CN114897541B - Method, device, equipment and readable storage medium for predicting after-sale failure rate of vehicle - Google Patents
Method, device, equipment and readable storage medium for predicting after-sale failure rate of vehicle Download PDFInfo
- Publication number
- CN114897541B CN114897541B CN202210513236.XA CN202210513236A CN114897541B CN 114897541 B CN114897541 B CN 114897541B CN 202210513236 A CN202210513236 A CN 202210513236A CN 114897541 B CN114897541 B CN 114897541B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- date
- preset
- sales
- failure rate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000012423 maintenance Methods 0.000 claims abstract description 67
- 238000005315 distribution function Methods 0.000 claims abstract description 57
- 238000004458 analytical method Methods 0.000 claims abstract description 33
- 238000009826 distribution Methods 0.000 claims abstract description 25
- 238000012216 screening Methods 0.000 claims abstract description 12
- 230000001186 cumulative effect Effects 0.000 claims description 14
- 238000004519 manufacturing process Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 abstract description 5
- 238000013461 design Methods 0.000 abstract description 4
- 238000012360 testing method Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method, a device, equipment and a readable storage medium for predicting the after-sale failure rate of a vehicle, wherein the method for predicting the after-sale failure rate of the vehicle comprises the following steps: determining a sales date and a total sales volume of the vehicle; acquiring a maintenance date of the vehicle for first time according to a preset fault report; determining a first observation date based on the maintenance date, and calculating a first duration from the expiration date of a preset sales date range to the first observation date; screening out a target vehicle, and obtaining a first data set based on the target vehicle; and carrying out the parameter analysis of weber distribution based on the first data set to obtain an accumulated distribution function, wherein the accumulated distribution function is used for predicting the probability of failure of the vehicle in preset faults in different time periods after the vehicle is sold. The invention can predict the probability of failure of the vehicle due to corresponding faults in different time periods after sale, and the predicted probability can be directly used by a host factory, thereby providing basis for prediction of maintenance cost and decision of design change.
Description
Technical Field
The present invention relates to the field of after-sale quality management of vehicles, and in particular, to a method, an apparatus, a device and a readable storage medium for predicting a failure rate of a vehicle after-sale.
Background
After the automobile host factory is on the market, the future failure rate prediction is needed based on the automobile failure in the after-market to predict the quality performance of the product in the whole life cycle of the automobile, so that whether the product improvement or the design change is needed for the quality problem of a certain part is determined. In the prior art, failure rate prediction under the real after-sales use situation of the whole vehicle is generally carried out based on a product life distribution model deduced from the complete life test results of the component levels in a laboratory. While this approach has the following drawbacks: the effectiveness of the sampled sample is insufficient; the laboratory environment (component level, continuous duty cycle) deviates from the real use conditions (vehicle, real use cycle). The part failure probability distribution model obtained through the full life test only obtains the direct relation between the life of the part and the continuous working period, and cannot be directly corresponding to the actual after-sale time of the vehicle. The real demand of the host factory is the failure occurrence rate of the whole vehicle level vehicle in each period after being sold.
Disclosure of Invention
The invention mainly aims to provide a method, a device, equipment and a readable storage medium for predicting the after-sale failure rate of a vehicle, and aims to solve the technical problem that in the prior art, a failure prediction model of the vehicle in different after-sale time periods is lacked.
In a first aspect, the present invention provides a method for predicting an after-market failure rate of a vehicle, the method comprising the steps of:
determining the sales date and the total sales volume of a vehicle, wherein the vehicle is sold in a preset sales date range, produced in a preset production date range and preset whole vehicle configuration;
acquiring a maintenance date of the vehicle for first time according to a preset fault report;
determining a first observation date based on the maintenance date, and calculating a first duration from the expiration date of a preset sales date range to the first observation date;
screening out a target vehicle, and obtaining a first data set based on the target vehicle, wherein the interval duration from the sales date to the maintenance date of the target vehicle is not longer than the first duration;
And carrying out the parameter analysis of weber distribution based on the first data set to obtain an accumulated distribution function, wherein the accumulated distribution function is used for predicting the probability of failure of the vehicle in preset faults in different time periods after the vehicle is sold.
Optionally, the step of performing a weber distribution parameter analysis based on the first data set to obtain an accumulated distribution function includes:
Dividing the interval duration from the sales date to the maintenance date of the target vehicle in the first data set into different time ranges by a preset step length;
The number of all target vehicles in different time ranges is imported into data analysis software to perform weber distribution parameter analysis, and proportional parameters and shape parameters are obtained;
substituting the proportion parameter and the shape parameter into a first formula to obtain an accumulated distribution function, wherein the first formula is as follows:
wherein F (x) is an accumulated distribution function, x is the after-sales time length, lambda is a proportion parameter, and k is a shape parameter.
Optionally, after the step of performing the parameter analysis of weber distribution based on the first data set to obtain the cumulative distribution function, the method further includes:
determining a second observation date based on the maintenance date, and calculating a second duration from the expiration date of the preset sales date range to the second observation date;
substituting the second time length into the cumulative distribution function to obtain a predicted failure rate of the vehicle in the second time length after sale in a preset failure mode;
dividing the number of vehicles with the interval time from the sales date to the maintenance date not more than the second time by the total sales volume of the vehicles to obtain the actual failure rate of the vehicles in the second time after sales in the preset failure;
Obtaining a confidence coefficient based on the actual fault rate and the predicted fault rate;
Judging whether the confidence coefficient meets the preset confidence coefficient requirement or not;
and if the preset confidence coefficient requirement is met, predicting the failure rate of the vehicle in different time periods after sale in the future by using the accumulated distribution function.
Optionally, the second observation date is the last date in the maintenance date, and the interval time between the first observation date and the second observation date is longer than the preset time.
In a second aspect, the present invention also provides a device for predicting an after-market failure rate of a vehicle, the device comprising:
the system comprises a determining module, a storage module and a display module, wherein the determining module is used for determining the sales date and the total sales volume of vehicles, and the vehicles are sold in a preset sales date range, produced in a preset production date range and preset whole vehicle configuration;
the acquisition module is used for acquiring the maintenance date of the vehicle for reporting and repairing the preset fault for the first time;
the calculating module is used for determining a first observation date based on the maintenance date and calculating a first duration from the expiration date of the preset sales date range to the first observation date;
The screening module is used for screening out a target vehicle and obtaining a first data set based on the target vehicle, wherein the interval duration from the sales date to the maintenance date of the target vehicle is not longer than the first duration;
and the parameter analysis module is used for carrying out the parameter analysis of the Weber distribution based on the first data set to obtain an accumulated distribution function, and the accumulated distribution function is used for predicting the probability of failure of the vehicle in preset faults in different time periods after the vehicle is sold.
Optionally, the parameter analysis module is further specifically configured to:
Dividing the interval duration from the sales date to the maintenance date of the target vehicle in the first data set into different time ranges by a preset step length;
The number of all target vehicles in different time ranges is imported into data analysis software to perform weber distribution parameter analysis, and proportional parameters and shape parameters are obtained;
substituting the proportion parameter and the shape parameter into a first formula to obtain an accumulated distribution function, wherein the first formula is as follows:
wherein F (x) is an accumulated distribution function, x is the after-sales time length, lambda is a proportion parameter, and k is a shape parameter.
Optionally, the after-sales failure rate predicting device for a vehicle further includes a judging module, configured to:
determining a second observation date based on the maintenance date, and calculating a second duration from the expiration date of the preset sales date range to the second observation date;
substituting the second time length into the cumulative distribution function to obtain a predicted failure rate of the vehicle in the second time length after sale in a preset failure mode;
dividing the number of vehicles with the interval time from the sales date to the maintenance date not more than the second time by the total sales volume of the vehicles to obtain the actual failure rate of the vehicles in the second time after sales in the preset failure;
Obtaining a confidence coefficient based on the actual fault rate and the predicted fault rate;
Judging whether the confidence coefficient meets the preset confidence coefficient requirement or not;
and if the preset confidence coefficient requirement is met, predicting the failure rate of the vehicle in different time periods after sale in the future by using the accumulated distribution function.
Optionally, the second observation date is the last date in the maintenance date, and the interval time between the first observation date and the second observation date is longer than the preset time.
In a third aspect, the present invention also provides an after-market vehicle failure rate prediction apparatus, the after-market vehicle failure rate prediction apparatus comprising a processor, a memory, and an after-market vehicle failure rate prediction program stored on the memory and executable by the processor, wherein the after-market vehicle failure rate prediction program, when executed by the processor, implements the steps of the after-market vehicle failure rate prediction method as described above.
In a fourth aspect, the present invention further provides a readable storage medium, where a vehicle after-market failure rate prediction program is stored, where the vehicle after-market failure rate prediction program, when executed by a processor, implements the steps of the vehicle after-market failure rate prediction method as described above.
The invention provides a method, a device, equipment and a readable storage medium for predicting the after-sale failure rate of a vehicle, wherein the method for predicting the after-sale failure rate of the vehicle comprises the following steps: determining the sales date and the total sales volume of a vehicle, wherein the vehicle is sold in a preset sales date range, produced in a preset production date range and preset whole vehicle configuration; acquiring a maintenance date of the vehicle for first time according to a preset fault report; determining a first observation date based on the maintenance date, and calculating a first duration from the expiration date of a preset sales date range to the first observation date; screening out a target vehicle, and obtaining a first data set based on the target vehicle, wherein the interval duration from the sales date to the maintenance date of the target vehicle is not longer than the first duration; and carrying out the parameter analysis of weber distribution based on the first data set to obtain an accumulated distribution function, wherein the accumulated distribution function is used for predicting the probability of failure of the vehicle in preset faults in different time periods after the vehicle is sold. The invention can predict the probability of failure of the vehicle due to corresponding faults in different time periods after sale, and the predicted probability can be directly used by a host factory, thereby providing basis for prediction of maintenance cost and decision of design change.
Drawings
FIG. 1 is a schematic hardware architecture of an after-market failure rate prediction device for a vehicle according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating an embodiment of a method for predicting after-market failure rate of a vehicle according to the present invention;
FIG. 3 is a flow chart of a method for predicting after-market failure rate of a vehicle according to another embodiment of the present invention;
FIG. 4 is a schematic diagram of functional modules of an apparatus for predicting after-market failure rate of a vehicle according to an embodiment of the invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In a first aspect, an embodiment of the present invention provides an apparatus for predicting a failure rate after sale of a vehicle.
Referring to fig. 1, fig. 1 is a schematic hardware configuration of an after-market failure rate prediction apparatus for a vehicle according to an embodiment of the present invention. In an embodiment of the present invention, the after-market failure rate predicting device may include a processor 1001 (e.g., a central processing unit Central Processing Unit, a CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein the communication bus 1002 is used to enable connected communications between these components; the user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard); the network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., wireless FIdelity WIreless-FICAT interface); the memory 1005 may be a high-speed random access memory (random access memory, RAM) or a stable memory (non-volatile memory), such as a disk memory, and the memory 1005 may alternatively be a storage device independent of the processor 1001. Those skilled in the art will appreciate that the hardware configuration shown in fig. 1 is not limiting of the invention and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
With continued reference to FIG. 1, an operating system, a network communication module, a user interface module, and an after-market failure rate prediction program for a vehicle may be included in memory 1005, which is one type of computer storage medium in FIG. 1. The processor 1001 may call the after-sales failure rate prediction program stored in the memory 1005, and execute the after-sales failure rate prediction method provided by the embodiment of the present invention.
In the second aspect, since the product life distribution model obtained in the existing scheme is derived based on the result obtained by taking a plurality of mass-produced new parts randomly on the production line as samples and performing a full life test on the samples after the after-market vehicle fails in the market. The product life model is applied to failure rate prediction under the real use scene of the whole vehicle after sale, and has the following defects:
Firstly, the validity of the sampled sample is insufficient: when the whole vehicle fails, the parts loaded by the vehicle are produced in the past, the parts in the test are produced at present, and the 6M change (man-machine material method loop test) in the time difference can affect the states of the parts, so that the sampled part samples cannot represent the actual level of the failed parts. Even if some parts manufacturers sample and hold parts produced in a certain batch for future investigation of quality problems, the amount of the sample is usually small. And the reliability of the test result of the small sample is low, and the cost of the test of the large sample is high.
Secondly, the environment of the laboratory is deviated from the actual use condition, a full life test is carried out in the laboratory, and the experimental condition and the duty cycle are set based on the assumption of manual work and are different from the working condition and the environment when the actual use of the vehicle by a driver is failed, so that the deviation can be caused.
Thirdly, the current technical proposal is mostly aimed at the tests of parts and system levels, and the actual faults occur in the whole vehicle environment. The test subjects and the environment are different, and the result may be deviation.
Fourth, the life model of the part product obtained through the full life test only obtains the direct relation between the life of the part and the continuous working period, and the direct relation cannot be directly corresponding to the actual after-sale time of the vehicle. For example, it is known based on the part product life model that 60% of the parts fail after 1w hours of continuous operation, but this 1w hours cannot correspond to 1 year or 2 years after the vehicle is sold to the owners. It is possible that the owner buys the vehicle for 2 years, but most of the time the vehicle is stopped, and it is also possible that the owner drives for a long period of time, but most of the time the function related to the component (such as fog lamp) is not used. What the host factory really needs is the failure occurrence rate of all time periods after the whole vehicle level vehicle is sold.
Therefore, the embodiment of the invention provides a vehicle after-sale fault rate prediction method.
Referring to fig. 2, fig. 2 is a flowchart illustrating an after-market failure rate prediction method according to an embodiment of the invention.
In an embodiment of the present invention, an after-market failure rate prediction method for a vehicle includes:
Step S10, determining the sales date and the total sales volume of vehicles, wherein the vehicles are vehicles sold in a preset sales date range, produced in a preset production date range and preset whole vehicle configuration;
In this embodiment, the actual fault vehicle is taken as a sample, the sample size is large, the actual running condition of the vehicle is the truest, and no additional test is required. Compared with the prior art, after the current production line part is sampled, the product life model is deduced based on the result obtained by the full life test, and the obtained result is strong in representativeness and high in model accuracy.
Because the actual fault vehicle is required to be taken as a sample, the existing fault vehicle can be firstly analyzed, and the results of fault phenomena, failure parts, failure modes, fault reasons, whole vehicle configuration corresponding to the fault vehicle, production intervals corresponding to the fault vehicle and the like are confirmed. Meanwhile, the sample size of sampling and calculating the real fault vehicle is limited, vehicles which meet the conditions of production within a preset production date range, sales within a preset sales date range and vehicle configuration are screened out from an enterprise sales system based on the analysis result, and the specific sales date and the total sales size corresponding to the screened vehicles are determined. Based on the part of the screened vehicle samples, secondary screening is performed based on after-sales data.
Step S20, acquiring a maintenance date of the vehicle for first time according to a preset fault report;
In this embodiment, based on the analysis result, vehicles meeting the preset conditions with a limited sample size are screened from the enterprise sales system. At this time, based on the failure parts, including failure modes and failure description of failure reasons, the vehicle maintenance data failed by the preset failure in the total vehicle sample is screened from the after-sale system, and the data of the preset failure of the vehicle in different after-sale time periods is required. Based on the date of sale of the vehicle and the corresponding date of repair of the vehicle for the first time with the preset fault warranty, it is possible to determine which period of time the vehicle is after sale to report with the preset fault warranty. Therefore, the maintenance date of the screened vehicle for the first time subjected to the preset fault maintenance can be obtained from the after-sale system, so that the time period of the preset fault after the after-sale is obtained.
Step S30, determining a first observation date based on the maintenance date, and calculating a first duration from the expiration date of a preset sales date range to the first observation date;
In this embodiment, before performing the parameter analysis of the failure rate based on the corresponding sales and maintenance data, it is necessary to determine the first observation date based on the determined maintenance dates of the plurality of vehicles, and calculate the first time period from the expiration date to the first observation date within the preset sales date range. The first observation date is at least 6 months prior to the last maintenance date.
Step S40, screening out a target vehicle, and obtaining a first data set based on the target vehicle, wherein the interval duration from the sales date to the maintenance date of the target vehicle is not longer than a first duration;
in this embodiment, the target vehicle is determined based on the determined first observation date and the first time period, the interval time period from the sales date to the maintenance date of the target vehicle is not greater than the first time period, and the first data set may be obtained based on the target vehicle, where the obtained first data set includes the after-sales fault time period from the specific sales date to the maintenance date of the target vehicle first reported by the preset fault.
And step S50, carrying out the parameter analysis of Weber distribution based on the first data set to obtain an accumulated distribution function, wherein the accumulated distribution function is used for predicting the probability of failure of the vehicle in preset faults in different time periods after the vehicle is sold.
In this embodiment, weber distribution parameter analysis is performed based on the obtained first data set, so as to obtain an accumulated distribution function, where the accumulated distribution function is used to predict the probability of failure of the vehicle in a preset failure within different time periods after the vehicle is sold. Compared with the prior art, the method has the advantages that the complete life test is needed, the parameter analysis is performed based on the test result, the additional experiment is not needed, the first data set can be obtained only by processing the prior sales data and maintenance data, the fault prediction model is obtained based on the first data set, the probability of failure of the vehicle in preset faults in different time periods after the vehicle is sold is predicted, and the cost is saved. And the vehicle sales time-the first maintenance time of the preset fault report is taken as the output of the prediction model, the output result does not need to be converted, and the method can be directly used by a host factory, and can be used for the prediction of the after-sales fault rate and the quality improvement decision.
Further, in an embodiment, the step S50 includes:
Dividing the interval duration from the sales date to the maintenance date of the target vehicle in the first data set into different time ranges by a preset step length;
The number of all target vehicles in different time ranges is imported into data analysis software to perform weber distribution parameter analysis, and proportional parameters and shape parameters are obtained;
substituting the proportion parameter and the shape parameter into a first formula to obtain an accumulated distribution function, wherein the first formula is as follows:
wherein F (x) is an accumulated distribution function, x is the after-sales time length, lambda is a proportion parameter, and k is a shape parameter.
In this embodiment, the interval duration from the sales date to the maintenance date of the target vehicle in the first dataset is divided into different time ranges with a preset step size. For example, the first dataset includes 500 target vehicles in which the vehicle was sold for the first time that a preset malfunction occurred, 1 for 0-30 days, 0 for 30-40 days, 5 for 40-50 days, 1 for 50-60 days, 3 for 60-70 days, 8 for 70-80 days, 13 for 80-90 days, 18 for 90-100 days, and so on.
And importing the number of all target vehicles in different time ranges into data analysis software such as Minitab, and carrying out weber distribution parameter analysis to obtain the proportion parameters and the shape parameters. For example, 2000 sales were taken, the first time period was t 1, the sales, the start time, the end time, the number of failures were arranged in rows, the first row (0, 30, 1999), the second row (30, 40, 1999), the third row (40, 50, 1994), and so on, and the last row (t 1, 1500), wherein x represents the deleted data indicating the number of remaining 1500 vehicles failed in a preset failure during the unknown after-market period after t 1. All the data after the row arrangement are imported into data analysis software such as Minitab for weber distribution parameter analysis, and the proportion parameter lambda and the shape parameter k can be obtained.
Substituting the ratio parameter lambda and the shape parameter k into a first formula to obtain an accumulated distribution function, wherein the first formula is as follows:
wherein F (x) is an accumulated distribution function, x is the after-sales time length, lambda is a proportion parameter, and k is a shape parameter.
Further, in an embodiment, referring to fig. 3, after the step S50, the method further includes:
Step S60, determining a second observation date based on the maintenance date, and calculating a second time length from the expiration date of the preset sales date range to the second observation date;
step S70, substituting the second time length into the cumulative distribution function to obtain a predicted failure rate of the vehicle in the second time length after sales in a preset failure mode;
Step S80, dividing the number of vehicles with the interval time from the sales date to the maintenance date not more than the second time by the total sales volume of the vehicles to obtain the actual failure rate of the vehicles in the second time after sales in the preset failure;
Step S90, obtaining a confidence coefficient based on the actual fault rate and the predicted fault rate;
Step S100, judging whether the confidence coefficient meets the preset confidence coefficient requirement;
And step S110, if the preset confidence requirement is met, predicting the failure rate of the vehicle in different time periods after sale in the future by using the accumulated distribution function.
In this embodiment, after the step of performing data analysis based on the first data set to obtain the cumulative distribution function, verification calculation is required to be performed on the cumulative distribution function to determine whether the failure rate obtained by calculation based on the cumulative distribution function meets the preset confidence requirement. That is, a second observation date is determined based on the maintenance date, and a second time period from the expiration date of the preset sales date range to the second observation date can be calculated. In one aspect, dividing the number of vehicles in which the interval time from the sales date to the maintenance date is not greater than the second time by the total sales volume of the vehicles to obtain an actual failure rate of the vehicles in the second time after sales in which the vehicles fail in a preset failure; and on the other hand, substituting the second time length into the cumulative distribution function to obtain the predicted failure rate of the vehicle in the second time length after sales in the preset failure.
And obtaining a confidence coefficient based on the actual fault rate and the predicted fault rate. And judging whether the confidence coefficient meets the preset confidence coefficient requirement or not after obtaining the confidence coefficient. And if the judgment result meets the preset confidence coefficient requirement, predicting the failure rate of the vehicle in different time periods after sale in the future by using the accumulated distribution function. For example, the 1020-day intra-prediction failure rate calculated based on the prediction model is: 33%, the preset confidence requirement is that the actual failure rate is within a 99.7% confidence interval of the predicted failure rate result, namely the actual failure rate meeting the preset confidence requirement is 28% -40%, if the actual failure rate obtained based on the actual data is 19.15% at this time and is not in the value range, the accumulated distribution function is not used for predicting the failure rate of the vehicle in the preset failure in different time periods after sale in the future. And if the actual failure rate is 29.15% based on the actual data and is in the value range, predicting the failure rate of the vehicle in the preset failure in different time periods after sale in the future by using the accumulated distribution function. In this way, the accuracy of the prediction result is further improved.
Further, in an embodiment, the second observation date is a last date of the maintenance date, and a time interval between the first observation date and the second observation date is longer than a preset time period.
In this embodiment, the second observation date is a last date in the maintenance date, and a time interval between the first observation date and the second observation date is longer than a preset time period. The preset duration is valued based on the actual fault analysis condition, and in order to ensure the accuracy of model verification, the preset duration is usually valued for not less than 6 months.
In this embodiment, a method, an apparatus, a device, and a readable storage medium for predicting an after-sale failure rate of a vehicle are provided, where the method for predicting an after-sale failure rate of a vehicle includes: determining the sales date and the total sales volume of a vehicle, wherein the vehicle is sold in a preset sales date range, produced in a preset production date range and preset whole vehicle configuration; acquiring a maintenance date of the vehicle for first time according to a preset fault report; determining a first observation date based on the maintenance date, and calculating a first duration from the expiration date of a preset sales date range to the first observation date; screening out a target vehicle, and obtaining a first data set based on the target vehicle, wherein the interval duration from the sales date to the maintenance date of the target vehicle is not longer than the first duration; and carrying out the parameter analysis of weber distribution based on the first data set to obtain an accumulated distribution function, wherein the accumulated distribution function is used for predicting the probability of failure of the vehicle in preset faults in different time periods after the vehicle is sold. The invention can predict the probability of failure of the vehicle due to corresponding faults in different time periods after sale, and the predicted probability can be directly used by a host factory, thereby providing basis for prediction of maintenance cost and decision of design change.
In a third aspect, the embodiment of the invention further provides a device for predicting the after-sale failure rate of the vehicle.
Referring to fig. 4, a functional block diagram of an embodiment of a vehicle after-market failure rate prediction apparatus is shown.
In this embodiment, the apparatus for predicting a failure rate after sale of a vehicle includes:
A determining module 10, configured to determine a sales date and a total sales volume of a vehicle, where the vehicle is a vehicle that is sold within a preset sales date range, is produced within a preset production date range, and is configured as a preset whole vehicle;
an obtaining module 20, configured to obtain a maintenance date of the vehicle for first repairing with a preset fault;
A calculating module 30, configured to determine a first observation date based on the maintenance date, and calculate a first duration from an expiration date of a preset sales date range to the first observation date;
A screening module 40, configured to screen out a target vehicle, and obtain a first data set based on the target vehicle, where an interval duration from a sales date to a maintenance date of the target vehicle is not greater than a first duration;
The parameter analysis module 50 is configured to perform a weber distribution parameter analysis based on the first data set, so as to obtain a cumulative distribution function, where the cumulative distribution function is used to predict the probability of failure of the vehicle in a preset failure within different time periods after the vehicle is sold.
Further, in an embodiment, the parameter analysis module 50 is configured to:
Dividing the interval duration from the sales date to the maintenance date of the target vehicle in the first data set into different time ranges by a preset step length;
The number of all target vehicles in different time ranges is imported into data analysis software to perform weber distribution parameter analysis, and proportional parameters and shape parameters are obtained;
substituting the proportion parameter and the shape parameter into a first formula to obtain an accumulated distribution function, wherein the first formula is as follows:
wherein F (x) is an accumulated distribution function, x is the after-sales time length, lambda is a proportion parameter, and k is a shape parameter.
Further, in an embodiment, the after-sales failure rate prediction apparatus for a vehicle further includes a judging module, configured to:
determining a second observation date based on the maintenance date, and calculating a second duration from the expiration date of the preset sales date range to the second observation date;
substituting the second time length into the cumulative distribution function to obtain a predicted failure rate of the vehicle in the second time length after sale in a preset failure mode;
dividing the number of vehicles with the interval time from the sales date to the maintenance date not more than the second time by the total sales volume of the vehicles to obtain the actual failure rate of the vehicles in the second time after sales in the preset failure;
Obtaining a confidence coefficient based on the actual fault rate and the predicted fault rate;
Judging whether the confidence coefficient meets the preset confidence coefficient requirement or not;
and if the preset confidence coefficient requirement is met, predicting the failure rate of the vehicle in different time periods after sale in the future by using the accumulated distribution function.
Further, in an embodiment, the second observation date is a last date of the maintenance date, and a time interval between the first observation date and the second observation date is longer than a preset time period.
The function implementation of each module in the vehicle after-sales failure rate prediction device corresponds to each step in the vehicle after-sales failure rate prediction method embodiment, and the function and implementation process of each module are not described in detail herein.
In a fourth aspect, embodiments of the present invention also provide a readable storage medium.
The invention stores the after-sales failure rate prediction program of the vehicle on the readable storage medium, wherein the after-sales failure rate prediction program of the vehicle realizes the steps of the after-sales failure rate prediction method of the vehicle when being executed by a processor.
The method implemented when the after-market failure rate prediction program is executed may refer to various embodiments of the after-market failure rate prediction method of the present invention, and will not be described herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising several instructions for causing a terminal device to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (8)
1. An after-market failure rate prediction method for a vehicle, characterized in that the after-market failure rate prediction method for a vehicle comprises the following steps:
determining the sales date and the total sales volume of a vehicle, wherein the vehicle is sold in a preset sales date range, produced in a preset production date range and preset whole vehicle configuration;
acquiring a maintenance date of the vehicle for first time according to a preset fault report;
determining a first observation date based on the maintenance date, and calculating a first duration from the expiration date of a preset sales date range to the first observation date;
screening out a target vehicle, and obtaining a first data set based on the target vehicle, wherein the interval duration from the sales date to the maintenance date of the target vehicle is not longer than the first duration;
Carrying out weber distribution parameter analysis based on the first data set to obtain an accumulated distribution function, wherein the accumulated distribution function is used for predicting the probability of failure of the vehicle in preset faults in different time periods after the vehicle is sold;
after the step of performing weber distribution parameter analysis based on the first data set to obtain an accumulated distribution function, the method further comprises:
determining a second observation date based on the maintenance date, and calculating a second duration from the expiration date of the preset sales date range to the second observation date;
substituting the second time length into the cumulative distribution function to obtain a predicted failure rate of the vehicle in the second time length after sale in a preset failure mode;
dividing the number of vehicles with the interval time from the sales date to the maintenance date not more than the second time by the total sales volume of the vehicles to obtain the actual failure rate of the vehicles in the second time after sales in the preset failure;
Obtaining a confidence coefficient based on the actual fault rate and the predicted fault rate;
Judging whether the confidence coefficient meets the preset confidence coefficient requirement or not;
and if the preset confidence coefficient requirement is met, predicting the failure rate of the vehicle in different time periods after sale in the future by using the accumulated distribution function.
2. The method of predicting after-market failure rate of a vehicle of claim 1, wherein the step of performing a weber distribution parameter analysis based on the first data set to obtain a cumulative distribution function comprises:
Dividing the interval duration from the sales date to the maintenance date of the target vehicle in the first data set into different time ranges by a preset step length;
The number of all target vehicles in different time ranges is imported into data analysis software to perform weber distribution parameter analysis, and proportional parameters and shape parameters are obtained;
substituting the proportion parameter and the shape parameter into a first formula to obtain an accumulated distribution function, wherein the first formula is as follows:
wherein F (x) is an accumulated distribution function, x is the after-sales time length, lambda is a proportion parameter, and k is a shape parameter.
3. The method for predicting after-market failure rate of a vehicle of claim 1, wherein: the second observation date is the last date in the maintenance date, and the interval time length between the first observation date and the second observation date is longer than the preset time length.
4. An after-market failure rate predicting apparatus for a vehicle, characterized by comprising:
the system comprises a determining module, a storage module and a display module, wherein the determining module is used for determining the sales date and the total sales volume of vehicles, and the vehicles are sold in a preset sales date range, produced in a preset production date range and preset whole vehicle configuration;
the acquisition module is used for acquiring the maintenance date of the vehicle for reporting and repairing the preset fault for the first time;
the calculating module is used for determining a first observation date based on the maintenance date and calculating a first duration from the expiration date of the preset sales date range to the first observation date;
The screening module is used for screening out a target vehicle and obtaining a first data set based on the target vehicle, wherein the interval duration from the sales date to the maintenance date of the target vehicle is not longer than the first duration;
The parameter analysis module is used for carrying out the parameter analysis of weber distribution based on the first data set to obtain an accumulated distribution function, and the accumulated distribution function is used for predicting the probability of failure of the vehicle in preset faults in different time periods after the vehicle is sold;
The after-sales failure rate prediction device of the vehicle further comprises a judgment module for:
determining a second observation date based on the maintenance date, and calculating a second duration from the expiration date of the preset sales date range to the second observation date;
substituting the second time length into the cumulative distribution function to obtain a predicted failure rate of the vehicle in the second time length after sale in a preset failure mode;
dividing the number of vehicles with the interval time from the sales date to the maintenance date not more than the second time by the total sales volume of the vehicles to obtain the actual failure rate of the vehicles in the second time after sales in the preset failure;
Obtaining a confidence coefficient based on the actual fault rate and the predicted fault rate;
Judging whether the confidence coefficient meets the preset confidence coefficient requirement or not;
and if the preset confidence coefficient requirement is met, predicting the failure rate of the vehicle in different time periods after sale in the future by using the accumulated distribution function.
5. The after-market failure rate prediction device of claim 4, wherein the parameter analysis module is configured to:
Dividing the interval duration from the sales date to the maintenance date of the target vehicle in the first data set into different time ranges by a preset step length;
The number of all target vehicles in different time ranges is imported into data analysis software to perform weber distribution parameter analysis, and proportional parameters and shape parameters are obtained;
substituting the proportion parameter and the shape parameter into a first formula to obtain an accumulated distribution function, wherein the first formula is as follows:
wherein F (x) is an accumulated distribution function, x is the after-sales time length, lambda is a proportion parameter, and k is a shape parameter.
6. The after-market failure rate predicting apparatus for a vehicle according to claim 4, wherein: the second observation date is the last date in the maintenance date, and the interval time length between the first observation date and the second observation date is longer than the preset time length.
7. An after-market vehicle failure rate prediction device comprising a processor, a memory, and an after-market vehicle failure rate prediction program stored on the memory and executable by the processor, wherein the after-market vehicle failure rate prediction program, when executed by the processor, implements the steps of the after-market vehicle failure rate prediction method of any of claims 1-3.
8. A readable storage medium, wherein a vehicle after-market failure rate prediction program is stored on the readable storage medium, wherein the vehicle after-market failure rate prediction program, when executed by a processor, implements the steps of the vehicle after-market failure rate prediction method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210513236.XA CN114897541B (en) | 2022-05-11 | 2022-05-11 | Method, device, equipment and readable storage medium for predicting after-sale failure rate of vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210513236.XA CN114897541B (en) | 2022-05-11 | 2022-05-11 | Method, device, equipment and readable storage medium for predicting after-sale failure rate of vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114897541A CN114897541A (en) | 2022-08-12 |
| CN114897541B true CN114897541B (en) | 2024-09-13 |
Family
ID=82721162
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210513236.XA Active CN114897541B (en) | 2022-05-11 | 2022-05-11 | Method, device, equipment and readable storage medium for predicting after-sale failure rate of vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114897541B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610266A (en) * | 2021-06-25 | 2021-11-05 | 东风本田发动机有限公司 | Method and device for predicting failure of automobile part, computer device and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11333578B2 (en) * | 2017-09-19 | 2022-05-17 | Raytheon Technologies Corporation | Method for online service policy tracking using optimal asset controller |
| CN111630464A (en) * | 2017-09-29 | 2020-09-04 | 大众前瞻有限公司 | Prediction of vehicle repair operations |
| US11010222B2 (en) * | 2019-08-29 | 2021-05-18 | Sap Se | Failure mode specific analytics using parametric models |
| CN111915184A (en) * | 2020-07-30 | 2020-11-10 | 上海数策软件股份有限公司 | Early warning method for quality of parts in automobile industry and storage medium |
| CN113807547A (en) * | 2021-08-12 | 2021-12-17 | 江铃汽车股份有限公司 | Vehicle fault early warning method and system, readable storage medium and computer equipment |
| CN114329921A (en) * | 2021-12-10 | 2022-04-12 | 岚图汽车科技有限公司 | Method, device, equipment and medium for evaluating reliability performance of whole vehicle |
-
2022
- 2022-05-11 CN CN202210513236.XA patent/CN114897541B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610266A (en) * | 2021-06-25 | 2021-11-05 | 东风本田发动机有限公司 | Method and device for predicting failure of automobile part, computer device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114897541A (en) | 2022-08-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7107187B1 (en) | Method for modeling system performance | |
| US8352867B2 (en) | Predictive monitoring dashboard | |
| US6823287B2 (en) | Method for predicting the quality of a product | |
| CN111881023B (en) | Software aging prediction method and device based on multi-model comparison | |
| CN111611172A (en) | Project test defect analysis method, device, equipment and storage medium | |
| CN112115005B (en) | Test data acquisition method and device, computer equipment and storage medium | |
| CN114138634B (en) | Test case selection method and device, computer equipment and storage medium | |
| CN114691521A (en) | Software testing platform based on artificial intelligence | |
| CN113610266B (en) | Method and device for predicting failure of automobile part, computer equipment and storage medium | |
| CN114897541B (en) | Method, device, equipment and readable storage medium for predicting after-sale failure rate of vehicle | |
| CN116300782A (en) | Fault code threshold adjustment method, device, equipment and storage medium | |
| CN111752786A (en) | Data storage method, data summarization method, equipment and medium in pressure test process | |
| CN112559000A (en) | Vehicle software updating method and device | |
| CN113127804A (en) | Method and device for determining number of vehicle faults, computer equipment and storage medium | |
| CN111210105A (en) | Continuous operation performance verification device, computer equipment and storage medium | |
| CN111274687A (en) | Component failure rate prediction method and device, computer equipment and storage medium | |
| CN114817077B (en) | Method, system and network equipment for judging test quality and specification | |
| CN118118379B (en) | Equipment operation monitoring method and system based on Internet of things | |
| CN117556187B (en) | Cloud data restoration method and system based on deep learning and readable storage medium | |
| CN113110971B (en) | Abnormal data detection method, device, computer equipment and storage medium | |
| CN117478394B (en) | Network security analysis method, system, computer equipment and computer readable storage medium based on digital twin | |
| CN115457769B (en) | Data correction method, device, equipment and readable storage medium | |
| CN112734173B (en) | Elevator component producer evaluation system and evaluation method | |
| CN115114775B (en) | Method and device for converting Weibull type failure-free data into failure type reliability data | |
| EP4212892B1 (en) | System and method for analysis of vehicle electrical system performance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |