CN-117705941-B - Stone relic damage detection and prediction method, device and storable medium

CN117705941BCN 117705941 BCN117705941 BCN 117705941BCN-117705941-B

Abstract

The invention discloses a method, a device and a storage medium for detecting and predicting stone relic damage, wherein the method comprises the steps of carrying out ultrasonic signal detection, physicochemical property parameter detection and image detection on stone relics to be detected to obtain corresponding ultrasonic detection signal data, physicochemical property parameter data and relic image data, constructing and training a damage evaluation model, inputting the preprocessed ultrasonic detection signal data and the pre-processed relic image data into the damage evaluation model to process to obtain a corresponding current damage degree evaluation result and the like.

Inventors

ZHANG LONGYUN
Xiong Xiaoyuan

Assignees

山东大学

Dates

Publication Date: 20260512
Application Date: 20231215

Claims (8)

1. The stone relic damage detection and prediction method is characterized by comprising the following steps of: Carrying out ultrasonic signal detection, physicochemical property parameter detection and image detection on stone relics to be detected to obtain corresponding ultrasonic detection signal data, physicochemical property parameter data and relic image data; preprocessing the ultrasonic detection signal data and the cultural relic image data; Constructing and training a damage evaluation model, and inputting the preprocessed ultrasonic detection signal data and the preprocessed cultural relic image data into the damage evaluation model for processing to obtain a corresponding current damage degree evaluation result; and acquiring the environmental data of the stone relic to be detected, processing the environmental data of the stone relic to be detected, combining the environmental data of the ultrasonic detection signal data, the physicochemical property parameter data and the environmental parameter data of the environment, and judging whether damage prediction is needed according to the processing result.
2. The method for detecting and predicting stone relic damage according to claim 1, wherein the specific process of constructing and training the damage evaluation model comprises the following steps: Acquiring historical stone cultural relic damage type data and corresponding damage characteristic data, processing the damage type data and the corresponding damage characteristic data, and dividing the damage type data and the corresponding damage characteristic data into a training set and a testing set according to a certain proportion; Constructing a damage evaluation model, training the damage evaluation model by using the training set, stopping training when the model loss is minimum, and testing the damage evaluation model by using the testing set; and outputting the damage evaluation model at the moment after the test is finished.
3. The method for detecting and predicting stone relic damage according to claim 1, wherein the specific processing procedure for preprocessing the ultrasonic detection signal data and the relic image data comprises: sequentially filtering and linearly calculating and converting the ultrasonic detection signal data to obtain a corresponding longitudinal wave speed ratio fitting model; and carrying out gray scale, filtering and enhancement treatment on the cultural relic image data to obtain corresponding damage characteristics.
4. The method for detecting and predicting stone relic damage according to claim 1, wherein the physicochemical property parameter data includes porosity data and water content data of a stone temperature to be detected, and the environmental data includes humidity data and temperature data.
5. The method for detecting and predicting stone relic damage according to claim 1, wherein the specific process of processing the environmental data of the stone relic to be detected, the ultrasonic detection signal data, the physicochemical property parameter data, and the environmental parameter data of the environment includes: Normalizing the environmental data of the stone relics to be detected, the ultrasonic detection signal data, the physicochemical property parameter data and the environmental parameter data of the environment; Constructing a linear discrimination model, and substituting the environment data of the stone relic to be detected, the ultrasonic detection signal data, the physicochemical property parameter data and the environment parameter data of the environment into the linear discrimination model after normalization treatment; And when the judging result is greater than or equal to a preset judging threshold value, carrying out damage prediction, otherwise, not carrying out damage prediction.
6. The method for detecting and predicting stone relic damage according to claim 5, wherein the specific process of damage prediction comprises: Constructing a prediction model, and inputting the environment data of the stone relic to be detected, the ultrasonic detection signal data, the physicochemical property parameter data and the environment parameter data of the environment to be detected which are subjected to normalization processing into the prediction model for processing to obtain a first predicted arrival time; establishing a three-dimensional simulation model of the stone relic to be detected by utilizing the relic image data and the physicochemical property parameter data; constructing a simulation environment model, inputting environment data of the stone relics to be detected into the simulation environment model, and applying the simulation environment model to the three-dimensional simulation model; Acquiring images corresponding to the three-dimensional simulation model according to a preset time interval, preprocessing the images, and inputting the preprocessed images into the damage evaluation model for processing to obtain a simulation damage degree evaluation result; comparing the current damage degree evaluation result with the simulated damage degree evaluation result, and determining the time at the moment as a second expected arrival time when the comparison result is larger than a preset threshold value; And weighting the first expected arrival time and the second expected arrival time to obtain comprehensive expected arrival time, and completing prediction.
7. A detection apparatus using the stone relic damage detection and prediction method as claimed in any one of claims 1 to 6, characterized by comprising: The data acquisition module is used for carrying out ultrasonic signal detection, physicochemical property parameter detection and image detection on the stone relics to be detected to obtain corresponding ultrasonic detection signal data, physicochemical property parameter data and relic image data; the preprocessing module is used for preprocessing the ultrasonic detection signal data and the cultural relic image data; The processing module is used for constructing and training a damage evaluation model, inputting the preprocessed ultrasonic detection signal data and the preprocessed cultural relic image data into the damage evaluation model for processing, and obtaining a corresponding current damage degree evaluation result; The prediction module is used for acquiring the environmental data of the stone relic to be detected, processing the environmental data of the stone relic to be detected, the ultrasonic detection signal data, the physicochemical property parameter data and the environmental parameter data of the environment, and judging whether damage prediction is needed according to the processing result.
8. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and when executed by a processor, the computer program implements the method for detecting and predicting stone relic damage according to any one of claims 1 to 6.

Description

Stone relic damage detection and prediction method, device and storable medium Technical Field The invention relates to the technical field of cultural relic protection, in particular to a method and a device for detecting and predicting damage of a stone cultural relic and a storable medium. Background At present, stone cultural relics are remains in the historic development process of human beings, are remains or remains with artistic, historical and scientific values, are important physical data for researching ancient social productivity, scientific level and other substance cultural relics, and are important substance carriers for carrying ancient human ideas, beliefs, artistic, chinese and foreign cultural exchanges, national fusion development and other mental cultural relics. However, as time goes by, stone relics will gradually generate damage along with social transition, and the damage degree detection of stone relics in the prior art has the problems of low precision and detection efficiency, and meanwhile, after the stone relics are applied with related protection measures, whether new damage can be generated or not can not be determined, so that the time of possible damage of the relics can not be determined, and preventive and reinforcing repair can not be performed before the damage occurs. Therefore, how to accurately evaluate the damage degree of stone relics and judge whether damage prediction is needed or not is a problem to be solved by those skilled in the art. Disclosure of Invention In view of the above, the present invention provides a method, an apparatus and a storage medium for detecting and predicting damage of a stone relic, which can implement nondestructive detection on the stone relic by using ultrasonic waves, and judge whether damage prediction is required, if so, the damage prediction is required to be completed according to various types of data, thereby performing preventive repair on the relic. In order to achieve the above purpose, the present invention adopts the following technical scheme: A stone relic damage detection and prediction method comprises the following steps: Carrying out ultrasonic signal detection, physicochemical property parameter detection and image detection on stone relics to be detected to obtain corresponding ultrasonic detection signal data, physicochemical property parameter data and relic image data; preprocessing the ultrasonic detection signal data and the cultural relic image data; Constructing and training a damage evaluation model, and inputting the preprocessed ultrasonic detection signal data and the preprocessed cultural relic image data into the damage evaluation model for processing to obtain a corresponding current damage degree evaluation result; and acquiring the environmental data of the stone relic to be detected, processing the environmental data of the stone relic to be detected, combining the environmental data of the ultrasonic detection signal data, the physicochemical property parameter data and the environmental parameter data of the environment, and judging whether damage prediction is needed according to the processing result. Preferably, the specific process of constructing and training the damage evaluation model includes: Acquiring historical stone cultural relic damage type data and corresponding damage characteristic data, processing the damage type data and the corresponding damage characteristic data, and dividing the damage type data and the corresponding damage characteristic data into a training set and a testing set according to a certain proportion; Constructing a damage evaluation model, training the damage evaluation model by using the training set, stopping training when the model loss is minimum, and testing the damage evaluation model by using the testing set; and outputting the damage evaluation model at the moment after the test is finished. Preferably, the specific processing procedure for preprocessing the ultrasonic detection signal data and the cultural relic image data includes: sequentially filtering and linearly calculating and converting the ultrasonic detection signal data to obtain a corresponding longitudinal wave speed ratio fitting model; and carrying out gray scale, filtering and enhancement treatment on the cultural relic image data to obtain corresponding damage characteristics. Preferably, the physicochemical property parameter data comprise porosity data and water content data of the temperature of the stone to be detected, and the environmental data comprise humidity data and temperature data. Preferably, the specific process of processing by combining the environmental data of the stone relic to be detected, the ultrasonic detection signal data, the physicochemical property parameter data and the environmental parameter data of the environment includes: Normalizing the environmental data of the stone relics to be detected, the ultrasonic detection signal data, the physicochemical