Method for measuring macro and micro damage characteristics of early age concrete under high temperature tunnel blasting load

Abstract

The application provides a measurement method for macroscopic and microscopic damage characteristics of early-age concrete under high-temperature tunnel blasting load, relates to the technical field of concrete macroscopic and microscopic damage measurement, and solves the technical problem of early-age concrete damage detection in a high-temperature tunnel blasting environment through multi-scale data feature fusion. Firstly, a cross-scale data synchronization mechanism of a high-temperature resistant sensor network and a microfocus CT is constructed to capture the cooperative damage characteristics of temperature gradient and blasting impact. Secondly, a temperature correction factor and a dynamic damage threshold model are introduced to quantize the coupling effect of high temperature and hydration reaction and improve the criterion adaptability under complex working conditions. Finally, based on the multi-modal feature fusion technology of deep learning, the correlation analysis of macroscopic and microscopic data and the adaptive classification of damage grades are realized, and the detection precision and anti-interference ability are improved. The applicability in a high-temperature scene is improved, and reliable technical support is provided for the whole life cycle health monitoring of concrete structures.

Description

Technical Field

[0001] This invention relates to the field of macroscopic and microscopic damage measurement technology for concrete, specifically a method for measuring the macroscopic and microscopic damage characteristics of early-age concrete under high-temperature tunnel blasting loads. Background Technology

[0002] In special geological environments such as plateaus and deep-buried tunnels, the coupled effect of high ground temperatures (above 28℃) and frequent blasting operations significantly exacerbates the damage and deterioration of early-age concrete, leading to macroscopic and microscopic structural damage such as microcrack propagation and increased porosity, seriously threatening the safety and durability of tunnel engineering. Traditional concrete damage detection methods (such as ultrasonic testing and strain gauges) are mostly designed for normal temperature or single load conditions, making it difficult to capture the synergistic effect of high temperatures and dynamic loads. Furthermore, they rely on single-scale data (macroscopic or microscopic), resulting in insufficient accuracy and reliability of damage criteria. Especially in the early-age stage, when concrete hydration is active, traditional fixed-threshold models cannot adapt to the dynamic evolution of material properties, easily leading to false positives and false negatives. While existing machine learning-based damage identification methods partially solve the data analysis problem, they lack physical model-driven approaches, limiting their generalization ability under complex conditions.

[0003] The existing technology, disclosed in CN106649925A, presents a method for analyzing concrete fatigue damage based on monitoring complex dynamic stresses at both micro and macro scales. The method includes the following steps: determining the micro-macro stress relationship between uniaxial normal stress and uniaxial shear stress in typical concrete structures; measuring the macro-stress values ​​of concrete using an optimized array of spatial stress sensors; deploying the spatial stress sensor array in the component under test; equating the monitored complex dynamic stresses of concrete to triaxial stresses in the principal stress space; determining the key principal stresses controlling the fatigue damage behavior of the material; using rainflow counting to equate the time histories of the key principal stresses to multi-level amplitude stresses; and equating the multi-level amplitude stresses to single-amplitude stresses based on the maximum stress; and analyzing and evaluating the fatigue state of the concrete. While this method can monitor complex stresses in concrete, it does not consider the coupling effect of high ground temperature and blasting loads, cannot capture the nonlinear influence of temperature on damage evolution, and relies solely on the average stress to simplify the macro-micro correlation, lacking a cross-scale data synchronous acquisition and dynamic fusion mechanism, resulting in insufficient accuracy in fatigue assessment under complex working conditions.

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

[0005] The purpose of this invention is to provide a method for measuring the macroscopic and microscopic damage characteristics of early-age concrete under high-temperature tunnel blasting loads, so as to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A method for measuring the macroscopic and microscopic damage characteristics of early-age concrete under high-temperature tunnel blasting loads, the specific steps of which include:

[0008] S1: Concrete specimens were constructed and divided into two groups. One group underwent a split Hopkinson bar test to collect the corresponding mechanical data. The other group was subjected to a burst load, and macroscopic and microscopic data and temperature field distribution of the concrete specimens under the burst load were collected.

[0009] S2: Calculate the temperature correction factor based on the temperature field distribution of the concrete specimen, and calculate the critical damage threshold using the temperature correction factor and mechanical data;

[0010] S3: Based on deep learning algorithms, features are extracted from the macro and micro data, temperature correction factor, and critical damage threshold of concrete specimens. After multimodal feature fusion, the corresponding damage level is output by combining the critical damage threshold.

[0011] Preferably, in step S1, a high-temperature resistant sensor network and microfocus CT scanning technology are used to acquire macroscopic and microscopic data and temperature field distribution of the concrete specimen.

[0012] The high-temperature resistant sensor network consists of several sets of fiber Bragg grating sensors, and the arrangement satisfies the following conditions:

[0013] The fiber optic grating sensor is embedded at intervals along the axial, circumferential, and radial directions of the concrete specimen, with an embedding depth of 1 / 5 to 1 / 2 of the thickness of the concrete specimen.

[0014] The sampling rate of the fiber Bragg grating sensor is not less than 10 kHz, and the operating temperature range is 20℃~100℃.

[0015] Preferably, in step S2, the temperature correction factor is calculated as follows:

[0016]

[0017] In the formula Indicates the temperature correction factor. Indicates the temperature coefficient. , These represent the internal temperature and reference temperature of the concrete specimen, respectively. , These represent the concrete age and the reference age, respectively. This represents the coupling weight.

[0018] Preferably, the method for determining the range of values ​​for the coupling weights is as follows:

[0019] When the water-cement ratio of the concrete specimen is less than or equal to the water-cement ratio threshold ;

[0020] When the water-cement ratio of the concrete specimen is greater than the water-cement ratio threshold... .

[0021] Preferably, the critical damage threshold is calculated as follows:

[0022]

[0023] In the formula Indicates the critical damage threshold. These represent the measured maximum stress and theoretical tensile strength in the mechanical data, respectively. This indicates the maximum allowable value of the temperature correction factor. .

[0024] Preferably, the macroscopic and microscopic data of the concrete include macroscopic data and microscopic data;

[0025] In step S3, the deep learning network first extracts features from the macroscopic and microscopic data respectively, generating corresponding macroscopic and microscopic feature vectors. Then, it performs multimodal feature fusion based on the macroscopic and microscopic feature vectors, the expression of which is:

[0026]

[0027] In the formula Represents the fused feature vector. Represents macroscopic eigenvectors. Represents a microscopic vector. This indicates the fusion weight.

[0028] Preferably, the fusion weight is dynamically calculated using a temperature correction factor and a critical damage threshold, and the calculation method is as follows:

[0029]

[0030] In the formula This indicates the preset adjustment coefficient.

[0031] Preferably, the final damage is calculated based on the fused feature vector and the critical damage threshold, and the calculation method is as follows:

[0032]

[0033] In the formula Indicates the final damage. Indicates the volatility coefficient. , express The norm of .

[0034] Preferably, the corresponding damage level is output based on the final damage and the critical damage threshold, specifically as follows:

[0035] satisfy At that time, it was considered that the concrete specimens were undamaged;

[0036] satisfy At that time, the concrete specimen was considered to have suffered only minor damage;

[0037] satisfy At that time, it was considered that the concrete specimen was severely damaged;

[0038] in , Both represent scaling factors, and .

[0039] Compared with the prior art, the beneficial effects of the present invention are:

[0040] This invention systematically solves the technical challenge of early-age concrete damage detection in high-temperature tunnel blasting environments by employing multi-scale collaborative data acquisition, temperature-load coupled modeling, and intelligent feature fusion. First, a cross-scale data synchronization mechanism between a high-temperature resistant sensor network and micro-focus CT is constructed, overcoming the limitations of traditional single-detection methods and accurately capturing the collaborative damage characteristics of temperature gradients and blasting impacts. Second, an innovative temperature correction factor and dynamic damage threshold model are introduced to quantify the coupling effect of high temperature and hydration reaction, significantly improving the adaptability of criteria under complex working conditions. Finally, based on deep learning-based multi-modal feature fusion technology, the correlation analysis of macro and micro data and adaptive classification of damage levels are achieved, greatly improving detection accuracy and anti-interference capability. This method can be widely applied in high-temperature scenarios such as deeply buried railway tunnels and underground energy storage facilities, providing reliable technical support for the full life-cycle health monitoring of concrete structures and assisting in safe operation and maintenance and risk early warning of engineering projects. Attached Figure Description

[0041] Figure 1 This is a schematic diagram of the overall method flow of the present invention;

[0042] Figure 2 A schematic diagram of the data simulation for the temperature correction factor;

[0043] Figure 3 This is a schematic diagram of data simulation for the critical damage threshold;

[0044] Figure 4 This is a schematic diagram of the final damage data simulation. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0046] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0047] Example:

[0048] Please see Figure 1 The present invention provides a technical solution:

[0049] A method for measuring the macroscopic and microscopic damage characteristics of early-age concrete under high-temperature tunnel blasting loads, the specific steps of which include:

[0050] S1: Concrete specimens are constructed based on tunnel building materials. The proportions of various components in the concrete within the tunnel building materials are collected, and concrete specimens with identical mix proportions are constructed. These specimens are then divided into two groups. One group undergoes a split Hopkinson bar test to collect corresponding mechanical data, such as stress data, elastic modulus, and yield strength. The other group is subjected to a blast load, and macroscopic and microscopic data, as well as temperature field distribution, are collected under the blast load. Considering the needs of different tests, the concrete specimens for the split Hopkinson bar test can be constructed using standard dynamic mechanical specimens, such as those with a diameter of 75mm and a height of 37.5mm, with a sensor embedment depth ranging from 7.5mm to 18.75mm. The concrete specimens used to apply the blast load can be cubes with a side length of 150mm or cylinders with a diameter of 150mm and a height of 75mm, facilitating macroscopic and microscopic damage observation.

[0051] In this embodiment, to meet the requirements of high ground temperature, the test conditions for the split Hopkinson bar test can be set as follows:

[0052] The temperature gradient is set to three groups: 30℃, 50℃, and 70℃, with a temperature control accuracy of ±1℃.

[0053] The pressure bar is made of high-strength alloy steel with an elastic modulus ≥200 GPa to ensure distortion-free stress wave propagation; the pressure bar diameter is 75 mm, consistent with the specimen diameter, to avoid impedance mismatch; the incident / transmission bar length is ≥2 m, thus ensuring stress wave separation and data acquisition time window;

[0054] The bullet velocity was set to 20±2 m / s, corresponding to a strain rate of 300±50 s⁻¹. -1 The typical strain rate range of simulated blast load;

[0055] The waveform shaper uses a copper sheet with a thickness of 0.8 mm to achieve a loading pulse rise time of 150 μs.

[0056] With this setup, the split Hopkinson bar test can cover the typical temperature range of high geothermal tunnels, better support the modeling of temperature correction factors, and this dynamic age setting method can avoid brittle fracture of concrete at early age, ensure data stability, and the age setting can also match the hydration process at early age, thus reflecting the age dependence of the critical damage threshold.

[0057] High-temperature resistant sensor networks and microfocus CT scanning technology were used to acquire macroscopic and microscopic data and temperature field distribution of concrete specimens.

[0058] The high-temperature resistant sensor network consists of several sets of fiber Bragg grating sensors, and the arrangement satisfies the following conditions:

[0059] Fiber grating sensors are embedded at intervals along the axial, circumferential, and radial directions of the concrete specimen, with an embedding depth of 1 / 5 to 1 / 2 of the thickness of the concrete specimen.

[0060] The sampling rate of the fiber Bragg grating sensor is no less than 10 kHz, and the operating temperature range is 20℃~100℃.

[0061] By employing a high-temperature resistant sensor network and micro-focus CT scanning technology, spatiotemporal alignment of macroscopic and microscopic data can be achieved, overcoming the scale limitations of single detection methods. The joint acquisition of temperature field distribution and strain field data reveals the coupling mechanism between temperature gradient and load impact.

[0062] In this step, by simulating the real tunnel environment through the design of experimental parameters (temperature, load, age), the engineering adaptability of the technology can be improved. Moreover, the grouped tests can separate mechanical performance testing from environmental effect research, ensuring the relevance and comparability of data collection. This provides cross-scale, multimodal input for subsequent modeling and classification, and provides a systematic analysis of complex damage evolution.

[0063] S2: Calculate the temperature correction factor based on the temperature field distribution of the concrete specimen, and use the temperature correction factor and mechanical data to calculate the critical damage threshold.

[0064] The temperature correction factor is calculated as follows:

[0065]

[0066] In the formula Indicates the temperature correction factor. Indicates the temperature coefficient. , These represent the internal temperature and reference temperature of the concrete specimen, respectively. , These represent the concrete age and the reference age, respectively. This represents the coupling weight. The internal temperature of the concrete specimen can be obtained from the temperature field distribution data. For example, the mean value of the temperature field distribution data inside the concrete specimen can be calculated. The reference temperature can be set to room temperature (25℃), and the reference age can be set to the early age baseline, which is 3 days. The temperature coefficient can be determined according to the type of concrete or by fitting it to the dynamic compression test. It is usually set to around 0.015.

[0067] The method for determining the range of coupling weight values ​​is as follows:

[0068] When the water-cement ratio of the concrete specimen is less than or equal to the water-cement ratio threshold ;

[0069] When the water-cement ratio of the concrete specimen is greater than the water-cement ratio threshold... .

[0070] As can be seen from the calculation formula of the temperature correction factor, its main function is to quantify the coupled influence of high temperature and age on the dynamic elastic modulus of concrete. It is divided into a basic term, a temperature linear correction term, and a temperature-age coupling term. Specifically, 1 represents the basic term, providing a basic value for the temperature correction factor; This represents the temperature linear correction term, used to quantify the linear effect of temperature rise on the dynamic elastic modulus of concrete, reflecting the stiffness reduction of the material under the thermal expansion effect. This represents the temperature-age coupling term, used to characterize the synergistic effect of high temperature and early-age hydration reactions, capturing the nonlinear effect of temperature-accelerated microcrack propagation. The water-cement ratio threshold can be set to 0.45, the dividing line between ordinary concrete and high-strength concrete. Concrete with a low water-cement ratio has high density and a weak temperature coupling effect, resulting in a lower corresponding coupling weight range. Concrete with a high water-cement ratio has more porosity and a significant temperature coupling effect, resulting in a higher corresponding second-generation coupling weight range.

[0071] This multi-parameter coupling can correct the elastic response of the model under high geothermal conditions, quantify the synergistic effect of high temperature and early-age hydration reaction on the dynamic elastic modulus of concrete, avoid the limitations of traditional single temperature correction, and thus provide a theoretical basis for the long-term service performance evaluation of high-temperature tunnel concrete and guide the optimization of curing cycle.

[0072] The critical damage threshold is calculated as follows:

[0073]

[0074] In the formula Indicates the critical damage threshold. These represent the measured maximum stress and theoretical tensile strength, respectively, in the mechanical data. The theoretical tensile strength can be calculated by inverting the porosity obtained from CT scans. Generally, for every 1% increase in porosity, the theoretical tensile strength decreases by 2% to 5%. This indicates the maximum allowable value of the temperature correction factor. The calculation formula incorporates normalization; specifically, under high-temperature conditions, the temperature correction factor... Approaching This indicates that the material has completely lost its resistance to damage, that is... However, under normal temperature conditions, the temperature correction factor When the value approaches 1, the material exhibits the strongest damage resistance, and the critical damage threshold reaches its theoretical maximum value. .

[0075] As can be seen from the calculation formula for the critical damage threshold, its function is to determine the critical damage point of concrete under high temperature-load coupling, and it is also divided into different items. Specifically, This represents the strength ratio, which is the ratio of the measured maximum stress to the theoretical tensile strength, reflecting the degree of reduction in the material's actual load-bearing capacity. This represents the temperature decay term, which is used to quantify the weakening effect of the temperature correction factor on the damage threshold.

[0076] Therefore, by establishing a critical damage threshold driven by both temperature and load, the problem of misjudgment caused by fixed traditional thresholds can be solved. It can also be automatically adjusted according to environmental changes in tunnel engineering, thereby enabling timely intervention under high-risk conditions and reducing construction risks.

[0077] In this step, by establishing a critical damage threshold driven by both temperature and load factors to replace the traditional fixed threshold, the reliability of the criterion under complex working conditions can be improved, providing a quantitative basis for the service life assessment and maintenance decision-making of tunnel concrete.

[0078] S3: Based on deep learning algorithms, features are extracted from the macro and micro data, temperature correction factor, and critical damage threshold of concrete specimens. After multimodal feature fusion, the corresponding damage level is output by combining the critical damage threshold.

[0079] Macroscopic and microscopic data for concrete include both macroscopic and microscopic data. Specifically, macroscopic data can include parameters such as dynamic strain field and temperature gradient, while microscopic data can include parameters such as porosity and crack fractal dimension. The specific data can be determined based on expert experience and research direction.

[0080] In step S3, the deep learning network first extracts features from the macroscopic and microscopic data respectively, generating corresponding macroscopic and microscopic feature vectors. Then, it performs multimodal feature fusion based on the macroscopic and microscopic feature vectors, the expression of which is:

[0081]

[0082] In the formula Represents the fused feature vector. Represents macroscopic eigenvectors. Represents a microscopic vector. The extracted macroscopic feature vectors should include dynamic strain field characteristics: for example, strain distribution statistics reflected by parameters such as mean and variance to characterize the overall deformation response of concrete under blasting load, or the strain gradient change trend extracted through time series analysis; temperature field characteristics: for example, temperature gradient distribution along the axial and circumferential directions of the specimen, or the change in thermal conductivity based on temperature field data inversion. The extracted mesoscopic feature vectors should include pore structure characteristics: for example, the proportion of pore volume in different regions and its spatial distribution, or morphological parameters such as pore equivalent diameter, aspect ratio, and connectivity, to characterize the influence of microstructure on mechanical properties; crack evolution characteristics: for example, using crack fractal dimension to quantify the complexity and disorder of crack propagation paths, or using the number of cracks per unit area and the direction angle of the main crack to characterize the degree of damage localization. It is understandable that, regardless of whether it is a macroscopic or mesoscopic feature vector, its data size should be proportional to the degree of damage. For example, larger parameters such as mean and variance in the dynamic strain field characteristics indicate more severe and uneven deformation of concrete under blasting loads, and a greater likelihood of damage. Similarly, larger morphological parameters such as pore equivalent diameter, aspect ratio, and connectivity in the mesoscopic feature vectors, or larger crack fractal dimension, reflect more severe pore cracks and a higher degree of damage in the concrete specimen. The same applies to other parameters. Specific feature extraction can be determined based on research needs and expert experience, and is not limited here.

[0083] By leveraging deep learning networks and dynamically balancing the contributions of macroscopic mechanical responses (strain field, temperature gradient) and microstructural features (porosity, crack fractal dimension) through weighted analysis, cross-scale data can be integrated to highlight the hidden damage characteristics of microcrack propagation at high temperatures. This overcomes the blind spots of single-scale detection, enables the correlation analysis of macroscopic and microscopic damage, and suppresses noise caused by sensor drift and CT imaging errors through data fusion, thereby improving detection accuracy and increasing the overall robustness of the system.

[0084] The fusion weight is dynamically calculated based on the temperature correction factor and the critical damage threshold, and the calculation method is as follows:

[0085]

[0086] In the formula This indicates the preset adjustment coefficient.

[0087] As can be seen from the calculation formula of the fusion weight, when the temperature correction factor increases (the high temperature effect is significant), the weight of macroscopic features is reduced and the decision-making dominance of microscopic features is strengthened. Conversely, the weight of microscopic features is reduced and the decision-making dominance of macroscopic features is strengthened. In this way, the main cause of damage (such as temperature-dominated or load-dominated) can be located through weight changes, supporting targeted maintenance strategies.

[0088] The final damage is calculated based on the fused feature vector and the critical damage threshold, using the following method:

[0089]

[0090] In the formula Indicates the final damage. Indicates the volatility coefficient. , express The norm of the function can quantify the degree of joint anomaly in multimodal data and amplify potential damage signals.

[0091] The fluctuation coefficient can be determined according to the type of concrete: 0.1 for fiber-reinforced concrete, 0.2 for ordinary concrete, and 0.3 for high-strength concrete.

[0092] The corresponding damage level is output based on the final damage and the critical damage threshold, specifically as follows:

[0093] satisfy At that time, it was considered that the concrete specimens were undamaged;

[0094] satisfy At that time, the concrete specimen was considered to have suffered only minor damage;

[0095] satisfy At that time, it was considered that the concrete specimen was severely damaged;

[0096] in , Both represent scaling factors, and Generally speaking, , The specific range of values ​​can be determined based on project requirements or expert experience.

[0097] In this embodiment, during simulation, the reference temperature is set to 25℃, the reference age is set to 3 days, the temperature coefficient is set to 0.015, and the coupling weight is set according to the water-cement ratio in segments: 0.3 when the water-cement ratio is less than or equal to the threshold, and 0.5 when it is greater than the threshold. The maximum allowable value of the temperature correction factor is also specified. Let's take a uniform value of 1.8. Take 0.8, With a value of 1.2, and other parameters fluctuating randomly within the specified range, measurements and analyses were performed on 18 groups of concrete specimens. The specific measurement data are shown in the table below:

[0098]

[0099] Reference Figures 2-4 As can be seen from the data in the table above, when the temperature rises, the high temperature accelerates the hydration reaction and the propagation of microcracks, which weakens the tensile strength and load-bearing capacity of the material, thus significantly reducing the normalized critical damage threshold. The extended age also leads to material deterioration and a higher risk of damage. Therefore, in practical applications, early-age (≤3 days) concrete needs to be closely monitored to avoid the superposition of hydration heat effects by explosive loads. High water-cement ratio concrete has higher porosity, and the temperature conduction and hydration reaction are more active, which exacerbates the temperature-time coupling effect and thus accelerates microstructural damage.

[0100] In this step, implicit features of macro and micro data are extracted using deep learning algorithms to construct a cross-scale correlation model. This can solve the problem of information partiality from a single data source. Moreover, the dynamic fusion weight mechanism can achieve environmental adaptation and strengthen the contribution of key features under different dominant scenarios. By combining the critical damage threshold and the fusion feature strength, a gradient damage level is defined, thereby quantifying the continuous change in the degree of damage. This not only provides a basis for prioritizing tunnel maintenance but also transforms complex damage data into intuitive engineering language, reducing the threshold for manual interpretation and improving detection efficiency.

[0101] In summary, this invention systematically solves the technical challenges of early-age concrete damage detection in high-temperature tunnel blasting environments through multi-scale collaborative data acquisition, temperature-load coupled modeling, and intelligent feature fusion. First, a cross-scale data synchronization mechanism between a high-temperature resistant sensor network and micro-focus CT is constructed, overcoming the limitations of traditional single detection methods and accurately capturing the collaborative damage characteristics of temperature gradients and blasting impacts. Second, an innovative temperature correction factor and dynamic damage threshold model are introduced to quantify the coupling effect of high temperature and hydration reaction, significantly improving the adaptability of criteria under complex working conditions. Finally, based on deep learning-based multi-modal feature fusion technology, the correlation analysis of macro and micro data and adaptive classification of damage levels are achieved, greatly improving detection accuracy and anti-interference capabilities. This method can be widely applied in high-temperature scenarios such as deeply buried railway tunnels and underground energy storage facilities, providing reliable technical support for the full life-cycle health monitoring of concrete structures and assisting in safe operation and maintenance and risk early warning of engineering projects.

[0102] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0103] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0104] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0105] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for measuring the macroscopic and microscopic damage characteristics of early-age concrete under high-temperature tunnel blasting loads, characterized in that, The specific steps include: S1: Concrete specimens were constructed based on tunnel building materials. The concrete specimens were divided into two groups. One group underwent a split Hopkinson bar test to collect the corresponding mechanical data. The other group was subjected to blast load, and macroscopic and microscopic data and temperature field distribution of the concrete specimens under the blast load were collected. In step S1, a high-temperature resistant sensor network and micro-focus CT scanning technology are used to collect macroscopic and microscopic data and temperature field distribution of the concrete specimen. The high-temperature resistant sensor network consists of several sets of fiber Bragg grating sensors, and the arrangement satisfies the following conditions: The fiber optic grating sensor is embedded at intervals along the axial, circumferential, and radial directions of the concrete specimen, with an embedding depth of 1 / 5 to 1 / 2 of the thickness of the concrete specimen. The sampling rate of the fiber Bragg grating sensor is not less than 10KHz, and the operating temperature range is 20℃~100℃; S2: Calculate the temperature correction factor based on the temperature field distribution of the concrete specimen, and calculate the critical damage threshold using the temperature correction factor and mechanical data; In step S2, the temperature correction factor is calculated as follows: In the formula Indicates the temperature correction factor. Indicates the temperature coefficient. , These represent the internal temperature and reference temperature of the concrete specimen, respectively. , These represent the concrete age and the reference age, respectively. Indicates coupling weights; The critical damage threshold is calculated as follows: In the formula Indicates the critical damage threshold. These represent the measured maximum stress and theoretical tensile strength in the mechanical data, respectively. This indicates the maximum allowable value of the temperature correction factor. ; S3: Based on deep learning algorithms, features are extracted from the macro and micro data, temperature correction factor, and critical damage threshold of concrete specimens. After multimodal feature fusion, the corresponding damage level is output by combining the critical damage threshold.

2. The method for measuring the macroscopic and microscopic damage characteristics of early-age concrete under high-temperature tunnel blasting load as described in claim 1, characterized in that: The method for determining the range of values ​​for the coupling weights is as follows: When the water-cement ratio of the concrete specimen is less than or equal to the water-cement ratio threshold ; When the water-cement ratio of the concrete specimen is greater than the water-cement ratio threshold... .

3. The method for measuring the macroscopic and microscopic damage characteristics of early-age concrete under high-temperature tunnel blasting load as described in claim 1, characterized in that: The macroscopic and microscopic data of the concrete include macroscopic data and microscopic data; In step S3, the deep learning network first extracts features from the macroscopic and microscopic data respectively, generating corresponding macroscopic and microscopic feature vectors. Then, it performs multimodal feature fusion based on the macroscopic and microscopic feature vectors, the expression of which is: In the formula Represents the fused feature vector. Represents macroscopic eigenvectors. Represents a microscopic vector. This indicates the fusion weight.

4. The method for measuring the macroscopic and microscopic damage characteristics of early-age concrete under high-temperature tunnel blasting load as described in claim 3, characterized in that: The fusion weight is dynamically calculated based on the temperature correction factor and the critical damage threshold, and the calculation method is as follows: In the formula This indicates the preset adjustment coefficient.

5. The method for measuring the macroscopic and microscopic damage characteristics of early-age concrete under high-temperature tunnel blasting load as described in claim 3, characterized in that: The final damage is calculated based on the fused feature vector and the critical damage threshold, using the following method: In the formula Indicates the final damage. Indicates the volatility coefficient. , express The norm of .

6. The method for measuring the macroscopic and microscopic damage characteristics of early-age concrete under high-temperature tunnel blasting load as described in claim 5, characterized in that: The corresponding damage level is output based on the final damage and the critical damage threshold, specifically as follows: satisfy At that time, it was considered that the concrete specimens were undamaged; satisfy At that time, the concrete specimen was considered to have suffered only minor damage; satisfy At that time, it was considered that the concrete specimen was severely damaged; in , Both represent scaling factors, and .

Images