Connection quality detection method for building outer wall and base connection structure

Abstract

The invention relates to the technical field of building outer wall connection quality detection, in particular to a connection quality detection method for a building outer wall and base connection structure, and the method comprises the steps: obtaining the stress data of a screw rod and the vibration data of the connection structure in the working process of the connection structure; the method comprises the following steps: performing modal decomposition on stress data in a vibration period, obtaining a vibration interference degree according to a correlation between each modal vector and the vibration data and a fluctuation degree of an element in each modal vector, further obtaining a sudden change significant degree of stress on a screw in each vibration period, and calculating a sudden change credible coefficient according to the vibration interference degree, obtaining a sudden change characteristic value of the stress on the screw in each vibration period by combining the sudden change significant degree; and according to the abrupt change characteristic values of the stress on the screw rod in all the vibration periods, obtaining abrupt change differences so as to detect the connection quality of the building outer wall and the base connection structure. According to the invention, the accuracy of detecting the connection quality of the connection structure can be improved.

Description

Technical Field

[0001] This application relates to the technical field of building exterior wall connection quality inspection, and specifically relates to a connection quality inspection method for the connection structure between a building exterior wall and a base. Background Art

[0002] The connection structure between a building exterior wall and a base generally consists of components such as a base, an exterior wall panel, a clamping plate, a card slot, a sliding groove, a convex block, a sliding block, and a screw rod. Through the mutual cooperation between the components within the connection structure, the stable clamping and limiting of the exterior wall panel are realized, and then the connection between the building exterior wall and the base is realized. However, if the stability of the connection structure between the building exterior wall and the base is poor, it will affect the stable clamping and limiting during the installation of the building exterior wall panel, thereby easily reducing the reliability of the connection and the overall stability of the building exterior wall. Therefore, by detecting the connection stability of the connection structure between the building exterior wall and the base, it helps to improve the reliability of the connection and the overall stability of the building exterior wall, and the detection of connection stability has important practical significance.

[0003] At present, most of the stress data on the screw rod is monitored in real time through intelligent stress sensors, and the stress data is analyzed for volatility, so as to identify the loosening characteristics on the screw rod and realize the detection of the connection quality within the connection structure. However, during the working process of the connection structure, the connection structure is prone to complex vibration phenomena, which will generate vibration interference on the stress data on the screw rod, affecting the accuracy of identifying the loosening of the screw rod, resulting in the inability to accurately detect the connection quality of the connection structure, and thus unable to effectively improve the reliability of the connection and the overall stability of the building exterior wall. Summary of the Invention

[0004] In order to solve the above technical problems, this application provides a connection quality inspection method for the connection structure between a building exterior wall and a base to solve the existing problems.

[0005] The connection quality inspection method for the connection structure between a building exterior wall and a base of this application adopts the following technical solutions: An embodiment of this application provides a connection quality inspection method for the connection structure between a building exterior wall and a base, including the following steps: Obtain the stress data on the screw rod and the vibration data of the connection structure during the working process of the connection structure through sensors; Obtain the vibration period of the connection structure through the vibration data, decompose the stress data mode within the vibration period, and obtain the vibration interference degree generated by the connection structure vibration on the stress on the screw rod within each vibration period according to the correlation between each modal vector and the vibration data, as well as the fluctuation degree of the elements within each modal vector; Construct the mutation feature vectors for each vibration period based on the extreme value difference degree of the stress data within each vibration period, analyze the cumulative results of the data within the mutation feature vectors, obtain the mutation significance degree of the stress on the screw for each vibration period, calculate the mutation credibility coefficient according to the vibration interference degree, and then combine the mutation significance degree to obtain the mutation feature values of the stress on the screw for each vibration period; Obtain the mutation difference based on the mutation feature values of the stress on the screw for all vibration periods to detect the connection quality of the connection structure between the building exterior wall and the foundation.

[0006] Preferably, the method for obtaining the vibration period of the connection structure is as follows: Perform frequency domain conversion on the vibration data within a preset time duration to obtain the frequency spectrum diagram of the vibration data, and count the frequency corresponding to the maximum amplitude in the frequency spectrum diagram. The reciprocal of this frequency is used as a vibration period of the connection structure.

[0007] Preferably, the method for calculating the vibration interference degree generated by the vibration of the connection structure on the stress on the screw within each vibration period is as follows: ; where is the vibration interference degree generated by the vibration of the connection structure on the stress on the screw within the t-th vibration period, is the number of the modal vector corresponding to the t-th vibration period, is the exponential normalization function, is the covariance between the j-th modal vector corresponding to the t-th vibration period and the vibration data vector of the t-th vibration period. Among them, the vibration data within each vibration period are arranged in chronological order to form the vibration data vector of each vibration period, is the degree of dispersion of the elements within the j-th modal vector corresponding to the t-th vibration period.

[0008] Preferably, the method for constructing the mutation feature vectors for each vibration period is as follows: For each vibration period, form the extreme value vector of each vibration period by arranging the extreme values at all extreme value points of the stress data within the vibration period in chronological order; analyze the deviation degree of the elements within the extreme value vector to construct the extreme value difference vector for each vibration period; subtract the mean value of the extreme value difference vector from each element within the extreme value difference vector to obtain the mutation feature vector.

[0009] Preferably, the method for constructing the extreme value difference vector for each vibration period is as follows: Take the absolute value of each element within the first-order difference vector of the extreme value vector to obtain the extreme value difference vector for each vibration period.

[0010] Preferably, the method for obtaining the mutation significance degree of the stress on the screw for each vibration period is as follows: For each vibration period, all elements in the mutation feature vector are normalized to obtain a mutation weight vector, and each element in the mutation weight vector is used as the weight of each element in the extreme value difference vector. All elements in the extreme value difference vector are weighted and summed to obtain the mutation significance degree of the stress on the screw for each vibration period.

[0011] Preferably, the calculation method of the mutation credibility coefficient is as follows: , where is the mutation credibility coefficient of the t-th vibration period, is the exponential function with the natural constant as the base, is the degree of vibration interference generated by the vibration of the connection structure on the stress of the screw within the t-th vibration period.

[0012] Preferably, the method for obtaining the mutation eigenvalue of the stress on the screw for each vibration period is as follows: Calculate the sum value of the number 1 and the mutation credibility coefficient of each vibration period, and calculate the exponential normalization result of the product of the sum value and the mutation significance degree of the stress on the screw for each vibration period, which is used as the mutation eigenvalue of the stress on the screw for each vibration period.

[0013] Preferably, the method for obtaining the mutation difference is as follows: Perform threshold segmentation on the mutation eigenvalues of the stress on the screw for all vibration periods, and output the segmentation threshold; respectively count the mean values of all mutation eigenvalues less than or equal to the segmentation threshold and all mutation eigenvalues greater than the segmentation threshold, and denote them as the first mean value and the second mean value respectively; take the difference between the second mean value and the first mean value as the mutation difference.

[0014] Preferably, the method for detecting the connection quality of the connection structure between the building exterior wall and the foundation includes: when the mutation difference is higher than the preset normal difference, it is determined that the connection quality is unqualified; otherwise, the connection quality is qualified.

[0015] This application has at least the following beneficial effects: This application extracts the vibration periods on the connection structure and, according to the modal analysis results of the stress data within each vibration period, more comprehensively synthesizes the vibration interference characteristics within each modal vector, improves the accuracy of measuring the degree of vibration interference on the stress of the screw, and enables more effective reduction of the vibration interference generated on the stress of the screw subsequently; The analysis of the stress data within the vibration period in this application combines the extreme value difference of the stress data and the mutation characteristics of the range difference, comprehensively measures the significance of the stress mutation on the screw, and considering that the measurement of the significance of the stress mutation on the screw will be affected by the vibration interference on the screw, constructs a mutation credibility coefficient using the degree of vibration interference of the stress on the screw, uses the mutation credibility coefficient to reduce the influence caused by the vibration interference on the screw, more accurately obtains the mutation characteristic value of the stress on the screw, improves the accuracy of analyzing the stress mutation characteristics on the screw, avoids affecting the accuracy of identifying the loosening of the screw, and realizes more accurate detection of the connection quality of the connection structure; Through the mutation characteristic value of the stress on the screw, this application further analyzes the mutation difference between the average levels of the stress mutation characteristics on the screw during normal operation and abnormal operation, so as to more accurately judge whether the screw connection is loose, improve the accuracy of detecting the connection quality of the connection structure, and avoid affecting the reliability of the connection and the overall stability of the building exterior wall. Brief Description of the Drawings

[0016] In order to more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 It is a flowchart of the steps of the method for detecting the connection quality of the connection structure between the building exterior wall and the base provided by this application. Detailed Embodiments

[0018] In order to further elaborate on the technical means and effects adopted by this application to achieve the intended invention purpose, the following, in combination with the drawings and preferred embodiments, details the specific embodiments, structures, features and their effects of the method for detecting the connection quality of the connection structure between the building exterior wall and the base proposed according to this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, terms such as "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the article or device including the said element. In addition, the term "and / or" used herein includes any and all combinations of any one of the one or more related listed items. All technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs.

[0020] The following specifically describes the specific solution of the connection quality detection method for the connection structure between the building exterior wall and the base provided by this application in conjunction with the attached drawings.

[0021] A connection quality detection method for the connection structure between a building exterior wall and a base provided by an embodiment of this application. Specifically, please refer to Figure 1 , including the following steps: Step 1: Obtain the stress data on the screw and the vibration data of the connection structure during the working process of the connection structure through sensors.

[0022] Install an intelligent stress sensor on the screw in the connection structure between the building exterior wall and the base. The intelligent stress sensor can collect the stress data on the screw in real time during the working process of the connection structure. At the same time, install an intelligent vibration sensor at the position where the screw is connected. The intelligent vibration sensor can collect the vibration data of the connection structure in real time during the working process of the connection structure. The sampling rates of the intelligent stress sensor and the intelligent vibration sensor are both 100Hz.

[0023] During the working process of the connection structure, the connection structure is prone to complex vibration phenomena, which will generate strong vibration interference on the stress data on the screw under normal conditions, easily confuse the abnormal stress data that appears when the connection position on the screw becomes loose, and will have an interference effect on the accuracy of detecting the connection quality in the connection structure. Therefore, it is necessary to reduce or even eliminate the vibration interference in the stress data on the screw, improve the reliability of the stress data on the screw, and achieve more accurate detection of the connection quality in the connection structure.

[0024] Step 2: Obtain the vibration period of the connection structure through the vibration data, perform modal decomposition on the stress data within the vibration period, and obtain the degree of vibration interference generated by the vibration of the connection structure on the stress of the screw within each vibration period according to the correlation between each modal vector and the vibration data, as well as the degree of fluctuation of the elements within each modal vector.

[0025] As the working process continues, due to the continuous influence of vibration during the working process, the connection position of the screw is prone to loosening. At this time, the stress on the screw will undergo a sudden change phenomenon, resulting in the inability to provide stable clamping and limiting for the clamping plate, thereby affecting the reliability of the connection and the overall stability of the building exterior wall. Therefore, in order to improve the reliability of the connection and the overall stability of the building exterior wall, it is necessary to accurately analyze the sudden change characteristics of the stress when the screw connection becomes loose.

[0026] Input the vibration data within the preset time duration during the working process of the connection structure into the discrete Fourier transform algorithm, and use the discrete Fourier transform to obtain the frequency spectrum diagram of the vibration data. The discrete Fourier transform is a well-known technology, and the specific process will not be elaborated here. In this embodiment, the preset time duration is set to 10s, and the implementer can set the duration according to the actual vibration situation.

[0027] Furthermore, count the frequency corresponding to the maximum amplitude in the frequency spectrum diagram, and take the reciprocal of this frequency as a vibration period of the connection structure. The vibration data within one vibration period reflects the vibration data characteristics of the connection structure during normal operation. If the vibration characteristics of the stress on the screw under one vibration period are more similar to the vibration characteristics of the connection structure, it indicates that the interference effect of the vibration generated during work is greater at this time, and it is easier to confuse the loosening characteristics of the screw. Therefore, it is more necessary to reduce the vibration interference characteristics of the screw, thereby improving the accuracy of detecting the connection quality of the connection structure.

[0028] Furthermore, denote the vector formed by the vibration data within each vibration period in chronological order as the vibration data vector of each vibration period, and denote the vector formed by the stress data on the screw corresponding to each vibration period in chronological order as the stress data vector of each vibration period. The vibration data vector and the stress data vector respectively reflect the vibration data characteristics and stress data characteristics within one vibration period.

[0029] Input the stress data vectors of each vibration period into the modal decomposition algorithm, and use the modal decomposition algorithm to obtain the modal vectors of the stress data vectors of each vibration period. The modal decomposition algorithm can be the VMD variational mode decomposition algorithm (variational mode decomposition) or the EMD empirical mode decomposition algorithm (Empirical Mode Decomposition). This invention does not make specific restrictions. In this embodiment, the EMD empirical mode decomposition algorithm is selected for modal decomposition, where the number of decomposed modal layers K is 2, and two modal vectors of the stress data vectors of each vibration period are obtained. The EMD empirical mode decomposition algorithm is a well-known technology, and the specific process will not be elaborated here.

[0030] Since the stress on the screw is affected by vibration interference, the modal vector of the stress on the screw will contain more vibration characteristics. If the vibration characteristics in the modal vector of the stress on the screw are more significant, to a certain extent, it indicates that the stress on the screw is more affected by vibration interference, and it is more necessary to reduce or even eliminate the vibration interference in the stress data on the screw to improve the reliability of the stress data analysis on the screw.

[0031] Through the above analysis, calculate the degree of vibration interference generated by the vibration of the connection structure on the stress of the screw in each vibration period: ; where is the degree of vibration interference generated by the vibration of the connection structure on the stress of the screw in the t-th vibration period, is the number of the modal vector corresponding to the t-th vibration period, is the exponential normalization function, is the covariance between the j-th modal vector corresponding to the t-th vibration period and the vibration data vector of the t-th vibration period, is the degree of dispersion of the elements in the j-th modal vector corresponding to the t-th vibration period. The measurement method of the degree of dispersion can be variance, standard deviation or coefficient of variation. In this embodiment, the standard deviation is selected to measure the degree of dispersion. The calculations of exponential normalization, covariance and standard deviation are all well-known technologies, and the specific process will not be elaborated.

[0032] It can be understood that the degree of vibration interference reflects the vibration interference characteristics generated by the vibration on the connection structure on the stress of the screw. If the correlation degree between the modal vector and the vibration data vector is greater, it indicates that the modal vector is more likely to contain more vibration characteristics, and the higher the degree of dispersion, the greater the change in the vibration interference reflected. Therefore, the weighted sum of the degree of dispersion is calculated using the exponential normalization result of the correlation degree, so that the vibration interference characteristics in each modal vector can be more comprehensively integrated, and the accuracy of measuring the degree of vibration interference on the stress of the screw can be improved.

[0033] Step 3: According to the degree of extreme value difference of the stress data in each vibration period, construct the mutation feature vector of each vibration period, analyze the cumulative result of the data in the mutation feature vector, obtain the mutation significance degree of the stress on the screw in each vibration period, and calculate the mutation credibility coefficient according to the degree of vibration interference, and then combine the mutation significance degree to obtain the mutation feature value of the stress on the screw in each vibration period.

[0034] At the same time, analyze the degree of stress mutation in each vibration period time segment. During the working process of the connection structure, if the connection position of the screw becomes loose, it is easy to cause the stress on the screw to mutate, and the higher the significance degree of the stress mutation on the screw, the more it can reflect the phenomenon of screw connection looseness.

[0035] Further, input the stress data vectors of each vibration cycle into the extreme point detection algorithm. Use the extreme point detection algorithm to obtain all the extreme points within the stress data vectors. The extreme point detection algorithm is a well-known technology, and the specific process will not be elaborated here.

[0036] The vector formed by arranging the extreme values at all the extreme points within the stress data vector in chronological order is denoted as the extreme value vector of each vibration cycle. Calculate the first-order difference vector of the extreme value vector. This first-order difference vector reflects the difference between all adjacent maximum and minimum values in the change of the screw stress data. The higher the extreme value difference between adjacent extreme points, the more prominent the significant degree of stress mutation on the screw.

[0037] Further, after taking the absolute value of all elements in the first-order difference vector of the extreme value vector, the extreme value difference vector of each vibration cycle is obtained. Generally, the higher the extreme value difference at adjacent positions is compared with the average level of the extreme value difference, the more prominent the stress mutation characteristics on the screw at that adjacent position. Therefore, in this embodiment, subtract the mean value of the extreme value difference vector from each element in the extreme value difference vector to obtain the mutation characteristic vector. Furthermore, in order to analyze the significant degree of stress mutation on the screw more accurately, normalize all elements in the mutation characteristic vector. The normalized elements form the mutation weight vector. Among them, in this embodiment, the exponential normalization method is adopted, and the implementer can select the normalization method by himself in the actual application scenario. And use the normalized elements in the mutation weight vector to perform weighted summation on the elements in the extreme value difference vector to obtain the significant degree of stress mutation on the screw in each vibration cycle.

[0038] However, the measurement of the significant degree of stress mutation on the screw in each vibration cycle will be affected by the vibration interference on the screw, thereby reducing the accuracy of analyzing the tightness of the connection on the screw and affecting the detection of the connection quality in the connection structure.

[0039] In order to reduce the interference effect caused by vibration on the connection structure and improve the reliability of analyzing the stress mutation characteristics, calculate the mutation characteristics through the mutation credibility coefficient. The calculation formula of the mutation credibility coefficient is: , where is the mutation credibility coefficient of the t-th vibration cycle, is the exponential function with the natural constant as the base. The mutation credibility coefficient reflects the credibility of the stress mutation on the screw. The larger the mutation credibility coefficient, the smaller the influence of the vibration interference on the stress on the screw during the corresponding vibration cycle.

[0040] To reduce the interference effect caused by vibration on the connection structure, calculate the sum value of the mutation credibility coefficient of the number 1 and the t-th vibration cycle, and calculate the exponential normalization result of the product of the sum value and the mutation significance degree of the stress on the screw during the t-th vibration cycle, which is used as the mutation characteristic value of the stress on the screw during the t-th vibration cycle, so as to measure the mutation situation of the stress on the screw, reduce the influence caused by vibration interference on the screw, improve the accuracy of analyzing the mutation characteristics of the stress on the screw, avoid affecting the accuracy of identifying screw loosening, and achieve more accurate detection of the connection quality of the connection structure.

[0041] Step 4: Obtain the mutation difference based on the mutation characteristic values of the stress on the screw during all vibration cycles, so as to detect the connection quality of the connection structure between the building exterior wall and the base.

[0042] Under normal circumstances, due to the continuous influence of vibration during the operation of the screw, it is easy for the connection position of the screw to become loose. At this time, the stress on the screw will undergo a mutation phenomenon. There are significant differences between the stress mutation characteristics of the screw during normal operation and those during screw connection loosening. When the difference between the two exceeds the normal difference, it can more accurately indicate the loosening phenomenon at the screw connection, and the tightening degree of the screw connection should be inspected to avoid affecting the connection reliability and the overall stability of the building exterior wall.

[0043] Further, input the mutation characteristic values of the stress on the screw during all vibration cycles into the maximum inter-class variance algorithm. The output segmentation threshold of the maximum inter-class variance algorithm is used. The maximum inter-class variance algorithm is a well-known technology, and the specific process will not be elaborated here.

[0044] Respectively, count the mean values of all mutation characteristic values less than or equal to the segmentation threshold and all mutation characteristic values greater than the segmentation threshold, and denote them as the first mean value and the second mean value respectively. Take the difference between the second mean value and the first mean value as the mutation difference. Among them, the first mean value represents the average level of the stress mutation characteristics of the screw during normal operation; the second mean value represents the average level of the stress mutation characteristics of the screw during abnormal operation. When the mutation difference is higher than the preset normal difference, it is judged that the screw becomes loose during the operation, indicating that the connection quality of the screw in the connection structure is unqualified; when the mutation difference is lower than the normal difference, it is judged that the screw does not become loose during the operation, indicating that the connection quality of the screw in the connection structure is qualified. In this embodiment, the value of the normal difference in the example is 0.25.

[0045] It should be understood that references to "one embodiment" or "some embodiments" or the like described in the specification of the present application mean that a particular feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of the present application. Thus, when "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. appear in different places in this specification, they do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0046] It should be noted that the above sequence of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above specific embodiments of this specification have been described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous. At the same time, the magnitude of the serial numbers of the steps in the embodiments does not mean the sequence of execution is prior or subsequent. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments in this specification.

[0047] The above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and should all be included within the protection scope of the present application.

Claims

1. A method for detecting the connection quality of the connection structure between the building exterior wall and the base, characterized in that Including the following steps: Obtain the stress data on the screw during the working process of the connection structure and the vibration data of the connection structure through sensors; Obtain the vibration period of the connection structure from the vibration data, perform modal decomposition on the stress data within the vibration period, and obtain the degree of vibration interference caused by the vibration of the connection structure on the stress of the screw according to the correlation between each modal vector and the vibration data, as well as the fluctuation degree of the elements within each modal vector; Construct a mutation feature vector for each vibration period according to the extreme value difference degree of the stress data within each vibration period, analyze the cumulative result of the data within the mutation feature vector, obtain the mutation significance degree of the stress on the screw for each vibration period, calculate the mutation credibility coefficient according to the vibration interference degree, and then combine the mutation significance degree to obtain the mutation feature value of the stress on the screw for each vibration period; Obtain the mutation difference according to the mutation feature values of the stress on the screw for all vibration periods, so as to detect the connection quality of the connection structure between the building exterior wall and the base.

2. The connection quality inspection method for the connection structure between the building exterior wall and the base according to claim 1, characterized in that, The method for obtaining the vibration period of the connection structure is as follows: Perform frequency domain conversion on the vibration data within a preset time length to obtain the frequency spectrum diagram of the vibration data, and statistically calculate the frequency corresponding to the maximum amplitude in the frequency spectrum diagram. The reciprocal of this frequency is used as a vibration period of the connection structure.

3. The connection quality inspection method for the connection structure between the building exterior wall and the base according to claim 2, characterized in that, The calculation method for the degree of vibration interference caused by the vibration of the connection structure on the stress of the screw within each vibration period is as follows: ; where, is the degree of vibration interference generated by the vibration of the connection structure on the stress of the screw during the t-th vibration cycle, is the number of the modal vector corresponding to the t-th vibration cycle, is the exponential normalization function, is the covariance between the j-th modal vector corresponding to the t-th vibration cycle and the vibration data vector of the t-th vibration cycle, where the vibration data within each vibration cycle is composed of the vibration data vectors of each vibration cycle in chronological order, is the degree of dispersion of the elements within the j-th modal vector corresponding to the t-th vibration cycle.

4. The connection quality detection method for the connection structure between the building exterior wall and the base according to claim 1, characterized in that, The construction method for the mutation feature vector of each vibration period is as follows: For each vibration period, form an extreme value vector for each vibration period by arranging the extreme values at all extreme value points of the stress data within the vibration period in chronological order; analyze the deviation degree of the elements within the extreme value vector, and construct an extreme value difference vector for each vibration period; subtract the mean value of the extreme value difference vector from each element within the extreme value difference vector to obtain the mutation feature vector.

5. The connection quality inspection method for the connection structure between the building exterior wall and the base according to claim 4, characterized in that, The construction method for the extreme value difference vector of each vibration period is as follows: Take the absolute value of each element within the first-order difference vector of the extreme value vector to obtain the extreme value difference vector of each vibration period.

6. The connection quality inspection method for the connection structure between the building exterior wall and the base according to claim 1, characterized in that, The method for obtaining the mutation significance degree of the stress on the screw for each vibration period is as follows: For each vibration period, normalize all elements within the mutation feature vector to obtain a mutation weight vector, and use each element within the mutation weight vector as the weight of each element within the extreme value difference vector, and perform weighted summation on all elements within the extreme value difference vector to obtain the mutation significance degree of the stress on the screw for each vibration period.

7. The connection quality inspection method for the connection structure between the building exterior wall and the base according to claim 1, characterized in that, The calculation method for the mutation credibility coefficient is as follows: , where is the mutation credibility coefficient of the t-th vibration period, is the exponential function with the natural constant as the base, is the degree of vibration interference generated by the vibration of the connecting structure on the stress of the screw during the t-th vibration period.

8. The connection quality inspection method for the connection structure between the building exterior wall and the base according to claim 1, characterized in that, The method for obtaining the mutation feature value of the stress on the screw for each vibration period is as follows: Calculate the sum value of the number 1 and the mutation credibility coefficient of each vibration period, and calculate the exponential normalization result of the product of the sum value and the mutation significance degree of the stress on the screw for each vibration period, which is used as the mutation feature value of the stress on the screw for each vibration period.

9. The connection quality inspection method for the connection structure between the building exterior wall and the base according to claim 1, characterized in that The method for obtaining the mutation difference is as follows: Perform threshold segmentation on the mutation feature values of the stress on the screw for all vibration periods, and output the segmentation threshold; respectively statistically calculate the mean value of all mutation feature values less than or equal to the segmentation threshold and the mean value of all mutation feature values greater than the segmentation threshold, and record them as the first mean value and the second mean value respectively; use the difference between the second mean value and the first mean value as the mutation difference.

10. The connection quality inspection method for the connection structure between the building exterior wall and the base according to claim 1, characterized in that, Testing the connection quality of the connection structure between the building exterior wall and the base includes: when the mutation difference is higher than the preset normal difference, determining that the connection quality is unqualified; otherwise, the connection quality is qualified.

Images