CN-122016484-A - Abnormal recognition method and system for bonding detection data

CN122016484ACN 122016484 ACN122016484 ACN 122016484ACN-122016484-A

Abstract

The invention relates to the technical field of performance test and discloses a method and a system for identifying abnormal bonding detection data, wherein the method comprises the steps of applying force to a wall body arranged in a concrete column through a pressurizing rod, and collecting bonding detection data of the wall body in real time through a strain sensor arranged on the concrete column; the method comprises the steps of determining the stress fluctuation intensity of a wall body according to the stress fluctuation value in the bonding detection data, carrying out fluctuation characteristic spectroscopy on the stress fluctuation intensity based on time stamp information in the stress fluctuation value to construct a stress fluctuation intensity spectrum of the wall body, carrying out self-adaptive spectral domain feature merging on the fluctuation intensity value in the fluctuation intensity spectrum to obtain an aggregate fluctuation intensity value of the wall body, judging the aggregate fluctuation intensity value exceeding a preset intensity threshold value as bonding data abnormality to obtain a bonding abnormality judgment result of the wall body, and generating a bonding abnormality identification report of the wall body according to the bonding abnormality judgment result.

Inventors

ZHANG XIANMING
ZHANG YIZHOU
ZHANG YIJIN
ZHU JIAHUA
TANG XIAOWU

Assignees

杭州明磊工程技术有限公司
浙江省建筑装饰行业协会
浙江杰立建设集团有限公司

Dates

Publication Date: 20260512
Application Date: 20260414

Claims (10)

1. A method for identifying anomalies in bond-detecting data, the method comprising: S1, applying force to a wall body arranged in a concrete column through a pressurizing rod, and acquiring bonding detection data of the wall body in real time through a strain sensor arranged on the concrete column; S2, determining the stress fluctuation intensity of the wall body according to the stress fluctuation value in the bonding detection data; s3, carrying out fluctuation characteristic spectroscopy on the stress fluctuation intensity based on the timestamp information in the stress fluctuation value so as to construct a stress fluctuation intensity spectrum of the wall body; S4, carrying out self-adaptive spectral domain feature merging on the fluctuation intensity values in the fluctuation intensity spectrum to obtain an aggregate fluctuation intensity value of the wall body; s5, judging the aggregate fluctuation intensity value exceeding a preset intensity threshold value as abnormal bonding data, and obtaining a bonding abnormality judgment result of the wall body; s6, generating a bonding abnormality identification report of the wall body according to the bonding abnormality judgment result.
2. The method for identifying anomalies according to claim 1, wherein applying a force to a wall disposed within a concrete column via a compression bar and collecting, in real time, the bonding detection data of the wall via a strain sensor disposed on the concrete column, comprises: applying load to a wall body arranged in a concrete column through a pressurizing rod, and synchronously starting a strain sensor positioned on the concrete column to obtain an analog strain electric signal of the wall body; And performing signal characteristic interpretation on the simulated strain electric signals to obtain bonding detection data of the wall body.
3. The method for anomaly identification of bonding detection data according to claim 1, wherein the determining the strength of the stress fluctuation of the wall based on the stress fluctuation value in the bonding detection data comprises: taking a stress level central value of the stress fluctuation value sequence in the bonding detection data in a preset time window as a representative reference value of a corresponding time window; identifying peaks and valleys of the stress fluctuation value sequence within the preset time window according to the representative reference value; And carrying out quotient evaluation on the absolute amplitude difference between the peak value and the valley value and the representative reference value to obtain the stress fluctuation intensity of the wall body.
4. The method of claim 1, wherein said characterizing the stress fluctuation intensity based on the time stamp information in the stress fluctuation value to construct a stress fluctuation intensity spectrum of the wall, comprises: organizing the stress fluctuation intensity and the timestamp information in the stress fluctuation value sequence into time domain fluctuation signals of the wall body; mapping the time domain fluctuation signal from a time dimension to a frequency dimension to obtain the strength information of the wall body; And constructing a stress wave intensity spectrum of the wall body by taking the frequency in the frequency dimension as an abscissa and the intensity information as an ordinate.
5. The method for anomaly identification of bonding detection data according to claim 4, wherein mapping the time domain fluctuation signal from a time dimension to a frequency dimension to obtain the strength information of the wall comprises: performing smooth transition processing on the time domain fluctuation signal to reduce spectrum leakage of the time domain fluctuation signal and obtain a smooth time domain fluctuation signal of the wall; Performing Fourier transform on the smooth time domain fluctuation signal to obtain a smooth frequency domain fluctuation signal of the wall body; And carrying out multidimensional parameter coupling on the frequency component and the amplitude component in the smooth frequency domain fluctuation signal to obtain the fluctuation amplitude of the smooth frequency domain fluctuation signal, and taking the fluctuation amplitude as the intensity information of the wall body.
6. The method for anomaly identification of bonding detection data according to claim 1, wherein the performing adaptive spectral domain feature merging on the fluctuation intensity values in the fluctuation intensity spectrum to obtain the aggregate fluctuation intensity values of the wall body comprises: Identifying continuous adjacent frequency points with the amplitude exceeding a preset noise reference in the stress wave motion intensity spectrum; Defining a frequency band interval of the continuous adjacent frequency points to obtain an effective fluctuation frequency band of the wall; Prioritizing the effective fluctuation bands based on the magnitude of the average amplitude in the effective fluctuation bands, and defining the maximum effective fluctuation band of the average amplitude as the dominant fluctuation band of the wall; taking the central point of the frequency range covered by the dominant fluctuation frequency band as a characteristic frequency, and taking the average value of the amplitudes of the frequency points in the dominant fluctuation frequency band as a characteristic amplitude; And generating an aggregate fluctuation intensity value of the wall body according to the characteristic frequency and the characteristic amplitude.
7. The method for anomaly identification of bonding detection data according to claim 6, wherein the aggregate fluctuation intensity value is calculated as follows: ; In the formula, Representing the value of the intensity of the aggregate fluctuation, Represent the first The characteristic amplitudes of the individual dominant fluctuation bands, Represent the first The characteristic frequencies of each of said dominant fluctuation bands, Representing the total number of dominant fluctuating bands.
8. The method for identifying abnormal bonding detection data according to claim 1, wherein the step of determining the aggregate fluctuation intensity value exceeding a preset intensity threshold as abnormal bonding data to obtain the abnormal bonding determination result of the wall body comprises the steps of: Comparing the aggregate fluctuation intensity value with a preset intensity threshold value one by one, and when the aggregate fluctuation intensity value exceeds the preset intensity threshold value, performing abnormal marking on the detection time period and the position of the aggregate fluctuation intensity value to obtain abnormal detection time period and abnormal position information of the wall body; And collecting the normal detection period and the abnormal position information to obtain a bonding abnormality judgment result of the wall body.
9. The method for identifying an anomaly in bonding detection data according to claim 1, wherein the generating a bonding anomaly identification report for the wall based on the bonding anomaly determination result comprises: taking the abnormal detection period and the aggregate fluctuation intensity value in the bonding abnormal judgment result as abnormal fluctuation data of the wall body; Based on the stress wave intensity spectrum, carrying out key influence analysis on the abnormal fluctuation data to obtain main frequency components of the abnormal fluctuation data; Integrating the abnormality detection period, the abnormality fluctuation data and the main frequency component into structural description data of the wall body; And carrying out document template recombination on the structural description data to obtain a bonding abnormality identification report of the wall body.
10. A bonding detection data anomaly identification system for implementing a bonding detection data anomaly identification method of claim 1, said system comprising: The data acquisition module is used for applying force to a wall body arranged in the concrete column through the pressurizing rod and acquiring bonding detection data of the wall body in real time through the strain sensor arranged on the concrete column; the stress fluctuation intensity evaluation module is used for determining the stress fluctuation intensity of the wall body according to the stress fluctuation value in the bonding detection data; The stress fluctuation intensity spectrum construction module is used for carrying out fluctuation characteristic spectroscopy on the stress fluctuation intensity based on the timestamp information in the stress fluctuation value so as to construct a stress fluctuation intensity spectrum of the wall body; the fluctuation intensity aggregation module is used for carrying out self-adaptive spectral domain feature merging on the fluctuation intensity values in the fluctuation intensity spectrum to obtain aggregate fluctuation intensity values of the wall body; the abnormality judging module is used for judging the aggregate fluctuation intensity value exceeding a preset intensity threshold value as abnormal bonding data, and obtaining a bonding abnormality judging result of the wall body; And the report generation module is used for generating a bonding abnormality identification report of the wall body according to the bonding abnormality judgment result.

Description

Abnormal recognition method and system for bonding detection data Technical Field The invention relates to the technical field of performance testing, in particular to a bonding detection data anomaly identification method and system. Background In the field of safety detection of building engineering structures, the bonding performance of a wall body and a concrete column is one of core indexes for determining the stability of the whole structure, and abnormal identification of bonding detection data is a key link for guaranteeing the validity of a detection result. Along with the expansion of the construction engineering scale and the improvement of the structural complexity, the acquisition frequency and the analysis precision requirements of the bonding detection data are continuously improved, the timeliness and the accuracy of the data anomaly identification are directly related to the overall effect of engineering quality control, and the requirements of the industry on efficient bonding detection data anomaly identification schemes are more urgent. The conventional bonding detection data anomaly identification technology has obvious performance shortboards, mostly adopts manual research and judgment or a single fixed threshold comparison method, cannot accurately sense the dynamic change rule of stress fluctuation, is difficult to develop multi-dimensional spectral domain feature mining on fluctuation data, causes frequent missed judgment and misjudgment of the anomaly data and seriously affects the reliability of detection conclusion, and meanwhile, the conventional technology lacks a self-adaptive feature merging mechanism, has complicated and low efficiency on the aggregation analysis flow of multiband fluctuation data, cannot quickly complete the positioning and tracing of the anomaly data, is difficult to efficiently generate a standardized anomaly identification report, and has no adaptability to the timeliness and accuracy requirements of the engineering site on the detection data processing in the whole processing mode. Disclosure of Invention The invention provides a bonding detection data anomaly identification method and a bonding detection data anomaly identification system, which are used for solving the problems in the background technology. In order to achieve the above object, the present invention provides a method for identifying abnormality of bonding detection data, comprising: S1, applying force to a wall body arranged in a concrete column through a pressurizing rod, and acquiring bonding detection data of the wall body in real time through a strain sensor arranged on the concrete column; S2, determining the stress fluctuation intensity of the wall body according to the stress fluctuation value in the bonding detection data; s3, carrying out fluctuation characteristic spectroscopy on the stress fluctuation intensity based on the timestamp information in the stress fluctuation value so as to construct a stress fluctuation intensity spectrum of the wall body; S4, carrying out self-adaptive spectral domain feature merging on the fluctuation intensity values in the fluctuation intensity spectrum to obtain an aggregate fluctuation intensity value of the wall body; s5, judging the aggregate fluctuation intensity value exceeding a preset intensity threshold value as abnormal bonding data, and obtaining a bonding abnormality judgment result of the wall body; s6, generating a bonding abnormality identification report of the wall body according to the bonding abnormality judgment result. In a preferred embodiment, the applying force to the wall body placed in the concrete column through the pressurizing rod, and collecting the bonding detection data of the wall body in real time through the strain sensor positioned on the concrete column, includes: applying load to a wall body arranged in a concrete column through a pressurizing rod, and synchronously starting a strain sensor positioned on the concrete column to obtain an analog strain electric signal of the wall body; And performing signal characteristic interpretation on the simulated strain electric signals to obtain bonding detection data of the wall body. In a preferred embodiment, the determining the stress fluctuation intensity of the wall according to the stress fluctuation value in the bonding detection data includes: taking a stress level central value of the stress fluctuation value sequence in the bonding detection data in a preset time window as a representative reference value of a corresponding time window; identifying peaks and valleys of the stress fluctuation value sequence within the preset time window according to the representative reference value; And carrying out quotient evaluation on the absolute amplitude difference between the peak value and the valley value and the representative reference value to obtain the stress fluctuation intensity of the wall body. In a preferred embodiment, the step of performing wave c