A remaining life prediction method, computer device and readable storage medium

Abstract

The application discloses a residual life prediction method, computer equipment and a readable storage medium, relates to the life prediction technical field, and is used for predicting the residual life of an electric drive system and comprises the following steps: a simulation model of virtual accumulated fatigue damage under a probability distribution is constructed; a parameter set is calculated and verified; fatigue data is acquired; parameters of the simulation model under the probability distribution and BIC values of each part are acquired, and the simulation model with the minimum BIC value is the optimal model of the part; the reliability function of each part is calculated; the reliability of the transmission system is calculated according to the reliability function of each part; and the residual available life of the electric drive system is calculated according to the reliability. The application enables relatively accurate life calculation of damage data of various parts.

Description

Technical Field

[0001] This invention relates to the field of lifetime prediction technology, specifically to a method for predicting remaining lifetime, a computer device, and a readable storage medium. Background Technology

[0002] During vehicle operation, the service environment of mechanical components is complex, leading to frequent damage and failure. Therefore, accurately assessing the reliability and lifespan of mechanical systems is not only crucial for effectively preventing losses and injuries caused by mechanical failures, but also essential for developing reasonable maintenance strategies. Corrosion, wear, and fatigue are the main failure modes of mechanical systems, with fatigue damage being particularly prominent. For mechanical components subjected to alternating cyclic loads over long periods, fatigue fracture is the most prevalent failure mode. Existing technologies such as variable amplitude loading history effects and Miner's rule do not consider the material's springback properties when calculating cumulative fatigue damage. This alters the material's state before fatigue damage occurs, causing the cumulative damage threshold to be earlier than the actual situation, thus incorrectly estimating the failure life of components. Summary of the Invention

[0003] This invention aims to address, to a certain extent, one of the technical problems in related technologies. To this end, this invention provides a method for predicting remaining lifespan, a computer device, and a readable storage medium, enabling relatively accurate lifespan calculations based on damage data of various components.

[0004] To achieve the above objectives, the present invention adopts the following technical solution:

[0005] A method for predicting the remaining lifetime of an electric drive system includes the following steps:

[0006] Construct a simulation model of virtual cumulative fatigue damage under a probability distribution;

[0007] Calculate and verify the parameter set of the simulation model under the probability distribution;

[0008] Obtain fatigue data;

[0009] Based on the acquired fatigue data, the parameters of the simulation model of each part in the electric drive system under the probability distribution and the BIC value of each part are obtained. Among them, for each part, the simulation model with the smallest BIC value is the optimal model of that part.

[0010] The reliability function of each component in the electric drive system in the optimal model is calculated based on the acquired fatigue data.

[0011] The reliability of the transmission system is calculated based on the reliability function of each component in the optimal model of the electric drive system.

[0012] The remaining usable life of the electric drive system is calculated based on the reliability of the transmission system.

[0013] Optionally, constructing a simulation model of virtual cumulative fatigue damage under a probability distribution includes the following steps:

[0014] The cumulative probability density function of the damage value of the nth injury is calculated using the following formula:

[0015]

[0016] V n =V n-1 +qX n ,q∈[0,1]

[0017] Where F(x) is the damage value; V n It is virtual cumulative fatigue damage, X n denoted as , where is the magnitude of the damage, and q is the rebound coefficient.

[0018] Substituting the cumulative probability density function into the probability distribution yields the cumulative damage density function under the probability distribution, which serves as a simulation model for virtual cumulative fatigue damage.

[0019] Optionally, calculating and validating the parameters of the simulation model for each scenario includes the following steps:

[0020] Obtain the log-likelihood function of the simulation model of virtual cumulative fatigue damage under a probability distribution;

[0021] The optim function is used to calculate the maximum likelihood function or the log-likelihood function of the simulation model under the probability distribution. The calculation result is the set of calculation parameters of the simulation model under the probability distribution.

[0022] The parameter set of the simulation model under the constructed probability distribution is used to verify the calculation parameter set. If the verification result is unqualified, the maximum likelihood function or the log-likelihood function of the simulation model under the probability distribution is recalculated until the verification result is qualified.

[0023] Optionally, obtaining fatigue data includes the following steps:

[0024] Construct damage models for each component in the electric drive system;

[0025] Data on user usage of the electric drive system is acquired and divided into several segments of equal time duration.

[0026] The fatigue data is calculated by using a damage model to calculate single-instance damage data and cumulative damage data.

[0027] Optionally, fatigue data can be normalized before obtaining the parameters of the simulation models of each component in the electric drive system under various scenarios.

[0028] Optionally, the BIC value of each part can be calculated using the following formula:

[0029]

[0030]

[0031] in, It is the maximum value of the likelihood function of the simulation model, where x is the fatigue data. M is the parameter set, n is the number of fatigue data points, and k is the number of parameters in the simulation model.

[0032] Optionally, the reliability function can be calculated using the following formula:

[0033] R(t i |V i-1 =v i-1 )=1-F(t i |V i-1 =v i-1 )

[0034] Wherein, R(t) i |V i-1 =v i-1 F(t) is the reliability function. i |V i-1 =v i-1 () is the optimal model.

[0035] Optionally, the reliability of the transmission system is:

[0036]

[0037] in, For the reliability of the reducer gears; For the reliability of the bearing; The reliability of the shaft.

[0038] Optional calculations of the remaining usable life of the electric drive system based on the reliability of the transmission system include the following steps:

[0039] Set a reliability threshold;

[0040] The number of damages is calculated using a reliability threshold.

[0041] The remaining number of damage cycles for the system is calculated using the following formula:

[0042]

[0043] Among them, i remaining The remaining number of damage cycles for the system. For, i dataLength This represents the theoretical number of damages to the system.

[0044] The remaining usable lifespan of the electric drive system is calculated using the following formula:

[0045] URL=f sampling *i remaining

[0046] Where URL represents the remaining usable lifespan of the electric drive system, f sampling The sampling rate.

[0047] The technical solution provided by this invention is the first to consider the influence of material springback coefficient on the amplitude of fatigue damage in components, and proposes a virtual cumulative fatigue damage model. This model assumes that the cumulative fatigue damage of a component throughout its entire lifespan will be in a dynamically changing state, accurately calculating the component's lifespan based on these specific changes. This invention fully considers that different components may have different optimal distributions of damage. It provides several statistical models under different probability distributions, and through simulation-verification-case analysis, ensures the accuracy and reliability of the lifespan calculation results.

[0048] Furthermore, the present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the remaining lifetime prediction method described in any of the above-mentioned embodiments.

[0049] In addition, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the remaining lifetime prediction method described in any one of the above claims.

[0050] These features and advantages of the present invention will be disclosed in detail in the following specific embodiments and accompanying drawings. The preferred embodiments or means of the present invention will be shown in detail in conjunction with the accompanying drawings, but are not intended to limit the technical solutions of the present invention. In addition, each of these features, elements and components appearing in the following text and drawings is a plurality of, and different symbols or numbers are used for convenience of representation, but all represent parts with the same or similar construction or function. Attached Figure Description

[0051] The present invention will be further described below with reference to the accompanying drawings:

[0052] Figure 1 This is a flowchart illustrating an embodiment of the present invention. Detailed Implementation

[0053] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described are intended to explain the present invention and should not be construed as limiting the invention.

[0054] The terms "an embodiment," "example," or "trademark" used in this specification refer to a particular feature, structure, or characteristic described in connection with the embodiment itself that may be included in at least one embodiment disclosed in this patent. The phrase "in an embodiment" appearing in various places throughout the specification does not necessarily refer to the same embodiment.

[0055] Example:

[0056] like Figure 1 As shown, this embodiment provides a remaining lifetime prediction method for predicting the remaining lifetime of an electric drive system, including the following steps:

[0057] Construct a simulation model of virtual cumulative fatigue damage under a probability distribution. In this step, if the component has a virtual cumulative fatigue damage V after the (n-1)th damage, n =v, then the damage amplitude of the nth injury is X. n Its distribution should conform to the following function:

[0058]

[0059] Where F(x) is the damage value, V n It is virtual cumulative fatigue damage, X n Let X be the amplitude of the damage, and q be the springback coefficient, specifically the springback coefficient of the component material. In this embodiment, the nth springback cannot eliminate the impact of the (n-1)th springback. The additional cumulative fatigue damage will affect X. n Reduced to q*X n Therefore, the springback coefficient q will affect the virtual cumulative fatigue damage value according to the following relationship:

[0060] V n =V n-1 +qX n

[0061] V n =q(X1+X2+...+X) n ),q∈[0,1]

[0062] The springback coefficient q is a random variable with a value between 0 and 1. When the springback coefficient q is 0, it indicates that the material fully springs back, and the single stress application causes no damage. When q is 1, it indicates that the material does not spring back at all. This embodiment introduces a springback coefficient into the single damage, thereby changing the fatigue damage probability density function and making the calculation more closely resemble the actual damage situation.

[0063] Therefore, after the (n-1)th rebound, virtual cumulative fatigue damage V will be caused. n-1 =v. The magnitude of the nth injury is calculated using the following formula:

[0064]

[0065] In this step, the probability distribution includes, but is not limited to, the Weibull distribution, the log-normal distribution, and the gamma distribution. This embodiment will use three different probability distributions as examples for detailed explanation.

[0066] The cumulative probability density function of the damage value of the nth injury is calculated using the following formula:

[0067]

[0068] V n =V n-1 +qX n ,q∈[0,1]

[0069] Where F(x) is the damage value; V n It is virtual cumulative fatigue damage, X n denoted as , where is the magnitude of the damage, and q is the rebound coefficient.

[0070] Substituting the cumulative probability density function into the probability distribution yields the cumulative damage density function under the probability distribution. This cumulative damage density function under the probability distribution serves as a simulation model for virtual cumulative fatigue damage.

[0071] The simulation model for virtual cumulative fatigue damage under the Weibull distribution is as follows:

[0072] D i =D i-1 +X i

[0073] (X i +V i-1 )~rtweibull(shape,scale,V i-1 )

[0074]

[0075] The simulation model for virtual cumulative fatigue damage under a normal distribution is as follows:

[0076] D i =D i-1 +X i

[0077] (X i +V i-1 )~rtlognormal(mean,variance,V i-1 )

[0078]

[0079] The simulation model for virtual cumulative fatigue damage under gamma distribution is as follows:

[0080] D i =D i-1 +X i

[0081] (X i +V i-1 )~rtgamma(shape, scale, V i-1 )

[0082]

[0083] β and λ are the shape and scale parameters of the Weibull distribution, respectively; μ and σ are the mean and standard deviation of the normal distribution, respectively; α and σ are the shape and scale parameters of the gamma distribution, respectively; and v and V are the virtual lifetime added after i-1 maintenance and the cumulative virtual lifetime, respectively.

[0084] After completing the construction of the simulation model, the parameter set of the simulation model under the probability distribution is calculated and verified, including the following sub-steps:

[0085] The log-likelihood function of the simulation model of virtual cumulative fatigue damage under a probability distribution is obtained. In this embodiment, the log-likelihood function has a general technical meaning in this field. Specifically, the log-likelihood function of the simulation model under the Weibull distribution is:

[0086]

[0087] Log-likelihood function of the simulation model under log-normal distribution:

[0088]

[0089] Log-likelihood function of the simulation model under gamma distribution:

[0090]

[0091] The optim function is used to calculate the maximum likelihood function or the log-likelihood function of the simulation model under the probability distribution. The result is the set of calculation parameters for the simulation model under the probability distribution.

[0092]

[0093] Similarly, This refers to the set of calculation parameters.

[0094] The calculated parameter set is validated using the parameter set of the simulation model under the constructed probability distribution. If the validation result is unsatisfactory, the maximum likelihood function or the log-likelihood function of the simulation model under the probability distribution is recalculated until the validation result is satisfactory. This indicates that the parameter estimation algorithm adopted in this step can effectively and accurately estimate the parameters of the simulation model using a given set of data. Since the data obtained from each simulation is different, the parameter estimation results will also have slight deviations. Multiple simulations and parameter estimations can be performed iteratively, and the root mean square error (RMSE) of the obtained parameter set can be calculated using the following formula:

[0095]

[0096] Where θ i The parameter set θ is set for the i-th simulation. il This represents the parameter set obtained from a single parameter estimation, where M is the total number of simulations performed. The results after 10, 30, and 50 simulations and parameter estimations are as follows:

[0097]

[0098] As the number of simulations increases, the root mean square error of the parameter estimation gradually decreases and remains below 0.05, indicating that the parameter estimation results are accurate and can be used for real data analysis.

[0099] In other embodiments, the results of parameter verification can be determined by those skilled in the art based on the components and the scenarios in which the components are used.

[0100] After completing the model construction and parameter determination, fatigue data needs to be acquired. Acquiring fatigue data includes the following steps:

[0101] Damage models for each component in the electric drive system are constructed. Specifically, in this embodiment, damage models are mainly constructed for the motor shaft, reducer gears, and bearings. The constructed damage models are also common damage calculation models in this field, and will not be described in detail here.

[0102] Data on user usage of the electric drive system is acquired and divided into segments of equal time duration. This user usage data refers to the user's interaction with the electric drive system through driving behavior, including data such as vehicle speed, motor speed, motor torque, current, and voltage. For different components, the dominant failure load is selected. For example, the failure mode of the motor shaft is torsional fatigue, and the dominant failure load is torque. Therefore, the motor torque data is divided into segments of equal duration. Simulation models are used to calculate the damage of different components at each equal duration. In this embodiment, the equal duration is preferably 1 minute; other equal durations can be used in other embodiments.

[0103] The fatigue data is calculated by using a damage model to calculate single-instance damage data and cumulative damage data.

[0104] Then, based on the acquired fatigue data, the parameters of the simulation model for each component in the electric drive system under the probability distribution are obtained. Before obtaining the parameters of the simulation model for each component in the electric drive system under each scenario, the fatigue data is normalized. In this embodiment, a Min-Max normalization function within a certain range expands the original data to the interval (1, 10000000), and normalization is performed according to the following formula:

[0105]

[0106] Among them, D new For the normalized fatigue data, D original For obtaining fatigue data.

[0107] Then calculate the BIC value of each part according to the following formula:

[0108]

[0109]

[0110] in, It is the maximum value of the likelihood function of the simulation model, where x is the fatigue data. M is the parameter set, n is the number of fatigue data points, and k is the number of parameters in the simulation model. Repeat the aforementioned steps until the BIC values ​​of all components are obtained. For each component, the simulation model with the minimum BIC value is the optimal model for that component.

[0111] Based on the acquired fatigue data, the reliability function of each component in the electric drive system in the optimal model is calculated according to the following formula:

[0112] R(t i |V i-1 =v i-1 )=1-F(ti |V i-1 =v i-1 )

[0113] Wherein, R(t) i |V i-1 =v i-1 F(t) is the reliability function. i |V i-1 =v i-1 () is the optimal model.

[0114] Specifically, in this embodiment, the reliability function under the Weibull distribution is:

[0115]

[0116] The reliability function under the log-normal distribution is:

[0117]

[0118] The reliability function under the gamma distribution is:

[0119]

[0120] The reliability of the transmission system is calculated based on the reliability functions of each component in the optimal model. Assuming the electric drive system follows a series system reliability model, the system reliability can be expressed as:

[0121]

[0122] From the above, we can see that the reliability of the electric drive system is:

[0123]

[0124] in, For the reliability of the reducer gears; For the reliability of the bearing; The reliability of the shaft.

[0125] Finally, the remaining usable life of the electric drive system is calculated based on the reliability of the transmission system, including the following sub-steps:

[0126] A reliability threshold is set. The reliability threshold is determined by those skilled in the art based on the actual usage scenario of the electric drive system; in this embodiment, it is preferably 80%.

[0127] The number of damages is calculated using a reliability threshold.

[0128] The remaining number of damage cycles for the system is calculated using the following formula:

[0129]

[0130] Among them, i remaining The remaining number of damage cycles for the system. For, i dataLength This represents the theoretical number of damages to the system.

[0131] The remaining usable lifespan of the electric drive system is calculated using the following formula:

[0132] URL=f sampling *i remaining

[0133] Where URL represents the remaining usable lifespan of the electric drive system, f sampling The sampling rate.

[0134] The following example uses a simulation model based on the Weibull distribution to illustrate the prediction of remaining lifetime:

[0135] The parameter set is set as θ = {n = 40, β = 0.9, λ = 1.1, q = 0.8}. Here, n is the number of damage points to be simulated; β is the shape parameter; λ is the scale parameter; and q is the material elastic coefficient. The generated virtual cumulative damage and its amplitude are as follows:

[0136]

[0137]

[0138] The parameters were calculated and verified using the above data. The calculation results are shown in the table below:

[0139] Shape parameter β Scale parameter λ elastic coefficient q 1.011932 1.368924 0.8018174

[0140] By comparison, the result of the parameter calculation in this step is qualified.

[0141] Acquire data on user usage of the electric drive system and collect fatigue data for each component;

[0142] Based on a user's driving data over three months, the above process was used to calculate the mileage, motor shaft damage, reducer gear damage, bearing damage, etc., per minute. A total of 50,000 fatigue damage data segments were collected, as shown in the table below. The fatigue data at any given time point is obtained by summing the damage per minute, as shown in the figure.

[0143] Segment number mileage motor shaft Reducer Gear 1 Bearing L Bearing A 1 5.41E-02 5.29E-13 8.66E-08 1.23E-07 2.27E-07 2 3.00E-03 2.11E-14 1.62E-09 3.42E-09 1.10E-08 3 3.05E-02 1.51E-13 2.02E-08 3.41E-08 8.36E-08 4 2.60E-03 1.27E-14 2.93E-09 5.91E-09 1.80E-08 5 3.87E-03 4.24E-13 2.09E-08 2.71E-08 4.41E-08 6 7.90E-02 3.08E-12 5.53E-07 6.27E-07 8.35E-07 7 1.39E-02 1.74E-14 3.15E-09 6.43E-09 1.99E-08 8 4.08E-02 9.66E-13 4.36E-08 5.55E-08 9.18E-08 9 3.86E-02 2.13E-14 4.04E-09 7.96E-09 2.34E-08 10 3.82E-03 7.03E-15 5.34E-09 1.04E-08 3.00E-08 ··· ··· ··· ··· ··· ···

[0144] Thus, single-instance damage data d and fatigue data D of the reducer gears, bearings, and motor shaft were successfully obtained from the user's data on the electric drive system.

[0145] Calculate the BIC value for each component, as shown in the table below, and find the optimal model for each component:

[0146]

[0147]

[0148] Reliability of the electric drive system:

[0149]

[0150] In the series system mode, the system reliability function can be obtained:

[0151]

[0152] Finally, the remaining usable life (RUL) of the electric drive system is calculated.

[0153] When the number of damage cycles reaches 1.57 * 10⁶, the reliability of the electric drive system drops to 0.7994679, which is less than the set failure threshold of 80%. Therefore, the remaining number of damage cycles is:

[0154] i remaining =i threshold -i dataLength

[0155] i remaining =1.57*10 6 -5*10 4 =1.52*10 6

[0156] Remaining service life of the electric drive system:

[0157] URL=f sampling *i remaining

[0158] URL=10 6 Minutes = 25333.3 hours.

[0159] This embodiment is the first to consider the impact of material springback coefficient on the amplitude of fatigue damage in components, and proposes a virtual cumulative fatigue damage model. It assumes that the cumulative fatigue damage of a component over its entire lifespan will be in a dynamically changing state, accurately calculating the component's lifespan based on these specific changes. This embodiment fully considers that different components may have different optimal damage distributions. Several statistical models under different probability distributions are provided, and the accuracy and reliability of the lifespan calculation results are ensured through simulation, verification, and case study analysis.

[0160] Meanwhile, this embodiment also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the aforementioned remaining lifetime prediction method. The steps of the remaining lifetime prediction method here can be steps from the memory analysis methods of the various embodiments described above.

[0161] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. Accordingly, the computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can implement the methods of any of the above embodiments. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0162] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Those skilled in the art should understand that the present invention includes, but is not limited to, the contents described in the accompanying drawings and the specific embodiments above. Any modifications that do not depart from the functional and structural principles of the present invention will be included within the scope of the claims.

Claims

1. A method for predicting remaining lifetime of an electric drive system, characterized in that, The remaining lifetime prediction method includes the following steps: Construct a simulation model of virtual cumulative fatigue damage under a probability distribution; Calculate and verify the parameter set of the simulation model under the probability distribution; Obtain fatigue data; obtaining fatigue data includes the following steps: Construct damage models for each component in the electric drive system; Data on user usage of the electric drive system is acquired and divided into several segments of equal time duration. The fatigue data is calculated by using a damage model to calculate single damage data and cumulative damage data. Based on the acquired fatigue data, the parameters of the simulation model of each part in the electric drive system under the probability distribution and the BIC value of each part are obtained. Among them, for each part, the simulation model with the smallest BIC value is the optimal model of that part. The reliability function of each component in the electric drive system in the optimal model is calculated based on the acquired fatigue data. The reliability of the transmission system is calculated based on the reliability function of each component in the optimal model of the electric drive system. The remaining usable life of the electric drive system is calculated based on the reliability of the transmission system. This calculation includes the following steps: Set a reliability threshold; The number of damages is calculated using a reliability threshold; The remaining number of damage cycles for the system is calculated using the following formula: in, i remaining The remaining number of damage cycles for the system. To calculate the number of damages based on a reliability threshold, i dataLength This represents the theoretical number of damages to the system. The remaining usable lifespan of the electric drive system is calculated using the following formula: URL= f sampling * i remaining Where URL represents the remaining usable lifespan of the electric drive system. f sampling The sampling rate.

2. The remaining lifetime prediction method according to claim 1, characterized in that, The simulation model of virtual cumulative fatigue damage under a probability distribution includes the following steps: The cumulative probability density function of the damage value of the nth injury is calculated using the following formula: in, F ( v ) is the damage value. V n It is virtual cumulative fatigue damage. X n The magnitude of the damage. q The rebound coefficient; Substituting the cumulative probability density function into the probability distribution yields the cumulative damage density function under the probability distribution, which serves as a simulation model for virtual cumulative fatigue damage.

3. The remaining lifetime prediction method according to claim 1, characterized in that, The calculation and verification of the simulation model parameters for each scenario includes the following steps: Obtain the log-likelihood function of the simulation model of virtual cumulative fatigue damage under a probability distribution; The optim function is used to calculate the maximum likelihood function or the log-likelihood function of the simulation model under the probability distribution. The calculation result is the set of calculation parameters of the simulation model under the probability distribution. The parameter set of the simulation model under the constructed probability distribution is used to verify the calculation parameter set. If the verification result is unqualified, the maximum likelihood function or the log-likelihood function of the simulation model under the probability distribution is recalculated until the verification result is qualified.

4. The remaining lifetime prediction method according to claim 1, characterized in that, Before obtaining the parameters of the simulation models of each component in the electric drive system under various scenarios, the fatigue data is normalized.

5. The remaining lifetime prediction method according to claim 1, characterized in that, Calculate the BIC value of each part using the following formula: in, It is the maximum value of the likelihood function of the simulation model. x For fatigue data, M is the parameter set. n The number of fatigue data points; k This represents the number of parameters in the simulation model.

6. The remaining lifetime prediction method according to claim 1, characterized in that, Calculate the reliability function using the following formula: in, For reliability function, This is the optimal model.

7. The remaining lifetime prediction method according to claim 1, characterized in that, The reliability of the transmission system is: in, For the reliability of the reducer gears; For the reliability of the bearing; The reliability of the shaft.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the remaining lifetime prediction method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the remaining lifetime prediction method according to any one of claims 1 to 7.

Images