configured to analyze the relevant damage data information and construct a damage coefficient Xps after dimensionless processing, wherein the damage coefficient Xps is obtained by the following formula:

[0029] Xps = β1*Sgq + β2*Lcd + β3*Skd + β4*Sqp + B.

[0030] In the formula, Sgq represents the bulging area, Lcd represents the crack length, Skd represents the pit area, and Sqp represents the peeling area, wherein β1, β2, β3 and β4 represent the weight values of the bulging area Sgq, the crack length Lcd, the pit area Skd and the peeling area Sqp, respectively, and B represents a second correction constant.

[0031] Preferably, the thermal bridge prediction unit is configured to calculate the thermal bridge distribution density Mrq in the corresponding thermal map detection area according to the relevant thermal bridge distribution data information, and the thermal bridge distribution density Mrq is obtained by the following formula:

[0032]

[0033] In the formula, represents the average thermal bridge area, and δRmj represents the standard deviation of the thermal bridge area.

[0034] According to the relevant thermal bridge distribution data information and in combination with the thermal bridge distribution density Mrq, a thermal bridge distribution coefficient Xfb is calculated after dimensionless processing, wherein the thermal bridge distribution coefficient Xfb is obtained by the following formula:

[0035]

[0036] In the formula, Vbh i represents the thermal bridge change rate in the i-th thermal map detection area, represents the average thermal bridge change rate, and Mrq i represents the thermal bridge distribution density in the i-th thermal map detection area, The average thermal bridge distribution density is represented by i=1, 2, 3,..., m, m represents the number of detection areas, and γ1 and γ2 represent weight values.

[0037] Preferably, the comprehensive evaluation unit is used to analyze the relevant damage data information and the relevant thermal bridge distribution data information, and combines the external environment influence coefficient Xwh to obtain the surface layer quality evaluation index Zmc after dimensionless processing. The surface layer quality evaluation index Zmc is obtained by the following formula:

[0038]

[0039] In the formula, Xps represents a damage coefficient, Xfb represents a thermal bridge distribution coefficient, wherein, and respectively represent weight values of the external environment influence coefficient Xwh, the damage coefficient Xps and the thermal bridge distribution coefficient Xfb, and C represents a third correction constant.

[0040] Preferably, the feedback module is used to pre-set a quality evaluation threshold P and compare and analyze the surface layer quality evaluation index Zmc to comprehensively judge whether the quality detection of the current building outer wall surface layer is qualified. The specific process is as follows:

[0041] If the surface layer quality evaluation index Zmc exceeds the quality evaluation threshold P, it means that the quality detection of the current building outer wall surface layer is qualified, and a first detection report is generated, which shows that the surface layer quality meets the safety and design standards, and it is recommended to continue to use, and no additional repair measures are needed;

[0042] If the surface layer quality evaluation index Zmc does not exceed the quality evaluation threshold P, it means that the quality detection of the current building outer wall surface layer is unqualified, and a second detection report is generated, which shows that the surface layer quality does not meet the safety and design standards, and it is recommended to repair the surface layer damage as soon as possible and strengthen the thermal insulation performance of the thermal insulation layer.

[0043] A non-contact building outer wall surface layer quality detection method, comprising the following steps:

[0044] Step one, first, use multiple environment monitoring devices to monitor the external environment state of the building outer wall surface layer in real time to obtain an external environment state data set;

[0045] Step two, second, construct the external environment influence coefficient Xwh according to the external environment state data set. If the external environment influence coefficient Xwh exceeds the threshold, the surface layer quality detection instruction is sent out.

[0046] Step three, then after receiving the surface layer quality detection instruction, the building outer wall surface layer is photographed according to the shooting device arranged on the front of the building outer wall, and the surface image of the facing layer and the distribution heat map of the thermal insulation layer are generated respectively, and after uniform division and feature extraction, the related damage data information and the related thermal bridge distribution data information are obtained respectively;

[0047] Step four, in addition, the related damage data information and the related thermal bridge distribution data information are analyzed, and the surface layer quality evaluation index Zmc is fitted and obtained in combination with the external environment influence coefficient Xwh;

[0048] Step five, finally, the quality evaluation threshold P is pre-set, and it is compared and analyzed with the surface layer quality evaluation index Zmc, so as to comprehensively judge whether the quality detection of the current building outer wall surface layer is qualified, and the corresponding detection report is generated.

[0049] The application provides a non-contact building outer wall surface layer quality detection system and method, which has the following beneficial effects:

[0050] (1) By integrating the environment monitoring, image acquisition, data analysis and comprehensive evaluation process, the multiple shortcomings in the traditional building outer wall detection method are solved; first, the temperature Twd, humidity Ssd and illumination intensity Ggz data of the environment where the building outer wall is located are collected in real time by multiple environment monitoring devices, and after preprocessing, the external environment state data set is formed, so that the influence of environmental changes on detection can be accurately evaluated, and the external environment influence coefficient Xwh is constructed according to these data, if the coefficient exceeds the set threshold, the surface layer quality detection instruction is automatically sent, so as to ensure the timeliness and accuracy of detection; the visible light high-definition camera and infrared thermal imaging device installed on the building outer wall are used to obtain the surface image of the facing layer and the distribution heat map of the thermal insulation layer, and the related damage data information and the related thermal bridge distribution data information are obtained through uniform division and feature extraction; further combined with the external environment influence coefficient Xwh, the surface layer quality evaluation index Zmc is calculated, and compared with the quality evaluation threshold P to judge whether the building outer wall surface layer quality detection is qualified; the system does not rely on manual inspection, has high automation, improves the detection precision and efficiency, reduces the risk of human judgment error, and can dynamically adjust according to environmental changes to ensure the accuracy of the detection result; in addition, the generated detection report provides an objective and reliable basis for the repair and maintenance of the building outer wall, further prolongs the service life of the building, and improves the safety and durability of the building; by applying advanced non-contact detection technology, the quality of the building outer wall surface layer can be accurately evaluated, and the accuracy and intelligent level of the building outer wall surface layer quality detection are improved.

[0051] (2) Through the innovative environmental monitoring and analysis means, the accuracy and intelligent level of the building outer wall quality detection are improved; through the deployment of various environmental monitoring equipment, the external environment data of the outer wall surface layer are collected in real time, so that the environmental changes of the building outer wall surface layer can be understood within the whole monitoring period; through the preprocessing of the collected external environment state data set, including denoising, missing value filling and data smoothing, the accuracy and stability of the data are ensured, and the errors caused by external environmental changes are avoided; in the analysis of the external environment state data set, the statistical method is combined to calculate the temperature difference value , the humidity average value , and the light intensity average value , and the external environment influence coefficient Xwh is further constructed to evaluate the influence of environmental changes on the quality of the building outer wall surface layer; when the external environment exceeds the preset threshold value, the surface layer quality detection instruction is automatically triggered for further analysis, which effectively reduces the invalid detection and improves the detection efficiency; at the same time, through this intelligent and automatic monitoring and analysis method, the accuracy of detection is improved, and the real-time response capability to the quality changes of the building outer wall is enhanced, avoiding the misjudgment and omission caused by environmental factors, and ensuring the reliability of the detection results.

[0052] (3) Through the introduction of visible light high-definition camera and infrared thermal imaging technology, combined with intelligent automatic control, the precision and efficiency of the outer wall surface layer quality detection are improved; through the dynamic shooting and data processing of the building outer wall, the surface image of the facing layer and the distribution heat map of the thermal insulation layer can be obtained in real time; in addition, through the wavelet denoising technology and gamma correction image enhancement technology, the noise is effectively removed and the brightness and contrast of the image are improved, ensuring the high quality of the detection data; then the related damage data information and the related thermal bridge distribution data information are accurately identified and detected, avoiding the limitations and errors of traditional manual detection; the related damage data information and the thermal bridge distribution data information are also processed and analyzed without dimension, the damage coefficient Xps and the thermal bridge distribution coefficient Xfb are constructed, and the quality of the building outer wall surface layer is comprehensively evaluated by combining the external environment influence coefficient Xwh, and finally the surface layer quality evaluation index Zmc is formed; by comparing with the preset quality evaluation threshold P, the health status of the outer wall surface layer is accurately judged; if the surface layer quality is qualified, the first detection report is generated and the use is recommended to continue; if it is unqualified, the second detection report is generated to propose repair suggestions in time; this detection method based on high-tech sensors and intelligent analysis not only improves the accuracy of detection, but also reduces the waste of human resources, realizes the intelligent management and timely maintenance of the quality of the building outer wall surface layer, and prolongs the service life of the building outer wall surface layer. BRIEF DESCRIPTION OF DRAWINGS

[0053] Figure 1 is a non-contact building outer wall surface layer quality detection system block diagram of the application;

[0054] Figure 2 It is a non-contact building outer wall surface layer quality detection method flowchart. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0056] Embodiment 1

[0057] Please refer to Figure 1 The present application provides a non-contact building outer wall surface layer quality detection system, comprising an external environment monitoring module, an external environment analysis module, a surface layer detection module, a quality comprehensive evaluation module and a feedback module.

[0058] The external environment monitoring module is used for monitoring the external environment state of the building outer wall surface layer in real time by using a plurality of environment monitoring devices, and obtaining an external environment state data set.

[0059] The external environment analysis module is used for constructing an external environment influence coefficient Xwh according to the external environment state data set, and issuing a surface layer quality detection instruction to the outside if the external environment influence coefficient Xwh exceeds a threshold value.

[0060] The surface layer detection module is used for photographing the building outer wall surface layer by a photographing device arranged on the front of the building outer wall after receiving the surface layer quality detection instruction, generating a surface image of the surface layer and a heat distribution map of the thermal insulation layer, respectively, and obtaining related damage data information and related heat bridge distribution data information after uniform division and feature extraction.

[0061] The quality comprehensive evaluation module is used for analyzing the related damage data information and the related heat bridge distribution data information, and fitting to obtain a surface layer quality evaluation index Zmc in combination with the external environment influence coefficient Xwh.

[0062] The feedback module is used for pre-setting a quality evaluation threshold P, comparing and analyzing the quality evaluation threshold P with the surface layer quality evaluation index Zmc, comprehensively judging whether the quality detection of the current building outer wall surface layer is qualified or not, and generating a corresponding detection report.

[0063] In this embodiment, by integrating various advanced technologies, an efficient, intelligent and accurate building outer wall surface layer quality detection solution is provided; first, the external environment monitoring module uses multiple environmental monitoring devices to obtain real-time external environment state data set, and constructs the external environment influence coefficient Xwh, compares the preset threshold value, judges whether the external environment influences the quality of the building outer wall surface layer; if the external environment influence coefficient Xwh exceeds the threshold value, the surface layer quality detection instruction is automatically triggered, to ensure the timeliness and accuracy of the detection; second, the surface layer detection module adjusts the shooting distance, angle and focal length dynamically without contact, accurately captures the surface state of the building outer wall surface layer and the thermal bridge distribution of the thermal insulation layer; through image processing technology, relevant damage data information and relevant thermal bridge distribution data information are extracted; the quality comprehensive evaluation module combines the external environment influence coefficient Xwh, the damage coefficient Xps and the thermal bridge distribution coefficient Xfb, and fits to obtain the surface layer quality evaluation index Zmc, to realize the comprehensive evaluation of the outer wall quality; finally, the feedback module compares the surface layer quality evaluation index Zmc with the quality evaluation threshold P, comprehensively judges whether the quality of the building outer wall surface layer is qualified, and generates the corresponding detection report, provides repair suggestions or continues to use the decision; the advantage lies in its non-contact, automatic and high-precision detection method, which reduces the error of manual detection, ensures the reliability and timeliness of the detection, effectively prolongs the service life of the building outer wall surface layer, and improves the detection efficiency and safety.

[0064] Embodiment 2

[0065] Please refer to Figure 1 , specifically: the external environment monitoring module includes a monitoring unit and a preprocessing unit;

[0066] The monitoring unit is used for deploying multiple environmental monitoring devices in the external environment where the building outer wall surface layer is located, monitoring the external environment state of the building outer wall surface layer for real-time monitoring, obtaining the external environment state data set, the external environment state data set including temperature Twd, humidity Ssd and illumination intensity Ggz at each monitoring time point in the monitoring period, wherein the monitoring period is one day, and the environmental monitoring device includes a temperature sensor, a humidity sensor and an optical sensor.

[0067] The preprocessing unit is used for preprocessing the related data information in the external environment state data set, which includes noise removal, missing value filling and data smoothing operation, wherein the missing value filling method includes mean filling, median filling, interpolation filling and regression filling.

[0068] In this embodiment, by combining various environmental monitoring devices and efficient data preprocessing technology, the accuracy and reliability of the external environment data of the building outer wall surface layer are improved; first, the monitoring unit monitors the external environment state of the building outer wall by deploying temperature sensors, humidity sensors and optical sensors, and obtains environmental data including temperature Twd, humidity Ssd and light intensity Ggz; the subsequent quality analysis provides detailed and multi-dimensional external environment information, which helps to understand the potential influence of the external environment on the building outer wall surface layer; in addition, the monitoring unit collects data within a day, effectively captures the change rule of the external environment state, and ensures that the monitoring result is representative and timely; the introduction of the preprocessing unit ensures the accuracy and consistency of the monitoring data through noise removal, missing value filling and data smoothing; through the method of filling missing values, including mean filling, median filling, interpolation filling and regression filling, the data integrity is further improved, and the interference of data missing on the analysis result is avoided; this efficient data preprocessing and environmental data integration analysis provide a solid foundation for subsequent external environment influence evaluation and accurate detection of building outer wall quality, which helps to optimize the function of the detection system and improve the accuracy and reliability of the detection result.

[0069] Embodiment 3

[0070] Please refer to Figure 1 , specifically: the external environment analysis module includes an analysis unit and an early warning unit;

[0071] The analysis unit is used for feature extraction on the acquired external environment state data set, and the statistical mean value algorithm is combined to respectively acquire the temperature minimum value Twd min , the temperature maximum value Twd max , the humidity mean value and the light intensity mean value By associating the temperature minimum value Twd min and the temperature maximum value Twd max , the temperature difference value ΔTwd in the monitoring period is obtained, and the temperature difference value ΔTwd is obtained by the following formula:

[0072] ΔTwd=Twd max -Twd min ;

[0073] According to the external environment state data set, the external environment influence coefficient Xwh is constructed, and the external environment influence coefficient Xwh is obtained by the following formula:

[0074]

[0075] In the formula, ΔTwd represents the temperature difference value, represents the humidity mean value, is the average value of the light intensity, wherein, α1, α2 and α3 are weight values of the average value of the temperature difference ΔTwd, the average value of the humidity and the average value of the light intensity respectively, and A is the first correction constant.

[0076] Specifically, the early warning unit is configured to compare and analyze the external environment influence coefficient Xwh with a preset threshold value to determine whether the current external environment has an influence on the quality of the building outer wall surface layer, and the specific comparison content is as follows:

[0077] If the external environment influence coefficient Xwh exceeds the threshold value, it is determined that the current external environment has an influence on the quality of the building outer wall surface layer, and at this time, a surface layer quality detection instruction is issued to the outside to further analyze the surface layer quality;

[0078] If the external environment influence coefficient Xwh does not exceed the threshold value, it is determined that the current external environment has no influence on the quality of the building outer wall surface layer, and at this time, no additional surface layer quality detection instruction is issued.

[0079] In this embodiment, by comprehensively analyzing the external environment state data and accurately calculating the external environment influence coefficient Xwh, the accuracy of the influence degree of the external environment factor on the building outer wall surface layer is improved. First, the analysis unit extracts features from the temperature, humidity and light intensity environment data, and combines the statistical mean value algorithm to obtain the minimum temperature Twd min , the maximum temperature Twd max , the average value of the humidity and the average value of the light intensity These data not only reflect the specific changes of the external environment, but also further reveal the potential influence of the external environment changes on the building outer wall through the calculation of the temperature difference ΔTwd. By constructing the external environment influence coefficient Xwh, the influence degree of the external environment on the quality of the building outer wall surface layer can be quantified. The early warning unit compares and analyzes the external environment influence coefficient Xwh with the preset threshold value to effectively determine whether the current external environment has an influence on the quality of the outer wall surface layer. If the external environment influence coefficient Xwh exceeds the threshold value, the surface layer quality detection instruction is automatically triggered for further quality evaluation. If it does not exceed the threshold value, no additional detection instruction is issued, effectively avoiding invalid monitoring operations. This intelligent judgment mechanism improves the automatic analysis level of the influence of the external environment on the quality of the outer wall surface layer.

[0080] Embodiment 4

[0081] Please refer to Figure 1 , specifically: the surface layer detection module comprises a detection unit and an extraction unit;

[0082] ​​The detection unit is used to, after receiving the surface layer quality detection instruction, through the visible light high-definition camera and the infrared thermal imaging shooting device arranged on the facade of the building outer wall, and combining the automatic control technology, dynamically adjusting the shooting distance, angle and focal length according to the shape and size characteristics of the building outer wall surface layer, capturing and shooting the surface state of the facing layer of the building outer wall surface layer and the distribution of the thermal insulation layer by orthographic projection, to obtain the facing layer surface image and the thermal insulation layer distribution thermal map respectively; based on the wavelet denoising technology, the obtained facing layer surface image and the thermal insulation layer distribution thermal map are removed from noise, and the brightness distribution and contrast of the facing layer surface image and the thermal insulation layer distribution thermal map are adjusted through the gamma correction image enhancement technology;

[0083] The thermal insulation layer distribution thermal map is evenly divided into a plurality of thermal map detection regions, and the plurality of thermal map detection regions of the thermal insulation layer distribution thermal map are respectively marked as a first thermal map detection region T1, a second thermal map detection region T2, a third thermal map detection region T3,..., and an mth thermal map detection region Tm.

[0084] The extraction unit is used to identify and detect the related damage data information of the facing layer surface by using the facing layer surface image, the related damage data information including the arch area Sgq, the crack length Lcd, the pit area Skd and the peeling area Sqp; and the related thermal bridge distribution data information of the thermal insulation layer distribution is identified and detected by using the thermal insulation layer distribution thermal map, the related thermal bridge distribution data information including the thermal bridge area Rmj and the thermal bridge change rate Vbh of each thermal map detection region.

[0085] It should be noted that the related damage data information is obtained by processing and analyzing the facing layer surface image, and the boundary of the surface damage region is identified by image processing technology such as Canny edge detection, texture analysis and segmentation algorithm; the arch area Sgq and the pit area Skd are obtained by measuring the area of the pixel points of the damage region after image segmentation; the crack length Lcd is calculated after the crack morphology is extracted by morphological operation; the peeling area Sqp is identified by combining the texture feature extraction technology to identify the area of the missing surface coating, and the area is calculated;

[0086] The relevant thermal bridge distribution data information is obtained by analyzing the heat distribution diagram of the thermal insulation layer. The heat distribution diagram of the thermal insulation layer is evenly divided into a plurality of detection regions. The thermal bridge region is identified by analyzing the temperature distribution of each detection region. The thermal bridge area Rmj is calculated by the thermal image pixel value and the resolution. The thermal bridge change rate Vbh is calculated by recording the temperature change of the same thermal bridge region at different time points, calculating the temperature change rate per unit time, and combining the image labeling tool and algorithm to extract the thermal bridge area Rmj and the thermal bridge change rate Vbh. The thermal bridge refers to the region with high heat conduction performance in the building outer wall surface layer. Compared with the surrounding thermal insulation material, the thermal bridge region is more likely to transfer heat, which leads to the intensification of indoor and outdoor heat exchange. Usually, the thermal bridge appears at the position of weak, broken and joint thermal insulation layer.

[0087] In the embodiment, by combining advanced visible light high-definition camera and infrared thermal imaging technology, the quality of the building outer wall surface layer can be efficiently and accurately detected. The detection unit adjusts the distance, angle and focal length of the shooting device dynamically to ensure the accurate capture of the surface state of the finish layer and the distribution of the thermal insulation layer, thereby obtaining the surface image of the finish layer and the heat distribution diagram of the thermal insulation layer. The wavelet denoising technology and gamma correction image enhancement technology are used to further improve the definition and contrast of the image, ensuring the accuracy of the detection data. On the basis of the heat distribution diagram of the thermal insulation layer, it is divided into a plurality of thermal image detection regions, which can detect and analyze the thermal bridge condition of each region in detail, providing a basis for subsequent thermal bridge distribution analysis. The extraction unit accurately identifies the damage information through deep analysis of the surface image of the finish layer, and extracts the thermal bridge area Rmj and the thermal bridge change rate Vbh through the thermal image. This comprehensive detection method not only realizes the non-contact high-precision evaluation of the quality of the outer wall surface layer, but also effectively identifies the damage of the finish layer and the thermal bridge effect problem of the thermal insulation layer, improves the accuracy of building quality detection, and provides a scientific basis and technical support for subsequent maintenance and maintenance work.

[0088] Embodiment 5

[0089] Please refer to Figure 1 , specifically: the quality comprehensive evaluation module includes a damage analysis unit, a thermal bridge prediction unit and a comprehensive evaluation unit;

[0090] The damage analysis unit is used for analyzing the relevant damage data information. After dimensionless processing, the damage coefficient Xps is constructed. The damage coefficient Xps is obtained by the following formula:

[0091] Xps = β1*Sgq + β2*Lcd + β3*Skd + β4*Sqp + B;

[0092] In the formula, Sgq represents the arching area, Lcd represents the crack length, Skd represents the pit area, Sqp represents the peeling area, β1, β2, β3 and β4 represent the weight values of the arching area Sgq, the crack length Lcd, the pit area Skd and the peeling area Sqp respectively, and B represents the second correction constant.

[0093] Specifically, the thermal bridge prediction unit is configured to calculate the thermal bridge distribution density Mrq in the corresponding thermal map detection area according to the relevant thermal bridge distribution data information, and specifically obtain the thermal bridge distribution density Mrq through the following formula:

[0094]

[0095] In the formula, represents the average thermal bridge area, and δRmj represents the standard deviation of the thermal bridge area.

[0096] According to the relevant thermal bridge distribution data information, in combination with the thermal bridge distribution density Mrq, and after dimensionless processing, the thermal bridge distribution coefficient Xfb is calculated, and the thermal bridge distribution coefficient Xfb is obtained through the following formula:

[0097]

[0098] In the formula, Vbh i represents the thermal bridge change rate in the i-th thermal map detection area, represents the average thermal bridge change rate, and Mrq i represents the thermal bridge distribution density in the i-th thermal map detection area, represents the average thermal bridge distribution density, wherein i=1, 2, 3, …, m, m represents the number of detection areas, and γ1 and γ2 both represent weight values.

[0099] Specifically, the comprehensive evaluation unit is configured to analyze the relevant damage data information and the relevant thermal bridge distribution data information, in combination with the external environment influence coefficient Xwh, and after dimensionless processing, the surface layer quality evaluation index Zmc is fitted and obtained, and the surface layer quality evaluation index Zmc is obtained through the following formula:

[0100]

[0101] In the formula, Xps represents the damage coefficient, Xfb represents the thermal bridge distribution coefficient, wherein, and respectively represent the weight values of the external environment influence coefficient Xwh, the damage coefficient Xps and the thermal bridge distribution coefficient Xfb, and C represents the third correction constant.

[0102] In this embodiment, through the comprehensive analysis of damage analysis, thermal bridge prediction and external environmental influence, the quality of the building outer wall surface layer is accurately evaluated, and strong data support is provided for subsequent decision-making. First, the damage analysis unit non-dimensionalizes the relevant damage data information of the surface layer of the outer wall surface layer, quantifies the severity of the surface layer damage by constructing the damage coefficient Xps, and effectively analyzes the potential damage risk. This processing method based on the weighting coefficient effectively avoids the scale difference between different damage types, ensuring the scientificity and fairness of the evaluation results. The thermal bridge prediction unit analyzes the depth of the thermal bridge distribution of the insulation layer, calculates the thermal bridge distribution density Mrq of each thermal map detection area, and obtains the thermal bridge distribution coefficient Xfb through further processing. This process not only reflects the area and distribution of the thermal bridge, but also considers the change rate of the thermal bridge, and comprehensively evaluates the thermal insulation performance of the thermal insulation layer in the outer wall surface layer. As a key factor in building energy saving and comfort evaluation, the thermal bridge helps to find potential areas that may cause energy loss, thereby providing a strong basis for optimizing building energy saving design and insulation layer performance. The comprehensive evaluation unit weights and sums up the damage coefficient Xps, the thermal bridge distribution coefficient Xfb and the external environmental influence coefficient Xwh, and fits to calculate the surface layer quality evaluation index Zmc. Not only does it reflect the comprehensive quality of the building outer wall surface layer under different environments, but also can flexibly adjust the quality evaluation results according to the changes of external climate factors, realizing more accurate monitoring and early warning. Through this comprehensive analysis, the health status of the building outer wall surface layer can be dynamically evaluated under the influence of external environmental changes, and scientific maintenance and repair decisions can be made based on real-time data, thereby prolonging the service life of the building and reducing maintenance costs. Overall, through multi-dimensional analysis methods, not only detailed damage analysis and thermal bridge prediction are provided, but also external environmental factors are considered, improving the accuracy and scientificity of quality evaluation, and improving the intelligent level of building outer wall surface layer quality detection, helping repair personnel to timely discover and handle potential problems, improving the safety, energy saving and long-term sustainability of the building outer wall surface layer.

[0103] Embodiment 6

[0104] Please refer to Figure 1 , specifically: the feedback module is used to pre-set a quality evaluation threshold P, and compare it with the surface layer quality evaluation index Zmc to comprehensively judge whether the quality detection of the current building outer wall surface layer is qualified, the specific process is as follows:

[0105] If the surface layer quality evaluation index Zmc exceeds the quality evaluation threshold P, it means that the quality detection of the current building outer wall surface layer is qualified, and a first detection report is generated, which shows that the surface layer quality meets the safety and design standards, and it is recommended to continue to use, and no additional repair measures are needed.

[0106] If the surface layer quality evaluation index Zmc does not exceed the quality evaluation threshold P, it indicates that the quality detection of the current building outer wall surface layer is unqualified, and a second detection report is generated, which states that the surface layer quality does not meet the safety and design standards, and that cracks and peeling phenomena are found in the finish layer, and the thermal insulation layer is unevenly distributed, and it is recommended to repair the damaged finish layer as soon as possible and strengthen the thermal insulation performance of the thermal insulation layer.

[0107] In this embodiment, by comparing the obtained surface layer quality evaluation index Zmc with the preset quality evaluation threshold P, intelligent judgment and classification management of the quality of the building outer wall surface layer can be realized; when the surface layer quality evaluation index Zmc exceeds the quality evaluation threshold P, a first detection report is automatically generated, confirming that the surface layer quality meets the standards, avoiding unnecessary repair costs and waste of maintenance work; and when the surface layer quality evaluation index Zmc does not exceed the quality evaluation threshold P, a second detection report is timely issued, indicating the specific problems that need to be repaired, including cracks and peeling of the finish layer and uneven distribution of the thermal insulation layer, thereby helping repair personnel to take targeted repair measures; through this precise feedback mechanism, not only the quality detection process is optimized, but also the management efficiency of the building outer wall surface layer is improved, ensuring the safety and reliability of the building outer wall surface layer in long-term use.

[0108] Embodiment 7

[0109] Please refer to Figure 1 and Figure 2 , specifically: a non-contact building outer wall surface layer quality detection method, comprising the following steps:

[0110] Step one, first use multiple environmental monitoring devices to monitor the external environment state of the building outer wall surface layer in real time, and obtain an external environment state data set;

[0111] Step two, according to the external environment state data set, an external environment influence coefficient Xwh is constructed, and if the external environment influence coefficient Xwh exceeds the threshold, a surface layer quality detection instruction is issued;

[0112] Step three, after receiving the surface layer quality detection instruction, the building outer wall surface layer is photographed by a shooting device arranged on the front of the building outer wall, and a finish layer surface image and a thermal insulation layer distribution thermal image are generated, respectively, after uniform division and feature extraction, related damage data information and related thermal bridge distribution data information are obtained;

[0113] Step four, in addition, the related damage data information and the related thermal bridge distribution data information are analyzed, and combined with the external environment influence coefficient Xwh, the surface layer quality evaluation index Zmc is fitted and obtained;

[0114] Step five, finally, the pre-set quality assessment threshold P is compared with the surface layer quality assessment index Zmc to comprehensively judge whether the quality detection of the current building outer wall surface layer is qualified, and a corresponding detection report is generated.

[0115] While the embodiments of the application have been illustrated and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the spirit and scope of the application, which is defined by the appended claims and their equivalents.

Claims

1. A non-contact building exterior wall surface quality detection system, characterized in that: The system comprises an external environment monitoring module, an external environment analysis module, a surface layer detection module, a quality comprehensive evaluation module and a feedback module. The external environment monitoring module is configured to utilize multiple environment monitoring devices to monitor the external environment state of the building outer wall surface layer in real time and obtain an external environment state data set. The external environment analysis module is configured to construct an external environment influence coefficient Xwh based on the external environment state data set. The surface layer detection module is configured to, after receiving the surface layer quality detection instruction, capture the building outer wall surface layer based on a shooting device arranged on the front of the building outer wall to generate a surface layer surface image and a thermal insulation layer distribution heat map, respectively, and obtain related damage data information and related thermal bridge distribution data information after uniform division and feature extraction. The quality comprehensive evaluation module is configured to analyze the related damage data information and the related thermal bridge distribution data information and combine the external environment influence coefficient Xwh to fit and obtain a surface layer quality evaluation index Zmc. The feedback module is configured to set a quality evaluation threshold P in advance and compare and analyze the quality evaluation threshold P with the surface layer quality evaluation index Zmc to comprehensively determine whether the quality of the current building outer wall surface layer is qualified and generate a corresponding detection report.

2. The non-contact building exterior wall surface quality detection system according to claim 1, characterized in that: The external environment monitoring module comprises a monitoring unit and a preprocessing unit. The monitoring unit is configured to utilize multiple environment monitoring devices arranged in the external environment of the building outer wall surface layer to monitor the external environment state of the building outer wall surface layer in real time and obtain an external environment state data set. The preprocessing unit is configured to preprocess related data information in the external environment state data set, and the preprocessing comprises noise removal, missing value filling and data smoothing operation.

3. The non-contact building exterior wall surface quality detection system according to claim 2, characterized in that: The external environment analysis module comprises an analysis unit and a warning unit. The analysis unit is used for feature extraction on the acquired external environment state data set, and the statistical mean value algorithm is combined to acquire the temperature minimum value Twd min , the temperature maximum value Twd max , the humidity mean value , and the light intensity mean value in the monitoring period respectively. By associating the temperature minimum value Twd min and the temperature maximum value Twd max , the temperature difference value ΔTwd in the monitoring period is acquired, and the temperature difference value ΔTwd is acquired through the following formula: ΔTwd = Twd max - Twd min ; The external environment influence coefficient Xwh is obtained through the following formula: where ΔTwd represents a temperature difference value, where H represents a humidity average value, where α1, α2, and α3 represent weight values of the temperature difference value ΔTwd, the humidity average value H, and the light intensity average value I, respectively, and A represents a first correction constant. where α1, α2, and α3 represent weight values of the temperature difference value ΔTwd, the humidity average value H, and the light intensity average value I, respectively, and A represents a first correction constant.​ 4. The non-contact building exterior wall surface quality detection system according to claim 3, characterized in that: The warning unit is configured to compare and analyze the external environment influence coefficient Xwh with a preset threshold to determine whether the current external environment has an impact on the quality of the building outer wall surface layer. The surface layer detection module comprises a detection unit and an extraction unit. ​ 5. The non-contact building exterior wall surface quality detection system according to claim 4, characterized in that: ​ The detection unit is used for, after receiving the surface layer quality detection instruction, capturing and shooting the surface state of the finishing layer and the distribution of the thermal insulation layer of the building outer wall surface layer by the visible light high-definition camera and the infrared thermal imaging shooting device arranged on the front of the building outer wall, and dynamically adjusting the shooting distance, angle and focal length according to the shape and size characteristics of the building outer wall surface layer, in combination with the automatic control technology, to obtain the finishing layer surface image and the thermal insulation layer distribution thermal image respectively; the wavelet denoising technology is used to remove the noise of the obtained finishing layer surface image and thermal insulation layer distribution thermal image, and the gamma correction image enhancement technology is used to adjust the brightness distribution and contrast of the finishing layer surface image and the thermal insulation layer distribution thermal image; The thermal insulation layer distribution thermal image is evenly divided into a plurality of thermal image detection regions, and the plurality of thermal image detection regions of the thermal insulation layer distribution thermal image are marked as a first thermal image detection region T1, a second thermal image detection region T2, a third thermal image detection region T3,..., and an mth thermal image detection region Tm. The extraction unit is used for identifying and detecting the related damage data information of the finishing layer surface by using the finishing layer surface image, wherein the related damage data information includes the arch area Sgq, the crack length Lcd, the pit area Skd and the peeling area Sqp; and the related thermal bridge distribution data information of the thermal insulation layer distribution is identified and detected by using the thermal insulation layer distribution thermal image, wherein the related thermal bridge distribution data information includes the thermal bridge area Rmj and the thermal bridge change rate Vbh of each thermal image detection region.

6. The non-contact building exterior wall surface quality detection system according to claim 5, characterized in that: The quality comprehensive evaluation module includes a damage analysis unit, a thermal bridge prediction unit and a comprehensive evaluation unit. The damage analysis unit is used for analyzing the related damage data information, and constructing a damage coefficient Xps after dimensionless processing, wherein the damage coefficient Xps is obtained by the following formula: Xps = β1*Sgq + β2*Lcd + β3*Skd + β4*Sqp + B; In the formula, Sgq represents the arch area, Lcd represents the crack length, Skd represents the pit area, and Sqp represents the peeling area, wherein β1, β2, β3 and β4 represent the weight values of the arch area Sgq, the crack length Lcd, the pit area Skd and the peeling area Sqp respectively, and B represents a second correction constant.

7. The non-contact building exterior wall surface quality detection system according to claim 6, characterized in that: The thermal bridge prediction unit is used for calculating the thermal bridge distribution density Mrq in the corresponding thermal image detection region according to the related thermal bridge distribution data information, and the thermal bridge distribution density Mrq is obtained by the following formula: wherein is expressed as the average thermal bridge area, and δRmj is expressed as the standard deviation of the thermal bridge area; According to the related thermal bridge distribution data information and the thermal bridge distribution density Mrq, and after dimensionless processing, the thermal bridge distribution coefficient Xfb is calculated, and the thermal bridge distribution coefficient Xfb is obtained by the following formula: where Vbh i denotes the rate of change of thermal bridge within the ith thermal map detection region, denotes the average rate of change of thermal bridge, Mrq i denotes the distribution density of thermal bridge within the ith thermal map detection region, denotes the average distribution density of thermal bridge, where i = 1, 2, 3,..., m, m denotes the number of detection regions, and γ1 and γ2 both denote weight values.

8. The non-contact building exterior wall surface quality detection system of claim 6, wherein: The comprehensive evaluation unit is used for analyzing the related damage data information and the related thermal bridge distribution data information, and fitting to obtain a surface layer quality evaluation index Zmc after dimensionless processing in combination with an external environmental influence coefficient Xwh, wherein the surface layer quality evaluation index Zmc is obtained by the following formula: In the formula, Xps represents a breakage coefficient, and Xfb represents a thermal bridge distribution coefficient, wherein, and respectively represent weight values of the external environment influence coefficient Xwh, the breakage coefficient Xps, and the thermal bridge distribution coefficient Xfb, and C represents a third correction constant.

9. The non-contact building exterior wall surface quality detection system of claim 8, wherein: The feedback module is used to set a quality evaluation threshold P in advance and compare and analyze the quality evaluation index Zmc of the surface layer to comprehensively judge whether the quality detection of the current building outer wall surface layer is qualified, and the specific process is as follows: If the quality evaluation index Zmc of the surface layer exceeds the quality evaluation threshold P, it indicates that the quality detection of the current building outer wall surface layer is qualified, and a first detection report is generated, which shows that the quality of the surface layer meets the safety and design standards, and it is recommended to continue to use, and no additional repair measures are needed. If the quality evaluation index Zmc of the surface layer does not exceed the quality evaluation threshold P, it indicates that the quality detection of the current building outer wall surface layer is unqualified, and a second detection report is generated, which shows that the quality of the surface layer does not meet the safety and design standards, and it is found in the detection that the facing layer has cracks and peeling phenomenon, and the thermal insulation layer is unevenly distributed, and it is recommended to repair the damaged facing layer as soon as possible and strengthen the thermal insulation performance of the thermal insulation layer.

10. A non-contact building outer wall surface layer quality detection method for realizing the non-contact building outer wall surface layer quality detection system according to any one of claims 1-9, characterized in that: The method comprises the following steps: Step one, first, use multiple environmental monitoring devices to monitor the external environment state of the building outer wall surface layer in real time, and obtain an external environment state data set; Step two, second, construct an external environment influence coefficient Xwh according to the external environment state data set, and if the external environment influence coefficient Xwh exceeds the threshold, issue a surface layer quality detection instruction; Step three, after receiving the surface layer quality detection instruction, use the shooting device arranged on the front of the building outer wall to shoot the building outer wall surface layer, generate a facing layer surface image and a thermal insulation layer distribution thermal image respectively, and after uniform division and feature extraction, obtain related damage data information and related thermal bridge distribution data information respectively; Step four, in addition, analyze the related damage data information and the related thermal bridge distribution data information, and combine the external environment influence coefficient Xwh to fit and obtain the quality evaluation index Zmc of the surface layer; Step five, finally, set a quality evaluation threshold P in advance, and compare and analyze the quality evaluation index Zmc of the surface layer to comprehensively judge whether the quality detection of the current building outer wall surface layer is qualified, and generate a corresponding detection report.

Images