Quality detection method and system for main structure of buried sewage treatment plant

Abstract

The invention discloses a quality detection method and system for a main structure of a buried sewage treatment plant, relates to the technical field of structure quality detection, and aims to solve the problem that early recognition of local micro cracks of the structure and dynamic tracking of the crack development trend cannot be realized. Water level depth change and displacement deformation quantity are collected, the displacement change trend is analyzed, and an abnormal area is judged in combination with water level data. Transmitting ultrasonic waves to the abnormal area, obtaining reflection echoes, marking the position and the trend of the crack, analyzing the stress characteristics of the structure based on the trend, collecting material characteristic data, analyzing the crack type, and generating a crack damage index by integrating the stress characteristics and the crack type. And setting detection time, collecting state information, calculating a closing amplitude and a dislocation rate, judging a state trend, and analyzing an early warning level in combination with a damage index, so that intelligent monitoring and early warning of the structural crack are realized, and the monitoring accuracy is improved.

Description

Technical Field

[0001] This invention relates to the field of structural quality testing technology, and more specifically, to a method and system for testing the quality of the main structure of an underground sewage treatment plant. Background Technology

[0002] As an important part of urban infrastructure, underground sewage treatment plants are usually located in a high-humidity, high-load underground environment. They are subjected to multiple stresses such as groundwater pressure, soil displacement and operational loads over a long period of time, which can easily lead to structural defects such as cracks, displacement and settlement. If structural damage is not identified and intervened in time, it can easily lead to serious safety and environmental problems such as sewage leakage and ground collapse.

[0003] The existing technology has the following shortcomings: Currently, most common structural inspection methods rely on single-point monitoring, which cannot achieve early identification of local microcracks in the structure or dynamic tracking of crack development trends. They are also unable to accurately assess the potential risk level of structural cracks or achieve multi-dimensional data-driven automatic early warning decisions, resulting in a significant increase in the risk of structural failure and a significant reduction in operational safety assurance capabilities.

[0004] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a method and system for quality inspection of the main structure of a buried sewage treatment plant. This method and system utilize a detection mechanism that combines multi-source data fusion analysis with an intelligent crack identification algorithm to address the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for quality inspection of the main structure of an underground sewage treatment plant, comprising the following steps: Step S1: Divide the main structure into regions, collect water level depth change data and displacement deformation data of the divided regions, analyze the displacement change trend based on the displacement deformation data, and determine whether it is an abnormal region based on the water level depth change data. Step S2: Transmit ultrasonic signals to the abnormal area and acquire reflected echo data. Mark the crack location based on the reflected echo data, acquire the orientation information of the marked location, analyze the structural stress characteristics based on the orientation information of the marked location, and generate feature acquisition signals. Step S3: After detecting the feature acquisition signal, collect the material property data of the marked location, analyze the crack type based on the material property data, and generate a crack damage index by combining the structural stress characteristics of the marked location and the crack type. Step S4: Set the detection time, collect the status information of the marked position within the detection time, calculate the closure amplitude and fault rate, fuse the closure amplitude and fault rate to generate the status trend of the marked position, and analyze the early warning level in combination with crack damage index.

[0007] In a preferred embodiment, in step S1, the main structure of the underground sewage treatment plant is divided into functional zones. Multiple consecutive sampling windows are preset, and the water pressure value of the divided area is detected at the end of each sampling window. The water level depth data is calculated based on the water pressure value. The difference between the mean of each water level depth data and the absolute value of each water level depth data is taken as the water level change value, and the maximum value of the water level change value is taken as the water level depth change data. Displacement deformation data are displacement deformation values; At the end of the detection sampling window, the strain wavelength of the divided region is used to calculate the displacement deformation of the divided region based on the strain wavelength. Calculate the rate of change of displacement deformation over continuous time, obtain the acceleration of deformation change based on the rate of change of deformation, and take the average value of each acceleration of deformation change as the displacement change trend.

[0008] In a preferred embodiment, in step S1, the displacement change trend and water level depth change data are considered together to determine whether the divided area is an abnormal area. If the displacement change trend is greater than the preset displacement threshold, the divided area is judged as an abnormal area. If the displacement change trend is less than or equal to the preset displacement threshold, and the water level depth change data is greater than the preset water level change threshold, then the area is determined to be an abnormal area. Otherwise, the area is determined to be a normal area.

[0009] In a preferred embodiment, in step S2, multiple monitoring points are uniformly selected in the abnormal area, ultrasonic waves are emitted into the main structure of the abnormal area, and the reflected echo data after the ultrasonic waves propagate inside the main structure are acquired, including the time difference of flight and the reflection intensity of the echo signal. The time difference of flight is the total time it takes for an ultrasonic wave to travel from transmission to return to the receiver; The reflection intensity of an echo signal refers to the amplitude of the echo signal; The MAD algorithm is used to calculate the flight difference threshold to determine whether the flight time difference is abnormal. The mean and standard deviation of the reflection intensity at each monitoring point are calculated, and the reflection intensity threshold is determined based on the mean and standard deviation to determine whether the reflection intensity is abnormal. If both the time difference of flight and the reflection intensity are abnormal, then it is determined that there is a crack in the abnormal area; Based on the reflection time difference and location of multiple monitoring points, the abnormal area is reconstructed in three dimensions to obtain the spatial coordinates of multiple crack locations and combined into a set of crack spatial coordinate points.

[0010] In a preferred embodiment, in step S2, the set of crack spatial coordinate points is linearly fitted to the crack position coordinates and marked to obtain the orientation information of the marked positions, including the direction vector of the crack orientation. Based on the orientation information of the marked positions, the stress characteristics of the structure are analyzed and feature acquisition signals are generated; Structural stress characteristics include local stress concentration factor and the angle between crack orientation and principal stress direction; The strain wavelengths in different directions at the marked position are detected, and the strain components are obtained based on the strain wavelengths; The strain components are converted into stresses by the generalized Hooke's law and the three-dimensional stress tensor is obtained. The three-dimensional stress tensor is then decomposed into eigenvalues ​​by a power iteration algorithm to obtain the maximum stress and principal stress direction vectors at the marked positions. The local stress concentration factor is the ratio of the maximum stress to the average stress at the marked location; The angle between the crack direction and the principal stress direction is the angle between the direction vector of the crack direction and the direction vector of the principal stress direction.

[0011] In a preferred embodiment, in step S3, after the feature acquisition signal is detected, the propagation velocities of longitudinal and transverse waves are calculated based on the geometric dimensions of the crack region using the ultrasonic pulse echo detection method. Combined with the density of the material in the crack region, the local elastic modulus and local Poisson's ratio are calculated according to the acoustic elasticity theory relationship. The local elastic modulus and local Poisson's ratio are normalized, a fuzzy logic reasoning model is constructed, and a Mamdani-type reasoning mechanism is adopted to obtain the membership degree of the crack type determination index. The centroid method is then used to defuzzify the index and obtain the type determination index.

[0012] In a preferred embodiment, in step S3, if the type determination index is greater than the preset determination threshold, the crack type is determined to be a normal crack. If the type determination index is less than or equal to the determination threshold, the crack type is determined to be an abnormal crack. For the marked locations of abnormal cracks, the structural stress characteristics of the marked cracks are extracted to construct feature vectors, and the crack damage index is calculated using a regression analysis method based on support vector machine.

[0013] In a preferred embodiment, in step S4, a detection time window is set, and relative displacement data of the structural surfaces on both sides of the crack and micro-deformation data of the stress concentration area at the crack tip are acquired during the detection time. The relative displacement data are the maximum and minimum closure amounts of the structural surfaces on both sides of the crack, and the difference between the maximum and minimum closure amounts is taken as the closure amplitude. Microscopic deformation data is the relative displacement change along the tangential direction on both sides of the crack. Dividing the relative displacement change by the detection time yields the fault rate. The closure amplitude and slip rate are normalized, and a hyperbolic tangent function is used for nonlinear fusion to generate the state trend value of the marked position.

[0014] In a preferred embodiment, the state trend value and crack damage index are used as input parameters, and the comprehensive early warning probability is calculated through a logistic regression model. When the overall early warning probability is greater than or equal to the preset level classification threshold, it is judged as a high-level early warning, prompting immediate on-site inspection and handling; When the overall early warning probability is less than the level classification threshold, it is judged as a low-level early warning, and it is suggested to maintain routine monitoring.

[0015] A quality inspection system for the main structure of an underground sewage treatment plant includes an anomaly detection module, a crack marking module, a damage analysis module, and a status early warning module. The functions of each module are as follows: Anomaly Detection Module: Divides the main structure into regions, collects water level and depth change data and displacement deformation data of the divided regions, analyzes the displacement change trend based on the displacement deformation data, and determines whether it is an abnormal region based on the water level and depth change data. Crack marking module: It transmits ultrasonic signals to the abnormal area and acquires reflected echo data. It marks the crack location based on the reflected echo data, acquires the orientation information of the marked location, analyzes the stress characteristics of the structure based on the orientation information of the marked location, and generates feature acquisition signals. Damage Analysis Module: After detecting the feature acquisition signal, it collects material property data at the marked location, analyzes the crack type based on the material property data, and generates a crack damage index by combining the structural stress characteristics at the marked location with the crack type. Status early warning module: Set the detection time, collect status information of marked positions within the detection time, calculate the closure amplitude and fault rate, fuse the closure amplitude and fault rate to generate the status trend of marked positions, and analyze the early warning level in combination with crack damage indicators.

[0016] The technical effects and advantages of this invention are as follows: This invention divides the main structure into regions, collects water level and depth variation data and displacement deformation data for each region, analyzes displacement trends based on displacement deformation data, determines whether a region is abnormal by combining water level and depth variation data, emits ultrasonic signals to abnormal regions and acquires reflected echo data, marks crack locations based on reflected echo data, acquires the orientation information of the marked locations, analyzes structural stress characteristics based on the orientation information of the marked locations, collects material property data for the marked locations, analyzes crack types based on material property data, generates crack damage indices by combining structural stress characteristics and crack types at the marked locations, sets a detection time, collects state information of the marked locations during the detection time, calculates closure amplitude and fault rate, judges the state trend of the marked locations, and analyzes the early warning level by combining crack damage indices, thus realizing intelligent monitoring and early warning of structural cracks and improving the accuracy of structural crack monitoring. Attached Figure Description

[0017] Figure 1 This is a flowchart of a method for quality inspection of the main structure of an underground sewage treatment plant according to the present invention.

[0018] Figure 2 This is a schematic diagram of a module of a quality inspection system for the main structure of an underground sewage treatment plant according to the present invention. Detailed Implementation

[0019] 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 only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] This invention divides the main structure into regions, collects water level and depth change data and displacement deformation data for each region, analyzes displacement change trends based on displacement deformation data, determines whether a region is abnormal based on water level and depth change data, emits ultrasonic signals to abnormal regions and acquires reflected echo data, marks crack locations based on reflected echo data, analyzes structural stress characteristics based on the orientation information of the marked locations, collects material property data for the marked locations, analyzes crack types based on material property data, generates crack damage indices by combining structural stress characteristics and crack types at the marked locations, sets a detection time, collects state information of the marked locations during the detection time, calculates closure amplitude and slip rate, judges the state trend of the marked locations, and analyzes the early warning level based on the crack damage indices, thus achieving intelligent monitoring and early warning of structural cracks.

[0021] Example 1: A method for quality inspection of the main structure of an underground sewage treatment plant, such as... Figure 1 As shown, it includes the following steps: Step S1: Divide the main structure into regions, collect water level depth change data and displacement deformation data of the divided regions, analyze the displacement change trend based on the displacement deformation data, and determine whether it is an abnormal region based on the water level depth change data. Step S2: Transmit ultrasonic signals to the abnormal area and acquire reflected echo data. Mark the crack location based on the reflected echo data, acquire the orientation information of the marked location, analyze the structural stress characteristics based on the orientation information of the marked location, and generate feature acquisition signals. Step S3: After detecting the feature acquisition signal, collect the material property data of the marked location, analyze the crack type based on the material property data, and generate a crack damage index by combining the structural stress characteristics of the marked location and the crack type. Step S4: Set the detection time, collect the status information of the marked position within the detection time, calculate the closure amplitude and fault rate, fuse the closure amplitude and fault rate to generate the status trend of the marked position, and analyze the early warning level in combination with crack damage index.

[0022] The specific implementation is as follows: In step S1, the main structure of the underground sewage treatment plant is divided into functional zones.

[0023] Multiple consecutive sampling windows are preset. The hydrostatic level sensor is placed at the bottom or top of the divided area. The water pressure value of the divided area is detected at the end of each sampling window. The product of water density and gravitational acceleration is taken as the water weight, and the ratio of the water pressure value of the divided area to the water weight is taken as the water level depth data of the divided area.

[0024] It should be noted that multiple consecutive sampling windows are preset to collect water level depth data and displacement deformation data of the main structure in segments. The sampling window has a fixed time length, and each sampling window corresponds to an independent data acquisition interval. The length of the sampling window can be set according to the response characteristics of the monitored object and the sampling frequency of the acquisition device.

[0025] The difference between the mean of each water level depth data and the absolute value of each water level depth data is taken as the water level change value, and the maximum value of the water level change value is taken as the water level depth change data. When the water level changes significantly, the water pressure load on the main structure changes considerably, which in turn causes stress redistribution and may lead to abnormal phenomena such as cracks.

[0026] Displacement deformation data are displacement deformation values; The strain wavelength of the segmented region is detected by a fiber optic strain sensor at the end of the sampling window, and the product of the strain wavelength and the preset initial reference length is used as the displacement deformation of the segmented region. Displacement deformation is the magnitude of the spatial position shift or length change of the main structure relative to its initial state under the action of external loads.

[0027] The ratio of the difference between adjacent displacement deformation variables and the sampling window is taken as the deformation rate of each acquired displacement deformation variable according to the time series. The ratio of the difference between adjacent deformation rates is taken as the deformation acceleration. The average value of each deformation acceleration is taken as the displacement trend. The displacement change trend reflects the overall acceleration or deceleration trend of the deformation response rate of the main structure within the monitoring window; when the displacement change trend is greater than 0, it indicates that the deformation rate of the main structure is accelerating, which may indicate instability of the main structure or increased external load; when the displacement change trend is less than or equal to 0, it indicates that the deformation of the main structure tends to be stable.

[0028] The overall displacement trend and water level / depth change data are used to determine whether the delineated area is an abnormal area; If the displacement change trend is greater than the preset displacement threshold, the divided area is judged as an abnormal area. If the displacement change trend is less than or equal to the preset displacement threshold, and the water level depth change data is greater than the preset water level change threshold, then the area is determined to be an abnormal area. Otherwise, the area is determined to be a normal area.

[0029] When the displacement change trend is greater than the preset displacement threshold, it indicates that the deformation rate of the structure in the divided area is increasing rapidly, and there is a risk of instability. If the displacement change trend does not exceed the displacement threshold, but the corresponding water level depth change data exceeds the preset water level change threshold, it indicates that the external water pressure load disturbance is obvious and may cause potential structural anomalies, and it is also judged as an abnormal area; otherwise, it is judged as a normal area.

[0030] It should be noted that a hydrostatic level sensor is a sensor that measures liquid level height based on the principle of hydrostatic pressure; a fiber optic strain sensor is an optical structure with periodic refractive index changes written into an optical fiber, which monitors strain through the Bragg reflection principle. When the fiber optic strain sensor is embedded in the main structure and deforms with the force on the main structure, the period of its internal grating will change slightly, resulting in a Bragg wavelength drift. The strain wavelength is obtained by measuring the wavelength drift value; the preset initial reference length is the designed installation length between the fixed anchor points at both ends of the fiber optic strain sensor, representing the grating measurement reference length in the unstressed state; the preset displacement threshold is a critical value set by professionals to determine whether the main structure has undergone abnormal displacement changes; the preset water level change threshold is a threshold set by professionals to determine whether the water level change is abnormal, identifying the indicator value of structural risk caused by changes in liquid pressure.

[0031] In step S2, multiple monitoring points are uniformly selected in the abnormal area, and the main structure of the abnormal area is detected by an ultrasonic transmitter and receiver. Ultrasonic waves are emitted into the main structure of the abnormal area, and the reflected echo data after the ultrasonic waves propagate inside the main structure are obtained by the receiver, including the time difference of flight and the reflection intensity of the echo signal. The time difference of flight is the total time it takes for an ultrasonic wave to travel from emission to return to the receiver. When the main structure is continuous and uniform, the time difference of flight is relatively stable. However, if cracks appear in the main structure, the propagation path of the ultrasonic wave will change abruptly, causing the time difference of flight to advance or be delayed. The reflection intensity of an echo signal refers to the amplitude of the echo signal. In a continuous and uniform main structure, the reflection intensity is low, while when there is a crack in the main structure, a higher reflection intensity will be formed. Conversely, due to the expansion or attenuation of the crack, it may also manifest as an abnormally low echo signal energy. Therefore, the location of the crack is determined by combining the time difference of flight.

[0032] The MAD algorithm is used to calculate the first flight difference threshold and the second flight difference threshold. The median of the flight time difference at each monitoring point is taken as the absolute value of the difference between each flight time difference. The median of the absolute deviations is taken as the median absolute deviation. The difference between the median absolute deviation and the median flight time difference is taken as the first flight difference threshold. The sum of the median absolute deviation and the median flight time difference is taken as the second flight difference threshold. If the flight time difference is between the first flight difference threshold and the second flight difference threshold, the flight time difference is judged to be normal. Otherwise, the flight time difference is judged to be abnormal. The mean and standard deviation of the reflection intensity at each monitoring point are calculated. The difference between the mean and the standard deviation is used as the first reflection threshold, and the sum of the mean and the standard deviation is used as the second reflection threshold. If the reflection intensity is between the first and second reflection thresholds, the reflection intensity is considered normal; otherwise, the reflection intensity is considered abnormal. If both the time difference of flight and the reflection intensity are abnormal, then it is determined that there is a crack in the abnormal area; Based on the reflection time difference and location of multiple monitoring points, the spatial coordinates of multiple crack locations are obtained by three-dimensional spatial reconstruction of the abnormal area using ultrasonic imaging algorithms and combined into a set of crack spatial coordinate points. The crack spatial coordinate point set is linearly fitted to the crack position coordinates and marked to obtain the orientation information of the marked positions, including the direction vector of the crack orientation. Based on the orientation information of the marked positions, the stress characteristics of the structure are analyzed and feature acquisition signals are generated; Among them, the feature acquisition signal refers to the digital trigger signal, which is used to trigger the acquisition of material property data at the marked location and subsequent calculations; Structural stress characteristics include local stress concentration factor and the angle between crack orientation and principal stress direction; By deploying fiber optic grating strain sensors in multiple directions, strain wavelengths in different directions at the marked location are collected, and strain components are obtained based on the strain wavelengths. ,in, Let be the strain wavelength in the i-th direction. The preset wavelength is for the i-th direction. For the effective photoelastic constant, Let be the strain component in the i-th direction; It should be explained that the effective photoelastic constant is a calibration parameter provided by the fiber optic strain sensor, and the preset wavelength is the reflection wavelength of the fiber optic grating under no strain. The strain components are converted into stresses by the generalized Hooke's law and the three-dimensional stress tensor is obtained. The three-dimensional stress tensor is then decomposed into eigenvalues ​​by a power iteration algorithm to obtain the maximum stress and principal stress direction vectors at the marked positions. Among them, the maximum principal stress value is used to quantify the local maximum stress state, and the principal stress direction vector reflects the spatial direction of the force at the marked position.

[0033] The local stress concentration factor is the ratio of the maximum stress to the average stress at a marked location, used to quantify the degree of stress concentration at discontinuous locations. The angle between the crack direction and the principal stress direction is the angle between the crack at the marked location and the principal stress direction. The formula for the angle between the crack direction and the principal stress direction is: ,in, Let be the direction vector of the crack's orientation. The principal stress direction vector, The angle between the crack direction and the principal stress direction; It should be noted that the ultrasonic transmitting and receiving device consists of an ultrasonic transducer, integrating the functions of a transmitter and a receiver, used to acquire the time difference of flight and reflection intensity data of the monitoring points; the ultrasonic imaging algorithm is a calculation method that back-calculates the spatial structural features from the information of multiple ultrasonic propagation paths, reconstructs the three-dimensional geometric shape of internal defects in materials, calculates the propagation path of ultrasonic waves within the structure by combining the position coordinates of multiple monitoring points and the time difference of ultrasonic flight, and performs spatial reconstruction through the propagation path to obtain the set of spatial coordinate points of the crack location; linear fitting refers to modeling the set of spatial coordinate points of the crack using the least squares method to minimize the sum of squared errors, thereby obtaining an optimal fitting straight line; the power iteration algorithm is an eigenvalue decomposition algorithm used to solve for the largest eigenvalue of a matrix and its corresponding eigenvector; the generalized Hooke's law describes the linear relationship between stress and strain in elastic materials under external force, and obtains the three-dimensional stress tensor by using the strain components and the elastic modulus of the material; the MAD algorithm is an anomaly detection method for non-Gaussian distributed data, used for outlier removal and boundary judgment.

[0034] In step S3, after the feature acquisition signal is detected, data is acquired at the marked position to obtain the material property data of the marked position, including the local elastic modulus and the local Poisson's ratio.

[0035] Using the ultrasonic pulse-echo detection method, ultrasonic transmitting and receiving devices are deployed at the crack location to emit high-frequency longitudinal and transverse waves. The propagation time of these waves within the crack region is recorded. The propagation velocities of the longitudinal and transverse waves are calculated based on the geometric dimensions of the crack region. Combined with the density parameters of the material in the crack region, the local elastic modulus and local Poisson's ratio are calculated according to the acoustic elasticity theory. The specific calculation formulas are as follows: ; ; in, For local elastic modulus, For local Poisson's ratio, The density of the material in the crack region. For the propagation speed of longitudinal waves, This represents the propagation speed of the transverse wave.

[0036] After data acquisition, a fuzzy logic reasoning model is used to comprehensively analyze the local elastic modulus and local Poisson's ratio to determine the crack type.

[0037] The local elastic modulus and local Poisson's ratio are normalized to ensure that indices with different dimensions and numerical ranges can be comprehensively analyzed under a unified standard. The normalization process uses a linear normalization method, mapping the original measured values ​​to the [0,1] interval. The normalization formula is as follows: ; in, The normalized dimensionless value, This represents the original measured values ​​of the local elastic modulus and local Poisson's ratio. and These represent the minimum and maximum values ​​of the corresponding indicators in the historical data sample, respectively.

[0038] After normalizing the local elastic modulus and local Poisson's ratio, a fuzzy logic reasoning model is constructed and a crack type determination index is output. The local elastic modulus and local Poisson's ratio are defined as corresponding to three fuzzy sets: low, medium, and high, respectively. The crack type determination index is output to correspond to two types: normal cracks and abnormal cracks.

[0039] Fuzzy inference rules are constructed based on material performance specifications and historical experimental results. Example rules include: If the local elastic modulus is low and the local Poisson's ratio is low, then the crack type determination index is abnormal. If the local elastic modulus is high and the local Poisson's ratio is high, then the crack type determination index is normal. If the local elastic modulus is low and the local Poisson's ratio is high, then the crack type determination index is abnormal. The fuzzy inference system employs a Mamdani-type inference mechanism to obtain the membership degree of the crack type determination index, and uses the centroid method for defuzzification to obtain the type determination index. The calculation formula is as follows: ; in, It is a type determination indicator and meets the conditions. , The membership degree of the crack type determination index.

[0040] The type determination index is compared with the preset determination threshold. If the type determination index is greater than the determination threshold, the crack type is determined to be a normal crack. If the type determination index is less than or equal to the determination threshold, the crack type is determined to be an abnormal crack.

[0041] It should be noted that the Mamdani-type inference mechanism is an inference method based on fuzzy set theory, used to realize the mapping relationship from input fuzzy variables to output fuzzy variables, which will not be elaborated here; the judgment threshold refers to the numerical boundary used to determine whether the crack type is abnormal. It is set according to the normalized results of the local elastic modulus and local Poisson's ratio collected in history, using the statistical quantile method or the standard deviation multiple method.

[0042] For the marked locations of abnormal cracks, the structural stress characteristics of the marked cracks are extracted, including the angle between the crack direction and the principal stress direction and the local stress concentration coefficient. The crack damage index is calculated using a regression analysis method based on support vector machine.

[0043] The angle between the crack orientation and the principal stress direction, and the local stress concentration factor are used as the basis for calculating crack damage indices, and a feature vector is constructed. ,in, This indicates the angle between the crack direction and the principal stress direction. The feature vector represents the local stress concentration factor. It is used as the input vector to a support vector machine (SVM) to evaluate crack damage indices. During the SVM training phase, a training sample set is constructed based on the historical task dataset. ,in, Let i be the feature vector of the i-th training sample. Let be the output value of the i-th training sample, and n be the total number of training samples.

[0044] eigenvectors The input is fed into the trained support vector regression model to predict the crack damage index. The specific calculation formula is as follows: ; in, The crack damage index meets the conditions. , These are the Lagrange multipliers. The kernel function is in the form of a Gaussian radial basis function. , is the kernel function bandwidth parameter, and b is the model bias term.

[0045] In step S4, a detection time window is set, and the status information of the crack mark position is acquired in real time within the detection time. The status information includes the relative displacement data of the structural surfaces on both sides of the crack and the micro-deformation data of the stress concentration area at the crack tip.

[0046] The relative displacement data are the maximum and minimum closure amounts of the structural surfaces on both sides of the crack. High-precision displacement sensors deployed on both sides of the crack continuously collect displacement data. Through time series analysis, the extreme values ​​during the crack closure and opening process are determined, namely the maximum and minimum closure amounts of the structural surfaces on both sides of the crack. The difference between the maximum and minimum closure amounts is taken as the closure amplitude. The closure amplitude reflects the dynamic response capability of the crack under natural or loaded conditions.

[0047] Microscopic deformation data are the relative displacement changes on both sides of the crack along the tangential direction. Triaxial strain gauges installed on the crack surface are used to record the relative displacement changes on both sides of the crack along the crack direction. By dividing the relative displacement changes by the detection time, the slip rate is obtained. The slip rate characterizes the shear slip tendency of the crack during the detection time. The higher the slip rate, the more unstable the stress state of the structure.

[0048] After calculating the closure amplitude and the slip rate, the two indices are normalized to the interval [0,1] to eliminate the influence of dimensional differences and data scale. After normalizing the closure amplitude and the slip rate, a nonlinear fusion function is used to combine the two normalized indices to generate the state trend value of the marked position. The fusion function is the hyperbolic tangent function, and the specific calculation formula is as follows: ; in, This represents the state trend value. This is the result after normalizing the closure amplitude. This is the result after normalizing the fault rate. and is the characteristic coefficient of the fusion function, b is the bias term, the hyperbolic tangent function is sensitive to the coordinated change of the closure amplitude and the fault rate, and the output state trend value takes the range of (0,1). The closer the value is to 1, the more stable the crack state is, and the closer it is to 0, the greater the risk of abnormal fluctuations in the crack state.

[0049] After obtaining the state trend value, the crack damage index is further introduced. Both are used as input parameters, and the comprehensive early warning probability is calculated through a logistic regression model. The specific calculation formula is as follows: ; in, To comprehensively predict the probability of an early warning, and These are the weight parameters for logistic regression. As a bias term, the overall early warning probability is the risk probability of significant damage to the crack.

[0050] The overall early warning probability is compared with the preset level classification threshold to classify the early warning level: When the overall early warning probability is greater than or equal to the level classification threshold, it is judged as a high-level early warning, prompting immediate on-site inspection and handling; When the overall early warning probability is less than the level classification threshold, it is judged as a low-level early warning, and it is recommended to maintain routine monitoring.

[0051] It should be noted that a high-precision displacement sensor is a sensing device capable of measuring changes in the displacement of an object. It has extremely high resolution and measurement accuracy and is used for monitoring minute deformations. The output digital signal can reflect real-time changes in displacement. A triaxial strain gauge is a sensor that integrates three strain measuring elements in mutually perpendicular directions. It is used to simultaneously measure the strain components of a material or structure in three orthogonal directions, enabling multi-dimensional stress-strain analysis. The hyperbolic tangent function is a mathematical function used for nonlinear mapping. The logistic regression model is a statistical model used for binary classification problems. By weighted summing of input features, the result is mapped to a probability value between 0 and 1 using a logistic function, realizing probability prediction and discrimination of sample categories. This will not be elaborated upon here. The level classification threshold refers to the critical value used to distinguish warning levels. Based on historical monitoring data and confirmed abnormal cases, the comprehensive warning probability distribution characteristics corresponding to different warning levels are statistically analyzed to determine the probability interval that can cover real abnormal events as the level classification threshold.

[0052] Example 2: A quality inspection system for the main structure of an underground sewage treatment plant, such as... Figure 2 As shown, a method for quality inspection of the main structure of a buried sewage treatment plant is implemented, including an anomaly detection module, a crack marking module, a damage analysis module, and a status early warning module. The modules are interconnected by signals, and their functions are as follows: Anomaly Detection Module: Divides the main structure into regions, collects water level and depth change data and displacement deformation data of the divided regions, analyzes the displacement change trend based on the displacement deformation data, and determines whether it is an abnormal region based on the water level and depth change data. Crack marking module: It transmits ultrasonic signals to the abnormal area and acquires reflected echo data. It marks the crack location based on the reflected echo data, acquires the orientation information of the marked location, analyzes the stress characteristics of the structure based on the orientation information of the marked location, and generates feature acquisition signals. Damage Analysis Module: After detecting the feature acquisition signal, it collects material property data at the marked location, analyzes the crack type based on the material property data, and generates a crack damage index by combining the structural stress characteristics at the marked location with the crack type. Status warning module: Set the detection time, collect status information of marked positions within the detection time, calculate the closure amplitude and fault rate, fuse the closure amplitude and fault rate to generate the status trend of marked positions, and analyze the warning level in combination with crack damage indicators.

[0053] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0054] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or 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 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 includes one or more sets of 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. A semiconductor medium can be a solid-state drive.

[0055] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0056] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0057] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0058] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0059] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0060] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0061] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0062] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0063] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0064] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for quality inspection of the main structure of an underground sewage treatment plant, characterized in that: Includes the following steps: Step S1: Divide the main structure into regions, collect water level depth change data and displacement deformation data of the divided regions, analyze the displacement change trend based on the displacement deformation data, and determine whether it is an abnormal region based on the water level depth change data. Step S2: Transmit ultrasonic signals to the abnormal area and acquire reflected echo data. Mark the crack location based on the reflected echo data, acquire the orientation information of the marked location, analyze the structural stress characteristics based on the orientation information of the marked location, and generate feature acquisition signals. Step S3: After detecting the feature acquisition signal, collect the material property data of the marked location, analyze the crack type based on the material property data, and generate a crack damage index by combining the structural stress characteristics of the marked location and the crack type. Step S4: Set the detection time, collect the status information of the marked position within the detection time, calculate the closure amplitude and fault rate, fuse the closure amplitude and fault rate to generate the status trend of the marked position, and analyze the early warning level in combination with crack damage index.

2. The method for quality inspection of the main structure of an underground sewage treatment plant according to claim 1, characterized in that: In step S1, the main structure of the underground sewage treatment plant is divided into functional zones. Multiple consecutive sampling windows are preset, and the water pressure value of the divided area is detected at the end of each sampling window. The water level depth data is calculated based on the water pressure value. The difference between the mean of each water level depth data and the absolute value of each water level depth data is taken as the water level change value, and the maximum value of the water level change value is taken as the water level depth change data. Displacement deformation data are displacement deformation values; At the end of the detection sampling window, the strain wavelength of the divided region is used to calculate the displacement deformation of the divided region based on the strain wavelength. Calculate the rate of change of displacement deformation over continuous time, obtain the acceleration of deformation change based on the rate of change of deformation, and take the average value of each acceleration of deformation change as the displacement change trend.

3. The method for quality inspection of the main structure of an underground sewage treatment plant according to claim 2, characterized in that: In step S1, the displacement change trend and water level depth change data are combined to determine whether the divided area is an abnormal area; If the displacement change trend is greater than the preset displacement threshold, the divided area is judged as an abnormal area. If the displacement change trend is less than or equal to the preset displacement threshold, and the water level depth change data is greater than the preset water level change threshold, then the area is determined to be an abnormal area. Otherwise, the area is determined to be a normal area.

4. The method for quality inspection of the main structure of an underground sewage treatment plant according to claim 3, characterized in that: In step S2, multiple monitoring points are uniformly selected in the abnormal area, ultrasonic waves are emitted into the main structure of the abnormal area, and the reflected echo data after the ultrasonic waves propagate inside the main structure are acquired, including the time difference of flight and the reflection intensity of the echo signal. The time difference of flight is the total time it takes for an ultrasonic wave to travel from transmission to return to the receiver; The reflection intensity of an echo signal refers to the amplitude of the echo signal; The MAD algorithm is used to calculate the flight difference threshold to determine whether the flight time difference is abnormal. The mean and standard deviation of the reflection intensity at each monitoring point are calculated, and the reflection intensity threshold is determined based on the mean and standard deviation to determine whether the reflection intensity is abnormal. If both the time difference of flight and the reflection intensity are abnormal, then it is determined that there is a crack in the abnormal area; Based on the reflection time difference and location of multiple monitoring points, the abnormal area is reconstructed in three dimensions to obtain the spatial coordinates of multiple crack locations and combined into a set of crack spatial coordinate points.

5. The method for quality inspection of the main structure of an underground sewage treatment plant according to claim 4, characterized in that: In step S2, the crack spatial coordinate point set is linearly fitted to the crack position coordinates and marked to obtain the orientation information of the marked position, including the direction vector of the crack orientation. Based on the orientation information of the marked positions, the stress characteristics of the structure are analyzed and feature acquisition signals are generated; Structural stress characteristics include local stress concentration factor and the angle between crack orientation and principal stress direction; The strain wavelengths in different directions at the marked position are detected, and the strain components are obtained based on the strain wavelengths; The strain components are converted into stresses by the generalized Hooke's law and the three-dimensional stress tensor is obtained. The three-dimensional stress tensor is then decomposed into eigenvalues ​​by a power iteration algorithm to obtain the maximum stress and principal stress direction vectors at the marked positions. The local stress concentration factor is the ratio of the maximum stress to the average stress at the marked location; The angle between the crack direction and the principal stress direction is the angle between the direction vector of the crack direction and the direction vector of the principal stress direction.

6. The method for quality inspection of the main structure of an underground sewage treatment plant according to claim 1, characterized in that: In step S3, after the feature acquisition signal is detected, the propagation velocities of longitudinal and transverse waves are calculated based on the geometric dimensions of the crack region using the ultrasonic pulse echo detection method. Combined with the density of the material in the crack region, the local elastic modulus and local Poisson's ratio are obtained by converting according to the acoustic elasticity theory relationship. The local elastic modulus and local Poisson's ratio are normalized, a fuzzy logic reasoning model is constructed, and a Mamdani-type reasoning mechanism is adopted to obtain the membership degree of the crack type determination index. The centroid method is then used to defuzzify the index and obtain the type determination index.

7. The method for quality inspection of the main structure of an underground sewage treatment plant according to claim 6, characterized in that: In step S3, if the type determination index is greater than the preset determination threshold, the crack type is determined to be a normal crack. If the type determination index is less than or equal to the determination threshold, the crack type is determined to be an abnormal crack. For the marked locations of abnormal cracks, the structural stress characteristics of the marked cracks are extracted to construct feature vectors, and the crack damage index is calculated using a regression analysis method based on support vector machine.

8. The method for quality inspection of the main structure of an underground sewage treatment plant according to claim 1, characterized in that: In step S4, a detection time window is set, and relative displacement data of the structural surfaces on both sides of the crack and micro-deformation data of the stress concentration area at the crack tip are acquired during the detection time. The relative displacement data are the maximum and minimum closure amounts of the structural surfaces on both sides of the crack, and the difference between the maximum and minimum closure amounts is taken as the closure amplitude. Microscopic deformation data is the relative displacement change along the tangential direction on both sides of the crack. Dividing the relative displacement change by the detection time yields the fault rate. The closure amplitude and slip rate are normalized, and a hyperbolic tangent function is used for nonlinear fusion to generate the state trend value of the marked position.

9. A method for quality inspection of the main structure of an underground sewage treatment plant according to claim 8, characterized in that: Using the state trend value and crack damage index as input parameters, the comprehensive early warning probability is calculated through a logistic regression model. When the overall early warning probability is greater than or equal to the preset level classification threshold, it is judged as a high-level early warning, prompting immediate on-site inspection and handling; When the overall early warning probability is less than the level classification threshold, it is judged as a low-level early warning, and it is recommended to maintain routine monitoring.

10. A quality inspection system for the main structure of an underground sewage treatment plant, used to implement the quality inspection method for the main structure of an underground sewage treatment plant as described in any one of claims 1-9, characterized in that: It includes an anomaly detection module, a crack marking module, a damage analysis module, and a status early warning module. The functions of each module are as follows: Anomaly Detection Module: Divides the main structure into regions, collects water level and depth change data and displacement deformation data of the divided regions, analyzes the displacement change trend based on the displacement deformation data, and determines whether it is an abnormal region based on the water level and depth change data. Crack marking module: It transmits ultrasonic signals to the abnormal area and acquires reflected echo data. It marks the crack location based on the reflected echo data, acquires the orientation information of the marked location, analyzes the stress characteristics of the structure based on the orientation information of the marked location, and generates feature acquisition signals. Damage Analysis Module: After detecting the feature acquisition signal, it collects material property data at the marked location, analyzes the crack type based on the material property data, and generates a crack damage index by combining the structural stress characteristics at the marked location with the crack type. Status early warning module: Set the detection time, collect status information of marked positions within the detection time, calculate the closure amplitude and fault rate, fuse the closure amplitude and fault rate to generate the status trend of marked positions, and analyze the early warning level in combination with crack damage indicators.

Images