Digital simulation and verification system and method for the repair and reinforcement of ancient buildings

Abstract

The present invention discloses a digital simulation verification system and method for the repair and reinforcement of ancient buildings, relating to the technical field of data processing. The method includes: performing damage analysis on the three-dimensional modeling of the first ancient building, and extracting the structural type, material, shape and size of the damaged area; indexing and matching the repair and reinforcement process knowledge graph in the repair and reinforcement process library, and inputting the damaged data to update the prediction of material usage; based on the repair and reinforcement process number and the predicted material usage, simulating the repair and reinforcement to generate the second three-dimensional modeling; comparing the first and second modelings, calculating the feasibility of the repair and reinforcement, if the threshold is reached, recording the passing mark and outputting the corresponding scheme, thereby achieving the technical effects of providing accurate and efficient repair and reinforcement evaluation and improving the accuracy and reliability of the repair.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a digital simulation verification system and method for the repair and reinforcement of ancient buildings. Background Art

[0002] In the field of the repair and reinforcement of ancient buildings, traditional methods mainly rely on manual experience for damage analysis and the formulation of repair plans, which require a large amount of on-site investigation and manual measurement. The efficiency of damage analysis is relatively low, and the accuracy is limited by the professional level and experience of personnel. The evaluation lacks effective quantitative indicators and methods, making it difficult to comprehensively and objectively evaluate the repair effect. Summary of the Invention

[0003] In view of the technical problems of low evaluation efficiency and accuracy in the repair and reinforcement of ancient buildings in the prior art, the present invention provides a digital simulation verification system and method for the repair and reinforcement of ancient buildings to solve these problems.

[0004] The technical solution of the present invention for solving the above technical problems is as follows:

[0005] In a first aspect, the present invention provides a digital simulation verification system for the repair and reinforcement of ancient buildings, wherein the system includes:

[0006] A damage analysis module, configured to perform damage analysis on the three-dimensional model of the first ancient building to generate a damaged identification area.

[0007] A damage feature extraction module, configured to extract the damaged structure type, damaged area material, damaged area shape, and damaged area size of the damaged identification area.

[0008] A process knowledge graph acquisition module, configured to perform a first-level index on the damaged structure type by inputting it into a repair and reinforcement process library to obtain a first repair and reinforcement process knowledge graph, wherein any one of the first repair and reinforcement process knowledge graphs includes a first entity, a second entity, and a third entity. The first entity is a repair and reinforcement process type number, the second entity is a triple, the triple includes a material vector representation, a shape vector representation, and a size vector representation, the third entity is a material usage amount, the initial states of the second entity and the third entity are blank entities, the first entity, the second entity, and the third entity are connected in an undirected manner in sequence, and a preset mapping rule is deployed between the second entity and the third entity.

[0009] A material usage prediction module, configured to, when the number of the first repair and reinforcement process knowledge graphs is equal to 1, input the damaged area material, the damaged area shape, and the damaged area size into the second entity to obtain the predicted material usage amount of the third entity.

[0010] The simulation reinforcement module is used to simulate the reinforcement of the three-dimensional model of the first ancient building according to the reinforcement process type number and the predicted consumption of the material, and obtain the three-dimensional model of the second ancient building.

[0011] The reinforcement verification module is used to compare the three-dimensional model of the second ancient building and the three-dimensional model of the first ancient building for reinforcement verification, and obtain the reinforcement feasibility.

[0012] The identification construction module is used to construct a simulation verification passed identification according to the reinforcement process type number and the predicted consumption of the material when the reinforcement feasibility is greater than or equal to the reinforcement feasibility threshold.

[0013] In a second aspect, the present invention provides a digital simulation verification method for the repair and reinforcement of ancient buildings. Among them, the method includes:

[0014] Perform damage analysis on the three-dimensional model of the first ancient building to generate a damaged identification area.

[0015] Extract the damaged structure type, damaged area material, damaged area shape, and damaged area size of the damaged identification area.

[0016] Input the damaged structure type into the reinforcement process library for primary indexing to obtain the first reinforcement process knowledge graph. Any one of the first reinforcement process knowledge graphs includes a first entity, a second entity, and a third entity. The first entity is the reinforcement process type number, the second entity is a triple array, the triple array includes a material vector representation, a shape vector representation, and a size vector representation, the third entity is the material consumption, the initial states of the second entity and the third entity are blank entities, the first entity, the second entity, and the third entity are connected in an undirected manner in sequence, and a preset mapping rule is deployed between the second entity and the third entity.

[0017] When the number of the first reinforcement process knowledge graphs is equal to 1, input the damaged area material, the damaged area shape, and the damaged area size into the second entity to obtain the predicted material consumption of the third entity.

[0018] Simulate the reinforcement of the three-dimensional model of the first ancient building according to the reinforcement process type number and the predicted consumption of the material, and obtain the three-dimensional model of the second ancient building.

[0019] Compare the three-dimensional model of the second ancient building and the three-dimensional model of the first ancient building for reinforcement verification, and obtain the reinforcement feasibility.

[0020] When the reinforcement feasibility is greater than or equal to the reinforcement feasibility threshold, construct a simulation verification passed identification according to the reinforcement process type number and the predicted consumption of the material.

[0021] The beneficial effects of the present invention are as follows: By performing damage analysis on the three-dimensional modeling of the first ancient building, a damaged identification area is generated; information on the damaged structure type, material, shape, and size is extracted; a primary index is performed in the repair and reinforcement process library according to the damaged structure type to obtain the first repair and reinforcement process knowledge graph. This knowledge graph contains a triple array (the second entity) represented by the repair and reinforcement process number (the first entity), material, shape, and size, and the material consumption (the third entity), where the second entity and the third entity are initially blank and are connected by a preset mapping rule. If the uniquely corresponding knowledge graph is indexed, the damaged material, shape, and size are input into the second entity to generate a predicted value of the material consumption of the third entity; based on the repair and reinforcement process number and the predicted material consumption, a simulated repair and reinforcement is performed on the three-dimensional modeling of the first ancient building to generate a three-dimensional modeling of the second ancient building; the first and the second modelings are compared to calculate the feasibility of the repair and reinforcement; if the feasibility reaches the threshold, a simulated verification passed mark is generated, and the repair and reinforcement process number and the material consumption are recorded. The digital simulation verification system and method for the repair and reinforcement of ancient buildings disclosed in the present invention solve the technical problems of low evaluation efficiency and low evaluation accuracy for the repair and reinforcement of ancient buildings, and achieve the technical effects of providing accurate and efficient repair and reinforcement evaluations and improving the accuracy and reliability of the repair and reinforcement. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a schematic structural diagram of the digital simulation verification system for the repair and reinforcement of ancient buildings of the present invention;

[0023] Figure 2 It is a schematic flow diagram of the digital simulation verification method for the repair and reinforcement of ancient buildings of the present invention.

[0024] In the drawings, the components represented by each reference numeral are described as follows:

[0025] Damage analysis module 11, damage feature extraction module 12, process knowledge graph acquisition module 13, material consumption prediction module 14, simulated repair and reinforcement module 15, repair and reinforcement verification module 16, mark construction module 17. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0027] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present invention, "a plurality of" means two or more unless otherwise specifically defined.

[0028] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as more preferred or more advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without the use of these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0029] Embodiment 1:

[0030] As Figure 1 shown, the embodiment of the present invention provides a structural schematic diagram of a digital simulation verification system for the renovation and reinforcement of ancient buildings. Among them, the system includes:

[0031] A damage analysis module 11, configured to perform damage analysis on the three-dimensional model of the first ancient building and generate a damaged identification area.

[0032] Specifically, first, a detailed three-dimensional modeling and damage analysis are performed on the target ancient building, so as to comprehensively identify the damage characteristics of the first ancient building and generate corresponding identification areas. Among them, the damage analysis includes classifying the damage according to the damage type, such as crack areas, spalling areas, deformation areas, biological erosion, etc.

[0033] Specifically, the generated damaged identification area is marked with the nature and magnitude of the damage (area, depth, or volume) to indicate the degree of damage; optionally, the damaged area is marked on the three-dimensional model with different colors or textures.

[0034] In some embodiments, the execution steps of the damage analysis module 11 include:

[0035] Through the client, configure the six views of the first ancient building concept; based on the 3D modeling of the first ancient building, extract the six views of the first ancient building for monitoring; compare the six views of the first ancient building concept and the six views of the first ancient building for monitoring to obtain the six views of the damaged area; perform damaged area modeling according to the six views of the damaged area to obtain a 3D model of the damaged area; identify the 3D modeling of the first ancient building according to the 3D model of the damaged area to generate the damaged identification area.

[0036] Specifically, first, configure the six views of the ancient building concept through the client (including software programs and interactive hardware), including the front view, back view, left view, right view, top view and bottom view. These six views of the concept reflect the ideal state of the ancient building; then, based on the 3D modeling of the first ancient building, obtain the corresponding six views of the first ancient building for monitoring through the same perspective as the above six views of the concept. Among them, the 3D modeling of the first ancient building is a 3D model constructed from the detailed point cloud data and high-resolution photos of the first ancient building obtained by 3D laser scanning and unmanned aerial vehicle oblique photography technology, which reflects the current situation of the ancient building.

[0037] Specifically, compare the six views of the concept and the six views of the monitoring. For example, through image difference technology, identify damaged areas such as cracks on the walls of the ancient building and missing tiles on the roof, and generate the six views of the damaged area; then, according to the comparison result, use 3D modeling software to perform detailed modeling on the damaged area to generate a 3D model of the damaged area. The 3D model of the damaged area details information such as the width and depth of the cracks, and the location and quantity of the missing tiles.

[0038] Furthermore, combine the 3D model of the damaged area and use model editing software on the 3D modeling of the first ancient building to identify the damaged area (such as identification based on coordinate mapping) to generate the damaged identification area. The marked model can be visually presented in the software. Exemplarily, the damaged area is displayed in different colors or transparencies, which is convenient for the repair personnel to intuitively understand the damage situation of the ancient building.

[0039] In some implementation manners, when comparing the six views of the first ancient building concept and the six views of the first ancient building for monitoring to obtain the six views of the damaged area, the execution steps of the damaged analysis module 11 further include:

[0040] Extract the first conceptual view of the first six-view of the ancient building concept; extract the first monitoring view of the first six-view of the ancient building monitoring, wherein the image acquisition perspective and image acquisition parameters of the first monitoring view are the same as those of the first conceptual view; center-align the first monitoring view and the first conceptual view to obtain the non-coincident area and the coincident area of the first conceptual view with respect to the first monitoring view; perform deviation analysis on the first monitoring view and the first conceptual view of the coincident area to obtain the coincident damaged area; add the non-coincident area and the coincident damaged area to the first view damaged area, and add the first view damaged area to the six-view of the damaged area.

[0041] Specifically, first, through the first six-view of the ancient building concept configured by the user terminal and the first six-view of the ancient building monitoring extracted based on 3D modeling, extract any view from the corresponding perspective (such as extracting the front view for both) as the first conceptual view and the first monitoring view, ensuring that both are exactly the same in terms of image acquisition perspective and parameters; then, determine the center points and main feature points of the two views (such as building corner points, boundary lines), and through translation, rotation, and scale transformation, align the center point and main feature points of the first monitoring view with those of the first conceptual view, and then divide the first monitoring view and the first conceptual view into a coincident area (the matching part in the two views) and a non-coincident area (the part that only appears in the first monitoring view or the first conceptual view) according to the alignment result.

[0042] Specifically, mark the area in the first monitoring view that has no corresponding part with the first conceptual view as the missing area; at the same time, perform deviation analysis on the area in the first conceptual view that has no corresponding part with the first monitoring view, which involves comparing features such as pixel brightness, color, and texture between the first monitoring view and the first conceptual view of the coincident area; analyze the differences in geometric attributes such as the shape, edge position, and area of the coincident area; and then mark the part with obvious deviation in the coincident area as the damaged area, including cracks, peeling, deformation, etc.; finally, merge the non-coincident area and the coincident damaged area to form the complete first view damaged area.

[0043] Further, repeat the above process, compare and analyze each view in the first six-view of the ancient building concept and the corresponding monitoring view respectively, generate the damaged area of each view one by one, and integrate the damaged area data of the six views into a complete six-view of the damaged area as the final result of the first ancient building damage assessment.

[0044] Through the above process, the damaged areas of ancient buildings are accurately identified, providing detailed data support and visual reference for the subsequent formulation and implementation of renovation plans. Furthermore, it helps to improve the efficiency and accuracy of the renovation work of ancient buildings, reduce the interference of human factors, and ensure the effective protection of the historical value and cultural connotations of ancient buildings.

[0045] In some implementation manners, deviation analysis is performed on the first monitoring view and the first concept view of the overlapping area to obtain an overlapping damaged area. The execution steps of the damage analysis module 11 further include:

[0046] The first concept view has texture deviation threshold distribution information, color deviation threshold distribution information, and shape deviation threshold distribution information; according to the texture deviation threshold distribution information, the color deviation threshold distribution information, and the shape deviation threshold distribution information, deviation binary conditions for the overlapping area are configured, where the texture deviation threshold, color deviation threshold, and shape deviation threshold in the deviation binary conditions at any position are in a logical AND relationship; based on the deviation binary conditions, deviation analysis is performed on the first monitoring view and the first concept view of the overlapping area to obtain the overlapping damaged area.

[0047] Specifically, the texture deviation threshold distribution information, color deviation threshold distribution information, and shape deviation threshold distribution information in the first concept view are pre-set through expert knowledge or historical data to ensure the adaptability of deviation conditions at different positions; among them, the texture deviation threshold distribution information represents the maximum allowable difference range of texture features in the view; the color deviation threshold distribution information represents the maximum allowable difference range of color features; the shape deviation threshold distribution information represents the maximum allowable difference range of geometric shapes, such as based on the edge contour matching degree or shape feature point deviation.

[0048] Specifically, the deviation binary conditions are logically combined by the deviation thresholds of texture, color, and shape, and all conditions are in a logical "AND" relationship, that is, when the above three are satisfied simultaneously, it is regarded as a non-damaged area; if any one condition is not satisfied, it is marked as a damaged area; for example, at any position, the texture deviation is less than or equal to the texture deviation threshold, the color deviation is less than or equal to the color deviation threshold, and the shape deviation is less than or equal to the shape deviation threshold.

[0049] Through the above precise analysis based on the deviation binary conditions, the damaged areas in the overlapping area can be effectively identified, providing a scientific basis for the monitoring and repair of ancient buildings.

[0050] The damage feature extraction module 12 is used to extract the damaged structure type, damaged area material, damaged area shape, and damaged area size of the damaged identification area.

[0051] Specifically, according to the three-dimensional model of the damaged identification area, the damaged structure type, the material of the damaged area, the shape of the damaged area, and the size of the damaged area are extracted correspondingly. Among them, the damaged structure type is obtained through image recognition or a neural network model, including component cracking, decay, deformation, insect damage, damage to mortise and tenon joints, etc.; the material of the damaged area is obtained through labeled tag information and feature information; the shape of the damaged area is obtained through the edge coordinates and depth data of the damaged area; the size of the damaged area is calculated by column-by-column scanning.

[0052] By obtaining the above-mentioned damaged structure type, the material of the damaged area, the shape of the damaged area, and the size of the damaged area, a detailed quantitative identification of the damaged condition of the ancient building is carried out.

[0053] The craft knowledge graph acquisition module 13 is used to input the damaged structure type into the repair and reinforcement process library for primary indexing to obtain the first repair and reinforcement craft knowledge graph. Among them, any one of the first repair and reinforcement craft knowledge graphs includes a first entity, a second entity, and a third entity. The first entity is the repair and reinforcement craft type number, the second entity is a triple array, the triple array includes a material vector representation, a shape vector representation, and a size vector representation, the third entity is the material consumption, the initial states of the second entity and the third entity are blank entities, the first entity, the second entity, and the third entity are connected undirected in sequence, and a preset mapping rule is deployed between the second entity and the third entity.

[0054] Specifically, the repair and reinforcement process library is a database containing various ancient building repair and reinforcement process knowledge, used to store and retrieve information such as process types, materials, shapes, sizes, etc. related to ancient building repair; in the repair and reinforcement process library, the primary index refers to the index directly stored together with the data, usually used for quickly retrieving the primary key, that is, quickly finding a specific repair and reinforcement process type.

[0055] Specifically, in the repair and reinforcement process, the knowledge graph includes entities and the relationships between entities, used to represent various aspects of the repair and reinforcement process. The entities include the repair and reinforcement process type number, the material vector representation, the shape vector representation, the size vector representation, and the material consumption.

[0056] Specifically, the preset mapping rule refers to the rule used to map one entity to another entity in the knowledge graph. In the repair and reinforcement craft knowledge graph, the preset mapping rule is used to map the material vector representation and the shape vector representation to the material consumption to predict the required material consumption, provide accurate material preparation for the repair work, and reduce resource waste.

[0057] Through the above process, the repair and reinforcement process library and the knowledge graph provide comprehensive and systematic technical support for the repair of ancient buildings, ensuring the scientificity and accuracy of the repair work.

[0058] In some embodiments, the step of constructing the preset mapping rule includes:

[0059] Collect material type record data, shape record data, dimension record data, and material usage identification data according to a preset repair and strengthening process type number. Among them, the material usage identification data is generated by taking the average of multiple material usage record data of multiple groups of material type record data, shape record data, and dimension record data of the same modality; through an encoder, encode the material type record data, the shape record data, and the dimension record data to obtain material vector characterization record data, shape vector characterization record data, and dimension vector characterization record data; input the material vector characterization record data, the shape vector characterization record data, and the dimension vector characterization record data into a feedforward neural network, and perform supervision through the material usage identification data to train the preset mapping rule.

[0060] Specifically, the preset repair and strengthening process type number is a pre-defined number used to identify a specific repair and strengthening process type. Through this preset repair and strengthening process type number, relevant process information can be quickly retrieved from the database.

[0061] Specifically, first, according to the preset repair and strengthening process type number, collect material type record data, shape record data, dimension record data, and material usage identification data related to this type. Among them, the material usage identification data is the average value calculated from multiple groups of data of the same modality. For example, for a specific repair and strengthening process, collect multiple groups of data with the same material type, shape, and dimension, and calculate the average value of the material usage corresponding to these data.

[0062] Specifically, the encoder is used to convert material type, shape, and dimension data into vector characterization record data. This encoder can be a simple linear transformation or a complex neural network layer to obtain a vector form suitable for neural network processing.

[0063] Specifically, construct a feedforward neural network. The network structure includes: an input layer for receiving vector characterization record data of materials, shapes, and dimensions; a hidden layer containing a non-linear activation function (such as ReLU) to learn complex mapping relationships; an output layer for generating corresponding predicted values of material usage; then, concatenate the material vector characterization record data, the shape vector characterization record data, and the dimension vector characterization record data into a single input vector, input it into the neural network, and use the material usage identification data (such as the actual required quantity of wood, the area of bricks and tiles, etc.) as a supervision label for iterative supervised training to minimize the error between the predicted value and the actual material usage identification data and optimize the preset mapping rule.

[0064] By encoding material, shape, and size data into vector representations; using a feedforward neural network to learn the mapping relationship of material usage identification data, and then obtaining a preset mapping rule to achieve efficient and automated optimization of the mapping rule, providing accurate material usage prediction capabilities for the repair of damaged areas in ancient buildings, and reducing resource waste and costs.

[0065] The material usage prediction module 14 is used to, when the number of the first repair process knowledge graphs is equal to 1, input the damaged area material, the damaged area shape, and the damaged area size into the second entity to obtain the predicted material usage of the third entity.

[0066] Specifically, when the number of the first repair process knowledge graphs is equal to 1, it means that there is only one repair process knowledge graph that exactly matches the specific damaged structure type found in the repair process library through the first-level index, that is, the first repair process knowledge graph is unique and accurate. Then, the material type, shape, and size data extracted from the damaged identification area are input into the second entity of the knowledge graph, represented as material vector representation, shape vector representation, and size vector representation. Furthermore, using the preset mapping rule, the input material vector representation, shape vector representation, and size vector representation are processed through a trained feedforward neural network to generate a predicted value of the material usage, and the predicted material usage is stored in the third entity of the knowledge graph to complete the prediction of the material usage.

[0067] Through this process, the uniqueness of the knowledge graph is confirmed, ensuring that the repair process used is unique and accurate, avoiding repair failures caused by improper process selection. Combining with the accurate material usage prediction based on the preset mapping rule, the accurate prediction of the material usage is realized, enabling the repair personnel to prepare the required materials in advance, avoiding material shortages or surpluses, and reducing resource waste and costs.

[0068] The simulated repair module 15 is used to perform simulated repair on the three-dimensional model of the first ancient building according to the repair process type number and the predicted material usage to obtain a three-dimensional model of the second ancient building.

[0069] Through simulated repair, the effect after repair can be predicted before actual repair, helping the repair personnel to discover potential problems in advance and optimize the repair plan.

[0070] Specifically, according to the repair process type number and the predicted material usage, the corresponding repair process type (such as reinforcement, replacement, etc.) is simulated and applied to the specified area through computer three-dimensional modeling technology to achieve simulated repair and reinforcement; then, a three-dimensional model of the overall structure after repair is output, including the shape, material information, and process type of the marked repair area, generating a three-dimensional model of the second ancient building.

[0071] The consolidation verification module 16 is used to perform consolidation verification by comparing the three-dimensional model of the second ancient building and the three-dimensional model of the first ancient building, and obtain the consolidation feasibility.

[0072] Specifically, compare the three-dimensional model after simulated consolidation (the three-dimensional model of the second ancient building) with the original three-dimensional model (the three-dimensional model of the first ancient building), and evaluate the feasibility and effect of the renovation plan, including structural analysis and verification of material usage; Exemplarily, compare the shape deviation ratio of the repaired area with the original model to obtain the geometric matching degree, which is used to ensure that the shape of the repaired area of the second model matches the surrounding structure of the first model; Compare the similarity of material properties such as elastic modulus and density with the original materials to obtain the material compatibility matching degree to verify the compatibility of the materials used in the repaired area with the surrounding area; Through computer simulation analysis methods, obtain the stress analysis results of the repaired area, and compare them with the set goals to obtain the mechanical property matching degree to ensure that the repaired area can withstand the set external stress.

[0073] Furthermore, based on the weighting method, comprehensively consider the above geometric matching degree, material compatibility matching degree and mechanical property matching degree to obtain the consolidation feasibility, which is used to quantitatively represent the feasibility and effect of the renovation plan.

[0074] The identification construction module 17 is used to construct a simulation verification passed identification according to the consolidation process type number and the predicted material usage when the consolidation feasibility is greater than or equal to the consolidation feasibility threshold.

[0075] Specifically, when the consolidation feasibility reaches or exceeds the preset threshold, it can be considered that the current consolidation plan and the predicted material usage are reasonable, and a renovated ancient building that meets the expected goals can be obtained and can be actually applied.

[0076] In some embodiments, the system further includes a map scale control unit, which is used for:

[0077] When the number of the first consolidation process knowledge maps is greater than 1, input the damaged area material, the damaged area shape, and the damaged area size into the consolidation process library for secondary indexing to obtain the second consolidation process knowledge map; Take the intersection map of the first consolidation process knowledge map and the second consolidation process knowledge map to obtain the third consolidation process knowledge map; When the number of the third consolidation process knowledge maps is equal to 1, input the damaged area material, the damaged area shape, and the damaged area size into the second entity execution process; When the number of the first consolidation process knowledge maps is equal to 0, or the number of the third consolidation process knowledge maps is equal to 0, generate a consolidation process null value alarm signal to the user terminal.

[0078] Specifically, in the repair process library, when the first-level index returns multiple results, that is, when the number of the first repair process knowledge graphs is greater than 1, more detailed conditions (such as the material, shape, and size of the damaged area) are further used for the second-level index to obtain a more accurate second repair process knowledge graph; then, the first repair process knowledge graph is compared with the second repair process knowledge graph to find the knowledge graph that satisfies both index conditions and obtain the third repair process knowledge graph.

[0079] Specifically, determine the number of the third repair process knowledge graphs. If the number of the third repair process knowledge graphs is equal to 1, it means that the uniquely matched repair process has been found. At this time, the material, shape, and size data of the damaged area are input into the second entity of the knowledge graph, and a preset process is executed, such as material usage prediction, etc.

[0080] Specifically, if the number of results of the first-level index or the intersection graph is 0, or the number of the third repair process knowledge graphs is equal to 0, it means that no matching repair process has been found. An alarm signal with a null value of the repair process is generated to the user terminal, prompting the user to perform corresponding operations, such as checking the accuracy of the input information or supplementing the data of the repair process library.

[0081] In the above steps, through the acquisition of the second-level index and the intersection graph, a more accurate match for the repair process suitable for a specific damaged situation can be obtained, improving the pertinence and effectiveness of the repair plan; when no matching repair process is found, an alarm signal is sent to the user terminal in a timely manner to help the user discover and solve problems in a timely manner, further ensuring the smooth progress of the repair work.

[0082] In some embodiments, the execution steps of the graph scale control unit further include:

[0083] When the number of the third repair process knowledge graphs is greater than 1, the third repair process knowledge graphs are sent to the user terminal to obtain the user-selected repair process knowledge graph; a process is executed according to the user-selected repair process knowledge graph.

[0084] Specifically, when the number of the third repair process knowledge graphs is greater than 1, all the knowledge graphs are sent to the user terminal for the user to select the most suitable graph from multiple repair process knowledge graphs according to their professional knowledge or preferences.

[0085] Through the above process, the right of choice is given to the user, increasing the user's participation and decision-making power, ensuring that the repair plan better meets the user's actual needs and professional judgment, and at the same time ensuring flexibility through the user's selection when the uniquely best repair process cannot be automatically determined, so as to select the most suitable repair method according to the specific situation.

[0086] In some implementations, the damaged area material, the damaged area shape, and the damaged area size are input into the repair and reinforcement process library for secondary indexing to obtain a second repair and reinforcement process knowledge graph. The execution steps of the graph scale control unit further include:

[0087] Taking the damaged area material, the damaged area shape, and the damaged area size as constraints, perform a trigger frequency statistics on the first repair and reinforcement process types of the first repair and reinforcement process knowledge graph in the repair and reinforcement process library to obtain a first trigger frequency; until taking the damaged area material, the damaged area shape, and the damaged area size as constraints, perform a trigger frequency statistics on the Nth repair and reinforcement process types of the Nth repair and reinforcement process knowledge graph in the repair and reinforcement process library to obtain an Nth trigger frequency; based on the first trigger frequency until the Nth trigger frequency, extract the repair and reinforcement process knowledge graphs in the repair and reinforcement process library whose trigger frequencies are greater than or equal to the trigger frequency threshold, and add them to the second repair and reinforcement process knowledge graph.

[0088] Specifically, first, taking the material, shape, and size of the damaged area as constraints, perform a trigger frequency statistics on each repair and reinforcement process type (from the first to the Nth) in the repair and reinforcement process library. For example, count the number of times each repair and reinforcement process type is triggered under the conditions that the given material type is "wood", the shape is "square", and the size is "1m×1m"; then, based on the statistically obtained trigger frequencies, extract the repair and reinforcement process knowledge graphs in the repair and reinforcement process library whose trigger frequencies are greater than or equal to the preset threshold. These knowledge graphs can be considered as repair and reinforcement processes highly relevant to the given damaged area; finally, add the selected repair and reinforcement process knowledge graphs to the second repair and reinforcement process knowledge graph, so as to provide a more accurate reference for the subsequent formulation of the repair plan.

[0089] In summary, the digital simulation and verification system for the repair and reinforcement of ancient buildings provided by the present invention has the following technical effects:

[0090] By performing damage analysis on the 3D model of the first ancient building, a damaged identification area is generated; the damaged structure type, material, shape, and size information are extracted; based on the damaged structure type, a primary index is conducted in the restoration process library to obtain the first restoration process knowledge graph. This knowledge graph includes a triple array (the second entity) represented by the restoration process number (the first entity), material, shape, and size, and the material consumption (the third entity), where the second entity and the third entity are initially blank and are connected by a preset mapping rule. If the uniquely corresponding knowledge graph is indexed, the damaged material, shape, and size are input into the second entity to generate a predicted value of the material consumption of the third entity; based on the restoration process number and the predicted material consumption, a simulated restoration is performed on the 3D model of the first ancient building to generate a 3D model of the second ancient building; by comparing the first and the second models, the restoration feasibility is calculated; if the feasibility reaches the threshold, a simulated verification passed flag is generated, and the restoration process number and the material consumption are recorded, thereby achieving the technical effects of providing accurate and efficient renovation and reinforcement evaluation and improving the accuracy and reliability of renovation.

[0091] Embodiment 2:

[0092] Figure 2 It is a schematic flow chart of the digital simulation verification method for the renovation and reinforcement of ancient buildings in the present invention. For example, Figure 1 In the present invention, the structural schematic diagram of the digital simulation verification system for the renovation and reinforcement of ancient buildings is used to implement the process as Figure 2 shown.

[0093] Based on the same concept as the digital simulation verification system for the renovation and reinforcement of ancient buildings in the above embodiment, the digital simulation verification method for the renovation and reinforcement of ancient buildings provided by the present invention further includes:

[0094] Perform damage analysis on the 3D model of the first ancient building to generate a damaged identification area.

[0095] Extract the damaged structure type, damaged area material, damaged area shape, and damaged area size of the damaged identification area.

[0096] Input the damaged structure type into the restoration process library for primary indexing to obtain the first restoration process knowledge graph. Among them, any one of the first restoration process knowledge graphs includes a first entity, a second entity, and a third entity. The first entity is the restoration process type number, the second entity is a triple array, the triple array includes a material vector representation, a shape vector representation, and a size vector representation, the third entity is the material consumption, the initial states of the second entity and the third entity are blank entities, the first entity, the second entity, and the third entity are connected in an undirected manner in sequence, and a preset mapping rule is deployed between the second entity and the third entity.

[0097] When the number of the first consolidation process knowledge graphs is equal to 1, input the damaged area material, the damaged area shape, and the damaged area size into the second entity to obtain the predicted material consumption of the third entity.

[0098] Perform simulated consolidation on the first three-dimensional modeling of the ancient building according to the consolidation process type number and the predicted material consumption to obtain the second three-dimensional modeling of the ancient building.

[0099] Compare the second three-dimensional modeling of the ancient building and the first three-dimensional modeling of the ancient building for consolidation calculation to obtain the consolidation feasibility.

[0100] When the consolidation feasibility is greater than or equal to the consolidation feasibility threshold, construct a simulation verification passed flag according to the consolidation process type number and the predicted material consumption.

[0101] In some embodiments, perform damage analysis on the first three-dimensional modeling of the ancient building to generate a damaged identification area, including:

[0102] Configure the six concept views of the first ancient building through the user terminal.

[0103] Extract the six monitoring views of the first ancient building based on the first three-dimensional modeling of the ancient building.

[0104] Compare the six concept views of the first ancient building and the six monitoring views of the first ancient building to obtain the six views of the damaged area.

[0105] Perform damaged area modeling according to the six views of the damaged area to obtain a three-dimensional model of the damaged area.

[0106] Mark the first three-dimensional modeling of the ancient building according to the three-dimensional model of the damaged area to generate the damaged identification area.

[0107] In some implementation manners, comparing the six concept views of the first ancient building and the six monitoring views of the first ancient building to obtain the six views of the damaged area includes:

[0108] Extract the first concept view of the six concept views of the first ancient building.

[0109] Extract the first monitoring view of the six monitoring views of the first ancient building, where the first monitoring view has the same image acquisition perspective and image acquisition parameters as the first concept view.

[0110] Align the centers of the first monitoring view and the first concept view to obtain the non-coincident area and the coincident area of the first concept view with the first monitoring view.

[0111] Perform deviation analysis on the first monitoring view and the first concept view of the overlapping region to obtain an overlapping damaged region.

[0112] Add the non - overlapping region and the overlapping damaged region to the first view damaged region, and add the first view damaged region to the six - view damaged region.

[0113] Further, performing deviation analysis on the first monitoring view and the first concept view of the overlapping region to obtain an overlapping damaged region includes:

[0114] The first concept view has texture deviation threshold distribution information, color deviation threshold distribution information, and shape deviation threshold distribution information.

[0115] Configure the deviation binary condition for the overlapping region according to the texture deviation threshold distribution information, the color deviation threshold distribution information, and the shape deviation threshold distribution information, where the texture deviation threshold, color deviation threshold, and shape deviation threshold in the deviation binary condition at any position are in a logical AND relationship.

[0116] Based on the deviation binary condition, perform deviation analysis on the first monitoring view and the first concept view of the overlapping region to obtain the overlapping damaged region. Perform deviation analysis on the first monitoring view and the first concept view of the overlapping region to obtain the overlapping damaged region.

[0117] In some embodiments, the construction steps of the preset mapping rule include:

[0118] According to the preset repair process type number, collect material type record data, shape record data, dimension record data, and material usage identification data, where the material usage identification data is generated by taking the average of multiple material usage record data of multiple groups of the same - modality material type record data, shape record data, and dimension record data.

[0119] Encode the material type record data, the shape record data, and the dimension record data through an encoder to obtain material vector representation record data, shape vector representation record data, and dimension vector representation record data.

[0120] Input the material vector representation record data, the shape vector representation record data, and the dimension vector representation record data into a feed - forward neural network, and perform supervision through the material usage identification data to train the preset mapping rule.

[0121] Further, the method further includes:

[0122] When the number of the first repair process knowledge graphs is greater than 1, input the damaged area material, the damaged area shape, and the damaged area size into the repair process library for secondary indexing to obtain a second repair process knowledge graph.

[0123] Take the intersection graph of the first repair process knowledge graph and the second repair process knowledge graph to obtain a third repair process knowledge graph.

[0124] When the number of the third repair process knowledge graphs is equal to 1, input the damaged area material, the damaged area shape, and the damaged area size into the second entity execution process.

[0125] When the number of the first repair process knowledge graphs is equal to 0, or the number of the third repair process knowledge graphs is equal to 0, generate a repair process null value alarm signal to the client.

[0126] In some implementation manners, the method further includes:

[0127] When the number of the third repair process knowledge graphs is greater than 1, send the third repair process knowledge graphs to the client to obtain a user-selected repair process knowledge graph.

[0128] Execute a process according to the user-selected repair process knowledge graph.

[0129] In some implementation manners, inputting the damaged area material, the damaged area shape, and the damaged area size into the repair process library for secondary indexing to obtain a second repair process knowledge graph includes:

[0130] Taking the damaged area material, the damaged area shape, and the damaged area size as constraints, perform a trigger frequency statistics on the first repair process types of the first repair process knowledge graphs in the repair process library to obtain a first trigger frequency.

[0131] Until taking the damaged area material, the damaged area shape, and the damaged area size as constraints, perform a trigger frequency statistics on the Nth repair process types of the Nth repair process knowledge graphs in the repair process library to obtain an Nth trigger frequency.

[0132] Based on the first trigger frequency until the Nth trigger frequency, extract the repair process knowledge graphs with a trigger frequency greater than or equal to a trigger frequency threshold from the repair process library and add them to the second repair process knowledge graph.

[0133] It should be noted that in the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailedly described in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0134] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0135] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0136] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that realize the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0137] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0138] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic inventive concept.

[0139] Obviously, those skilled in the art can make various changes and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. The digital simulation verification system for the repair and reinforcement of ancient buildings is characterized by: include: A damage analysis module is used to perform damage analysis on the three-dimensional modeling of the first ancient building and generate a damage identification area; A damage feature extraction module, used to extract the damage structure type, damage area material, damage area shape, and damage area size of the damage identification area; A process knowledge graph acquisition module is used to input the damaged structure type into the repair process library for primary indexing to obtain a first repair process knowledge graph, wherein any one of the first repair process knowledge graphs includes a first entity, a second entity and a third entity, the first entity is a repair process type number, the second entity is a ternary array, the ternary array includes a material vector representation, a shape vector representation and a size vector representation, the third entity is a material usage, the initial states of the second entity and the third entity are blank entities, the first entity, the second entity and the third entity are undirectedly connected in sequence, and a preset mapping rule is deployed between the second entity and the third entity; A material usage prediction module, used for inputting the damaged area material, the damaged area shape, and the damaged area size into the second entity when the number of the first fixing process knowledge graph is equal to 1, to obtain the predicted material usage of the third entity; A simulation repair module, used for performing simulation repair on the first ancient building three-dimensional model according to the repair process type number and the predicted material usage to obtain a second ancient building three-dimensional model; A repair and verification module is used to compare the second ancient building three-dimensional modeling and the first ancient building three-dimensional modeling to perform repair and verification to obtain the repair feasibility; An identification construction module is used to construct a simulation verification pass identification according to the fixing process type number and the predicted material usage when the fixing feasibility is greater than or equal to the fixing feasibility threshold.

2. The system according to claim 1, characterized in that Perform damage analysis on the 3D model of the first ancient building and generate a damage identification area. The execution steps include: Through the user end, configure the first ancient building concept six views; Based on the three-dimensional modeling of the first ancient building, extracting six monitoring views of the first ancient building; Comparing the first six conceptual views of the ancient building with the first six monitoring views of the ancient building to obtain six views of the damaged area; Modeling the damaged area according to the six views of the damaged area to obtain a three-dimensional model of the damaged area; The first ancient building three-dimensional model is marked according to the three-dimensional model of the damaged area to generate the damaged marked area.

3. The system according to claim 2, characterized in that Comparing the first six views of the ancient building concept with the first six views of the ancient building monitoring to obtain six views of the damaged area, the execution steps include: Extracting a first conceptual view of the six conceptual views of the first ancient building; Extracting a first monitoring view of the six monitoring views of the first ancient building, wherein the first monitoring view has the same image acquisition viewing angle and image acquisition parameters as the first conceptual view; Performing center alignment on the first monitoring view and the first conceptual view to obtain a non-overlapping area and an overlapping area in the first conceptual view with the first monitoring view; Performing deviation analysis on the first monitoring view and the first conceptual view of the overlapping area to obtain an overlapping damaged area; The non-overlapping area and the overlapping damaged area are added into the first view damaged area, and the first view damaged area is added into the damaged area six views.

4. The system according to claim 3, characterized in that Performing deviation analysis on the first monitoring view and the first conceptual view of the overlapping area to obtain an overlapping damaged area includes: The first concept view has texture deviation threshold distribution information, color deviation threshold distribution information and shape deviation threshold distribution information; According to the texture deviation threshold distribution information, the color deviation threshold distribution information and the shape deviation threshold distribution information, a deviation binary division condition of the overlapped area is configured, wherein the texture deviation threshold, the color deviation threshold and the shape deviation threshold in the deviation binary division condition at any position are in a logical AND relationship; Based on the deviation binary condition, a deviation analysis is performed on the first monitoring view and the first conceptual view of the overlapped area to obtain the overlapped damaged area.

5. The system according to claim 1, wherein: The preset mapping rules are constructed by the following steps: According to the preset fixing process type number, material type record data, shape record data, size record data and material usage identification data are collected, wherein the material usage identification data is generated by taking the average of multiple material usage record data of multiple groups of material type record data, shape record data and size record data of the same mode; Encoding the material type record data, the shape record data, and the size record data through an encoder to obtain material vector representation record data, shape vector representation record data, and size vector representation record data; The material vector representation record data, shape vector representation record data and size vector representation record data are spliced ​​into a single input vector, input into the neural network, and the material usage identification data is used as the supervision label for iterative supervision training to obtain the preset mapping rules.

6. The system according to claim 1, characterized in that The system also includes a map scale control unit for: When the number of the first repair process knowledge graphs is greater than 1, the damaged area material, the damaged area shape, and the damaged area size are input into the repair process library for secondary indexing to obtain a second repair process knowledge graph; Taking the intersection graph of the first fixing process knowledge graph and the second fixing process knowledge graph to obtain a third fixing process knowledge graph; When the number of the third fixing process knowledge graph is equal to 1, the damaged area material, the damaged area shape, and the damaged area size are input into the second entity execution process; When the number of the first fixing process knowledge graphs is equal to 0, or the number of the third fixing process knowledge graphs is equal to 0, a fixing process null value alarm signal is generated to the user end.

7. The system according to claim 6, characterized in that The execution steps of the atlas scale control unit also include: When the number of the third fixing process knowledge graphs is greater than 1, the third fixing process knowledge graph is sent to the user end to obtain the fixing process knowledge graph selected by the user; The process is executed according to the repair process knowledge graph selected by the user.

8. The system according to claim 6, characterized in that The damaged area material, the damaged area shape, and the damaged area size are input into the repair process library for secondary indexing to obtain a second repair process knowledge graph, and the execution steps include: Taking the damaged area material, the damaged area shape and the damaged area size as constraints, performing trigger frequency statistics on the first fixing process type of the first fixing process knowledge graph of the fixing process library to obtain a first trigger frequency; Until the Nth repair process type of the Nth repair process knowledge graph of the repair process library is subjected to trigger frequency statistics based on the damaged area material, the damaged area shape, and the damaged area size, to obtain the Nth trigger frequency; Based on the first trigger frequency to the Nth trigger frequency, a repair process knowledge graph having a trigger frequency greater than or equal to a trigger frequency threshold is extracted from the repair process library and added into the second repair process knowledge graph.

9. A digital simulation verification method for the repair and reinforcement of ancient buildings, characterized in that: The method is applied to the digital simulation verification system for the repair and reinforcement of ancient buildings according to any one of claims 1 to 8, and the method comprises: Conduct damage analysis on the three-dimensional model of the first ancient building and generate damage identification areas; Extracting the damaged structure type, damaged area material, damaged area shape, and damaged area size of the damaged identification area; Input the damaged structure type into the repair process library for primary indexing to obtain a first repair process knowledge graph, wherein any one of the first repair process knowledge graphs includes a first entity, a second entity and a third entity, the first entity is a repair process type number, the second entity is a ternary array, the ternary array includes a material vector representation, a shape vector representation and a size vector representation, the third entity is a material usage, the initial states of the second entity and the third entity are blank entities, the first entity, the second entity and the third entity are undirectedly connected in sequence, and a preset mapping rule is deployed between the second entity and the third entity; When the number of the first fixing process knowledge graphs is equal to 1, the damaged area material, the damaged area shape, and the damaged area size are input into the second entity to obtain the predicted material usage of the third entity; Performing simulated repair on the first ancient building three-dimensional model according to the repair process type number and the predicted material usage to obtain a second ancient building three-dimensional model; Comparing the second three-dimensional modeling of the ancient building with the first three-dimensional modeling of the ancient building to perform repair verification calculation and obtain the repair feasibility; When the feasibility of the repair is greater than or equal to the threshold value of the feasibility of the repair, a simulation verification pass mark is constructed according to the repair process type number and the predicted material usage.

Images