Method for detecting internal damage of wood structure in cultural relic and ancient building repairing link

Through the combination of multimodal detection platform and machine learning model, the accuracy and complexity problems in the internal damaging detection of wooden structures are solved, and high-resolution, real-time detection and repair solutions are realized, improving the accuracy and repair efficiency of detection .

CN119064567APending Publication Date: 2024-12-03CHANGSHU ANCIENT STYLE GARDEN CONSTR CORP
View PDF 0 Cites 6 Cited by

Patent Information

Application Number
CN202411203661.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-30
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The prior art has limitations in accuracy and resolution, data processing complexity, balance of non-destructiveness and accuracy, environmental impact, cost and operational complexity, insufficient data integration and information visualization, and traditional detection technology. The limitations of this method make it difficult to accurately detect internal damage of complex wood structures.

Method used

Using a multimodal detection platform combined with three-dimensional laser scanning, ultrasonic, X-ray, infrared thermal imaging and electromagnetic wave detector, data integration and analysis are carried out through data fusion algorithms and machine learning models, detailed detection reports are generated, and AR/VR technology is used. Conduct visualization to achieve real-time dynamic monitoring and feedback.

Benefits of technology

It improves the accuracy and comprehensiveness of the detection, reduces the dependence of manual analysis, enhances the intuitive understanding of the wood state of the repair personnel, dynamically adjusts the repair strategy, and improves the reliability and repair efficiency of the detection results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119064567A_ABST
    Figure CN119064567A_ABST
Patent Text Reader

Abstract

The invention discloses a wood structure internal damage detection method for a cultural relic and ancient building repair link, and the method comprises the following steps: obtaining wood structure damage data, carrying out the preliminary investigation of a building based on three-dimensional laser scanning, determining a key detection region, constructing a multi-modal detection platform, and arranging an environment control system for the multi-modal detection platform. Determining a detection environment; multi-modal detection is conducted on a to-be-repaired wood structure based on the multi-modal detection platform, target wood structure damage data are obtained, and the multi-modal detection platform comprises a high-frequency ultrasonic detector, an X-ray imaging system, an infrared thermal imaging camera and an electromagnetic wave detector; high-resolution three-dimensional laser scanning and various sensors (such as ultrasonic waves, infrared rays and X-rays) are combined, and more comprehensive wood detection data are provided through a sensor fusion technology (weighted average and the like). The wood can be comprehensively detected from different angles and depths, and the limitation of a single sensor technology is overcome.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of image object detection, and in particular to a method for detecting internal damage of a wooden structure in a restoration process of cultural relics and ancient buildings. Background Art

[0002] Currently, in wood inspection and ancient building restoration, internal damage inspection of wooden structures is a key link, which involves identifying and evaluating the damage inside the wood. Traditional methods include manual inspection and some basic tool inspection. Problems in current technology:

[0003] The technical problems faced by internal damage detection of wooden structures mainly include the following aspects:

[0004] 1. Detection accuracy and resolution:

[0005] Problem Description: Resolution limitation: Existing non-destructive inspection technologies such as ultrasound, X-ray and laser scanning have limitations in high-resolution imaging, especially in the detection of fine cracks or small internal damage, which may not provide sufficient resolution.

[0006] Accuracy issues: In complex wooden structures and extreme environments (such as large humidity changes, complex structures, etc.), the detection accuracy of existing technologies may be insufficient, making it difficult to accurately assess the scope and severity of internal damage.

[0007] Example: For example, ultrasonic testing can lead to inaccurate imaging when dealing with highly variable wood density, especially when detecting small cracks or internal decay.

[0008] 2. Complexity of data processing and interpretation:

[0009] Problem description: Complex data processing: The large amount of data generated by existing technologies requires complex post-processing and interpretation, especially when using X-ray or laser scanning, the interpretation of data and damage identification requires expertise and experience.

[0010] Low level of automation: Most traditional testing technologies rely on manual analysis and have a low level of automation, which leads to high subjectivity in test results and affects the consistency and reliability of testing.

[0011] Example: The large amount of point cloud data generated by laser scanning requires complex calculations and analysis, and the automated processing technology is not yet mature, making data interpretation difficult.

[0012] 3. Balance between non-destructiveness and accuracy:

[0013] Problem Description: Nondestructive Limitations: Although nondestructive inspection techniques can avoid causing additional damage to wood structures, the nondestructive nature of these techniques often limits their effectiveness in detecting deep damage.

[0014] Deep damage is difficult to detect: Some technologies (such as infrared thermal imaging) have limited effectiveness in detecting deep internal damage (such as deep decay) and may only be effective for surface or shallow damage.

[0015] Example: When inspecting deep decay in wooden structures, infrared thermal imaging may not accurately identify internal problems due to uneven heat distribution.

[0016] 4. Impact of the testing environment:

[0017] Problem description: Environmental interference: Environmental conditions such as humidity, temperature and light may affect the accuracy of the detection results. For example, a high humidity environment may interfere with the results of infrared thermal imaging.

[0018] Insufficient adaptability: Existing technologies have limited adaptability to various environmental conditions and may require additional calibration or environmental control to ensure detection accuracy.

[0019] Example: Ultrasonic testing may experience signal attenuation or unstable reflection in a humid or high temperature environment, affecting the test results.

[0020] 5. Cost and operational complexity:

[0021] Problem Description: High cost: Some advanced inspection technologies such as X-ray imaging and high-resolution laser scanning equipment are expensive, and economic feasibility may become an issue for small-scale or budget-constrained restoration projects.

[0022] Operational complexity: These detection technologies usually require professional operation and maintenance, and the operation is highly complex, which increases the complexity and time cost of the repair process.

[0023] Example: The high cost and operational complexity of X-ray imaging equipment limit its widespread application in some cultural relic restoration projects.

[0024] 6. Data integration and information visualization:

[0025] Problem description: Difficulty in data integration: The data formats and types generated by different detection technologies are inconsistent, which makes data integration difficult and affects comprehensive evaluation.

[0026] Insufficient information visualization: Insufficient visualization and interpretation tools for test data make it difficult to transform complex test results into easily understandable information, which affects the decision-making process.

[0027] Example: When combining ultrasound and X-ray data, manual integration and interpretation may be required, lacking effective integration and visualization tools to help restorers make decisions.

[0028] 7. Limitations of traditional detection technology:

[0029] Problem description: Technical limitations: Traditional wood structure detection technology has its limitations and cannot solve problems in some complex or special situations.

[0030] Poor adaptability: Traditional technologies may lack adequate adaptability and solutions for new or unseen injury types.

[0031] Example: For certain types of wood damage, conventional techniques may not provide adequate detection information or solutions. Summary of the invention

[0032] In order to solve one of the above technical problems, a method for detecting internal damage of wooden structures in the restoration process of cultural relics and ancient buildings is provided, which solves some significant problems existing in the existing technology in the detection of internal damage of wooden structures, including limitations of accuracy and resolution, complexity of data processing, balance between non-destructiveness and accuracy, environmental impact, cost and operation complexity, data integration and visualization problems, and technical problems of limitations of traditional detection technology.

[0033] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0034] A first aspect: A method for detecting internal damage of a wooden structure in the restoration of a cultural relic or ancient building, comprising the following steps:

[0035] Acquire the damage data of the wood structure, conduct a preliminary survey of the building based on 3D laser scanning, determine the key inspection areas, build a multimodal inspection platform, equip the multimodal inspection platform with an environmental control system, and determine the inspection environment;

[0036] Based on the multimodal detection platform, a multimodal detection is performed on the wood structure to be repaired to obtain damage data of the target wood structure, wherein the multimodal detection platform includes a high-frequency ultrasonic detector, an X-ray imaging system, an infrared thermal imaging camera and an electromagnetic wave detector;

[0037] An algorithm model is constructed, and data from different sources are integrated into a unified database based on the data fusion algorithm according to the target wood structure damage data integration; the data in the database is analyzed by a machine learning algorithm and a deep learning model, and the algorithm model pre-processes the fused data, and the pre-processing includes noise reduction, feature extraction and damage classification;

[0038] The preprocessed data is analyzed using visualization tools to generate a test report.

[0039] Optimum: Scan the wood structure with a high-frequency ultrasonic detector to obtain preliminary information on internal defects. Formula:

[0040] Δu=f(x,y,z);

[0041]

[0042] Among them, Δu is the Laplace operator of the objective function, which is used to describe the propagation and reflection of sound waves inside the wood, and f(x, y, z) represents the damage at the detection position.

[0043] Preferred: Scan the key detection area based on the X-ray imaging system to obtain detailed internal structure images, formula:

[0044] I(x, y) = I 0 e -μ(x,y)z ;

[0045] Where I(x, y) is the X-ray intensity received by the detector, I 0 is the initial X-ray intensity, μ(x, y) is the attenuation coefficient of wood, and z is the depth of ray penetration.

[0046] Optimum: Based on infrared thermal imaging camera to detect the temperature distribution of wooden structure, identify the humidity and thermal anomalies on the surface and shallow layer, formula:

[0047] T(x, y) = T ambient +ΔT(x,y);

[0048] Among them, T(x, y) is the actual temperature of a certain point of the wood, T ambient is the ambient temperature and ΔT(x, y) is the temperature difference.

[0049] Optimum: Based on the laser scanner, the wood structure is scanned in high precision 3D to obtain detailed surface point cloud data. The formula is:

[0050] P(x, y, z) = f(x, y);

[0051] Where P(x, y, z) represents the coordinates in the 3D point cloud of the wood, and f(x, y) describes the shape of the wood surface.

[0052] Preferred: Using electromagnetic wave detector to detect wooden structures, obtain and identify moisture and rot areas, formula:

[0053] S(t)=Ae -βt ;

[0054] Where S(t) is the electromagnetic wave signal strength, A is the initial signal strength, β is the attenuation coefficient, and t is time.

[0055] Preferably: the data fusion algorithm is based on which the data from different sources are merged into a unified database. The specific formula is:

[0056]

[0057] Where: X fused is the fused data, W i is the weight of the i-th sensor data, X i is the raw data of the i-th sensor.

[0058] Preferably: the algorithm model includes a convolutional neural network and a random forest, and the detection report includes a three-dimensional model, a heat map, an X-ray image and a data analysis result.

[0059] Preferably: the method also includes developing a repair plan and budget, and after the repair is completed, using the same detection technology to verify the repair effect, determine the quality of the repair, collect post-repair data and feedback, and optimize the detection technology and repair plan.

[0060] The second aspect: A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the processor implements the method for detecting internal damage of wooden structures in the restoration of cultural relics and ancient buildings.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] 1. Combining high-resolution 3D laser scanning with multiple sensors (such as ultrasonic, infrared, and X-ray), it provides more comprehensive wood detection data through sensor fusion technology (weighted average, etc.). It can conduct comprehensive detection of wood from different angles and depths, overcoming the limitations of single sensor technology.

[0063] Data mining and artificial intelligence technologies are used to analyze the comprehensive data in real time to identify wood damage patterns. This real-time processing capability makes the test results more accurate and timely, avoiding the problems of slow manual analysis and large errors in traditional methods.

[0064] 2. Use deep learning (such as convolutional neural networks) to perform intelligent analysis of wood damage patterns. It can identify complex damage patterns and generate detailed damage reports by learning a large amount of historical data. This technology can handle subtle damage that traditional methods cannot identify, improving the accuracy and comprehensiveness of detection.

[0065] Data mining techniques are used to identify patterns and trends in wood damage, allowing restorers to take preventive measures based on the predicted results.

[0066] 3. Through AR / VR technology, users can visualize the damage inside the wood in real time in a virtual environment. This not only enhances the restorer's intuitive understanding of the wood's condition, but also enables operation simulation and verification of the repair plan in a virtual environment.

[0067] 4. The proposed dynamic monitoring and real-time feedback system can promptly detect new damage inside the wood and quickly adjust the repair strategy. Combining real-time data processing and historical data comparison, it can more accurately track changes in the state of the wood. The real-time feedback mechanism can dynamically adjust the repair according to the monitoring data, reducing the reliance on manual intervention and improving the efficiency of repair.

[0068] 5. Through cutting-edge technologies such as multi-sensor fusion, deep learning intelligent analysis, AR / VR visualization, and real-time dynamic monitoring, a comprehensive, real-time and high-precision method for detecting internal damage of wooden structures is provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 The present invention is a flow chart of a method for detecting internal damage of a wooden structure in the restoration of cultural relics and ancient buildings. DETAILED DESCRIPTION

[0070] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0071] Embodiment 1:

[0072] Reference Figure 1 As shown, a method for detecting internal damage of a wooden structure in the restoration of a cultural relic or ancient building comprises the following steps:

[0073] Acquire the damage data of the wood structure, conduct a preliminary survey of the building based on 3D laser scanning, determine the key inspection areas, build a multimodal inspection platform, equip the multimodal inspection platform with an environmental control system, and determine the inspection environment;

[0074] Conduct a preliminary survey of the building and identify key inspection areas.

[0075] Use 3D laser scanning technology to generate detailed 3D models of buildings.

[0076] Configure a multimodal inspection platform, including ultrasonic detectors, X-ray imaging systems, infrared thermal imaging cameras, laser scanners and electromagnetic wave detectors.

[0077] The equipment needs to be installed on a movable bracket to fully cover different detection areas.

[0078] Equipped with an environmental control system to ensure that the temperature, humidity and other conditions of the testing environment are within an appropriate range to reduce the impact of the environment on the test results.

[0079] Based on the multimodal detection platform, a multimodal detection is performed on the wood structure to be repaired to obtain damage data of the target wood structure, wherein the multimodal detection platform includes a high-frequency ultrasonic detector, an X-ray imaging system, an infrared thermal imaging camera and an electromagnetic wave detector;

[0080] Specific: Based on the high-frequency ultrasonic detector scanning the wooden structure, preliminary information on internal defects is obtained. The formula is:

[0081] Δu=f(x,y,z);

[0082]

[0083] Where Δu is the Laplace operator of the objective function, which is used to describe the propagation and reflection of sound waves inside the wood, and f(x, y, z) represents the damage at the detection location. Application: By measuring the propagation time and reflection of sound waves, internal cracks and rot areas are identified. It represents the attenuation of sound waves in wood, and then infers the defects inside the wood (such as cracks or rot). In practical applications, Δu represents the change in the propagation of sound waves in wooden structures, which affects the reflection time and intensity of sound waves.

[0084] Based on the X-ray imaging system, the key detection area is scanned to obtain detailed internal structure images. The formula is:

[0085] I(x, y) = I 0 e -μ(x,y)z ;

[0086] Where I(x, y) is the X-ray intensity received by the detector, I 0 is the initial X-ray intensity, μ(x, y) is the attenuation coefficient of the wood, and z is the depth of the ray penetration. Application: Based on the attenuation of X-rays, the density differences and potential defects inside the wood are identified. It describes the attenuation of X-rays when passing through the wood, from which the density changes and damaged areas inside the wood can be identified. In specific applications, μ(x, y) reflects the degree of absorption of X-rays by defects inside the wood, helping to determine the specific location of decay or damage.

[0087] Based on the infrared thermal imaging camera to detect the temperature distribution of the wooden structure, the surface and shallow humidity and thermal anomalies are identified. The formula is:

[0088] T(x, y) = T ambient +ΔT(x,y);

[0089] Among them, T(x, y) is the actual temperature of a certain point of the wood, T ambientis the ambient temperature, and ΔT(x, y) is the temperature difference. Application: Temperature difference is used to identify surface and shallow decay areas. Infrared thermal imaging detects temperature distribution on the surface of wood to identify humidity changes and potential thermal anomalies. In applications, T(x, y) helps identify thermal anomalies caused by humidity or decay.

[0090] Specific: Based on the laser scanner, the wood structure is scanned in high precision in 3D to obtain detailed surface point cloud data. The formula is:

[0091] P(x, y, z) = f(x, y);

[0092] Where P(x, y, z) represents the coordinates in the 3D point cloud of the wood, and f(x, y) describes the shape of the wood surface. Application: Generate a high-precision 3D model of the wood surface for detecting deformation and damage. Laser scanning generates a high-precision 3D model of the wood surface for detecting surface deformation and damage. In practical applications, P(x, y, z) helps build a detailed 3D model of the wood structure for analyzing the morphological changes and potential damage of the wood surface. Specific: Detect the wood structure based on the electromagnetic wave detector to obtain and identify the moisture and rot areas. Formula:

[0093] S(t)=Ae -βt ;

[0094] Where S(t) is the electromagnetic wave signal strength, A is the initial signal strength, β is the attenuation coefficient, and t is time. Application: The attenuation of electromagnetic wave signals is used to identify the moisture and decay of wood. The attenuation of electromagnetic waves can be used to infer the moisture and decay of wood. In the application, β reflects the moisture changes and damage of wood, helping to identify moisture problems and decay areas inside the wood.

[0095] Specifically: The data fusion algorithm is based on which the data from different sources are integrated into a unified database. The specific formula is:

[0096]

[0097] Where: X fused is the fused data, W i is the weight of the i-th sensor data, X i is the raw data of the i-th sensor.

[0098] In practical applications, W i Reflects the data contribution of different detection technologies, X fused It is the final comprehensive consideration of information from various data sources.

[0099] An algorithm model is constructed, and data from different sources are integrated into a unified database based on the data fusion algorithm according to the target wood structure damage data integration; the data in the database is analyzed by a machine learning algorithm and a deep learning model, and the algorithm model pre-processes the fused data, and the pre-processing includes noise reduction, feature extraction and damage classification;

[0100] In-depth data analysis, formula:

[0101] f(x) = σ(Wx + b);

[0102] Where: f(x) is the output of the deep learning model, W is the weight matrix, b is the bias, and σ is the activation function (such as ReLU or Sigmoid). Deep learning algorithms train neural networks to analyze and classify data and identify damage patterns. In practical applications, W and b are optimized through training, and σ provides nonlinear transformations to enhance the expressive power of the model.

[0103] The preprocessed data is analyzed using visualization tools to generate a test report.

[0104] Use visualization tools to present processed data into easy-to-understand graphs and reports.

[0105] Combined with 3D modeling software, the damage distribution and repair suggestions of the wooden structure are displayed, and a detailed inspection report is generated based on the analysis results, including the damage location, type, severity and repair suggestions.

[0106] The report should include 3D models, thermal maps, X-ray images and data analysis results.

[0107] Specifically: the algorithm model includes convolutional neural network and random forest, and the detection report includes three-dimensional model, heat map, X-ray image and data analysis results.

[0108] By integrating multiple cutting-edge detection technologies (ultrasound, X-ray, infrared, laser, electromagnetic waves), the limitations of a single technology are overcome, achieving comprehensive detection of internal damage to wooden structures.

[0109] Combining data fusion technology and machine learning algorithms, automated data analysis and damage identification can be achieved to improve detection accuracy and efficiency.

[0110] The reliability and adaptability of the test results are improved through environmental control systems and intelligent data processing.

[0111] Generate detailed inspection reports using advanced visualization tools for easy understanding and decision making.

[0112] Embodiment 2

[0113] A method for detecting objects in X-ray security inspection machine images, applied to deep learning and multimodal fusion, includes the following steps:

[0114] Step 1: Integrate digital inspection platform:

[0115] 1.1 High-resolution 3D laser scanning, mathematical modeling formula:

[0116] P(x,y,z)=f(x,y,z);

[0117] Among them: P(x, y, z) is the three-dimensional point cloud coordinates obtained by laser scanning, and f(x, y, z) describes the shape and concavity of the wood surface.

[0118] Laser scanning can provide high-resolution 3D models of wooden structures for detecting surface damage and deformation. In practical applications, this point cloud data will be used to generate a detailed 3D model of the wood, thus helping to identify possible areas of damage.

[0119] 1.2 Sensor fusion technology: mathematical modeling formula:

[0120]

[0121] Where: X fused is the fused data, W i is the weight of the i-th sensor data, X i is the raw data of the i-th sensor. By weighted averaging the data from different sensors (such as ultrasonic, infrared, X-ray, etc.), the overall detection accuracy and consistency can be improved.

[0122] Step 2: Apply advanced data analysis techniques:

[0123] 2.1 Artificial Intelligence and Machine Learning, Mathematical Modeling Formula:

[0124] Y = ReLU(WX+b);

[0125] Where: Y is the output of the neural network, W is the weight matrix, X is the input data, b is the bias, and ReLU is the activation function (RectifiedLinearUnit). Machine learning models (such as convolutional neural networks) are used to analyze sensor data and identify damage patterns. In practical applications, W and b are trained to optimize the model's predictive ability, and ReLU provides nonlinear transformations to enhance the model's ability to recognize complex patterns.

[0126] 2.2 Data mining and pattern recognition, mathematical modeling formula:

[0127]

[0128] Among them: Clusteri is the label of the i-th cluster, xk is the k-th data point, c i is the center of the jth cluster, distance(x k , c j ) is the distance from the data point to the cluster center. Data mining techniques (such as K-means clustering) are used to identify and classify damage patterns inside wood. In practical applications, the damage area is accurately divided by optimizing the distance calculation.

[0129] Step 3: Virtual Reality (VR) and Augmented Reality (AR) Visualization:

[0130] 3.1. VR / AR model construction, mathematical modeling formula:

[0131] V AR / VR =M·P;

[0132] Where: V AR / VR It is a visualization model in augmented reality / virtual reality. M is the model matrix and P is the point cloud data or 3D model data. AR / VR technology uses real-time visualization to display the spatial distribution of internal damage in wood, helping restoration experts to perform more accurate repairs. In practical applications, M maps 3D model data to virtual space to enhance the intuitive understanding of wood damage.

[0133] Step 4: Real-time monitoring system: mathematical modeling formula:

[0134] Update(t)=f(CurrentData(t), HistoricalData)

[0135] Where: Update(t) is the real-time updated monitoring result, CurrentData(t) is the data at the current time t,

[0136] HistoricalData is historical data. Through real-time data analysis and updating, the health status of wood is dynamically monitored and the repair strategy is adjusted in time. In practical applications, f is a data processing function that combines current data and historical data to generate the latest monitoring results.

[0137] Step 5: Develop a repair plan and budget. After the repair is completed, use the same detection technology to verify the repair effect, determine the quality of the repair, collect post-repair data and feedback, and optimize the detection technology and repair plan.

[0138] Through high-resolution 3D laser scanning and sensor fusion technology, a comprehensive model of the internal structure of wood is constructed, and accurate damage identification is carried out through advanced data analysis technology.

[0139] Use artificial intelligence and machine learning for data analysis to improve the accuracy of damage identification. Deep learning models are able to process complex damage patterns and provide detailed damage reports.

[0140] Use AR / VR technology to visualize internal damage to wood in real time, improving the accuracy of repair plans and the operational efficiency of repair personnel.

[0141] Through real-time monitoring systems and dynamic data updates, new damage inside the wood can be discovered in time and effective intervention can be carried out.

[0142] Embodiment 3

[0143] An embodiment of the present application also provides a computer-readable storage medium, which can be set in a server to store at least one instruction or at least one program related to a method for detecting internal damage of a wooden structure in a cultural relic and ancient building restoration process in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement a method for detecting internal damage of a wooden structure in a cultural relic and ancient building restoration process provided in the above method embodiment.

[0144] Optionally, in this embodiment, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0145] Embodiment 4

[0146] The embodiment of the present invention also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes a method for detecting internal damage of a wooden structure in the restoration of a cultural relic and an ancient building provided in the above-mentioned various optional embodiments.

[0147] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0148] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0149] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0150] Based on the above ideal embodiments of the present invention, the relevant staff can make various changes and modifications without departing from the technical concept of the present invention through the above description. The technical scope of the present invention is not limited to the contents of the specification, and its technical scope must be determined according to the scope of the claims.

[0151] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of various changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for detecting internal damage of wooden structures in the restoration of cultural relics and ancient buildings. It is characterized in that The following steps are involved: Acquire the damage data of the wood structure, conduct a preliminary survey of the building based on 3D laser scanning, determine the key inspection areas, build a multimodal inspection platform, equip the multimodal inspection platform with an environmental control system, and determine the inspection environment; Based on the multimodal detection platform, a multimodal detection is performed on the wood structure to be repaired to obtain damage data of the target wood structure, wherein the multimodal detection platform includes a high-frequency ultrasonic detector, an X-ray imaging system, an infrared thermal imaging camera and an electromagnetic wave detector; An algorithm model is constructed, and data from different sources are integrated into a unified database based on the data fusion algorithm according to the target wood structure damage data integration; the data in the database is analyzed by a machine learning algorithm and a deep learning model, and the algorithm model pre-processes the fused data, and the pre-processing includes noise reduction, feature extraction and damage classification; The preprocessed data is analyzed using visualization tools to generate a test report.

2. The method according to claim 1, Features: Based on the high-frequency ultrasonic detector scanning the wooden structure, preliminary information on internal defects is obtained. The formula is: Δu=f(x,y,z); Among them, Δu is the Laplace operator of the objective function, which is used to describe the propagation and reflection of sound waves inside the wood, and f(x, y, z) represents the damage at the detection position.

3. The method according to claim 2, Features: Based on the X-ray imaging system, the key detection area is scanned to obtain detailed internal structure images. The formula is: I(x,y)=I 0 e -μ(x ,y)z; Where I(x,y) is the intensity of X-rays received by the detector, I 0 is the initial X-ray intensity, μ(x,y is the attenuation coefficient of wood, and z is the depth of ray penetration.

4. The method according to claim 1, Features: Based on the infrared thermal imaging camera to detect the temperature distribution of the wooden structure, the surface and shallow humidity and thermal anomalies are identified. The formula is: T(x,y)=T ambient +ΔT(x,y); Among them, T(x,y) is the actual temperature of a certain point of the wood, T ambient is the ambient temperature and ΔT(x,y) is the temperature difference.

5. The method according to claim 1, Features: Based on the laser scanner, the wood structure is scanned in high precision in 3D to obtain detailed surface point cloud data. The formula is: P(x,y,z)=f(x,y); Where P(x,y,z) represents the coordinates in the 3D point cloud of the wood, and f(x,y) describes the shape of the wood surface.

6. The method according to claim 1, Features: The wooden structure is inspected based on electromagnetic wave detectors to obtain and identify moisture and rot areas. The formula is: S(t)=Ae -βt ; in S(t) is the electromagnetic wave signal strength, A is the initial signal strength, β is the attenuation coefficient, and t is time.

7. The method according to claim 1, Features: The data fusion algorithm is based on which the data from different sources are merged into a unified database. The specific formula is: Where: X fused is the fused data, W i is the weight of the i-th sensor data, X i is the raw data of the i-th sensor.

8. The method according to claim 1, Features: The algorithm model includes convolutional neural network and random forest, and the detection report includes three-dimensional model, heat map, X-ray image and data analysis results.

9. The method according to claim 1, Features: The method also includes developing a repair plan and budget, and after the repair is completed, using the same detection technology to verify the repair effect, determine the quality of the repair, collect post-repair data and feedback, and optimize the detection technology and repair plan.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the processor implements the method for detecting internal damage of wooden structures in the restoration of cultural relics and ancient buildings as described in any one of claims 1 to 9.

Citation Information

Cited By

  • Multi-sensor fusion building structure detection and evaluation system and method

    CN120027851A

  • A building structure detection and evaluation system and method based on multi-sensor fusion

    CN120027851B

  • Multi-modal intelligent wood defect detection and performance evaluation system and method

    CN120064307A

  • On-line detection system and method for internal defects of sliding plate wood based on X rays

    CN120490165A

  • Ancient building repairing auxiliary system based on color quantization technology

    CN120927669A