A method and system for detecting the quality of a main structure of a buried sewage treatment plant

Abstract

The application discloses a buried sewage treatment plant main body structure quality detection method and system, relates to the technical field of structure quality detection, and is used for solving the problem that early identification of structure local microcracks and dynamic tracking of crack development trend cannot be realized, collecting water level depth variation and displacement deformation variables by regionally dividing the main body structure, analyzing displacement variation trend and determining abnormal regions in combination with water level data. Ultrasonic waves are emitted to the abnormal regions and reflection echoes are acquired, crack positions and directions thereof are marked, structure stress characteristics are analyzed based on the directions, material characteristic data are collected and crack types are analyzed, crack damage indexes are generated in combination of the stress characteristics and the crack types. Detection time is set, state information is collected to calculate closing amplitude and dislocation rate, state trend is judged, early warning grades are analyzed in combination with the damage indexes, structure crack intelligent monitoring and early warning are realized, and monitoring accuracy is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of structural quality detection, more particularly, the present application relates to a buried sewage treatment plant main structure quality detection method and system. BACKGROUND

[0002] As an important part of urban infrastructure, the main structure of the buried sewage treatment plant is usually in a high-humidity and high-load underground environment, and is subjected to multiple stresses such as underground water pressure, soil displacement and operating load for a long time, which can easily cause structural diseases such as cracks, dislocations and settlement. Once the structural damage is not identified and intervened in time, it is easy to cause serious safety and environmental problems such as sewage leakage and ground subsidence.

[0003] The prior art has the following disadvantages:

[0004] At present, the common structural detection method is mainly single-point monitoring, which cannot realize early identification of local micro-cracks of the structure and dynamic tracking of crack development trend, and cannot accurately evaluate the potential risk level of structural cracks, nor can it realize automatic early warning decision driven by multi-dimensional data, resulting in significant increase in structural failure risk and significant reduction in operation safety guarantee capability.

[0005] The above information disclosed in the background section is only used to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide a buried sewage treatment plant main structure quality detection method and system, which uses a detection mechanism combining multi-source data fusion analysis and intelligent crack identification algorithm to solve the problems raised in the above background.

[0007] To achieve the above-mentioned purpose, the present application provides the following technical scheme, a buried sewage treatment plant main structure quality detection method, comprising the following steps:

[0008] 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 according to the displacement deformation, and determine whether it is an abnormal region according to the water level depth change data;

[0009] Step S2: emit ultrasonic signals to the abnormal region and obtain reflected echo data, mark the crack position according to the reflected echo data, obtain the strike information of the marked position, analyze the stress characteristics of the structure based on the strike information of the marked position, and generate a feature collection signal;

[0010] Step S3: After detecting the feature acquisition signal, the material property data of the marked position is acquired, the crack type is analyzed based on the material property data, the crack damage index is generated by comprehensively considering the structural stress characteristics of the marked position and the crack type;

[0011] Step S4: Set the detection time, acquire the state information of the marked position in the detection time, calculate the closing amplitude and the displacement rate, generate the state trend of the marked position by fusing the closing amplitude and the displacement rate, and analyze the early warning level in combination with the crack damage index.

[0012] In a preferred embodiment, in step S1, the main structure of the buried sewage treatment plant is regionally divided according to functional areas;

[0013] A plurality of continuous sampling windows are preset, the water pressure value of the divided region at the end of each sampling window is detected, and the water level depth data is calculated based on the water pressure value;

[0014] The mean value of each water level depth data is subtracted from each water level depth data and the absolute value 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;

[0015] The displacement deformation data is a displacement deformation variable;

[0016] The strain wavelength of the divided region at the end of the sampling window is detected, and the displacement deformation variable of the divided region is calculated based on the strain wavelength;

[0017] The deformation change rate of the continuous time displacement deformation variable is calculated, the deformation change acceleration is obtained based on the deformation change rate, and the mean value of each deformation change acceleration is taken as the displacement change trend.

[0018] In a preferred embodiment, in step S1, the displacement change trend and the water level depth change data are comprehensively considered to determine whether the divided region is an abnormal region;

[0019] If the displacement change trend is greater than a preset displacement threshold, the divided region is determined to be an abnormal region;

[0020] 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 a preset water level change threshold, the divided region is determined to be an abnormal region;

[0021] Otherwise, the divided region is determined to be a normal region.

[0022] In a preferred embodiment, in step S2, a plurality of monitoring points are uniformly selected in the abnormal region, an ultrasonic wave is emitted to the main structure of the abnormal region, and reflected echo data of the ultrasonic wave after propagating in the main structure is obtained, including a flight time difference and a reflection intensity of an echo signal;

[0023] The time of flight difference is the total time taken by the ultrasound wave to travel from the transmitter to the return receiver;

[0024] The reflection intensity of the echo signal refers to the amplitude of the echo signal;

[0025] The flight difference threshold is calculated by the MAD algorithm to determine whether the time of flight difference is abnormal;

[0026] The reflection intensity of each monitoring point is averaged and the standard deviation is calculated, and the reflection intensity threshold is calculated based on the average and the standard deviation to determine whether the reflection intensity is abnormal;

[0027] If both the time of flight difference and the reflection intensity are abnormal, it is determined that the abnormal region has a crack;

[0028] According to the reflection time difference of the plurality of monitoring points and the position of the monitoring points, the abnormal region is reconstructed in three-dimensional space to obtain spatial coordinates of a plurality of crack positions and combine them into a crack spatial coordinate point set.

[0029] In a preferred embodiment, in step S2, the crack spatial coordinate point set is obtained by linearly fitting the crack position coordinates and marking the marked position to obtain the strike information of the marked position, including the direction vector of the crack strike;

[0030] Based on the strike information of the marked position, the structural stress characteristics are analyzed and a characteristic acquisition signal is generated;

[0031] The structural stress characteristics include a local stress concentration coefficient and an angle between the crack strike and the principal stress direction;

[0032] The strain wavelength in different directions of the marked position is detected, and the strain component is obtained based on the strain wavelength;

[0033] The strain component is converted into stress by the generalized Hooke's law, and a three-dimensional stress tensor is obtained, and the three-dimensional stress tensor is subjected to eigenvalue decomposition by a power iteration algorithm to obtain the maximum stress of the marked position and the principal stress direction vector;

[0034] The local stress concentration coefficient is the ratio of the maximum stress of the marked position to the average stress;

[0035] The angle between the crack strike and the principal stress direction is the angle between the direction vector of the crack strike and the principal stress direction vector.

[0036] In a preferred embodiment, in step S3, after the characteristic acquisition signal is detected, the propagation velocities of the longitudinal wave and the transverse wave are calculated according to the geometric dimensions of the crack region by the ultrasonic pulse echo detection method, and the local elastic modulus and the local Poisson's ratio are converted according to the acoustic elastic theory relationship formula in combination with the density of the crack region material;

[0037] The local elastic modulus and the local Poisson's ratio are normalized to construct a fuzzy logic reasoning model, a Mamdani type reasoning mechanism is adopted to obtain the membership degree of the crack type determination index, and the gravity method is used to defuzzify to obtain the type determination index.

[0038] In a preferred embodiment, in step S3, if the type determination index is greater than a preset determination threshold, the crack type is determined to be a normal crack;

[0039] If the type determination index is less than or equal to the determination threshold, the crack type is determined to be an abnormal crack.

[0040] For the marked position with the determination result of the abnormal crack, the structural stress characteristics of the marked crack are extracted to construct a feature vector, and a support vector machine-based regression analysis method is used to calculate a crack damage index.

[0041] In a preferred embodiment, in step S4, a detection time window is set, and 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 are obtained at the detection time.

[0042] The relative displacement data is 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.

[0043] The micro-deformation data is the relative displacement change amount along the tangential direction on both sides of the crack, and the relative displacement change amount is divided by the detection time to obtain the dislocation rate.

[0044] The closure amplitude and the dislocation rate are normalized, and a hyperbolic tangent function is used for nonlinear fusion to generate a state trend value of the marked position.

[0045] In a preferred embodiment, the state trend value and the crack damage index are taken as input parameters, and a comprehensive early warning probability is calculated through a logistic regression model.

[0046] When the comprehensive early warning probability is greater than or equal to a preset level division threshold, it is determined to be a high-level early warning, prompting immediate on-site inspection and disposal.

[0047] When the comprehensive early warning probability is less than the level division threshold, it is determined to be a low-level early warning, prompting to maintain routine monitoring.

[0048] A buried sewage treatment plant main structure quality detection system includes an abnormality determination module, a crack marking module, a damage analysis module, and a state early warning module, and the functions of each module are as follows:

[0049] Anomaly determination module: divide the main structure into regions, collect water level depth change data and displacement variable of the divided regions, analyze the displacement change trend according to the displacement variable, and determine whether it is an abnormal region in combination with the water level depth change data;

[0050] Crack marking module: emit ultrasonic signals to the abnormal region and obtain reflected echo data, mark the crack position according to the reflected echo data, obtain the strike information of the marked position, analyze the structural stress characteristics based on the strike information of the marked position, and generate a characteristic collection signal;

[0051] Damage analysis module: after detecting the characteristic collection signal, collect material property data of the marked position, analyze the crack type based on the material property data, and generate a crack damage index by comprehensively considering the structural stress characteristics of the marked position and the crack type;

[0052] State warning module: set a detection time, collect state information of the marked position within the detection time to calculate the closing amplitude and the throw rate, generate the state trend of the marked position by fusing the closing amplitude and the throw rate, and analyze the warning level in combination with the crack damage index.

[0053] Technical effects and advantages of the present application:

[0054] The present application divides the main structure into regions, collects water level depth change data and displacement variable of the divided regions, analyzes the displacement change trend according to the displacement variable, determines whether it is an abnormal region in combination with the water level depth change data, emits ultrasonic signals to the abnormal region and obtains reflected echo data, marks the crack position according to the reflected echo data, obtains the strike information of the marked position, analyzes the structural stress characteristics based on the strike information of the marked position, collects material property data of the marked position, analyzes the crack type based on the material property data, generates a crack damage index by comprehensively considering the structural stress characteristics of the marked position and the crack type, sets a detection time, collects state information of the marked position within the detection time to calculate the closing amplitude and the throw rate, judges the state trend of the marked position, and analyzes the warning level in combination with the crack damage index. The present application realizes intelligent monitoring and warning of structural cracks, and improves the accuracy of structural crack monitoring. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 The method flowchart of the main structure quality detection method of the buried sewage treatment plant of the present application.

[0056] Figure 2 The module schematic diagram of the main structure quality detection system of the buried sewage treatment plant of the present application. DETAILED DESCRIPTION

[0057] With reference to the accompanying drawings: the technical solutions in the embodiments of the present application will be described clearly and completely, obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor belong to the scope of protection of the present application.

[0058] The present application divides the main structure into regions, collects water level depth change data and displacement deformation data of the divided regions, analyzes displacement change trend according to displacement deformation data, determines whether it is an abnormal region in combination with water level depth change data, emits ultrasonic signals to the abnormal region and obtains reflected echo data, marks the crack position according to the reflected echo data, analyzes the structural stress characteristics based on the strike information of the marked position, collects material property data of the marked position, analyzes the crack type based on the material property data, generates a crack damage index by comprehensively considering the structural stress characteristics and crack type of the marked position, sets a detection time, collects state information of the marked position within the detection time to calculate the closing amplitude and the throw rate, judges the state trend of the marked position, analyzes the warning level in combination with the crack damage index, and realizes intelligent monitoring and early warning of the structural crack.

[0059] Embodiment 1, a buried sewage treatment plant main structure quality detection method, as shown in Figure 1 The method comprises the following steps:

[0060] Step S1: the main structure is divided into regions, water level depth change data and displacement deformation data of the divided regions are collected, displacement change trend is analyzed according to displacement deformation variable, and whether it is an abnormal region is determined in combination with water level depth change data;

[0061] Step S2: ultrasonic signals are emitted to the abnormal region and reflected echo data is obtained, the crack position is marked according to the reflected echo data, the strike information of the marked position is obtained, the structural stress characteristics are analyzed based on the strike information of the marked position, and a characteristic collection signal is generated;

[0062] Step S3: after detecting the characteristic collection signal, the material property data of the marked position is collected, the crack type is analyzed based on the material property data, and a crack damage index is generated by comprehensively considering the structural stress characteristics and crack type of the marked position;

[0063] Step S4: set a detection time, collect state information of the marked position within the detection time to calculate the closing amplitude and the throw rate, generate the state trend of the marked position by fusing the closing amplitude and the throw rate, and analyze the warning level in combination with the crack damage index.

[0064] The specific implementation is as follows:

[0065] In step S1, the main structure of the buried sewage treatment plant is regionally divided according to functional areas.

[0066] A plurality of continuous sampling windows are preset, a static pressure type liquid level sensor is arranged at the bottom or top of the divided area, the water pressure value of the divided area at the end of each sampling window is detected, the product of the water body density and the gravitational acceleration is taken as the water body specific weight, and the ratio of the water pressure value of the divided area to the water body specific weight is taken as the water level depth data of the divided area.

[0067] It should be noted that the plurality of continuous sampling windows are used for segmented collection of the water level depth data and the displacement deformation data of the main structure, the sampling window has a fixed time length, each sampling window corresponds to an independent data collection interval, and the length of the sampling window can be set according to the response characteristics of the monitored object and the sampling frequency of the collection equipment.

[0068] The mean value of each water level depth data is subtracted from each water level depth data, and the absolute value 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.

[0069] When the water level depth change amplitude is large, the water pressure load borne by the main structure changes greatly, thereby causing stress redistribution of the structure, and abnormal phenomena such as crack generation may occur.

[0070] The displacement deformation data is a displacement deformation variable.

[0071] The strain wavelength of the divided area at the end of the sampling window is detected by the fiber grating strain sensor, the product of the strain wavelength and the preset initial reference length is taken as the displacement deformation variable of the divided area.

[0072] The displacement deformation variable is the amount of change of the spatial position offset or length change of the main structure relative to the initial state under the action of the external load.

[0073] The adjacent displacement deformation variables are sequentially subtracted from each obtained displacement deformation variable according to the time sequence, and the ratio of the sampling window is taken as the deformation change rate, and the adjacent deformation change rates are sequentially subtracted, and the ratio of the sampling window is taken as the deformation change acceleration, and the mean value of each deformation change acceleration is taken as the displacement change trend.

[0074] The displacement change trend reflects the overall acceleration or deceleration trend of the deformation response rate of the main structure in the monitoring window; when the displacement change trend is greater than 0, it indicates that the deformation change speed of the main structure is in an accelerating upward trend, and the main structure may be unstable or the external load may be enhanced; when the displacement change trend is less than or equal to 0, it indicates that the deformation change of the main structure tends to be stable.

[0075] The displacement change trend and the water level depth change data are comprehensively judged to determine whether the divided area is an abnormal area.

[0076] If the displacement change trend is greater than the preset displacement threshold, it is determined that the divided region is an abnormal region;

[0077] 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, it is determined that the divided region is an abnormal region;

[0078] Otherwise, it is determined that the divided region is a normal region.

[0079] When the displacement change trend is greater than the preset displacement threshold, it indicates that the deformation rate of the divided region structure is rapidly increasing, 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, which may cause potential abnormalities of the structure, and is also determined as an abnormal region. Otherwise, it is determined as a normal region.

[0080] It should be noted that the static pressure type liquid level sensor is a sensor for measuring the height of the liquid level based on the principle of liquid static pressure; the fiber Bragg grating strain sensor is an optical structure with periodic refractive index changes written in the optical fiber, which realizes strain monitoring through the Bragg reflection principle. When the fiber Bragg grating strain sensor is embedded in the main structure and deforms under stress, the internal grating period will change slightly, causing the Bragg wavelength to shift. The strain wavelength is obtained by the wavelength shift value; the preset initial reference length is the designed installation length between the two fixed anchor points of the fiber Bragg grating strain sensor, which represents 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 abnormal displacement change; the preset water level change threshold is a threshold set by professionals to determine whether the water level change is abnormal, which is an index value for identifying the risk of structure caused by liquid pressure change.

[0081] In step S2, a plurality of monitoring points are uniformly selected in the abnormal region, and the main structure of the abnormal region is detected by the ultrasonic emission and receiving device. The ultrasonic wave is emitted to the main structure of the abnormal region, and the reflection echo data of the ultrasonic wave after propagating in the main structure is obtained by the receiving device, including the time difference and the reflection intensity of the echo signal;

[0082] The time difference is the total time experienced by the ultrasonic wave from emission to return to the receiver. When the main structure is continuous and uniform, the time difference is relatively stable. If the main structure has a crack, the propagation path of the ultrasonic wave will change, causing the time difference to be advanced or delayed.

[0083] The reflection intensity of the echo signal refers to the amplitude of the echo signal, and in a continuous and uniform body structure, the reflection intensity is low, and when there is a crack in the body structure, a higher reflection intensity is formed, and conversely, the crack may also exhibit abnormally low echo signal energy due to expansion or attenuation, so the crack position is comprehensively judged in combination with the time difference.

[0084] The first flight difference threshold and the second flight difference threshold are calculated by the MAD algorithm, the median of the flight time difference of each monitoring point is taken, and the absolute deviation is obtained by taking the absolute value of the difference between each flight time difference, the median of the absolute deviation is taken as the median absolute deviation, the median absolute deviation and the median of the flight time difference are taken as the first flight difference threshold, and the median absolute deviation and the sum of the median of the flight time difference are 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;

[0085] The reflection intensity of each monitoring point is averaged and the standard deviation is obtained, the difference between the average and the standard deviation is taken as the reflection first threshold, and the sum of the average and the standard deviation is taken as the reflection second threshold;

[0086] If the reflection intensity is between the reflection first threshold and the reflection second threshold, the reflection intensity is judged to be normal, otherwise, the reflection intensity is judged to be abnormal;

[0087] If the flight time difference and the reflection intensity are both abnormal, it is judged that the abnormal area has a crack;

[0088] According to the reflection time difference of the plurality of monitoring points and the position of the monitoring points, the three-dimensional space reconstruction of the abnormal area is performed by the ultrasonic imaging algorithm to obtain the spatial coordinates of the plurality of crack positions and combine them into a crack spatial coordinate point set;

[0089] The crack spatial coordinate point set is linearly fitted with the crack position coordinates and marked to obtain the strike information of the marked position, including the direction vector of the crack strike;

[0090] Based on the strike information of the marked position, the structural stress characteristics are analyzed and the characteristic acquisition signal is generated;

[0091] The characteristic acquisition signal refers to a digital quantity trigger signal, which is used to trigger the acquisition of the material characteristic data of the marked position and subsequent calculation;

[0092] The structural stress characteristics include the local stress concentration coefficient and the angle between the crack strike and the principal stress direction;

[0093] The strain wavelength in different directions of the marked position is acquired by laying optical fiber grating strain sensors in multiple directions, and the strain component is obtained based on the strain wavelength: , wherein, is the strain wavelength in the i-th direction, is the preset wavelength of the i-th direction, is the effective photoelastic constant, is the strain component of the i-th direction;

[0094] It needs to be explained that the effective photoelastic constant is a calibration parameter provided by the fiber grating strain sensor, and the preset wavelength is the reflection wavelength of the fiber grating under no strain action;

[0095] The strain component is converted into stress through the generalized Hooke's law, and the three-dimensional stress tensor is obtained. The three-dimensional stress tensor is subjected to eigenvalue decomposition through the power iteration algorithm to obtain the maximum stress and principal stress direction vector of the marked position;

[0096] 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 stress of the marked position.

[0097] The local stress concentration coefficient is the ratio of the maximum stress to the average stress of the marked position, which is used to quantify the concentration degree of stress at the discontinuous position;

[0098] The crack direction and the principal stress direction angle is the angle between the crack and the principal stress direction of the marked position, and the crack direction and the principal stress direction angle formula is: , wherein, is the direction vector of the crack direction, is the principal stress direction vector, is the crack direction and the principal stress direction angle;

[0099] It needs to be explained that the ultrasonic wave transmitting and receiving device is composed of an ultrasonic transducer, which integrates the functions of transmitter and receiver, and is used to obtain the time difference and reflection intensity data of the monitoring point; the ultrasonic imaging algorithm is a calculation method for calculating the spatial structure characteristics of multiple ultrasonic wave propagation path information, reconstructing the three-dimensional geometry of the internal defects of the material, calculating the propagation path of the ultrasonic wave in the structure by combining the position coordinates of multiple monitoring points and the time difference of the ultrasonic wave, and obtaining the crack spatial coordinate point set of the crack position through spatial reconstruction; linear fitting is to model the crack spatial coordinate point set by the least square method to minimize the sum of squares of errors, so as to obtain a best fitting straight line; the power iteration algorithm is an eigenvalue decomposition algorithm, which is used to solve the maximum eigenvalue and its corresponding eigenvector of a matrix; the generalized Hooke's law is the linear relationship between the stress and strain of elastic materials under external force, and the three-dimensional stress tensor is obtained by strain component and material elastic modulus; the MAD algorithm is an anomaly detection method for non-Gaussian distributed data, which is used for outlier rejection and boundary judgment.

[0100] In step S3, after detecting the feature acquisition signal, data acquisition is performed on the mark position to obtain material property data of the mark position, including local elastic modulus and local Poisson's ratio.

[0101] Through ultrasonic pulse echo detection method, ultrasonic transmitting and receiving devices are arranged at the crack position, high-frequency longitudinal and transverse waves are emitted, and their propagation times in the crack area are recorded respectively. According to the geometric size of the crack area, the propagation velocities of longitudinal and transverse waves are calculated, and combined with the density parameters of the crack area material, the local elastic modulus and the local Poisson's ratio are converted according to the acoustic elastic theory relationship formula, and the specific calculation formula is as follows:

[0102] ;

[0103] ;

[0104] Wherein, is the local elastic modulus, is the local Poisson's ratio, is the density of the crack area material, is the longitudinal wave propagation velocity, is the transverse wave propagation velocity.

[0105] After completing the data acquisition, the local elastic modulus and the local Poisson's ratio are comprehensively analyzed by using the fuzzy logic inference model to determine the crack type.

[0106] The local elastic modulus and the local Poisson's ratio are normalized to ensure that indicators of different dimensions and value ranges can be comprehensively analyzed under a unified standard. The linear normalization method is used for normalization, and the original measurement values are mapped to the [0, 1] interval. The normalization formula is as follows:

[0107] ;

[0108] Wherein, is the normalized dimensionless value, represents the original measurement value of the local elastic modulus and the local Poisson's ratio, and respectively represent the minimum value and the maximum value of the corresponding index in the historical data sample.

[0109] After completing the normalization of the local elastic modulus and the local Poisson's ratio, a fuzzy logic inference model is constructed and a crack type determination index is output. The local elastic modulus and the local Poisson's ratio are defined to correspond to three fuzzy sets of low, medium and high respectively, and the crack type determination index corresponds to two types of normal cracks and abnormal cracks.

[0110] The fuzzy inference rules are set according to the material performance specifications and historical experimental results. The example rules include:

[0111] If the local elastic modulus is low and the local Poisson's ratio is low, the crack type determination index is abnormal;

[0112] If the local elastic modulus is high and the local Poisson's ratio is high, the crack type determination index is normal;

[0113] If the local elastic modulus is low and the local Poisson's ratio is high, the crack type determination index is abnormal;

[0114] The fuzzy inference system adopts a Mamdani-type inference mechanism to obtain the membership degree of the crack type determination index, and adopts the gravity method to defuzzify to obtain the type determination index, and the calculation formula is as follows:

[0115] ;

[0116] Wherein, is the type determination index, and satisfies the condition , is the membership degree of the crack type determination index.

[0117] The type determination index and the preset determination threshold are compared, if the type determination index is greater than the determination threshold, it is determined that the crack type is normal crack, if the type determination index is less than or equal to the determination threshold, it is determined that the crack type is abnormal crack.

[0118] It should be noted that the Mamdani-type inference mechanism is a reasoning method based on fuzzy set theory, which is used to realize the mapping relationship from input fuzzy variables to output fuzzy variables, which will not be described here; the determination threshold refers to the numerical boundary for determining whether the crack type is abnormal, according to the normalized results of the local elastic modulus and the local Poisson's ratio collected in history, statistical quantile method or standard deviation multiple method is used to set.

[0119] For the marked position of the determination result of abnormal crack, the structural stress characteristics of the marked crack are extracted, including the angle between the crack direction and the principal stress direction and the local stress concentration coefficient, and the regression analysis method based on support vector machine is used to calculate the crack damage index.

[0120] The angle between the crack direction and the principal stress direction and the local stress concentration coefficient are used as the calculation basis of the crack damage index to construct the feature vector , wherein, represents the angle between the crack direction and the principal stress direction, represents the local stress concentration coefficient, and the feature vector is used as the input vector of the support vector machine to evaluate the crack damage index. In the training stage of the support vector machine, the training sample set is constructed based on the historical task data set , wherein, is the feature vector of the i-th training sample, yi is the output value of the i-th training sample, and n is the total number of training samples.

[0121] The feature vector is input into the trained support vector regression model to predict the crack damage index, and the specific calculation formula is as follows:

[0122]

[0123] wherein, is the crack damage index, and the condition is satisfied, is the Lagrange multiplier coefficient, is the kernel function, and the Gaussian radial basis function form is adopted, is the kernel function bandwidth parameter, and b is the model bias term.

[0124] In step S4, a detection time window is set, and the state information of the crack marker position is acquired in real time within the detection time, including the relative displacement data of the crack two sides and the micro deformation data of the crack tip stress concentration area.

[0125] The relative displacement data is the maximum and minimum closure of the crack two sides. High-precision displacement sensors are arranged on the two sides of the crack to continuously collect displacement data, and the extreme values in the crack closure and opening process are determined through time series analysis, i.e. the maximum and minimum closure of the crack two sides. The difference between the maximum and minimum closure is taken as the closure amplitude, which reflects the dynamic response ability of the crack under natural or load action.

[0126] The micro deformation data is the relative displacement change along the tangential direction of the two sides of the crack. A triaxial strain gauge is installed on the surface of the crack to record the relative displacement change along the crack direction. The dislocation rate is obtained by dividing the relative displacement change by the detection time, which characterizes the shear slip trend of the crack within the detection time. The higher the dislocation rate, the more unstable the stress state of the structure.

[0127] After the calculation of the closure amplitude and dislocation rate, the two indicators are normalized to standardize their values to the interval [0, 1] to eliminate the dimensional difference and data scale influence. After the normalization of the closure amplitude and dislocation rate, the two normalized indicators are integrated using a nonlinear fusion function to generate the state trend value of the marker position. The hyperbolic tangent function is selected as the fusion function, and the specific calculation formula is as follows:

[0128]

[0129] wherein, is 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.

[0130] 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:

[0131] ;

[0132] 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.

[0133] The overall early warning probability is compared with the preset level classification threshold to classify the early warning level:

[0134] 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;

[0135] 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.

[0136] 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.

[0137] Embodiment 2, a quality detection system for a main structure of a buried sewage treatment plant, as shown in Figure 2 for realizing a quality detection method for a main structure of a buried sewage treatment plant, comprising an anomaly determination module, a crack marking module, a damage analysis module and a state early warning module, the modules are signal connected, and the functions are as follows:

[0138] Anomaly determination module: divide the main structure into regions, collect water level depth change data and displacement deformation variables of the divided regions, analyze the displacement change trend according to the displacement deformation variables, and determine whether it is an abnormal region according to the water level depth change data;

[0139] Crack marking module: emit ultrasonic signals to the abnormal region and obtain reflected echo data, mark the crack position according to the reflected echo data, obtain the strike information of the marked position, analyze the structure stress characteristics based on the strike information of the marked position, and generate characteristic collection signals;

[0140] Damage analysis module: after detecting the characteristic collection signals, collect material property data of the marked position, analyze the crack type based on the material property data, and generate a crack damage index by combining the structure stress characteristics of the marked position and the crack type;

[0141] State early warning module: set a detection time, collect state information of the marked position within the detection time to calculate the closing amplitude and the dislocation rate, generate the state trend of the marked position by fusing the closing amplitude and the dislocation rate, and analyze the early warning level in combination with the crack damage index.

[0142] The above formulas are all dimensionless values, and the formulas are obtained by software simulation of a large amount of data to obtain a formula closest to the real situation. The preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0143] The above-described embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, the above-described embodiments can be implemented in whole or in part in the form of 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, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing a set of one or more available media. The available media can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0144] It should be understood that the term "and / or" herein merely describes an association relationship of associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In addition, the character " / " herein generally represents an "or" relationship between the front and rear associated objects, but it can also represent an "and / or" relationship, which can be understood according to the context before and after.

[0145] In this application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0146] It should be understood that in various embodiments of the present application, the size of the sequence number of the above-described processes does not mean the order of execution, and the execution order of the processes should be determined according to their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0147] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed 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 the present application.

[0148] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0149] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are merely schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0150] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0151] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0152] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0153] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for quality inspection of the main structure of an underground sewage treatment plant, characterized in that: The method comprises the following steps: Step S1: regional division is performed on the main structure, water level depth variation data and displacement deformation data of the divided region are collected, displacement variation trend is analyzed according to the displacement deformation variable, and whether the region is an abnormal region is determined according to the water level depth variation data; Step S2: an ultrasonic signal is emitted to the abnormal region and reflected echo data are obtained, a crack position is marked according to the reflected echo data, strike information of the marked position is obtained, structural stress characteristics are analyzed based on the strike information of the marked position, and a characteristic collection signal is generated; Step S3: after the characteristic collection signal is detected, material characteristic data of the marked position are collected, a crack type is analyzed based on the material characteristic data, and a crack damage index is generated by comprehensively considering the structural stress characteristics of the marked position and the crack type; Step S4: a detection time is set, state information of the marked position in the detection time is collected, a closing amplitude and a dislocation rate are calculated, a state trend of the marked position is generated by fusing the closing amplitude and the dislocation rate, and a warning level is analyzed in combination with the crack damage index; In step S4, a detection time window is set, relative displacement data of structural surfaces on both sides of the crack and micro-deformation data of a stress concentration region at a crack tip are obtained in the detection time; The relative displacement data are maximum and minimum closing amounts of the structural surfaces on both sides of the crack, and a difference between the maximum and minimum closing amounts is taken as the closing amplitude; The micro-deformation data are a relative displacement variation amount along a tangential direction of the structural surfaces on both sides of the crack, and the relative displacement variation amount is divided by the detection time to obtain the dislocation rate; The closing amplitude and the dislocation rate are normalized, and a hyperbolic tangent function is used for nonlinear fusion to generate a state trend value of the marked position.

2. The main structure quality detection method for a buried sewage treatment plant according to claim 1, characterized in that: In step S1, the main structure of the buried sewage treatment plant is regionally divided according to functional areas; A plurality of continuous sampling windows are preset, water pressure values of the divided regions at the end of each sampling window are detected, and water level depth data are calculated based on the water pressure values; A mean value of each water level depth data is subtracted from each water level depth data, and an absolute value is taken as a water level variation value, and a maximum value of the water level variation value is taken as the water level depth variation data; The displacement deformation data are displacement deformation variables; Strain wavelengths of the divided regions at the end of the sampling window are detected, and displacement deformation variables of the divided regions are calculated based on the strain wavelengths; A deformation change rate of the displacement deformation variables in continuous time is calculated, and a deformation change acceleration is obtained based on the deformation change rate, and a mean value of each deformation change acceleration is taken as the displacement variation trend.

3. The main structure quality detection method for a buried sewage treatment plant according to claim 2, characterized in that: In step S1, whether the divided region is an abnormal region is determined by comprehensively considering the displacement variation trend and the water level depth variation data; If the displacement variation trend is greater than a preset displacement threshold value, the divided region is determined to be an abnormal region; If the displacement variation trend is less than or equal to the preset displacement threshold value and the water level depth variation data are greater than a preset water level variation threshold value, the divided region is determined to be an abnormal region; Otherwise, the divided region is determined to be a normal region.

4. The method of claim 3, wherein: in step S2, a plurality of monitoring points are selected in the abnormal area, ultrasonic waves are emitted to the main structure of the abnormal area, and reflected echo data of the ultrasonic waves after propagating inside the main structure are obtained, including a flight time difference and a reflection intensity of the echo signal; the flight time difference is a total time experienced by the ultrasonic waves from emission to return to the receiver; the reflection intensity of the echo signal refers to an amplitude of the echo signal; whether the flight time difference is abnormal is determined by calculating a flight difference threshold value through a MAD algorithm; whether the reflection intensity is abnormal is determined based on a mean value and a standard deviation of the reflection intensity of each monitoring point; if both the flight time difference and the reflection intensity are abnormal, it is determined that the abnormal area has a crack; and based on the flight time difference of the plurality of monitoring points and the positions of the monitoring points, a three-dimensional space of the abnormal area is reconstructed to obtain spatial coordinates of a plurality of crack positions and combine the spatial coordinates into a crack spatial coordinate point set.

5. The method of claim 4, wherein: in step S2, the crack spatial coordinate point set is marked by linearly fitting the coordinates of the crack positions to obtain strike information of the marked positions, including a direction vector of the strike of the crack; structural stress characteristics are analyzed based on the strike information of the marked positions to generate a characteristic acquisition signal; the structural stress characteristics include a local stress concentration coefficient and an angle between the strike of the crack and a principal stress direction vector; a strain wavelength in different directions of the marked positions is detected, and a strain component is obtained based on the strain wavelength; a stress is converted from the strain component through a generalized Hooke's law to obtain a three-dimensional stress tensor, and the three-dimensional stress tensor is subjected to eigenvalue decomposition through a power iteration algorithm to obtain a maximum stress of the marked positions and a principal stress direction vector; the local stress concentration coefficient is a ratio of the maximum stress to an average stress of the marked positions; and the angle between the strike of the crack and the principal stress direction vector is an angle between the direction vector of the strike of the crack and the principal stress direction vector.

6. The method of claim 1, wherein: in step S3, after the characteristic acquisition signal is detected, a longitudinal wave and a transverse wave propagation velocity are calculated based on a geometric size of the crack area through an ultrasonic pulse echo detection method, and a local elastic modulus and a local Poisson's ratio are converted according to an acoustic elastic theory relationship formula in combination with a density of a material of the crack area; the local elastic modulus and the local Poisson's ratio are subjected to normalization processing to construct a fuzzy logic reasoning model, a Mamdani type reasoning mechanism is adopted to obtain a membership degree of a crack type judgment index, and a gravity method is used to defuzzify to obtain the type judgment index.

7. The method of claim 6, wherein: in step S3, if the type judgment index is greater than a preset judgment threshold value, the crack type is determined to be a normal crack; and if the type judgment index is less than or equal to the judgment threshold value, the crack type is determined to be an abnormal crack. ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ For the marked position of abnormal crack, the structural stress characteristics of the marked crack are extracted to construct a feature vector, and a regression analysis method based on support vector machine is used to calculate the crack damage index.

8. The method of claim 1, wherein the buried sewage treatment plant main structure quality detection method is characterized in that: The state trend value and the crack damage index are used as input parameters, and a logistic regression model is used to calculate the comprehensive early warning probability; When the comprehensive early warning probability is greater than or equal to the preset grade division threshold, it is determined as high-grade early warning, prompting immediate on-site inspection and disposal; When the comprehensive early warning probability is less than the grade division threshold, it is determined as low-grade early warning, prompting to maintain routine monitoring.

9. A buried sewage treatment plant main structure quality detection system for implementing the buried sewage treatment plant main structure quality detection method of any one of claims 1-8, wherein the system comprises an anomaly determination module, a crack marking module, a damage analysis module, and a state early warning module, and each module has the following functions: The anomaly determination module divides the main structure into regions, collects water level depth change data and displacement deformation variables of the divided regions, analyzes displacement change trends based on the displacement deformation variables, and determines whether it is an abnormal region based on the water level depth change data; The crack marking module emits ultrasonic signals to the abnormal region and obtains reflected echo data, marks the crack position based on the reflected echo data, obtains the strike information of the marked position, analyzes the structural stress characteristics based on the strike information of the marked position, and generates a feature collection signal; The damage analysis module detects the feature collection signal, collects material property data of the marked position, analyzes the crack type based on the material property data, and generates a crack damage index based on the structural stress characteristics of the marked position and the crack type; The state early warning module sets a detection time, collects state information of the marked position within the detection time to calculate the closing amplitude and the throw rate, fuses the closing amplitude and the throw rate to generate the state trend of the marked position, and analyzes the early warning grade based on the crack damage index. ​

Images