Preventive protection method for cultural relics and related device

Abstract

The invention discloses a cultural relic preventive protection method and a related device, and relates to the technical field of cultural relic preventive protection, and the method comprises the steps: obtaining internal basic data and external environment data of a plurality of cultural relics, and actual deformation data; inputting the internal basic data and the external environment data of the plurality of cultural relics into a back propagation neural network to obtain predicted deformation data of the plurality of cultural relics; determining individual fitness values of the plurality of cultural relics based on the actual deformation data and the predicted deformation data of the plurality of cultural relics; performing genetic algorithm operation based on the individual fitness value to obtain an optimized parameter value; optimizing the back-propagation neural network based on the optimization parameter value to obtain an optimized back-propagation neural network model optimized by the genetic algorithm; and optimizing the back propagation neural network model based on a genetic algorithm to predict deformation data of the target cultural relic. According to the method, the globally optimal model parameter is searched based on the genetic algorithm, and then the GA-BP model is trained, so that the accuracy of cultural relic deformation prediction is improved.

Description

Technical Field

[0001] The present application relates to the technical field of preventive protection of cultural relics, and in particular to a preventive protection method for cultural relics and related devices. Background Art

[0002] An existing preventive protection method for cultural relics uses a graph attention network model to predict the deformation of cultural relics in the future. However, the graph attention network model is prone to fall into local optimal solutions when processing large amounts of data and complex graph structure data, resulting in inaccurate predictions when predicting the deformation of cultural relics based on the graph attention network model. Summary of the invention

[0003] In view of the above problems, this application provides a preventive protection method and related devices for cultural relics to achieve the purpose of accurately predicting the deformation of cultural relics. The specific scheme is as follows:

[0004] The first aspect of the present application provides a method for preventive protection of cultural relics, comprising:

[0005] Acquiring internal basic data and external environmental data of a plurality of cultural relics, as well as actual deformation data of the plurality of cultural relics;

[0006] Inputting the internal basic data and external environmental data of the plurality of cultural relics into a back propagation neural network to obtain predicted deformation data of the plurality of cultural relics;

[0007] Determining individual fitness values ​​of the plurality of cultural relics based on the actual deformation data and the predicted deformation data of the plurality of cultural relics;

[0008] Performing a genetic algorithm operation based on the individual fitness values ​​of the plurality of cultural relics to obtain an optimized parameter value of the back propagation neural network;

[0009] Optimizing the back propagation neural network based on the optimization parameter values ​​to obtain an optimized genetic algorithm optimized back propagation neural network model;

[0010] The deformation data of the target cultural relic is predicted based on the genetic algorithm-optimized back-propagation neural network model.

[0011] In a possible implementation, for each of the plurality of cultural relics, determining the individual fitness value of the cultural relic based on the actual deformation data and the predicted deformation data of the cultural relic includes:

[0012] Calculating a first fitness value of the cultural relic based on actual deformation amounts of multiple preset feature dimensions included in the actual deformation data of the cultural relic;

[0013] Calculating a second fitness value of the cultural relic based on the actual deformation amount at each first time point included in the actual deformation data of the cultural relic;

[0014] Calculating a cultural relic deformation prediction mapping error value of the cultural relic based on the actual deformation data and the predicted deformation data of the cultural relic, and calculating a third fitness value of the cultural relic based on the cultural relic deformation prediction mapping error value of the cultural relic;

[0015] Calculating a fourth fitness value of the cultural relic based on actual deformation amounts monitored at multiple monitoring points at each second time point included in the actual deformation data of the cultural relic;

[0016] Based on the first fitness value, the second fitness value, the third fitness value and the fourth fitness value of the cultural relic, an individual fitness value of the cultural relic is obtained.

[0017] In a possible implementation, the calculating the first fitness value of the cultural relic based on the actual deformation amounts of the plurality of preset feature dimensions included in the actual deformation data of the cultural relic includes:

[0018] Calculating a cultural relic deformation feature matrix of the cultural relic based on actual deformation amounts of multiple preset feature dimensions included in the actual deformation data of the cultural relic;

[0019] Based on the cultural relic deformation feature matrix of the cultural relic and the actual deformation amounts of the plurality of preset feature dimensions, a first fitness value of the cultural relic is calculated.

[0020] In a possible implementation, the calculating the second fitness value of the cultural relic based on the actual deformation amount at each first time point included in the actual deformation data of the cultural relic includes:

[0021] Calculating the time fractal feature of the cultural relic based on the actual deformation amount at each first time point included in the actual deformation data of the cultural relic;

[0022] Based on the time fractal feature of the cultural relic, a second fitness value of the cultural relic is calculated.

[0023] In a possible implementation, the calculating the fourth fitness value of the cultural relic based on the actual deformation amounts monitored at the multiple monitoring points at the second time points included in the actual deformation data of the cultural relic includes:

[0024] Calculating a deformation prediction probability value of the cultural relic based on actual deformation amounts monitored at multiple monitoring points at each second time point included in the actual deformation data of the cultural relic;

[0025] Based on the deformation prediction probability value of the cultural relic, a fourth fitness value of the cultural relic is calculated.

[0026] In a possible implementation, obtaining the individual fitness value of the cultural relic based on the first fitness value, the second fitness value, the third fitness value, and the fourth fitness value of the cultural relic includes:

[0027] The average of the first fitness value, the second fitness value, the third fitness value and the fourth fitness value of the cultural relic is calculated as the individual fitness value of the cultural relic.

[0028] In a possible implementation, the external environment data includes: spatial location information, temperature information, and humidity information.

[0029] In a possible implementation, the internal basic data includes: geometric information, material properties, mechanical characteristics, three-dimensional models, images, basic information, detailed description information, and data association information.

[0030] In a possible implementation, before inputting the internal basic data and the external environment data of the plurality of cultural relics into the back propagation neural network to obtain the predicted deformation data of the plurality of cultural relics, the method further includes:

[0031] The internal basic data and the external environment data are preprocessed, wherein the preprocessing includes one or more of the following processes: outlier removal, missing value filling, continuous value normalization, and discrete value encoding.

[0032] The second aspect of the present application provides a preventive protection device for cultural relics, comprising:

[0033] A data acquisition module, used to acquire internal basic data and external environmental data of a plurality of cultural relics, as well as actual deformation data of the plurality of cultural relics;

[0034] A first prediction module is used to input the internal basic data and external environmental data of the plurality of cultural relics into a back propagation neural network to obtain predicted deformation data of the plurality of cultural relics;

[0035] A fitness calculation module, used to determine individual fitness values ​​of the plurality of cultural relics based on the actual deformation data and the predicted deformation data of the plurality of cultural relics;

[0036] A parameter optimization module, used for performing a genetic algorithm operation based on the individual fitness values ​​of the plurality of cultural relics to obtain an optimized parameter value of the back propagation neural network;

[0037] A model optimization module, used to optimize the back propagation neural network based on the optimization parameter value to obtain an optimized genetic algorithm optimized back propagation neural network model;

[0038] The second prediction module is used to predict the deformation data of the target cultural relic based on the genetic algorithm optimized back propagation neural network model.

[0039] The third aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the method for preventive protection of cultural relics according to the first aspect or any implementation method of the first aspect.

[0040] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0041] The memory is used to store computer programs;

[0042] The processor is used to execute the computer program so that the electronic device can implement the cultural relics preventive protection method of the first aspect or any implementation method of the first aspect.

[0043] A fifth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can perform the method for preventive protection of cultural relics according to the first aspect or any implementation method of the first aspect.

[0044] By means of the above technical scheme, the preventive protection method of cultural relics provided by the present application obtains the internal basic data and external environmental data of multiple cultural relics, as well as the actual deformation data of multiple cultural relics; inputs the internal basic data and external environmental data of multiple cultural relics into the back propagation neural network to obtain the predicted deformation data of multiple cultural relics; calculates the fitness values ​​of multiple cultural relics based on the actual deformation data and predicted deformation data of multiple cultural relics; performs genetic algorithm operation based on the fitness values ​​of multiple cultural relics to obtain the optimized parameter values ​​of the back propagation neural network; optimizes the back propagation neural network based on the optimized parameter values ​​to obtain the optimized genetic algorithm optimized back propagation neural network model; predicts the deformation data of the target cultural relics based on the genetic algorithm optimized back propagation neural network model. It can be seen that the present application can find the global optimal model parameters based on the genetic algorithm to obtain the optimized parameter values, and can train the optimal genetic algorithm optimized back propagation neural network model based on the preferred parameter values, so as to accurately predict the deformation data of the target cultural relics. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0046] Figure 1 A schematic diagram of a system architecture provided for this application;

[0047] Figure 2 A schematic diagram of an optional hardware structure of the terminal 100 provided in this application;

[0048] Figure 3 A schematic diagram of the structure of a server 200 provided in this application;

[0049] Figure 4 A schematic diagram of a preventive protection method for cultural relics provided in this application;

[0050] Figure 5 A schematic diagram of the structure of a preventive protection device for cultural relics provided in this application;

[0051] Figure 6 A schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0052] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0053] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0054] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0055] See also Figure 1 , Figure 1 A schematic diagram of a system architecture is shown. The system may include a terminal 100 and a server 200. The server 200 may include one or more servers ( Figure 1 In the example, a server is included, and the server 200 can provide the method provided in the embodiment of the present application for one or more terminals.

[0056] Among them, an application can be installed on the terminal 100, and the above application and web page can provide an interface. The terminal 100 can receive relevant parameters entered by the user on the interface and send the above parameters to the server 200. The server 200 can obtain processing results based on the received parameters and return the processing results to the terminal 100.

[0057] It should be understood that in some optional implementations, the terminal 100 can also complete the action of obtaining the processing result based on the received parameters by itself without the cooperation of the server, and the embodiments of the present application are not limited to this.

[0058] Next describe Figure 1 The product form of the mid-terminal 100;

[0059] The terminal 100 in the embodiment of the present application can be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc., and the embodiment of the present application does not impose any restrictions on this.

[0060] Figure 2 An optional hardware structure diagram of the terminal 100 is shown.

[0061] refer to Figure 2 As shown, the terminal 100 may include a radio frequency unit 110, a memory 120, an input unit 130, a display unit 140, a camera 150 (optional), an audio circuit 160 (optional), a speaker 161 (optional), a microphone 162 (optional), an earphone jack 163 (optional), a processor 170, an external interface 180, a power supply 190 and other components. Those skilled in the art will appreciate that Figure 2 These are merely examples of terminals or multi-function devices and do not constitute limitations on the terminals or multi-function devices, which may include more or fewer components than those shown in the figures, or combinations of certain components, or different components.

[0062] The input unit 130 can be used to receive input digital or character information, and generate key signal input related to the user settings and function control of the portable multifunctional device. Specifically, the input unit 130 may include a touch screen 131 (optional) and / or other input devices 132. The touch screen 131 can collect the user's touch operations on or near it (such as the user's operation on or near the touch screen using any suitable object such as fingers, joints, stylus, etc.), and drive the corresponding connection device according to a pre-set program. The touch screen can detect the user's touch action on the touch screen, convert the touch action into a touch signal and send it to the processor 170, and can receive and execute the command sent by the processor 170; the touch signal at least includes the touch point coordinate information. The touch screen 131 can provide an input interface and an output interface between the terminal 100 and the user. In addition, the touch screen can be implemented using multiple types such as resistive, capacitive, infrared and surface acoustic wave. In addition to the touch screen 131, the input unit 130 can also include other input devices. Specifically, other input devices 132 may include, but are not limited to, one or more of a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, a joystick, and the like.

[0063] Among them, the input device 132 can receive input data and the like.

[0064] The display unit 140 may be used to display information input by a user or provided to a user, various menus of the terminal 100, an interactive interface, file display, and / or playback of any multimedia file.

[0065] The memory 120 can be used to store instructions and data. The memory 120 can mainly include an instruction storage area and a data storage area. The data storage area can store various data, such as multimedia files, texts, etc.; the instruction storage area can store software units such as operating systems, applications, instructions required for at least one function, or their subsets and extensions. It can also include a non-volatile random access memory; provide the processor 170 with hardware, software and data resources including management of computing and processing equipment, and support control software and applications. It is also used for the storage of multimedia files, and the storage of running programs and applications.

[0066] The processor 170 is the control center of the terminal 100. It uses various interfaces and lines to connect various parts of the entire terminal 100. By running or executing instructions stored in the memory 120 and calling data stored in the memory 120, it executes various functions of the terminal 100 and processes data, thereby controlling the terminal device as a whole. Optionally, the processor 170 may include one or more processing units; preferably, the processor 170 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application program, and the modem processor mainly processes wireless communication. It is understandable that the above-mentioned modem processor may not be integrated into the processor 170. In some embodiments, the processor and the memory may be implemented on a single chip, and in some embodiments, they may also be implemented separately on separate chips. The processor 170 may also be used to generate corresponding operation control signals, send them to corresponding components of the computing and processing device, read and process data in the software, especially read and process data and programs in the memory 120, so that each functional module therein performs corresponding functions, thereby controlling the corresponding components to act according to the requirements of the instructions.

[0067] Among them, the memory 120 can be used to store software codes related to the preventive protection method of cultural relics, the processor 170 can execute the steps of the preventive protection method of cultural relics, and can also schedule other units (such as the above-mentioned input unit 130 and display unit 140) to realize corresponding functions.

[0068] The radio frequency unit 110 (optional) can be used for receiving and sending information or receiving and sending signals during a call, for example, after receiving the downlink information of the base station, it is sent to the processor 170 for processing; in addition, the designed uplink data is sent to the base station. Generally, the RF circuit includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (Low Noise Amplifier, LNA), a duplexer, etc. In addition, the radio frequency unit 110 can also communicate with network devices and other devices through wireless communication. The wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobile Communication (Global System of Mobile Communication, GSM), General Packet Radio Service (General Packet Radio Service, GPRS), Code Division Multiple Access (Code Division Multiple Access, CDMA), Wideband Code Division Multiple Access (Wideband Code Division Multiple Access, WCDMA), Long Term Evolution (Long Term Evolution, LTE), email, Short Messaging Service (SMS), etc.

[0069] In this embodiment of the present application, the RF unit 110 can send data to the server 200 and receive processing results sent by the server 200.

[0070] It should be understood that the radio frequency unit 110 is optional and can be replaced by other communication interfaces, such as a network port.

[0071] The terminal 100 also includes a power supply 190 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 170 through a power management system, so that the power management system can manage functions such as charging, discharging, and power consumption.

[0072] The terminal 100 further includes an external interface 180 , which may be a standard Micro USB interface or a multi-pin connector, and may be used to connect the terminal 100 to communicate with other devices, or to connect a charger to charge the terminal 100 .

[0073] Although not shown, the terminal 100 may also include a flashlight, a wireless fidelity (WiFi) module, a Bluetooth module, sensors with different functions, etc., which are not described in detail here. Some or all of the methods described below may be applied in the following embodiments. Figure 2 In the terminal 100 shown.

[0074] Next describe Figure 1 The product form of the server 200;

[0075] Figure 3 A structural diagram of a server 200 is provided, such as Figure 3 As shown, the server 200 includes a bus 201, a processor 202, a communication interface 203, and a memory 204. The processor 202, the memory 204, and the communication interface 203 communicate with each other via the bus 201.

[0076] The bus 201 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0077] The processor 202 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0078] The memory 204 may include a volatile memory, such as a random access memory (RAM). The memory 204 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0079] The memory 204 may be used to store software codes related to the preventive protection method for cultural relics, and the processor 202 may execute the steps of the preventive protection method for cultural relics of the chip, and may also schedule other units to implement corresponding functions.

[0080] It should be understood that the above-mentioned terminal 100 and server 200 can be centralized or distributed devices, and the processors in the above-mentioned terminal 100 and server 200 (such as processor 170 and processor 202) can be hardware circuits (such as application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), general-purpose processors, DSPs, microprocessors or microcontrollers, etc.), or a combination of these hardware circuits. For example, the processor can be a hardware system with an instruction execution function, such as a CPU, DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the above-mentioned hardware systems without an instruction execution function and hardware systems with an instruction execution function.

[0081] The present application provides a method for preventive protection of cultural relics. The preventive protection method for cultural relics of the present application is described in detail below in conjunction with the accompanying drawings.

[0082] Reference Figure 4 , Figure 4 A schematic flow chart of a method for preventive protection of cultural relics provided in an embodiment of the present application, the method may include:

[0083] Step S401: Acquire internal basic data and external environment data of multiple cultural relics, as well as actual deformation data of multiple cultural relics.

[0084] Specifically, the relevant data of multiple cultural relics can be used as training data to train a genetic algorithm optimized back propagation neural network (GA-BP) model, so as to predict the deformation data of cultural relics based on the trained GA-BP model. The GA-BP model is an optimization algorithm that combines the genetic algorithm (GA) and the back propagation neural network (BPNN).

[0085] In this embodiment, the relevant data of the above-mentioned multiple cultural relics include internal basic data and external environmental data of the multiple cultural relics, as well as actual deformation data of the multiple cultural relics, wherein the internal basic data and external environmental data can be used as input data of the GA-BP model, and the actual deformation data is used as an annotation label for training the GA-BP model.

[0086] Optionally, the above-mentioned internal basic data includes one or more of the following data: geometric information, material properties, mechanical characteristics, three-dimensional models, images, basic information, detailed description information, and data association information.

[0087] Among them, geometric information includes information such as the size and shape of the target cultural relics, material properties include the material type and physical and chemical properties used in the target cultural relics, and mechanical information includes data such as the stress and strain of the target cultural relics under different loads.

[0088] The above-mentioned three-dimensional model and image can be obtained by laser scanning or photogrammetry. Of course, the three-dimensional model and image can also be obtained by other methods, which are not specifically limited in this application.

[0089] The data association information is, for example, the relationship between materials and mechanical properties.

[0090] Optionally, the external environment data includes one or more of the following data: spatial location information, temperature information and humidity information.

[0091] Optionally, external environmental data can be monitored and recorded in real time by sensors installed in the target cultural relics storage area.

[0092] Optionally, the actual deformation data includes: the actual deformation amount of the cultural relic. In order to obtain a suitable individual fitness value in the genetic algorithm later, the actual deformation amount of the cultural relic can be described from multiple perspectives. For example, the actual deformation amount of the cultural relic may include: the actual deformation amount of multiple preset feature dimensions, the actual deformation amount of multiple first time points, and the actual deformation amount of multiple monitoring points monitored at multiple second time points.

[0093] Optionally, the multiple preset feature dimensions refer to dimensions that affect the degree of deformation of the cultural relics, such as time dimension, temperature dimension, etc. For example, the multiple preset feature dimensions include: 5 different time points (such as 1 hour, 2 hours, 4 hours, 8 hours and 16 hours) and 5 different temperature values ​​(such as 22°, 24°, 26°, 28° and 30°).

[0094] The first time point, the second time point, and the time points included in the plurality of preset characteristic dimensions may be the same or different.

[0095] Of course, the above-mentioned actual deformation data may also include others, which are not specifically limited in this application.

[0096] Step S402: input the internal basic data and external environmental data of the plurality of cultural relics into a back propagation neural network to obtain predicted deformation data of the plurality of cultural relics.

[0097] Specifically, in this embodiment, a back propagation neural network BP can be initialized, and predicted deformation data of multiple cultural relics can be obtained based on the initialized BP prediction.

[0098] Step S403: determining individual fitness values ​​of the plurality of cultural relics based on the actual deformation data and the predicted deformation data of the plurality of cultural relics.

[0099] As described above, the actual deformation data of each cultural relic may include the actual deformation amounts of multiple preset feature dimensions, the actual deformation amounts of multiple first time points, and the actual deformation amounts monitored by multiple monitoring points at multiple second time points. Then, in one possible implementation method, this embodiment may determine the individual fitness value of each cultural relic based on at least one of the above actual deformation amounts and / or predicted deformation data.

[0100] For example, in a first embodiment, the individual fitness value of a cultural relic can be determined based on the actual deformation amount of multiple preset feature dimensions; in a second embodiment, the individual fitness value of a cultural relic can be determined based on the actual deformation amount of multiple first time points; in a third embodiment, the individual fitness value of a cultural relic can be determined based on the actual deformation amount monitored by multiple monitoring points at multiple second time points; in a fourth embodiment, the individual fitness value of a cultural relic can be determined based on the actual deformation amount of multiple preset feature dimensions, the actual deformation amount of multiple first time points, the actual deformation amount monitored by multiple monitoring points at multiple second time points, and predicted deformation data.

[0101] Of course, there may be other embodiments, which are not specifically limited in this application.

[0102] Step S404: Perform a genetic algorithm operation based on the individual fitness values ​​of the plurality of cultural relics to obtain an optimized parameter value of a back propagation neural network.

[0103] Specifically, the internal basic data and external environmental data of multiple cultural relics can be encoded into chromosomes respectively, and each encoded chromosome can be represented as a set of weights and thresholds (i.e., a set of BP parameters) of the back propagation neural network BP. Then, multiple cultural relics correspond to multiple sets of BP parameters.

[0104] In this step, genetic algorithm operations such as selection, crossover and mutation can be performed on multiple groups of BP parameters based on the individual fitness values ​​of multiple cultural relics to obtain a set of optimized parameter values ​​of BP.

[0105] Step S405: Optimize the back propagation neural network based on the optimized parameter values ​​to obtain an optimized genetic algorithm optimized back propagation neural network model.

[0106] Step S406: predicting the deformation data of the target cultural relic based on the genetic algorithm-optimized back propagation neural network model.

[0107] The cultural relics preventive protection method provided by the present application obtains the internal basic data and external environmental data of multiple cultural relics, as well as the actual deformation data of multiple cultural relics; inputs the internal basic data and external environmental data of multiple cultural relics into the back propagation neural network to obtain the predicted deformation data of multiple cultural relics; calculates the fitness values ​​of multiple cultural relics based on the actual deformation data and predicted deformation data of multiple cultural relics; performs genetic algorithm operation based on the fitness values ​​of multiple cultural relics to obtain the optimized parameter values ​​of the back propagation neural network; optimizes the back propagation neural network based on the optimized parameter values ​​to obtain the optimized genetic algorithm optimized back propagation neural network model; predicts the deformation data of the target cultural relics based on the genetic algorithm optimized back propagation neural network model. It can be seen that the present application can find the global optimal model parameters based on the genetic algorithm to obtain the optimized parameter values, and can train the optimal genetic algorithm optimized back propagation neural network model based on the preferred parameter values, so as to accurately predict the deformation data of the target cultural relics.

[0108] In some embodiments of the present application, for each of the multiple cultural relics provided in the above embodiments, the process of determining the individual fitness value of the cultural relic based on the actual deformation data and the predicted deformation data of the cultural relic in step S403 is introduced.

[0109] Here, the process of "determining the individual fitness value of the cultural relic based on the actual deformation data and the predicted deformation data of the cultural relic" can be implemented in many ways. This embodiment provides but is not limited to the following implementation methods.

[0110] The first implementation method: based on the actual deformation amounts of multiple preset feature dimensions included in the actual deformation data of the cultural relic, the first fitness value of the cultural relic can be calculated, and the first fitness value of the cultural relic can be used as the individual fitness value of the cultural relic.

[0111] Optionally, the above-mentioned process of "calculating the first fitness value of the cultural relic based on the actual deformation amounts of multiple preset feature dimensions contained in the actual deformation data of the cultural relic" may include: calculating the cultural relic deformation feature matrix of the cultural relic based on the actual deformation amounts of multiple preset feature dimensions contained in the actual deformation data of the cultural relic, and then calculating the first fitness value of the cultural relic based on the cultural relic deformation feature matrix of the cultural relic and the actual deformation amounts of multiple preset feature dimensions.

[0112] Optionally, the actual deformation amount of each preset characteristic dimension includes the actual deformation amount of each preset characteristic dimension at each coordinate point of the cultural relic. Then, the following formula (1) can be used to calculate the cultural relic deformation characteristics at each coordinate point of the cultural relic.

[0113] Formula (1)

[0114] in, Indicates The preset feature dimensions are at the coordinate points of the cultural relics. The actual deformation under Indicates that the cultural relic is at the coordinate point The deformation characteristics of cultural relics under Indicates the total number of preset feature dimensions. For example, if multiple preset feature dimensions include: 5 different time points and 5 different temperature values, then The value of is 10.

[0115] Each coordinate point of the cultural relic is calculated according to the above formula (1), and the deformation characteristics of the cultural relic at each coordinate point can be obtained.

[0116] In this embodiment, the deformation characteristics of the cultural relic at each coordinate point can be calculated according to For the line, The columns constitute the cultural relic deformation feature matrix.

[0117] Optionally, the above-mentioned process of "calculating the first fitness value of the cultural relic based on the cultural relic deformation feature matrix and the actual deformation of multiple preset feature dimensions" may include: calculating the total deformation of the cultural relic based on the cultural relic deformation feature matrix of the cultural relic, calculating the variable coefficient of each preset feature dimension based on the total deformation of the cultural relic and the actual deformation of each preset feature dimension, and obtaining the first fitness value of the cultural relic based on the variable coefficients of multiple preset feature dimensions and the actual deformation of multiple preset feature dimensions.

[0118] As described above, the cultural relic deformation feature matrix of the cultural relic is composed of the cultural relic deformation features at various coordinate points. Therefore, in this embodiment, the sum of the cultural relic deformation features at various coordinate points can be calculated, and the sum is used as the total deformation amount of the cultural relic. That is, the total deformation amount of the cultural relic is calculated using the following formula (2).

[0119] Formula (2)

[0120] in, Indicates the total deformation of the artifact.

[0121] In a possible implementation, the above process of "calculating the variable coefficient of each preset feature dimension based on the total deformation of the cultural relic and the actual deformation of each preset feature dimension, and obtaining the first fitness value of the cultural relic based on the variable coefficients of multiple preset feature dimensions and the actual deformation of multiple preset feature dimensions" can be calculated in a more fine-grained manner according to the coordinate points. Specifically, the variable coefficient of each preset dimension at each coordinate point can be calculated using the following formula (3).

[0122] Optionally, in this embodiment, the variable coefficient of each preset dimension at each coordinate point can be multiplied by the actual deformation of each preset dimension at each coordinate point to obtain the product value of each preset dimension at each coordinate point, and then the sum of the product values ​​of each preset dimension at each coordinate point is calculated, and the sum value is used as the first fitness value of the cultural relic. The above calculation process is shown in the following formula (4).

[0123] Formula (3)

[0124] Formula (4)

[0125] in, Indicates The preset feature dimensions are at the coordinate points of the cultural relics. The variable coefficients under Indicates the first fitness value of the artifact.

[0126] This embodiment uses the deformation feature matrix to calculate the first fitness value, which is more suitable for multi-dimensional space or feature processing scenarios. That is, if it is necessary to comprehensively evaluate the influence of multiple preset feature dimensions on the prediction of cultural relic deformation, then the first fitness value can be used as the individual fitness value of the cultural relic, so as to better evaluate the adaptability of the GA-BP model to multi-dimensional space or feature complexity.

[0127] The second implementation method: the second fitness value of the cultural relic can be calculated based on the actual deformation amount of each first time point included in the actual deformation data of the cultural relic, and the second fitness value of the cultural relic is used as the individual fitness value of the cultural relic.

[0128] Optionally, the process of "calculating the second fitness value of the cultural relic based on the actual deformation amount of each first time point included in the actual deformation data of the cultural relic" may include: calculating the time fractal characteristics of the cultural relic based on the actual deformation amount of each first time point included in the actual deformation data of the cultural relic, and then calculating the second fitness value of the cultural relic based on the time fractal characteristics of the cultural relic.

[0129] For example, optionally, the temporal fractal feature of the cultural relic may be calculated using the following formula (5), and the second fitness value of the cultural relic may be calculated using the following formula (6).

[0130] Formula (5)

[0131] Formula (6)

[0132] in, Represents the temporal fractal characteristics of cultural relics, represents the second fitness value of the artifact, Indicates the actual deformation of the cultural relic at each first time point, Indicates the first point in time.

[0133] For example, assuming that the actual deformation at each first time point For: First Year hour, ; Second year hour, ; Fourth year hour, ; Eighth Year hour, .

[0134] Then we can calculate and Then in and A straight line is fitted between them, and the slope of the straight line is .

[0135] This embodiment uses the time fractal feature to calculate the second fitness value, which is more suitable for the scenario of time series analysis. That is, if it is necessary to consider the dynamic characteristics of the deformation of cultural relics over time, then the second fitness value can be used as the individual fitness value of the cultural relics, so as to better evaluate the adaptability of the GA-BP model to time complexity.

[0136] The third implementation method: based on the actual deformation data and predicted deformation data of the cultural relic, the cultural relic deformation prediction mapping error value of the cultural relic can be calculated, and then based on the cultural relic deformation prediction mapping error value of the cultural relic, the third fitness value of the cultural relic can be calculated, and the third fitness value of the cultural relic can be used as the individual fitness value of the cultural relic.

[0137] In a preferred implementation, the deformation errors of the cultural relic and other cultural relics can be considered together to obtain a third fitness value that can better reflect the error between the predicted output of the GA-BP model and the actual deformation, and the third fitness value at this time is used as the individual fitness value of the cultural relic. Then, the following formula (7) can be used to calculate the cultural relic deformation prediction mapping error value of the cultural relic.

[0138] Formula (7)

[0139] in, Indicates the artifact deformation prediction mapping error value of the artifact; represents the sum of squared errors of multiple artifacts, and its calculation formula is as follows (8): Indicates the number of training batches of the BP neural network. For example, if 100 trainings are performed, then ; Indicates the number of features of the model input data. For example, if the internal basic data and external environment data mentioned above contain 10 dimensions of data (such as humidity, temperature, cultural relic size, material properties, etc., a total of 10 dimensions), then .

[0140] Formula (8)

[0141] in, Indicates the total number of multiple artifacts, It indicates the first The predicted deformation data of each cultural relic (specifically, the predicted deformation amount), Indicates The actual deformation data of each cultural relic (specifically, the actual deformation amount, where the actual deformation amount refers to the total deformation amount without distinguishing between preset feature dimensions, monitoring points and time points).

[0142] It should be noted that formula (8) is a value calculated by considering the deformation errors of multiple cultural relics (i.e., all cultural relics in the training sample), so the cultural relic deformation prediction mapping error values ​​of multiple cultural relics are the same.

[0143] Furthermore, the third fitness value of the cultural relic can be calculated using the following formula (9).

[0144] Formula (9)

[0145] in, Indicates the third fitness value of the artifact.

[0146] This embodiment uses the cultural relic deformation prediction mapping error value to calculate the third fitness value, which is more suitable for scenarios where the core goal is to reduce the prediction error of the GA-BP model. That is, if it is necessary to make the error between the cultural relic prediction deformation data output by the GA-BP model and the actual deformation data of the cultural relic as small as possible, the third fitness value can be used as the individual fitness value of the cultural relic.

[0147] A fourth implementation method: based on the actual deformation amounts monitored at each second time point by multiple monitoring points included in the actual deformation data of the cultural relic, the fourth fitness value of the cultural relic can be calculated, and the fourth fitness value of the cultural relic can be used as the individual fitness value of the cultural relic.

[0148] Optionally, the process of "calculating the fourth fitness value of the cultural relic based on the actual deformation amounts monitored at each second time point by multiple monitoring points included in the actual deformation data of the cultural relic" may include: calculating the deformation prediction probability value of the cultural relic based on the actual deformation amounts monitored at each second time point by multiple monitoring points included in the actual deformation data of the cultural relic, and then calculating the fourth fitness value of the cultural relic based on the deformation prediction probability value of the cultural relic.

[0149] For example, optionally, the deformation prediction probability value of the cultural relic can be calculated using the following formula (10), and the fourth fitness value of the cultural relic can be calculated using the following formula (11).

[0150] Formula (10)

[0151] Formula (11)

[0152] in, represents the marginal integral of the artifact deformation prediction, represents the marginal likelihood of the deformation prediction of the artifact hyperparameters, represents the maximum number of iterations of the genetic algorithm, Indicates the second time point, represents the predicted probability value of the deformation of the cultural relic, Indicates the fourth fitness value of the artifact.

[0153] right , , The further explanation is as follows:

[0154] Specifically, it represents the accumulated deformation or the total integral value of the deformation on the cultural relic structure, that is, the total integral value of the actual deformation monitored by the multiple monitoring points at each second time point. The accumulated deformation data on the cultural relic structure can be collected by a displacement sensor (such as an inclinometer, an inclinometer, etc.) installed on the cultural relic structure, and these deformation data are integrated to obtain the accumulated deformation, that is, In this application, It describes the impact of deformation on the structure of cultural relics and is an important indicator for evaluating deformation trends and overall stability.

[0155] For example, suppose on the first day In the first day of observation, the cumulative displacement of the wall detected by monitoring point A is 3mm, and the cumulative displacement of the wall detected by monitoring point B is 2mm. (mm).

[0156] It represents the credibility and volatility of the GA-BP model under specific conditions in the process of cultural relic deformation prediction. The smaller the value of is, the more stable the GA-BP model is in predicting deformation.

[0157] Optional, above The calculation formula can be ,in, represents the number of monitoring points, Indicates The cumulative deformation of the cultural relics was detected by each monitoring point. Represents the mean of the predicted deformations of multiple artifacts.

[0158] For example, suppose on the first day The cumulative displacements of the wall detected by monitoring points A, B, C, D and E were 4.1mm, 5.0mm, 4.8mm, 5.2mm and 4.9mm respectively. ,but .

[0159] It is a hyperparameter set manually during the training process of the GA-BP model, representing the maximum number of iterations of the genetic algorithm. The parameters can make the GA-BP model converge within a reasonable time. For example, after experiments, it was found that when When it is 50, the GA-BP model can converge to the optimal solution better, so 50 is selected as the maximum number of iterations of the genetic algorithm.

[0160] In this embodiment, The higher the value, the higher the accuracy of the GA-BP model in predicting the deformation of cultural relics. According to the prediction results, corresponding protective measures can be taken in advance. If the value is low (for example, lower than 0.5), it indicates that the uncertainty of the GA-BP model prediction is large, and it may be necessary to increase the training data or adjust the model parameters (such as increasing the number of BP network layers or adjusting the maximum number of GA iterations) to improve the prediction accuracy of the GA-BP model.

[0161] This embodiment uses the deformation prediction probability value to calculate the fourth fitness value, which is more suitable for scenarios where the core goal is to predict whether a cultural relic will undergo a certain degree of deformation. That is, if it is necessary to predict whether a cultural relic will undergo a certain degree of deformation, the fourth fitness value can be used as the individual fitness value of the cultural relic.

[0162] It should be noted that the above four implementation methods are only examples. In addition, other implementation methods can also be used. For example, according to specific goals, at least two fitness values ​​are selected from the first fitness value, the second fitness value, the third fitness value and the fourth fitness value for fusion to obtain the individual fitness value of the cultural relic.

[0163] For example, in order to achieve multi-objective optimization, this embodiment can obtain the individual fitness value of the cultural relic based on the first fitness value, second fitness value, third fitness value and fourth fitness value of the cultural relic after calculating the first fitness value, second fitness value, third fitness value and fourth fitness value of the cultural relic.

[0164] Optionally, an average of the first fitness value, the second fitness value, the third fitness value and the fourth fitness value of the cultural relic may be calculated as the individual fitness value of the cultural relic.

[0165] In summary, this embodiment provides a variety of methods for determining the individual fitness values ​​of cultural relics, which can measure the degree of adaptation of cultural relics to deformation from multiple perspectives, thereby improving the accuracy of subsequent GA-BP model training.

[0166] In some embodiments of the present application, before the internal basic data and external environmental data of multiple cultural relics are input into the back propagation neural network in the previous step S402 to obtain the predicted deformation data of the multiple cultural relics, the present embodiment can also preprocess the internal basic data and the external environmental data so that the preprocessed data can be input into BP as input data.

[0167] Optionally, the preprocessing includes one or more of the following processes: outlier removal, missing value filling, continuous value normalization and discrete value encoding.

[0168] Optionally, statistical methods and standard deviation methods based on outliers can be used to remove outliers in the internal basic data and / or external environmental data to prevent a small number of outliers from affecting the predictive ability of the GA-BP model.

[0169] Optionally, the above abnormal values ​​can also be corrected to reasonable normal values.

[0170] Optionally, interpolation methods (such as mean imputation, median imputation) or regression models can be used to estimate and fill in missing values ​​in internal basic data and / or external environmental data.

[0171] Optionally, continuous values ​​in the internal basic data and / or external environmental data (such as temperature, length, etc.) may be normalized to eliminate the influence of different dimensions and make the data comparable.

[0172] Optionally, discrete values ​​in the internal basic data and / or external environmental data (such as material properties and other data) may be encoded, such as one-hot encoding, to be converted into a form suitable for model processing.

[0173] This embodiment preprocesses the internal basic data and the external environment data to make the preprocessed data more suitable as input data for the GA-BP model. At the same time, the preprocessing process can also improve the prediction accuracy of the GA-BP model to a certain extent.

[0174] A preventive protection method for cultural relics provided in an embodiment of the present application is introduced above, and a device for executing the above-mentioned preventive protection method for cultural relics will be introduced below.

[0175] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of a preventive protection device for cultural relics provided in an embodiment of the present application. Figure 5 As shown, the device may include:

[0176] The data acquisition module 501 is used to acquire the internal basic data and external environment data of multiple cultural relics, as well as the actual deformation data of multiple cultural relics;

[0177] The first prediction module 502 is used to input the internal basic data and external environmental data of the plurality of cultural relics into the back propagation neural network to obtain the predicted deformation data of the plurality of cultural relics;

[0178] A fitness calculation module 503, for determining individual fitness values ​​of the plurality of cultural relics based on actual deformation data and predicted deformation data of the plurality of cultural relics;

[0179] A parameter optimization module 504 is used to perform a genetic algorithm operation based on the individual fitness values ​​of the plurality of cultural relics to obtain an optimized parameter value of the back propagation neural network;

[0180] A model optimization module 505 is used to optimize the back propagation neural network based on the optimization parameter value to obtain an optimized genetic algorithm optimized back propagation neural network model;

[0181] The second prediction module 506 is used to predict the deformation data of the target cultural relic based on the genetic algorithm optimized back propagation neural network model.

[0182] Optionally, when the fitness calculation module determines the individual fitness value of each of the plurality of cultural relics based on the actual deformation data and the predicted deformation data of the cultural relic, it can be specifically used to:

[0183] Calculating a first fitness value of the cultural relic based on actual deformation amounts of multiple preset feature dimensions included in the actual deformation data of the cultural relic;

[0184] Calculating a second fitness value of the cultural relic based on the actual deformation amount at each first time point included in the actual deformation data of the cultural relic;

[0185] Calculating a cultural relic deformation prediction mapping error value of the cultural relic based on the actual deformation data and the predicted deformation data of the cultural relic, and calculating a third fitness value of the cultural relic based on the cultural relic deformation prediction mapping error value of the cultural relic;

[0186] Calculating a fourth fitness value of the cultural relic based on actual deformation amounts monitored at multiple monitoring points at each second time point included in the actual deformation data of the cultural relic;

[0187] Based on the first fitness value, the second fitness value, the third fitness value and the fourth fitness value of the cultural relic, an individual fitness value of the cultural relic is obtained.

[0188] Optionally, when the fitness calculation module calculates the first fitness value of the cultural relic based on the actual deformation amounts of multiple preset feature dimensions included in the actual deformation data of the cultural relic, it can be specifically used to:

[0189] Calculating a cultural relic deformation feature matrix of the cultural relic based on actual deformation amounts of multiple preset feature dimensions included in the actual deformation data of the cultural relic;

[0190] Based on the cultural relic deformation feature matrix of the cultural relic and actual deformation amounts of multiple preset feature dimensions, a first fitness value of the cultural relic is calculated.

[0191] Optionally, when the fitness calculation module calculates the second fitness value of the cultural relic based on the actual deformation amount at each first time point included in the actual deformation data of the cultural relic, it can be specifically used to:

[0192] Calculating the time fractal feature of the cultural relic based on the actual deformation amount at each first time point included in the actual deformation data of the cultural relic;

[0193] Based on the time fractal feature of the cultural relic, a second fitness value of the cultural relic is calculated.

[0194] Optionally, when the fitness calculation module calculates the fourth fitness value of the cultural relic based on the actual deformation amounts monitored at the multiple monitoring points at the second time points included in the actual deformation data of the cultural relic, it can be specifically used to:

[0195] Calculating a deformation prediction probability value of the cultural relic based on actual deformation amounts monitored at multiple monitoring points at each second time point included in the actual deformation data of the cultural relic;

[0196] Based on the deformation prediction probability value of the cultural relic, a fourth fitness value of the cultural relic is calculated.

[0197] Optionally, when the above-mentioned fitness calculation module obtains the individual fitness value of the cultural relic based on the first fitness value, the second fitness value, the third fitness value and the fourth fitness value of the cultural relic, it is specifically used to: calculate the average value of the first fitness value, the second fitness value, the third fitness value and the fourth fitness value of the cultural relic as the individual fitness value of the cultural relic.

[0198] Optionally, the above external environment data includes: spatial location information, temperature information and humidity information.

[0199] Optionally, the above-mentioned internal basic data includes: geometric information, material properties, mechanical characteristics, three-dimensional models, images, basic information, detailed description information, and data association information.

[0200] Optionally, the preventive protection device for cultural relics provided in the embodiment of the present application may also include a preprocessing module.

[0201] The preprocessing module is used to preprocess the internal basic data and external environmental data of multiple cultural relics before inputting them into the back propagation neural network to obtain the predicted deformation data of the multiple cultural relics, wherein the preprocessing includes one or more of the following processes: outlier elimination, missing value filling, continuous value normalization and discrete value encoding.

[0202] The cultural relics preventive protection device provided in this application and the cultural relics preventive protection method provided in the previous text can correspond to each other. For details, please refer to the previous introduction and will not be repeated here.

[0203] The present application also provides an electronic device in an embodiment. Figure 6 As shown, it shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiment of the present application. The electronic device in the embodiment of the present application may include but is not limited to fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 6 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0204] like Figure 6As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 to a random access memory (RAM) 603. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0205] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a memory card, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0206] Also provided in an embodiment of the present application is a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any one of the preventive protection methods for cultural relics provided in the embodiments of the present application.

[0207] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any one of the preventive protection methods for cultural relics provided in the embodiment of the present application.

[0208] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0209] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0210] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0211] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A preventive protection method for cultural relics, characterized in that: include: Acquiring internal basic data and external environmental data of a plurality of cultural relics, as well as actual deformation data of the plurality of cultural relics; Inputting the internal basic data and external environmental data of the plurality of cultural relics into a back propagation neural network to obtain predicted deformation data of the plurality of cultural relics; Determining individual fitness values ​​of the plurality of cultural relics based on the actual deformation data and the predicted deformation data of the plurality of cultural relics; Performing a genetic algorithm operation based on the individual fitness values ​​of the plurality of cultural relics to obtain an optimized parameter value of the back propagation neural network; Optimizing the back propagation neural network based on the optimization parameter values ​​to obtain an optimized genetic algorithm optimized back propagation neural network model; The deformation data of the target cultural relic is predicted based on the genetic algorithm-optimized back-propagation neural network model.

2. The preventive protection method for cultural relics according to claim 1, characterized in that: For each of the plurality of cultural relics, determining an individual fitness value of the cultural relic based on the actual deformation data and the predicted deformation data of the cultural relic, comprising: Calculating a first fitness value of the cultural relic based on actual deformation amounts of multiple preset feature dimensions included in the actual deformation data of the cultural relic; Calculating a second fitness value of the cultural relic based on the actual deformation amount at each first time point included in the actual deformation data of the cultural relic; Calculating a cultural relic deformation prediction mapping error value of the cultural relic based on the actual deformation data and the predicted deformation data of the cultural relic, and calculating a third fitness value of the cultural relic based on the cultural relic deformation prediction mapping error value of the cultural relic; Calculating a fourth fitness value of the cultural relic based on actual deformation amounts monitored at multiple monitoring points at each second time point included in the actual deformation data of the cultural relic; Based on the first fitness value, the second fitness value, the third fitness value and the fourth fitness value of the cultural relic, an individual fitness value of the cultural relic is obtained.

3. The preventive protection method for cultural relics according to claim 2, characterized in that: The calculating the first fitness value of the cultural relic based on the actual deformation amounts of the plurality of preset feature dimensions included in the actual deformation data of the cultural relic comprises: Calculating a cultural relic deformation feature matrix of the cultural relic based on actual deformation amounts of multiple preset feature dimensions included in the actual deformation data of the cultural relic; Based on the cultural relic deformation feature matrix of the cultural relic and the actual deformation amounts of the plurality of preset feature dimensions, a first fitness value of the cultural relic is calculated.

4. The preventive protection method for cultural relics according to claim 2, characterized in that: The calculating the second fitness value of the cultural relic based on the actual deformation amount at each first time point included in the actual deformation data of the cultural relic includes: Calculating the time fractal feature of the cultural relic based on the actual deformation amount at each first time point included in the actual deformation data of the cultural relic; Based on the time fractal feature of the cultural relic, a second fitness value of the cultural relic is calculated.

5. The preventive protection method for cultural relics according to claim 2, characterized in that: The calculating the fourth fitness value of the cultural relic based on the actual deformation amounts monitored at the second time points by the multiple monitoring points included in the actual deformation data of the cultural relic comprises: Calculating a deformation prediction probability value of the cultural relic based on actual deformation amounts monitored at multiple monitoring points at each second time point included in the actual deformation data of the cultural relic; Based on the deformation prediction probability value of the cultural relic, a fourth fitness value of the cultural relic is calculated.

6. The preventive protection method for cultural relics according to claim 1, characterized in that: Before inputting the internal basic data and external environmental data of the plurality of cultural relics into the back propagation neural network to obtain the predicted deformation data of the plurality of cultural relics, the method further includes: The internal basic data and the external environment data are preprocessed, wherein the preprocessing includes one or more of the following processes: outlier removal, missing value filling, continuous value normalization, and discrete value encoding.

7. A preventive protection device for cultural relics, characterized in that: include: A data acquisition module, used to acquire internal basic data and external environmental data of a plurality of cultural relics, as well as actual deformation data of the plurality of cultural relics; A first prediction module is used to input the internal basic data and external environmental data of the plurality of cultural relics into a back propagation neural network to obtain predicted deformation data of the plurality of cultural relics; A fitness calculation module, used to determine individual fitness values ​​of the plurality of cultural relics based on the actual deformation data and the predicted deformation data of the plurality of cultural relics; A parameter optimization module, used for performing a genetic algorithm operation based on the individual fitness values ​​of the plurality of cultural relics to obtain an optimized parameter value of the back propagation neural network; A model optimization module, used to optimize the back propagation neural network based on the optimization parameter value to obtain an optimized genetic algorithm optimized back propagation neural network model; The second prediction module is used to predict the deformation data of the target cultural relic based on the genetic algorithm optimized back propagation neural network model.

8. A computer program product, characterized in that It comprises computer-readable instructions, and when the computer-readable instructions are executed on an electronic device, the electronic device implements the preventive protection method for cultural relics as claimed in any one of claims 1 to 6.

9. An electronic device, characterized in that: The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the preventive protection method for cultural relics as described in any one of claims 1 to 6.

10. A computer storage medium, characterized in that: The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the preventive protection method for cultural relics as described in any one of claims 1 to 6.

Images