Bridge pile foundation defect detection system based on ultrasonic technology

Abstract

The invention relates to the technical field of bridge pile detection, and provides a bridge pile foundation defect detection system based on an ultrasonic technology. The control terminal is used for controlling and managing the whole operation process of the system and monitoring data in real time; the multi-channel high-frequency ultrasonic detection module is used for transmitting ultrasonic signals through a multi-channel high-frequency probe array and receiving reflection signals in the bridge pile foundation to form original detection data; and the parallel computing and 3D imaging module is used for carrying out parallel computing processing on the received ultrasonic signal data and generating a three-dimensional structure image in the bridge pile foundation. The multi-channel high-frequency ultrasonic detection module is combined with the phased array technology and the multi-reflection wave processing technology, and high-precision detection of the internal structure of the bridge pile foundation is achieved. The phased array technology can flexibly control the propagation direction and depth of ultrasonic waves, and the coverage of a detection range and the resolution of signals are remarkably improved, so that the system can detect hidden defects such as micro cracks and holes.

Description

Technical Field

[0001] The invention relates to the technical field of bridge pile detection, and in particular to a bridge pile foundation defect detection system based on ultrasonic technology. Background Art

[0002] As an important infrastructure, the safety and stability of bridges have a vital impact on social and economic development. Bridge pile foundations are the key load-bearing parts of bridge structures, and the health of the pile foundations directly determines the overall safety of the bridge. However, bridge pile foundations have been in a complex environment for a long time and are affected by a variety of factors, such as loads, geological changes, environmental corrosion, etc., which can easily lead to various defects or damages, such as cracks, voids, and material aging. If these defects are not detected and repaired in time, they may lead to partial or overall failure of the bridge, causing serious safety hazards and economic losses.

[0003] At present, bridge pile foundation detection technology mainly includes traditional drilling sampling detection, static load test and other methods, which usually have limitations, such as time-consuming detection process, high cost, complex operation and susceptibility to human factors. In addition, traditional methods are difficult to fully and accurately reflect the internal structural state of the pile foundation without destroying the pile foundation, especially in the detection of deep defects. Therefore, how to efficiently, non-destructively and accurately detect internal defects of pile foundations has become an important challenge in the field of engineering detection.

[0004] In recent years, ultrasonic nondestructive testing technology has been gradually applied to the field of bridge pile foundation testing. Ultrasonic testing has the advantages of strong penetration, high resolution, and non-contact detection. It can quickly obtain internal structural information without destroying the pile foundation structure, and is suitable for defect detection of deeply buried pile foundations. However, the existing ultrasonic testing technology still faces some challenges in practical applications, such as interference from multi-reflection signals, imaging accuracy issues in complex environments, and how to efficiently process and analyze massive amounts of test data.

[0005] In order to solve the above problems, the present invention provides a bridge pile foundation defect detection system based on ultrasonic technology. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a bridge pile foundation defect detection system based on ultrasonic technology, which solves the problems of interference from multi-reflection signals and imaging accuracy in complex environments.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a bridge pile foundation defect detection system based on ultrasonic technology, comprising:

[0008] Control terminal, used to control and manage the overall operation process of the system and conduct real-time monitoring of data;

[0009] A multi-channel high-frequency ultrasonic detection module is used to transmit ultrasonic signals through a multi-channel high-frequency probe array and receive reflected signals inside the bridge pile foundation to form original detection data;

[0010] A parallel computing and 3D imaging module is used to perform parallel computing processing on the received ultrasonic signal data and generate a three-dimensional structural imaging of the interior of the bridge pile foundation;

[0011] Defect recognition module, which is used to automatically identify defects in the internal structure of bridge pile foundations based on the results of 3D structural imaging, identify possible structural defects and classify them;

[0012] The risk and failure prediction module is used to conduct risk assessment and failure prediction of bridge pile foundations based on the results of the defect identification module, and generate a prediction report;

[0013] Data storage unit, used to store various data information during the detection process;

[0014] The remote control terminal is used to remotely access and control the detection system, realize remote management of detection operations and remote transmission of data.

[0015] Preferably, the multi-channel high-frequency ultrasonic detection module includes:

[0016] A high-frequency probe detection unit is used to transmit and receive ultrasonic signals through a high-frequency probe array to detect the internal structure of the pile foundation;

[0017] Phased array unit, used to control the transmission and reception phases of the high-frequency probe array to adjust the propagation direction of ultrasound and achieve imaging at different angles and depths;

[0018] The multi-reflection wave processing unit is used to process the multiple reflection echoes of the ultrasonic signal, extract the structural information at different depths and angles, and improve the imaging accuracy.

[0019] Preferably, the parallel computing and 3D imaging module includes:

[0020] Multimodal data fusion unit, used to fuse the detection data of multi-channel high-frequency ultrasonic detection modules, combine the information collected by different sensors, and generate comprehensive defect detection data;

[0021] GPU parallel computing unit is used to accelerate ultrasonic signal processing and imaging calculation, shorten the computing time required for imaging, and improve system response efficiency;

[0022] An inverse scattering imaging unit is used to construct a preliminary image of the internal structure of the pile foundation through an inverse scattering algorithm based on the reflection and scattering characteristics of ultrasound;

[0023] The three-dimensional imaging unit is used to reconstruct the inverse scattering imaging results in three dimensions and generate a three-dimensional structural diagram inside the bridge pile foundation to facilitate the detection of the location and shape of defects.

[0024] Preferably, the defect identification module comprises:

[0025] A depth feature extraction unit is used to extract depth information reflecting the internal structural features of the pile foundation from the ultrasonic detection data to identify the features of potential defects;

[0026] The defect classification unit is used to classify the extracted depth features according to different types of defect features and distinguish different forms of defects such as cracks and voids;

[0027] Intelligent decision-making unit, used to make risk level judgment and decision support for defects based on classification results and system preset risk standards;

[0028] The deep learning unit is used to continuously optimize the defect recognition model through deep learning algorithms, thereby improving the system's recognition accuracy and adaptability to complex defects.

[0029] Preferably, the risk and failure prediction module includes:

[0030] The physical model simulation unit is used to establish a physical model of the bridge structure based on the structural characteristics of the bridge pile foundation and simulate and analyze its bearing state and response characteristics;

[0031] Fatigue life prediction unit, which is used to evaluate the fatigue life of bridge pile foundations and predict their remaining service life based on the data output by the defect identification module and the mechanical model of the pile foundation structure;

[0032] Fault prediction model unit, used to predict the development trend of pile foundation defects through algorithm model and provide an estimate of the time when faults will occur;

[0033] The risk assessment unit is used to assess the risk level of the pile foundation structure based on the prediction results combined with the safety standards;

[0034] The maintenance decision generation unit is used to generate maintenance and inspection plans for bridge pile foundations based on risk assessment results, providing a decision-making basis for safety assurance.

[0035] Preferably, the relationship between the reflected signal intensity and the propagation time of the multi-reflected wave processing unit can be expressed as:

[0036] I(t)=I0·e -αt

[0037] Among them, I(t) is the received signal strength, I0 is the initial signal strength, α is the attenuation coefficient, and t is the propagation time.

[0038] Preferably, the mathematical model of the inverse scattering imaging unit is expressed as:

[0039]

[0040] Among them, I(x,y,z) is the imaging result, P i is the reflection intensity of the i-th scatterer, k i is the wave number, r i is the distance between the scatterer and the probe.

[0041] Preferably, the defect classification unit classifies defect features by a classification algorithm to distinguish defects such as cracks and cavities. Assuming that the detected feature vector is X={x1,x2,…,x n}, the classification model is represented as;

[0042] y=f(X)=argmax c P(c|X)

[0043] Where P(c|X) is the posterior probability of category c.

[0044] Preferably, the deep learning unit optimizes the defect recognition model through a convolutional neural network (CNN). The convolution operation formula of the CNN model is:

[0045]

[0046] Among them, x i,j is the input feature, w m,n is the convolution kernel weight, and b is the bias term.

[0047] Preferably, the fault prediction model unit performs prediction through a defect development trend model, based on a time series model, an ARIMA model, and its prediction formula is:

[0048] y t =φ1y t-1 +φ2y t-2 +…+φ p y t-p +θ1∈ t-1 +…+θ q ∈ t-q +∈ t

[0049] Among them, y t is the defect state at the current time, ∈ t is the noise term.

[0050] Working principle: The system uses a multi-channel high-frequency ultrasonic detection module to perform ultrasonic detection on the internal structure of the bridge pile foundation. The module uses a high-frequency probe array to transmit ultrasonic signals. When the ultrasonic signal propagates inside the pile foundation, it encounters interfaces of different materials or structural defects, which will generate reflected waves and scattered waves. The receiving unit of the high-frequency probe array is responsible for capturing these echo signals, converting them into electrical signals, and forming raw detection data. These signals are then adjusted through phased array technology to adjust the beam direction and depth, allowing the system to obtain detailed information inside the pile foundation from different angles and depths.

[0051] The parallel computing and 3D imaging modules process the received ultrasonic signal data. Through GPU parallel computing, a large amount of ultrasonic signal data can be processed quickly and efficiently, and the complex echo signal can be converted into a structural image inside the pile foundation through inverse scattering imaging technology. Through three-dimensional reconstruction technology, the system can generate a three-dimensional image of the bridge pile foundation. This process allows inspectors to visualize the location, shape and size of defects inside the pile foundation, thereby accurately evaluating the health of the bridge pile foundation.

[0052] After generating the 3D structure diagram, the system's defect recognition module will further analyze the imaging data. First, the system extracts key information reflecting the internal characteristics of the pile foundation from the detection data through the deep feature extraction unit, and then uses the classification algorithm to classify the identified defects into different categories, such as cracks, voids, etc. Through the intelligent decision-making unit, the system assesses the risk level of these defects according to the preset standards to help users judge the severity of the defects.

[0053] The risk and failure prediction module conducts a comprehensive assessment of the risk of pile foundations based on the results of defect identification. This module analyzes the response of pile foundations under different loads through physical model simulation, combined with the actual structure and material properties of the pile foundation. The system evaluates the fatigue life of the pile foundation, predicts its remaining service life, and estimates the possible time of future failures based on the defect development trend model. With this information, the system can provide users with health status reports and risk assessment results of bridge pile foundations to guide maintenance and repair decisions.

[0054] The remote control terminal and data storage unit equipped in the system further ensure the management and control of the test data. The remote control terminal allows users to remotely operate and monitor, making it convenient to manage the test equipment in a different location. The data storage unit is used to store all the data during the test for subsequent analysis and long-term monitoring.

[0055] The present invention provides a bridge pile foundation defect detection system based on ultrasonic technology.

[0056] Beneficial effects:

[0057] 1. The present invention realizes high-precision detection of the internal structure of bridge pile foundations by combining multi-channel high-frequency ultrasonic detection modules with phased array technology and multi-reflection wave processing technology. Phased array technology can flexibly control the propagation direction and depth of ultrasonic waves, significantly improving the coverage of the detection range and the resolution of the signal, so that the system can detect hidden defects such as tiny cracks and cavities.

[0058] 2. The present invention accelerates data processing through parallel computing and 3D imaging module through GPU parallel computing, and combines inverse scattering algorithm and 3D reconstruction technology to achieve real-time imaging of the internal structure of the pile foundation. The system can not only generate accurate 3D structural diagrams, but also intuitively display the specific location and shape of defects, providing comprehensive detection information for engineers, greatly improving detection efficiency.

[0059] 3. The present invention can automatically identify various defects in pile foundation structures through the defect recognition module based on deep feature extraction and intelligent decision-making algorithms, and optimize the recognition model through deep learning to improve the system's adaptability and recognition accuracy to complex structural defects. This intelligent defect classification and recognition method reduces the subjectivity of human judgment and improves the reliability of the detection results.

[0060] 4. The present invention can predict the fatigue life and failure time of bridge pile foundation in long-term use through physical model simulation, fatigue life assessment and failure prediction model through risk and failure prediction module. Combined with the risk assessment unit, the system can quantitatively assess the safety of pile foundation structure and generate reasonable maintenance and repair plans based on the assessment results to ensure the continuous safety and service life of the pile foundation. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 A framework diagram of the system of the present invention;

[0062] Figure 2 It is a schematic diagram of a multi-channel high-frequency ultrasonic detection module of the present invention;

[0063] Figure 3 A schematic diagram of the parallel computing and 3D imaging module of the present invention;

[0064] Figure 4 It is a schematic diagram of a defect recognition module of the present invention;

[0065] Figure 5 It is a schematic diagram of the risk and fault prediction module of the present invention. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] Please see attached Figure 1 - Attachment Figure 5 , an embodiment of the present invention provides a bridge pile foundation defect detection system based on ultrasonic technology, comprising;

[0068] Control terminal, used to control and manage the overall operation process of the system and conduct real-time monitoring of data;

[0069] A multi-channel high-frequency ultrasonic detection module is used to transmit ultrasonic signals through a multi-channel high-frequency probe array and receive reflected signals inside the bridge pile foundation to form original detection data;

[0070] A parallel computing and 3D imaging module is used to perform parallel computing processing on the received ultrasonic signal data and generate a three-dimensional structural imaging of the interior of the bridge pile foundation;

[0071] Defect recognition module, which is used to automatically identify defects in the internal structure of bridge pile foundations based on the results of 3D structural imaging, identify possible structural defects and classify them;

[0072] The risk and failure prediction module is used to conduct risk assessment and failure prediction of bridge pile foundations based on the results of the defect identification module, and generate a prediction report;

[0073] Data storage unit, used to store various data information during the detection process;

[0074] The remote control terminal is used to remotely access and control the detection system, realize remote management of detection operations and remote transmission of data.

[0075] The multi-channel high-frequency ultrasonic detection module includes:

[0076] A high-frequency probe detection unit is used to transmit and receive ultrasonic signals through a high-frequency probe array to detect the internal structure of the pile foundation;

[0077] Phased array unit, used to control the transmission and reception phases of the high-frequency probe array to adjust the propagation direction of ultrasound and achieve imaging at different angles and depths;

[0078] Multi-reflection wave processing unit, used to process multiple reflection echoes of ultrasonic signals, extract structural information at different depths and angles, and improve imaging accuracy;

[0079] Specifically, the multi-channel high-frequency ultrasonic detection module is responsible for transmitting and receiving ultrasonic signals to detect the internal structure of the bridge pile foundation and obtain original detection data. The high-frequency probe detection unit uses a high-frequency probe array to perform ultrasonic detection of the pile foundation structure. The high-frequency probe converts electrical signals into ultrasonic signals through the piezoelectric effect and transmits them to the interior of the pile foundation. When the ultrasonic wave encounters different material interfaces or defects inside, it will generate reflected waves or scattered waves. The receiving unit in the probe array is responsible for capturing these echo signals and converting them into electrical signals to form preliminary original detection data;

[0080] In order to enhance the directional control capability of ultrasonic signals, the detection module adopts phased array technology. The phased array unit can adjust the ultrasonic beam direction and focus depth by controlling the transmission and reception phases of each probe, thereby achieving accurate imaging of different areas inside the pile foundation. Phased array technology controls the beam direction through the following formula;

[0081]

[0082] Among them, Δφ is the phase difference between the phased array probes, d is the distance between the probes, θ is the deflection angle of the beam, and λ is the wavelength of the ultrasound. By controlling Δφ, the system can achieve precise adjustment of the beam direction, thereby effectively improving the imaging resolution and depth detection capability;

[0083] In order to extract effective structural information from complex ultrasonic signals, the detection module integrates a multi-reflection wave processing unit. Due to the complex internal structure of the pile foundation, the ultrasonic wave will encounter multiple interfaces or defects during propagation, resulting in multiple reflections and scattering of the signal. The relationship between the reflection signal intensity and propagation time of the multi-reflection wave processing unit is expressed as;

[0084] I(t)=I0·e -αt

[0085] Where I(t) is the received signal strength, I0 is the initial signal strength, α is the attenuation coefficient, and t is the propagation time;

[0086] Short-time Fourier transform (STFT) can extract and distinguish reflection signals at different depths and angles. Short-time Fourier transform is used to convert time domain signals into time-frequency domain signals, so as to analyze the temporal variation trend of the signals. The formula of STFT is as follows;

[0087]

[0088] Among them, x(t) is the original ultrasonic signal, w(t-τ) is the time window function, and f is the frequency variable. Through time-frequency domain analysis, the system can detect echo signals at different depths and mark them as corresponding structural features.

[0089] The parallel computing and 3D imaging module includes:

[0090] Multimodal data fusion unit, used to fuse the detection data of multi-channel high-frequency ultrasonic detection modules, combine the information collected by different sensors, and generate comprehensive defect detection data;

[0091] GPU parallel computing unit is used to accelerate ultrasonic signal processing and imaging calculation, shorten the computing time required for imaging, and improve system response efficiency;

[0092] An inverse scattering imaging unit is used to construct a preliminary image of the internal structure of the pile foundation through an inverse scattering algorithm based on the reflection and scattering characteristics of ultrasound;

[0093] A three-dimensional imaging unit is used to reconstruct the inverse scattering imaging results in three dimensions to generate a three-dimensional structural diagram inside the bridge pile foundation, so as to facilitate the detection of the location and shape of defects;

[0094] Specifically, the multi-dimensional signals from the multi-channel high-frequency ultrasonic detection module are first fused and processed by the multi-modal data fusion unit. The data generated by multi-channel detection includes not only reflected waves and scattered waves, but also structural information obtained from different angles and depths. Therefore, in order to ensure the integrity and accuracy of the detection results, the system integrates these multi-modal data through a weighted fusion algorithm.

[0095] The process of weighted fusion is expressed by the following formula;

[0096]

[0097] Among them, S i is the ultrasonic signal of each channel, w i is the weight of the corresponding channel, S fused is the fused signal. Weight w i Determined by factors such as signal quality and depth, the optimization algorithm is adaptively adjusted to ensure that signals at different depths and angles are reasonably integrated;

[0098] In order to process and analyze large-scale ultrasonic signal data, the system integrates GPU parallel computing units, which can process multiple data streams simultaneously, thereby greatly improving the speed and efficiency of data processing. In particular, large-scale matrix operations and signal processing algorithms in ultrasonic testing can achieve real-time and efficient computing through parallelization technology;

[0099] The Fast Fourier Transform (FFT), which is commonly used in parallel computing, is used to process the frequency domain analysis of ultrasonic signals. Its basic formula is as follows;

[0100]

[0101] By parallelizing FFT operations, the GPU computing unit can quickly process massive amounts of ultrasonic echo data and convert time domain signals into frequency domain signals, thereby extracting structural information inside the pile foundation. This calculation process greatly reduces the time required for signal processing and imaging, and improves the real-time performance of the system;

[0102] The inverse scattering imaging unit uses an algorithm based on the ultrasonic scattering characteristics to reconstruct the multi-channel reflected wave signal into a preliminary image of the internal structure of the pile foundation. The reflection and scattering phenomenon produced by ultrasonic waves at the interface of different media is the basis of imaging;

[0103] The mathematical model is expressed as;

[0104]

[0105] Among them, I)x,y,z) is the imaging result, P i is the reflection intensity of the i-th scatterer, k i is the wave number, r i is the distance between the scatterer and the probe;

[0106] Inverse scattering imaging is done by reversely deducing the received reflected signal to reconstruct the position and shape of the reflecting interface. The basis of inverse scattering imaging is the use of the wave equation.

[0107]

[0108] Among them, p(r,t) is the pressure field at position r and time t, G(r,t; r′,t′) is the Green's function, which describes the propagation of ultrasound at different positions r′ and time t′, and f(r′) is the intensity function of the reflected wave source. Through the inverse propagation equation, the system can infer the internal geometric characteristics of the pile foundation from the reflected wave data;

[0109] Based on the inverse scattering imaging results, the 3D imaging unit generates a 3D structural image of the bridge pile foundation through 3D reconstruction technology. 3D imaging is a further improvement of 2D data, allowing inspectors to visually observe the internal structural state of the pile foundation, thereby making accurate judgments on the shape, size and location of defects. 3D imaging uses a voxel-based method, where each voxel represents a minimum unit in space. The system combines these voxels to form a 3D model based on the strength and position information of the ultrasonic signal. The basic principle of 3D imaging can be expressed by the volume rendering formula;

[0110] C final =∫ ray C voxel (r)e -τ(r) dr

[0111] Among them, Cfinal is the final color of the ray reaching the observation point after passing through the volume, C voxel (r) is the color value of each voxel, and τ(r) is the optical thickness of the voxel. Through this formula, the system can render a three-dimensional image of the pile foundation from multiple angles to show the morphology of its internal defects.

[0112] The defect identification module comprises:

[0113] A depth feature extraction unit is used to extract depth information reflecting the internal structural features of the pile foundation from the ultrasonic detection data to identify the features of potential defects;

[0114] The defect classification unit is used to classify the extracted depth features according to different types of defect features and distinguish different forms of defects such as cracks and voids;

[0115] Intelligent decision-making unit, used to make risk level judgment and decision support for defects based on classification results and system preset risk standards;

[0116] Deep learning unit, which is used to continuously optimize the defect recognition model through deep learning algorithms to improve the system's recognition accuracy and adaptability to complex defects;

[0117] Specifically, the defect recognition module first extracts the depth feature information reflecting the internal structure of the pile foundation from the three-dimensional structural imaging results through the depth feature extraction unit. During the propagation of ultrasonic signals, the reflected signals will change due to the different physical properties of different materials and structures. By analyzing these changes, the system can extract the geometric features of the internal structure of the pile foundation. The extracted depth features are processed by the defect classification unit, and the system can automatically classify them according to the characteristics of different defect types. Different types of defects, such as cracks, voids, or areas of uneven density, have different signal patterns, which are distinguished by feature vectors; classify the defect features, distinguish cracks, voids, and other defects, and assume that the detected feature vector is X={x1,x2,…,x n}, the classification model is represented as;

[0118] y=f(X)=argmax c P(c|X)

[0119] Where P(c|X) is the posterior probability of category c;

[0120] The intelligent decision-making unit makes a risk level judgment on the defects based on the output of the defect classification unit and the system's preset safety standards or design specifications. The system conducts a risk assessment on each identified defect type and calculates its impact on the safety of the pile foundation structure. This unit uses a rule-based reasoning system (RBR) or a Bayesian network-based decision support system to provide quantitative analysis of risk levels. The deep learning unit uses a convolutional neural network (CNN). The convolution operation formula of the CNN model is:

[0121]

[0122] Among them, x i,j is the input feature, w m,n is the convolution kernel weight, b is the bias term;

[0123] Continuously optimize the defect recognition model. The system collects a large amount of historical inspection data and uses it as a training set to train the model, enabling it to have self-learning capabilities and continuously improve recognition accuracy and robustness. The goal of the deep learning unit is to improve the system's ability to recognize complex defects (such as material delamination or tiny cracks);

[0124]

[0125] Among them, θ represents the parameter set of the model, is the loss function, y i is the true label of the i-th sample, f(x i ; θ) is the predicted output of the model. By minimizing the loss function, the system can optimize the model parameters and thus improve the accuracy of defect identification.

[0126] The risk and failure prediction module includes:

[0127] The physical model simulation unit is used to establish a physical model of the bridge structure based on the structural characteristics of the bridge pile foundation and simulate and analyze its bearing state and response characteristics;

[0128] Fatigue life prediction unit, which is used to evaluate the fatigue life of bridge pile foundations and predict their remaining service life based on the data output by the defect identification module and the mechanical model of the pile foundation structure;

[0129] Fault prediction model unit, used to predict the development trend of pile foundation defects through algorithm model and provide an estimate of the time when faults will occur;

[0130] The risk assessment unit is used to assess the risk level of the pile foundation structure based on the prediction results combined with the safety standards;

[0131] Maintenance decision generation unit, used to generate maintenance and repair plans for bridge pile foundations based on risk assessment results, providing a decision basis for safety assurance;

[0132] Specifically, the physical model simulation unit is used to establish a physical simulation model based on the actual structure and material properties of the bridge pile foundation. The model simulates the bearing state and response characteristics of the pile foundation under various loads and environmental factors. The pile foundation structure can be simplified as an elastic material model, and the finite element method is used for stress analysis. The basic equation of the finite element method is:

[0133] K·u=F

[0134] Among them, K is the stiffness matrix of the structure, u is the displacement vector, and F is the external force vector. Through simulations under different loading conditions, the system can analyze the deformation and stress distribution of the pile foundation under various working conditions, thereby providing basic data for risk assessment;

[0135] The fatigue life prediction unit evaluates the fatigue life of the pile foundation based on the data output by the defect identification module and the mechanical model of the pile foundation. During long-term use, the pile foundation may suffer fatigue damage due to the constantly changing loads. The prediction of fatigue life is usually based on the SN curve (stress-life curve), which describes the fatigue life of the material under different stress levels;

[0136] The formula for fatigue life prediction is:

[0137]

[0138] Among them, N f is the fatigue life (number of cycles), σ a is the stress amplitude, σ0 is the fatigue limit of the material, and b is the fatigue index of the material. Based on the structural defects identified by defects, the system can evaluate the impact of defects on fatigue life and calculate the remaining service life of the pile foundation. The fault prediction model unit predicts the possible failure time of the bridge pile foundation based on the development trend of the defects;

[0139] Prediction is performed through the defect development trend model, based on the time series model, ARIMA model, and its prediction formula is:

[0140] y t =φ1y t-1 +φ2y t-2 +…+φ p y t-p +θ1∈ t-1 +…+θ q ∈ t-q +∈ t

[0141] Among them, y tis the defect state at the current time, ∈ t is the noise term;

[0142] The risk assessment unit conducts a quantitative assessment of the risk level of bridge pile foundations based on the results of failure prediction and in combination with national standards or bridge safety design specifications. The assessment model uses the risk matrix method or probabilistic risk assessment to comprehensively consider the probability of failure and its potential impact.

[0143] The formula for calculating the risk level is;

[0144] R=P×C

[0145] Among them, P represents the probability of failure, which is usually calculated through historical failure data and prediction models; C represents the severity of the consequences that may be caused by the failure, which is evaluated through the stress state of the structure and design specifications. The system displays the evaluation results in a risk matrix or other forms to facilitate users to understand the risk level and its specific meaning;

[0146] The maintenance decision generation unit generates corresponding bridge pile foundation maintenance and inspection plans by analyzing the output results of the risk assessment unit. This unit uses a rule-based decision support system to combine established maintenance rules and risk standards to make recommendations for maintenance or further inspection;

[0147] Maintenance decisions can be generated using the following algorithm;

[0148] M=f(R,T,C)

[0149] Among them, M represents the maintenance decision plan, R is the risk level, T is the estimated remaining service life, and C is the cost of repairing the defect. Through comprehensive analysis of these parameters, the system automatically recommends the best maintenance time and plan to ensure the safety and service life of the pile foundation structure.

[0150] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A bridge pile foundation defect detection system based on ultrasonic technology, characterized in that: include; Control terminal, used to control and manage the overall operation process of the system and conduct real-time monitoring of data; A multi-channel high-frequency ultrasonic detection module is used to transmit ultrasonic signals through a multi-channel high-frequency probe array and receive reflected signals inside the bridge pile foundation to form original detection data; A parallel computing and 3D imaging module is used to perform parallel computing processing on the received ultrasonic signal data and generate a three-dimensional structural imaging of the interior of the bridge pile foundation; Defect recognition module, which is used to automatically identify defects in the internal structure of bridge pile foundations based on the results of 3D structural imaging, identify possible structural defects and classify them; The risk and failure prediction module is used to conduct risk assessment and failure prediction of bridge pile foundations based on the results of the defect identification module, and generate a prediction report; Data storage unit, used to store various data information during the detection process; The remote control terminal is used to remotely access and control the detection system, realize remote management of detection operations and remote transmission of data.

2. The bridge pile foundation defect detection system based on ultrasonic technology according to claim 1 is characterized in that: The multi-channel high-frequency ultrasonic detection module includes: A high-frequency probe detection unit is used to transmit and receive ultrasonic signals through a high-frequency probe array to detect the internal structure of the pile foundation; Phased array unit, used to control the transmission and reception phases of the high-frequency probe array to adjust the propagation direction of ultrasound and achieve imaging at different angles and depths; The multi-reflection wave processing unit is used to process the multiple reflection echoes of the ultrasonic signal, extract the structural information at different depths and angles, and improve the imaging accuracy.

3. The bridge pile foundation defect detection system based on ultrasonic technology according to claim 1 is characterized in that: The parallel computing and 3D imaging module includes: Multimodal data fusion unit, used to fuse the detection data of multi-channel high-frequency ultrasonic detection modules, combine the information collected by different sensors, and generate comprehensive defect detection data; GPU parallel computing unit is used to accelerate ultrasonic signal processing and imaging calculation, shorten the computing time required for imaging, and improve system response efficiency; An inverse scattering imaging unit is used to construct a preliminary image of the internal structure of the pile foundation through an inverse scattering algorithm based on the reflection and scattering characteristics of ultrasound; The three-dimensional imaging unit is used to reconstruct the inverse scattering imaging results in three dimensions and generate a three-dimensional structural diagram inside the bridge pile foundation to facilitate the detection of the location and shape of defects.

4. The bridge pile foundation defect detection system based on ultrasonic technology according to claim 1 is characterized in that: The defect identification module comprises: A depth feature extraction unit is used to extract depth information reflecting the internal structural features of the pile foundation from the ultrasonic detection data to identify the features of potential defects; The defect classification unit is used to classify the extracted depth features according to different types of defect features and distinguish different forms of defects such as cracks and voids; Intelligent decision-making unit, used to make risk level judgment and decision support for defects based on classification results and system preset risk standards; The deep learning unit is used to continuously optimize the defect recognition model through deep learning algorithms, thereby improving the system's recognition accuracy and adaptability to complex defects.

5. The bridge pile foundation defect detection system based on ultrasonic technology according to claim 1 is characterized in that: The risk and failure prediction module includes: The physical model simulation unit is used to establish a physical model of the bridge structure based on the structural characteristics of the bridge pile foundation and simulate and analyze its bearing state and response characteristics; Fatigue life prediction unit, which is used to evaluate the fatigue life of bridge pile foundations and predict their remaining service life based on the data output by the defect identification module and the mechanical model of the pile foundation structure; Fault prediction model unit, used to predict the development trend of pile foundation defects through algorithm model and provide an estimate of the time when faults will occur; The risk assessment unit is used to assess the risk level of the pile foundation structure based on the prediction results combined with the safety standards; The maintenance decision generation unit is used to generate maintenance and inspection plans for bridge pile foundations based on risk assessment results, providing a decision-making basis for safety assurance.

6. The bridge pile foundation defect detection system based on ultrasonic technology according to claim 2 is characterized in that: The relationship between the reflected signal intensity and the propagation time of the multi-reflected wave processing unit is expressed as: I(t)=I0·e -αt Among them, I(t) is the received signal strength, I0 is the initial signal strength, α is the attenuation coefficient, and t is the propagation time.

7. The bridge pile foundation defect detection system based on ultrasonic technology according to claim 3 is characterized in that: The mathematical model of the inverse scattering imaging unit is expressed as follows: Among them, I(x,y,z) is the imaging result, P i is the reflection intensity of the i-th scatterer, k i is the wave number, r i is the distance between the scatterer and the probe.

8. The bridge pile foundation defect detection system based on ultrasonic technology according to claim 4 is characterized in that: The defect classification unit classifies defect features through a classification algorithm to distinguish defects such as cracks and cavities. Assuming that the detected feature vector is X={x1,x2,…,x n }, the classification model is represented as; y=f(X)=argmax c P(c|X) Where P(c|X) is the posterior probability of category c.

9. The bridge pile foundation defect detection system based on ultrasonic technology according to claim 4 is characterized in that: The deep learning unit optimizes the defect recognition model through a convolutional neural network (CNN), and the convolution operation formula of the CNN model is: Among them, x i,j is the input feature, w m,n is the convolution kernel weight, and b is the bias term.

10. The bridge pile foundation defect detection system based on ultrasonic technology according to claim 5 is characterized in that: The fault prediction model unit predicts through the defect development trend model, based on the time series model, the ARIMA model, and its prediction formula is: y t =φ1y t-1 +φ2y t-2 +…+φ p y t-p +θ1∈ t-1 +…+θ q ∈ t-q +∈ t Among them, y t is the defect state at the current time, ∈ t is the noise term.

Images