CN110516823B - Vehicle intelligent maintenance model based on time sequence model - Google Patents
Vehicle intelligent maintenance model based on time sequence model Download PDFInfo
- Publication number
- CN110516823B CN110516823B CN201910784276.6A CN201910784276A CN110516823B CN 110516823 B CN110516823 B CN 110516823B CN 201910784276 A CN201910784276 A CN 201910784276A CN 110516823 B CN110516823 B CN 110516823B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- mileage
- model
- maintenance
- day
- 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
- 238000012423 maintenance Methods 0.000 title claims abstract description 107
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims abstract description 56
- 230000001932 seasonal effect Effects 0.000 claims abstract description 56
- 238000003062 neural network model Methods 0.000 claims abstract description 28
- 230000002354 daily effect Effects 0.000 claims description 34
- 238000000034 method Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 10
- 230000003203 everyday effect Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Time Recorders, Dirve Recorders, Access Control (AREA)
Abstract
The application relates to a vehicle wisdom maintenance model based on time sequence model, vehicle wisdom maintenance model includes: the first acquisition unit is used for acquiring the equivalent mileage of the vehicle on the same day according to a pre-established deep neural network model; a determining unit for determining a remaining maintenance mileage of the vehicle using a current day equivalent mileage of the vehicle; and the second acquisition unit is used for acquiring the remaining maintenance days of the vehicle by utilizing a pre-established seasonal ARIMA model according to the remaining maintenance mileage of the vehicle. The technical scheme provided by the invention can accurately inform the vehicle owner of the specific time required to be maintained, so that the user reasonably arranges own time for maintenance.
Description
Technical Field
The application relates to the technical field of automobile maintenance, in particular to a vehicle intelligent maintenance model based on a time sequence model.
Background
With the promotion of the market and the improvement of the cognition of users, the internet protocol vehicles can be explosively increased in the next few years, and the user quantity can be kept in a surge state. The rapid development of the automotive industry has led to a rapid growth in vehicle maintenance business.
Most of maintenance schemes in the related art only consider single dimension of the driving mileage, and urge the vehicle owner to return to the factory for maintenance through the vehicle maintenance alarm information report, but only consider that the driving mileage is too single and incomplete, and the real health condition of the vehicle cannot be reflected.
Disclosure of Invention
In order to overcome the problem that the vehicle maintenance alarm information in the related technology can not reflect the real health condition of the vehicle at least to a certain extent, the application provides a vehicle intelligent maintenance model based on a time sequence model.
According to a first aspect of embodiments of the present application, there is provided a vehicle intelligent maintenance model based on a time series model, including:
the first acquisition unit is used for acquiring the equivalent mileage of the vehicle on the same day according to a pre-established deep neural network model;
a determining unit for determining a remaining maintenance mileage of the vehicle using a current day equivalent mileage of the vehicle;
and the second acquisition unit is used for acquiring the remaining maintenance days of the vehicle by utilizing a pre-established seasonal ARIMA model according to the remaining maintenance mileage of the vehicle.
Preferably, the establishing process of the pre-established deep neural network model includes:
and training by taking historical weather data as an input layer training sample of the deep neural network model and taking the weight of the influence of the historical weather on the vehicle as an output layer training sample of the deep neural network model to obtain the pre-established deep neural network model.
Preferably, the first acquiring unit includes:
the first acquisition module is used for acquiring the weight of the influence of the weather of the day between the last maintenance date of the vehicle and the current day on the vehicle by taking the weather data of the day between the last maintenance date of the vehicle and the current day as the input of the pre-established deep neural network model;
and the second acquisition module is used for acquiring the equivalent mileage of the vehicle on the same day by using the weight of the influence of the weather of the vehicle on the vehicle from the last maintenance date of the vehicle to the day.
Further, the second obtaining module is configured to determine a current equivalent mileage i of the vehicle according to the following formula:
in the above formula, i is [1, n ]]N is the date of the day, l' is the actual travel mileage of the vehicle when the date is i, and w i The weight of the influence of weather on the vehicle when the date is i; where i=1 is the date of the last maintenance of the vehicle.
Preferably, the determining unit is configured to determine the remaining maintenance mileage L of the vehicle according to the following formula:
L＝l 1 -(l-l 2 )
in the above, l 1 Is the maintenance cycle mileage of the vehicle, l is the equivalent mileage of the vehicle on the same day, l 2 The mileage of the vehicle is the mileage of the vehicle when the vehicle is last serviced.
Preferably, the establishing process of the pre-established seasonal ARIMA model includes:
before history n 1 The daily mileage of a vehicle of one month is input by a seasonal ARIMA (p, d, q) model, and a predicted post-history n is obtained 2 Daily mileage of a vehicle for a month;
modulating the seasonal ARIMA (p, d, q) model using grid search and using the predicted post-historic n 2 Acquiring an optimal seasonal ARIMA (p, d, q) model, namely a pre-established seasonal ARIMA model, from the daily mileage of the vehicles of the month;
wherein n=n 1 +n 2 N is the total month number of the history time, p is the regression coefficient, d is the difference coefficient, and q is the moving average coefficient.
Further, the post-historic n using the prediction 2 The daily mileage of a vehicle for a month obtains an optimal seasonal ARIMA (p, d, q) model comprising:
historical n using the prediction 2 Daily mileage and post-history n of a monthly vehicle 2 Acquiring AIC values of a seasonal ARIMA (p, d, q) model by using the mileage number of the vehicle every day of the month;
and selecting the seasonal ARIMA (p, d, q) model corresponding to the minimum AIC value as the optimal seasonal ARIMA (p, d, q) model.
Specifically, the post-historic n using the prediction 2 Daily mileage and post-history n of a monthly vehicle 2 The daily mileage of a vehicle for a month obtains the AIC value of a seasonal ARIMA (p, d, q) model, comprising:
the AIC values of the seasonal ARIMA (p, d, q) model are determined as follows:
in the above, k is [1, K ]]K is n after history 2 Total number of days of the month, ssr is the sum of squares of residuals;
wherein the residual square sum ssr is determined as follows:
in the above, a k For history of n 2 Number of mileage of vehicle on the k-th day of month, a k ' post-history of prediction n 2 Number of mileage of vehicle on the k-th day of the month.
Further, the second obtaining unit includes:
the third acquisition module is used for acquiring the driving mileage of the vehicle in a plurality of days in the future by taking the driving mileage of the vehicle in a plurality of days in the history as the input of a pre-established seasonal ARIMA model;
and the determining module is used for determining the remaining maintenance days of the vehicle by using the daily driving mileage of the vehicle and the remaining maintenance mileage of the vehicle in a plurality of days in the future.
Specifically, the determining module is configured to, when the remaining maintenance mileage L of the vehicle satisfies
When the vehicle is in a maintenance state, m is the remaining maintenance days of the vehicle;
wherein j is E [1, m]，l j The driving mileage of the vehicle on the m-th day of several days in the future.
The technical scheme provided by the embodiment of the application can comprise the following beneficial effects:
according to the technical scheme, the current equivalent mileage of the vehicle is obtained according to the pre-established deep neural network model, the current equivalent mileage of the vehicle is utilized to determine the remaining maintenance mileage of the vehicle, and the pre-established seasonal ARIMA model is utilized to obtain the remaining maintenance days of the vehicle according to the remaining maintenance mileage of the vehicle, so that the specific time of maintenance required by a vehicle owner can be accurately informed, and a user can reasonably arrange own time for maintenance;
according to the technical scheme, the historical weather data, the historical driving data of the vehicle and the historical maintenance data of the vehicle are utilized, so that the data dimension is enriched, and the obtained remaining maintenance days of the vehicle result is more objective and accurate.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
FIG. 1 is a block diagram illustrating a timing model-based vehicle intelligent maintenance model in accordance with an exemplary embodiment;
FIG. 2 is a flowchart illustrating a vehicle intelligent maintenance method based on a time series model, according to an exemplary embodiment.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.
FIG. 1 is a block diagram of a timing model-based vehicle smart maintenance model, as shown in FIG. 1, according to an exemplary embodiment, including:
the first acquisition unit is used for acquiring the equivalent mileage of the vehicle on the same day according to a pre-established deep neural network model;
a determining unit for determining a remaining maintenance mileage of the vehicle using a current day equivalent mileage of the vehicle;
and the second acquisition unit is used for acquiring the remaining maintenance days of the vehicle by utilizing a pre-established seasonal ARIMA model according to the remaining maintenance mileage of the vehicle.
Further, the establishing process of the pre-established deep neural network model includes:
and training by taking historical weather data as an input layer training sample of the deep neural network model and taking the weight of the influence of the historical weather on the vehicle as an output layer training sample of the deep neural network model to obtain the pre-established deep neural network model.
Further, the first acquisition unit includes:
the first acquisition module is used for acquiring the weight of the influence of the weather of the day between the last maintenance date of the vehicle and the current day on the vehicle by taking the weather data of the day between the last maintenance date of the vehicle and the current day as the input of the pre-established deep neural network model;
and the second acquisition module is used for acquiring the equivalent mileage of the vehicle on the same day by using the weight of the influence of the weather of the vehicle on the vehicle from the last maintenance date of the vehicle to the day.
For example, the date of the last maintenance of the automobile of the main armor is 1 month 1 day in 2019, and the date of the current day is 1 month 1 day in 2019, taking the weather data of each day between 1 month 1 day in 2019 and 1 month 4 day in 2019 as the input of the pre-established deep neural network model, and acquiring the weight of the influence of the weather of each day between 1 month 1 day in 2019 and 1 month 4 day in 2019 on the automobile; wherein, each day between 1.1.1.2019 and 4.1.1.2019 comprises 1.1.1.2019 and 4.1.1.2019.
Specifically, the second obtaining module is configured to determine a current equivalent mileage i of the vehicle according to the following formula:
in the above formula, i is [1, n ]]N is the date of the day, l' is the actual travel mileage of the vehicle when the date is i, and w i The weight of the influence of weather on the vehicle when the date is i; where i=1 is the date of the last maintenance of the vehicle.
Further, the determining unit is configured to determine a remaining maintenance mileage L of the vehicle according to the following formula:
L＝l 1 -(l-l 2 )
in the above, l 1 Is the maintenance cycle mileage of the vehicle, l is the equivalent mileage of the vehicle on the same day, l 2 The mileage of the vehicle is the mileage of the vehicle when the vehicle is maintained last time;
for example, the maintenance cycle mileage of the vehicle owner b is 10000 km, the equivalent mileage of the vehicle on the day is 31000 km, the mileage of the vehicle at the last maintenance of the vehicle is 25000 km, and the remaining maintenance mileage of the vehicle=10000- (31000-25000) =4000 km.
Further, the establishing process of the pre-established seasonal ARIMA model includes:
before history n 1 The daily mileage of a vehicle of one month is input by a seasonal ARIMA (p, d, q) model, and a predicted post-history n is obtained 2 Daily mileage of a vehicle for a month;
modulating the seasonal ARIMA (p, d, q) model using grid search and using the predicted post-historic n 2 Acquiring an optimal seasonal ARIMA (p, d, q) model, namely a pre-established seasonal ARIMA model, from the daily mileage of the vehicles of the month;
wherein n=n 1 +n 2 N is the total month number of the history time, p is the regression coefficient, d is the difference coefficient, and q is the moving average coefficient.
Specifically, the post-historic n using the prediction 2 The daily mileage of a vehicle for a month obtains an optimal seasonal ARIMA (p, d, q) model comprising:
historical n using the prediction 2 Daily mileage and post-history n of a monthly vehicle 2 Acquiring AIC values of a seasonal ARIMA (p, d, q) model by using the mileage number of the vehicle every day of the month;
and selecting the seasonal ARIMA (p, d, q) model corresponding to the minimum AIC value as the optimal seasonal ARIMA (p, d, q) model.
Specifically, the post-historic n using the prediction 2 Daily mileage and post-history n of a monthly vehicle 2 The daily mileage of a vehicle for a month obtains the AIC value of a seasonal ARIMA (p, d, q) model, comprising:
the AIC values of the seasonal ARIMA (p, d, q) model are determined as follows:
in the above, k is [1, K ]]K is n after history 2 Total number of days of the month, ssr is the sum of squares of residuals;
wherein the residual square sum ssr is determined as follows:
in the above, a k For history of n 2 Number of mileage of vehicle on the k-th day of month, a k ' post-history of prediction n 2 Number of mileage of vehicle on the k-th day of the month;
for example, taking the car of the car owner of the third party as an example, the date of the current day is 2019, 4, 1, the car owner of the third party buys the car in 2018, 4, 1, and starts to use the car in 2018, 4, 1, the total month number of the history time n=n 1 +n 2 =12, let n 1 ＝6，n 2 =6, 30 days a month, then n 1 180 days in one month, n 2 180 days in one month, n is the number after history 2 Total number of months k=180, K e [1,180 ]]。
Further, the second obtaining unit includes:
the third acquisition module is used for acquiring the driving mileage of the vehicle in a plurality of days in the future by taking the driving mileage of the vehicle in a plurality of days in the history as the input of a pre-established seasonal ARIMA model;
and the determining module is used for determining the remaining maintenance days of the vehicle by using the daily driving mileage of the vehicle and the remaining maintenance mileage of the vehicle in a plurality of days in the future.
Specifically, the determining module is configured to, when the remaining maintenance mileage L of the vehicle satisfies
When the vehicle is in a maintenance state, m is the remaining maintenance days of the vehicle;
wherein j is E [1, m]，l j The driving mileage of the vehicle on the m-th day of several days in the future.
According to the technical scheme provided by the invention, on one hand, the influence of weather data on driving conditions and historical driving mileage are considered, each user area is sufficiently differentiated, and users with excellent dimensions can be given corresponding rewards (for example, maintenance is carried out later than other users); on the other hand, the remaining maintenance days of the vehicle are predicted, so that the user can reasonably arrange own time for maintenance;
the historical driving mileage is considered, that is, the actual road condition, the driving environment, the driving behavior and the like are considered.
Fig. 2 is a flowchart illustrating a vehicle intelligent maintenance method based on a time series model according to an exemplary embodiment, and as shown in fig. 2, a vehicle intelligent maintenance method based on a time series model is used in a terminal, comprising the steps of:
101. acquiring the equivalent mileage of the vehicle on the same day according to a pre-established deep neural network model;
102. determining the remaining maintenance mileage of the vehicle by using the equivalent mileage of the vehicle on the same day;
103. and according to the remaining maintenance mileage of the vehicle, acquiring the remaining maintenance days of the vehicle by utilizing a pre-established seasonal ARIMA model.
Further, the establishing process of the pre-established deep neural network model includes:
and training by taking historical weather data as an input layer training sample of the deep neural network model and taking the weight of the influence of the historical weather on the vehicle as an output layer training sample of the deep neural network model to obtain the pre-established deep neural network model.
Further, the step 101 includes:
taking the weather data of each day from the last maintenance date of the vehicle to the current day as input of the pre-established deep neural network model, and acquiring the weight of the influence of the weather of each day from the last maintenance date of the vehicle to the current day on the vehicle;
and obtaining the equivalent mileage of the vehicle on the same day by using the weight of the influence of the weather of the vehicle on the vehicle from the last maintenance date of the vehicle to the day.
For example, the date of the last maintenance of the automobile of the main armor is 1 month 1 day in 2019, and the date of the current day is 1 month 1 day in 2019, taking the weather data of each day between 1 month 1 day in 2019 and 1 month 4 day in 2019 as the input of the pre-established deep neural network model, and acquiring the weight of the influence of the weather of each day between 1 month 1 day in 2019 and 1 month 4 day in 2019 on the automobile; wherein, each day between 1.1.1.2019 and 4.1.1.2019 comprises 1.1.1.2019 and 4.1.1.2019.
Specifically, the obtaining the equivalent mileage of the vehicle on the day by using the weight of the influence of the weather of the day between the last maintenance date of the vehicle and the current day on the vehicle includes:
the equivalent mileage of the vehicle on the day is determined as follows:
in the above formula, i is [1, n ]]N is the date of the day, l' is the actual travel mileage of the vehicle when the date is i, and w i For date iThe weight of the weather's impact on the vehicle; where i=1 is the date of the last maintenance of the vehicle.
Further, the step 102 after obtaining the equivalent mileage of the vehicle on the same day includes:
the remaining maintenance mileage L of the vehicle is determined as follows:
L＝l 1 -(l-l 2 )
in the above, l 1 Is the maintenance cycle mileage of the vehicle, l is the equivalent mileage of the vehicle on the same day, l 2 The mileage of the vehicle is the mileage of the vehicle when the vehicle is last serviced.
For example, the maintenance cycle mileage of the vehicle owner b is 10000 km, the equivalent mileage of the vehicle on the day is 31000 km, the mileage of the vehicle at the last maintenance of the vehicle is 25000 km, and the remaining maintenance mileage of the vehicle=10000- (31000-25000) =4000 km.
Further, the establishing process of the pre-established seasonal ARIMA model includes:
before history n 1 The daily mileage of a vehicle of one month is input by a seasonal ARIMA (p, d, q) model, and a predicted post-history n is obtained 2 Daily mileage of a vehicle for a month;
modulating the seasonal ARIMA (p, d, q) model using grid search and using the predicted post-historic n 2 Acquiring an optimal seasonal ARIMA (p, d, q) model, namely a pre-established seasonal ARIMA model, from the daily mileage of the vehicles of the month;
wherein n=n 1 +n 2 N is the total month number of the history time, p is the regression coefficient, d is the difference coefficient, and q is the moving average coefficient.
Specifically, the post-historic n using the prediction 2 The daily mileage of a vehicle for a month obtains an optimal seasonal ARIMA (p, d, q) model comprising:
historical n using the prediction 2 Daily mileage and post-history n of a monthly vehicle 2 Daily mileage of vehicle for monthAcquiring AIC values of a seasonal ARIMA (p, d, q) model;
and selecting the seasonal ARIMA (p, d, q) model corresponding to the minimum AIC value as the optimal seasonal ARIMA (p, d, q) model.
Specifically, the post-historic n using the prediction 2 Daily mileage and post-history n of a monthly vehicle 2 The daily mileage of a vehicle for a month obtains the AIC value of a seasonal ARIMA (p, d, q) model, comprising:
the AIC values of the seasonal ARIMA (p, d, q) model are determined as follows:
in the above, k is [1, K ]]K is n after history 2 Total number of days of the month, ssr is the sum of squares of residuals;
wherein the residual square sum ssr is determined as follows:
in the above, a k For history of n 2 Number of mileage of vehicle on the k-th day of month, a k ' post-history of prediction n 2 Number of mileage of vehicle on the k-th day of the month.
For example, taking the car of the car owner of the third party as an example, the date of the current day is 2019, 4, 1, the car owner of the third party buys the car in 2018, 4, 1, and starts to use the car in 2018, 4, 1, the total month number of the history time n=n 1 +n 2 =12, let n 1 ＝6，n 2 =6, 30 days a month, then n 1 180 days in one month, n 2 180 days in one month, n is the number after history 2 Total number of months k=180, K e [1,180 ]]。
Further, after determining the remaining maintenance mileage of the vehicle, the step 103 includes:
taking the driving mileage of the vehicle every day in a plurality of historical days as the input of a pre-established seasonal ARIMA model, and acquiring the driving mileage of the vehicle every day in a plurality of future days;
the remaining days of maintenance for the vehicle is determined using the driving range of the vehicle and the remaining maintenance range of the vehicle for each of several days in the future.
Specifically, the determining the remaining maintenance days of the vehicle by using the driving mileage of the vehicle and the remaining maintenance mileage of the vehicle every day in a plurality of days in the future includes:
when the remaining maintenance mileage L of the vehicle is satisfied
When the vehicle is in a maintenance state, m is the remaining maintenance days of the vehicle;
wherein j is E [1, m]，l j The driving mileage of the vehicle on the m-th day of several days in the future.
It is to be understood that the same or similar parts in the above embodiments may be referred to each other, and that in some embodiments, the same or similar parts in other embodiments may be referred to.
It should be noted that in the description of the present application, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Furthermore, in the description of the present application, unless otherwise indicated, the meaning of "plurality" means at least two.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.
Claims (7)
1. A vehicle smart maintenance model based on a time series model, the vehicle smart maintenance model comprising:
the first acquisition unit is used for acquiring the equivalent mileage of the vehicle on the same day according to a pre-established deep neural network model;
a determining unit for determining a remaining maintenance mileage of the vehicle using a current day equivalent mileage of the vehicle;
the second acquisition unit is used for acquiring the remaining maintenance days of the vehicle by utilizing a pre-established seasonal ARIMA model according to the remaining maintenance mileage of the vehicle;
the establishing process of the pre-established seasonal ARIMA model comprises the following steps:
before history n 1 The daily mileage of a vehicle of one month is input by a seasonal ARIMA (p, d, q) model, and a predicted post-history n is obtained 2 Daily mileage of a vehicle for a month;
modulating the seasonal ARIMA (p, d, q) model using grid search and using the predicted post-historic n 2 Acquiring an optimal seasonal ARIMA (p, d, q) model, namely a pre-established seasonal ARIMA model, from the daily mileage of the vehicles of the month;
wherein n=n 1 +n 2 N is the total month number of the history time, p is a regression coefficient, d is a difference coefficient, and q is a moving average coefficient;
the post-historic n using the prediction 2 The daily mileage of a vehicle for a month obtains an optimal seasonal ARIMA (p, d, q) model comprising:
using the predictionHistory of n 2 Daily mileage and post-history n of a monthly vehicle 2 Acquiring AIC values of a seasonal ARIMA (p, d, q) model by using the mileage number of the vehicle every day of the month;
selecting a seasonal ARIMA (p, d, q) model corresponding to the minimum AIC value as an optimal seasonal ARIMA (p, d, q) model;
the post-historic n using the prediction 2 Daily mileage and post-history n of a monthly vehicle 2 The daily mileage of a vehicle for a month obtains the AIC value of a seasonal ARIMA (p, d, q) model, comprising:
historical post n using predictions 2 Daily mileage and post-history n of a monthly vehicle 2 Acquiring AIC values of a seasonal ARIMA (p, d, q) model from daily mileage of a vehicle of a month;
the obtaining of AIC values for the seasonal ARIMA (p, d, q) model includes:
the AIC values of the seasonal ARIMA (p, d, q) model are determined as follows:
in the above, k is [1, K ]]K is n after history 2 Total number of days of the month, ssr is the sum of squares of residuals;
wherein the residual square sum ssr is determined as follows:
in the above, a k For history of n 2 Number of mileage of vehicle on the k-th day of month, a k ' post-history of prediction n 2 Number of mileage of vehicle on the k-th day of the month.
2. The vehicle smart maintenance model of claim 1, wherein the pre-established deep neural network model creation process includes:
and training by taking historical weather data as an input layer training sample of the deep neural network model and taking the weight of the influence of the historical weather on the vehicle as an output layer training sample of the deep neural network model to obtain the pre-established deep neural network model.
3. The vehicle smart maintenance model of claim 1, wherein the first acquisition unit includes:
the first acquisition module is used for acquiring the weight of the influence of the weather of the day between the last maintenance date of the vehicle and the current day on the vehicle by taking the weather data of the day between the last maintenance date of the vehicle and the current day as the input of the pre-established deep neural network model;
and the second acquisition module is used for acquiring the equivalent mileage of the vehicle on the same day by using the weight of the influence of the weather of the vehicle on the vehicle from the last maintenance date of the vehicle to the day.
4. A vehicle smart maintenance model according to claim 3, wherein the second acquisition module is adapted to determine the equivalent mileage of the vehicle/by:
in the above formula, i is [1, n ]]N is the date of the day, l' is the actual travel mileage of the vehicle when the date is i, and w i The weight of the influence of weather on the vehicle when the date is i; where i=1 is the date of the last maintenance of the vehicle.
5. The vehicle smart maintenance model according to claim 1, wherein the determining unit is configured to determine a remaining maintenance mileage L of the vehicle according to the following formula:
L＝l 1 -(l-l 2 )
in the above, l 1 Is the maintenance cycle mileage of the vehicle, l is the equivalent mileage of the vehicle on the same day, l 2 The mileage of the vehicle is the mileage of the vehicle when the vehicle is last serviced.
6. The vehicle smart maintenance model of claim 5, wherein the second acquisition unit includes:
the third acquisition module is used for acquiring the driving mileage of the vehicle in a plurality of days in the future by taking the driving mileage of the vehicle in a plurality of days in the history as the input of a pre-established seasonal ARIMA model;
and the determining module is used for determining the remaining maintenance days of the vehicle by using the daily driving mileage of the vehicle and the remaining maintenance mileage of the vehicle in a plurality of days in the future.
7. The vehicle smart maintenance model of claim 6, wherein the determination module is configured to, when a remaining maintenance mileage L of the vehicle satisfies
When in use;
wherein j is E [1, m]M is the remaining maintenance days of the vehicle, l j The travel mileage of the vehicle on the j th day of several days in the future.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910784276.6A CN110516823B (en) | 2019-08-23 | 2019-08-23 | Vehicle intelligent maintenance model based on time sequence model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910784276.6A CN110516823B (en) | 2019-08-23 | 2019-08-23 | Vehicle intelligent maintenance model based on time sequence model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110516823A CN110516823A (en) | 2019-11-29 |
| CN110516823B true CN110516823B (en) | 2023-06-27 |
Family
ID=68626441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910784276.6A Active CN110516823B (en) | 2019-08-23 | 2019-08-23 | Vehicle intelligent maintenance model based on time sequence model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110516823B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112785055B (en) * | 2021-01-18 | 2024-02-06 | 优必爱信息技术（北京）有限公司 | Method and equipment for predicting vehicle refueling date |
| CN113911051A (en) * | 2021-11-04 | 2022-01-11 | 艾尔卡(北京)科技有限公司 | Method and device for obtaining current driving mileage of vehicle and electronic equipment |
| CN115438811A (en) * | 2022-08-18 | 2022-12-06 | 合众新能源汽车有限公司 | Intelligent maintenance method and device for extended range vehicle, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105139476A (en) * | 2015-08-05 | 2015-12-09 | 武汉理工大学 | Mining area vehicle maintenance information prompting method |
| CN105922952A (en) * | 2016-05-31 | 2016-09-07 | 惠州华阳通用电子有限公司 | Vehicle maintenance reminding method and device |
| CN106515478A (en) * | 2016-10-27 | 2017-03-22 | 合肥工业大学 | Online prediction method and device for remaining mileage of electric automobile |
| WO2019018980A1 (en) * | 2017-07-24 | 2019-01-31 | Beijing Didi Infinity Technology And Development Co., Ltd. | Methods and systems for vehicle management |
| CN109711870A (en) * | 2018-12-13 | 2019-05-03 | 江苏中科瀚星数据科技有限公司 | A kind of prediction of residential block electric car charging load and configuration method |
-
2019
- 2019-08-23 CN CN201910784276.6A patent/CN110516823B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105139476A (en) * | 2015-08-05 | 2015-12-09 | 武汉理工大学 | Mining area vehicle maintenance information prompting method |
| CN105922952A (en) * | 2016-05-31 | 2016-09-07 | 惠州华阳通用电子有限公司 | Vehicle maintenance reminding method and device |
| CN106515478A (en) * | 2016-10-27 | 2017-03-22 | 合肥工业大学 | Online prediction method and device for remaining mileage of electric automobile |
| WO2019018980A1 (en) * | 2017-07-24 | 2019-01-31 | Beijing Didi Infinity Technology And Development Co., Ltd. | Methods and systems for vehicle management |
| CN109711870A (en) * | 2018-12-13 | 2019-05-03 | 江苏中科瀚星数据科技有限公司 | A kind of prediction of residential block electric car charging load and configuration method |
Non-Patent Citations (2)
| Title |
|---|
| 基于序列模式挖掘的公交车辆维修保养数据;高亮泉;《华南农业大学硕士论文》;20170414;正文第1-38页 * |
| 基于自回归求和滑动平均模型的;赖国书;《科学技术与工程》;20190228;第176-182页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110516823A (en) | 2019-11-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110516823B (en) | Vehicle intelligent maintenance model based on time sequence model | |
| US20230118340A1 (en) | Artificial intelligence-based systems and methods for vehicle operation | |
| CN108072381B (en) | Path planning method and device | |
| CN110415516B (en) | Urban traffic flow prediction method and medium based on graph convolution neural network | |
| CN103177570B (en) | Method for predicting traffic jam indexes for rush hours in morning and evening | |
| CN111613054B (en) | Multi-step traffic speed prediction method cooperatively considering space-time correlation and contribution difference | |
| CN109376935B (en) | Bus passenger flow time interval combined prediction method based on neural network | |
| Ben-Akiva et al. | Some estimation results of a simultaneous model of auto ownership and mode choice to work | |
| CN112071062B (en) | Driving time estimation method based on graph convolution network and graph attention network | |
| WO2006029022A2 (en) | Out-of-home advertising inventory ratings methods and systems | |
| CN110738523B (en) | Maintenance order quantity prediction method and device | |
| US20240054321A1 (en) | Traffic prediction | |
| CN112579900B (en) | Second-hand vehicle replacement information recommendation method, system and equipment | |
| CN108573600B (en) | Driver behavior induction and local traffic flow optimization method | |
| CN110490365B (en) | Method for predicting network car booking order quantity based on multi-source data fusion | |
| CN111862583B (en) | Traffic flow prediction method and device | |
| WO2019049141A1 (en) | A system and method for using knowledge gathered by a vehicle | |
| CN111121803B (en) | Method and device for acquiring common stop points of road | |
| Treboux et al. | A predictive data-driven model for traffic-jams forecasting in smart santader city-scale testbed | |
| CN116453541A (en) | Sound source intensity prediction method and device, electronic equipment and storage medium | |
| CN114418606B (en) | Network vehicle order demand prediction method based on space-time convolution network | |
| CN116386317A (en) | Traffic intersection traffic flow prediction method and device | |
| CN115080388A (en) | Simulation test scene generation method for automatic driving system | |
| JP2022002101A (en) | Operation evaluation model generation device, operation evaluation model generation method, and program | |
| JP7103237B2 (en) | Flow rate prediction device and flow rate prediction method |
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 |