Data analysis early warning method and system for concrete defect detection

Abstract

The invention discloses a data analysis early warning method and system for concrete defect detection, and the method comprises the steps: dividing a concrete detection region, laying defect detection equipment, setting a scientific monitoring period, collecting the detection abnormal data of each period, and carrying out the traceability marking; constructing a traceability sample set and a traceability behavior matrix based on the abnormal data, and calculating regional center early warning weights among different detection devices; and determining an early warning relationship according to the weight, counting the behavior proportion and generating a sorted early warning table. The system correspondingly comprises a data acquisition and traceability marking module, a traceability sample set construction module, a traceability behavior matrix construction and weight calculation module, an early warning relation determination and early warning table generation module and a main control unit. According to the invention, systematic integration and correlation analysis of concrete defect detection data are realized, the manual screening cost is reduced, the pertinence and timeliness of defect early warning are improved, and a quick response decision is provided for safety maintenance of a concrete structure.

Description

Technical Field

[0001] This invention relates to the field of concrete defect detection technology, and specifically to a data analysis and early warning method and system for concrete defect detection. Background Technology

[0002] Concrete structures are widely used in various engineering projects such as sluice gates, pumping stations, gravity dams, arch dams, bridges, tunnels, and high-rise buildings. Their structural safety is directly related to the overall stability and service life of the project. Timely detection and early warning of concrete defects (such as cracks, insufficient strength, abnormal moisture content, etc.) are key to ensuring structural safety.

[0003] Existing concrete defect detection technologies suffer from the following shortcomings: First, data collection is fragmented, relying heavily on single-device monitoring or manual inspections, making it difficult to comprehensively cover all areas of large concrete structures and prone to missing defect data. Second, data analysis lacks systematicity; abnormal data is not correlated with detection equipment or monitoring cycles, making it difficult to trace the source and development trend of defects. Third, the early warning mechanism is imperfect; staff must manually sift through massive amounts of data, which not only consumes a lot of time and energy but is also susceptible to subjective factors, leading to delayed or insufficiently targeted early warnings. Fourth, no correlation analysis has been established between detection equipment, making it impossible to capture potential large-scale defect risks through abnormal correlations between equipment in different areas, thus failing to meet the defect monitoring needs of large-scale, complex concrete structures. Summary of the Invention

[0004] This invention proposes a data analysis and early warning method and system for concrete defect detection, in order to solve the technical problems of scattered data, inefficient analysis, and delayed early warning in the prior art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: A data analysis and early warning method for concrete defect detection according to the present invention includes the following steps: S1. Divide the concrete testing area and deploy defect detection equipment. Set the defect monitoring cycle according to the development law of concrete defects. Collect and report the abnormal detection indicators in each defect monitoring cycle in real time. Mark the defect detection equipment for the abnormal detection indicators. S2. Statistically analyze the abnormal detection indicators of each defect detection device in different defect monitoring cycles, and construct a source tracing sample set for each defect detection device corresponding to different defect monitoring cycles; S3. Based on the source tracing sample set, establish a source tracing behavior matrix, clarify the mapping relationship between the source tracing sample set and the source tracing behavior matrix, and take the detection area where each defect detection device is located as the center of the simulated area, calculate the area center warning weight between the defect detection device and other defect detection devices. S4. Determine the relevant early warning objects and early warning relationships among defect detection devices based on the regional center early warning weight, and count the percentage of times each defect detection device is identified as a relevant early warning object when it acts as a simulated regional center. Sort the data by percentage, generate an early warning table, and output it.

[0006] Preferably, step S1 includes the following steps: S11. Based on the concrete structure, divide the inspection area and, based on the concrete structure characteristics and working conditions of the inspection area, deploy defect detection equipment in the corresponding inspection area. S12. A pre-set defect monitoring cycle is established based on the defect development pattern of the concrete structure under the influence of the service environment and structural type. S13. The backend records and aggregates the abnormal detection indicators fed back by each defect detection device in each defect monitoring cycle in real time to form the corresponding abnormal trigger feedback set in each defect monitoring cycle, and marks the defect detection device that fed back the abnormal detection indicators to form abnormal feedback traceability features.

[0007] Preferably, step S2 includes the following steps: S21. Construct an anomaly triggering feedback set corresponding to the defect monitoring cycle, wherein the anomaly triggering feedback set is as follows: ,in, For the first The abnormal trigger feedback set for each defect monitoring cycle, where R and E represent the code sequence number of the defect detection equipment and the detection abnormality index item, respectively. For the e-th abnormal indicator item, For the first A defect detection device, For the first One defect monitoring cycle; S22. Based on the abnormal trigger feedback set, statistically analyze the abnormal detection indicators reported by each defect detection device in different defect monitoring cycles to form a source tracing sample set, which is as follows:

[0008] in, Indicates defect detection equipment During the defect monitoring cycle The source tracing sample set is formed when internal feedback detects abnormal indicators.

[0009] Preferably, step S3 includes the following steps: S31. Based on the source tracing sample set, construct a source tracing behavior matrix, where the row number corresponds to the code sequence number of the defect monitoring cycle, and the column number corresponds to the code sequence number of the detected abnormal indicator item. This forms a mapping relationship between the source tracing sample set and the source tracing behavior matrix. If the detected abnormal indicator item exists in the source tracing sample set, then the 1st item in the source tracing behavior matrix will be... Line number The matrix element value of column 1 is recorded as 1. If the detected anomaly indicator does not exist in the source tracing sample set, then the value of column 1 in the source tracing behavior matrix is ​​set to 1. Line number The matrix element value of a column is denoted as 0; S32. Based on the mapping relationship between the traceability sample set and the traceability behavior matrix, the traceability behavior matrix of the defect detection equipment is obtained; S33. Based on the source tracing behavior matrix, take the detection area where the defect detection equipment is located as the center of the simulated area of ​​the concrete structure, and evaluate the regional center warning weight between the defect detection equipment and the defect detection equipment. The formula for calculating the regional center early warning weight is as follows:

[0010] in, This indicates the x-th defect detection device. The corresponding generated source tracing behavior matrix, where x ≠ r. Indicates defect detection equipment Source tracing behavior matrix With defect detection equipment Source tracing behavior matrix The number of 1s contained in the result of a logical AND operation. Indicates defect detection equipment Source tracing behavior matrix With defect detection equipment Source tracing behavior matrix The number of 1s contained after a logical OR operation.

[0011] Preferably, step S4 includes the following steps: S41. Determine the early warning relationship between defect detection devices based on the regional center early warning weight; The early warning relationships are as follows: Here, argmax{} is a feedback function used to determine the defect detection device corresponding to the simulated regional center when the regional center warning weight is maximized. This locks the warning relationship between defect detection devices. The corresponding simulated area center is the defect detection equipment. Relevant early warning targets; S42, Statistical Defect Detection Equipment When serving as the center of a simulated region, the percentage of behaviors identified as relevant early warning targets is used by the defect detection equipment. The corresponding behavior frequency accounts for a certain percentage of the defect detection equipment The ratio of the total number of corresponding behaviors; S43. Sort each defect detection device in descending order of the percentage of behavior frequency, generate a data analysis and early warning table, and output it to the staff port.

[0012] A data analysis and early warning system for concrete defect detection, the system comprising: The data acquisition and traceability marking module is used to divide the concrete testing area and deploy defect detection equipment, set the defect monitoring cycle according to the development law of concrete defects, collect the abnormal indicators in each defect monitoring cycle in real time, and trace the defect detection equipment that reports abnormal indicators. The traceability sample set construction module is used to statistically analyze the abnormal detection indicators of each defect detection device in different defect monitoring cycles and construct the traceability sample set corresponding to each defect detection device in different defect monitoring cycles. The traceability behavior matrix construction and weight calculation module is used to build a traceability behavior matrix based on the traceability sample set, clarify the mapping relationship between the traceability sample set and the traceability behavior matrix, and calculate the regional center warning weight between the defect detection equipment and other defect detection equipment, with the detection area where each defect detection equipment is located as the center of the simulated area. The early warning relationship determination and early warning table generation module is used to determine the relevant early warning objects and early warning relationships among defect detection devices based on the early warning weight of the regional center, to count the percentage of times each defect detection device is identified as a relevant early warning object when it is used as a simulated regional center, and to generate and output a data analysis early warning table by sorting the percentages.

[0013] Preferably, the data acquisition and traceability marking module includes: The detection area division and equipment deployment unit is used to divide the detection area according to the characteristics of the concrete structure and the working conditions, and to deploy the corresponding defect detection equipment in each area. The monitoring cycle setting unit is used to set the defect monitoring cycle based on the defect development pattern of concrete structures affected by the service environment and structural type. The abnormal data collection unit is used to record and collect the abnormal detection indicators reported by each defect detection device in each monitoring cycle in real time. The traceability marking unit is used to mark the defect detection equipment for feedback detection anomaly indicators, forming anomaly feedback traceability features.

[0014] Preferably, the source tracing sample set construction module includes: The abnormal indicator statistics unit is used to count the abnormal detection indicators reported by each defect detection device in different defect monitoring cycles based on the abnormal trigger feedback set. The traceability sample set generation unit is used to construct a traceability sample set containing feedback anomaly indicators for each defect detection device within the corresponding defect monitoring cycle.

[0015] Preferably, the source tracing behavior matrix construction and weight calculation module includes: The source tracing behavior matrix construction unit is used to construct a source tracing behavior matrix based on the source tracing sample set, with row numbers corresponding to monitoring periods and column numbers corresponding to abnormal indicator items, thus clarifying the mapping relationship between the sample set and the matrix. The regional center early warning weight calculation unit is used to calculate the regional center early warning weight between each defect detection device and other detection devices, taking the detection area where each defect detection device is located as the simulated regional center.

[0016] Preferably, the early warning relationship determination and early warning table generation module includes: The early warning relationship determination unit is used to determine the relevant early warning objects and early warning relationships among defect detection devices based on the early warning weight of the regional center. The behavior percentage statistics unit is used to count the percentage of behaviors that are identified as relevant warning objects when each defect detection device is used as the center of the simulated area. The early warning table generation and output unit is used to sort data by the percentage of frequency of each behavior from largest to smallest, generate a data analysis early warning table, and output it to the staff's port.

[0017] As can be seen from the above technical solution, this invention provides a data analysis and early warning method for concrete defect detection. Compared with the prior art, this invention has the following advantages: by dividing the concrete detection area, deploying defect detection equipment, and setting a scientific monitoring cycle, abnormal detection data from each cycle are collected and traced back to their source; based on the abnormal data, a traceability sample set and a traceability behavior matrix are constructed, and the regional center early warning weights among different detection equipment are calculated; based on the weights, the early warning relationships are determined, the behavior proportions are statistically analyzed, and a sorted early warning table is generated. This invention achieves systematic integration and correlation analysis of concrete defect detection data, reduces manual screening costs, improves the pertinence and timeliness of defect early warning, and provides rapid response decisions for the safe maintenance of concrete structures. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating a data analysis and early warning method for concrete defect detection according to the present invention. Figure 2 This is a structural block diagram of a data analysis and early warning system for concrete defect detection according to the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments.

[0020] like Figure 1 As shown in the figure, this embodiment provides a data analysis and early warning method for concrete defect detection. The method includes the following steps: Step S1: Divide the concrete testing area and deploy defect detection equipment. Set the defect monitoring cycle according to the development law of concrete defects. Collect abnormal detection indicators in each defect monitoring cycle in real time and trace the defect detection equipment that reports abnormal indicators. This embodiment takes the concrete structure of a cross-sea bridge as the application object. The bridge is 3,200 meters long and the concrete structure includes 28 piers, 3,000 meters of bridge deck and guardrails on both sides. The environment is a marine environment with high humidity and salt spray corrosion. It is necessary to achieve monitoring and early warning of five defect indicators of the entire structure, namely crack width, concrete strength, moisture content, carbonation depth and steel corrosion, to ensure the safe operation of the bridge. Inspection area division: Based on the structural differences and stress characteristics of the bridge piers, bridge deck, and guardrails, 25 inspection areas are divided (28 bridge piers are merged into 10 areas, the bridge deck is divided into 12 areas, and the guardrails are divided into 3 areas), with each area ranging from 300 to 600 square meters. Equipment deployment: One multi-functional defect detection device is deployed in each detection area, for a total of 25 devices. All devices support real-time detection and data transmission of 5 defect indicators. Monitoring cycle: Based on the bridge's historical defect data, it takes an average of 28 days for concrete defects to develop to a critical state from their appearance. Therefore, the defect monitoring cycle is set at 7 days to ensure that key nodes in the development of defects are captured. Staff can configure weight thresholds in the backend: set the regional center warning weight threshold to 0.65. If it is higher than the threshold, it is considered that there is a strong correlation between the detection devices and an anomaly requires a key warning.

[0021] Furthermore, based on the concrete structure, inspection areas are divided, and based on the concrete structure characteristics and working conditions of the inspection areas, defect detection equipment is deployed in the corresponding inspection areas, with one defect detection equipment deployed for each inspection area. The defect monitoring cycle is preset, and the defect monitoring cycle is formulated based on the defect development pattern of concrete structures under the influence of the service environment and structural type. The backend records and aggregates the abnormal detection indicators fed back by each defect detection device in each defect monitoring cycle in real time, so as to form the corresponding abnormal trigger feedback set in each defect monitoring cycle, and marks the defect detection device that feeds back the abnormal detection indicators to form abnormal feedback traceability features. For example, 25 detection areas were set up and 25 detection devices were deployed. The installation positions of the devices were confirmed by structural mechanics analysis to ensure that there were no blind spots in the monitoring. Based on the development law of concrete defects in marine environment, a 7-day monitoring cycle was set. After 3 consecutive monitoring cycles (21 days), the abnormal data collection unit collected a total of 108 abnormal indicators (32 abnormal crack widths, 28 abnormal moisture content, and 48 abnormal indicators). The source tracing and marking unit marked the detection device corresponding to each abnormal data, forming 108 abnormal feedback source tracing features.

[0022] Step S2: Statistically analyze the abnormal detection indicators of each defect detection device in different defect monitoring cycles, and construct a source tracing sample set for each defect detection device corresponding to different defect monitoring cycles; Furthermore, let the i-th defect monitoring cycle be denoted as Let the r-th defect detection device be denoted as Let the e-th abnormal indicator be denoted as This will detect abnormal indicators in the feedback. Defect detection equipment The anomaly feedback traceability features generated during traceability tagging are denoted as follows: Defect monitoring cycle The corresponding exception trigger feedback set is denoted as Where R and E represent the code numbers of the defect detection equipment and the detection anomaly index item, respectively; Based on the anomaly trigger feedback set, the anomaly indicators reported by each defect detection device during different defect monitoring cycles are statistically analyzed to form a traceability sample set, denoted as . , Indicates defect detection equipment During the defect monitoring cycle The source tracing sample set formed when detecting abnormal indicators using internal feedback; For example, the abnormal indicator statistics unit classifies and statistically analyzes 108 abnormal data from 25 devices, of which 18 devices reported abnormal indicators (7 devices in the pier area, 8 devices in the bridge deck area, and 3 devices in the guardrail area); the source tracing sample set generation unit constructs source tracing sample sets for the 18 devices in 3 monitoring cycles, generating a total of 54 sample sets, each of which fully contains the abnormal indicator items and monitoring cycle information of the corresponding device.

[0023] Step S3: Establish a source tracing behavior matrix based on the source tracing sample set, clarify the mapping relationship between the source tracing sample set and the source tracing behavior matrix, and calculate the regional center warning weight between the defect detection equipment and other defect detection equipment, taking the detection area where each defect detection equipment is located as the center of the simulated area. Furthermore, based on the source tracing sample set, a source tracing behavior matrix is ​​constructed, where the row number corresponds to the code sequence number of the defect monitoring cycle, and the column number corresponds to the code sequence number of the detected abnormal indicator item. This forms a mapping relationship between the source tracing sample set and the source tracing behavior matrix: if the detected abnormal indicator item... Existing in the source sample set In the process, the element value in the i-th row and e-th column of the source tracing behavior matrix is ​​recorded as 1. If an abnormal indicator item is detected... Not present in the source sample set In this case, the element value in the i-th row and e-th column of the traceability behavior matrix is ​​recorded as 0; based on the mapping relationship between the traceability sample set and the traceability behavior matrix, the defect detection equipment is obtained. The source tracing behavior matrix, denoted as ; Based on the source tracing behavior matrix, with defect detection equipment The detection area is located at the center of a simulated area of ​​a concrete structure, and the defect detection equipment is being evaluated. With defect detection equipment Regional center early warning weight In the formula, This indicates the x-th defect detection device. The corresponding generated source tracing behavior matrix, where x ≠ r. Indicates defect detection equipment Source tracing behavior matrix With defect detection equipment Source tracing behavior matrix The number of 1s contained in the result of a logical AND operation. Indicates defect detection equipment Source tracing behavior matrix With defect detection equipment Source tracing behavior matrix The number of 1s contained after a logical OR operation; For example, the source tracing behavior matrix construction unit constructs a source tracing behavior matrix based on 54 source tracing sample sets, with row numbers corresponding to 3 monitoring periods (codes 1-3) and column numbers corresponding to 5 abnormal indicators (codes 1-5), generating a total of 18 matrices corresponding to each device, ensuring that the matrix is ​​filled without omissions; the regional center early warning weight calculation unit uses each device as the simulation center and calculates the weights of the other 24 devices, among which 11 devices have weights higher than 0.65 (threshold) with at least 4 other devices, indicating that there are strong correlation anomalies in these areas.

[0024] Step S4: Determine the relevant early warning objects and early warning relationships among defect detection devices based on the regional center early warning weight, and count the percentage of times each defect detection device is identified as a relevant early warning object when it acts as a simulated regional center. Sort the data by percentage, generate an early warning table, and output it. Furthermore, based on the regional center early warning weights, the early warning relationships among defect detection devices are determined: Where argmax{} is the feedback function, used to determine the defect detection device corresponding to the simulated regional center when the regional center warning weight is maximized. Then, the warning relationship between the defect detection devices is locked as follows: Defect detection devices The corresponding simulated area center is the defect detection equipment. Relevant early warning targets; Statistical Defect Detection Equipment When serving as the center of a simulated region, the percentage of behaviors identified as relevant early warning targets is used by defect detection equipment. The corresponding behavior frequency accounts for a certain percentage of the defect detection equipment The ratio of the total number of corresponding behaviors; The defect detection equipment is sorted in descending order of the percentage of occurrences, and a data analysis and early warning table is generated and output to the staff's interface. Based on the weighted results, the early warning relationship determination unit identified 11 devices as core early warning targets and clarified their corresponding relevant early warning areas. The behavior proportion statistics unit counted the percentage of behaviors of each device when it was the simulation center. Among them, the proportions of devices in the three bridge pier areas were 21%, 17%, and 14%, respectively, ranking in the top three, indicating that the bridge pier area is a key area with high incidence of defects and high correlation. The early warning table generation and output unit generated an early warning table according to the proportion. Based on the early warning table, the staff focused on checking the top 5 high-proportion areas and found 3 potential crack expansion risks, which improved the efficiency of the investigation.

[0025] like Figure 2 As shown in this second embodiment: a data analysis and early warning system for concrete defect detection is provided to be applicable to the first embodiment above. The system includes: a data acquisition and traceability marking module, a traceability sample set construction module, a traceability behavior matrix construction and weight calculation module, an early warning relationship determination and early warning table generation module, and a main control unit for coordinating data interaction and process control of each module, so as to realize full-process data analysis and early warning from data acquisition to early warning table output. The data acquisition and traceability marking module is used to divide the concrete testing area and deploy defect detection equipment, set the defect monitoring cycle according to the development law of concrete defects, collect the abnormal indicators in each defect monitoring cycle in real time, and trace the defect detection equipment that reports abnormal indicators. The data acquisition and traceability marking module includes a detection area division and equipment deployment unit, a monitoring cycle setting unit, an abnormal data collection unit, and a traceability marking unit. The detection area division and equipment deployment unit is used to divide the detection area according to the characteristics of the concrete structure and the working conditions, and to deploy the corresponding defect detection equipment in each area. The monitoring cycle setting unit is used to set the defect monitoring cycle based on the defect development pattern of concrete structures affected by the service environment and structural type. The abnormal data collection unit is used to record and collect the abnormal detection indicators reported by each defect detection device in each monitoring cycle in real time. The traceability marking unit is used to mark the defect detection equipment for feedback detection anomaly indicators, forming anomaly feedback traceability features; The traceability sample set construction module is used to statistically analyze the abnormal detection indicators of each defect detection device in different defect monitoring cycles and construct the traceability sample set corresponding to each defect detection device in different defect monitoring cycles. The source tracing sample set construction module includes an anomaly indicator statistics unit and a source tracing sample set generation unit; The abnormal indicator statistics unit is used to count the abnormal detection indicators reported by each defect detection device in different defect monitoring cycles based on the abnormal trigger feedback set. The traceability sample set generation unit is used to construct a traceability sample set containing feedback anomaly indicators for each defect detection device within the corresponding defect monitoring cycle. The traceability behavior matrix construction and weight calculation module is used to build a traceability behavior matrix based on the traceability sample set, clarify the mapping relationship between the traceability sample set and the traceability behavior matrix, and calculate the regional center warning weight between the defect detection equipment and other defect detection equipment, with the detection area where each defect detection equipment is located as the center of the simulated area. The source tracing behavior matrix construction and weight calculation module includes a source tracing behavior matrix construction unit and a regional center early warning weight calculation unit. The source tracing behavior matrix construction unit is used to construct a source tracing behavior matrix based on the source tracing sample set, with row numbers corresponding to monitoring periods and column numbers corresponding to abnormal indicator items, thus clarifying the mapping relationship between the sample set and the matrix. The regional center early warning weight calculation unit is used to calculate the regional center early warning weight between each defect detection device and other detection devices, with the detection area where each defect detection device is located as the simulated regional center. The module for determining early warning relationships and generating early warning tables is used to determine the relevant early warning objects and early warning relationships among defect detection devices based on the early warning weight of the regional center, to count the percentage of times each defect detection device is identified as a relevant early warning object when it is used as a simulated regional center, to generate and output a data analysis early warning table by sorting the percentages. The early warning relationship determination and early warning table generation module includes an early warning relationship determination unit, a behavior proportion statistics unit, and an early warning table generation and output unit. The early warning relationship determination unit is used to determine the relevant early warning objects and early warning relationships among defect detection devices based on the early warning weight of the regional center. The behavior percentage statistics unit is used to count the percentage of behaviors that are identified as relevant warning objects when each defect detection device is used as the center of the simulated area. The early warning table generation and output unit is used to sort data by the percentage of frequency of each behavior from largest to smallest, generate a data analysis early warning table, and output it to the staff's port.

[0026] In summary, this invention provides a data analysis and early warning method for concrete defect detection. Compared with existing technologies, this invention has the following advantages: by dividing the concrete detection area, deploying defect detection equipment, and setting a scientific monitoring cycle, abnormal detection data from each cycle are collected and traced back to their source; based on the abnormal data, a traceability sample set and a traceability behavior matrix are constructed, and the regional center early warning weights among different detection equipment are calculated; based on the weights, early warning relationships are determined, the proportion of behaviors is statistically analyzed, and a sorted early warning table is generated. This invention achieves systematic integration and correlation analysis of concrete defect detection data, reduces manual screening costs, improves the pertinence and timeliness of defect early warning, and provides rapid response decisions for the safety maintenance of concrete structures (such as bridges and factories).

[0027] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., a solid-state disk (SSD)).

[0028] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0029] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0030] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data analysis and early warning method for concrete defect detection according to the present invention, characterized in that, Includes the following steps: S1. Divide the concrete testing area and deploy defect detection equipment. Set the defect monitoring cycle according to the development law of concrete defects. Collect and report the abnormal detection indicators in each defect monitoring cycle in real time. Mark the defect detection equipment for the abnormal detection indicators. S2. Statistically analyze the abnormal detection indicators of each defect detection device in different defect monitoring cycles, and construct a source tracing sample set for each defect detection device corresponding to different defect monitoring cycles; S3. Based on the source tracing sample set, establish a source tracing behavior matrix, clarify the mapping relationship between the source tracing sample set and the source tracing behavior matrix, and take the detection area where each defect detection device is located as the center of the simulated area, calculate the area center warning weight between the defect detection device and other defect detection devices. S4. Determine the relevant early warning objects and early warning relationships among defect detection devices based on the regional center early warning weight, and count the percentage of times each defect detection device is identified as a relevant early warning object when it acts as a simulated regional center. Sort the data by percentage, generate an early warning table, and output it.

2. The holographic enhancement system for strong interference environments based on reverse diffusion generation according to claim 1, characterized in that: The steps included in S1 are as follows: S11. Based on the concrete structure, divide the inspection area and, based on the concrete structure characteristics and working conditions of the inspection area, deploy defect detection equipment in the corresponding inspection area. S12. A pre-set defect monitoring cycle is established based on the defect development pattern of concrete structures affected by the service environment and structural type. S13. The backend records and aggregates the abnormal detection indicators fed back by each defect detection device in each defect monitoring cycle in real time to form the corresponding abnormal trigger feedback set in each defect monitoring cycle, and marks the defect detection device that fed back the abnormal detection indicators to form abnormal feedback traceability features.

3. The data analysis and early warning method for concrete defect detection according to claim 2, characterized in that: S2 includes the following steps: S21. Construct an anomaly triggering feedback set corresponding to the defect monitoring cycle, wherein the anomaly triggering feedback set is as follows: ,in, For the first The abnormal trigger feedback set for each defect monitoring cycle, where R and E represent the code sequence number of the defect detection equipment and the detection abnormality index item, respectively. For the e-th abnormal indicator item, For the first A defect detection device, For the first One defect monitoring cycle; S22. Based on the abnormal trigger feedback set, statistically analyze the abnormal detection indicators reported by each defect detection device in different defect monitoring cycles to form a source tracing sample set, which is as follows: in, Indicates defect detection equipment During the defect monitoring cycle The source tracing sample set is formed when internal feedback detects abnormal indicators.

4. The data analysis and early warning method for concrete defect detection according to claim 3, characterized in that: S3 includes the following steps: S31. Based on the source tracing sample set, construct a source tracing behavior matrix, where the row number corresponds to the code sequence number of the defect monitoring cycle, and the column number corresponds to the code sequence number of the detected abnormal indicator item. This forms a mapping relationship between the source tracing sample set and the source tracing behavior matrix. If the detected abnormal indicator item exists in the source tracing sample set, then the 1st item in the source tracing behavior matrix will be... Line number The matrix element value of column 1 is recorded as 1. If the detected anomaly indicator does not exist in the source tracing sample set, then the value of column 1 in the source tracing behavior matrix is ​​set to 1. Line number The matrix element value of a column is denoted as 0; S32. Based on the mapping relationship between the traceability sample set and the traceability behavior matrix, the traceability behavior matrix of the defect detection equipment is obtained; S33. Based on the source tracing behavior matrix, take the detection area where the defect detection equipment is located as the center of the simulated area of ​​the concrete structure, and evaluate the regional center warning weight between the defect detection equipment and the defect detection equipment. The formula for calculating the regional center early warning weight is as follows: in, This indicates the x-th defect detection device. The corresponding generated source tracing behavior matrix, where x ≠ r. Indicates defect detection equipment Source tracing behavior matrix With defect detection equipment Source tracing behavior matrix The number of 1s contained in the result of a logical AND operation. Indicates defect detection equipment Source tracing behavior matrix With defect detection equipment Source tracing behavior matrix The number of 1s contained after a logical OR operation.

5. The data analysis and early warning method for concrete defect detection according to claim 4, characterized in that: S4 includes the following steps: S41. Determine the early warning relationship between defect detection devices based on the regional center early warning weight; The early warning relationships are as follows: Here, argmax{} is a feedback function used to determine the defect detection device corresponding to the simulated regional center when the regional center warning weight is maximized. This locks the warning relationship between defect detection devices. The corresponding simulated area center is the defect detection equipment. Relevant early warning targets; S42, Statistical Defect Detection Equipment When serving as the center of a simulated region, the percentage of behaviors identified as relevant early warning targets is used by the defect detection equipment. The corresponding behavior frequency accounts for a certain percentage of the defect detection equipment The ratio of the total number of corresponding behaviors; S43. Sort each defect detection device in descending order of the percentage of behavior frequency, generate a data analysis and early warning table, and output it to the staff port.

6. A data analysis and early warning system for concrete defect detection, characterized in that: The system includes: The data acquisition and traceability marking module is used to divide the concrete testing area and deploy defect detection equipment, set the defect monitoring cycle according to the development law of concrete defects, collect the abnormal indicators in each defect monitoring cycle in real time, and trace the defect detection equipment that reports abnormal indicators. The traceability sample set construction module is used to statistically analyze the abnormal detection indicators of each defect detection device in different defect monitoring cycles and construct the traceability sample set corresponding to each defect detection device in different defect monitoring cycles. The traceability behavior matrix construction and weight calculation module is used to build a traceability behavior matrix based on the traceability sample set, clarify the mapping relationship between the traceability sample set and the traceability behavior matrix, and calculate the regional center warning weight between the defect detection equipment and other defect detection equipment, with the detection area where each defect detection equipment is located as the center of the simulated area. The early warning relationship determination and early warning table generation module is used to determine the relevant early warning objects and early warning relationships among defect detection devices based on the early warning weight of the regional center, to count the percentage of times each defect detection device is identified as a relevant early warning object when it is used as a simulated regional center, and to generate and output a data analysis early warning table by sorting the percentages.

7. A data analysis and early warning system for concrete defect detection according to claim 6, characterized in that: The data acquisition and traceability marking module includes: The detection area division and equipment deployment unit is used to divide the detection area according to the characteristics of the concrete structure and the working conditions, and to deploy the corresponding defect detection equipment in each area. The monitoring cycle setting unit is used to set the defect monitoring cycle based on the defect development pattern of concrete structures affected by the service environment and structural type. The abnormal data collection unit is used to record and collect the abnormal detection indicators reported by each defect detection device in each monitoring cycle in real time. The traceability marking unit is used to mark the defect detection equipment for feedback detection anomaly indicators, forming anomaly feedback traceability features.

8. The data analysis and early warning method for concrete defect detection according to claim 7, characterized in that: The source tracing sample set construction module includes: The abnormal indicator statistics unit is used to count the abnormal detection indicators reported by each defect detection device in different defect monitoring cycles based on the abnormal trigger feedback set. The traceability sample set generation unit is used to construct a traceability sample set containing feedback anomaly indicators for each defect detection device within the corresponding defect monitoring cycle.

9. A data analysis and early warning method for concrete defect detection according to claim 8, characterized in that: The source tracing behavior matrix construction and weight calculation module includes: The source tracing behavior matrix construction unit is used to construct a source tracing behavior matrix based on the source tracing sample set, with row numbers corresponding to monitoring periods and column numbers corresponding to abnormal indicator items, thus clarifying the mapping relationship between the sample set and the matrix. The regional center early warning weight calculation unit is used to calculate the regional center early warning weight between each defect detection device and other detection devices, taking the detection area where each defect detection device is located as the simulated regional center.

10. A data analysis and early warning method for concrete defect detection according to claim 9, characterized in that: The early warning relationship determination and early warning table generation module includes: The early warning relationship determination unit is used to determine the relevant early warning objects and early warning relationships among defect detection devices based on the early warning weight of the regional center. The behavior percentage statistics unit is used to count the percentage of behaviors that are identified as relevant warning objects when each defect detection device is used as the center of the simulated area. The early warning table generation and output unit is used to sort data by the percentage of frequency of each behavior from largest to smallest, generate a data analysis early warning table, and output it to the staff's port.

Images