CN114997060A - Time-varying reliability testing method for photonic crystal, computing equipment and storage medium - Google Patents

Time-varying reliability testing method for photonic crystal, computing equipment and storage medium Download PDF

Info

Publication number
CN114997060A
CN114997060A CN202210663980.8A CN202210663980A CN114997060A CN 114997060 A CN114997060 A CN 114997060A CN 202210663980 A CN202210663980 A CN 202210663980A CN 114997060 A CN114997060 A CN 114997060A
Authority
CN
China
Prior art keywords
sample
phononic crystal
neural network
parameters
network model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210663980.8A
Other languages
Chinese (zh)
Inventor
陈宁
张琨
刘坚
李蓉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan University
Original Assignee
Hunan University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hunan University filed Critical Hunan University
Priority to CN202210663980.8A priority Critical patent/CN114997060A/en
Publication of CN114997060A publication Critical patent/CN114997060A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/26—Composites
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Hardware Design (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Geometry (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the field of phononic crystals, and discloses a method for testing time-varying reliability of a phononic crystal, computing equipment and a storage medium, which comprises the following steps: determining a sample space according to parameters of the phononic crystal; constructing a reliability test model according to the sample space and the failure conditions of the phononic crystal; constructing a neural network model according to the reliability test model; and predicting the failure rate of the phononic crystal in the service time according to the neural network model and the sample space. According to the method, the failure rate of the phononic crystal in the service time can be predicted by constructing the reliability test model of the phononic crystal and constructing the neural network model through the reliability test model, the phenomenon that the performance of the phononic crystal cannot be judged due to the lack of parameters of the phononic crystal is avoided, and the performance of the phononic crystal in the service time is determined.

Description

Time-varying reliability testing method for photonic crystal, computing equipment and storage medium
Technical Field
The invention relates to the field of photonic crystals, in particular to a method for testing time-varying reliability of a photonic crystal, computing equipment and a storage medium.
Background
Phononic crystals generally refer to functional materials having elastic (acoustic) band gaps, in which materials having different densities and elastic parameters are combined together in a periodic structure. However, the self-structure and material properties of the phononic crystal can lead to time-varying uncertainty in the presentation of the phononic crystal. Time-varying uncertainty refers to the fact that one or more parameters of the phononic crystal may change over time, resulting in fluctuations in the performance of the phononic crystal. Therefore, time-varying reliability testing of the phononic crystal becomes particularly important.
In the prior art, when a photonic crystal is tested, the characteristic parameters of the photonic crystal are often set through sufficient sample data, and then a test model of the photonic crystal is constructed according to the set characteristic parameters to test the performance of the photonic crystal. However, in actual work and research, sample data of the phononic crystal is often difficult to obtain, and accurate characteristic parameters cannot be constructed, so that the test result is not accurate enough.
For this reason, a new phononic crystal time-varying reliability test method is required.
Disclosure of Invention
To this end, the present invention provides a phononic crystal time varying reliability test method in an attempt to solve or at least alleviate the above-presented problems.
According to an aspect of the present invention, there is provided a phononic crystal time-varying reliability testing method, adapted to be executed in a computing device, the method comprising the steps of: determining a sample space according to parameters of the phononic crystal; constructing a reliability test model according to the sample space and the failure condition of the phononic crystal; constructing a neural network model according to the reliability test model; and predicting the failure rate of the phononic crystal in the service time according to the neural network model and the sample space.
Optionally, in the method according to the present invention, the parameters of the phononic crystal include: random variable parameters, random process parameters, interval variable parameters and interval process parameters; the method for constructing the reliability test model according to the failure conditions of the sample space and the phononic crystal comprises the following steps: converting random process parameters in the crystal parameters to obtain equivalent random variable parameters; converting the interval process parameters in the crystal parameters to obtain equivalent interval variable parameters; converting the time parameter of the service time of the phononic crystal into an equivalent distribution time parameter; and constructing a reliability test model according to the random variable parameters, the equivalent random variable parameters, the interval variable parameters, the equivalent distribution time parameters and the failure conditions.
Optionally, in the method according to the invention, the failure condition comprises: and in the service time, when the lower limit of the band gap of the phononic crystal is greater than the preset frequency, the phononic crystal fails.
Optionally, in the method according to the present invention, constructing the neural network model from the reliability test model comprises the steps of: determining a training set according to the sample point set; and training the neural network model according to the reliability test model and the training set.
Optionally, in the method according to the present invention, determining the training set from the set of sample points comprises the steps of: converting the sample points in the sample space to obtain a converted sample point set; and determining a training set according to the converted sample point set.
Optionally, in the method according to the present invention, determining the training set according to the transformed sample point set comprises the steps of: determining the sample weight of each sample point in the converted sample point set; determining the characteristic value of each sample point according to the sample weight; and determining a training set from the converted sample point set according to the characteristic values.
Optionally, in the method according to the present invention, transforming the sample points of the sample space comprises the steps of: and performing equivalent uncertain transformation on each sample point in the sample space to obtain a time-independent sample point set.
Optionally, in the method according to the present invention, further comprising the step of: judging whether the failure rate of the instantaneous reliability calculated by the neural network model meets a stopping rule or not; if the stopping rule is not met, setting iteration times, and determining an incremental sample point according to the iteration times; determining a new sample set according to the incremental sample points and the sample set; and training a new neural network model according to the new sample set until the training obtains the neural network model meeting the stopping rule.
Optionally, in the method according to the present invention, determining the incremental sample points according to the number of iterations comprises the steps of: determining a candidate point set according to the training set, and determining a first point set according to the candidate point set; determining a second set of points from the first set of points by weight sampling; incremental sample points are determined from the second set of points according to an active learning function.
Optionally, in the method according to the present invention, determining incremental sample points from the second set of points according to an active learning function comprises the steps of: determining an uncertainty for each sample point in the second set of points; determining the Euclidean distance between each sample point in the second point set and the training set; inputting the uncertainty and Euclidean distance of each sample point into an active learning function to obtain a function value of each sample point; and taking the sample point with the minimum function value in the second point set as the incremental sample point.
Optionally, in a method according to the invention, determining the uncertainty of each sample point in the second set of points comprises the steps of: generating a plurality of training complementary sets according to the sample set generated last time; generating a supplementary neural network model according to each training complementary set; the uncertainty for each sample point is determined from the supplemental neural network model and the last generated neural network model.
Optionally, in the method according to the present invention, predicting the failure rate of the phononic crystal in the service time according to the neural network model and the sample space comprises the steps of: and calculating the failure rate of the mixing time-varying reliability of the phononic crystal according to the neural network model and the sample points in the sample space.
Optionally, in the method according to the present invention, further comprising the step of: calculating the variation coefficient of the failure rate according to the failure rate of the mixing time-varying reliability of the phononic crystal; determining whether the coefficient of variation is greater than a preset coefficient threshold; if the variation coefficient is not larger than the preset coefficient threshold, adding a new sample point into the sample space to obtain a new sample space; and training the neural network model according to the new sample space until the variation coefficient of the neural network model is greater than a preset minimum threshold value.
According to another aspect of the invention, there is provided a computing device comprising: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing the phononic crystal time varying reliability test method in accordance with the present invention.
According to yet another aspect of the present invention, there is provided a computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform a phononic crystal time-varying reliability test method according to the present invention.
The invention discloses a phononic crystal time-varying reliability testing method which is suitable for being executed in computing equipment. The method comprises the following steps: determining a sample space according to parameters of the phononic crystal; constructing a reliability test model according to the sample space and the failure condition of the phononic crystal; constructing a neural network model according to the reliability test model; and predicting the failure rate of the phononic crystal in the service time according to the neural network model and the sample space. According to the method, the failure rate of the phononic crystal in the service time can be predicted by constructing the reliability test model of the phononic crystal and constructing the neural network model through the reliability test model, the phenomenon that the performance of the phononic crystal cannot be judged due to the lack of parameters of the phononic crystal is avoided, and the performance of the phononic crystal in the service time is determined.
Drawings
To the accomplishment of the foregoing and related ends, certain illustrative aspects are described herein in connection with the following description and the annexed drawings, which are indicative of various ways in which the principles disclosed herein may be practiced, and all aspects and equivalents thereof are intended to be within the scope of the claimed subject matter. The above and other objects, features and advantages of the present disclosure will become more apparent from the following detailed description when read in conjunction with the accompanying drawings. Throughout this disclosure, like reference numerals generally refer to like parts or elements.
FIG. 1 shows a schematic diagram of a phononic crystal time varying reliability test method 100 in accordance with one exemplary embodiment of the present invention;
FIG. 2 illustrates a block diagram of a computing device 200, according to an exemplary embodiment of the invention;
FIG. 3a shows a schematic diagram of the propagation of an acoustic wave in a phononic crystal according to an exemplary embodiment of the present invention;
FIG. 3b shows a schematic structural diagram of a phononic crystal according to an exemplary embodiment of the present invention;
FIGS. 4 a-4 d are schematic diagrams illustrating equivalent uncertain transformations in accordance with an exemplary embodiment of the present invention;
FIG. 5 shows a schematic diagram of a phononic crystal time varying reliability analysis in accordance with an exemplary embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. Like reference numerals generally refer to like parts or elements.
The invention provides a method for testing the time-varying reliability of a phononic crystal. The phononic crystal time-varying reliability testing method is suitable for being executed in a computing device. FIG. 2 illustrates a block diagram of a computing device 200, according to an exemplary embodiment of the invention.
In a basic configuration, computing device 200 includes at least one processing unit 220 and system memory 210. According to one aspect, depending on the configuration and type of computing device, system memory 210 includes, but is not limited to, volatile storage (e.g., random access memory), non-volatile storage (e.g., read-only memory), flash memory, or any combination of such memories. According to one aspect, system memory 210 includes an operating system 211.
According to one aspect, the operating system 211, for example, is adapted to control the operation of the computing device 200. Further, the examples are practiced in conjunction with a graphics library, other operating systems, or any other application program, and are not limited to any particular application or system. This basic configuration is illustrated in fig. 2 by those components within dashed line 215. According to one aspect, computing device 200 has additional features or functionality. For example, according to one aspect, computing device 200 includes additional data storage devices (removable and/or non-removable) such as, for example, magnetic disks, optical disks, or tape.
As stated hereinabove, according to one aspect, program modules 212 are stored in system memory 210. According to one aspect, program modules 212 may include one or more applications, the invention not being limited to the type of application, e.g., applications further include: email and contacts applications, word processing applications, spreadsheet applications, database applications, slide show applications, drawing or computer-aided applications, web browser applications, and the like.
According to one aspect, examples may be practiced in a circuit comprising discrete electronic elements, a packaged or integrated electronic chip containing logic gates, a circuit utilizing a microprocessor, or on a single chip containing electronic elements or microprocessors. For example, an example may be practiced via a system on a chip (SOC) in which each or many of the components shown in fig. 2 may be integrated on a single integrated circuit. According to one aspect, such SOC devices may include one or more processing units, graphics units, communication units, system virtualization units, and various application functions, all integrated (or "burned") onto a chip substrate as a single integrated circuit. When operating via an SOC, the functionality described herein may be operated via application-specific logic integrated with other components of the computing device 200 on the single integrated circuit (chip). Embodiments of the invention may also be practiced using other technologies capable of performing logical operations (e.g., AND, OR, AND NOT), including but NOT limited to mechanical, optical, fluidic, AND quantum technologies. In addition, embodiments of the invention may be practiced within a general purpose computer or in any other circuits or systems.
According to one aspect, computing device 200 may also have one or more input devices 231, such as a keyboard, mouse, pen, voice input device, touch input device, or the like. Output device(s) 232 such as a display, speakers, printer, etc. may also be included. The foregoing devices are examples and other devices may also be used. Computing device 200 may include one or more communication connections 233 that allow communication with other computing devices 200. Examples of suitable communication connections 233 include, but are not limited to: RF transmitter, receiver and/or transceiver circuitry; universal Serial Bus (USB), parallel, and/or serial ports.
Embodiments of the present invention also provide a non-transitory readable storage medium storing instructions for causing the computing device to perform a method according to embodiments of the present invention. The readable media of the present embodiments include permanent and non-permanent, removable and non-removable media, and the storage of information may be accomplished by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of readable storage media include, but are not limited to: phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transitory readable storage medium.
According to one aspect, communication media is embodied by computer readable instructions, data structures, program modules, or other data in a modulated data signal (e.g., a carrier wave or other transport mechanism) and includes any information delivery media. According to one aspect, the term "modulated data signal" describes a signal that has one or more characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communication media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, Radio Frequency (RF), infrared, and other wireless media.
It should be noted that although the computing device described above shows only processing unit 220, system memory 210, input device 231, output device 232, and communication connection 233, in particular implementations, the device may include other components necessary for proper operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only the components necessary to implement the embodiments of the present disclosure, and need not include all of the components shown in the figures.
Next, a detailed description will be given of a specific implementation procedure of the phononic crystal time-varying reliability testing method of the present invention with reference to fig. 1. FIG. 1 shows a schematic diagram of a phononic crystal time varying reliability test method 100 according to one exemplary embodiment of the present invention. As shown in fig. 1, step S110 is first performed to determine a sample space according to the parameters of the phononic crystal.
In the phononic crystal, materials with different density and elastic parameters related to the propagation of elastic waves are periodically compounded together according to a structure similar to a natural crystal, materials distributed on lattice points and not communicated with each other are called scatterers, and background medium materials communicated into a whole are called matrixes. The elastic wave forbidden band means that any elastic wave eigenmode does not exist in a certain frequency range, namely, the elastic wave in the frequency range is forbidden to propagate.
Phononic crystals can be divided into three types, namely one-dimensional (lamellar), two-dimensional and three-dimensional phononic crystals, according to the shape of the scatterers and the form of the scatterers periodically distributed in the matrix. Common two-dimensional phononic crystals are further classified according to the periodicity of the crystal lattice as follows: tetragonal lattice, triangular lattice, hexagonal lattice, etc. According to one embodiment of the invention, the phononic crystal for the time-varying reliability test is specifically a two-dimensional phononic crystal.
Fig. 3a shows a schematic view of an acoustic wave propagating in a phononic crystal according to an exemplary embodiment of the present invention.
The phononic crystal has various parameters in its own structure and material properties, and these parameters can be divided into random variable parameters, random process parameters, interval variable parameters and interval process parameters according to the continuity and time correlation.
According to one embodiment of the invention, the random variable parameters include the Young's modulus and density of the scatterers and matrix; the random process parameters include the side length of the substrate; the interval variable parameters comprise the Poisson ratio of the scatterer and the matrix; the interval process parameter includes the diameter of the scatterers.
Fig. 3b shows a schematic structural diagram of a phononic crystal according to an exemplary embodiment of the present invention. As shown in fig. 3b, the phononic crystal includes scatterers and a matrix; wherein the diameter of the scatterer is R C The length of the substrate is a.
And determining a sample space for taking the parameter of the phononic crystal according to the value range of each parameter of the phononic crystal. The sample space includes a plurality of sample points. Each sample point comprises a plurality of parameters, and the value range of each parameter is within the value range of the corresponding parameter of the phononic crystal. Each sample point in the sample space represents a possible parameter value of the phononic crystal.
According to an embodiment of the present invention, for the simulation of the parameter value of the photonic crystal, monte carlo simulation may be adopted to randomly distribute the sample points in the sample space. At this point, each sample point in the sample space is a monte carlo sample point. The number of sample points in the sample space is N mc From N to N mc The set of sample points formed by sample points is a sample point set S MCS 。
Subsequently, step S120 is performed to construct a reliability test model according to the sample space and the failure condition of the phononic crystal.
According to an embodiment of the invention, in order to explore the reliability of the phononic crystal, a reliability test model needs to be constructed to test the phononic crystal. The basic rule of the reliability test model is that when the lower band gap limit of the elastic wave forbidden band is smaller than the preset frequency in the service time of the phononic crystal, the phononic crystal structure is considered to be invalid. When the band gap lower limit of the elastic wave forbidden band of the phononic crystal is smaller than the preset frequency, the blocking performance of the phononic crystal to the elastic wave is not expected, and the phononic crystal fails. Thus, the failure conditions for a phononic crystal are: and in the service time, when the lower limit of the band gap of the phononic crystal is greater than the preset frequency, the phononic crystal fails. And establishing a reliability test model of the phononic crystal according to the failure condition of the phononic crystal.
According to one embodiment of the invention, the lower band gap limit of the phononic crystal may be calculated by a finite element method. The band gap lower limit is obtained by calculating a random variable parameter, a random process parameter, an interval variable parameter and an interval process parameter, and the specific calculation result is as follows:
Figure BDA0003688663360000091
wherein X is (X) 1 ，X 2 ，...X m ) Representing an m-dimensional vector composed of random variable parameters; y ═ Y 1 ，Y 2 ，...Y n ) Representing an n-dimensional vector consisting of interval variable parameters; s (t) ([ S ] 1 (t)，S 2 (t)，...S k (t)]Representing a vector consisting of k random process parameters; i (t) ═ I 1 (t)，I 2 (t)，...I l (t)]Representing a vector consisting of l interval process parameters; and t is the preset service time of the phononic crystal.
Predetermined frequency f th Can be set according to the needs. The invention is suitable for the preset frequency f th The specific values of (a) are not limiting. According to one embodiment of the invention, the frequency f is preset th May be set to 268.
According to the failure condition of the phononic crystal, the extreme state equation for calculating whether the phononic crystal fails can be expressed as:
Figure BDA0003688663360000092
wherein g (X, Y, S (t), I (t), t) represents interpolation of the preset frequency and the lower limit of the band gap of the phononic crystal, and when g (X, Y, S (t), I (t), t) is less than 0, the phononic crystal fails.
The time-varying declaration period of the phononic crystal is [0, T L ]The service time of the phononic crystal in the time-varying declaration period is T, and T is more than or equal to 0 and less than or equal to T L . The failure probability of the phononic crystal in service time can be expressed as:
Figure BDA0003688663360000093
when the parameters of the phononic crystal are at a specific value, the maximum value and the minimum value of the band gap lower limit are calculated. Correspondingly substituting the band gap lower limit of the maximum value into a limit state equation, and calculating to obtain a lower bound of the phononic crystal failure probability; substituting the band gap lower limit of the minimum value into a limit state equation, and calculating to obtain an upper bound of the phononic crystal failure probability. The lower and upper bounds of the phononic crystal failure rate over the time of service can be expressed as:
Figure BDA0003688663360000094
Figure BDA0003688663360000095
in order to test the reliability of the phononic crystal conveniently and reduce the influence of service time on random process parameters and interval process parameters, therefore, the random process parameters and the interval process parameters are subjected to equivalent uncertain transformation to obtain equivalent random variable parameters and equivalent interval variable parameters which are irrelevant to time, and time-varying reliability analysis is converted into time-invariant reliability analysis.
According to an embodiment of the present invention, the equivalent indeterminate transformation may be specifically realized by the following formula:
Figure BDA0003688663360000101
wherein, P t ＝[S(t)，I(t)]，P t Representing time-varying uncertainty parameters including S (t) and I (t). P t ′＝[S′，I′]，P t ' means time invariant uncertain parameters after transformation, including S ' and I '. S 'is an equivalent random variable parameter after the random process parameter is converted, and I' is an equivalent interval variable parameter after the interval process parameter is converted.
Fig. 4 a-4 d show schematic diagrams of equivalent uncertain transformations in accordance with an exemplary embodiment of the present invention. Fig. 4a to 4d illustrate the equivalent uncertain transformation process by taking the transformation of the interval process parameters into the equivalent interval variable parameters as an example.
As shown in fig. 4a, the interval process parameter i (t) is related to the time t; upper bound function I U (t) and a lower bound function I L (t) determining the value range of the interval process parameter I (t) at the time t. Wherein the time T is continuous time and has a value range of [0, T]。
As shown in fig. 4b, first take N discrete times over a continuous time t: t is t 1 ～t N . Determining an upper bound function I U (t) taking values at discrete time to obtain a discrete upper bound function I of interval process parameters I (t) U (t i ). Determining a lower bound function I L (t) taking value at discrete time ti to obtain a discrete lower bound function I of interval process parameters I (t) L (t i ). Wherein i is a positive integer between 1 and N, and i is 1, 2, … … or N.
As shown in FIG. 4c, the discrete upper bound function and the discrete lower bound function are at discrete time t i Is used to determine the process parameter I (t) of the interval at the discrete time t i The value range of (a). Subsequently, the interval process parameter I (t) is measured at a discrete time t i Is taken as an interval variable I i Wherein i is a positive integer between 1 and N, and i is 1, 2, … … or N.
As shown in FIG. 4d, the statistical interval variable I 1 ～I N Determining the value probability function f of the interval process parameter I (t) on the value space PDF (I) In that respect Value-taking probability function f PDF (I) Namely the equivalent interval variable parameter which is not related to time.
According to one embodiment of the invention, the time parameter T describing the time of service of the phononic crystal is also converted into a time-varying life cycle [0, T ] of the phononic crystal L ]Equivalent distribution time parameter T ', T' -U (0, T) of internal equipartition distribution L )。
And constructing to obtain a reliability test model according to the random variable parameters, the interval variable parameters, the converted equivalent random variable parameters, the equivalent interval variable parameters and the equivalent distribution time parameters.
In the finally obtained reliability test model, the limit state function for calculating whether the phononic crystal fails is as follows:
Figure BDA0003688663360000111
correspondingly, the failure probability of the phononic crystal is calculated through the reliability test model, and can be calculated through the following formula:
P f ＝Pr(g(X，Y，S′，I′，t′)＜0)
next, step S130 is executed to construct a neural network model according to the reliability test model.
And when the failure probability of the photonic crystal needs to be predicted according to the reliability test model, the neural network model is trained according to the reliability test model to predict the failure probability of the photonic crystal. According to an embodiment of the present invention, the neural network model used may be specifically a DNN neural network model, and the present invention does not limit the specific type of the neural network model.
When training the neural network model, firstly, the sample point set S forming the sample space MCS Performing equivalent uncertain transformation, converting the sample point in the sample point set and the time-related parameters into time-unrelated parameters according to an equivalent uncertain transformation formula to obtain a transformed sample point set
Figure BDA0003688663360000112
In order to reduce the effect of time on random and interval process parameters during training. Then, from the generated sample point set
Figure BDA0003688663360000113
And selecting a sample point to obtain a training set S. The number of sample points included in the training set S is M, M is less than or equal to N mc ，N mc As a set of sample points
Figure BDA0003688663360000114
The number of sample points included in (a). The invention does not limit the specific number of the sample points in the training set S, and can be determined according to requirements by comprehensively considering factors such as training time and the like.
According to an embodiment of the present invention, when selecting sample points from the sample space to obtain the training set S, the sample points may be selected by weight sampling. Weight sampling is used to solve the sampling imbalance problem. Because random sampling collects more samples in a region with high sampling space probability, and sample points close to the extreme state surface are generally in a region with low sampling space probability, in order to ensure that the sampled samples are as uniform as possible, the small-probability sample points are weighted to be weighted more heavily to ensure that the sampled samples are as uniform as possible through weighted sampling.
When obtaining a training set S from a sample space by weight sampling, a sample point V of the sample space is first sampled t (i) The sample weight can be calculated by the following formula:
Figure BDA0003688663360000121
wherein, w (i) Is the sample weight, f (V), of a sample point t (i) ) Is a sample point V t (i) Probability density in sample space. Sample point V t (i) Has a parameter of V t ＝[X，Y，S′，I′，t′]。
Then, calculating the characteristic value of each sample point according to the sample weight, specifically by the following formula:
Figure BDA0003688663360000122
wherein u is (i) A random number in the range of (0, 1) may be set. The invention is to u (i) The specific value range of (a) is not limited, and can be specifically set according to needs.
And finally, sequencing each sample point according to the characteristic value from small to large, and selecting the first M sample points to obtain a training set S.
Sample point set
Figure BDA0003688663360000123
In the training set, the unselected sample points, i.e. the sample points not in the training set S, are used as the candidate point set S * . Candidate point set S * Combining with the training set S to obtain a sample point set
Figure BDA0003688663360000124
Sample point set
Figure BDA0003688663360000125
In (1), candidate point set S * Is the complement of the training set S.
And after obtaining the training set S, training the neural network model according to the training set S. And after the neural network model is obtained through training, predicting the failure rate of the phononic crystal according to the neural network model. According to one embodiment of the invention, when the failure rate of the phononic crystal is predicted, the converted sample point set is used
Figure BDA0003688663360000126
Inputting the trained neural network model to obtain the failure rate of the instantaneous reliability of the phononic crystal.
According to an embodiment of the invention, in order to realize more accurate testing on the reliability of the phononic crystal, the neural network model obtained by training is updated by using an iterative learning method, so that more accurate failure rate of the phononic crystal is obtained.
According to one embodiment of the invention, a stopping rule is set to determine when to end the iteration based on the stopping rule, stopping the updating of the neural network model. And after a new neural network model is determined every time iteration is performed, calculating the failure rate of the phononic crystal according to the new neural network model, and then judging whether to stop iteration according to a stopping rule. If the judgment result does not meet the stop rule, iteration is continued, and the application network model is updated. And if the judgment result meets the stopping rule, stopping iteration and exiting the loop.
The stopping rules include:
Figure BDA0003688663360000131
Figure BDA0003688663360000132
Figure BDA0003688663360000133
wherein k represents the kth iteration process, n represents the nth iteration process, and n is more than or equal to 1 and less than or equal to k.
Figure BDA0003688663360000134
And in the ith iteration process, the failure rate of the phononic crystal calculated by the neural network model is shown, and n is more than or equal to i and less than or equal to k. Epsilon th In order to define the stop threshold value by user, factors such as test time and the like can be considered for determination as required. According to one embodiment of the invention,. epsilon th May be set to 0.01. n is a self-defined iteration range needing to be calculated; and when the stopping rule is judged, calculating whether the stopping rule is met according to the failure rate of the phononic crystal from the nth iteration to the kth iteration.
According to one embodiment of the invention, the initially generated neural network is modeled as iteration number 1, where k is 1, and then the transformed sample point set is used
Figure BDA0003688663360000135
Inputting the trained neural network model to obtain the failure rate of the instantaneous reliability of the phononic crystal. Then judging whether a stopping rule is met; if the stopping rule is satisfied, the iteration is stopped. Then, based on the sample point set S MCS And inputting the initially generated neural network model and outputting the failure rate of the mixed time-varying reliability of the phononic crystal. If the stopping rule is not satisfied, iteration is continued, and the neural network model is updated.
When the neural network model is updated, the candidate point set S is firstly selected * Determine a first set of points
Figure BDA0003688663360000136
Specifically, the method comprises the following steps: using the neural network model generated last time to set S of candidate points * Calculating each sample point to obtain a response value g of each sample point, wherein the response value g is calculated according to the following formula:
Figure BDA0003688663360000141
then sorting according to the absolute value of the response value of each sample point, and selecting N S * Sample points as a first set of points
Figure BDA0003688663360000142
In accordance with one embodiment of the present invention,
Figure BDA0003688663360000143
the magnitude of (c) can be calculated by the following formula:
Figure BDA0003688663360000144
the invention is right
Figure BDA0003688663360000145
The specific value of (A) is not limited, and can be determined according to the training requirement。
Then, from the first set of points
Figure BDA0003688663360000146
Selecting M experimental points as a second point set S according to a weight sampling mode K . The specific value of M is not limited by the invention and can be determined according to the needs.
Next, an active learning function is used to extract a second set of points S K In determining the incremental sample point V new 。
Specifically, the method comprises the following steps: firstly, processing a training set by adopting a K-fold verification cross-validation method. The training set is equally divided into k training subsets, and each training subset comprises the same number of sample points. Then, one training subset is selected from the k training subsets to be used as a testing subset during each training, and the other training subsets are used as training complementary sets to train the neural network model. And (4) sequentially using each training subset in the k training subsets as a test subset to train to obtain k supplementary neural network models.
And inputting the sample points into a supplementary neural network model to obtain a response value g. Obtaining a supplementary neural network model according to training of the training complementary set
Figure BDA0003688663360000147
Wherein l is a positive integer between 1 and k, and l is 1, 2, a.
The response value is calculated according to the following formula:
Figure BDA0003688663360000148
set the second point S K Each sample point in the training set is input into the neural network model trained by the training set last time and k supplementary neural network models obtained by training by the training complement set, and the uncertainty of each sample point is calculated. Specifically, the calculation can be performed by the following formula:
Figure BDA0003688663360000149
wherein us (V) t i ) As a second set of points S K Of each sample point.
Figure BDA00036886633600001410
In order to input sample points to the response values calculated by the neural network model trained using the training set last time,
Figure BDA00036886633600001411
the calculated response value is input to the l-th supplementary neural network model for the sample point.
Subsequently, a second set of points S is calculated K The euclidean distance between each sample point and the existing training set S can be specifically calculated by the following formula:
Figure BDA0003688663360000151
wherein d (V) t i ) Euclidean distance, V, of each sample point to the existing training set S t i As a second set of points S K In the sample points in (1), i is a positive integer between 1 and M, and i is 1, 2, … …, or M. V t j J is a positive integer between 1 and M for the sample points in the existing training set S, and j is 1, 2, … …, M.
Finally, determining an incremental sample point V by using an active learning function according to the Euclidean distance and the uncertainty new Specifically, the calculation can be performed by the following formula:
Figure BDA0003688663360000152
wherein N (-) denotes a standardized operation SLF (V) t i ) Is to set the second point S K And inputting the function value obtained by calculation of the active learning function into each sample point. The value range of beta is (0, 1), and the specific value of beta is not limited by the invention. According to one embodiment of the invention, the value of β may be 0.5,the expression comprehensively considers Euclidean distance and uncertainty according to equal importance when calculating the active learning function.
For the second point set S K Inputting each sample point into the function value obtained by calculation of the active learning function, sequencing, and taking the sample point with the minimum function value obtained by calculation as an increment sample point V new 。
And then adding the incremental sample points into the sample set S to obtain a new sample set, and training to obtain a new neural network model.
According to the steps, the neural network model is updated iteratively by using an active learning method, and the most appropriate incremental sample point is selected each time and added into the sample set to obtain a new sample set. The incremental sample points calculated according to the method are far away from the existing sample points, so that the problem of the model is prevented, the progress of the model is ensured, the trained sample points are reduced, the sample points are close to the extreme state surface as much as possible, and high uncertainty is also provided.
Adding the incremental sample points into the sample set S to obtain a new sample set, and simultaneously, adding the incremental sample points from the candidate point set S * And removing to obtain a new candidate point set for subsequent iteration.
Training to obtain new neural network model, and collecting sample points
Figure BDA0003688663360000161
And inputting a new neural network model to obtain the failure rate of the instantaneous reliability of the phononic crystal. Then judging whether a stopping rule is met; if the stopping rule is satisfied, the iteration is stopped.
Finally, step S140 is executed to predict the failure rate of the phononic crystal in the service time according to the neural network model and the sample space.
According to the sample point set S MCS And inputting a new neural network model and outputting the failure rate of the mixed time-varying reliability of the phononic crystal. If the stopping rule is not met, continuing the iteration and increasing the iteration times k by 1; the newly generated neural network model is then continually updated until the failure rate of the instantaneous reliability of the output meets the stopping rule.
According to an embodiment of the present invention, after the failure rate of the mixing time-varying reliability of the photonic crystal is calculated, the variation coefficient of the failure rate is calculated according to the failure rate, which can be specifically calculated by the following formula:
Figure BDA0003688663360000162
wherein, P f For failure rate, N is the number of sample points in the sample space, which can be implemented as the number of Monte Carlo samples N mc 。
And then, comparing the calculated variation coefficient with a preset coefficient threshold, and if the variation coefficient is larger than the preset coefficient threshold, outputting the failure rate. According to an embodiment of the present invention, the preset coefficient threshold may be set to 0.05, and the specific value of the preset coefficient threshold is not limited by the present invention.
If the coefficient of variation is smaller than the preset coefficient threshold, increasing the number of sample points in the sample space to obtain a new sample space, executing the steps S110 to S1n0 according to the new sample space to obtain a new neural network model, and calculating the failure rate and the coefficient of variation until the calculated coding coefficient is larger than the preset coefficient threshold.
In the reliability test model, the failure rate of the phononic crystal in the service time is calculated, including the lower bound
Figure BDA0003688663360000163
And upper bound
Figure BDA0003688663360000164
The resulting failure rates thus include an upper failure rate bound and a lower failure rate bound, i.e., between the upper failure rate bound and the lower real-time rate bound.
Fig. 5 shows a schematic diagram of a time-varying reliability analysis of a phononic crystal according to an exemplary embodiment of the present invention. As shown in fig. 5, the parameters of the phononic crystal are determined according to the self-structure and material properties of the phononic crystal; these parameters include: a random variable parameter,Random process parameters, interval variable parameters, and interval process parameters. According to the specific value range of each parameter in each parameter, the sample space of the value of the phononic crystal parameter can be determined. The sample space includes a plurality of sample points. When taking sample points in the sample space, Monte Carlo can be used to generate N mc Sample points, the set of these sample points being a sample point set S MCS 。
And then constructing a reliability test model to test the phononic crystal. When a reliability test model is constructed and set, determining that the failure conditions of the phononic crystal are as follows: and in the service time, when the lower limit of the band gap of the phononic crystal is greater than the preset frequency, the phononic crystal fails. And taking the failure condition of the phononic crystal as a basic rule for constructing a reliability test model, thereby constructing the reliability test model.
In the reliability test model: the extreme equation of state for calculating whether a phononic crystal is failing can be expressed as:
Figure BDA0003688663360000171
the failure probability of the phononic crystal in service time can be further calculated according to the extreme state equation as follows:
Figure BDA0003688663360000172
when the parameters of the phononic crystal are at a specific value, the maximum value and the minimum value of the band gap lower limit are calculated. Correspondingly substituting the band gap lower limit of the maximum value into a limit state equation, and calculating to obtain a lower bound of the phononic crystal failure probability; substituting the band gap lower limit of the minimum value into a limit state equation, and calculating to obtain an upper bound of the phononic crystal failure probability. The lower and upper bounds of the phononic crystal failure rate over the time of service can be expressed as:
Figure BDA0003688663360000173
Figure BDA0003688663360000174
in order to reduce the influence of service time on random process parameters and interval process parameters when testing the reliability of the phononic crystal, the random process parameters and the interval process parameters are subjected to equivalent uncertain transformation, and the specific formula is as follows:
Figure BDA0003688663360000181
and obtaining equivalent random variable parameters and equivalent interval variable parameters which are irrelevant to time after conversion, thereby converting time-varying reliability analysis into time-invariant reliability analysis.
The time parameter T describing the service time of the phononic crystal is also converted into the time-varying life cycle [0, T ] of the phononic crystal L ]Equivalent distribution time parameter T ', T' -U (0, T) of internal equipartition distribution L )。
And constructing to obtain a reliability test model according to the random variable parameters, the interval variable parameters, the converted equivalent random variable parameters, the equivalent interval variable parameters and the equivalent distribution time parameters.
In the reliability test model, the limit state function for calculating whether the phononic crystal fails is correspondingly modified as follows:
Figure BDA0003688663360000182
the formula for calculating the failure probability of a phononic crystal becomes:
P f ＝Pr(g(X，Y，S′，I′，t′)＜0)
and when the failure probability of the phononic crystal needs to be predicted according to the reliability test model, training a neural network model according to the reliability test model to predict the failure probability of the phononic crystal. In order to accurately test the reliability of the phononic crystal, the invention uses an iterative learning method to update the trained neural network model. Therefore, the number of iterations is set to 1 when the neural network model is initially trained.
When training the neural network model, firstly, the sample point set S forming the sample space MCS Performing equivalent uncertain transformation, converting the sample point in the sample point set and the time-related parameters into time-unrelated parameters according to an equivalent uncertain transformation formula to obtain a transformed sample point set
Figure BDA0003688663360000183
Then, from the generated sample point set
Figure BDA0003688663360000184
And selecting a sample point to obtain a training set S. The number of sample points included in the training set S is M, M is less than or equal to N mc ，N mc As a set of sample points
Figure BDA0003688663360000185
The number of sample points included in (a).
And selecting sample points in a weight sampling mode when the sample points are selected from the sample space to obtain a training set S. First, for a sample point V of a sample space t (i) The sample weight can be calculated by the following formula:
Figure BDA0003688663360000191
then, calculating the characteristic value of each sample point according to the sample weight, specifically by the following formula:
Figure BDA0003688663360000192
and finally, sequencing each sample point according to the characteristic value from small to large, and selecting the first M sample points to obtain a training set S.
Sample point set
Figure BDA0003688663360000193
In the method, the unselected sample points, the sample points not in the training set S are taken as the candidate point set S * 。
And after obtaining the training set S, training the neural network model according to the training set S. After the neural network model is obtained through training, predicting the failure rate of the phononic crystal according to the neural network model; the transformed sample point set
Figure BDA0003688663360000194
Inputting the trained neural network model to obtain the failure rate of the instantaneous reliability of the phononic crystal.
And then, judging whether the failure rate of the instantaneous reliability of the obtained phononic crystal meets the stopping rule or not according to the stopping rule. The stopping rules include:
Figure BDA0003688663360000195
Figure BDA0003688663360000196
Figure BDA0003688663360000197
if the stopping rule is satisfied, the sample point set S is MCS And inputting the neural network model and outputting the failure rate of the mixed time-varying reliability of the phononic crystal.
If the stopping rule is not satisfied, updating the iteration number to increase the iteration number by 1.
Subsequently, from the candidate point set S * Determine a first set of points
Figure BDA0003688663360000198
Using the neural network model generated last time to set S of candidate points * Is calculated for each sample point in theA response value g to each sample point, calculated according to the formula:
Figure BDA0003688663360000201
then sorting according to the absolute value of the response value of each sample point, and selecting
Figure BDA0003688663360000202
Sample points as a first set of points
Figure BDA0003688663360000203
Figure BDA0003688663360000204
The magnitude of (c) can be calculated by the following formula:
Figure BDA0003688663360000205
then, from the first set of points
Figure BDA0003688663360000206
Selecting M experimental points as a second point set S according to a weight sampling mode K 。
Next, an active learning function is used to extract from the second set of points S K In determining the incremental sample point V new . Firstly, a K-fold verification cross-validation method is adopted to process a training set. The training set is equally divided into k training subsets, each of which includes the same number of sample points. And (3) sequentially taking each training subset of the k training subsets as a testing subset, taking other training subsets as training complement sets to train the neural network model, and training to obtain k supplementary neural network models.
And inputting the sample points into a supplementary neural network model to obtain a response value g. Obtaining a supplementary neural network model according to training of a training complement set
Figure BDA0003688663360000207
The response value is calculated according to the following formula:
Figure BDA0003688663360000208
set the second point S K Each sample point in the training set is input into the neural network model trained by the training set last time and k supplementary neural network models obtained by training by the training complement set, and the uncertainty of each sample point is calculated. Specifically, the calculation can be performed by the following formula:
Figure BDA0003688663360000209
subsequently, a second set of points S is calculated K The euclidean distance between each sample point and the existing training set S can be specifically calculated by the following formula:
Figure BDA00036886633600002010
finally, determining an incremental sample point V by using an active learning function according to the Euclidean distance and the uncertainty new Specifically, the calculation can be performed by the following formula:
Figure BDA0003688663360000211
for the second point set S K Inputting each sample point into the function value obtained by calculation of the active learning function, sequencing, and taking the sample point with the minimum function value obtained by calculation as an increment sample point V new 。
And adding the incremental sample points into the sample set S to obtain a new sample set, and training to obtain a new neural network model.
Training to obtain new neural network model, and collecting sample points
Figure BDA0003688663360000212
And inputting a new neural network model to obtain the failure rate of the instantaneous reliability of the phononic crystal. Then judging whether a stopping rule is met; if the stopping rule is satisfied, the iteration is stopped. Then, based on the sample point set S MCS And inputting a new neural network model and outputting the failure rate of the mixed time-varying reliability of the phononic crystal. If the stopping rule is not met, continuing the iteration, and increasing the iteration number k by 1; the newly generated neural network model is then continually updated until the failure rate of the instantaneous reliability of the output meets the stopping rule.
When the stopping rule is satisfied, calculating the variation coefficient of the failure rate according to the failure rate of the obtained mixed time-varying reliability of the phononic crystal, specifically calculating by the following formula:
Figure BDA0003688663360000213
and comparing the calculated variation coefficient with a preset coefficient threshold, and outputting the failure rate if the variation coefficient is greater than the preset coefficient threshold.
And if the variation coefficient is smaller than the preset coefficient threshold, increasing the number of sample points in the sample space to obtain a new sample space, repeating the steps according to the new sample space to obtain a new neural network model, and calculating the failure rate and the variation coefficient until the calculated coding coefficient is larger than the preset coefficient threshold.
When failure rate of the phononic crystal in service time is calculated, the failure rate includes a lower bound
Figure BDA0003688663360000214
And upper bound
Figure BDA0003688663360000215
The failure rate generated at the end includes an upper failure rate bound and a lower failure rate bound, i.e., between the upper failure rate bound and the lower real-time rate bound.
The invention discloses a phononic crystal time-varying reliability testing method which is suitable for being executed in computing equipment. The method comprises the following steps: determining a sample space according to parameters of the phononic crystal; constructing a reliability test model according to the sample space and the failure conditions of the phononic crystal; constructing a neural network model according to the reliability test model; and predicting the failure rate of the phononic crystal in the service time according to the neural network model and the sample space. According to the method, the failure rate of the phononic crystal in the service time can be predicted by constructing the reliability test model of the phononic crystal and constructing the neural network model through the reliability test model, the phenomenon that the performance of the phononic crystal cannot be judged due to the lack of parameters of the phononic crystal is avoided, and the performance of the phononic crystal in the service time is determined.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
A9, the method as claimed in A8, wherein said determining incremental sample points according to said number of iterations comprises the steps of:
determining a candidate point set according to a training set, and determining a first point set according to the candidate point set;
determining a second set of points from the first set of points by weight sampling;
determining incremental sample points from the second set of points according to an active learning function.
A10, the method of A9, wherein said determining incremental sample points from said second set of points according to an active learning function comprises the steps of:
determining an uncertainty for each sample point in the second set of points;
determining the Euclidean distance between each sample point in the second point set and the training set;
inputting the uncertainty and Euclidean distance of each sample point into an active learning function to obtain a function value of each sample point;
and taking the sample point with the minimum function value in the second point set as the increment sample point.
A11, the method of A10, wherein the determining the uncertainty of each sample point in the second set of points comprises the steps of:
generating a plurality of training complementary sets according to the sample set generated last time;
generating a supplementary neural network model according to each training complementary set;
the uncertainty for each sample point is determined from the supplemental neural network model and the last generated neural network model.
A12, the method as claimed in any one of A1-A11, wherein the predicting the failure rate of the phononic crystal in service time according to the neural network model and the sample space comprises the steps of:
and calculating the failure rate of the mixing time-varying reliability of the phononic crystal according to the neural network model and the sample points in the sample space.
A13, the method of A12, wherein the method further comprises the steps of:
calculating the variation coefficient of the failure rate according to the failure rate of the mixing time-varying reliability of the phononic crystal;
determining whether the coefficient of variation is greater than a preset coefficient threshold;
if the variation coefficient is not larger than a preset coefficient threshold value, adding a new sample point into the sample space to obtain a new sample space;
and training a neural network model according to the new sample space until the variation coefficient of the neural network model is greater than the preset minimum threshold.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects.
Those skilled in the art will appreciate that the modules or units or groups of devices in the examples disclosed herein may be arranged in a device as described in this embodiment, or alternatively may be located in one or more devices different from the devices in this example. The modules in the foregoing examples may be combined into one module or may be further divided into multiple sub-modules.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. Modules or units or groups in embodiments may be combined into one module or unit or group and may furthermore be divided into sub-modules or sub-units or sub-groups. All of the features disclosed in this specification, and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except for at least some of such features and/or processes or elements being mutually exclusive. Each feature disclosed in this specification may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments.
Additionally, some of the embodiments are described herein as a method or combination of method elements that can be implemented by a processor of a computer system or by other means of performing the described functions. A processor having the necessary instructions for carrying out the method or method elements thus forms a means for carrying out the method or method elements. Further, the elements of the apparatus embodiments described herein are examples of the following apparatus: the apparatus is used to implement the functions performed by the elements for the purpose of carrying out the invention.
The various techniques described herein may be implemented in connection with hardware or software or, alternatively, with a combination of both. Thus, the methods and apparatus of the present invention, or certain aspects or portions thereof, may take the form of program code (i.e., instructions) embodied in tangible media, such as floppy diskettes, CD-ROMs, hard drives, or any other machine-readable storage medium, wherein, when the program is loaded into and executed by a machine, such as a computer, the machine becomes an apparatus for practicing the invention.
In the case of program code execution on programmable computers, the computing device will generally include a processor, a storage medium readable by the processor (including volatile and non-volatile memory and/or storage elements), at least one input device, and at least one output device. Wherein the memory is configured to store program code; the processor is configured to execute the phononic crystal time-varying reliability test method of the present invention in accordance with instructions in the program code stored in the memory.
By way of example, and not limitation, computer readable media may comprise computer storage media and communication media. Computer-readable media includes both computer storage media and communication media. Computer storage media store information such as computer readable instructions, data structures, program modules or other data. Communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. Combinations of any of the above are also included within the scope of computer readable media.
As used herein, unless otherwise specified the use of the ordinal adjectives "first", "second", "third", etc., to describe a common object, merely indicate that different instances of like objects are being referred to, and are not intended to imply that the objects so described must be in a given sequence, either temporally, spatially, in ranking, or in any other manner.
While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of this description, will appreciate that other embodiments can be devised which do not depart from the scope of the invention as described herein. Furthermore, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, many modifications and variations will be apparent to practitioners skilled in this art. The disclosure of the present invention is intended to be illustrative, but not limiting, of the scope of the invention.

Claims (10)

1. A phononic crystal time-varying reliability testing method, adapted to be executed in a computing device, the method comprising the steps of:
determining a sample space according to parameters of the phononic crystal;
constructing a reliability test model according to the sample space and the failure condition of the phononic crystal;
constructing a neural network model according to the reliability test model;
and predicting the failure rate of the phononic crystal in service time according to the neural network model and the sample space.
2. The method of claim 1, wherein the parameters of the phononic crystal comprise: random variable parameters, random process parameters, interval variable parameters and interval process parameters;
the method for constructing the reliability test model according to the sample space and the failure condition of the phononic crystal comprises the following steps:
converting random process parameters in the crystal parameters to obtain equivalent random variable parameters;
converting the interval process parameters in the crystal parameters to obtain equivalent interval variable parameters;
converting the time parameter of the service time of the phononic crystal into an equivalent distribution time parameter;
and constructing a reliability test model according to the random variable parameters, the equivalent random variable parameters, the interval variable parameters, the equivalent distribution time parameters and the failure conditions.
3. The method of claim 2, wherein the failure condition comprises:
and in the service time, when the lower limit of the band gap of the phononic crystal is greater than the preset frequency, the phononic crystal fails.
4. The method of any one of claims 1-3, wherein said building a neural network model from said reliability test model comprises the steps of:
determining a training set according to the sample point set;
and training the neural network model according to the reliability test model and the training set.
5. The method of claim, wherein said determining a training set from a set of sample points comprises the steps of:
converting the sample points in the sample space to obtain a converted sample point set;
and determining a training set according to the converted sample point set.
6. The method of claim 5, wherein the determining a training set from the transformed sample point set comprises the steps of:
determining the sample weight of each sample point in the converted sample point set;
determining a characteristic value of each sample point according to the sample weight;
and determining a training set from the converted sample point set according to the characteristic value.
7. The method of claim 5, wherein said translating the sample points of the sample space comprises the steps of:
and carrying out equivalent uncertain transformation on each sample point in the sample space to obtain a sample point set independent of time.
8. The method of claim 4, wherein the method further comprises the steps of:
judging whether the failure rate of the instantaneous reliability calculated by the neural network model meets a stopping rule or not;
if the stopping rule is not met, setting iteration times, and determining an incremental sample point according to the iteration times;
determining a new sample set according to the incremental sample points and the sample set;
and training a new neural network model according to the new sample set until the training obtains the neural network model meeting the stopping rule.
9. A computing device, comprising:
one or more processors;
a memory; and
one or more apparatuses comprising instructions for performing the method of any of claims 1-8.
10. A computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform the method of any of claims 1-8.
CN202210663980.8A 2022-06-10 2022-06-10 Time-varying reliability testing method for photonic crystal, computing equipment and storage medium Pending CN114997060A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210663980.8A CN114997060A (en) 2022-06-10 2022-06-10 Time-varying reliability testing method for photonic crystal, computing equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210663980.8A CN114997060A (en) 2022-06-10 2022-06-10 Time-varying reliability testing method for photonic crystal, computing equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114997060A true CN114997060A (en) 2022-09-02

Family

ID=83032984

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210663980.8A Pending CN114997060A (en) 2022-06-10 2022-06-10 Time-varying reliability testing method for photonic crystal, computing equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114997060A (en)

Similar Documents

Publication Publication Date Title
Wan et al. Data-assisted reduced-order modeling of extreme events in complex dynamical systems
Robert et al. The metropolis—hastings algorithm
JP2023522567A (en) Generation of integrated circuit layouts using neural networks
Gįmiz et al. Applied nonparametric statistics in reliability
Yondo et al. A review of surrogate modeling techniques for aerodynamic analysis and optimization: current limitations and future challenges in industry
CN109643398A (en) The fidelity of quantum computing systems is estimated
Ipek et al. Efficient architectural design space exploration via predictive modeling
US20210151128A1 (en) Learning Method, Mixing Ratio Prediction Method, and Prediction Device
Chakraborty et al. Polynomial correlated function expansion for nonlinear stochastic dynamic analysis
Ezzell et al. Quantum mixed state compiling
Michoski et al. Solving irregular and data-enriched differential equations using deep neural networks
Jin Compositional kernel learning using tree-based genetic programming for Gaussian process regression
JP2023510922A (en) Optimizing High-Cost Functions for Complex Multidimensional Constraints
US10803218B1 (en) Processor-implemented systems using neural networks for simulating high quantile behaviors in physical systems
JP6219528B2 (en) Simulation system and simulation method
Glynn Exact simulation vs exact estimation
JP2020091791A (en) Estimation device, optimizing device, estimating method, optimizing method, and program
US20220253740A1 (en) Systems and methods for simulating a quantum processor
CN114692529B (en) CFD high-dimensional response uncertainty quantification method and device, and computer equipment
CN114997060A (en) Time-varying reliability testing method for photonic crystal, computing equipment and storage medium
WO2021250751A1 (en) Learning method, learning device, and program
US20200381078A1 (en) Structure search apparatus, method, and recording medium
Gratton et al. Derivative‐free optimization for large‐scale nonlinear data assimilation problems
US20110257943A1 (en) Node-based transient acceleration method for simulating circuits with latency
McConaghy et al. 3-Sigma verification and design: rapid design iterations with Monte Carlo accuracy

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination