Concrete service performance evaluation method and device, electronic equipment and storage medium

Abstract

The invention relates to a concrete service performance evaluation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring performance data of a concrete sample in a service process; determining performance indexes of the concrete sample based on the performance data; wherein the performance indexes comprise at least one of a structural characteristic index, a damage characteristic index and a protection characteristic index; the performance indexes are input into a target classification model for classification processing, and a classification evaluation result is obtained; wherein the target classification model is obtained by optimizing and adjusting parameters based on a bald eagle search algorithm. Thus, the determination of the multi-dimensional performance indexes provides a rich and detailed information basis for subsequent classification processing, and the different types of indexes describe the performance of the concrete from different angles, so that classification evaluation based on the indexes by using the target classification model is more targeted and reliable, and the accuracy of classification evaluation is improved. And the durability, the damage degree and the like of the concrete can be evaluated more accurately.

Description

Technical Field

[0001] The present application relates to the technical field of engineering material testing, and in particular to a method, device, electronic equipment and storage medium for evaluating the service performance of concrete. Background Art

[0002] Concrete, a widely used building material in modern infrastructure construction, faces increasing attention for its durability in sulfate environments. Concrete exposed to sulfate environments faces the risk of failure due to a continuous loss of performance over the course of its service life. For key projects such as bridges and dams, the durability of concrete structures is directly linked to their safety and service life. Therefore, conducting multiple performance evaluations of concrete materials in these key projects is essential.

[0003] Traditional concrete durability assessment methods mostly rely on macroscopic properties, such as compressive strength and flexural strength, as a single criterion. However, in the complex service environment of actual projects, multiple factors, including concrete's internal structural characteristics, damage status, and protective measures, significantly influence concrete's sulfate attack process. Relying solely on macroscopic performance indicators for evaluation cannot fully and accurately reflect concrete's true durability in sulfate environments.

[0004] Therefore, how to accurately and comprehensively test the service performance of concrete is an urgent problem that needs to be solved. Summary of the Invention

[0005] Based on the technical pain points in concrete service performance evaluation, the present invention provides a concrete service performance evaluation method, device, electronic equipment and storage medium.

[0006] In a first aspect, the present application provides a method for evaluating the service performance of concrete, the method comprising: Obtain performance data of concrete specimens during service; Determining a performance index of the concrete sample based on the performance data; wherein the performance index includes at least one of a structural characteristic index, a damage characteristic index, and a protective characteristic index; The performance indicators are input into a target classification model for classification processing to obtain a classification evaluation result; wherein, the target classification model is obtained based on the optimization and parameter adjustment of the vulture search algorithm.

[0007] In one embodiment, the structural characteristic index includes an overall structural index, a damaged structural index, and / or an erosion impact range index; and determining the performance index of the concrete sample based on the performance data includes at least one of the following: determining the overall structural index according to the aggregate volume, pore volume, and first total volume of the concrete sample; determining the damage structure index based on a second total volume of capillary pores with pore diameters within a preset range in the concrete sample and the pore volume; The erosion impact range index is determined according to the size of the concrete sample in the erosion direction and the critical erosion depth.

[0008] In one embodiment, the damage characteristic index includes a strength loss index, a sound velocity performance damage index, and / or a microcrack density index; and determining the performance index of the concrete sample based on the performance data includes at least one of the following: determining the strength loss index according to the current compressive strength and the initial compressive strength of the concrete sample; determining the sonic performance damage index according to the Poisson's ratio, material density, and average sonic velocity of the concrete sample; The microcrack density index is determined according to the cumulative impact number and the cumulative energy number of the acoustic emission event activity index in the concrete sample within a preset time window.

[0009] In one embodiment, the protective characteristic index includes a surface integrity index and / or a protective layer thickness index; and determining the performance index of the concrete specimen based on the performance data includes at least one of the following: determining the surface integrity index based on the erosion source contact area and the total area of ​​the damaged area of ​​the concrete sample; The protective layer thickness index is determined according to the average thickness of the protective layer of the concrete sample and the designed thickness of the protective layer.

[0010] In one embodiment, the target classification model is a support vector machine; the training method of the target classification model includes: Acquire a sample set; wherein the sample set includes a training set and a test set; the sample set includes the performance indicators with multiple labeled classification labels; wherein the classification labels include healthy state, critical state, disease state, and failure state; Constructing an initial classification model according to the feature vector corresponding to the performance indicator, the classification label, the model penalty factor and the Gaussian kernel function; The initial classification model is trained using the training set, and during the training process, the model penalty factor and the kernel function variance in the Gaussian kernel function are iteratively optimized using the vulture search algorithm to obtain a target penalty factor and a target kernel function variance; The target classification model is determined based on the target penalty factor and the target kernel function variance.

[0011] In one embodiment, the method further comprises: Inputting the test set into the target classification model to obtain a classification verification result; Determine an evaluation index result based on the classification verification result; wherein the evaluation index result includes at least one of classification accuracy, precision, recall rate and confusion matrix; Based on the evaluation index results, the performance of the target classification model is determined.

[0012] In one embodiment, the method of iteratively optimizing the model penalty factor and the kernel function variance in the Gaussian kernel function using the vulture search algorithm during the training process to obtain a target penalty factor and a target kernel function variance includes: During the mth iteration, the mth fitness is determined according to the classification accuracy, the total number of features corresponding to the performance index, and the number of selected optimized features; wherein m is a positive integer; When the mth fitness is better than the m-1th fitness, the model penalty factor and the kernel function variance are updated based on the mth fitness until the number of iterations reaches a preset number, thereby obtaining the target penalty factor and the target kernel function variance.

[0013] In a second aspect, the present application further provides a device for evaluating the service performance of concrete, the device comprising: An acquisition module is used to obtain performance data of concrete specimens during service; a detection module, configured to determine a performance index of the concrete sample based on the performance data; wherein the performance index includes at least one of a structural characteristic index, a damage characteristic index, and a protective characteristic index; An evaluation module is used to input the performance indicators into a target classification model for classification processing to obtain a classification evaluation result; wherein, the target classification model is obtained based on the optimization and parameter adjustment of the vulture search algorithm.

[0014] In a third aspect, the present application also provides an electronic device comprising a processor and a memory for storing a computer program for the processor; wherein the processor is configured to: when executing the computer program, implement the steps of the method execution described in any embodiment of the present application.

[0015] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method execution described in any embodiment of the present application.

[0016] The aforementioned concrete service performance evaluation method, on the one hand, acquires performance data from concrete specimens during service and determines multiple performance indicators covering structural, damage, and protective properties. This method comprehensively reflects the concrete's true condition during service from multiple dimensions. Compared to traditional evaluation methods that rely solely on a single macro-performance indicator (such as compressive strength), this multi-dimensional indicator system can more comprehensively and accurately capture the subtle changes in concrete under complex service environments such as sulfate attack, reducing misjudgments of concrete's true durability due to a single indicator. Furthermore, the identification of multi-dimensional performance indicators provides a rich and detailed information foundation for subsequent classification. Different types of indicators describe concrete performance from different perspectives, making the classification evaluation based on these indicators using the target classification model more targeted and reliable. This facilitates more accurate assessments of concrete durability, damage severity, and other aspects, providing a more scientific basis for engineering decision-making. Furthermore, the target classification model is optimized using the vulture search algorithm. By combining global and local search, it can quickly locate optimal model parameter combinations, avoiding the model from falling into local optimal solutions, thereby improving the model's generalization and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flow chart of a method for evaluating the service performance of concrete according to an exemplary embodiment; Figure 2 is a schematic diagram showing a parameter optimization process according to an exemplary embodiment; Figure 3 is a schematic diagram showing classification evaluation results of a training set and a test set according to an exemplary embodiment; Figure 4 is a structural block diagram of a concrete service performance evaluation device according to an exemplary embodiment; Figure 5 It is a diagram showing the internal structure of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0019] The terms "first", "second" and "third" in the embodiments of the present application are only used for descriptive purposes and are not to be understood as indicating or implying relative importance or implicitly indicating the number or order of the indicated technical features. Thus, a feature defined as "first", "second" and "third" may explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, method, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0020] References to "embodiments" herein mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] In some embodiments, the concrete service performance evaluation method provided in the embodiments of the present application can be applied to electronic devices or cloud servers. The electronic device can be any mobile terminal or fixed terminal. The terminal can be a device that provides voice and / or data connectivity to users. For example, the terminal can be an Internet of Things terminal, such as a sensor device, a mobile phone or so-called "cellular" phone, and a computer with an Internet of Things terminal, for example, a fixed, portable, pocket-sized, handheld, or computer-built-in device. The cloud server can be any virtualized computing resource or physical server cluster. The server can be a platform that provides on-demand, scalable computing, storage, network, and application services to users.

[0022] In some embodiments, as Figure 1 As shown, a method for evaluating the service performance of concrete is provided, the method comprising the following steps: S101, obtaining performance data of the concrete sample during service.

[0023] In one embodiment, to obtain performance data for the concrete structure to be evaluated, concrete samples can be collected through on-site core drilling. Sample collection strictly adheres to the procedures specified in the "Technical Specification for Concrete Strength Testing by Core Drilling" (JGJ / T 384-2016). For each concrete structure to be evaluated, one or more (e.g., three) concrete samples are precisely drilled, including the original surface of the structure, to fully preserve information about the initial state of the structure. After the core drilling operation is completed, repair work must be performed on the tested areas to promptly restore structural integrity and ensure that subsequent service performance is not affected.

[0024] In the embodiment of the present application, the performance data may include but is not limited to at least one of structural characteristic data, damage characteristic data and protection characteristic data.

[0025] Optionally, the structural characteristic data may include but is not limited to at least one of overall structural characteristic data, damaged structure distribution data, and erosion impact range data.

[0026] For example, the structural property data may include, but is not limited to, at least one of a first total volume of the concrete sample, an aggregate volume, a pore volume, a second total volume of capillary pores, and a size of the concrete sample in an erosion direction.

[0027] Optionally, the damage characteristic data may include but is not limited to at least one of strength loss data, dynamic elastic modulus loss data and microcrack density data.

[0028] For example, the damage characteristic data may include but is not limited to at least one of the compressive strength, Poisson's ratio, mass loss rate, relative dynamic elastic modulus damage, average sound velocity, and acoustic emission event activity index of the concrete specimen before and after corrosion.

[0029] Optionally, the protection characteristic data may include but is not limited to at least one of surface integrity data and protection layer thickness data.

[0030] For example, the protective characteristic data may include but is not limited to at least one of the erosion source contact area of ​​the concrete specimen, the total area of ​​the damaged area, the surface damaged area ratio, the average thickness of the protective layer, and the designed thickness of the protective layer.

[0031] S102: Determine a performance index of the concrete sample based on the performance data; wherein the performance index includes at least one of a structural characteristic index, a damage characteristic index, and a protective characteristic index.

[0032] In some embodiments, the electronic device may determine corresponding performance indicators for performance data of different data types based on algorithms / models that match the data types.

[0033] For example, the performance data includes a first total volume, aggregate volume, and pore volume of the concrete specimen; the data type is structural property data. The electronic device can determine a first value based on the difference between the first total volume and the aggregate volume; and determine an effective porosity based on the ratio of the pore volume to the first value. The effective porosity is used to characterize the overall structural index, reflecting the likelihood and rate of chemical reaction or physical damage to the concrete specimen in an environment such as sulfate.

[0034] S103: Input the performance indicator into a target classification model for classification processing to obtain a classification evaluation result; wherein, the target classification model is obtained based on the optimization and parameter adjustment of the vulture search algorithm.

[0035] In an embodiment of the present application, the target classification model may include but is not limited to at least one of a machine learning classification model (e.g., Random Forest, Support Vector Machine (SVM)) and a deep learning model (e.g., Transformer architecture, neural network model).

[0036] In the embodiments of this application, the Bald Eagle Search Algorithm (BES) is an optimization algorithm based on bionic principles. By simulating the behavior of a vulture in selecting, searching, and swooping down to catch prey, the Bald Eagle Search Algorithm combines global search with local, refined search, making it suitable for solving complex optimization problems, such as those involving nonlinear and nonconvex optimization.

[0037] In the embodiment of the present application, the classification evaluation result may include but is not limited to at least one of a classification label and a classification probability.

[0038] In one embodiment, a first concrete structure to be evaluated includes a first concrete sample, a second concrete sample, and a third concrete sample. The electronic device may input a performance indicator of the first concrete sample into a target classification model to obtain a first classification evaluation result; input the performance indicator of the second concrete sample into the target classification model to obtain a second classification evaluation result; and input the performance indicator of the third concrete sample into the target classification model to obtain a third classification evaluation result. Based on the first, second, and third classification evaluation results, a classification evaluation result for the first concrete structure may be determined. The classification evaluation result may represent the current service performance of the first concrete structure after being corroded by an environment such as sulfate.

[0039] The aforementioned concrete service performance evaluation method, on the one hand, acquires performance data from concrete specimens during service and determines multiple performance indicators covering structural, damage, and protective properties. This method comprehensively reflects the concrete's true condition during service from multiple dimensions. Compared to traditional evaluation methods that rely solely on a single macro-performance indicator (such as compressive strength), this multi-dimensional indicator system can more comprehensively and accurately capture the subtle changes in concrete under complex service environments such as sulfate attack, reducing misjudgments of concrete's true durability due to a single indicator. Furthermore, the identification of multi-dimensional performance indicators provides a rich and detailed information foundation for subsequent classification. Different types of indicators describe concrete performance from different perspectives, making the classification evaluation based on these indicators using the target classification model more targeted and reliable. This facilitates more accurate assessments of concrete durability, damage severity, and other aspects, providing a more scientific basis for engineering decision-making. Furthermore, the target classification model is optimized using the vulture search algorithm. By combining global and local search, it can quickly locate optimal model parameter combinations, avoiding the model from falling into local optimal solutions, thereby improving the model's generalization and accuracy.

[0040] In one embodiment, the structural characteristic index includes an overall structural index, a damaged structural index, and / or an erosion impact range index; and determining the performance index of the concrete sample based on the performance data includes at least one of the following: determining the overall structural index according to the aggregate volume, pore volume, and first total volume of the concrete sample; determining the damage structure index based on a second total volume of capillary pores with pore diameters within a preset range in the concrete sample and the pore volume; The erosion impact range index is determined according to the size of the concrete sample in the erosion direction and the critical erosion depth.

[0041] In one embodiment, the electronic device may calculate and determine the aggregate volume, pore volume, and first total volume of the concrete sample based on the X-CT test image.

[0042] In the embodiment of the present application, the first total volume is the total volume of the concrete sample, and the second total volume is the total volume of the capillary pores.

[0043] For example, the electronic device can be based on the effective porosity as an overall structural indicator. The calculation method is: ;in, indicating a first total volume; Indicate aggregate volume; Indicates the pore volume.

[0044] In some embodiments, since the deterioration of concrete in a sulfate environment is dominated by capillary pores with a pore size between 0.1 μm and 1 μm, the preset range can be determined to be 0.1 μm to 1 μm.

[0045] In one embodiment, the performance data includes the pore volume of the concrete specimen and a second total volume of capillary pores with a pore size within a preset range. The electronic device can determine the second total volume of the capillary pores using low-field nuclear magnetic resonance (NMR) and / or mercury intrusion porosimetry (MIP). The capillary porosity is determined based on the ratio of the second total volume to the pore volume. The capillary porosity is used to characterize the structural damage indicator.

[0046] For example, a method for determining capillary porosity The calculation method is: ;in, indicating a second total volume; Indicates the pore volume.

[0047] In the embodiment of the present application, the critical depth of corrosion can represent the depth of the transition area from the surface of the concrete to the interior that is not significantly corroded by sulfate, that is, the boundary position where the degree of deterioration suddenly changes.

[0048] In one embodiment, the electronic device can perform statistical analysis on various concrete samples with the same mix ratio to determine the expected value of the effective porosity. For the concrete sample to be tested, the concrete sample is layered in the radial direction starting from the center of the sample, and the porosity data obtained by CT image reconstruction is combined to verify the size relationship between the effective porosity of each layer and the expected value layer by layer. When the effective porosity is greater than or equal to the expected value for the first time, the radius of the layer corresponding to the effective porosity is determined as the critical radius. The critical depth of erosion is determined based on the difference between the actual radius of the concrete sample and the critical radius. The erosion range ratio is determined based on the ratio of the critical depth of erosion to the size of the concrete sample in the erosion direction. The erosion range ratio is used to represent the erosion impact range index.

[0049] It should be noted that when there is a crack structure in the concrete specimen that directly penetrates to the center, it can be directly considered that the entire concrete specimen is affected by sulfate corrosion and its critical radius is 0.

[0050] For example, an erosion range ratio The calculation method is: ;in, Indicates critical depth of erosion; Indicates the size of the concrete specimen in the erosion direction.

[0051] In the embodiments of the present application, by determining the overall structural index, the density of the concrete can be quantified, thereby determining the durability and strength of the concrete; by determining the damage structure index, the most vulnerable area can be determined; by determining the erosion impact range index, the impact range of erosion can be directly quantified, providing strong evidence for evaluating the material's anti-erosion ability.

[0052] In some embodiments, the damage characteristic index includes a strength loss index, a sound velocity performance damage index, and / or a microcrack density index; and determining the performance index of the concrete specimen based on the performance data includes at least one of the following: determining the strength loss index according to the current compressive strength and the initial compressive strength of the concrete sample; determining the sonic performance damage index according to the Poisson's ratio, material density, and average sonic velocity of the concrete sample; The microcrack density index is determined according to the cumulative impact number and the cumulative energy number of the acoustic emission event activity index in the concrete sample within a preset time window.

[0053] In one embodiment, the performance data may include the current compressive strength and initial compressive strength of the concrete sample. The electronic device may determine a second value based on the difference between the initial compressive strength of the concrete sample before corrosion and the current compressive strength after corrosion; and determine a strength loss index based on the ratio of the second value to the initial compressive strength. Specifically, the strength loss index is determined based on damage theory.

[0054] For example, a method for determining a strength loss index The calculation method is: ;in, Indicates the current compressive strength; Indicates initial compressive strength.

[0055] In one embodiment, the performance data may include the Poisson's ratio, material density, and average acoustic velocity of the concrete specimen. The acoustic velocity performance loss index can be characterized by a damage index of the overall dynamic elastic modulus. The overall dynamic elastic modulus is an important mechanical property that characterizes the concrete material's ability to resist elastic deformation under dynamic loads. The overall dynamic elastic modulus can be determined by measuring the propagation velocity of ultrasonic waves in concrete.

[0056] For example, an overall dynamic elastic modulus The calculation method can be: ;in, Indicates Poisson's ratio; Indicates material density; Indicates the average speed of sound. A damage indicator of the overall dynamic elastic modulus The calculation method can be: ;in, Indicates the initial dynamic elastic modulus.

[0057] In the embodiments of this application, the Acoustic Emission (AE) event activity indicator is the elastic waves released within a material due to processes such as damage, fracture, or phase change. These elastic waves can be captured by an AE sensor and converted into electrical signals, which are then analyzed by an AE detection system. Acoustic emission detection technology can dynamically and in real time reflect the damage status within a material.

[0058] In the embodiment of the present application, the number of impacts may indicate the number of times the acoustic emission sensor receives a signal. Each acoustic emission event (such as the formation, expansion, or microstructural change of a crack) may generate one or more impact signals.

[0059] In this embodiment of the present application, the cumulative impact count may indicate the sum of the impact counts within a predetermined time window or a predetermined statistical period. The cumulative impact count represents the overall level of acoustic emission activity / events within the predetermined time window or the predetermined statistical period, namely, the frequency and severity of internal material damage or structural changes.

[0060] In the embodiment of the present application, the energy number may indicate the energy released by each acoustic emission event. The energy is related to the dynamic process of the acoustic emission source, such as the propagation speed of the crack.

[0061] In the embodiment of the present application, the cumulative energy value may indicate the sum of energy released by all acoustic emission events within a predetermined time window or a predetermined statistical period. The cumulative energy value represents the intensity of the acoustic emission activity within the predetermined time window or the predetermined statistical period.

[0062] In one embodiment, the performance data may include the cumulative number of impacts and the cumulative number of energies, indicators of acoustic emission event activity. The electronic device may determine the energy concentration of the acoustic emission event based on the ratio of the cumulative number of impacts to the cumulative number of energies. The electronic device may also determine a microcrack density index based on the ratio of the energy concentration of the concrete sample being evaluated to the energy concentration of an uncorroded concrete control sample. A larger value of the microcrack density index indicates a more active low-energy acoustic emission event in the concrete sample.

[0063] For example, a method for determining energy concentration The calculation method can be: ;in, Indicates the cumulative number of impacts; Indicates the accumulated energy. In the early stage of erosion, for example, at the initial loading stage when the relative stress is between 0 and 0.3, the difference in the internal microstructure of the concrete specimen has a greater impact on the energy concentration. The energy concentration of the concrete specimen in the early stage of erosion is determined as , the energy concentration of the concrete control sample is , then a microcrack density index The calculation method is: .

[0064] In the embodiments of this application, by determining the strength loss index, the performance degradation of concrete specimens under environmental erosion or load can be assessed; by determining the sonic velocity performance damage index, it is helpful to achieve early damage identification and early warning before macro cracks appear; by determining the microcrack density index, it can further facilitate early failure warning. In this way, by using strength loss, sonic velocity damage, and microcrack density as key indicators of concrete performance, the damage state of concrete can be comprehensively characterized from the macro to micro, from static to dynamic, which not only improves the detection accuracy and reliability, but also provides a solid foundation for concrete structure health monitoring and life prediction.

[0065] In some embodiments, the protective characteristic index includes a surface integrity index and / or a protective layer thickness index; and determining the performance index of the concrete specimen based on the performance data includes at least one of the following: determining the surface integrity index based on the erosion source contact area and the total area of ​​the damaged area of ​​the concrete sample; The protective layer thickness index is determined according to the average thickness of the protective layer of the concrete sample and the designed thickness of the protective layer.

[0066] In one embodiment, the performance data may include the erosion source contact area and the total area of ​​the damaged area of ​​the concrete sample. The electronic device may determine the surface integrity index based on the ratio of the total area of ​​the damaged area to the erosion source contact area of ​​the concrete sample.

[0067] For example, a surface integrity index The calculation method is: ;in, Indicate the total area of ​​the damaged area; Indicates the contact area of ​​the erosion source.

[0068] In one embodiment, the performance data may include the average thickness of the protective layer and the designed thickness of the protective layer after corrosion of the concrete specimen. The electronic device may determine a third value based on the ratio of the average thickness of the protective layer to the designed thickness of the protective layer; and determine the protective layer thickness indicator based on the difference between the preset value and the third value.

[0069] For example, a protective layer thickness indicator The calculation method can be: ;in, Indicates the average thickness of the protective layer; Indicates the design thickness of the protective layer.

[0070] In the embodiments of the present application, by introducing the surface integrity index and the protective layer thickness index, it is not only helpful to fully understand the physical state and durability level of the concrete specimen or structure, but also provides a quantitative scientific basis for engineering inspection, maintenance management and life prediction, which is of great significance for improving the safety, economy and sustainability of infrastructure.

[0071] In some embodiments, the target classification model is a support vector machine; the training method of the target classification model includes: Acquire a sample set; wherein the sample set includes a training set and a test set; the sample set includes the performance indicators with multiple labeled classification labels; wherein the classification labels include healthy state, critical state, disease state, and failure state; Constructing an initial classification model according to the feature vector corresponding to the performance indicator, the classification label, the model penalty factor and the Gaussian kernel function; The initial classification model is trained using the training set, and during the training process, the model penalty factor and the kernel function variance in the Gaussian kernel function are iteratively optimized using the vulture search algorithm to obtain a target penalty factor and a target kernel function variance; The target classification model is determined based on the target penalty factor and the target kernel function variance.

[0072] In one embodiment, the electronic device may divide the sample set into a training set and a test set according to a preset ratio; for example, the preset ratio may be 4:1, or 5:2, etc.

[0073] In the present embodiment, the healthy state indicates that the concrete structure has not yet been affected by a disease, or is in the initial stage of disease development. At this point, all performance indicators of the concrete remain good, the working performance fully meets the design requirements, and there are no visible or detectable signs of damage.

[0074] It should be noted that for different types of target classification models, the types of model hyperparameters and iterative optimization methods can be different, and no further restrictions are made here.

[0075] In the examples presented herein, the critical state indicates that concrete defects have entered their early stages of development but have not yet resulted in significant structural damage. At this stage, the overall functionality of the concrete remains largely normal, but the concrete specimen's overall structural indicators and strength loss indicators show slight degradation, indicating that the structure is already affected by potential defects and warrants attention and monitoring.

[0076] In the examples of this application, the damage state indicates that the concrete structure has experienced significant damage, including visible cracks and spalling on the concrete surface, expansion cracking, surface spalling, and reduced strength. This has led to a significant decrease in some performance indicators, resulting in the structure being unable to fully meet the original design requirements. At this stage, reinforcement, repair, or protective measures are typically required to restore or delay further deterioration of the structural performance.

[0077] In the present embodiment, the failure state indicates that the concrete disease has developed on a large scale, and the structural load-bearing capacity or use function has been severely damaged or even completely lost, making it impossible to continue to serve safely. At this point, the structure is no longer worth repairing and needs to be demolished, rebuilt, or abandoned.

[0078] For example, a method of constructing an initial classification model may be: ;in, 、 Both indicate Lagrange multipliers, which are used to characterize the importance of samples to the initial classification model; 、 Indicates the classification label of the sample; Indicates the Gaussian kernel function; n indicates the number of samples in the training set. An expression of a Gaussian kernel function can be: ; where g indicates the kernel function variance.

[0079] In one embodiment, the electronic device iteratively solves the initial classification model based on the constraint conditions to obtain a classification evaluation result. The constraint conditions may be one or more.

[0080] For example, the first constraint condition may be: ;in, Indicates the Lagrange multiplier corresponding to sample i; Indicates the classification label of sample i. The second constraint can be: ; Where C indicates the model penalty factor. Solve the classification label of the concrete sample for the goal: ; Get the final classification evaluation results: .

[0081] In some embodiments, the iterative optimization of the model penalty factor and the kernel function variance in the Gaussian kernel function using the vulture search algorithm during the training process to obtain a target penalty factor and a target kernel function variance includes: During the mth iteration, the mth fitness is determined according to the classification accuracy, the total number of features corresponding to the performance index, and the number of selected optimized features; wherein m is a positive integer; When the mth fitness is better than the m-1th fitness, the model penalty factor and the kernel function variance are updated based on the mth fitness until the number of iterations reaches a preset number, thereby obtaining the target penalty factor and the target kernel function variance.

[0082] For example, a fitness calculation method is as follows: ; Among them, acc indicates the classification accuracy; N indicates the total number of features; R indicates the number of optimized features; Indicates the accuracy parameter.

[0083] In some embodiments, the electronic device can set a population size and a maximum number of iterations (the preset number is less than or equal to the maximum number of iterations), select a certain number of candidate parameter combinations as individuals, and each individual represents a set of model penalty factors and kernel function variances; in the process of selecting the search space, the vulture behavior is described according to the following equation: ; in, Indicates the updated position of the i-th individual; Indicates the best search position corresponding to the best fitness; Indicates the average distribution position of all individuals; Indicates the current position of the i-th individual; Indicates the position control parameter, the value is [1.5,2]; rand indicates a random number in the interval (0,1).

[0084] The vulture's behavior during the search for prey in space is described by the following equation: ; ; ; ; in, Indicates the updated position of the i-th individual; Indicates the best search position corresponding to the best fitness; Indicates the average distribution position of all individuals; Indicates the current position of the i-th individual; Indicates the flight angle control parameter, the value is [5,10]; R indicates the flight control parameter, the value is [0.5,2]; Indicates the model penalty factor; Indicates the kernel function variance; Indicates polar angle; Indicates the pole; rand indicates a random number in the interval (0,1).

[0085] The following equation describes the behavior of a vulture during the dive to capture its prey: ; ; ; ; in, Indicates the updated position of the i-th individual; Indicates the best search position corresponding to the best fitness; Indicates the average distribution position of all individuals; Indicates the current position of the i-th individual; Indicates the flight angle control parameter, the value is [5,10]; c1 and c2 indicate the motion factor, the value range is (1,2); Indicates the model penalty factor; Indicates the kernel function variance; Indicates polar angle; Indicates the pole; rand indicates a random number in the interval (0,1).

[0086] In one embodiment, the electronic device optimizes key parameters of the support vector machine (SVM) classification prediction model using a vulture search algorithm. The optimized model parameter values ​​are shown in Table 1:

[0087] Table 1

[0088] In the process of building the BES-SVM classification prediction model, the algorithm and SVM parameters are first initialized, including the population size, maximum number of iterations, initial search range, etc. Subsequently, the parameter optimization process is performed according to the standard operation process of the vulture search algorithm. After the program is completed, the target penalty factor and target kernel function parameters that achieve the best model performance are output, that is, the optimal hyperparameter combination is obtained. Figure 2 As shown, Figure 2 Schematic diagram of the parameter optimization process.

[0089] In the embodiment of the present application, by constructing an initial classification model and iteratively optimizing and adjusting the parameters of the initial classification model, the classification accuracy and generalization ability can be improved; and, by automatically optimizing the hyperparameters through the vulture algorithm, the BES optimization process can adapt to the data distribution characteristics of different sample sets, reducing the subjectivity and blindness of manual parameter adjustment; by inputting multi-dimensional performance indicators into the trained target classification model, accurate identification of the current state of the concrete sample can be achieved.

[0090] In some embodiments, the method further comprises: Inputting the test set into the target classification model to obtain a classification verification result; Determine an evaluation index result based on the classification verification result; wherein the evaluation index result includes at least one of classification accuracy, precision, recall rate and confusion matrix; Based on the evaluation index results, the performance of the target classification model is determined.

[0091] In the embodiment of the present application, the classification accuracy indicates the proportion of all correctly predicted / classified samples to the total number of samples.

[0092] In the embodiment of the present application, the recall rate indicates the proportion of positive samples correctly identified by the model to all true positive samples.

[0093] In the embodiment of the present application, the confusion matrix is ​​a statistical matrix used to display classification evaluation results.

[0094] For example, as shown in Tables 2 and 3, Table 2 is a schematic diagram of the data set corresponding to the training set, and Table 3 is a schematic diagram of the data set corresponding to the test set. Electronic devices can have a pre-established service status rating table, which can represent the relationship between status labels and evaluation levels. The evaluation level corresponding to the healthy state is 1; the critical state is 2; the diseased state is 3; and the failure state is 4.

[0095] Table 2

[0096] Table 3

[0097] For example, Figure 3 Schematic diagram of the classification evaluation results of the training set and test set.

[0098] In the embodiment of the present application, the test set is data that does not participate in parameter tuning during the training process, which can simulate new samples encountered by the model in actual applications; by determining the results of multiple evaluation indicators, a comprehensive understanding of the different performances of the target classification model in different categories can be achieved.

[0099] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0100] Based on the same inventive concept, embodiments of the present application also provide a concrete service performance evaluation device for implementing the aforementioned concrete service performance evaluation method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the concrete service performance evaluation device provided below can be found in the above-described limitations of the concrete service performance evaluation method and will not be further elaborated here.

[0101] In one embodiment, Figure 4 As shown, a concrete service performance evaluation device is provided, the device comprising: An acquisition module 10 is used to obtain performance data of the concrete sample during service; A detection module 20 is configured to determine a performance index of the concrete sample based on the performance data; wherein the performance index includes at least one of a structural characteristic index, a damage characteristic index, and a protective characteristic index; The evaluation module 30 is used to input the performance indicators into the target classification model for classification processing to obtain a classification evaluation result; wherein, the target classification model is obtained based on the optimization and parameter adjustment of the vulture search algorithm.

[0102] In one embodiment, the structural characteristic index includes an overall structural index, a damaged structural index, and / or an erosion impact range index; the detection module 20 is configured to perform at least one of the following steps: determining the overall structural index according to the aggregate volume, pore volume, and first total volume of the concrete sample; determining the damage structure index based on a second total volume of capillary pores with pore diameters within a preset range in the concrete sample and the pore volume; The erosion impact range index is determined according to the size of the concrete sample in the erosion direction and the critical erosion depth.

[0103] In one embodiment, the damage characteristic index includes a strength loss index, a sound velocity performance damage index, and / or a microcrack density index; the detection module 20 is configured to perform at least one of the following steps: determining the strength loss index according to the current compressive strength and the initial compressive strength of the concrete sample; determining the sonic performance damage index according to the Poisson's ratio, material density, and average sonic velocity of the concrete sample; The microcrack density index is determined according to the cumulative impact number and the cumulative energy number of the acoustic emission event activity index in the concrete sample within a preset time window.

[0104] In one embodiment, the protective characteristic index includes a surface integrity index and / or a protective layer thickness index; the detection module 20 is configured to perform at least one of the following steps: determining the surface integrity index based on the erosion source contact area and the total area of ​​the damaged area of ​​the concrete sample; The protective layer thickness index is determined according to the average thickness of the protective layer of the concrete sample and the designed thickness of the protective layer.

[0105] In one embodiment, the target classification model is a support vector machine; the apparatus further includes a training module; the training module includes: An acquisition unit, configured to acquire a sample set; wherein the sample set includes a training set and a test set; the sample set includes the performance indicators with a plurality of labeled classification labels; wherein the classification labels include healthy state, critical state, disease state, and failure state; A construction unit, configured to construct an initial classification model based on the feature vector corresponding to the performance indicator, the classification label, the model penalty factor, and the Gaussian kernel function; an optimization unit, configured to train the initial classification model using the training set, and iteratively optimize the model penalty factor and the kernel function variance in the Gaussian kernel function using the vulture search algorithm during the training process to obtain a target penalty factor and a target kernel function variance; A determination unit is used to determine the target classification model based on the target penalty factor and the target kernel function variance.

[0106] In one embodiment, the apparatus further comprises: A verification module, configured to input the test set into the target classification model to obtain a classification verification result; A determination module, configured to determine an evaluation index result based on the classification verification result; wherein the evaluation index result includes at least one of classification accuracy, precision, recall rate, and confusion matrix; An evaluation module is used to determine the performance of the target classification model based on the evaluation indicator results.

[0107] In one embodiment, the optimization unit is configured to perform the following steps: During the mth iteration, the mth fitness is determined according to the classification accuracy, the total number of features corresponding to the performance index, and the number of selected optimized features; wherein m is a positive integer; When the mth fitness is better than the m-1th fitness, the model penalty factor and the kernel function variance are updated based on the mth fitness until the number of iterations reaches a preset number, thereby obtaining the target penalty factor and the target kernel function variance.

[0108] Each module in the above-mentioned concrete service performance evaluation device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor of the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0109] In one embodiment, an electronic device is provided, whose internal structure diagram can be as follows: Figure 5 As shown. The electronic device includes a processor, memory, a communication interface, a display unit, and an input device connected via a method bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating method and a computer program. The internal memory provides an environment for the operation of the operating method and computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal via wired or wireless communication. The wireless communication method can be achieved through Wi-Fi, a mobile cellular network, NFC (near field communication), or other technologies. When executed by the processor, the computer program implements a method for evaluating the service performance of concrete. The display screen of the electronic device can be a liquid crystal display or an electronic ink display. The input device of the electronic device can be a touch layer covering the display screen, or keys, a trackball, or a touchpad provided on the electronic device housing, or an external keyboard, touchpad, or mouse.

[0110] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0111] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0112] In one embodiment, a computer program product is provided, comprising a computer program, which implements the steps performed by a processor of an electronic device when the computer program is executed by a processor.

[0113] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0114] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), compilable logic units, data processing logic units based on quantum computing, and the like.

[0115] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0116] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for evaluating the service performance of concrete, characterized in that: The method comprises: Obtain performance data of concrete specimens during service; Determining a performance index of the concrete sample based on the performance data; wherein the performance index includes at least one of a structural characteristic index, a damage characteristic index, and a protective characteristic index; The performance indicators are input into a target classification model for classification processing to obtain a classification evaluation result; wherein, the target classification model is obtained based on the optimization and parameter adjustment of the vulture search algorithm.

2. The method according to claim 1, characterized in that The structural characteristic index includes an overall structural index, a damaged structural index, and / or an erosion impact range index; and the performance index of the concrete sample determined based on the performance data includes at least one of the following: determining the overall structural index according to the aggregate volume, pore volume, and first total volume of the concrete sample; determining the damage structure index based on a second total volume of capillary pores with pore diameters within a preset range in the concrete sample and the pore volume; The erosion impact range index is determined according to the size of the concrete sample in the erosion direction and the critical erosion depth.

3. The method according to claim 1, characterized in that The damage characteristic index includes a strength loss index, a sound velocity performance damage index and / or a microcrack density index; and the performance index of the concrete sample determined based on the performance data includes at least one of the following: determining the strength loss index according to the current compressive strength and the initial compressive strength of the concrete sample; determining the sonic performance damage index according to the Poisson's ratio, material density, and average sonic velocity of the concrete sample; The microcrack density index is determined according to the cumulative impact number and the cumulative energy number of the acoustic emission event activity index in the concrete sample within a preset time window.

4. The method according to claim 1, wherein The protective characteristic index includes a surface integrity index and / or a protective layer thickness index; and the performance index of the concrete sample determined based on the performance data includes at least one of the following: determining the surface integrity index based on the erosion source contact area and the total area of ​​the damaged area of ​​the concrete sample; The protective layer thickness index is determined according to the average thickness of the protective layer of the concrete sample and the designed thickness of the protective layer.

5. The method according to claim 1, wherein The target classification model is a support vector machine; The training method of the target classification model includes: Acquire a sample set; wherein the sample set includes a training set and a test set; the sample set includes the performance indicators with multiple labeled classification labels; wherein the classification labels include healthy state, critical state, disease state, and failure state; Constructing an initial classification model according to the feature vector corresponding to the performance indicator, the classification label, the model penalty factor and the Gaussian kernel function; The initial classification model is trained using the training set, and during the training process, the model penalty factor and the kernel function variance in the Gaussian kernel function are iteratively optimized using the vulture search algorithm to obtain a target penalty factor and a target kernel function variance; The target classification model is determined based on the target penalty factor and the target kernel function variance.

6. The method according to claim 5, characterized in that The method further comprises: Inputting the test set into the target classification model to obtain a classification verification result; Determine an evaluation index result based on the classification verification result; wherein the evaluation index result includes at least one of classification accuracy, precision, recall rate and confusion matrix; Based on the evaluation index results, the performance of the target classification model is determined.

7. The method according to claim 5, characterized in that The method of iteratively optimizing the model penalty factor and the kernel function variance in the Gaussian kernel function using the vulture search algorithm during the training process to obtain a target penalty factor and a target kernel function variance includes: During the mth iteration, the mth fitness is determined according to the classification accuracy, the total number of features corresponding to the performance index, and the number of selected optimized features; wherein m is a positive integer; When the mth fitness is better than the m-1th fitness, the model penalty factor and the kernel function variance are updated based on the mth fitness until the number of iterations reaches a preset number, thereby obtaining the target penalty factor and the target kernel function variance.

8. A concrete service performance evaluation device, characterized in that: The device comprises: An acquisition module is used to obtain performance data of concrete specimens during service; a detection module, configured to determine a performance index of the concrete sample based on the performance data; wherein the performance index includes at least one of a structural characteristic index, a damage characteristic index, and a protective characteristic index; An evaluation module is used to input the performance indicators into a target classification model for classification processing to obtain a classification evaluation result; wherein, the target classification model is obtained based on the optimization and parameter adjustment of the vulture search algorithm.

9. An electronic device, characterized in that: The method comprises a processor and a memory for storing a computer program for the processor; wherein the processor is configured to: implement the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images