Concrete member apparent defect evaluation method and system

Abstract

The invention provides a concrete member apparent defect assessment method and system, and the method comprises the following steps: obtaining the three-dimensional point cloud, environmental erosion and characterization stress distribution data of the surface of a concrete member, calculating the defect area based on the three-dimensional point cloud data, taking the ratio of the defect area to the member area as a geometric factor, and calculating the apparent defect of the concrete member based on the environmental erosion data. Calculating a predicted erosion rate through a time sequence prediction model, taking a ratio of the predicted erosion rate to a standard erosion rate as an environmental factor, and taking a ratio of actually measured stress to surface stress obtained by the prediction analysis model as a mechanical factor based on characterization stress distribution data; and carrying out weighted fusion on the geometric factors, the environmental factors and the mechanical factors by adopting a dynamic adjustable mode to generate a comprehensive defect index, inputting the comprehensive defect index into the defect evaluation model, and outputting the severity level of the apparent defect. According to the method, automatic evaluation of the concrete member is realized, and the objectivity and scientificity of evaluation are improved.

Description

Technical Field

[0001] This invention belongs to the field of building engineering quality testing technology, and specifically relates to a method and system for assessing apparent defects in concrete components. Background Technology

[0002] Concrete surface quality inspection is a crucial step in ensuring the quality of construction projects. The results directly reflect the density and smoothness of the concrete surface, as well as the presence of common defects such as cracks and honeycomb. They can also indirectly assess the level of construction techniques and the rationality of the internal structural quality. Timely identification and treatment of surface quality problems can effectively eliminate potential safety hazards, ensure structural safety and durability, and improve the overall appearance quality and service life of the project.

[0003] However, current concrete surface quality inspection mainly relies on manual visual inspection combined with simple tools (such as rulers and measuring tapes). This results in significant errors in measuring key parameters such as crack width and honeycomb area, failing to meet accuracy requirements. Furthermore, existing methods primarily target single defect indicators, lacking the ability to assess the overall risk of surface quality issues. Simply classifying defects into "general defects" and "serious defects" without establishing a unified quantitative threshold system limits the objectivity and comparability of test results, hindering the development of refined quality control. Summary of the Invention

[0004] This invention provides a method and system for evaluating the apparent defects of concrete components. The method enables automated evaluation of concrete components, improving the objectivity and scientific rigor of the evaluation.

[0005] The technical solution of the present invention is as follows:

[0006] A method for assessing apparent defects in concrete components includes the following steps:

[0007] S1: Acquire three-dimensional point cloud data, environmental erosion data, and stress distribution data of the surface of the concrete component to be evaluated;

[0008] S2: Based on the data obtained in step S1, calculate multiple evaluation factors, including:

[0009] S21: Calculate the defect area based on the three-dimensional point cloud data, and use the ratio of the defect area to the component area as a geometric factor;

[0010] S22: Based on the environmental erosion data, the predicted erosion rate is calculated using a time-series prediction model, and the ratio of the predicted erosion rate to the standard erosion rate is used as an environmental factor.

[0011] S23: Based on the stress distribution data, combined with the predictive analysis model, the ratio of the measured stress to the surface stress obtained from the predictive analysis model is used as a mechanical factor.

[0012] S3: The geometric factors, environmental factors, and mechanical factors are weighted and fused using a dynamically adjustable weight configuration method to generate a comprehensive defect index;

[0013] S4: Input the comprehensive defect index into the trained defect assessment model and output the severity level of the apparent defect.

[0014] Furthermore, in the aforementioned method for assessing apparent defects in concrete components, in step S1, three-dimensional point cloud data of the surface of the concrete component to be assessed is acquired using laser scanning technology; and / or,

[0015] Environmental erosion data are obtained by acquiring at least one time-series data point of ambient temperature, humidity, chloride ion concentration, and corrosive medium concentration of the concrete component to be evaluated using a sensor array; and / or,

[0016] Data on the surface stress distribution of the concrete component to be evaluated are obtained using strain gauges or fiber optic sensors.

[0017] Furthermore, in the method for assessing apparent defects in concrete components, the sensor array includes at least one of a temperature sensor, a humidity sensor, a chloride ion sensor, and a pH sensor.

[0018] Furthermore, in the aforementioned method for assessing apparent defects in concrete components, in step S21, a point cloud distortion compensation algorithm is used to correct the three-dimensional point cloud data; and / or,

[0019] In step 21, a layered fusion architecture is used to extract the shape features of the defective parts in the three-dimensional point cloud data, and the defect area is calculated based on the shape features.

[0020] Furthermore, in the concrete component apparent defect assessment method, in step S22, the time-series prediction model is a long short-term memory network model, used to predict future erosion rates based on historical environmental erosion data.

[0021] The standard erosion rate is preset based on the type of concrete material and environmental conditions.

[0022] Furthermore, in the concrete component apparent defect assessment method, in step S23, the predictive analysis model is a predictive analysis model of concrete surface stress and crack propagation width, which is used for training and verification based on historical data, finite element simulation analysis and standard test block test results.

[0023] Furthermore, in the concrete component appearance defect assessment method, in step S3, the dynamically adjustable weight configuration method adaptively adjusts the weights based on the importance of the component, its service life, or the current environmental conditions, and the sum of the weights is 1. The weights are dynamically generated through fuzzy logic or neural networks.

[0024] Furthermore, in the concrete component appearance defect assessment method, in step S4, the defect assessment model adopts a deep neural network model, and the severity level includes mild, moderate and severe.

[0025] A system for assessing apparent defects in concrete components, comprising:

[0026] The data acquisition module is used to acquire three-dimensional point cloud data, environmental erosion data, and stress distribution data of the surface of the concrete component to be evaluated.

[0027] The factor calculation module is used to calculate multiple evaluation factors based on the data acquired by the data acquisition module. These evaluation factors include:

[0028] A geometric factor calculation unit is used to calculate the defect area based on the three-dimensional point cloud data, and the ratio of the defect area to the component area is used as the geometric factor.

[0029] An environmental factor calculation unit is used to calculate the predicted erosion rate based on the environmental erosion data using a time-series prediction model, and to use the ratio of the predicted erosion rate to the standard erosion rate as the environmental factor.

[0030] The mechanical factor calculation unit is used to calculate the mechanical factor based on the stress distribution data and the predictive analysis model, using the ratio of the measured stress to the surface stress obtained from the predictive analysis model as the mechanical factor.

[0031] The fusion processing module uses a dynamically adjustable weight configuration to weight and fuse the geometric factors, environmental factors, and mechanical factors to generate a comprehensive defect index.

[0032] The evaluation output module is used to input the comprehensive defect index into the trained defect evaluation model and output the severity level of the apparent defect.

[0033] Furthermore, the aforementioned concrete component appearance defect assessment system also includes:

[0034] The visualization module is used to visualize 3D point cloud data, stress distribution maps, and defect assessment results in 3D, and supports multi-angle viewing and detail magnification.

[0035] The beneficial effects of this invention are as follows:

[0036] This invention discloses a method for assessing apparent defects in concrete components. This method integrates geometric, environmental, and mechanical parameters for quantitative fusion, constructing a comprehensive and scientific assessment index system. Combined with a defect assessment model, it automatically determines the severity level of defects in concrete components. This method can be widely applied to the safety diagnosis of concrete structures such as bridges and buildings, overcoming the limitations of single-dimensional assessment. It also solves the problems of high subjectivity and low efficiency in existing manual inspection methods, improving the objectivity of defect assessment and the scientific nature of maintenance decisions. Attached Figure Description

[0037] Figure 1 This is a flowchart of a method for evaluating the apparent defects of concrete components according to the present invention;

[0038] Figure 2 This is a schematic diagram of a concrete component appearance defect assessment system according to the present invention. Detailed Implementation

[0039] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. The advantages and features of the present invention will become clearer from the following description and claims. It should be noted that the drawings are all in a very simplified form and use non-precise proportions, and are only used to facilitate and clarify the illustration of the embodiments of the present invention.

[0040] like Figure 1 As shown, this embodiment provides a method for evaluating the apparent defects of concrete components, including the following steps: S1-S4.

[0041] S1: Obtain three-dimensional point cloud data, environmental erosion data, and stress distribution data of the surface of the concrete component to be evaluated.

[0042] Specifically, three-dimensional point cloud data of the surface of the concrete component to be evaluated can be obtained through laser scanning technology. The laser scanning technology is preferably a 3D laser scanner. A terrestrial 3D laser scanner is used to scan the concrete component to obtain high-precision three-dimensional point cloud data.

[0043] Environmental erosion data is collected by an array of sensors deployed around the concrete component, which includes time-series data on at least one of the following: ambient temperature, humidity, chloride ion concentration, and corrosive medium concentration. The sensor array may include at least one of a temperature sensor, a humidity sensor, a chloride ion sensor, and a pH sensor. The pH sensor is used to collect corrosive medium concentration data. Preferably, a chloride ion sensor is used to collect chloride ion concentration data of the concrete component over a certain period.

[0044] Stress distribution data characterizing the surface of the concrete component under load are obtained by using strain gauges or fiber optic sensors attached to the surface of the component. Fiber optic sensors are preferably fiber optic strain gauges.

[0045] Step S1 enables the acquisition of multi-source raw data of the concrete component to be evaluated, improving acquisition efficiency and accuracy.

[0046] S2: Based on the data obtained in step S1, calculate multiple evaluation factors, including S21-S23.

[0047] S21: Calculate the defect area based on the three-dimensional point cloud data, and use the ratio of the defect area to the component area as the geometric factor F. geo The layered fusion architecture sequentially locates, segments, and optimizes the contours of the defective regions in the acquired 3D point cloud to extract the shape features (geometric parameters) of the defective parts. A point cloud distortion compensation algorithm is then used to correct projection errors caused by the scanning angle, thereby accurately calculating the defect area. Finally, the ratio of the defect area to the concrete component area is calculated to obtain the geometric factor F. geo .

[0048] Step S21 uses layered fusion and point cloud distortion compensation technology to transform the visual shape of the defect into a high-precision quantified area. By using the standardized ratio with the component area, it achieves an objective assessment of the defect's geometric scale, providing a reliable basis for multi-parameter fusion judgment.

[0049] S22: Based on the environmental erosion data, calculate the predicted erosion rate using a time-series prediction model, and use the ratio of the predicted erosion rate to the standard erosion rate as the environmental factor E. env The time-series prediction model is a Long Short-Term Memory (LSTM) network model, used to predict future erosion rates based on historical environmental erosion data. Time-series data (chloride ion concentration data) is input into a pre-trained LSTM network to obtain the predicted erosion rate. The standard erosion rate is preset based on the concrete material type and environmental conditions. The ratio of the predicted erosion rate to the standard erosion rate is calculated to obtain the environmental factor E. env .

[0050] Step S22 transforms environmental erosion from a static measurement parameter into a dynamic prediction index. By comparing the predicted erosion rate with the standard erosion rate, it enables early warning of the development trend of concrete defects under future environmental influences.

[0051] S23: Based on the stress distribution data (measured stress), combined with the actual crack propagation width obtained from the 3D point cloud data, and then combined with the predictive analysis model, the theoretical predicted surface stress at this width is obtained. The ratio of the measured stress to the surface stress obtained from the predictive analysis model is used as the mechanical factor M. mechThe predictive analysis model is a predictive analysis model for concrete surface stress and crack propagation width (stress-defect propagation correlation model), which is used for training and verification based on historical data, finite element simulation analysis, and standard test block test results.

[0052] Step S23 quantifies the degree of abnormal stress concentration caused by defects by comparing the measured stress with the theoretically predicted surface stress based on the actual crack size, thereby achieving a leap from "geometric observation" to "mechanical hazard" and accurately identifying high-risk defects.

[0053] S3: The geometric factor F is configured using a dynamically adjustable weighting method. geo Environmental factor E env and mechanical factor M mech Weighted fusion is performed to generate a comprehensive defect index S. dmg S dmg =α*F geo +β*E env +γ*M mech And α+β+γ=1. The weighting coefficients α,β,γ can be fixed values, such as α=0.3, β=0.3, γ=0.4; or they can be dynamically adjustable parameters that are adaptively adjusted according to the component type, importance, and defect type.

[0054] Step S3 uses fixed weights for ease of implementation and standardization, while using dynamic weights allows the model to adapt to different components and scenarios, enhancing the applicability of the method.

[0055] S4: Input the comprehensive defect index into the trained defect assessment model and output the severity level of the apparent defect. The defect assessment model is preferably a deep neural network model, and the severity levels include mild, moderate, and severe.

[0056] Step S4 uses a deep neural network model to intelligently analyze the comprehensive defect index, automatically mapping the quantitative results of multi-parameter fusion into an intuitive level of defect severity, greatly reducing the interference of subjective factors and realizing the standardization and automation of the evaluation process.

[0057] The above method integrates geometric, environmental, and mechanical parameters for quantitative fusion to construct a comprehensive and scientific evaluation index system. Combined with a defect assessment model, it enables the automatic determination of the severity level of defects in concrete components. This method can be widely applied to the safety diagnosis of concrete structures such as bridges and buildings, overcoming the limitations of single-dimensional assessment. It also solves the problems of high subjectivity and low efficiency in existing manual inspection techniques, improving the objectivity of defect assessment and the scientific nature of maintenance decisions.

[0058] like Figure 2As shown, this embodiment also provides a system for assessing apparent defects in concrete components, including:

[0059] The data acquisition module is used to acquire three-dimensional point cloud data, environmental erosion data, and stress distribution data of the surface of the concrete component to be evaluated.

[0060] The factor calculation module is used to calculate multiple evaluation factors based on the data acquired by the data acquisition module. These evaluation factors include:

[0061] A geometric factor calculation unit is used to calculate the defect area based on the three-dimensional point cloud data, and the ratio of the defect area to the component area is used as the geometric factor.

[0062] An environmental factor calculation unit is used to calculate the predicted erosion rate based on the environmental erosion data using a time-series prediction model, and to use the ratio of the predicted erosion rate to the standard erosion rate as the environmental factor.

[0063] The mechanical factor calculation unit is used to calculate the mechanical factor based on the stress distribution data and the predictive analysis model, using the ratio of the measured stress to the surface stress obtained from the predictive analysis model as the mechanical factor.

[0064] The fusion processing module uses a dynamically adjustable weight configuration to weight and fuse the geometric factors, environmental factors, and mechanical factors to generate a comprehensive defect index.

[0065] The evaluation output module is used to input the comprehensive defect index into the trained defect evaluation model and output the severity level of the apparent defect.

[0066] This evaluation system automates the entire process from data collection, processing, analysis to result output, overcoming the limitations of single-dimensional evaluation. It also solves the problems of high subjectivity and low efficiency in manual inspection in existing technologies, improving the objectivity of defect evaluation and the scientific nature of maintenance decisions.

[0067] As a preferred embodiment, it also includes:

[0068] The visualization module is used to visualize 3D point cloud data, stress distribution maps, and defect assessment results in 3D, and supports multi-angle viewing and detail magnification.

[0069] This visualization module communicates with other modules, receiving all their output data and severity level results. It presents the analysis results intuitively through a 3D visualization interface, and supports report generation and image export, providing intuitive evidence for manual detection and analysis.

[0070] The above description is merely a description of preferred embodiments of the present invention and is not intended to limit the scope of the present invention in any way. Any changes or modifications made by those skilled in the art based on the above disclosure shall fall within the protection scope of the claims.

Claims

1. A method for assessing apparent defects in concrete components, characterized in that, Includes the following steps: S1: Acquire three-dimensional point cloud data, environmental erosion data, and stress distribution data of the surface of the concrete component to be evaluated; S2: Based on the data obtained in step S1, calculate multiple evaluation factors, including: S21: Calculate the defect area based on the three-dimensional point cloud data, and use the ratio of the defect area to the component area as a geometric factor; S22: Based on the environmental erosion data, the predicted erosion rate is calculated using a time-series prediction model, and the ratio of the predicted erosion rate to the standard erosion rate is used as an environmental factor. S23: Based on the stress distribution data, combined with the predictive analysis model, the ratio of the measured stress to the surface stress obtained from the predictive analysis model is used as a mechanical factor. S3: The geometric factors, environmental factors, and mechanical factors are weighted and fused using a dynamically adjustable weight configuration method to generate a comprehensive defect index; S4: Input the comprehensive defect index into the trained defect assessment model and output the severity level of the apparent defect.

2. The method for assessing apparent defects in concrete components as described in claim 1, characterized in that, In step S1, three-dimensional point cloud data of the surface of the concrete component to be evaluated is acquired using laser scanning technology; and / or, Environmental erosion data are obtained by acquiring at least one time-series data point of ambient temperature, humidity, chloride ion concentration, and corrosive medium concentration of the concrete component to be evaluated using a sensor array; and / or, Data on the surface stress distribution of the concrete component to be evaluated are obtained using strain gauges or fiber optic sensors.

3. The method for assessing apparent defects in concrete components as described in claim 2, characterized in that, The sensor array includes at least one of a temperature sensor, a humidity sensor, a chloride ion sensor, and a pH sensor.

4. The method for assessing apparent defects in concrete components as described in claim 1, characterized in that, In step S21, a point cloud distortion compensation algorithm is used to correct the 3D point cloud data; and / or, In step 21, a layered fusion architecture is used to extract the shape features of the defective parts in the three-dimensional point cloud data, and the defect area is calculated based on the shape features.

5. The method for evaluating apparent defects in concrete components as described in claim 1, characterized in that, In step S22, the time-series prediction model is a long short-term memory network model, which is used to predict future erosion rates based on historical environmental erosion data. The standard erosion rate is preset based on the type of concrete material and environmental conditions.

6. The method for assessing apparent defects in concrete components as described in claim 1, characterized in that, In step S23, the predictive analysis model is a predictive analysis model for concrete surface stress and crack propagation width, which is used for training and verification based on historical data, finite element simulation analysis and standard test block test results.

7. The method for assessing apparent defects in concrete components as described in claim 1, characterized in that, In step S3, the dynamically adjustable weight configuration method adaptively adjusts the weights based on the importance of the component, its service life, or the current environmental conditions. The sum of the weights is 1, and the weights are dynamically generated through fuzzy logic or neural networks.

8. The method for assessing apparent defects in concrete components as described in claim 1, characterized in that, In step S4, the defect assessment model adopts a deep neural network model, and the severity level includes mild, moderate and severe.

9. A system for assessing apparent defects in concrete components, characterized in that, include: The data acquisition module is used to acquire three-dimensional point cloud data, environmental erosion data, and stress distribution data of the surface of the concrete component to be evaluated. The factor calculation module is used to calculate multiple evaluation factors based on the data acquired by the data acquisition module. These evaluation factors include: A geometric factor calculation unit is used to calculate the defect area based on the three-dimensional point cloud data, and the ratio of the defect area to the component area is used as the geometric factor. An environmental factor calculation unit is used to calculate the predicted erosion rate based on the environmental erosion data using a time-series prediction model, and to use the ratio of the predicted erosion rate to the standard erosion rate as the environmental factor. The mechanical factor calculation unit is used to calculate the mechanical factor based on the stress distribution data and the predictive analysis model, using the ratio of the measured stress to the surface stress obtained from the predictive analysis model as the mechanical factor. The fusion processing module uses a dynamically adjustable weight configuration to weight and fuse the geometric factors, environmental factors, and mechanical factors to generate a comprehensive defect index. The evaluation output module is used to input the comprehensive defect index into the trained defect evaluation model and output the severity level of the apparent defect.

10. The concrete component appearance defect assessment system according to claim 9, characterized in that, Also includes: The visualization module is used to visualize 3D point cloud data, stress distribution maps, and defect assessment results in 3D, and supports multi-angle viewing and detail magnification.

Images