A stone cultural relic damage detection and prediction method, device and storable medium
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANDONG UNIV
- Filing Date
- 2023-12-15
- Publication Date
- 2026-05-12
AI Technical Summary
Existing technologies for detecting damage to stone cultural relics have low accuracy and efficiency, and cannot predict the time of damage, thus making preventative repairs impossible.
采用超声波信号检测、理化性质参数检测和图像检测，结合环境数据，通过构建损伤评价模型进行损伤程度评价和预测，利用超声波实现无损检测，判断是否需要进行损伤预测和修补。
It enables accurate detection and prediction of damage to stone cultural relics, allowing for preventative repairs before damage occurs, thus improving detection accuracy and efficiency.
Smart Images
Figure CN117705941B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of cultural relic protection technology, and more specifically to a method, device, and storage medium for detecting and predicting damage to stone cultural relics. Background Technology
[0002] Currently, stone artifacts refer to relics or sites left behind in the course of human history, made or constructed from natural stone, and possessing artistic, historical, and scientific value. They are important material evidence for studying the material civilization of ancient societies, such as productivity and scientific levels, and are also important material carriers of the spiritual civilization of ancient humans, including their thoughts, beliefs, art, cultural exchanges between China and foreign countries, and the integration and development of ethnic groups.
[0003] However, over time, stone artifacts will gradually suffer damage due to social changes. Existing technologies for detecting the degree of damage to stone artifacts have problems with low accuracy and efficiency. Furthermore, after relevant protective measures are applied to stone artifacts, it is impossible to determine whether new damage will necessarily occur, and therefore it is impossible to determine when the artifacts may be damaged, and preventive and reinforcing repairs cannot be carried out before damage occurs.
[0004] Therefore, how to accurately assess the degree of damage to stone cultural relics and determine whether damage prediction is necessary is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention
[0005] In view of this, the present invention provides a method, device and storage medium for detecting and predicting damage to stone cultural relics. By using ultrasonic waves to perform non-destructive testing on stone cultural relics, it can simultaneously determine whether damage prediction is needed. If so, damage prediction can be completed based on multiple types of data, thereby enabling preventive repair of the cultural relics.
[0006] To achieve the above objectives, the present invention adopts the following technical solution:
[0007] A method for detecting and predicting damage to stone cultural relics includes the following steps:
[0008] Ultrasonic signal detection, physicochemical property parameter detection, and image detection are performed on the stone cultural relic to be tested, and the corresponding ultrasonic detection signal data, physicochemical property parameter data, and cultural relic image data are obtained.
[0009] The ultrasonic detection signal data and the artifact image data are preprocessed.
[0010] A damage assessment model is constructed and trained. The preprocessed ultrasonic detection signal data and the cultural relic image data are input into the damage assessment model for processing to obtain the corresponding current damage assessment result.
[0011] The environmental data of the stone artifact to be tested is obtained, and the environmental data, ultrasonic detection signal data, physicochemical property parameter data, and environmental parameter data of the environment are processed. Based on the processing results, it is determined whether damage prediction is required.
[0012] Preferably, the specific process for constructing and training the damage assessment model includes:
[0013] Data on damage types of historical stone artifacts and their corresponding damage characteristics are obtained. After processing the damage type data and the corresponding damage characteristic data, they are divided into training set and test set according to a certain ratio.
[0014] Construct a damage assessment model, train the damage assessment model using the training set, stop training when the model loss is minimized, and test the damage assessment model using the test set.
[0015] After the test is completed, the damage evaluation model at this point is output.
[0016] Preferably, the specific preprocessing steps for the ultrasonic detection signal data and the artifact image data include:
[0017] After filtering and linear calculation transformation of the ultrasonic detection signal data in sequence, the corresponding longitudinal wave velocity ratio fitting model is obtained;
[0018] The image data of the cultural relics is subjected to grayscale, filtering, and enhancement processing to obtain the corresponding damage features.
[0019] Preferably, the physicochemical property parameters include porosity data and moisture content data of the stone to be tested, and the environmental data includes humidity data and temperature data.
[0020] Preferably, the specific process of processing the environmental data of the stone artifact to be tested, the ultrasonic detection signal data, the physicochemical property parameter data, and the environmental parameter data of the environment includes:
[0021] The environmental data of the stone artifact to be tested, the ultrasonic detection signal data, the physicochemical property parameter data, and the environmental parameter data of the environment are normalized.
[0022] A linear discriminant model is constructed by substituting the normalized environmental data of the stone artifact to be detected, the ultrasonic detection signal data, the physicochemical property parameter data, and the environmental parameter data of the environment into the linear discriminant model.
[0023] Damage prediction is performed when the judgment result is greater than or equal to the preset judgment threshold; otherwise, damage prediction is not performed.
[0024] Preferably, the specific processing steps for damage prediction include:
[0025] A prediction model is constructed by inputting the normalized environmental data of the stone artifact to be detected, the ultrasonic detection signal data, the physicochemical property parameter data, and the environmental parameter data of the environment into the prediction model for processing, and obtaining the first estimated arrival time.
[0026] A three-dimensional simulation model of the stone artifact to be tested is established using the artifact image data and the physicochemical property parameter data.
[0027] A simulation environment model is constructed, and the environmental data of the stone artifact to be detected is input into the simulation environment model, and the simulation environment model is applied to the three-dimensional simulation model;
[0028] Images corresponding to the three-dimensional simulation model are collected at preset time intervals. After preprocessing, the images are input into the damage evaluation model for processing to obtain the simulated damage degree evaluation result.
[0029] By comparing the current damage assessment result with the simulated damage assessment result, when the comparison result is greater than a preset threshold, the time at this time is determined as the second estimated arrival time.
[0030] The first and second estimated arrival times are weighted to obtain a comprehensive estimated arrival time, thus completing the prediction.
[0031] The present invention also provides a detection device utilizing the method for detecting and predicting damage to stone cultural relics as described in any one of the above claims, comprising:
[0032] The data acquisition module is used to perform ultrasonic signal detection, physicochemical property parameter detection, and image detection on the stone artifacts to be tested, and to obtain the corresponding ultrasonic detection signal data, physicochemical property parameter data, and artifact image data.
[0033] The preprocessing module is used to preprocess the ultrasonic detection signal data and the cultural relic image data;
[0034] The processing module is used to build and train the damage assessment model. It inputs the preprocessed ultrasonic detection signal data and the cultural relic image data into the damage assessment model for processing, and obtains the corresponding current damage assessment result.
[0035] The prediction module is used to acquire environmental data of the stone artifact to be tested, process the environmental data of the stone artifact to be tested, the ultrasonic detection signal data, the physicochemical property parameter data, and the environmental parameter data of the environment, and determine whether damage prediction is needed based on the processing results.
[0036] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for detecting and predicting damage to stone cultural relics as described in any of the preceding claims.
[0037] As can be seen from the above technical solution, compared with the prior art, the present invention provides a method, device, and storage medium for detecting and predicting damage to stone cultural relics. It acquires ultrasonic detection signal data, physicochemical property parameter data, image data of the stone cultural relic to be tested, and environmental data of its surrounding environment. The pre-processed ultrasonic detection signal data and image data are input into a damage evaluation model for processing to obtain the corresponding current damage level evaluation result. The normalized environmental data, ultrasonic detection signal data, physicochemical property parameter data, and environmental parameter data of the surrounding environment are substituted into a linear discriminant model. Based on the calculation results of the discriminant model, it is determined whether damage prediction is needed. If so, subsequent damage prediction is performed. Through the above process, non-destructive testing of stone cultural relics using ultrasound can be achieved while simultaneously determining whether damage prediction is needed. If so, damage prediction is completed based on multiple types of data, enabling preventative repair of the cultural relics. Attached Figure Description
[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.
[0039] Figure 1 The overall flowchart of a method for detecting and predicting damage to stone cultural relics provided by the present invention;
[0040] Figure 2 The present invention provides a structural principle block diagram of a stone artifact damage detection and prediction device. Detailed Implementation
[0041] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0042] See appendix Figure 1 As shown in the figure, an embodiment of the present invention discloses a method for detecting and predicting damage to stone cultural relics, including the following steps:
[0043] Ultrasonic signal detection, physicochemical property parameter detection, and image detection are performed on the stone cultural relic to be tested, and the corresponding ultrasonic detection signal data, physicochemical property parameter data, and cultural relic image data are obtained.
[0044] Preprocessing of ultrasonic detection signal data and artifact image data;
[0045] A damage assessment model is constructed and trained. Preprocessed ultrasonic detection signal data and cultural relic image data are input into the damage assessment model for processing to obtain the corresponding current damage assessment result.
[0046] The environmental data of the stone artifact to be tested is obtained, and then combined with the environmental data of the stone artifact to be tested, ultrasonic detection signal data, physicochemical property parameter data, and environmental parameter data of the environment are processed. Based on the processing results, it is determined whether damage prediction is needed.
[0047] In a specific embodiment, the specific process of constructing and training the damage assessment model includes:
[0048] Data on damage types and corresponding damage characteristics of historical stone artifacts were obtained, and the damage type data and corresponding damage characteristic data were processed and divided into training set and test set according to a certain ratio.
[0049] A damage assessment model is constructed, which may include a multi-feature extraction network, a max pooling network, and a fusion module connected in sequence. The multi-feature extraction network can be an FCN network, and the fusion module can be implemented using convolutional operations, which can better extract damage features and complete data processing.
[0050] The damage assessment model is trained using the training set, and training is stopped when the model loss is minimized. The damage assessment model is then tested using the test set.
[0051] After the test is completed, output the damage assessment model at this time.
[0052] In a specific embodiment, the preprocessing steps for ultrasonic detection signal data and artifact image data include:
[0053] After filtering and linear transformation of the ultrasonic detection signal data, the corresponding longitudinal wave velocity ratio fitting model is obtained.
[0054] The image data of cultural relics is processed by grayscale, filtering and enhancement to obtain the corresponding damage features.
[0055] In one specific embodiment, the physicochemical property parameters include porosity data and moisture content data of the stone to be tested, and the environmental data includes humidity data and temperature data.
[0056] In a specific embodiment, the process of processing the stone artifact to be tested, combining environmental data of its location, ultrasonic detection signal data, physicochemical property parameter data, and environmental parameter data of its environment, includes:
[0057] The environmental data, ultrasonic detection signal data, physicochemical property parameter data, and environmental parameter data of the stone cultural relic to be tested are normalized.
[0058] A linear discriminant model is constructed by substituting the normalized environmental data, ultrasonic detection signal data, physicochemical property parameter data, and environmental parameter data of the environment in which the stone artifact to be tested is located into the linear discriminant model. The linear discriminant model can be obtained by SPSS software and principal component analysis.
[0059] Damage prediction is performed when the judgment result is greater than or equal to the preset judgment threshold; otherwise, damage prediction is not performed.
[0060] In a specific embodiment, the specific processing steps for damage prediction include:
[0061] Construct a prediction model, which can be a BP neural network model;
[0062] The normalized environmental data of the stone artifact to be tested, ultrasonic detection signal data, physicochemical property parameter data, and environmental parameter data of the environment are input into the prediction model for processing to obtain the first estimated arrival time.
[0063] A three-dimensional simulation model of the stone artifact to be tested was established using image data and physicochemical property parameters of the artifact.
[0064] A simulation environment model is constructed. The environmental data of the stone artifact to be detected is input into the simulation environment model, and the simulation environment model is applied to the three-dimensional simulation model.
[0065] Images corresponding to the three-dimensional simulation model are collected at preset time intervals. After preprocessing, the images are input into the damage evaluation model for processing to obtain the simulated damage degree evaluation results.
[0066] By comparing the current damage assessment results with the simulated damage assessment results, when the comparison result is greater than a preset threshold, the time at this point is determined as the second estimated arrival time.
[0067] The first and second estimated arrival times are weighted to obtain the comprehensive estimated arrival time, thus completing the forecast.
[0068] See appendix Figure 2 As shown, this embodiment of the invention also provides a detection device for a method for detecting and predicting damage to stone cultural relics using any of the above embodiments, comprising:
[0069] The data acquisition module is used to perform ultrasonic signal detection, physicochemical property parameter detection, and image detection on the stone artifacts to be tested, and to obtain the corresponding ultrasonic detection signal data, physicochemical property parameter data, and artifact image data.
[0070] The preprocessing module is used to preprocess ultrasonic detection signal data and cultural relic image data;
[0071] The processing module is used to build and train the damage assessment model. It inputs the pre-processed ultrasonic detection signal data and cultural relic image data into the damage assessment model for processing, and obtains the corresponding current damage assessment result.
[0072] The prediction module is used to acquire environmental data of the stone artifact to be tested, process the environmental data of the stone artifact to be tested, ultrasonic detection signal data, physicochemical property parameter data, and environmental parameter data of the environment, and determine whether damage prediction is needed based on the processing results.
[0073] This invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the stone artifact damage detection and prediction method as described in any of the above embodiments.
[0074] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.
[0075] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for detecting and predicting damage to stone cultural relics, characterized in that, Includes the following steps: Ultrasonic signal detection, physicochemical property parameter detection, and image detection are performed on the stone cultural relic to be tested, and the corresponding ultrasonic detection signal data, physicochemical property parameter data, and cultural relic image data are obtained. The ultrasonic detection signal data and the artifact image data are preprocessed. A damage assessment model is constructed and trained. The preprocessed ultrasonic detection signal data and the cultural relic image data are input into the damage assessment model for processing to obtain the corresponding current damage assessment result. The environmental data of the stone artifact to be tested is obtained, and the environmental data, ultrasonic detection signal data, physicochemical property parameter data, and environmental parameter data of the environment are processed. Based on the processing results, it is determined whether damage prediction is required.
2. The method for detecting and predicting damage to stone cultural relics according to claim 1, characterized in that, The specific process of constructing and training a damage assessment model includes: Data on damage types of historical stone artifacts and their corresponding damage characteristics are obtained. After processing the damage type data and the corresponding damage characteristic data, they are divided into training set and test set according to a certain ratio. Construct a damage assessment model, train the damage assessment model using the training set, stop training when the model loss is minimized, and test the damage assessment model using the test set. After the test is completed, the damage evaluation model at this point is output.
3. The method for detecting and predicting damage to stone cultural relics according to claim 1, characterized in that, The specific preprocessing steps for the ultrasonic detection signal data and the artifact image data include: After filtering and linear calculation transformation of the ultrasonic detection signal data in sequence, the corresponding longitudinal wave velocity ratio fitting model is obtained; The image data of the cultural relics is subjected to grayscale, filtering, and enhancement processing to obtain the corresponding damage features.
4. The method for detecting and predicting damage to stone cultural relics according to claim 1, characterized in that, The physicochemical property parameters include porosity data and moisture content data of the stone to be tested, and the environmental data includes humidity data and temperature data.
5. The method for detecting and predicting damage to stone cultural relics according to claim 1, characterized in that, The specific process of processing the environmental data of the stone artifact to be tested, the ultrasonic detection signal data, the physicochemical property parameter data, and the environmental parameter data of the environment includes: The environmental data of the stone artifact to be tested, the ultrasonic detection signal data, the physicochemical property parameter data, and the environmental parameter data of the environment are normalized. A linear discriminant model is constructed by substituting the normalized environmental data of the stone artifact to be detected, the ultrasonic detection signal data, the physicochemical property parameter data, and the environmental parameter data of the environment into the linear discriminant model. Damage prediction is performed when the judgment result is greater than or equal to the preset judgment threshold; otherwise, damage prediction is not performed.
6. The method for detecting and predicting damage to stone cultural relics according to claim 5, characterized in that, The specific process for damage prediction includes: A prediction model is constructed by inputting the normalized environmental data of the stone artifact to be detected, the ultrasonic detection signal data, the physicochemical property parameter data, and the environmental parameter data of the environment into the prediction model for processing, and obtaining the first estimated arrival time. A three-dimensional simulation model of the stone artifact to be tested is established using the artifact image data and the physicochemical property parameter data. A simulation environment model is constructed, and the environmental data of the stone artifact to be detected is input into the simulation environment model, and the simulation environment model is applied to the three-dimensional simulation model; Images corresponding to the three-dimensional simulation model are collected at preset time intervals. After preprocessing, the images are input into the damage evaluation model for processing to obtain the simulated damage degree evaluation result. By comparing the current damage assessment result with the simulated damage assessment result, when the comparison result is greater than a preset threshold, the time at this time is determined as the second estimated arrival time. The first and second estimated arrival times are weighted to obtain a comprehensive estimated arrival time, thus completing the prediction.
7. A detection device utilizing the method for detecting and predicting damage to stone cultural relics according to any one of claims 1-6, characterized in that, include: The data acquisition module is used to perform ultrasonic signal detection, physicochemical property parameter detection, and image detection on the stone artifacts to be tested, and to obtain the corresponding ultrasonic detection signal data, physicochemical property parameter data, and artifact image data. The preprocessing module is used to preprocess the ultrasonic detection signal data and the cultural relic image data; The processing module is used to build and train the damage assessment model. It inputs the preprocessed ultrasonic detection signal data and the cultural relic image data into the damage assessment model for processing, and obtains the corresponding current damage assessment result. The prediction module is used to acquire environmental data of the stone artifact to be tested, process the environmental data of the stone artifact to be tested, the ultrasonic detection signal data, the physicochemical property parameter data, and the environmental parameter data of the environment, and determine whether damage prediction is needed based on the processing results.
8. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the method for detecting and predicting damage to stone cultural relics as described in any one of claims 1 to 6.