A self-sensing concrete based damage monitoring assistance system

Abstract

The application provides a self-sensing concrete-based damage monitoring auxiliary system and relates to the technical field of concrete damage monitoring.The system comprises a self-sensing concrete hardware module, a data acquisition and processing module, an environment compensation correction module, a data decoupling module and a data analysis and prediction module.The high-density microelectrode grid is pre-buried in the self-sensing concrete by optimizing the sensing network layout.These microelectrodes can not only increase the signal acquisition points, but also effectively reduce the signal attenuation problem, and the electromagnetic suppression submodule is used to enhance the resistance to local electromagnetic interference of the application, so that the system can maintain good signal stability even in a complex construction environment.Thus, by optimizing the sensing network layout, enhancing the anti-electromagnetic interference capability, establishing a temperature and humidity compensation model and combining the intelligent signal processing algorithm, the high-precision and high-robustness damage monitoring is realized, so that the monitoring efficiency and engineering applicability of the self-sensing concrete in the complex environment are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of concrete damage monitoring, and particularly relates to a damage monitoring auxiliary system based on self-sensing concrete. BACKGROUND

[0002] With the continuous development of modern engineering technology, structural health monitoring (SHM) has become one of the key technologies to ensure the safety of infrastructure, prolong the service life and reduce the maintenance cost. In the structural health monitoring system, the traditional damage monitoring method usually relies on external sensors (such as strain gauges, accelerometers, displacement sensors, etc.) to monitor the stress, displacement or deformation of the structure. These sensors usually need to be installed on the surface or inside the structure and connected with the data acquisition system through wires. However, the traditional sensors have some inherent shortcomings, especially in large-scale monitoring and long-term use, the layout, maintenance and calibration of the sensors are often very tedious and increase the cost and complexity of the system.

[0003] In order to overcome the limitations of traditional sensor systems, in recent years, self-sensing concrete (Self-sensing Concrete) has gradually emerged as a new type of structural health monitoring technology. Self-sensing concrete is a kind of concrete that is mixed with conductive materials (such as carbon fibers, carbon nanotubes, steel fibers, etc.) to give it the ability of resistance self-sensing, so that the concrete itself becomes a sensor and can monitor its own health status in real time. This method not only improves the sensitivity and efficiency of monitoring, but also reduces the installation demand of external sensors, providing a new solution for structural health monitoring.

[0004] However, its actual application still faces many technical bottlenecks and challenges, for example, the uneven dispersion of conductive materials in the concrete matrix leads to exponential decay of resistance signal with transmission distance, which seriously affects the monitoring range and sensitivity; secondly, the complex environmental electromagnetic interference (such as large machinery, wireless communication equipment, etc.) in the construction site makes the weak damage signal easily overwhelmed by noise, the actual signal-to-noise ratio is generally lower than 5dB, greatly increasing the difficulty of signal extraction; in addition, the resistance drift caused by environmental temperature and humidity fluctuations can reach 300% to 500% of the damage signal, resulting in poor baseline stability and difficulty in distinguishing real damage from environmental interference; more complex is that the coupling of load, corrosion, freeze-thaw and other factors in actual engineering will cause serious aliasing of characteristic signals, and traditional methods are difficult to effectively decouple and identify damage characteristics, therefore the present application proposes a damage monitoring auxiliary system based on self-sensing concrete to solve the problems existing in the prior art. SUMMARY

[0005] In view of the above problems, the purpose of the present application is to provide a self-sensing concrete-based damage monitoring auxiliary system, which has the advantage of improving the monitoring efficiency of self-sensing concrete in complex environments and can solve the problems existing in the prior art.

[0006] To achieve the purpose of the present application, the present application realizes the following technical solutions: a self-sensing concrete-based damage monitoring auxiliary system, comprising a self-sensing concrete hardware module for collecting, processing and transmitting data related to the internal environment of the concrete in real time through a high-density microelectrode grid;

[0007] A data acquisition and processing module is used to collect and preprocess the data collected in the self-sensing concrete hardware module;

[0008] An environmental compensation correction module is used to establish a temperature and humidity compensation model and correct the processed data through the temperature and humidity compensation model;

[0009] A data decoupling module is used to decouple the influence of multiple factors in the corrected data;

[0010] A data analysis and prediction module is used to analyze and predict the decoupled data using a convolutional neural network to realize damage monitoring of self-sensing concrete.

[0011] Further improvement lies in that the self-sensing concrete hardware module comprises a distributed microelectrode sub-module for setting a high-density microelectrode grid inside the self-sensing concrete, an electromagnetic suppression sub-module for electromagnetic shielding and reducing electromagnetic interference, a signal enhancement sub-module for enhancing the signal of the high-density microelectrode grid, a temperature and humidity sensing sub-module for collecting the internal environmental parameters of the self-sensing concrete, and a data sending sub-module for sending data through wireless communication technology.

[0012] Further improvement lies in that the data acquisition and processing module comprises a data processing sub-module for collecting and processing the data of the self-sensing concrete hardware module and a data storage sub-module for storing the processed data.

[0013] Further improvement lies in that the processing flow of the data processing sub-module is:

[0014] S1: denoising processing is performed on the collected data using wavelet transform method, and then normalization processing is performed;

[0015] S2: feature extraction is performed on the data processed in S1 to obtain the required feature data;

[0016] S3: a corresponding timestamp is generated for the extracted feature data, which is then transmitted to the data storage sub-module for storage.

[0017] Further improvement lies in that the environment compensation correction module comprises a temperature and humidity compensation model establishing submodule for establishing a compensation model according to temperature and humidity changes of the environment and a data correction submodule for correcting data through the compensation model.

[0018] Further improvement lies in that the specific steps for establishing the compensation model according to temperature and humidity changes of the environment are:

[0019] SS1: Collecting experimental data between temperature, humidity and resistance change amount, and constructing a training data set;

[0020] SS2: Cleaning and standardizing the obtained data;

[0021] SS3: Using a support vector regression algorithm to establish a nonlinear mapping relationship between the resistance change amount and the temperature and humidity, and training the compensation model by using the training data set;

[0022] SS4: Using a ten-fold cross-validation method to evaluate the model, and completing establishment of the compensation model after evaluation.

[0023] Further improvement lies in that the data decoupling module comprises a decoupling processing submodule for separating different influencing factors mixed in the data through a variational modal decomposition method and a data fusion submodule for fusing the decoupled data.

[0024] Further improvement lies in that the data analysis and prediction module comprises a machine learning constructing submodule for constructing a damage analysis and prediction model based on a convolutional neural network, a damage prediction submodule for predicting damage of the self-sensing concrete through the damage analysis and prediction model, and a visual display submodule for visualizing analysis and prediction results.

[0025] Further improvement lies in that a system management platform module is further included for remote configuration, monitoring, updating and user interaction.

[0026] The present application has the following beneficial effects:

[0027] (1) The present application optimizes the sensor network layout, pre-buries a high-density microelectrode grid in the self-sensing concrete, the microelectrodes can not only increase the signal collection points, but also effectively solve the signal attenuation problem, and cooperate with the electromagnetic suppression submodule, so that the resistance of the present application to local electromagnetic interference is enhanced, and even in a complex construction environment, the present application can still maintain good signal stability.

[0028] (2) The present application provides a high-precision and high-robustness damage monitoring scheme by combining temperature and humidity compensation models and machine learning algorithms. Through effective compensation of environmental factors, accurate analysis and processing of signals, and intelligent damage prediction using machine learning, the system can provide stable and accurate monitoring results in complex environments, significantly improving the application effect of self-sensing concrete in various engineering. Therefore, the present application not only has high engineering applicability, but also can greatly reduce maintenance cost, improve the efficiency and safety of structural health monitoring. BRIEF DESCRIPTION OF DRAWINGS

[0029] Figure 1 is a module flowchart of the present application.

[0030] Figure 2 is a damage type classification diagram of the present application.

[0031] Figure 3 is an analysis flowchart of the data analysis and prediction module of the present application.

[0032] Figure 4 is a structural diagram of the distributed microelectrode sub-module of the present application. DETAILED DESCRIPTION

[0033] In order to deepen the understanding of the present application, the present application will be further described in combination with examples, and the present embodiment is only used to explain the present application and does not constitute a limitation on the protection scope of the present application.

[0034] The performance of self-sensing concrete depends on the dispersion of conductive materials. Common conductive materials such as carbon fiber, carbon nanotube and steel fiber need to be uniformly distributed in the concrete matrix to ensure that the resistance characteristics of the concrete can accurately reflect the structural health status. However, in actual application, due to the non-uniform dispersion of conductive materials in the concrete matrix, the concrete resistance signal presents exponential decay with transmission distance. This decay phenomenon seriously affects the effective monitoring range and sensitivity of the monitoring system, especially in large-area or complex structure applications. The decay of resistance signal means that only reliable data can be obtained in the local area, while the area far from the sensor may not be able to obtain accurate health information due to signal decay, thereby reducing the overall efficiency of the monitoring system.

[0035] In practical engineering, concrete structures are often exposed to complex environments, which include a large number of electromagnetic interference sources, such as large machinery, wireless communication equipment, power facilities, etc. The work of these devices will produce electromagnetic waves, which will interfere with the weak resistance signal, causing the signal to be overwhelmed by noise. This problem is particularly prominent in field applications, especially in large projects in urban construction or transportation infrastructure, where the stability and accuracy of the signal are difficult to guarantee. Due to the relatively weak signal itself, combined with the influence of electromagnetic interference, the measured signal-to-noise ratio is generally lower than 5dB, which means that even if the signal comes from a real damage, it may be overwhelmed by noise, making it difficult to effectively extract and analyze the signal. Therefore, when applying self-sensing concrete for damage monitoring in complex environments, the signal processing capability of traditional methods is limited, and efficient damage detection and real-time monitoring cannot be achieved.

[0036] Environmental temperature and humidity fluctuations are an important factor affecting concrete resistance. With changes in temperature and humidity, the electrical conductivity inside the concrete will change significantly, which will affect the resistance signal. The resistance drift caused by temperature and humidity fluctuations can reach 300% to 500% of the damage signal, making the baseline stability worse and making it difficult to distinguish between resistance changes caused by environmental changes and actual damage signals. Traditional self-sensing concrete monitoring systems often rely on simple calibration or baseline adjustment methods when dealing with such environmental drift, and cannot effectively eliminate the influence of environmental changes on the resistance signal, thereby affecting the reliability and accuracy of the monitoring results.

[0037] In practical engineering, concrete structures are often simultaneously affected by multiple factors, such as load, creep, corrosion, freeze-thaw, etc. These factors can cause changes in the resistance signal of the concrete, and these changes can superimpose on each other, forming a complex signal aliasing phenomenon. Traditional monitoring methods are usually difficult to effectively decouple the influence of these multiple factors, making signal interpretation and analysis complex. For damage monitoring systems, signal aliasing makes it difficult to separate damage characteristic signals from environmental and non-damage factors, thereby reducing the system's ability to accurately identify and locate concrete damage.

[0038] According to the Figures 1-4 The embodiment proposes a damage monitoring auxiliary system based on self-sensing concrete, which includes a self-sensing concrete hardware module for real-time collection, processing and transmission of concrete internal and environmental related data through a high-density micro electrode grid, which includes:

[0039] Distributed microelectrode sub-module for high-density microelectrode grid arranged inside self-aware concrete, specifically, it is composed of high-density microelectrode grid embedded inside concrete (material is alkali-resistant carbon nanofiber / stainless steel microfilament), which is distributed in matrix form, and then real-time measurement of resistance / impedance between electrodes can provide key data for structural health monitoring.

[0040] Electromagnetic suppression sub-module for electromagnetic shielding and reducing electromagnetic interference, which is composed of shielding layer and filtering circuit, the shielding layer is copper-nickel alloy metal mesh wrapped around the electrode grid, and the electrode density is ≥4 / m 2 . The filtering circuit is integrated in the band-pass filter (frequency band 1 kHz-10 MHz) of the signal acquisition unit, which suppresses external power frequency electromagnetic interference (such as power grid, communication equipment) and concrete internal steel stray current noise, and ensures that the signal signal-to-noise ratio is >30dB.

[0041] Signal enhancement sub-module for enhancing high-density microelectrode grid signal (functionally amplifying weak electrical signal (μV-mV level) of microelectrode and eliminating environmental noise through phase-sensitive detection), which is composed of preamplifier and lock-in amplifier, the preamplifier is a low-noise instrument amplifier (gain 100-1000 times, input impedance >1GΩ). The lock-in amplifier applies a 10mV-1V alternating excitation signal (frequency 1-100kHz) to the electrode, and synchronously demodulates the output effective signal.

[0042] Temperature and humidity sensing sub-module for collecting environmental parameters inside self-aware concrete, which is a temperature and humidity integrated sensor (accuracy: ±0.5℃, ±2%RH), which is co-located with the microelectrode grid. The function is to collect real-time concrete internal temperature (-20-80℃) and humidity (0-100%RH) data, and provide input for environmental compensation.

[0043] Data sending sub-module for sending data through wireless communication technology, which uses a low-power microprocessor (ARM Cortex-M4) and has a wireless transmission unit (LoRaWAN / NB-IoT dual-mode module, transmission distance >1km). When working, the microprocessor aggregates electrode data, environmental data and device status (battery voltage, signal quality), compresses the data into a binary frame (CRC check), and then uploads it to the cloud gateway through the wireless network.

[0044] Data acquisition and processing module for collecting and preprocessing data collected in self-aware concrete hardware module, which includes:

[0045] Data processing sub-module for collecting and processing self-aware concrete hardware module data, the processing flow of the data processing sub-module is:

[0046] S1: The collected data is denoised using wavelet transform method, and then normalized, specifically, the collected data includes microelectrode grid resistance / impedance time series signal (the signal collected by the electrode reflects the change of the electrical conductivity of the concrete, which helps to detect the damage such as crack), humidity and temperature sensor original data (humidity and temperature are important factors affecting the performance of concrete, which is directly related to its structural health) and device status code (signal quality mark, battery voltage, used to evaluate the working state of the device and the reliability of signal acquisition), then the original signal collected is denoised by using wavelet transform method, and the processed data is standardized by normalization, the electrode signal is compressed to [0, 1], and the humidity and temperature retain physical units (℃, %RH). The numerical range of each feature is unified to avoid unnecessary deviation of data with different dimensions in subsequent analysis;

[0047] S2: The data processed by S1 is feature extracted to obtain the required feature data, the feature data which helps to evaluate the health state of concrete is extracted from the processed data, specifically, the data types are electrode spatial signal (the features are regional average resistance value, resistance gradient extreme value, local variance (reflecting crack)), electrode time series signal (the features are resistance change rate within 1h, frequency domain principal component energy (FFT extracts 0.1-10Hz frequency band)), humidity and temperature data (humidity and temperature average (10min window), humidity and temperature change slope) and device state (signal packet loss rate, battery voltage drop trend), further, the spatial features are calculated by Delaunay triangulation based on electrode coordinates, and the resistance statistics of the grid unit, and the time series features are calculated by sliding window (length 60s, step 10s) change rate and FFT spectrum;

[0048] S3: The extracted feature data is generated with corresponding time stamp (GPS / Beidou dual-mode time service (accuracy ±1ms)), and then is transmitted to the data storage submodule for storage.

[0049] The above regional average resistance value can reflect the overall resistance characteristics of the concrete, the resistance gradient extreme value can help to identify the existence and development of the crack, and the local variance reflects the characteristics of the local crack of the concrete. The above resistance change rate within 1h is the change rate of resistance with time, and the frequency domain principal component energy is the principal component energy of 0.1-10Hz frequency band extracted by FFT (fast Fourier transform), which helps to analyze the frequency characteristics of resistance. The above humidity and temperature average is the average change of humidity and temperature in a short time, and the humidity and temperature change slope is the speed of humidity and temperature change, which helps to analyze the environmental response characteristics of concrete. The above signal packet loss rate reflects the stability of data transmission, which helps to judge whether there is abnormal packet loss, and the battery voltage drop trend reflects the health state of the battery.

[0050] A data storage submodule for storing the processed data, which is divided into an edge cache unit and a central database unit, wherein the edge cache unit is a data hard disk group column, which cyclically covers 7 days of original data, and the central database unit is deployed in a cloud server for storing extracted time series feature data.

[0051] An environmental compensation correction module for establishing a temperature and humidity compensation model and correcting the processed data through the temperature and humidity compensation model, which includes:

[0052] A temperature and humidity compensation model establishment submodule for establishing a compensation model according to changes in environmental temperature and humidity, and the specific steps for establishing a compensation model according to changes in environmental temperature and humidity are:

[0053] SS1: Collect experimental data between temperature, humidity and resistance change, construct training data set, specifically, conduct accelerated experiment on standard concrete test block (same mix ratio) in climate simulation cabin, cover temperature (-20℃~60℃), humidity (20%~100%RH) full working condition, then deploy reference node in healthy structure (undamaged area) under natural temperature variation, collect resistance baseline data, corresponding, data set structure includes temperature, humidity, resistance change and concrete age;

[0054] SS2: Clean and standardize the obtained data, the cleaning rule is to remove data (outliers) whose resistance change exceeds ±3 times the standard deviation, and then use linear interpolation method for missing value interpolation;

[0055] SS3: Use support vector regression algorithm to establish the nonlinear mapping relationship between resistance change and temperature, humidity, use training data set to train the compensation model, wherein the input data is temperature, humidity, age, and the output data is predicted resistance change;

[0056] SS4: Use ten-fold cross-validation method to evaluate the model, and complete the establishment of the compensation model after evaluation, specifically, divide the training data set into 10 subsets, 9 training + 1 validation, cycle 10 times, evaluation index is mean absolute error MAE≤0.05Ω, coefficient of determination R 2 ≥0.95, continuously monitor the healthy structure for 30 days under the field conditions, and the resistance fluctuation rate after compensation is ≤2% (verify the generalization ability of the model).

[0057] A data correction submodule for correcting data through the compensation model, which inputs preprocessed resistance real-time value, current temperature and humidity and concrete age, and outputs corrected resistance value through the compensation model.

[0058] Further, in the present application, the environmental compensation correction module compensates the accuracy as follows: temperature interference suppression rate ≥ 90% (error < 0.03Ω within the range of -20℃ to 60℃); humidity interference suppression rate ≥ 85% (error < 0.05Ω within the range of 20% to 100% RH). The variance of the resistance of the healthy reference node after compensation is calculated every month, and if it is > 150% of the initial value for 3 times in succession, the model retraining is triggered, the data under the new environmental conditions are automatically collected, and the model parameters are dynamically updated by using the online SVR (Online SVR) algorithm.

[0059] The above relates to the age of concrete. During the concrete pouring process, the construction personnel will record the time when the concrete pouring starts, which is the starting point of the age of the concrete. When detection or analysis is performed, the difference between the current time and the pouring time is used to calculate the age.

[0060] The data decoupling module is used to decouple the influence of multiple factors in the corrected data, and the role is to separate the multiple influence factors (load, creep, corrosion, etc.) mixed in the resistance data after environmental compensation, and extract the pure damage characteristic signal, which includes:

[0061] The decoupling processing submodule is used to separate the different influence factors mixed in the data by the variational mode decomposition method. Specifically, the input data is the resistance time series signal after environmental compensation, then the VMD parameters are determined, and the decomposition is performed. The parameters include the decomposition mode number K, that is, how many intrinsic mode functions the signal is decomposed into; the balance parameter is used to control the accuracy and complexity of signal decomposition; and the tolerance and error tolerance level parameters control the calculation progress in the decomposition process.

[0062] Then K intrinsic mode functions (IMF) are output, each intrinsic mode function represents a part of the frequency component or time domain characteristics of the signal. Some IMFs may contain interference signals (such as corrosion, load, etc.) unrelated to environmental changes, and others may be related to damage characteristics.

[0063] The data fusion submodule is used to fuse the decoupled data, which inputs the K intrinsic mode functions (IMF) obtained by decomposition, selects the intrinsic mode functions related to damage, which usually exhibit IMFs with frequency ranges and time series fluctuations consistent with damage characteristics, such as resistance changes caused by concrete cracks or corrosion. This function can be one or more, and the remaining is regarded as an interference component, and then the signal is reconstructed, that is, the selected IMF is time-frequency energy weighted and fused to obtain the final corrected damage signal. Through the reconstructed signal, the interference from factors such as load, creep or corrosion can be eliminated, and the pure damage characteristic signal can be extracted.

[0064] The calculation formula of the damage characteristic signal x r is as follows:

[0065]

[0066] where u i is the selected damage-related IMF, w i is the corresponding weighting coefficient, M is the number of damage-related IMFs, and i=1 means starting from the first IMF. The reconstructed damage signal can be used for subsequent damage analysis and structural health monitoring.

[0067] The data analysis and prediction module is configured to analyze and predict the decoupled data using a convolutional neural network to realize self-sensing concrete damage monitoring, and includes:

[0068] The machine learning construction submodule is configured to construct a damage analysis and prediction model based on a convolutional neural network, and includes the following steps:

[0069] A1: Construct a data set, and the source of the data set is consistent with the data source mode of the compensation model established based on the environmental temperature and humidity changes;

[0070] A2: Convert the distributed electrode signals of the distributed microelectrode submodule into a two-dimensional matrix to form an "electrode signal image", and mark it, i.e., each piece of data should correspond to a damage state label;

[0071] A3: Construct a damage analysis and prediction model based on a convolutional neural network, and perform model training, wherein an Adam optimizer is used for model training.

[0072] The damage prediction submodule is configured to predict the damage of self-sensing concrete through the damage analysis and prediction model, and the input receives the damage signal output by the decoupling module, analyzes it through the damage analysis and prediction model, determines the damage type (no damage, crack, corrosion, and freeze-thaw) according to the maximum probability, and then determines the damage degree according to the rounding (1 / 2 / 3 levels, with level 3 being the maximum), i.e., as shown in Figure 2 .

[0073] The visualization display submodule is configured to visualize the analysis and prediction results, and the output forms are a Web interface (B / S architecture) and a mobile APP (Android / iOS).

[0074] The system management platform module is further included for remote configuration, monitoring, updating, and user interaction.

[0075] With the traditional sensor system as a reference, the system is compared, the comparison conditions are to test the model accuracy in a salt freeze cycle + electrochemical corrosion + fatigue load coupling environment, and then deploy in a bridge maintenance path or a tunnel lining section to compare the traditional sensor data, and the results are shown in Table 1 as follows:

[0076] Object Conventional sensor system The present system Signal transmission stability > 10 cm severe attenuation < 20 cm attenuation < 5% Environmental drift proportion 300％～500％ ≤20％ Damage signal-to-noise ratio < 5 dB > 15 dB Multi-factor identification accuracy Unable to decouple > 85% (four types of factors) Crack positioning accuracy ± 50 cm ± 10 cm

[0077] Table I

[0078] As shown in Table I above, the system significantly outperforms the traditional sensor system in multiple key indicators. In particular, in terms of signal transmission stability, environmental drift proportion, damage signal-to-noise ratio, multi-factor recognition accuracy, and crack positioning accuracy, the system shows obvious advantages. These performance improvements enable the self-sensing concrete system to provide more reliable and accurate monitoring results in salt freezing cycles, electrochemical corrosion, and fatigue load coupling environments, greatly improving the efficiency and accuracy of structural health monitoring.

[0079] The above shows and describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above examples, and the above examples and descriptions in the specification are only to illustrate the principles of the present application. Without departing from the framework and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A damage monitoring auxiliary system based on self-sensing concrete, characterized in that: The system includes a self-sensing concrete hardware module for real-time collection, processing, and transmission of data related to the interior of the concrete and its environment via a high-density microelectrode grid. The self-sensing concrete hardware module includes a distributed microelectrode sub-module for setting the high-density microelectrode grid inside the self-sensing concrete, an electromagnetic suppression sub-module for electromagnetic shielding and reducing electromagnetic interference, a signal enhancement sub-module for enhancing the signal of the high-density microelectrode grid, a temperature and humidity sensing sub-module for collecting environmental parameters inside the self-sensing concrete, and a data transmission sub-module for transmitting data via wireless communication technology. The data acquisition and processing module is used to acquire and preprocess the data collected within the self-sensing concrete hardware module. The environmental compensation and correction module is used to establish a temperature and humidity compensation model and correct the processed data using the temperature and humidity compensation model. The data decoupling module is used to decouple and correct the influence of multiple factors in the data. The data analysis and prediction module is used to analyze and predict the decoupled data using a convolutional neural network to achieve damage monitoring of self-sensing concrete.

2. The damage monitoring auxiliary system based on self-sensing concrete according to claim 1, characterized in that: The data acquisition and processing module includes a data processing submodule for collecting and processing data from the self-sensing concrete hardware module and a data storage submodule for storing the processed data.

3. The damage monitoring auxiliary system based on self-sensing concrete according to claim 2, characterized in that: The processing flow of the data processing submodule is as follows: S1; The collected data is denoised using wavelet transform and then normalized. S2: Extract features from the data processed by S1 to obtain the required feature data; S3: Generate corresponding timestamps for the extracted feature data, and then send them to the data storage submodule for storage.

4. The damage monitoring auxiliary system based on self-sensing concrete according to claim 1, characterized in that: The environmental compensation and correction module includes a temperature and humidity compensation model establishment submodule for establishing a compensation model based on changes in environmental temperature and humidity, and a data correction submodule for correcting the data through the compensation model.

5. The damage monitoring auxiliary system based on self-sensing concrete according to claim 4, characterized in that: The specific steps for establishing a compensation model based on changes in environmental temperature and humidity are as follows: SS1: Collect experimental data on the relationship between temperature, humidity, and resistance changes to construct a training dataset; SS2: Clean and standardize the acquired data; SS3: Use the support vector regression algorithm to establish a nonlinear mapping relationship between resistance change and temperature and humidity, and use the training dataset to train the compensation model; SS4: Use the ten-fold cross-validation method to evaluate the model. Once the evaluation is successful, the compensation model is established.

6. The damage monitoring auxiliary system based on self-sensing concrete according to claim 1, characterized in that: The data decoupling module includes a decoupling processing submodule for separating different influencing factors mixed in the data using variational mode decomposition and a data fusion submodule for fusing the decoupled data.

7. The damage monitoring auxiliary system based on self-sensing concrete according to claim 1, characterized in that: The data analysis and prediction module includes a machine learning construction submodule for building a damage analysis and prediction model based on a convolutional neural network, a damage prediction submodule for predicting damage to self-sensing concrete using the damage analysis and prediction model, and a visualization display submodule for visualizing the analysis and prediction results.

8. The damage monitoring auxiliary system based on self-sensing concrete according to claim 1, characterized in that: It also includes a system management platform module for remote configuration, monitoring, updates, and user interaction.

Images