Digital twin mapping state prediction method, system, and equipment for physical artworks

Abstract

This invention discloses a method, system, and device for predicting the state of physical artworks using digital twin mapping, relating to the field of data processing technology. The method includes: constructing a digital twin based on exhibition hall architectural information and exhibit display data; synchronously collecting visitor behavior data, environmental parameters, and non-contact response data using multi-source sensing modules; performing coupling analysis on these data through a dynamic coupling model; outputting a collaborative perturbation coupling factor and injecting it into the digital twin; simulating the material degradation path caused by the collaborative effect of human-induced perturbation; and predicting the risk of artwork degradation. This invention solves the technical problem that existing artwork protection mainly relies on static environmental monitoring, which cannot quantify the dynamic collaborative degradation impact of visitor interaction on artwork materials. It achieves the technical effect of accurately predicting the material degradation path caused by the collaborative effect of multiple factors involving humans, objects, and the environment by dynamically coupling visitor behavior data, environmental parameters, and artwork response data.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, specifically to a method, system, and device for predicting the state of digital twin mappings of physical artworks. Background Technology

[0002] Currently, the field of art conservation primarily relies on environmental monitoring technologies, such as collecting basic environmental parameters like temperature, humidity, and light, to ensure the stability of artworks. However, these technologies are mostly geared towards static monitoring, failing to fully consider the comprehensive impact of visitor behavior, environmental changes, and non-contact responses on artworks. For example, factors such as visitor dwell time, camera flashes, and emotional responses can have subtle effects on exhibits, and traditional conservation methods cannot monitor and quantify the specific effects of these factors on artwork deterioration in real time. Furthermore, existing digital twin technologies are largely focused on static model construction, lacking dynamic integration of the exhibition environment and visitor behavior, making it difficult to effectively predict the comprehensive deterioration risks that artworks may suffer during long-term display. Summary of the Invention

[0003] This application provides a method, system, and device for predicting the state of physical artworks using digital twin mapping, which addresses the technical problem that existing artwork conservation mainly relies on static environmental monitoring and cannot quantify the dynamic and collaborative deterioration effects of audience interaction on artwork materials.

[0004] The first aspect of this application provides a method for predicting the state of a digital twin of a physical artwork. The method includes: constructing a digital twin of a target exhibition hall based on exhibition hall architectural information and exhibit display data; synchronously collecting visitor behavior data, direct environmental parameters, and non-contact response data within the exhibition hall using a multi-source sensing module. The visitor behavior data includes infrared thermal mapping, single-point dwell time, and voice emotion characteristics; the direct environmental parameters include temperature and humidity change data and gas concentration change data; and the non-contact response data includes vibration spectrum and surface micro-temperature field distribution. A dynamic coupling model is established to couple and analyze the visitor behavior data, direct environmental parameters, and non-contact response data, outputting a cooperative perturbation coupling factor. The cooperative perturbation coupling factor is injected into the digital twin to simulate the material degradation path caused by human-induced perturbation synergy, outputting a prediction of the artwork's degradation risk in the future.

[0005] The second aspect of this application provides a digital twin mapping state prediction system for physical artworks. The system includes: a digital twin construction module for constructing a digital twin of a target exhibition hall based on exhibition hall architectural information and exhibit display data; a data acquisition module for simultaneously acquiring visitor behavior data, direct environmental parameters, and non-contact response data within the exhibition hall using a multi-source sensing module. The visitor behavior data includes infrared thermal mapping, single-point dwell time, and voice emotion characteristics; the direct environmental parameters include temperature and humidity change data and gas concentration change data; and the non-contact response data includes vibration spectrum and surface micro-temperature field distribution. A collaborative perturbation coupling analysis module is used to establish a dynamic coupling model, perform coupling analysis on the visitor behavior data, direct environmental parameters, and non-contact response data, and output a collaborative perturbation coupling factor; and a degradation risk prediction module is used to inject the collaborative perturbation coupling factor into the digital twin, simulate the material degradation path caused by human-induced perturbation synergy, and output a degradation risk prediction for the artwork in the future.

[0006] A third aspect of this application provides an electronic device comprising: a processor coupled to a memory for storing a program that, when executed by the processor, causes the system to perform the method described in any of the first aspects.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The digital twin mapping state prediction method, system, and device for physical artworks provided in this application relate to the field of data processing technology. By constructing a digital twin and collecting audience behavior data, environmental parameters, and non-contact response data in real time, a synergistic perturbation coupling factor is generated through coupling analysis and injected into the digital twin. This simulates the impact of human-caused perturbations and environmental changes on the degradation path of artwork materials, achieving accurate prediction of artwork degradation risk. This solves the technical problem that existing artwork protection mainly relies on static environmental monitoring and cannot quantify the dynamic synergistic degradation impact of audience interaction on artwork materials. It achieves the technical effect of accurately predicting the material degradation path caused by the synergistic effect of multiple factors such as human-object-environment through dynamic coupling of audience behavior data, environmental parameters, and artwork response data. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 A schematic flowchart of the digital twin mapping state prediction method for physical artworks provided in this application embodiment;

[0011] Figure 2 A schematic diagram of the structure of the digital twin mapping state prediction system for physical artworks provided in this application embodiment;

[0012] Figure 3 This application provides a schematic diagram of the structure of an electronic device.

[0013] Figure labeling: Digital twin construction module 11, data acquisition module 12, cooperative disturbance coupling analysis module 13, degradation risk prediction module 14, electronic device 300, memory 301, processor 302, communication interface 303, bus architecture 304. Detailed Implementation

[0014] This application provides a method, system, and device for predicting the state of physical artworks using digital twin mapping, which addresses the technical problem that existing artwork conservation mainly relies on static environmental monitoring and cannot quantify the dynamic and collaborative deterioration effects of audience interaction on artwork materials.

[0015] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0016] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or devices.

[0017] Example 1, as Figure 1 As shown, this application provides a method for predicting the state of a digital twin mapping of a physical artwork, the method comprising:

[0018] P10: Construct a digital twin of the target exhibition hall based on the exhibition hall's architectural information and exhibit display data.

[0019] Furthermore, step P10 in this embodiment of the application also includes:

[0020] P11: Based on the exhibition hall building information and exhibit display data, perform 3D scanning modeling of the exhibition hall spatial structure to generate a virtual exhibition hall framework that includes the building structure and display case layout; P12: Import the material characteristics data of the artworks into the virtual exhibition hall framework to establish a digital twin; P13: Configure a dynamic data interface for the digital twin to communicate with the multi-source sensing module and receive dynamic sensing data in real time.

[0021] It should be understood that a digital twin of the target exhibition hall is constructed based on the exhibition hall's architectural information and exhibit display data. Specifically, the spatial structure of the exhibition hall is first digitally reconstructed using 3D scanning and modeling technology. High-precision data is collected of the exhibition hall's walls, floors, ceilings, and display case shapes using methods such as LiDAR, structured light scanning, or panoramic photogrammetry. This data is then geometrically calibrated using the exhibition hall's architectural floor plans and dimensional parameters to generate a complete 3D point cloud data model. After meshing and rendering, a virtual exhibition hall framework containing the architectural structure and display case layout is obtained. This virtual framework accurately reflects the spatial proportions and display case distribution of the exhibition hall, providing the basic supporting environment for the digital twin.

[0022] Within the generated virtual exhibition hall framework, art material characteristic data is further imported to create a digital twin. Art material characteristic data refers to parameters that characterize the physical, chemical, and mechanical properties of the artwork's main materials, such as the spectral reflectance and absorptivity of pigments, the hygroscopic properties of paper or fabrics, the coefficient of thermal expansion of wood, and the oxidation rate of metal surfaces. To ensure data accuracy, relevant information can be obtained through non-contact detection methods, such as Raman spectroscopy, infrared thermography, or X-ray fluorescence imaging. By binding these material characteristic parameters to the virtual exhibition hall framework, the digital twin not only possesses the ability to map appearance and form but also can present state evolution characteristics consistent with the physical material in the virtual environment.

[0023] To enable the digital twin to reflect real-time environmental changes within the exhibition hall, a dynamic data interface is configured. This interface communicates with a multi-source sensor module, receiving dynamic sensor data from within the exhibition hall in real time. This data includes visitor behavior data, direct environmental parameters, and non-contact response data. The dynamic data interface receives real-time dynamic information related to the environment and human factors, including temperature and humidity, gas concentration, light intensity, vibration spectrum, surface temperature field distribution, and visitor behavior data. Visitor behavior data can be obtained through infrared thermal imaging to capture dwell time and location distribution, or through acoustic sensors combined with emotion recognition algorithms to extract voice emotion features. Through this dynamic data interface, the collected multi-source dynamic information is injected into the digital twin in real time, allowing it to continuously update and evolve during operation. This achieves an accurate mapping of the physical exhibition hall and the real-time state of the artworks, providing continuous and reliable data support for the subsequent construction of collaborative perturbation factors and the prediction of degradation risks.

[0024] P20: Through a multi-source sensing module, visitor behavior data, direct environmental parameters, and non-contact response data are collected simultaneously in the exhibition hall. The visitor behavior data includes infrared thermal image positioning, single-point dwell time, and voice emotion characteristics. The direct environmental parameters include temperature and humidity change data and gas concentration change data. The non-contact response data includes vibration spectrum and surface micro-temperature field distribution.

[0025] Specifically, multiple data sources within the exhibition hall are collected synchronously through multi-source sensor modules. These data include visitor behavior data, direct environmental parameters, and non-contact response data.

[0026] Specifically, firstly, infrared thermal imaging equipment is deployed to capture the location, movement trajectory, and dwell time of each visitor in the exhibition hall in real time, generating precise infrared thermal image positioning data and single-point dwell time. Secondly, microphone arrays and voice emotion recognition algorithms are used to capture the emotional characteristics of visitors' voices, such as excitement, intensity, and sighs, analyzing the potential thermal disturbance or vibration impact of emotional changes on the artworks. By combining thermal imaging and emotion analysis, data on the potential correlation between visitor behavior and the artworks can be obtained.

[0027] Secondly, environmental conditions in the exhibition hall are monitored in real time by deploying temperature and humidity sensors, gas concentration sensors, and light sensors. For example, temperature and humidity sensors record changes in temperature and humidity within the exhibition hall to analyze the impact of these changes on the materials of the artworks, especially the chemical reactions and aging of organic pigments or paper. Gas concentration sensors monitor the concentrations of CO2, ammonia, or other volatile organic compounds in the air within the exhibition hall to analyze the potential corrosive effects of these changes on the surface materials of the artworks. Light sensors measure the lighting intensity within the exhibition hall, especially the wavelengths and intensities of ultraviolet and visible light, to analyze the effects of these lighting factors on the fading and aging of pigments, paper, and fabrics, providing a stable environmental benchmark for subsequent simulations.

[0028] Finally, high-precision accelerometers were used to capture the vibration spectrum within the exhibition hall in real time, assessing the impact of internal and external vibrations on the artworks. Analysis of the vibration spectrum identified the potential damage caused by vibrations of different frequencies to artworks made of different materials, particularly inorganic materials such as ceramics, metals, and glass. Furthermore, an infrared thermal imager was used to scan the artwork surfaces, collecting data on the distribution of micro-temperature fields. This device can accurately detect localized temperature changes on the artwork surface without contact, especially when visitors are present or when the surrounding environment changes, revealing areas of thermal disturbance and stress concentration. Combining this non-contact response data provides the model with more detailed temperature and vibration information, enabling the analysis of the long-term effects of environmental disturbances on the artworks.

[0029] P30: Establish a dynamic coupling model, perform coupling analysis on the audience behavior data, direct environmental parameters and non-contact response data, and output the cooperative perturbation coupling factor.

[0030] Furthermore, in establishing the dynamic coupling model, step P30 of this embodiment further includes:

[0031] P31: Create a spatiotemporal correlation matrix of audience behavior, environmental parameters, and non-contact responses; P32: Develop a material response function library for artworks, which includes an organic pigment hydrolysis rate model and an inorganic substrate fatigue accumulation model; P33: Integrate the spatiotemporal correlation matrix and the material response function library to form a dynamic coupling model that can quantify human-object interaction effects.

[0032] Optionally, a dynamic coupling model can be established to comprehensively process and couple audience behavior data, direct environmental parameters, and non-contact response data, thereby obtaining a cooperative disturbance coupling factor that can characterize the combined effect of multi-source disturbances.

[0033] Specifically, the first step is to create a spatiotemporal correlation matrix to quantify the spatiotemporal relationships between visitor behavior, environmental parameters, and non-contact responses. By analyzing the time series and spatial distribution of this data, we can determine how visitor activities within the exhibition hall affect local environmental parameters, and how changes in these parameters further influence the non-contact responses of the artworks. For example, visitor congregation in a particular area may lead to increased local temperature and humidity, which in turn affects the surface temperature and vibration of the artworks in that area. By constructing the spatiotemporal correlation matrix, these interactions can be systematically captured, providing a foundation for subsequent coupling analysis.

[0034] Furthermore, a material response function library for artworks was developed to elucidate the physical and chemical response mechanisms of artwork materials under various disturbances. This library contains response models for multiple materials, used to describe the physical and chemical changes of artworks under different environmental conditions. Specifically, the library includes an organic pigment hydrolysis rate model and an inorganic substrate fatigue accumulation model. The organic pigment hydrolysis rate model, based on chemical kinetics, can predict the hydrolysis rate of organic pigments under different humidity and temperature conditions to assess the risk of pigment fading and discoloration. The inorganic substrate fatigue accumulation model, based on materials mechanics and fatigue theory, is used to assess the fatigue accumulation of inorganic materials (such as ceramics and bronze) under long-term vibration and temperature changes, and can be used to predict the structural stability of artworks. By expressing these functions mathematically, the degradation rate of different materials under specific environmental conditions and disturbance factors can be quantitatively calculated, thus providing an executable basis for the material layer response of the model.

[0035] Finally, the spatiotemporal correlation matrix is ​​integrated with a material response function library to form a dynamic coupling model that can quantify human-object interaction effects. This model, by combining audience behavior, environmental parameters, and non-contact response data with the material response characteristics of the artwork, can comprehensively analyze and quantify human-object interaction effects, outputting a cooperative perturbation coupling factor. This factor reflects the combined strength of the effects of audience behavior, environmental changes, and non-contact responses on the risk of artwork degradation and can serve as a key input variable for subsequent degradation path simulation and risk prediction.

[0036] Furthermore, step P31 in the embodiments of this application also includes:

[0037] P31-1: Establish the spatial mapping relationship between the infrared thermal image location and the surface micro-temperature field distribution, the temporal cumulative relationship between the dwell time at a single point and the temperature and humidity change data, and the frequency domain response relationship between the voice emotion characteristics and the vibration spectrum; P31-2: Integrate the spatial mapping relationship, the temporal cumulative relationship and the frequency domain response relationship to construct a spatiotemporal correlation matrix.

[0038] Specifically, the construction process of the spatiotemporal correlation matrix can be further refined. First, a spatial mapping relationship between infrared thermal image positioning and surface micro-temperature field distribution is established. Using spatial mapping algorithms, such as nearest neighbor algorithms or spatial interpolation, a relationship is established between the location information of the audience and the surface temperature field of the artwork. The impact of the audience's location on the local temperature field of the artwork is calculated, thus establishing a spatial mapping relationship between thermal disturbance and surface temperature change of the artwork. For example, the gathering of audience members near a particular exhibit may cause the temperature in that area to rise; this temperature change can be monitored and recorded in real time by surface micro-temperature field sensors.

[0039] Secondly, a cumulative temporal relationship is established between the duration of visitor stay at a single location and temperature and humidity changes. By correlating the duration of visitor stay at a particular location with the temperature and humidity changes at that location, the impact of visitor behavior on local environmental changes is quantified. For example, time series analysis is used to correlate visitor stay duration with environmental parameters (such as temperature and humidity changes) to calculate the cumulative effect of stay duration on local environmental changes. For instance, prolonged visitor stays may lead to significant changes in local humidity, which could adversely affect the preservation of artworks.

[0040] Finally, a frequency domain response relationship between vocal emotion characteristics and vibration spectra is established. Using frequency domain analysis methods (such as Fourier transform), the correlation between emotional fluctuations and vibration spectra is analyzed to determine how the audience's vocal emotional fluctuations interact with vibration frequencies within the exhibition hall. For example, high-frequency acoustic vibrations may cause minute vibrations on the surface of artworks; these vibrations can be monitored using vibration sensors, and their frequency domain characteristics can be analyzed. This relationship reveals the interaction between emotional fluctuations and vibration effects, providing a quantitative description of the sound-vibration coupling effect for subsequent models.

[0041] After establishing the three mapping relationships mentioned above, these relationships are further integrated to construct a spatiotemporal correlation matrix. This matrix can uniformly represent multiple factors such as audience behavior, environmental changes, and vibration disturbances in time and space, providing accurate input data for subsequent dynamic coupling analysis. Through the spatiotemporal correlation matrix, the influence of all data sources can be processed and analyzed within a unified framework, ensuring the accuracy of subsequent predictions and simulations.

[0042] Furthermore, step P32 in the embodiments of this application also includes:

[0043] P32-1: Based on the molecular characteristics of organic materials, the influence parameters of temperature and humidity fluctuations on the stability of chemical bonds are quantified, and an organic pigment hydrolysis rate model is generated; P32-2: Based on the mechanical characteristics of inorganic materials, the damage parameters of vibration energy to the integrity of microstructure are quantified, and an inorganic substrate fatigue accumulation model is generated; P32-3: The organic pigment hydrolysis rate model and the inorganic substrate fatigue accumulation model are integrated into a material response function library with material specificity.

[0044] Optionally, the development process of the material response function library can be further refined. Specifically, based on the molecular characteristics of organic materials, the influence parameters of temperature and humidity fluctuations on the stability of chemical bonds are first quantified. This process involves in-depth analysis of the molecular structure of organic pigments, determining the impact of temperature and humidity changes on key chemical bonds (such as ester bonds and amide bonds) in organic pigment molecules through experiments and theoretical calculations. Specifically, through experimental measurements or molecular dynamics simulations, the rate constants of chemical bond breaking of typical organic pigments under increased humidity and temperature fluctuations are obtained, and a functional relationship between temperature and humidity and reaction rate is established to generate an organic pigment hydrolysis rate model. This model can predict the hydrolysis rate of organic pigments under different temperature and humidity conditions, thus providing a scientific basis for assessing the risk of pigment fading and discoloration.

[0045] Next, based on the mechanical properties of inorganic materials, the damage parameters of vibration energy on the integrity of the microstructure are quantified. This process involves analyzing the microstructure and mechanical properties of inorganic substrates (such as ceramics and bronze). Through experiments and numerical simulations, the influence of vibration energy on the microstructure of inorganic substrates (such as lattice defects and cracks) is determined. Specifically, the collected vibration spectrum energy distribution is combined with the evolution law of lattice defects in the material to calculate the probability of microcrack initiation and crack propagation rate. Based on these parameters, a functional relationship between vibration amplitude, frequency, and damage accumulation is established, generating a fatigue accumulation model for inorganic substrates. This model can predict the fatigue accumulation of inorganic substrates under long-term vibration and temperature changes, thus providing a scientific basis for assessing the structural stability of artworks.

[0046] Finally, the organic pigment hydrolysis rate model and the inorganic substrate fatigue accumulation model generated above are integrated into a material-specific material response function library. This function library is a comprehensive data structure containing response models of different materials under different environmental conditions. By integrating these models, the material response function library can provide comprehensive response predictions for various art materials. For example, for a mixed-material artwork containing organic pigments and inorganic substrates, this function library can simultaneously predict the fading risk of the pigments and the structural stability of the substrate.

[0047] This function library is stored as callable algorithm modules or sets of parameterized functions and supports interface connections with dynamically coupled models. When input environmental perturbation parameters and audience behavior perturbation factors are passed in, the library can quickly invoke the corresponding model and output the response rate and damage level of a specific material. In this way, the material response function library provides a standardized and executable data interface for subsequent dynamically coupled analysis, making the state prediction of artworks of different materials universal and scalable.

[0048] Furthermore, based on the dynamic coupling model, the audience behavior data, direct environmental parameters, and non-contact response data are coupled and analyzed. Step P30 in this embodiment further includes:

[0049] P34: Using the spatiotemporal correlation matrix, perform spatial overlay analysis on the infrared thermal image location and surface micro-temperature field distribution to calculate the local thermal disturbance intensity; P35: Perform time series correlation analysis on the single-point dwell time with the temperature and humidity change data and gas concentration change data to extract the environmental cumulative effect coefficient; P36: Perform frequency domain correlation analysis on the voice emotion features and vibration spectrum to determine the acoustic-vibration coupling strength; P37: According to the material type of the artwork, call the material response function library to match and generate the sensitivity weight of the artwork; P38: Based on the sensitivity weight, fuse the local thermal disturbance intensity, environmental cumulative effect coefficient, and acoustic-vibration coupling strength to generate a cooperative disturbance coupling factor.

[0050] It should be understood that, based on the dynamic coupling model, audience behavior data, direct environmental parameters, and non-contact response data are comprehensively coupled and analyzed to output the cooperative perturbation coupling factor.

[0051] First, spatial overlay analysis of infrared thermal image location and surface micro-temperature field distribution is performed using a spatiotemporal correlation matrix. Specifically, the spatial distribution information of visitors within the exhibition hall is extracted and mapped point-by-point with the corresponding micro-temperature field changes, thus obtaining the local thermal effect caused by visitor behavior. By establishing a functional relationship between temperature gradient and time persistence within the spatially overlapping region, the intensity of local thermal disturbance can be calculated, i.e., the direct impact of visitor activity on the surface temperature of the artwork. For example, when visitors gather near an exhibit, the temperature in that area may rise significantly; this temperature change can be monitored and recorded in real time by surface micro-temperature field sensors. Through spatial overlay analysis, the intensity of this local thermal disturbance can be quantified, providing data support for subsequent coupled analysis.

[0052] Next, a time-series correlation analysis was performed on the duration of stay at a single location with data on temperature and humidity changes, as well as gas concentration changes. By establishing a time correlation function between stay duration and changes in environmental parameters, the degree of influence of different disturbance factors on the exhibition hall's microenvironment under cumulative effects was extracted. For example, when visitors stay in a certain location for a long time, the local humidity may continuously increase and accumulate, forming a cumulative effect. Through this analysis, an environmental cumulative effect coefficient can be obtained, which is used to characterize the temporal coupling relationship between visitor behavior and environmental disturbances.

[0053] Next, a frequency domain correlation analysis was performed on the vocal emotion features and vibration spectrum. Specifically, an acoustic feature extraction algorithm was used to analyze the spectral components and emotional intensity of the audience's speech, and compared with the vibration spectrum signals collected by sensors in the exhibition hall. The correlation index between the two in the frequency domain was calculated, and then the acoustic vibrations generated by the audience's emotional changes (such as shouting, exclamations, etc.) were analyzed to determine the potential impact of these vibrations on the artworks, that is, the acoustic-vibration coupling strength. This reflects the potential contribution of emotionally intense vocal behavior to the vibration environment of the exhibition hall, providing acoustic disturbance quantification parameters for the dynamic coupling model.

[0054] Then, based on the artwork's material type, a material response function library is invoked to match and generate sensitivity weights for the artwork. Specifically, based on the artwork's specific material (e.g., organic pigments, inorganic substrates), a corresponding response model is selected from the material response function library, and sensitivity weights are generated for the artwork. Sensitivity weights characterize the vulnerability of different materials to specific perturbation factors. For example, for organic pigment artworks, humidity perturbation has a higher sensitivity weight; while for inorganic ceramic or stone artworks, vibration perturbation has a more significant sensitivity weight. By invoking the material response function library, targeted matching of perturbation factors and material responses can be achieved, enabling the coupled model to have differentiated processing capabilities.

[0055] Finally, based on sensitivity weights, the local thermal disturbance intensity, environmental cumulative effect coefficient, and acoustic-vibration coupling intensity are weighted and fused to generate a synergistic disturbance coupling factor. This factor can comprehensively reflect the superposition effect of multi-source disturbances on a specific material, quantitatively characterize the synergistic influence of human-caused disturbances and environmental disturbances on the state of artworks, and thus provide direct input for degradation path simulation and future risk prediction in digital twins.

[0056] P40: Inject the cooperative perturbation coupling factor into the digital twin to simulate the material degradation path caused by human-induced perturbation cooperative effects and output a prediction of the artwork's degradation risk in the future.

[0057] Furthermore, step P40 in this embodiment of the application also includes:

[0058] P41: Load a material degradation simulation module into the digital twin. The material degradation simulation module contains degradation evolution models of different artwork materials. P42: Inject the cooperative perturbation coupling factor as an external perturbation into the loaded material degradation simulation module to simulate the stress distribution changes and material performance evolution of the artwork under different time steps, generate a degradation risk map containing spatiotemporal distribution characteristics, and mark high-risk areas and their dominant perturbation factors.

[0059] Specifically, by injecting a cooperative perturbation coupling factor into the digital twin, and by simulating the material degradation path caused by human-induced perturbation cooperative effects, the project outputs a prediction of the artwork's degradation risk over a future period.

[0060] First, a material degradation simulation module is loaded into the digital twin to drive its virtual state evolution. This module pre-stores degradation evolution models for different artwork materials, including molecular hydrolysis models for organic materials, humidity fatigue models for fibrous materials, oxidation diffusion models for metallic materials, and microcrack propagation models for ceramics and stone. By loading these various degradation evolution models into the digital twin, it can perform targeted degradation evolution simulations based on material differences, thus ensuring consistency between the simulation process and the actual material degradation mechanism.

[0061] Next, the cooperative perturbation coupling factor is injected as an external perturbation parameter into the loaded material degradation simulation module, driving the twin to conduct dynamic simulations. Specifically, under a set time step, the stress distribution changes, material property degradation rate, and micro-damage evolution process of the artwork under cooperative perturbation are calculated. By spatially superimposing and temporally analyzing the simulation results at different time steps, a degradation risk map containing spatiotemporal distribution characteristics is generated. For example, by simulating the impact of audience behavior, environmental parameters, and non-contact responses on the artwork, the stress distribution changes and material property evolution of the artwork in the future can be predicted. The generated degradation risk map can intuitively display the risk distribution of the artwork at different locations within a certain period in the future, and further mark high-risk areas and their corresponding dominant perturbation factors, such as pigment degradation areas caused by localized high humidity and crack initiation areas caused by concentrated vibration energy. Through these detailed annotations, managers can more intuitively understand the degradation risk of the artwork and take corresponding protective measures.

[0062] Furthermore, to simulate the stress distribution changes and material property evolution of the artwork at different time steps, step P42 of this application embodiment also includes:

[0063] P42-1: Based on the material type of the artwork, call the corresponding degradation evolution model from the material degradation simulation module; P42-2: Decompose the cooperative disturbance coupling factor into thermal disturbance component, environmental cumulative component, and acoustic-vibration coupling component; P42-3: Based on the degradation evolution model, calculate the changes in thermal stress distribution, chemical bond breakage probability, and microcrack propagation rate of each component on the artwork within a preset time step, and fuse them to generate a degradation risk map.

[0064] Optionally, the specific operations for simulating the stress distribution changes and material property evolution of the artwork at different time steps can be further refined.

[0065] First, based on the type of artwork's material, the corresponding degradation evolution model is retrieved from the material degradation simulation module. This process involves identifying and classifying the artwork's material to select an appropriate degradation evolution model. For example, a hydrolysis rate model is used for organic pigments; an oxidation diffusion model is used for metallic substrates; and a microcrack propagation model is used for ceramics or stone. In this way, precise simulations can be performed for different material characteristics, ensuring high accuracy and consistency in the simulation results.

[0066] Next, the cooperative perturbation coupling factor is decomposed into thermal perturbation components, environmental cumulative components, and acoustic-vibration coupling components. This process involves a detailed analysis of the cooperative perturbation coupling factor, decomposing it into different physical effect components. The thermal perturbation component primarily reflects the impact of temperature and humidity fluctuations on the thermal expansion and chemical reactions of the material; the environmental cumulative component reflects the long-term cumulative effect of audience behavior and environmental changes on the artwork; and the acoustic-vibration coupling component reflects the impact of vibration on the structural integrity of the artwork and the propagation of microcracks. By decomposing these perturbation factors, the independent influence of different perturbation factors on the artwork can be assessed separately, further improving the accuracy of the simulation. This decomposition allows for a clearer analysis of the specific contribution of each component to the degradation of the artwork.

[0067] Then, based on the invoked degradation evolution model, the changes in thermal stress distribution, chemical bond breakage probability, and microcrack propagation rate caused by each component to the artwork within a preset time step are calculated. Specifically, based on the thermal disturbance component, the temperature changes in local areas and the resulting thermal stress are simulated, and the micro-deformation and stress distribution of the material caused by temperature changes are calculated; for the environmental accumulation component, the changes in material properties caused by long-term humidity, gas concentration, and audience behavior are calculated, such as pigment hydrolysis, paper or fiber fatigue, etc.; for the acoustic-vibration coupling component, based on the vibration spectrum and mechanical model, the propagation of microcracks and the accumulation of fatigue damage in the material are calculated.

[0068] Finally, the above calculation results are merged to generate a degradation risk map. This map not only includes the spatiotemporal distribution characteristics of artwork degradation but also marks high-risk areas and their dominant perturbation factors. It can show the degree of degradation of different parts of the artwork and the dominant role of different perturbation factors at different time steps. Through this fusion, managers can more intuitively understand the degradation risk of artworks and take corresponding protective measures.

[0069] In summary, the embodiments of this application have at least the following technical effects:

[0070] This application achieves precise simulation and prediction of the degradation path of artworks under the synergistic effect of people, objects, and environment by dynamically coupling audience behavior data, environmental parameters, and artwork response data. This solves the problem that traditional conservation methods cannot fully consider the impact of audience behavior and environmental changes on artworks. By synchronously collecting multi-source data and injecting it into a digital twin, it enables real-time degradation prediction of artworks under different environmental and interactive conditions, providing timely and effective decision support for artwork conservation. By combining multiple dynamic data sources and simulation models, it improves the scientific rigor and accuracy of artwork conservation, accurately identifies potential risk areas and dominant disturbance factors, provides data support for the long-term conservation and restoration of artworks, and effectively extends the preservation period of artworks.

[0071] It achieves the technical effect of accurately predicting the material degradation path caused by the synergistic effect of multiple factors such as people, objects, and environment by dynamically coupling audience behavior data, environmental parameters, and artwork response data.

[0072] Example 2, based on the same inventive concept as the digital twin mapping state prediction method for physical artworks in the foregoing examples, such as... Figure 2 As shown, this application provides a digital twin mapping state prediction system for physical artworks. The system and method embodiments in this application are based on the same inventive concept. The system includes:

[0073] Digital twin construction module 11 is used to construct a digital twin of the target exhibition hall based on the exhibition hall building information and exhibit display data.

[0074] The data acquisition module 12 is used to simultaneously collect visitor behavior data, direct environmental parameters, and non-contact response data in the exhibition hall through a multi-source sensing module. The visitor behavior data includes infrared thermal image positioning, single-point dwell time, and voice emotion characteristics. The direct environmental parameters include temperature and humidity change data and gas concentration change data. The non-contact response data includes vibration spectrum and surface micro-temperature field distribution.

[0075] The cooperative disturbance coupling analysis module 13 is used to establish a dynamic coupling model, perform coupling analysis on the audience behavior data, direct environmental parameters and non-contact response data, and output the cooperative disturbance coupling factor.

[0076] The degradation risk prediction module 14 is used to inject the cooperative perturbation coupling factor into the digital twin, simulate the material degradation path caused by human-induced perturbation cooperative effects, and output the degradation risk prediction of the artwork in the future time period.

[0077] Furthermore, the digital twin construction module 11 is also used to perform the following steps:

[0078] Based on the exhibition hall's architectural information and exhibit display data, a 3D scanning model of the exhibition hall's spatial structure is created to generate a virtual exhibition hall framework that includes the architectural structure and display case layout. Artwork material characteristic data is imported into the virtual exhibition hall framework to establish a digital twin. A dynamic data interface is configured for the digital twin to communicate with the multi-source sensing module and receive dynamic sensing data in real time.

[0079] Furthermore, the cooperative disturbance coupling analysis module 13 is also used to perform the following steps:

[0080] Create a spatiotemporal correlation matrix of audience behavior, environmental parameters, and non-contact responses; develop a material response function library for artworks, which includes an organic pigment hydrolysis rate model and an inorganic substrate fatigue accumulation model; integrate the spatiotemporal correlation matrix and the material response function library to form a dynamic coupling model that can quantify human-object interaction effects.

[0081] Furthermore, the cooperative disturbance coupling analysis module 13 is also used to perform the following steps:

[0082] The spatial mapping relationship between the infrared thermal image location and the surface micro-temperature field distribution, the temporal cumulative relationship between the dwell time at a single point and the temperature and humidity change data, and the frequency domain response relationship between the voice emotion features and the vibration spectrum are established respectively. The spatial mapping relationship, the temporal cumulative relationship and the frequency domain response relationship are fused to construct a spatiotemporal correlation matrix.

[0083] Furthermore, the cooperative disturbance coupling analysis module 13 is also used to perform the following steps:

[0084] Based on the molecular characteristics of organic materials, the influence parameters of temperature and humidity fluctuations on the stability of chemical bonds are quantified to generate an organic pigment hydrolysis rate model; based on the mechanical characteristics of inorganic materials, the damage parameters of vibration energy to the integrity of microstructure are quantified to generate an inorganic substrate fatigue accumulation model; the organic pigment hydrolysis rate model and the inorganic substrate fatigue accumulation model are integrated into a material response function library with material specificity.

[0085] Furthermore, the cooperative disturbance coupling analysis module 13 is also used to perform the following steps:

[0086] Using the spatiotemporal correlation matrix, spatial overlay analysis is performed on the infrared thermal image location and surface micro-temperature field distribution to calculate the local thermal disturbance intensity; time series correlation analysis is performed on the dwell time at a single point with the temperature and humidity change data and gas concentration change data to extract the environmental cumulative effect coefficient; frequency domain correlation analysis is performed on the voice emotion features and vibration spectrum to determine the acoustic-vibration coupling strength; according to the material type of the artwork, the material response function library is called to match and generate the sensitivity weight of the artwork; based on the sensitivity weight, the local thermal disturbance intensity, environmental cumulative effect coefficient, and acoustic-vibration coupling strength are fused to generate a cooperative disturbance coupling factor.

[0087] Furthermore, the degradation risk prediction module 14 is also used to perform the following steps:

[0088] A material degradation simulation module is loaded into the digital twin. The material degradation simulation module contains degradation evolution models of different artwork materials. The cooperative perturbation coupling factor is injected into the loaded material degradation simulation module as an external perturbation to simulate the stress distribution change and material performance evolution process of the artwork under different time steps, generate a degradation risk map containing spatiotemporal distribution characteristics, and mark high-risk areas and their dominant perturbation factors.

[0089] Furthermore, the degradation risk prediction module 14 is also used to perform the following steps:

[0090] Based on the material type of the artwork, the corresponding degradation evolution model is called from the material degradation simulation module; the cooperative disturbance coupling factor is decomposed into thermal disturbance component, environmental cumulative component and acoustic-vibration coupling component; based on the degradation evolution model, the thermal stress distribution change, chemical bond breakage probability and microcrack propagation rate caused by each component to the artwork within a preset time step are calculated respectively, and the degradation risk map is generated by fusion.

[0091] Example 3: Exemplary electronic device.

[0092] The following is for reference. Figure 3 The present application describes the electronic device according to its embodiments.

[0093] Based on the same inventive concept as the digital twin mapping state prediction method for physical artworks in the foregoing embodiments, this application also provides a digital twin mapping state prediction system for physical artworks, comprising: a processor coupled to a memory for storing a program, wherein when the program is executed by the processor, the system performs the steps of the method described in Embodiment 1.

[0094] The electronic device 300 includes a processor 302, a communication interface 303, and a memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. The communication interface 303, processor 302, and memory 301 can be interconnected via the bus architecture 304; the bus architecture 304 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus architecture 304 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0095] Processor 302 may be a CPU, microprocessor, ASIC, or one or more integrated circuits used to control the execution of programs according to the present application.

[0096] Communication interface 303 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), wired access network, etc.

[0097] Memory 301 can be ROM or other types of static storage devices capable of storing static information and instructions, RAM or other types of dynamic storage devices capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory can exist independently and be connected to the processor via bus architecture 304. Memory can also be integrated with the processor.

[0098] The memory 301 stores computer execution instructions for implementing the scheme of this application, and the processor 302 controls the execution. The processor 302 executes the computer execution instructions stored in the memory 301, thereby realizing the digital twin mapping state prediction method for physical artworks provided in the above embodiments of this application.

[0099] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0100] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0101] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A method for digital twin mapping state prediction of a physical artwork, characterized in that, The method comprises: Based on the exhibition hall building information and the exhibit display data, a digital twin of the target exhibition hall is constructed; Through a multi-source sensing module, audience behavior data, direct environmental parameters and non-contact response data in the exhibition hall are synchronously collected, wherein the audience behavior data includes infrared thermal image positioning, single-point stay duration and voice emotion features, the direct environmental parameters include temperature and humidity change data and gas concentration change data, and the non-contact response data includes vibration frequency spectrum and surface micro-temperature field distribution; A dynamic coupling model is established to couple and analyze the audience behavior data, direct environmental parameters and non-contact response data, and output a collaborative disturbance coupling factor; The collaborative disturbance coupling factor is injected into the digital twin to simulate the material degradation path caused by the human disturbance collaborative effect, and output a degradation risk prediction of the artwork in a future time period; The dynamic coupling model comprises: A space-time correlation matrix of audience behavior, environmental parameters and non-contact response is created; A material response function library of the artwork is developed, which includes an organic pigment hydrolysis rate model and an inorganic substrate fatigue accumulation model; The space-time correlation matrix and the material response function library are integrated to form a dynamic coupling model of quantifiable human-object interaction effects; The space-time correlation matrix of audience behavior, environmental parameters and non-contact response comprises: The spatial mapping relationship between the infrared thermal image positioning and the surface micro-temperature field distribution, the time accumulation relationship between the single-point stay duration and the temperature and humidity change data, and the frequency domain response relationship between the voice emotion features and the vibration frequency spectrum are established respectively; The space-time correlation matrix is constructed by fusing the spatial mapping relationship, the time accumulation relationship and the frequency domain response relationship; The material response function library of the artwork comprises: Based on the molecular characteristics of organic materials, the influence parameters of temperature and humidity fluctuations on chemical bond stability are quantified to generate an organic pigment hydrolysis rate model; Based on the mechanical characteristics of inorganic materials, the damage parameters of vibration energy on microstructure integrity are quantified to generate an inorganic substrate fatigue accumulation model; The organic pigment hydrolysis rate model and the inorganic substrate fatigue accumulation model are integrated into a material response function library with material-specific characteristics; Based on the dynamic coupling model, the audience behavior data, direct environmental parameters and non-contact response data are coupled and analyzed to output a collaborative disturbance coupling factor, which comprises: Through the space-time correlation matrix, spatial superposition analysis is performed on the infrared thermal image positioning and the surface micro-temperature field distribution to calculate the local thermal disturbance intensity; Time series correlation analysis is performed on the single-point stay duration and the temperature and humidity change data and the gas concentration change data to extract the environmental cumulative effect coefficient; Frequency domain correlation analysis is performed on the voice emotion features and the vibration frequency spectrum to determine the acoustic vibration coupling intensity; According to the material type of the artwork, the material response function library is called to match and generate the sensitivity weight of the artwork; According to the sensitivity weight, the local thermal disturbance intensity, the environmental cumulative effect coefficient and the acoustic vibration coupling intensity are fused to generate the collaborative disturbance coupling factor; The digital twin of the target exhibition hall is constructed based on the exhibition hall building information and the exhibit arrangement data, including: Based on the exhibition hall building information and the exhibit arrangement data, a three-dimensional scanning modeling is performed on the exhibition hall space structure to generate a virtual exhibition hall framework containing the building structure and the exhibit case layout; Artistic material texture characteristic data is imported into the virtual exhibition hall framework to establish a digital twin; A dynamic data interface is configured for the digital twin to be communicatively connected with the multi-source sensing module to receive dynamic sensing data in real time; The synergistic disturbance coupling factor is injected into the digital twin to simulate the material degradation path caused by the synergistic effect of human-induced disturbance, and to output the degradation risk prediction of the artwork in the future time period, including: A material degradation simulation module is loaded in the digital twin, and the material degradation simulation module contains degradation evolution models of different artistic materials; The synergistic disturbance coupling factor is injected into the loaded material degradation simulation module as an external disturbance to simulate the stress distribution change and material performance evolution process of the artwork at different time steps to generate a degradation risk atlas containing space-time distribution characteristics and label high-risk areas and their dominant disturbance factors.

2. The digital twin mapping state prediction method of a physical artwork of claim 1, wherein, Simulating the stress distribution change and material performance evolution process of the artwork at different time steps to generate a degradation risk atlas containing space-time distribution characteristics, including: According to the artistic material texture type, the corresponding degradation evolution model is called from the material degradation simulation module; The synergistic disturbance coupling factor is decomposed into a thermal disturbance component, an environmental cumulative component, and a sound vibration coupling component; Based on the degradation evolution model, the thermal stress distribution change, the chemical bond rupture probability, and the micro-crack propagation rate caused by each component to the artwork within the preset time step are calculated respectively to generate a degradation risk atlas.

3. A digital twin mapping state prediction system for physical artwork, characterized by, A system for performing the digital twin mapping state prediction method of the real artistic product according to any one of claims 1 to 2, the system comprising: A digital twin construction module for constructing a digital twin of a target exhibition hall based on exhibition hall building information and exhibit arrangement data; A data acquisition module for synchronously acquiring audience behavior data, direct environmental parameters, and non-contact response data in the exhibition hall through a multi-source sensing module, wherein the audience behavior data includes infrared thermal map positioning, single-point stay duration, and voice emotion features, the direct environmental parameters include temperature and humidity change data and gas concentration change data, and the non-contact response data includes vibration spectrum and surface micro-temperature field distribution; A synergistic disturbance coupling analysis module for establishing a dynamic coupling model and coupling analyzing the audience behavior data, direct environmental parameters, and non-contact response data to output a synergistic disturbance coupling factor; A degradation risk prediction module for injecting the synergistic disturbance coupling factor into the digital twin to simulate the material degradation path caused by the synergistic effect of human-induced disturbance and to output the degradation risk prediction of the artwork in the future time period.

4. An electronic device, comprising: including: A processor coupled with a memory, the memory for storing a program, when the program is executed by the processor, the system is caused to perform the steps of the method according to any one of claims 1 to 2.

Images