Product life prediction method, device, equipment and storage medium

Abstract

The present disclosure provides a product life prediction method, device, equipment and storage medium, by acquiring the ideal parameters of each part in the product; the ideal parameters of each part in the product are input into a life prediction model to obtain a predicted life value, wherein the life prediction model is a model trained based on the product gene life, environmental life coefficient and life growth coefficient product, solves the problem that there is no mature prediction method for the life of electronic products in the prior art, provides a relatively rigorous and comprehensive life prediction method, which can not only effectively improve the accuracy of product life prediction, but also provides guidance for the research and development design of new products, and is suitable for all electronic products, and has wide applicability.

Description

Technical Field

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

[0002] In the design and engineering phases of electronic products, predicting product lifespan early is more effective than post-hoc testing or precise statistical analysis. By implementing a cycle of "prediction-improvement design-redesign," product weaknesses can be identified and circuit design optimized, enabling products to meet specified lifespan requirements. Currently, existing methods for predicting product lifespan are costly and yield inaccurate results. Summary of the Invention

[0003] This disclosure provides a product life prediction method, apparatus, device, and storage medium to at least solve the above-mentioned technical problems existing in the prior art.

[0004] According to a first aspect of this disclosure, a product lifespan prediction method is provided, the method comprising:

[0005] Obtain the ideal parameters for each component within the product;

[0006] The ideal parameters of each part in the product are input into the life prediction model to obtain the predicted life value. The life prediction model is a model trained based on the product of the product's genetic life, environmental life coefficient, and life growth coefficient.

[0007] In one possible implementation, prior to obtaining the ideal parameters of each part within the product, the method further includes:

[0008] Obtain the product's base lifespan and genetic lifespan coefficient; determine the product's genetic lifespan based on the relationship between the product's base lifespan, genetic lifespan coefficient, and genetic lifespan, wherein the relationship is:

[0009] .

[0010] In one possible implementation, obtaining the product's base lifespan and genetic lifespan coefficient includes:

[0011] The basic lifespan of the product is determined according to the product's basic failure rate formula, wherein the product's basic failure rate formula is:

[0012]

[0013] in, For the first of the products The general failure rate of a type of component under specified conditions. For the first of the products The design influence coefficient of this type of part For the first of the products The quality coefficient of the type of part For the first of the products The number of parts;

[0014] The genetic lifespan coefficient of the product is determined by multiplying the production capacity and quality management level of the enterprise that produces the product by the genetic lifespan coefficient.

[0015] In one possible implementation, before determining the basic lifespan of the product according to the product's basic failure rate formula, the method further includes:

[0016] The design influence coefficient of each component is determined by multiplying the component selection failure rate coefficient, component application failure rate coefficient, component temperature stress failure rate coefficient, and electrical stress failure rate coefficient.

[0017] The quality coefficient of each component is determined by using a table showing the relationship between the component procurement strategy and the failure rate coefficient.

[0018] In one possible implementation, before determining the design influence coefficient of each component by multiplying the component selection failure rate coefficient, component application failure rate coefficient, component temperature stress failure rate coefficient, and electrical stress failure rate coefficient, the method further includes:

[0019] The failure rate coefficient for part selection is determined based on the relationship table between the part selection failure rate coefficient and the part size specifications;

[0020] The application failure rate coefficient of the part is determined based on the relationship table between the application failure rate coefficient of the part and the placement position of the part.

[0021] The temperature stress failure rate coefficient of the part is determined according to the calculation formula of the temperature stress failure rate coefficient of the part, wherein the calculation formula of the temperature stress failure rate coefficient of the part is:

[0022] in, For reference temperature, The actual operating temperature of the component. The activation energy is given by k, where k is the Boltzmann constant.

[0023] The electrical stress failure rate coefficient of the component is determined according to the calculation formula of the electrical stress failure rate coefficient of the component, wherein the calculation formula of the electrical stress failure rate coefficient of the component is as follows:

[0024]

[0025] Where P1 is the percentage of applied stress, P0 is the empirical percentage of rated stress, and m is the fitting parameter.

[0026] In one possible implementation, before determining the genetic lifespan coefficient of the product by multiplying the production capacity and quality management level of the enterprise where the product is located by the genetic lifespan coefficient, the method further includes:

[0027] Based on the relationship table between the solder paste type and the failure rate coefficient of the product, the solder paste type factor of the product is determined;

[0028] Based on the relationship table between the chip welding process and the failure rate coefficient of the product, determine the chip welding process factors of the product;

[0029] Based on the relationship table between the product's operation type and failure rate coefficient, determine the automation level factors of the product;

[0030] Based on the relationship table between the worker skill level and the failure rate coefficient of the product, the worker skill level factor of the product is determined;

[0031] The production capacity of the enterprise producing the product is determined by multiplying the solder paste type, chip soldering process, automation level, worker skill level, and production capacity of the product.

[0032] The quality management level of the company producing the product is determined by using the relationship table between the product's quality management level and failure rate coefficient.

[0033] In one possible implementation, it further includes:

[0034] Based on the relationship table between the product's working environment and failure rate coefficient, the environmental life coefficient of the product is determined.

[0035] In one possible implementation, determining the product's lifespan growth factor includes:

[0036] Based on the relationship table between the development batches and failure rate coefficients of the product, the lifespan growth coefficient of the product is determined.

[0037] According to a second aspect of this disclosure, a product life prediction apparatus is provided, the apparatus comprising:

[0038] The parameter acquisition module is used to obtain the ideal parameters of each part within the product.

[0039] The life prediction module is used to input the ideal parameters of each part in the product into the life prediction model to obtain the predicted life value. The life prediction model is a model trained based on the product of the product's genetic life, environmental life coefficient and life growth coefficient.

[0040] In one possible implementation, before acquiring the ideal parameters of each part within the product, the device further includes a model training module, specifically used for:

[0041] Obtain the product's base lifespan and genetic lifespan coefficient; determine the product's genetic lifespan based on the relationship between the product's base lifespan, genetic lifespan coefficient, and genetic lifespan, wherein the relationship is:

[0042] .

[0043] In one possible implementation, the model training module is further configured to: obtain the product's base lifespan and genetic lifespan coefficient, including:

[0044] The basic lifespan of the product is determined according to the product's basic failure rate formula, wherein the product's basic failure rate formula is:

[0045]

[0046] in, For the first of the products The general failure rate of a type of component under specified conditions. For the first of the products The design influence coefficient of this type of part For the first of the products The quality coefficient of the type of part For the first of the products The number of parts;

[0047] The genetic lifespan coefficient of the product is determined by multiplying the production capacity and quality management level of the enterprise that produces the product by the genetic lifespan coefficient.

[0048] In one possible implementation, the model training module is further configured to: before determining the basic lifespan of the product according to the product's basic failure rate formula, include:

[0049] The design influence coefficient of each component is determined by multiplying the component selection failure rate coefficient, component application failure rate coefficient, component temperature stress failure rate coefficient, and electrical stress failure rate coefficient.

[0050] The quality coefficient of each component is determined by using a table showing the relationship between the component procurement strategy and the failure rate coefficient.

[0051] In one possible implementation, the model training module is further configured to:

[0052] Before determining the design influence coefficient of each component by multiplying its selection failure rate coefficient, application failure rate coefficient, temperature stress failure rate coefficient, and electrical stress failure rate coefficient, the component selection failure rate coefficient is determined based on the relationship table between the component selection failure rate coefficient and component size specifications; the component application failure rate coefficient is determined based on the relationship table between the component application failure rate coefficient and component placement position; and the component temperature stress failure rate coefficient is determined based on the calculation formula for the component temperature stress failure rate coefficient, wherein the calculation formula for the component temperature stress failure rate coefficient is:

[0053] in, For reference temperature, The actual operating temperature of the component. The activation energy is given by k, where k is the Boltzmann constant.

[0054] The electrical stress failure rate coefficient of the component is determined according to the calculation formula of the electrical stress failure rate coefficient of the component, wherein the calculation formula of the electrical stress failure rate coefficient of the component is as follows:

[0055]

[0056] Where P1 is the percentage of applied stress, P0 is the empirical percentage of rated stress, and m is the fitting parameter.

[0057] In one possible implementation, the model training module is further configured to:

[0058] Before determining the genetic lifetime coefficient of a product by multiplying the production capacity and quality management level of the enterprise where the product is located with the genetic lifetime coefficient, the solder paste type factor of the product is determined according to the relationship table between the solder paste type and the failure rate coefficient of the product.

[0059] Based on the relationship table between the chip welding process and the failure rate coefficient of the product, determine the chip welding process factors of the product;

[0060] Based on the relationship table between the product's operation type and failure rate coefficient, determine the automation level factors of the product;

[0061] Based on the relationship table between the worker skill level and the failure rate coefficient of the product, the worker skill level factor of the product is determined;

[0062] The production capacity of the enterprise producing the product is determined by multiplying the solder paste type, chip soldering process, automation level, worker skill level, and production capacity of the product.

[0063] The quality management level of the company producing the product is determined by using the relationship table between the product's quality management level and failure rate coefficient.

[0064] In one possible implementation, the model training module is further configured to:

[0065] Based on the relationship table between the product's working environment and failure rate coefficient, the environmental life coefficient of the product is determined.

[0066] In one possible implementation, the model training module is further configured to:

[0067] Based on the relationship table between the development batches and failure rate coefficients of the product, the lifespan growth coefficient of the product is determined.

[0068] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0069] At least one processor; and

[0070] A memory communicatively connected to the at least one processor; wherein,

[0071] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods described in this disclosure.

[0072] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing the computer to perform the methods described in this disclosure.

[0073] This disclosure discloses a product lifespan prediction method, apparatus, device, and storage medium. It obtains ideal parameters for each component within a product; inputs these ideal parameters into a lifespan prediction model to obtain a predicted lifespan value. The lifespan prediction model is trained based on the product of the product's genetic lifespan, environmental lifespan coefficient, and lifespan growth coefficient. This addresses the lack of mature lifespan prediction methods for electronic products in China, providing a more rigorous and comprehensive method. It not only effectively improves the accuracy of product lifespan prediction but also provides guidance for the research and development of new products. Furthermore, it is applicable to all electronic products and has wide applicability.

[0074] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0075] The above and other objects, features, and advantages of this disclosure will become readily apparent from the following detailed description of exemplary embodiments, taken in conjunction with the accompanying drawings. Several embodiments of this disclosure are illustrated in the drawings by way of example and not limitation, in which:

[0076] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts.

[0077] Figure 1 A schematic diagram illustrating the implementation process of a product lifetime prediction method provided in Embodiment 1 of this disclosure is shown.

[0078] Figure 2 A schematic diagram of a product pyramid life model provided in Embodiment 1 of this disclosure is shown;

[0079] Figure 3 A schematic diagram of a bathtub curve provided in Embodiment 1 of this disclosure is shown;

[0080] Figure 4 This diagram illustrates the structure of a product life prediction device according to Embodiment 3 of this disclosure;

[0081] Figure 5 A schematic diagram of the composition structure of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0082] To make the objectives, features, and advantages of this disclosure more apparent and understandable, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0083] Example 1

[0084] Figure 1 This is a flowchart illustrating a product lifetime prediction method provided in Embodiment 1 of this disclosure. This method can be executed by the product lifetime prediction device provided in this embodiment, which can be implemented using software and / or hardware. Specifically, the method includes:

[0085] S110, Obtain the ideal parameters of each part within the product.

[0086] Among them, ideal parameters can be the parameter values ​​of each part in the product under ideal conditions, that is, the specifications at the time of leaving the factory.

[0087] Specifically, in this embodiment, in order to obtain the predicted lifespan of the product, it is necessary to first obtain the parameters of each component within the product under ideal conditions, i.e., the ideal parameters of each component within the product. Since electronic products are composed of different components, and the parameter values ​​of different components from different manufacturers vary, the predicted lifespan of electronic products is closely related to the parameter values ​​of each component under ideal conditions. Therefore, in this embodiment, the specification values ​​of each component within the product can be obtained as ideal parameter values.

[0088] S120. Input the ideal parameters of each part in the product into the life prediction model to obtain the predicted life value.

[0089] The lifespan prediction model is a model trained based on the product of the product's genetic lifespan, environmental lifespan coefficient, and lifespan growth coefficient.

[0090] The lifespan prediction model can be any neural network model used to predict product lifespan. The predicted lifespan value can be the duration of normal user operation of the product. Genetic lifespan is related to factors such as the product's components, the environmental lifespan coefficient is related to the environment in which the product is used, and the lifespan growth coefficient is derived from experience from the product's development batches.

[0091] Generally speaking, taking computer products as an example, product lifespan is influenced by two main factors: intrinsic genetics and environmental factors. In addition to these two factors, this embodiment also discovered through years of research that the lifespan of computer products follows certain growth patterns, which are termed the lifespan growth coefficient. Lifespan growth refers to the regular increase in product lifespan compared to its predecessors, achieved through accumulated experience. This experience includes not only the company's R&D capabilities... Internal factors include manufacturing level, quality management level, and supply and procurement strategies, as well as external factors such as the product's usage environment and users' usage habits.

[0092] This embodiment, through years of experimentation and maintenance big data tracking and analysis, has established a universal lifespan model for computer products, used for more comprehensive and accurate pre-setting of product lifespan. For example... Figure 2 As shown in the figure, the model is a product lifespan pyramid model. R&D capability is at the base of the pyramid, forming the foundation of product lifespan; lifespan growth is at the top, representing a combination of accumulated product experience and industry development trends. Procurement strategy, manufacturing capability, quality management level, and environment are external factors affecting product lifespan. According to the model, product lifespan is primarily determined by genetic lifespan, environmental lifespan coefficient, and lifespan growth coefficient, summarized in the following formula:

[0093]

[0094] It should be noted that this embodiment Figure 2 Although the lifespan model is based on computer products, the product lifespan prediction method in this embodiment can be extended to other types of electronic products because the composition and manufacturing process of electronic products are highly similar.

[0095] Specifically, since different electronic products have different components, this embodiment first performs targeted model training for different types and models of products to obtain a lifespan prediction model. Then, this embodiment inputs the ideal parameters of each component in the product sequentially or jointly into the lifespan prediction model to obtain the predicted lifespan value corresponding to that type of product.

[0096] In this embodiment of the disclosure, before obtaining the ideal parameters of each component within the product, the following steps are also included:

[0097] Obtain the product's base lifespan and genetic lifespan coefficient; determine the product's genetic lifespan based on the relationship between the base lifespan, genetic lifespan coefficient, and genetic lifespan, where the relationship is:

[0098]

[0099] In equation (2) above, gene lifespan is an internal factor of product lifespan, which is determined by the product manufacturing enterprise itself. Product gene lifespan consists of two parts: basic lifespan and gene lifespan coefficient. Basic lifespan is determined by the enterprise's R&D capabilities and procurement strategies, and is the main component of product lifespan; gene lifespan coefficient is mainly determined by the enterprise's manufacturing capabilities and quality management level.

[0100] In this embodiment of the disclosure, obtaining the product's base lifespan and genetic lifespan coefficient includes: determining the product's base lifespan according to the product's base failure rate formula, wherein the product's base failure rate formula is:

[0101]

[0102] in, For the first of the products The general failure rate of a type of component under specified conditions. For the first of the products The design influence coefficient of this type of part For the first of the products The quality coefficient of the type of part For the first of the products The number of parts;

[0103] The genetic lifespan coefficient of the product is determined by multiplying the production capacity and quality management level of the enterprise that produces the product by the genetic lifespan coefficient.

[0104] Specifically, different products exhibit different distribution characteristics in their lifespan data. Product failure is a random event, and its instantaneous failure rate is a function of time. Generally, product failure rate curves can be increasing, decreasing, or constant. Lifespan studies of computer products have revealed that these products follow a typical failure rate curve. This curve is characterized by high peaks and low troughs, and is known as a "bathtub curve," as shown below. Figure 3 As shown. (Through) Figure 3 As can be seen from the curve, the failure rate of electronic products, represented by computers, is not constant throughout their entire life cycle. The "bathtub curve" is divided into three time periods as follows:

[0105] 1) Early stage (or early failure stage): The early failure stage is characterized by a high failure rate at the beginning, but the failure rate drops rapidly. The causes of failure in this stage are mostly due to defects in design, raw materials, and manufacturing processes.

[0106] 2) Steady-state period (random failure period): During this stage, the product failure rate is low and stable, generally considered to occur at a constant failure rate, which is expressed as the steady-state failure rate. This period represents the product's optimal usability phase. Failures are mainly caused by factors such as quality defects, material weaknesses, environmental factors, and improper use. Research on product lifespan focuses on this period, hence it is also called the "useful lifespan." During the steady-state period, the failure rate follows an exponential distribution over time.

[0107] 3) Wear-out period: During this stage, the failure rate increases rapidly. The product failure rate rises with the increase of operating time. The main causes of failure in this stage are wear, fatigue, aging, and depletion.

[0108] This embodiment, through extensive statistical analysis of data, found that the probability density of computer product failures conforms to an exponential distribution, meaning its lifespan curve corresponds to the bottom of the bathtub curve. The failure probability density function is:

[0109] λ (4)

[0110] Wherein, the failure probability density f(t) represents the probability of product failure per unit time at time t. λ is the product failure rate, and the relationship between the failure rate λ and the product lifespan is:

[0111] MTBF= (5)

[0112] MTBF (Mean Time Between Failures) represents the product's lifespan, which is the reciprocal of the failure rate. Products like computers, which follow an exponential distribution, have no memory of their lifespan. These products tend to have short lifespans after a certain period of time. The remaining lifespan after the initial working period still follows the same distribution as the original working lifespan, and is independent of time t. This means that how long a computer product has been in operation in the past has no impact on its present and future lifespan distribution.

[0113] Based on formula (5), the basic lifespan formula of the product can be derived as follows:

[0114] Basic lifespan = (6)

[0115] To determine the basic lifespan of the product in this embodiment, the basic failure rate of the product must first be obtained. Since the product is composed of several components, the product's failure rate is the sum of the failure rates of all the components that make up the product, as shown in formula (3) above. Here, the general failure rate of the component under specified conditions is... It can be obtained from the supplier or through life-specific testing experiments. The quality coefficient of the part. The design impact factor can be determined by the company's procurement strategy, because parts obtained from different markets have different reliability characteristics and different failure rates. The design impact factor will be discussed in detail below.

[0116] In addition to research and development, the creation of a new product also involves two crucial stages: manufacturing and quality management. Therefore, a company's manufacturing capabilities and quality management level directly affect the product's basic lifespan; together, they constitute the product's genetic lifespan coefficient, as shown in the following formula:

[0117] Gene lifespan coefficient = manufacturing capacity × quality management level (7)

[0118] In other words, the genetic lifespan coefficient of a product is determined by multiplying the product's manufacturing capabilities and quality management level by the product's manufacturing capacity and genetic lifespan coefficient. The product's manufacturing capabilities can include: the selection of solder paste, chip soldering processes, automation levels, and worker skill levels; quality management is integral to the product's lifespan, therefore, the company's quality management level has a crucial impact on product lifespan.

[0119] In this embodiment of the disclosure, before determining the basic lifespan of the product according to the product basic failure rate formula, the method further includes: determining the design influence coefficient of each component by multiplying the component selection failure rate coefficient, component application failure rate coefficient, component temperature stress failure rate coefficient, and electrical stress failure rate coefficient of each component; and determining the quality coefficient of each component by using the relationship table between the component procurement strategy and the failure rate coefficient of each component.

[0120] Specifically, the design influence coefficient in this embodiment This is mainly reflected in the selection of parts, the use of parts, and the application of electrical stress coefficient. Partially, it can be expressed using the following formula.

[0121] (8)

[0122] in, Select a failure rate coefficient for each component; The application failure rate coefficient for each component; The temperature stress failure rate coefficient for each component; The electrical stress failure rate coefficient for each component.

[0123] Because companies prefer to source components directly from original manufacturers, the reality is that various reasons often lead to a shortage of parts. In recent years, electronic manufacturers have faced shortages of passive components, transistors, and ICs, making component shortages a common occurrence. On the one hand, Chinese companies have adopted flexible and varied procurement strategies to minimize the impact. On the other hand, these procurement strategies inevitably affect product lifespan. Therefore, a company's procurement strategy is crucial to the component failure rate. Common procurement strategies for electronic components by Chinese companies include: direct procurement from original manufacturers, procurement from distributors, procurement from the spot market, and recycling from the second-hand market.

[0124] The quality level of components varies under different procurement strategies; therefore, the impact of procurement strategies on product lifespan is referred to as the component quality coefficient. Table 1 below shows the component quality coefficients under different procurement strategies. This embodiment uses a multilayer ceramic capacitor (MLCC) as an example. The quality coefficient of each component can be determined by using the relationship table between the component procurement strategy and the failure rate coefficient. It should be noted that the classifications and failure rate coefficients in Table 1 of this embodiment are merely examples and can be adapted to different types of electronic products; therefore, they are not limited to these specific examples.

[0125] Table 1. Relationship between Failure Rate Coefficient and Procurement Strategy

[0126]

[0127] Before determining the design influence coefficient of each component by multiplying the component selection failure rate coefficient, component application failure rate coefficient, component temperature stress failure rate coefficient, and electrical stress failure rate coefficient, this embodiment further includes: determining the component selection failure rate coefficient based on the relationship table between the component selection failure rate coefficient and component size specifications; determining the component application failure rate coefficient based on the relationship table between the component application failure rate coefficient and component placement position; and determining the component temperature stress failure rate coefficient based on the calculation formula for the component temperature stress failure rate coefficient, wherein the calculation formula for the component temperature stress failure rate coefficient is:

[0128] (9)

[0129] in, For reference temperature, take room temperature 25°C, and Kelvin absolute temperature is calculated as °K = 273 + 25; The actual operating temperature of the part is defined as °C + 273. The activation energy is given by k, which is the Boltzmann constant, 8.2 × 10⁻⁶. -5 ;

[0130] The electrical stress failure rate coefficient of the component is determined according to the calculation formula of the electrical stress failure rate coefficient of the component, wherein the calculation formula of the electrical stress failure rate coefficient of the component is as follows:

[0131] (10)

[0132] in, Percentage of applied stress, is the empirical percentage of the rated stress, and m is the fitting parameter.

[0133] Specifically, this embodiment will still use multilayer ceramic capacitors (MLCCs) as an example. Through lifespan testing and failure data analysis, the general failure rate of multilayer ceramic capacitors is found to be 0.116 fits. Their failures are mainly divided into torsional fracture failure and thermal shock failure. Torsional fracture failure is related to mechanical stress, while thermal shock failure is related to electrical stress and temperature stress. Torsional fracture failure mainly manifests as follows: under mechanical force, the PCB board bends and deforms, and the range of motion of the multilayer ceramic capacitor is limited by its terminals and solder joints, making it prone to fracture. Therefore, torsional fracture failure caused by mechanical stress is related to the selection and application of components.

[0134] Specifically, the failure rate coefficient for multilayer ceramic capacitors is mainly related to their size. That is, under the same stress conditions, larger multilayer ceramic capacitors have a higher probability of torsional fracture failure. Therefore, based on the relationship between the component selection failure rate coefficient and component size specifications, the component selection failure rate coefficient is determined, as shown in Table 2. It should be noted that the component specification classifications and failure rate coefficients in Table 2 of this embodiment are merely examples and can be adapted to different types of electronic products; therefore, they are not limited thereto.

[0135] Table 2 Relationship between Failure Rate Coefficient and Size

[0136]

[0137] Specifically, the failure rate coefficient resulting from the use of components is mainly related to the placement of multilayer ceramic capacitors. For example, if the stress point on the PCB board is exactly perpendicular to the long side of the capacitor, the capacitor is more prone to torsion and breakage when the PCB board bends and deforms. Therefore, the relationship between the failure rate coefficient and the capacitor placement position in this embodiment is shown in Table 3. It should be noted that the component placement positions and failure rate coefficients in Table 3 of this embodiment are merely examples and can be adapted to different types of electronic products; therefore, they are not limited thereto.

[0138] Table 3 Relationship between Failure Rate Coefficient and Part Application

[0139]

[0140] The main cause of thermal shock failure in multilayer ceramic capacitors is that the components are subjected to excessively high temperatures or that the temperature rises and falls too rapidly. The related factors are electrical stress and temperature stress. Specifically, when electrical stress and temperature stress are overloaded, the temperature of the capacitor will rise sharply. Therefore, the effect of temperature stress on the capacitor failure rate is expressed by formula (9), and the effect of electrical stress failure rate coefficient is expressed by formula (10).

[0141] This embodiment considers the impact of a company's R&D capabilities on product lifespan. Based on the failure modes of commonly used computer components, it not only retains the impact of temperature and electrical stress on product failures but also fully considers the impact of mechanical stress caused by component selection and application on the product failure rate. Furthermore, this embodiment also reserves space for the impact of other design-related stresses on the product failure rate.

[0142] In this embodiment of the disclosure, before determining the genetic lifetime coefficient of the product by multiplying the production capacity and quality management level of the enterprise where the product is located by the genetic lifetime coefficient, the method further includes: determining the solder paste type factor of the product based on a relationship table between the solder paste type and the failure rate coefficient of the product; determining the chip soldering process factor of the product based on a relationship table between the chip soldering process and the failure rate coefficient of the product; determining the automation level factor of the product based on a relationship table between the job type and the failure rate coefficient of the product; determining the worker skill level factor of the product based on a relationship table between the worker skill level and the failure rate coefficient of the product; determining the production capacity of the enterprise where the product is located by multiplying the solder paste type factor, chip soldering process factor, automation level factor, worker skill level factor, and production capacity of the product; and determining the quality management level of the enterprise where the product is located by using a relationship table between the quality management level and the failure rate coefficient of the product.

[0143] Specifically, this embodiment still uses multilayer ceramic capacitors (MLCCs) as an example. Common solder pastes include low-temperature solder paste, medium-temperature solder paste, and high-temperature solder paste. The impact of solder paste selection on product failure rate is shown in Table 4 below. It should be noted that the solder paste types and failure rate coefficients in Table 4 of this embodiment are merely examples and can be adapted to different types of electronic products; therefore, they are not limited.

[0144] Table 4. Relationship between Failure Rate Coefficient and Solder Paste Type

[0145]

[0146] This embodiment takes into account the impact of enterprise manufacturing capabilities on product lifespan, making the model highly forward-looking. For example, it considers the medium-low temperature solder paste bonding process, a newly introduced and promising technology in the electronics industry. It collaborates with other companies within the Medium-Low Temperature Solder Paste Bonding Technology Research and Application Alliance to conduct in-depth research on the relationship between solder paste bonding technology and product failure rates, integrating these relationships into the lifespan model. Furthermore, the model also considers future large-scale applications of post-chip soldering processes and automated manufacturing in terms of enterprise manufacturing capabilities.

[0147] Due to frequent and tight chip supply, more and more companies are adopting post-chip soldering processes to effectively utilize production capacity and avoid waste. Post-chip soldering refers to a process where, when chips are in short supply, companies assemble components other than the chips first, and then assemble the chips themselves when they arrive. However, this process undoubtedly impacts the failure rate. Taking computer products as an example, the impact of chip soldering processes on product failure rates is shown in Table 5 below. It should be noted that the chip soldering process types and failure rate coefficients in Table 5 of this embodiment are merely examples and can be adapted to different types of electronic products; therefore, they are not limited to these examples.

[0148] Table 5 Relationship between Failure Rate Coefficient and Chip Soldering Process

[0149]

[0150] Since the equipment configurations of different manufacturers may vary, the failure rate of products produced by fully automated equipment is certainly lower than that produced by manual labor. Therefore, this embodiment sets up a relationship between automation level and failure rate coefficient for reference. It should be noted that the operation type and failure rate coefficient in Table 6 of this embodiment are merely examples and can be adapted to different types of electronic products; therefore, they are not limited thereto.

[0151] Table 6. Relationship between Failure Rate Coefficient and Automation Level

[0152]

[0153] Similarly, for products requiring manual or semi-automated operation, this embodiment also needs to consider the skill level of the workers, as different skill levels will affect the failure rate coefficient. Worker skill levels are categorized as skilled workers, semi-skilled workers, and new workers. The impact of worker skill level on product failure rate is shown in Table 7 below. It should be noted that the operation types and failure rate coefficients in Table 7 of this embodiment are merely examples and can be adapted to different types of electronic products; therefore, they are not limited to these categories.

[0154] Table 7 Relationship between Failure Rate Coefficient and Worker Skill Level

[0155]

[0156] In addition, a company's quality management level also affects the product failure rate coefficient. Generally, based on a company's quality management level and its corresponding quality performance level, the industry typically classifies a company's quality management level into four levels: inspection level, quality assurance level, prevention level, and perfect level. For example, the relationship between a company's quality management level and product failure rate is shown in Table 8 below. It should be noted that the quality management level levels and failure rate coefficients in Table 8 of this embodiment are merely examples and can be adapted to different types of electronic products; therefore, they are not limited to these levels.

[0157] Table 8. Relationship between Failure Rate Coefficient and Quality Management Level

[0158]

[0159] Therefore, after obtaining the above-mentioned factors, this embodiment can determine the production capacity of the enterprise where the product is located based on the product's solder paste type, chip welding process, automation level, worker skill level, and production capacity; and determine the quality management level of the enterprise where the product is located through the relationship table between the product's quality management level and failure rate coefficient.

[0160] The lifespan prediction model provided in this embodiment comprehensively considers the factors affecting the lifespan of computer products and is consistent with the Chinese context. Factors such as enterprise procurement strategies, manufacturing capabilities, and quality management levels are not included in other models. Moreover, these factors affecting product lifespan are highly relevant to the actual situation of Chinese enterprises. For example, regarding procurement strategies, in recent years, electronic manufacturers have encountered shortages of passive components, transistors, and ICs, making electronic component shortages a common occurrence. Chinese companies have adopted flexible and adaptable procurement strategies to minimize the impact, while actively pursuing domestic substitution solutions for electronic components, especially core components. These procurement strategies will inevitably affect the lifespan of the final product.

[0161] In this embodiment of the disclosure, determining the environmental lifespan coefficient of a product includes: determining the environmental lifespan coefficient of the product based on a relationship table between the product's working environment and the failure rate coefficient.

[0162] Specifically, the environmental conditions of a product mainly refer to the environmental conditions encountered by the product during its performance or by the user during product use. Environmental impacts introduced during transportation, storage, and manufacturing processes also deserve special attention. Among these, temperature is the most important environmental factor; other environmental factors besides temperature are generally related to the product's intended use. According to user surveys, the environmental impact factors of computer products can be categorized according to the usage environment as follows: good ground conditions, generally fixed ground, and fixed ground in harsh conditions; mobile use and fixed use; controllable environment and uncontrollable environment.

[0163] Specifically, the lifespan of the same product varies depending on the temperature and environmental conditions under which it is operated or used. The failure rate in a favorable environment can differ by 30 to 50 times compared to that in a harsh environment. For example, the lifespan of the same computer product used in an internet cafe is only one-third of that in a home environment, and only one-fifth of that in a business office environment. The same applies to other electronic products, although the difference may lie in the magnitude of the lifespan variation.

[0164] Therefore, in predicting product lifespan, this embodiment requires accurate knowledge of the operating temperature and environment of the product. The relationship between the failure rate coefficient and the operating environment is shown in Table 9 below. It should be noted that the environment and failure rate coefficient used in Table 9 of this embodiment are merely examples and can be adapted to different types of electronic products; therefore, they are not limited thereto.

[0165] Table 9. Relationship between Failure Rate Coefficient and Usage Environment

[0166]

[0167] In this embodiment of the disclosure, determining the product's lifespan growth factor includes: determining the product's lifespan growth factor based on a relationship table between the product's development batches and the failure rate factor.

[0168] Specifically, the lifespan growth factor is located at the top of the product lifespan pyramid model, encompassing the growth of all lifespan-influencing factors below it through long-term experience accumulation.

[0169] This embodiment leverages a wealth of design experience, product and component failure data, maintenance data, and customer feedback accumulated in the early stages. Based on this data, big data analysis was conducted to summarize the patterns of product lifespan growth, and these patterns were applied to a product lifespan model. For example, the relationship between the lifespan growth coefficient and the product failure rate is shown in Table 10. It should be noted that the product development generation and failure rate coefficient in Table 10 of this embodiment are merely examples and can be adapted to different types of electronic products; therefore, they are not limited to these models.

[0170] Table 10 Relationship between lifespan growth coefficient and product failure rate

[0171]

[0172] This embodiment of the lifespan prediction model creatively introduces the concept of a lifespan growth factor, drawing upon a wealth of design experience, product and component failure data, after-sales maintenance data, and customer feedback. Based on this data, big data analysis is conducted to summarize the patterns of product lifespan growth, and these patterns are applied to the product lifespan model, increasing the accuracy of the lifespan prediction.

[0173] In addition to the main factors mentioned above, this embodiment can also add other factors to the lifetime prediction model for training, such as confidence level, series and parallel connection, redundancy design, etc., which will not be elaborated in this embodiment.

[0174] This embodiment summarizes a comprehensive overview of various factors affecting product lifespan, including R&D capabilities, procurement strategies, manufacturing levels, quality management levels, external environment, and lifespan growth coefficients. The relationships between these factors can be determined using the formulas provided in this embodiment to train a lifespan prediction model, thereby obtaining a mature lifespan prediction model to predict the predicted lifespan values ​​of various products. In addition, it offers at least the following advantages:

[0175] (1) The life prediction model provided in this embodiment can provide guidance for the design of new products in the R&D stage of various types of electronic products. When the new product enters the mass production stage, it can predict the life of the product and then carry out brand promotion and formulate appropriate maintenance strategies.

[0176] (2) The lifespan prediction model provided in this embodiment also has the characteristics of strong versatility. It is applicable to the lifespan prediction and research of all computer products, including desktop and laptop computers, server computers, and tablet computers. It can also be applied to the lifespan research and prediction of other non-computer electronic products and equipment. While breaking through foreign technology blockade, it fills the gap in lifespan prediction methods in the domestic commercial electronic product field. In addition, through big data analysis of market research, R&D, testing, maintenance, and after-sales service, the model can be continuously improved to make it more and more reliable.

[0177] (3) The model provided in this embodiment has high reliability. Having been tested with a cumulative shipment of 60 million computers and non-computer electronic products across 25 categories, this model demonstrates higher accuracy compared to commonly used European and American lifespan prediction methods and models currently on the market. Specifically, the data obtained using this model shows an improvement of over 20% in accuracy.

[0178] Example 2

[0179] Figure 4 This is a schematic diagram of a product life prediction device provided in an embodiment of this disclosure. The device specifically includes:

[0180] The parameter acquisition module 410 is used to acquire the ideal parameters of each part in the product.

[0181] The life prediction module 420 is used to input the ideal parameters of each part in the product into the life prediction model to obtain the predicted life value. The life prediction model is a model trained based on the product of the product's genetic life, environmental life coefficient and life growth coefficient.

[0182] The parameter acquisition module is used to obtain the ideal parameters of each part within the product.

[0183] The life prediction module is used to input the ideal parameters of each part in the product into the life prediction model to obtain the predicted life value. The life prediction model is a model trained based on the product of the product's genetic life, environmental life coefficient and life growth coefficient.

[0184] In one embodiment, before acquiring the ideal parameters of each part within the product, the device further includes a model training module, specifically used for: acquiring the product's base lifespan and genetic lifespan coefficient; and determining the product's genetic lifespan based on the relationship between the product's base lifespan, genetic lifespan coefficient, and genetic lifespan, wherein the relationship is:

[0185] .

[0186] In one embodiment, the model training module is further configured to: obtain the product's base lifespan and genetic lifespan coefficient, including: determining the product's base lifespan according to the product's base failure rate formula, wherein the product's base failure rate formula is:

[0187]

[0188] in, For the first of the products The general failure rate of a type of component under specified conditions. For the first of the products The design influence coefficient of this type of part For the first of the products The quality coefficient of the type of part For the first of the products The number of parts;

[0189] The genetic lifespan coefficient of the product is determined by multiplying the production capacity and quality management level of the enterprise that produces the product by the genetic lifespan coefficient.

[0190] In one possible implementation, the model training module is further configured to: before determining the basic lifespan of the product based on the product's basic failure rate formula, further include: determining the design influence coefficient of each component by multiplying the component selection failure rate coefficient, component application failure rate coefficient, component temperature stress failure rate coefficient, and electrical stress failure rate coefficient of each component; and determining the quality coefficient of each component by using a relationship table between the component procurement strategy and the failure rate coefficient of each component.

[0191] In one embodiment, the model training module is further configured to: determine the part selection failure rate coefficient based on a table showing the relationship between the part selection failure rate coefficient and the part size specifications; determine the part application failure rate coefficient based on a table showing the relationship between the part application failure rate coefficient and the part placement position; and determine the part temperature stress failure rate coefficient based on a formula for calculating the part temperature stress failure rate coefficient, wherein the formula for calculating the part temperature stress failure rate coefficient is:

[0192] in, For reference temperature, The actual operating temperature of the component. The activation energy is given by k, where k is the Boltzmann constant.

[0193] The electrical stress failure rate coefficient of the component is determined according to the calculation formula of the electrical stress failure rate coefficient of the component, wherein the calculation formula of the electrical stress failure rate coefficient of the component is as follows:

[0194]

[0195] Where P1 is the percentage of applied stress, P0 is the empirical percentage of rated stress, and m is the fitting parameter.

[0196] In one possible implementation, the model training module is further configured to: before determining the product's genetic lifetime coefficient by multiplying the product's manufacturing capacity and quality management level by the enterprise where the product is located and the genetic lifetime coefficient, determine the solder paste type factor of the product based on a relationship table between the product's solder paste type and failure rate coefficient; determine the chip soldering process factor of the product based on a relationship table between the product's chip soldering process and failure rate coefficient; determine the automation level factor of the product based on a relationship table between the product's job type and failure rate coefficient; determine the worker skill level factor of the product based on a relationship table between the product's worker skill level and failure rate coefficient; determine the manufacturing capacity of the enterprise where the product is located by multiplying the product's solder paste type factor, chip soldering process factor, automation level factor, worker skill level factor, and manufacturing capacity; and determine the quality management level of the enterprise where the product is located by using a relationship table between the product's quality management level and failure rate coefficient.

[0197] In one embodiment, the model training module is further configured to: determine the environmental lifespan coefficient of the product based on a relationship table between the product's working environment and the failure rate coefficient.

[0198] In one embodiment, the model training module is further configured to: determine the product's lifespan growth coefficient based on a table showing the relationship between the product's development batches and failure rate coefficients.

[0199] According to embodiments of this disclosure, this disclosure also provides an electronic device and a readable storage medium.

[0200] Figure 5 A schematic block diagram of an example electronic device 500 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.

[0201] like Figure 5 As shown, device 500 includes a computing unit 501, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 502 or a computer program loaded from storage unit 508 into random access memory (RAM) 503. RAM 503 may also store various programs and data required for the operation of device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0202] Multiple components in device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0203] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as a product lifetime prediction method. For example, in some embodiments, a product lifetime prediction method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of a product lifetime prediction method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform a product lifetime prediction method by any other suitable means (e.g., by means of firmware).

[0204] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments 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 transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0205] 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.

[0206] 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, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0207] 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).

[0208] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user 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 of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0209] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0210] It should be understood that the various forms of processes shown above can be used to reorder, 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.

[0211] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means two or more, unless otherwise explicitly specified.

[0212] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A product lifespan prediction method, characterized in that, The method includes: Obtain the product's base lifespan and genetic lifespan coefficient; determine the product's genetic lifespan based on the relationship between the product's base lifespan, genetic lifespan coefficient, and genetic lifespan. Wherein, gene lifetime is the product of base lifetime and gene lifetime coefficient; the base lifetime of the product is the reciprocal of the product's base failure rate. The product base failure rate is the sum of the failure rates of all parts in the product. The failure rate of each part is the product of the following four factors: the general failure rate of the part under specified conditions, the design influence coefficient of the part, the quality coefficient of the part, and the quantity of the part. The genetic lifespan coefficient of the product is the product of the production capacity and quality management level of the enterprise that produces the product. Among them, the design influence coefficient of a part is the product of the part selection failure rate coefficient, the part application failure rate coefficient, the part temperature stress failure rate coefficient, and the part electrical stress failure rate coefficient. The quality coefficient of a part is determined by the relationship table between the part procurement strategy and the failure rate coefficient of each part. Obtain the ideal parameters for each component within the product; The ideal parameters of each part in the product are input into the life prediction model to obtain the predicted life value. The life prediction model is a model trained based on the product of the product's genetic life, environmental life coefficient, and life growth coefficient.

2. The method according to claim 1, wherein, Before determining the design influence coefficient of each component by multiplying the component selection failure rate coefficient, component application failure rate coefficient, component temperature stress failure rate coefficient, and component electrical stress failure rate coefficient, the following steps are also included: The failure rate coefficient for part selection is determined based on the relationship table between the part selection failure rate coefficient and the part size specifications; The application failure rate coefficient of the part is determined based on the relationship table between the application failure rate coefficient of the part and the placement position of the part. The temperature stress failure rate coefficient of the part is determined according to the calculation formula of the temperature stress failure rate coefficient of the part, wherein the calculation formula of the temperature stress failure rate coefficient of the part is: in, For reference temperature, The actual operating temperature of the component. The activation energy is given by k, where k is the Boltzmann constant. The electrical stress failure rate coefficient of the component is determined according to the calculation formula, wherein the calculation formula for the electrical stress failure rate coefficient of the component is as follows: Where P1 is the percentage of applied stress, P0 is the empirical percentage of rated stress, and m is the fitting parameter.

3. The method according to claim 2, characterized in that, Before determining the genetic lifespan coefficient of the product by multiplying the manufacturing capacity and quality management level of the company where the product is manufactured, the process also includes: Based on the relationship table between the solder paste type and the failure rate coefficient of the product, the solder paste type factor of the product is determined; Based on the relationship table between the chip welding process and the failure rate coefficient of the product, determine the chip welding process factors of the product; Based on the relationship table between the product's operation type and failure rate coefficient, determine the automation level factors of the product; Based on the relationship table between the worker skill level and the failure rate coefficient of the product, the worker skill level factor of the product is determined; The production capacity of the enterprise producing the product is determined by multiplying the factors of solder paste type, chip soldering process, automation level, and worker skill level. The quality management level of the company producing the product is determined by using the relationship table between the product's quality management level and failure rate coefficient.

4. The method according to claim 3, characterized in that, Also includes: Based on the relationship table between the product's working environment and failure rate coefficient, the environmental life coefficient of the product is determined.

5. The method according to claim 4, characterized in that, Also includes: Based on the relationship table between the development batches and failure rate coefficients of the product, the lifespan growth coefficient of the product is determined.

6. A product life prediction device, characterized in that, The device includes: The model training module is used to obtain the product's base lifespan and genetic lifespan coefficient; and to determine the product's genetic lifespan based on the relationship between the product's base lifespan, genetic lifespan coefficient, and genetic lifespan. Wherein, gene lifetime is the product of base lifetime and gene lifetime coefficient; the base lifetime of the product is the reciprocal of the product's base failure rate. The product base failure rate is the sum of the failure rates of all parts in the product. The failure rate of each part is the product of the following four factors: the general failure rate of the part under specified conditions, the design influence coefficient of the part, the quality coefficient of the part, and the quantity of the part. The genetic lifespan coefficient of the product is the product of the production capacity and quality management level of the enterprise that produces the product. Among them, the design influence coefficient of a part is the product of the part selection failure rate coefficient, the part application failure rate coefficient, the part temperature stress failure rate coefficient, and the part electrical stress failure rate coefficient. The quality coefficient of a part is determined by the relationship table between the part procurement strategy and the failure rate coefficient of each part. The parameter acquisition module is used to obtain the ideal parameters of each part within the product. The life prediction module is used to input the ideal parameters of each part in the product into the life prediction model to obtain the predicted life value. The life prediction model is a model trained based on the product of the product's genetic life, environmental life coefficient and life growth coefficient.

7. The apparatus according to claim 6, characterized in that, The model training module is further used for: Before determining the design influence coefficient of each component by multiplying its selection failure rate coefficient, application failure rate coefficient, temperature stress failure rate coefficient, and electrical stress failure rate coefficient, the component selection failure rate coefficient is determined based on the relationship table between the component selection failure rate coefficient and component size specifications; the component application failure rate coefficient is determined based on the relationship table between the component application failure rate coefficient and component placement position; and the component temperature stress failure rate coefficient is determined based on the calculation formula for the component temperature stress failure rate coefficient, wherein the calculation formula for the component temperature stress failure rate coefficient is: in, For reference temperature, The actual operating temperature of the component. The activation energy is given by k, where k is the Boltzmann constant. The electrical stress failure rate coefficient of the component is determined according to the calculation formula, wherein the calculation formula for the electrical stress failure rate coefficient of the component is as follows: Where P1 is the percentage of applied stress, P0 is the empirical percentage of rated stress, and m is the fitting parameter.

8. The apparatus according to claim 7, characterized in that, The model training module is further used for: Before determining the genetic lifespan coefficient of the product by multiplying the production capacity and quality management level of the enterprise where the product is produced, the solder paste type factor of the product is determined according to the relationship table between the solder paste type and the failure rate coefficient of the product. Based on the relationship table between the chip welding process and the failure rate coefficient of the product, determine the chip welding process factors of the product; Based on the relationship table between the product's operation type and failure rate coefficient, determine the automation level factors of the product; Based on the relationship table between the worker skill level and the failure rate coefficient of the product, the worker skill level factor of the product is determined; The production capacity of the enterprise producing the product is determined by multiplying the factors of solder paste type, chip soldering process, automation level, and worker skill level. The quality management level of the company producing the product is determined by using the relationship table between the product's quality management level and failure rate coefficient.

9. The apparatus according to claim 8, wherein the model training module is further configured to: Based on the relationship table between the product's working environment and failure rate coefficient, the environmental life coefficient of the product is determined.

10. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, 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 of any one of claims 1-5.

11. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-5.

Images