Device life determination method and apparatus, electronic device, and storage medium

Abstract

The present disclosure provides a device lifetime determination method and device, electronic equipment and storage medium. Wherein, the method comprises: obtaining a second array and a first array corresponding to the second array according to the standard normal cumulative distribution function, the second array comprising a plurality of failure rates, and the first array comprising variable values corresponding to the plurality of failure rates; performing data processing on the first array and the second array to construct a first distribution function; receiving any failure rate input by a user, and determining the device lifetime of a target device under any failure rate by using the first distribution function, so as to realize the determination of the device lifetime by customizing the failure rate through the construction of the first distribution function, guarantee the flexibility and expansibility of the determination of the device lifetime, and thus improve the accuracy of the determination of the device lifetime.

Description

Technical Field

[0001] This disclosure relates to the field of device lifetime prediction technology, and in particular to a device lifetime determination method, apparatus, electronic device and storage medium. Background Technology

[0002] As the integration level of electronic devices increases and their size shrinks, the lifespan of these devices becomes increasingly prominent, becoming a key factor affecting the overall performance and lifespan of circuits.

[0003] Currently, related technologies assume that the device lifetime follows a normal distribution and evaluate the circuit lifetime based on a specific failure rate (e.g., 0.1%). However, because the C language standard library does not directly provide an inverse function operation for the normal distribution cumulative function, these technologies cannot dynamically determine the corresponding device lifetime based on the user-specified failure rate. This limits the flexibility and scalability of device lifetime determination, thus affecting its accuracy. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, and storage medium for determining device lifetime.

[0005] According to a first aspect of this disclosure, a method for determining device lifetime is provided. The method includes: obtaining a second array and a first array corresponding to the second array based on a standard normal cumulative distribution function, wherein the second array includes multiple failure rates and the first array includes variable values ​​corresponding to multiple failure rates; performing data processing on the first array and the second array to construct a first distribution function; receiving any failure rate input by a user, and using the first distribution function to determine the device lifetime of the target device at any failure rate.

[0006] In some embodiments of this disclosure, data processing of the first array and the second array to construct a first distribution function includes: inverting each variable value in the first array to obtain a first processed array; taking the logarithm of each failure rate in the second array and inverting each failure rate after the logarithm taking to obtain a second processed array; and fitting the first processed array and the second processed array to obtain a fitted first distribution function.

[0007] In some embodiments of this disclosure, obtaining the first array corresponding to the second array based on the standard normal cumulative distribution function includes: determining the first array corresponding to the second array based on the mapping relationship between the variable values ​​of the standard normal distribution and the probability of the standard normal distribution in the standard normal cumulative distribution function.

[0008] In some embodiments of this disclosure, fitting a first processing array and a second processing array to obtain a fitted first distribution function includes: fitting the first processing array and the second processing array to obtain a first polynomial; multiplying the adjustment formula by the first polynomial to obtain a second polynomial, and using the second polynomial as the first distribution function.

[0009] In some embodiments of this disclosure, a second array and a first array corresponding to the second array are obtained based on the standard normal cumulative distribution function. Then, the method includes: if the failure rate in the second array is greater than or equal to a preset failure rate, then the failure rate in the second array is complemented to obtain a second array after complementation.

[0010] In some embodiments of this disclosure, receiving any failure rate input by the user and determining the device lifetime of the target device at any failure rate using a first distribution function includes: determining the distribution parameters of the target device and the estimated device lifetime corresponding to a preset failure rate; inputting any failure rate input by the user into the first distribution function, and using the distribution parameters, the estimated product, and the first distribution function to determine the device lifetime of the target device at any failure rate.

[0011] According to a second aspect of this disclosure, a device lifetime determination apparatus is provided, the apparatus comprising:

[0012] The array determination unit is used to obtain the second array and the first array corresponding to the second array based on the standard normal cumulative distribution function. The second array includes multiple failure rates, and the first array includes variable values ​​corresponding to multiple failure rates.

[0013] The function building unit is used to process the data of the first array and the second array to construct the first distribution function;

[0014] The lifetime determination unit is used to receive any failure rate input by the user and determine the device lifetime of the target device under any failure rate using a first distribution function.

[0015] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0019] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0020] A fifth aspect of this disclosure provides a computer program product including a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0021] The device lifetime determination method, apparatus, electronic device, and storage medium disclosed herein obtain a second array and a first array corresponding to the second array based on a standard normal cumulative distribution function. The second array includes multiple failure rates, and the first array includes variable values ​​corresponding to multiple failure rates. Data processing is performed on the first array and the second array to construct a first distribution function. Any failure rate input by the user is received, and the device lifetime of the target device under any failure rate is determined using the first distribution function. This enables the determination of device lifetime by customizing failure rates through the construction of the first distribution function, ensuring the flexibility and scalability of device lifetime determination, thereby improving the accuracy of device lifetime determination.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0023] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0024] Figure 1 A schematic flowchart illustrating a device lifetime determination method provided in an embodiment of this disclosure;

[0025] Figure 2 This is a schematic flowchart illustrating another method for determining device lifetime provided in an embodiment of this disclosure;

[0026] Figure 3 A schematic diagram of a standard normal cumulative distribution function provided in an embodiment of this disclosure;

[0027] Figure 4 This is a schematic diagram illustrating data processing of the failure rate in a second array, provided by an embodiment of the present disclosure.

[0028] Figure 5 This is a schematic diagram illustrating data processing of variable values ​​in a first array, provided by an embodiment of the present disclosure.

[0029] Figure 6 This is a schematic diagram illustrating the fitting of a first processing array and a second processing array according to an embodiment of the present disclosure;

[0030] Figure 7 This is a schematic diagram of a device lifetime determination apparatus provided in an embodiment of the present disclosure;

[0031] Figure 8 A schematic block diagram of an example electronic device 800 provided for embodiments of this disclosure. Detailed Implementation

[0032] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0033] As electronic devices become increasingly integrated and smaller, their reliability becomes increasingly critical. The failure of a single device can disrupt the timing of the entire circuit, leading to circuit failure. Reliability simulation models the degradation of individual devices and provides predictions of circuit degradation, enabling designers to understand how long the circuit can operate normally.

[0034] In reliability model simulations, the lifespan of individual components is also a concern for designers. Due to the randomness of processes and environments, fluctuations exist between the same type of components. Therefore, two components with identical designs may show differences in lifespan after fabrication and testing. A circuit contains a large number of components, each with a lifespan that is randomly distributed around the lifespan of that type of component. To ensure the normal operation of the circuit and minimize the impact of component failure on the circuit's lifespan, the industry commonly uses 0.1% of the component failure time as the component's lifespan output, ensuring that 99.9% of components can operate stably and normally within that time.

[0035] Currently, the fitting of reliability models in related technologies is based on actual test data. Since the reliability code supported by current simulators is almost entirely compiled in C language, and the C language standard library does not have the inverse function operation of the normal distribution cumulative function, it is usually assumed that the device lifetime conforms to a normal distribution, and the device lifetime is evaluated based on a specific failure rate (such as 0.1%).

[0036] It is evident that the relevant technologies have significant limitations. The methods for determining product lifetime in these technologies cannot support user-defined failure rates, such as 0.01%. This limits the flexibility and scalability of the simulator and affects the accuracy of device lifetime determination.

[0037] To address the problems in related technologies, this disclosure proposes a device lifetime determination method that constructs a distribution function. This distribution function allows the failure rate to be used as a user-input parameter, facilitating the determination of the device lifetime corresponding to that failure rate. This ensures the flexibility and scalability of device lifetime determination, thereby improving the accuracy of device lifetime determination.

[0038] The following description, with reference to the accompanying drawings, outlines a method, apparatus, electronic device, and storage medium for determining device lifetime according to embodiments of the present disclosure.

[0039] Figure 1 This is a schematic flowchart illustrating a device lifetime determination method provided in an embodiment of this disclosure. Figure 1 As shown, this method can be applied to a device lifetime determination system, and the method includes:

[0040] Step 101: Based on the standard normal cumulative distribution function, obtain the second array and the first array corresponding to the second array. The second array includes multiple failure rates, and the first array includes variable values ​​corresponding to multiple failure rates.

[0041] In some embodiments, the Standard Normal Cumulative Distribution Function (CDF) is used to describe the probability that a random variable is less than or equal to a specific value under a standard normal distribution. The standard normal distribution is a normal distribution with a mean of 0 and a standard deviation of 1.

[0042] In this disclosure, the multiple failure rates in the second array specifically refer to standard normal distribution probabilities. Since a large number of devices need to function correctly in simulations, the failure rate values ​​in this disclosure are typically small, below 1%. Therefore, this disclosure can select some commonly used failure rates. The variable values ​​refer to the variable values ​​of the standard normal distribution. This disclosure can use the standard normal cumulative distribution function to calculate the corresponding variable value (i.e., the inverse function value) of each failure rate (i.e., the standard normal distribution probability) in the standard normal distribution using each failure rate in the second array.

[0043] Step 102: Process the data of the first array and the second array to construct the first distribution function.

[0044] In some embodiments, the first distribution function is the inverse function of the standard normal cumulative distribution function that can be used in the program. This disclosure obtains a first processed array and a second processed array by processing the variable values ​​in the first array and the failure rate in the second array, and then fits the first processed array and the second processed array to obtain the first distribution function. The data processing includes inversion and logarithmic operations.

[0045] Step 103: Receive any failure rate input by the user, and use the first distribution function to determine the device lifetime of the target device under any failure rate.

[0046] In some embodiments, after obtaining the first distribution function, the present disclosure can use the first distribution function in the process of determining device lifetime, that is, substitute any failure rate input by the user into the first distribution function, and calculate the device lifetime of the target device at any efficiency through the device lifetime determination formula.

[0047] It is important to note that before calculating the device lifetime using the device lifetime determination formula, it is also necessary to determine the distributed parameters of the current target device and the estimated device lifetime corresponding to the failure rate of the preset failure rate.

[0048] It should be noted that the first distribution function disclosed herein can be widely applied to all simulation program solutions for engineering reliability, and is not limited to the device lifetime determination process under the device aging scenario in this disclosure.

[0049] In summary, the technical solution provided in this disclosure obtains a second array and a first array corresponding to the second array based on a standard normal cumulative distribution function. The second array includes multiple failure rates, and the first array includes variable values ​​corresponding to multiple failure rates. Data processing is performed on the first array and the second array to construct a first distribution function. Any failure rate input by the user is received, and the device lifetime of the target device under any failure rate is determined using the first distribution function. This enables the determination of device lifetime by customizing the failure rate through the construction of the first distribution function, ensuring the flexibility and scalability of device lifetime determination, thereby improving the accuracy of device lifetime determination.

[0050] Figure 2 This is a schematic flowchart of another method for determining device lifetime provided in an embodiment of this disclosure. Figure 2 based on Figure 1 The illustrated embodiment further defines steps 101 and 102. Figure 2 In the illustrated embodiment, step 201 precedes step 101, and step 101 includes steps 202, 203, and 204. For example... Figure 2 As shown, the method may include:

[0051] Step 201: Based on the mapping relationship between the variable values ​​of the standard normal distribution and the probability of the standard normal distribution in the standard normal cumulative distribution function, determine the first array corresponding to the second array.

[0052] In some embodiments, such as Figure 3 As shown, this disclosure provides a schematic diagram of a standard normal cumulative distribution function. This disclosure can be used to... Figure 3The mapping relationship between the variable values ​​and the standard normal cumulative distribution function in the standard normal cumulative distribution function is obtained, and the interval points of the standard normal cumulative distribution function are obtained by referring to... Figure 3 The vertical axis represents the standard normal distribution probability, and the horizontal axis represents the variable value. As shown in Table 1, the Y values ​​in Table 1 represent the standard normal distribution variable values ​​in the first array, and the standard normal cumulative distribution probability represents the failure rate in the second array, which can also be called the standard normal distribution probability.

[0053] Y value Standard normal cumulative distribution probability -5.199337582 0.00001％ -4.753424309 0.0001％ -4.264890794 0.001％ -3.719016485 0.01％ -3.090232306 0.1％ -2.326347874 1％ -1.281551566 10％ 0 50％

[0054] Table 1

[0055] It should be noted that in this disclosure, the variable values ​​and failure rates in the first and second arrays are arbitrary, and the number is greater than or equal to two. The failure rate in the second array must be between 0 and 1.

[0056] In this process, after obtaining the second array and the corresponding first array based on the standard normal cumulative distribution function, this disclosure utilizes the symmetry of the standard normal cumulative distribution function about 0.5. If the failure rate in the second array is greater than or equal to a preset failure rate, then the failure rate in the second array is complemented to obtain the second array after complementation. Specifically, when the failure rate (i.e., the standard normal distribution probability) is greater than or equal to 50%, since the standard normal distribution probability is represented by X, complementing X (i.e., first subtracting the value of X from 1) transforms X into 1-X for subsequent data processing. For example, when the standard normal distribution probability is 99%, 1% can be obtained by first subtracting X, and then data processing can be performed on 1%.

[0057] Step 202: Invert the value of each variable in the first array to obtain the first processed array.

[0058] Step 203: Take the logarithm of each failure rate in the second array, and then invert the logarithm of each failure rate to obtain the second processed array.

[0059] In some embodiments, such as Figure 4 The present disclosure provides a schematic diagram for data processing of the failure rate in the second array, as shown below. Figure 5 The present disclosure provides a schematic diagram for data processing of variable values ​​in a first array.

[0060] Reference Figure 4 This disclosure applies a logarithmic transformation to the failure rate (i.e., the standard normal cumulative distribution probability) with a base of 10. Since the failure rate ranges from 0 to 1, this disclosure requires a logarithmic transformation to the failure rate in the second array to avoid the problem that when the failure rate is very small, the differences between the data are very small, making it difficult to fit the data.

[0061] Reference Figure 4 and Figure 5 This disclosure inverts the logarithmic failure rate and variable values ​​(i.e., Y values) to obtain the first and second processed arrays. Except for the failure rate of modeling with measured data, which is around 50%, the failure rates of other simulations are between 0 and 50%. In these cases, the inverse value of the standard normal distribution cumulative function is negative. To facilitate subsequent modeling, this disclosure inverts each logarithmic failure rate and each variable value by multiplying them by -1 to convert them into positive values ​​and inverting them, thus changing the parameters to positive values ​​for easier subsequent fitting.

[0062] Step 204: Fit the first processing array and the second processing array to obtain the fitted first distribution function.

[0063] In some embodiments, when the failure rate is less than one ten-millionth (0.00001%), the lifetime is too short, and the differences between devices are also very small, making it difficult to reflect the degradation characteristics of actual devices, so it is rarely used. Therefore, this disclosure focuses on setting the failure rate range between 0.00001% and 50% to perform formula fitting on the first and second processing arrays, such as... Figure 6 The diagram shown is a schematic diagram of fitting a first processing array and a second processing array provided by this disclosure. Specifically, this disclosure fits the variable value (-Y) in the first processing array after inversion and the failure rate (-logX) in the second processing array after logarithmic and inversion processing.

[0064] The present disclosure describes fitting a first processing array and a second processing array to obtain a first distribution function, which includes: fitting the first processing array and the second processing array to obtain a first polynomial; multiplying the adjustment formula with the first polynomial to obtain a second polynomial, and using the second polynomial as the first distribution function.

[0065] The first polynomial refers to Y = -[(-log(X) - a) 2 +c], where a and c are constants. To ensure that the point of failure rate of 50% corresponds exactly to a variable value of 0, this disclosure multiplies the first polynomial by an adjustment formula, namely the formula related to (x-0.5). (x-0.5) is a simple linear factor, its value is 0 when x equals 0.5. However, directly multiplying by (x-0.5) may cause the value to change too drastically near x = 0.5 (unless the other terms of the polynomial are very small). Therefore, this disclosure proposes a smoother adjustment formula, such as power(2*abs(x-0.5), 0.1), which, when multiplied by the first polynomial, yields Y = -[(-log(X)-a)]2 +c]*power(2*abs(x-0.5), 0.1).

[0066] Step 205: Receive any failure rate input by the user, and use the first distribution function to determine the device lifetime of the target device under any failure rate.

[0067] In some embodiments, the distribution parameters of the target device and the estimated device lifetime corresponding to the failure rate of the preset failure rate are determined; any failure rate input by the user is input into the first distribution function, and the device lifetime of the target device under any failure rate is determined using the distribution parameters, the estimated product and the first distribution function.

[0068] Specifically, this disclosure first determines the distribution parameters of the target device and the estimated lifetime at a failure rate of 50% through experimental test data; then, using these distribution parameters, the estimated lifetime, and the first distribution function, the device lifetime of the target device at any failure rate is obtained. The specific formula is as follows:

[0069] Lifetime (any failure rate) = lifetime(50%) * exp[(normsinv(any failure rate) - normsinv(50%)) / (1 / sigma)]

[0070] Wherein, Lifetime(50%) is the estimated lifetime of the target device when the failure rate is 50%, sigma is the distribution parameter of the target device, normsinv is the first distribution function constructed in this disclosure, and Lifetime(any failure rate) refers to the device lifetime calculated for the target device under any failure rate.

[0071] In summary, this disclosure solves the problem of customers wanting to customize failure rates to view device lifetime and aging simulation results during the simulation process. It eliminates the need to purchase third-party library files, avoiding the problem of dynamic library simulations failing due to the lack of third-party libraries. Furthermore, the program is simple and practical, using a simple approximation formula to replace the standard normal cumulative distribution inverse function, thus solving the problems of the absence of the standard normal cumulative distribution inverse function in the program and the high computational complexity of the standard normal cumulative distribution inverse function. This can reduce the program's computation time while maintaining similar results. By adjusting parameters a and c in the first distribution function, this disclosure can effectively minimize the errors at the failure rates of 0.1%, 0.001%, and 0.0001%, ensuring simulation accuracy for commonly used industrial failure rates while supporting continuous user input.

[0072] Corresponding to the device lifetime determination method described above, this invention also proposes a device lifetime determination apparatus. Since the apparatus embodiments of this invention correspond to the method embodiments described above, details not disclosed in the apparatus embodiments can be referred to in the method embodiments described above, and will not be repeated here.

[0073] Figure 7 This is a schematic diagram of a device lifetime determination apparatus provided in an embodiment of the present disclosure, as shown below. Figure 7 As shown, the device includes:

[0074] The array determination unit 710 is used to obtain the second array and the first array corresponding to the second array based on the standard normal cumulative distribution function. The second array includes multiple failure rates, and the first array includes variable values ​​corresponding to multiple failure rates.

[0075] The function construction unit 720 is used to process the data of the first array and the second array to construct the first distribution function;

[0076] The lifetime determination unit 730 is used to receive any failure rate input by the user and determine the device lifetime of the target device under any failure rate using a first distribution function.

[0077] In some embodiments of this disclosure, the function construction unit 720 is used to: invert each variable value in the first array to obtain a first processing array; take the logarithm of each failure rate in the second array, and invert each failure rate after the logarithm taking to obtain a second processing array; and fit the first processing array and the second processing array to obtain a fitted first distribution function.

[0078] In some embodiments of this disclosure, the array determination unit 710 is used to: determine the first array corresponding to the second array based on the mapping relationship between the variable values ​​of the standard normal distribution and the probability of the standard normal distribution in the standard normal cumulative distribution function.

[0079] In some embodiments of this disclosure, the function construction unit 720 is configured to: fit a first processing array and a second processing array to obtain a first polynomial; multiply an adjustment formula by the first polynomial to obtain a second polynomial, and use the second polynomial as a first distribution function.

[0080] In some embodiments of this disclosure, the array determination unit 710 is used to: obtain a second array and a first array corresponding to the second array based on the standard normal cumulative distribution function; and then, if the failure rate in the second array is greater than or equal to a preset failure rate, perform complementary processing on the failure rate in the second array to obtain a second array after complementary processing.

[0081] In some embodiments of this disclosure, the lifetime determination unit 730 is used to: determine the distribution parameters of the target device and the estimated device lifetime corresponding to a preset failure rate; input any failure rate input by the user into a first distribution function, and use the distribution parameters, the estimated product and the first distribution function to determine the device lifetime of the target device under any failure rate.

[0082] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of this embodiment, and the principle is the same, so it is not limited in this embodiment.

[0083] According to embodiments of this disclosure, this disclosure also provides an electronic device and a readable storage medium.

[0084] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0085] like Figure 8 As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 802 or a computer program loaded from storage unit 808 into RAM (Random Access Memory) 803. RAM 803 can also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. I / O (Input / Output) interface 805 is also connected to bus 804.

[0086] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0087] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the device lifetime determination method. For example, in some embodiments, the device lifetime determination method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the aforementioned device lifetime determination method by any other suitable means (e.g., by means of firmware).

[0088] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0089] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0090] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0091] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0092] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0093] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0094] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0095] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0096] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method of determining the lifetime of a device, characterized in that The method comprises: According to the mapping relationship between the variable value of the standard normal distribution and the standard normal distribution probability in the standard normal cumulative distribution function, a second array and a first array corresponding to the second array are determined, the second array comprises a plurality of failure rates, and the first array comprises a plurality of variable values corresponding to the failure rates; Data processing is performed on the variable values in the first array and the failure rates in the second array to obtain a first processing array and a second processing array; Fitting is performed on the first processing array and the second processing array to construct a first distribution function; Any failure rate input by a user is received, and the device life of a target device under the any failure rate is determined by using the first distribution function; The data processing on the variable values in the first array and the failure rates in the second array to obtain the first processing array and the second processing array comprises: The first processing array is obtained by performing negation processing on each variable value in the first array; The second processing array is obtained by performing logarithm processing on each failure rate in the second array and then performing negation processing on each failure rate after the logarithm processing; The fitting on the first processing array and the second processing array to construct the first distribution function comprises: fitting the first and second sets of processed data to a first polynomial Y = -[(-log(X) - a) 2 + c], Wherein, Y is the first array, X is the second array, a and c are both constants; multiplying the adjustment formula power(2*abs(x-0.5), 0.1) with the first polynomial, resulting in a second polynomial Y = -[(-log(X) - a) 2 +c]*power(2*abs(x-0.5), 0.1), and using the second polynomial as the first distribution function, Wherein, x is the failure rate.

2. The method of claim 1, wherein, After the second array and the first array corresponding to the second array are determined according to the mapping relationship between the variable value of the standard normal distribution and the standard normal distribution probability in the standard normal cumulative distribution function, the method comprises: If the failure rate in the second array is greater than or equal to a preset failure rate, the failure rate in the second array is complementarily processed to obtain a second array after complementary processing.

3. The method of claim 2, wherein, The receiving of any failure rate input by a user and the determination of the device life of a target device under the any failure rate by using the first distribution function comprise: The distribution parameters of the target device and the estimated device life corresponding to the preset failure rate when the failure rate is the preset failure rate are determined; Any failure rate input by the user is input into the first distribution function, and the device life of the target device under any failure rate is determined by using the distribution parameters, the estimated device life, and the first distribution function.

4. A device lifetime determination apparatus characterized by comprising: The device comprises: An array determination unit is configured to determine a second array and a first array corresponding to the second array according to a mapping relationship between a variable value of a standard normal distribution and a standard normal distribution probability in a standard normal cumulative distribution function, the second array comprises a plurality of failure rates, and the first array comprises a plurality of variable values corresponding to the failure rates; A function construction unit is configured to perform data processing on the variable values in the first array and the failure rates in the second array to obtain a first processing array and a second processing array, and perform fitting on the first processing array and the second processing array to construct a first distribution function; The data processing on the variable values in the first array and the failure rates in the second array to obtain the first processing array and the second processing array comprises: performing negation processing on each variable value in the first array to obtain a first processing array; performing logarithm processing on each failure rate in the second array, and performing negation processing on each failure rate after the logarithm processing to obtain a second processing array; the fitting the first processing array and the second processing array to construct the first distribution function comprises: fitting the first and second sets of processed data to a first polynomial Y = -[(-log(X) - a) 2 + c], wherein Y is the first array, X is the second array, and a and c are constants; multiplying the adjustment formula power(2*abs(x-0.5), 0.1) with the first polynomial, resulting in a second polynomial Y = -[(-log(X) - a) 2 +c]*power(2*abs(x-0.5), 0.1), and using the second polynomial as the first distribution function, wherein x is the failure rate; a life determination unit configured to receive any failure rate input by a user, and determine a device life of the target device at the any failure rate by using the first distribution function.

5. An electronic device, comprising: comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 3.

6. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, the computer instructions are used to enable the computer to perform the method of any one of claims 1 to 3.

7. A computer program product, characterised in that, comprising a computer program which, when executed by a processor, implements the method of any one of claims 1 to 3.

Images