A method, system, device and storage medium for predicting gradient response of nanobeam

Abstract

The present application provides a method, system, device and storage medium for predicting the gradient response of a nanobeam. The method comprises the following steps: obtaining a nanobeam strain data set of a target nanobeam, converting the nanobeam strain data set into a nanobeam strain sequence, determining the cohesive loss of the target nanobeam according to the nanobeam strain sequence, determining the nanobeam curvature of each nanobeam strain in the nanobeam strain data set according to the nanobeam strain data set and a real-time surface load, determining an extension decision factor corresponding to each nanobeam curvature according to the cohesive loss, determining multiple stress response feature prediction bases of the target nanobeam according to all the extension decision factors and the nanobeam strain data set, predicting the gradient response of the target nanobeam according to all the stress response feature prediction bases, and avoiding interference of external temperature on the prediction of the nanobeam gradient response.

Description

Technical Field

[0001] The present application relates to the field of nanobeam technology, and more specifically, to a method, system, device and storage medium for predicting the gradient response of a nanobeam. Background Art

[0002] A nanobeam is a structure at the micro-nanoscale, usually a nanoscale beam-shaped object, which is used to study fields such as nanomechanics, nanoelectronics and nanooptics. These nanobeams have special mechanical, electrical and optical properties, making them an important part of nanotechnology and nanodevice research.

[0003] The gradient response of a nanobeam usually involves a strain or displacement gradient that varies in space. The prediction of the gradient response of a nanobeam is a complex process that usually requires the intersection of multiple disciplines, including mechanics, physics, mathematics, and engineering. Accurate prediction requires comprehensive consideration of the material's constitutive properties, geometry, and gradient effects in order to more fully understand the behavior of the nanobeam under a gradient strain field. In the existing prediction process of the gradient response of nanobeams, the gradient response of the nanobeam is often predicted based on workers' experience and artificial data. External factors (such as temperature) can cause changes in the thermal vibrations of atoms in the nanobeam, causing changes in the performance of the nanobeam, resulting in deviations in the gradient response of the nanobeam predicted based on workers' experience and artificial data. Therefore, how to avoid the interference of external temperature on the prediction of the gradient response of the nanobeam has become an urgent problem to be solved by technicians in this field. Summary of the invention

[0004] The present application provides a method, system, device and storage medium for predicting the gradient response of a nanobeam to avoid interference of external temperature on the prediction of the gradient response of the nanobeam.

[0005] In a first aspect, the present application provides a method for predicting the gradient response of a nanobeam, comprising the following steps:

[0006] Starting a nanobeam gradient response test to obtain a nanobeam strain data set of a target nanobeam;

[0007] Converting the nanobeam strain data set into a nanobeam strain sequence, and determining the cohesive loss of the target nanobeam according to the nanobeam strain sequence;

[0008] Determining a nanobeam curvature of each nanobeam strain in the nanobeam strain dataset according to the nanobeam strain dataset and the real-time surface load;

[0009] Determine the extension decision factor corresponding to the curvature of each nanobeam according to the cohesive loss, and determine multiple stress response feature prediction bases of the target nanobeam according to all the extension decision factors and the nanobeam strain data set;

[0010] The gradient response of the target nanobeam is predicted using all stress response feature prediction bases.

[0011] In some embodiments, determining the cohesive loss of the target nanobeam according to the nanobeam strain sequence specifically includes:

[0012] Determining the nanobeam strain difference of each group of adjacent nanobeam strains in the nanobeam strain sequence;

[0013] Determining the strain trend of the nanobeam according to the strain differences of all the nanobeams;

[0014] The cohesive loss amount of the target nanobeam is determined according to the nanobeam strain trend and the nanobeam strain sequence.

[0015] In some embodiments, determining the cohesive loss of the target nanobeam according to the nanobeam strain trend and the nanobeam strain sequence specifically includes:

[0016] determining a nanobeam deviation amount for each nanobeam strain in the nanobeam strain sequence;

[0017] Determine a lower limit value and an upper limit value according to all the nanobeam deviations and the strain trend of the nanobeam;

[0018] The interval formed by the lower limit value and the upper limit value is used as the nanobeam interference domain;

[0019] The nanobeam interference field is converted into the cohesive loss amount of the target nanobeam.

[0020] In some embodiments, determining the nanobeam curvature of each nanobeam strain in the nanobeam strain dataset according to the nanobeam strain dataset and the real-time surface load specifically includes:

[0021] Get real-time surface loads;

[0022] determining a nanobeam topological quantity of each nanobeam strain in the nanobeam strain data set according to the real-time surface load;

[0023] Convert all nanobeam topological quantities into nanobeam topological sequences;

[0024] The nanobeam curvature of each nanobeam topological quantity in the nanobeam topological sequence is determined.

[0025] In some embodiments, determining the extension decision factor corresponding to the curvature of each nanobeam by the cohesive loss specifically includes:

[0026] Determine the amount of test time balancing;

[0027] Selecting a nanobeam curvature, and determining an extension decision factor of the nanobeam curvature according to the test time balance amount, the cohesive loss amount and the nanobeam curvature;

[0028] Repeat the above steps to determine the extension decision factors of the remaining nanobeam curvature.

[0029] In some embodiments, determining a plurality of stress response characteristic prediction bases of a target nanobeam according to all extension decision factors and the nanobeam strain data set specifically includes:

[0030] Get the test time balance;

[0031] determining an average value of all nanobeam strains in the nanobeam strain data set;

[0032] A plurality of stress response characteristic prediction bases of the target nanobeam are determined according to the test time balance amount, all extension decision factors and the average value of all nanobeam strains.

[0033] In some embodiments, the nanobeam strain in the nanobeam strain dataset is the strain of the target nanobeam caused by the stress applied to the target nanobeam at different test temperatures.

[0034] In a second aspect, the present application provides a prediction system for a nanobeam gradient response, comprising:

[0035] An acquisition module, used for acquiring a nanobeam strain data set of a target nanobeam after starting a nanobeam gradient response test;

[0036] A conversion module, used for converting the nanobeam strain data set into a nanobeam strain sequence, and determining the cohesive loss of the target nanobeam according to the nanobeam strain sequence;

[0037] A processing module, configured to determine a nanobeam curvature of each nanobeam strain in the nanobeam strain data set according to the nanobeam strain data set and a real-time surface load;

[0038] The processing module is further used to determine the extension decision factor corresponding to the curvature of each nanobeam according to the cohesive loss amount, and determine multiple stress response feature prediction bases of the target nanobeam according to all the extension decision factors and the nanobeam strain data set;

[0039] The execution module is used to predict the gradient response of the target nanobeam through all stress response feature prediction bases.

[0040] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned method for predicting the gradient response of a nanobeam.

[0041] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, wherein the computer program implements the above-mentioned method for predicting the gradient response of a nanobeam when executed by a processor.

[0042] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0043] In the prediction method, system, device and storage medium of the nanobeam gradient response provided by the present application, the nanobeam strain trend is determined by the nanobeam strain data set of the target nanobeam, the difference between the strains at different test temperatures is judged, and then the cohesion loss is determined according to the nanobeam strain trend. The cohesion loss is the damping effect of the nanobeam, so as to facilitate the prediction of the strain of the nanobeam. The nanobeam curvature of each nanobeam strain in the nanobeam strain data set is used to determine the elastic change degree of the target nanobeam between adjacent test temperatures according to the nanobeam curvature, so as to determine the elastic change degree of the target nanobeam between adjacent test temperatures according to the cohesion loss. The consumption and all the nanobeam curvatures determine the nanobeam decision domain, which is used to predict the rebound performance of the nanobeam under different surface loads at different test temperatures, and then obtain the stress response characteristic prediction base at each test temperature, which is the predicted value of the rebound performance of the nanobeam. Finally, the stress of the nanobeam at each test temperature is predicted according to the stress response characteristic prediction base at each test temperature and the surface load at each temperature. Compared with the prediction of the gradient response of the nanobeam based on workers' experience and manual data, the interference of external temperature on the prediction of the gradient response of the nanobeam is avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is an exemplary flow chart of a method for predicting a nanobeam gradient response according to some embodiments of the present application;

[0045] Figure 2 is an exemplary flow chart for determining the amount of cohesive loss according to some embodiments of the present application;

[0046] Figure 3 is an exemplary flow chart for determining the curvature of a nanobeam according to some embodiments of the present application;

[0047] Figure 4 is a schematic diagram of exemplary hardware and / or software of a system for predicting gradient response of a nanobeam according to some embodiments of the present application;

[0048] Figure 5 It is a schematic diagram of the structure of a computer device for implementing a method for predicting the gradient response of a nanobeam according to some embodiments of the present application. DETAILED DESCRIPTION

[0049] The core of the present application is to determine the nanobeam strain sequence through the nanobeam strain data set, determine the cohesive loss of the target nanobeam according to the nanobeam strain sequence, determine the nanobeam curvature of each nanobeam strain in the nanobeam strain data set according to the nanobeam strain data set and the real-time surface load, determine the extension decision factor corresponding to each nanobeam curvature through the cohesive loss, determine multiple stress response feature prediction bases of the target nanobeam according to all the extension decision factors and the nanobeam strain data set, predict the gradient response of the target nanobeam through all the stress response feature prediction bases, and avoid the interference of external temperature on the prediction of the nanobeam gradient response.

[0050] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of a method for predicting a nanobeam gradient response according to some embodiments of the present application, wherein the method 100 for predicting a nanobeam gradient response mainly comprises the following steps:

[0051] In step 101, a nanobeam gradient response test is started to obtain a nanobeam strain data set of a target nanobeam.

[0052] In specific implementation, the nanobeam gradient response test is started, and the nanobeam strain data set of the target nanobeam is obtained through the nanobeam database. It should be noted that the nanobeam strain data set in the present application is a collection of all nanobeam strains, wherein the nanobeam strain in the nanobeam strain data set is the strain of the target nanobeam caused by the stress applied to the target nanobeam at different test temperatures, and the test temperature ranges from -50°C to 50°C. The test is started from -50°C, and each change of 5°C corresponds to a test temperature, and one test temperature corresponds to one strain.

[0053] In addition, it should be noted that the external factors in the present application may be, for example, temperature, humidity, wind speed, dust, etc. In this solution, the influence of the external factor of temperature on the target nanobeam is analyzed.

[0054] In step 102, the nanobeam strain data set is converted into a nanobeam strain sequence, and the cohesive loss of the target nanobeam is determined according to the nanobeam strain sequence.

[0055] In specific implementation, the nanobeam strain data set is converted into a nanobeam strain sequence, that is, all nanobeam strains in the nanobeam strain data set are arranged in ascending order according to the corresponding test temperature, and the arranged sequence is used as the nanobeam strain sequence.

[0056] In some embodiments, determining the cohesive loss of the target nanobeam according to the nanobeam strain sequence may be achieved by the following steps:

[0057] Determining the nanobeam strain difference of each group of adjacent nanobeam strains in the nanobeam strain sequence;

[0058] Determining the strain trend of the nanobeam according to the strain differences of all the nanobeams;

[0059] The cohesive loss amount of the target nanobeam is determined according to the nanobeam strain trend and the nanobeam strain sequence.

[0060] In specific implementation, the nanobeam strain difference of each group of adjacent nanobeam strains in the nanobeam strain sequence is determined, that is: a group of adjacent nanobeam strains in the nanobeam strain sequence is selected, and the previous nanobeam strain is subtracted from the next nanobeam strain of the group of adjacent nanobeam strains, and the value obtained by subtraction is used as the nanobeam strain difference of the group of adjacent nanobeam strains, and the nanobeam strain difference is a parameter value of the degree of strain difference of the nanobeam at adjacent temperatures. The above steps are repeated to determine the nanobeam strain difference of the remaining adjacent nanobeam strains in the nanobeam strain data set; the nanobeam strain trend is determined according to all the nanobeam strain differences, that is: the average value of all the nanobeam strain differences is divided by the total number of all the nanobeam strain differences, and the result of the division is used as the nanobeam strain trend of the nanobeam strain data set.

[0061] It should be noted that the strain trend of the nanobeam in the present application is a parameter value that reflects the speed of strain of the target nanobeam between different test temperatures under the same stress. The greater the strain trend of the nanobeam, the faster the strain of the target nanobeam between different test temperatures under the same stress, which is used to analyze the strain of the target nanobeam.

[0062] Wherein, in some embodiments, reference Figure 2 As shown, this figure is a schematic diagram of the process of determining the cohesive loss amount in some embodiments of the present application. In this embodiment, the cohesive loss amount can be determined by the following steps:

[0063] First, in step 1021, the nanobeam deviation of each nanobeam strain in the nanobeam strain sequence is determined;

[0064] Secondly, in step 1022, a lower limit value and an upper limit value are determined according to all the deviations of the nanobeams and the strain trends of the nanobeams;

[0065] Then, in step 1023, the interval formed by the lower limit value and the upper limit value is used as the nanobeam interference domain;

[0066] Finally, in step 1024, the nanobeam interference field is converted into the cohesive loss of the target nanobeam.

[0067] In specific implementation, the nanobeam deviation of each nanobeam strain in the nanobeam strain sequence is determined, that is: a nanobeam strain in the nanobeam strain sequence is selected, the average value of all nanobeam strains in the nanobeam strain sequence is subtracted from the nanobeam strain, and the value obtained by subtraction is used as the nanobeam deviation of the nanobeam strain, and the above steps are repeated to determine the nanobeam deviation of the remaining nanobeam strains in the nanobeam strain sequence; it should be noted that the nanobeam deviation in the present application is a parameter value that reflects the degree of deviation between the strain of the target nanobeam at the test temperature and the central trend of the nanobeam strain, and is used to measure the strain of the target nanobeam.

[0068] In some embodiments, the lower limit value and the upper limit value are determined according to all the nanobeam deviations and the nanobeam strain trend according to the following formula:

[0069]

[0070] in, Represents the lower limit value, Indicates the upper limit value, represents the minimum nanobeam deviation among all nanobeam deviations, represents the maximum nanobeam deviation among all nanobeam deviations, represents the strain trend of the nanobeam, represents the minimum nanobeam strain in the nanobeam strain series, represents the maximum nanobeam strain in the nanobeam strain series, represents the total number of all nanobeam strains in the nanobeam strain sequence, and the lower limit is set to and the upper limit value Composition of nanobeam interference domain .

[0071] It should be noted that the nanobeam interference domain in the present application is a range of values ​​reflecting the interference degree of the target nanobeam material at different temperatures, and is used to analyze the damping effect of the target nanobeam.

[0072] In some embodiments, converting the nanobeam interference domain into the cohesive loss of the target nanobeam can be achieved by the following steps:

[0073] Get the lower bound of the nanobeam interference domain ;

[0074] Get the upper limit of the nanobeam interference domain ;

[0075] Obtaining Nanobeam Strain Trends ;

[0076] Determining the stress correction coefficient of nanobeams ;

[0077] According to the lower limit of the nanobeam interference domain , the upper limit of the nanobeam interference domain , the strain trend of the nanobeam and the nanobeam stress correction coefficient Determine the cohesive loss of the target nanobeam, wherein the cohesive loss can be determined according to the following formula:

[0078]

[0079] in, represents the amount of cohesive loss, represents the minimum nanobeam strain in the nanobeam strain series, represents the maximum nanobeam strain in the nanobeam strain series, Represents the base 2 logarithmic function.

[0080] In specific implementation, the nanobeam stress correction coefficient is a parameter that reflects the degree of deviation of the nanobeam stress and is used to correct the nanobeam stress. The nanobeam stress correction coefficient is set according to all the nanobeam stresses in the historical nanobeam stress data through the linear regression method of the prior art. The value range of the nanobeam stress correction coefficient is 0-1. In other embodiments, other methods can be used for setting, which is not limited here.

[0081] It should be noted that the cohesive loss in the present application is a parameter value that reflects the central trend of the damping degree of the target nanobeam under stress, and is used to predict the damping effect of the target nanobeam.

[0082] In step 103 , the nanobeam curvature of each nanobeam strain in the nanobeam strain dataset is determined according to the nanobeam strain dataset and the real-time surface load.

[0083] In some embodiments, reference Figure 3 As shown in FIG. 1 , this figure is a schematic diagram of a process for determining the curvature of a nanobeam in some embodiments of the present application. In this embodiment, the curvature of a nanobeam can be determined by the following steps:

[0084] First, in step 1031, the real-time surface load is obtained;

[0085] Secondly, in step 1032, a nanobeam topological quantity of each nanobeam strain in the nanobeam strain data set is determined according to the real-time surface load;

[0086] Then, in step 1033, all nanobeam topological quantities are converted into nanobeam topological sequences;

[0087] Finally, in step 1034, the nanobeam curvature of each nanobeam topological quantity in the nanobeam topological sequence is determined.

[0088] In a specific implementation, a real-time surface load is obtained through a surface load device, and the real-time surface load is the real-time stress acting on the target nanobeam during the test process, and the real-time surface load is unchanged during the above test process; the nanobeam topological quantity of each nanobeam strain in the nanobeam strain data set is determined according to the real-time surface load, that is, a nanobeam strain in the nanobeam strain data set is selected, the real-time surface load is divided by the nanobeam strain, the value obtained by the division is multiplied by the test temperature corresponding to the nanobeam strain, and the multiplied value is used as the nanobeam topological quantity of the nanobeam strain, and the above steps are repeated to determine the nanobeam topological quantities of the remaining nanobeam strains in the nanobeam strain data set, and the nanobeam topological quantity is a parameter value reflecting the degree of stress rebound of the target nanobeam at the corresponding test temperature. The larger the nanobeam topological quantity, the smaller the stress rebound of the target nanobeam at the corresponding test temperature; all nanobeam topological quantities are converted The invention relates to a nanobeam topological sequence, that is, all nanobeam topological quantities are arranged in ascending order according to the corresponding test temperature, and the sequence obtained by the arrangement is used as the nanobeam topological sequence; the nanobeam curvature of each nanobeam topological quantity in the nanobeam topological sequence is determined, that is, the first nanobeam topological quantity is subtracted from the second nanobeam topological quantity in the nanobeam topological sequence, and the value obtained by the subtraction is used as the nanobeam curvature of the second nanobeam topological quantity, the second nanobeam topological quantity is subtracted from the third nanobeam topological quantity in the nanobeam topological sequence, and the value obtained by the subtraction is used as the nanobeam curvature of the third nanobeam topological quantity, and so on, until the second-to-last nanobeam topological quantity is subtracted from the last nanobeam topological quantity in the nanobeam topological sequence, and the value obtained by the subtraction is used as the nanobeam curvature of the last nanobeam topological quantity. It should be noted that in the present application, the nanobeam curvature of the second nanobeam topological quantity is used as the nanobeam curvature of the first nanobeam topological quantity.

[0089] It should be noted that in the present application, one nanobeam topological quantity corresponds to one test temperature; the nanobeam curvature is a parameter value that reflects the degree of elastic change of the target nanobeam between adjacent test temperatures. The greater the nanobeam curvature, the greater the elastic change of the target nanobeam between adjacent test temperatures. The nanobeam curvature is used to predict the strain of the target nanobeam.

[0090] In step 104, the extension decision factor corresponding to the curvature of each nanobeam is determined by the cohesive loss, and multiple stress response feature prediction bases of the target nanobeam are determined according to all the extension decision factors and the nanobeam strain data set.

[0091] In some embodiments, determining the extension decision factor corresponding to the curvature of each nanobeam by the cohesive loss can be achieved by the following steps:

[0092] Determine the amount of test time balancing;

[0093] Selecting a nanobeam curvature, and determining an extension decision factor of the nanobeam curvature according to the test time balance amount, the cohesive loss amount and the nanobeam curvature;

[0094] Repeat the above steps to determine the extension decision factors of the remaining nanobeam curvature.

[0095] It should be noted that the test time balance amount in the present application is a parameter value that reflects the degree of central trend of the test time, which is used to predict the test time. The test time of the nanobeam at each test temperature is obtained through a time recording device, and the average value of all test time sizes is used as the test time balance amount. In other embodiments, other methods can be used for setting, which is not limited here.

[0096] In some embodiments, determining the extension decision factor of the nanobeam curvature according to the test time balance amount, the cohesive loss amount and the nanobeam curvature can be achieved by the following steps:

[0097] Get the amount of cohesion loss ;

[0098] Obtaining the curvature of the nanobeam ;

[0099] Determining the nanobeam gauge factor ;

[0100] Get the nanobeam strain corresponding to the nanobeam curvature ;

[0101] According to the cohesive loss , the nanobeam curvature , the nanobeam strain coefficient The nanobeam strain corresponding to the nanobeam curvature Determine the extension decision factor of the nanobeam curvature, wherein the extension decision factor can be determined according to the following formula:

[0102]

[0103] in, represents the extended decision factor, represents the test time balance, Represents the natural logarithm.

[0104] In specific implementation, the nanobeam strain coefficient is a parameter that reflects the degree of deviation of the nanobeam strain and is used to correct the nanobeam strain. The nanobeam is placed at 20°C and the above-mentioned real-time surface load is applied. The strain of the nanobeam at this moment is used as the standard nanobeam stress. The standard nanobeam stress is subtracted from the average value of all nanobeam strains in the nanobeam strain data set, and the absolute value of the subtracted value is divided by the standard nanobeam stress. The value obtained by the division is used as the nanobeam strain coefficient. Other methods can be used for setting in other embodiments, which are not limited here.

[0105] It should be noted that in the present application, a nanobeam curvature corresponds to a nanobeam strain, and the extension decision factor is a parameter that reflects the reliability of the nanobeam strain under the real-time surface load at the current test temperature, so as to predict the nanobeam strain under different real-time surface loads at the test temperature.

[0106] In some embodiments, the multiple stress response feature prediction bases of the target nanobeam can be determined according to the following formula based on all the extension decision factors and the nanobeam strain data set:

[0107]

[0108] in, represents the first The stress response characteristics prediction base of nanobeam strain, represents the time correction factor, represents the test time balance, represents the first The elongation determining factor corresponding to the strain of the nanobeam is: represents the first The nanobeam strain, represents the average value of all nanobeam strains in the nanobeam strain dataset, Represents the base 2 logarithmic function.

[0109] In specific implementation, the time correction coefficient is a parameter that reflects the degree of deviation of the test time and is used to correct the test time. The value range of the time correction coefficient is 0-2. The time correction coefficient is set for all historical test times in the historical test time data through the linear regression method of the prior art. In other embodiments, other methods can be used for setting, which is not limited here.

[0110] It should be noted that the stress response characteristic prediction base in the present application is a parameter value reflecting the elasticity of the target nanobeam at the current test temperature, so as to predict the stress of the nanobeam at the test temperature.

[0111] In step 105, the gradient response of the target nanobeam is predicted using all stress response feature prediction bases.

[0112] In specific implementation, a surface load can be applied to the target nanobeam at a specified test temperature, and the real-time surface load is divided by the stress response characteristic prediction base corresponding to the specified test temperature. The value obtained by the division is used as the nanobeam strain of the target nanobeam at the specified test temperature for the surface load. The above steps are repeated to determine the nanobeam strain of the target nanobeam at different test temperatures and different surface loads. All the obtained nanobeam strains are used as the stress gradient values ​​of the target nanobeam. In some embodiments, all stress gradient values ​​can be used to generate a stress gradient table through the existing python software, and the stress gradient response of the target nanobeam is predicted through the stress gradient table, which will not be repeated here.

[0113] In addition, in another aspect of the present application, in some embodiments, the present application provides a prediction system for the gradient response of a nanobeam, referring to Figure 4 , which is a schematic diagram of exemplary hardware and / or software of a prediction system for nanobeam gradient response according to some embodiments of the present application, the prediction system 400 for nanobeam gradient response includes: an acquisition module 401, a conversion module 402, a processing module 403 and an execution module 404, which are described as follows:

[0114] Acquisition module 401, in the present application, acquisition module 401 is mainly used to acquire a nanobeam strain data set of a target nanobeam after starting the nanobeam gradient response test;

[0115] A conversion module 402, in the present application, the conversion module 402 is mainly used to convert the nanobeam strain data set into a nanobeam strain sequence, and determine the cohesive loss of the target nanobeam according to the nanobeam strain sequence;

[0116] Processing module 403, in the present application, the processing module 403 is used to determine the nanobeam curvature of each nanobeam strain in the nanobeam strain data set according to the nanobeam strain data set and the real-time surface load;

[0117] The processing module 403 in the present application is also used to determine the extension decision factor corresponding to the curvature of each nanobeam through the cohesive loss, and determine the multiple stress response feature prediction bases of the target nanobeam according to all the extension decision factors and the nanobeam strain data set;

[0118] Execution module 404: In the present application, execution module 404 is mainly used to predict the gradient response of the target nanobeam through all stress response feature prediction bases.

[0119] In addition, the present application also provides a computer device, which includes a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned method for predicting the gradient response of the nanobeam.

[0120] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device according to some embodiments of the present application using the method for predicting the gradient response of a nanobeam. The method for predicting the gradient response of a nanobeam in the above embodiment can be performed by Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503 and at least one communication interface 504.

[0121] The processor 501 may be a general purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more implementations of the prediction method for controlling the nanobeam gradient response in the present application.

[0122] Communication bus 502 may include a pathway for transmitting information between the above-mentioned components.

[0123] The memory 503 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 503 may exist independently and be connected to the processor 501 via the communication bus 502. The memory 503 may also be integrated with the processor 501.

[0124] The memory 503 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The determination of the nanobeam strain sequence in the above embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0125] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0126] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0127] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0128] In addition, the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for predicting the gradient response of the nanobeam is implemented.

[0129] In summary, in the prediction method, system, device and storage medium of the nanobeam gradient response disclosed in the embodiments of the present application, the nanobeam strain sequence is first determined through the nanobeam strain data set, the cohesive loss of the target nanobeam is determined according to the nanobeam strain sequence, the nanobeam curvature of each nanobeam strain in the nanobeam strain data set is determined according to the nanobeam strain data set and the real-time surface load, the extension decision factor corresponding to each nanobeam curvature is determined according to the cohesive loss, and multiple stress response feature prediction cardinalities of the target nanobeam are determined according to all the extension decision factors and the nanobeam strain data set. The gradient response of the target nanobeam is predicted through all the stress response feature prediction cardinalities to avoid the interference of external temperature on the prediction of the nanobeam gradient response.

[0130] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0131] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for predicting the gradient response of a nanobeam, characterized in that: The steps include: Starting a nanobeam gradient response test to obtain a nanobeam strain data set of a target nanobeam; Converting the nanobeam strain data set into a nanobeam strain sequence, and determining the cohesive loss of the target nanobeam according to the nanobeam strain sequence; Determining a nanobeam curvature of each nanobeam strain in the nanobeam strain dataset according to the nanobeam strain dataset and the real-time surface load; Determining the extension decision factor corresponding to the curvature of each nanobeam through the cohesive loss, and determining multiple stress response feature prediction bases of the target nanobeam according to all the extension decision factors and the nanobeam strain data set; The gradient response of the target nanobeam is predicted through all stress response feature prediction bases; Wherein, determining the cohesive loss of the target nanobeam according to the nanobeam strain sequence specifically includes: Determining the nanobeam strain difference of each group of adjacent nanobeam strains in the nanobeam strain sequence; Determining the strain trend of the nanobeam according to the strain differences of all the nanobeams; Determining the cohesive loss of the target nanobeam according to the nanobeam strain trend and the nanobeam strain sequence; Wherein, determining the cohesive loss of the target nanobeam according to the nanobeam strain trend and the nanobeam strain sequence specifically includes: determining a nanobeam deviation amount for each nanobeam strain in the nanobeam strain sequence; Determine a lower limit value and an upper limit value according to all the nanobeam deviations and the strain trend of the nanobeam; The interval formed by the lower limit value and the upper limit value is used as the nanobeam interference domain; converting the nanobeam interference domain into a cohesive loss amount of a target nanobeam; Wherein, determining the nanobeam curvature of each nanobeam strain in the nanobeam strain data set according to the nanobeam strain data set and the real-time surface load specifically includes: Get real-time surface loads; determining a nanobeam topological quantity of each nanobeam strain in the nanobeam strain data set according to the real-time surface load; Convert all nanobeam topological quantities into nanobeam topological sequences; The nanobeam curvature of each nanobeam topological quantity in the nanobeam topological sequence is determined.

2. The method according to claim 1, characterized in that Determining the extension decision factor corresponding to the curvature of each nanobeam by the cohesive loss specifically includes: Determine the amount of test time balancing; Selecting a nanobeam curvature, and determining an extension decision factor of the nanobeam curvature according to the test time balance amount, the cohesive loss amount and the nanobeam curvature; Repeat the above steps to determine the extension decision factors of the remaining nanobeam curvature.

3. The method according to claim 1, characterized in that Determining multiple stress response feature prediction bases of the target nanobeam based on all the extension decision factors and the nanobeam strain data set specifically includes: Get the test time balance; determining an average value of all nanobeam strains in the nanobeam strain data set; A plurality of stress response characteristic prediction bases of the target nanobeam are determined according to the test time balance amount, all extension decision factors and the average value of all nanobeam strains.

4. The method according to claim 1, characterized in that The nanobeam strain in the nanobeam strain data set is the strain of the target nanobeam caused by the stress applied to the target nanobeam at different test temperatures.

5. A nanobeam gradient response prediction system, which uses the method described in any one of claims 1 to 4 to predict the nanobeam gradient response, characterized in that: The system includes: An acquisition module, used for acquiring a nanobeam strain data set of a target nanobeam after starting a nanobeam gradient response test; A conversion module, used for converting the nanobeam strain data set into a nanobeam strain sequence, and determining the cohesive loss of the target nanobeam according to the nanobeam strain sequence; A processing module, configured to determine a nanobeam curvature of each nanobeam strain in the nanobeam strain data set according to the nanobeam strain data set and a real-time surface load; The processing module is further used to determine the extension decision factor corresponding to the curvature of each nanobeam according to the cohesive loss amount, and determine multiple stress response feature prediction bases of the target nanobeam according to all the extension decision factors and the nanobeam strain data set; The execution module is used to predict the gradient response of the target nanobeam through all stress response feature prediction bases.

6. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the method for predicting the gradient response of a nanobeam according to any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for predicting the gradient response of a nanobeam as claimed in any one of claims 1 to 4 is implemented.

Images