CN117114352B - Vehicle maintenance method, device, computer equipment and storage medium - Google Patents
Vehicle maintenance method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117114352B CN117114352B CN202311194719.9A CN202311194719A CN117114352B CN 117114352 B CN117114352 B CN 117114352B CN 202311194719 A CN202311194719 A CN 202311194719A CN 117114352 B CN117114352 B CN 117114352B
- Authority
- CN
- China
- Prior art keywords
- target
- state
- prediction
- vehicle
- usage
- 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 112
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000004590 computer program Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000012549 training Methods 0.000 description 4
- 230000004913 activation Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000009022 nonlinear effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Traffic Control Systems (AREA)
Abstract
The application relates to a vehicle maintenance method, a vehicle maintenance device, a computer device and a storage medium. The method comprises the following steps: acquiring state characteristic data and usage characteristic data of a target vehicle in a historical time period; acquiring a fault prediction model, inputting state characteristic data and using the characteristic data into the fault prediction model to perform fault prediction to obtain a fault prediction result of the target vehicle, wherein the fault prediction result is used for representing the probability of occurrence of faults of the target vehicle in a preset time period; and determining the target time for maintaining the target vehicle according to the fault prediction result, and maintaining the target vehicle according to the target time. The method combines the vehicle state condition and the vehicle service condition in the prediction result, can timely find and solve potential faults and damages of the vehicle, reduces the fault rate and the off-line time of the vehicle, improves the maintenance efficiency and timeliness of the shared vehicle, and improves the reliability and the availability of the shared vehicle.
Description
Technical Field
The present disclosure relates to the field of sharing technologies, and in particular, to a vehicle maintenance method, apparatus, computer device, and storage medium.
Background
With the development of sharing technology, sharing bicycles have become one of the important vehicles in modern cities. However, due to frequent use and uncontrolled environmental conditions, the sharing bicycle often suffers from various faults and damages, affecting user experience and operating efficiency.
The existing vehicle maintenance method monitors the running data and the environmental conditions of the vehicle through sensors, identifies potential faults and damages and then maintains the vehicle, thereby realizing maintenance on the shared bicycle. However, the existing vehicle maintenance method only focuses on the current state of the vehicle, and cannot predict the future faults of the vehicle, and the timeliness and maintenance efficiency of the vehicle maintenance are not high.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a vehicle maintenance method, apparatus, computer device, and storage medium that can improve timeliness and maintenance efficiency of maintenance.
In a first aspect, the present application provides a method of vehicle maintenance. The method comprises the following steps:
acquiring state characteristic data and usage characteristic data of a target vehicle in a historical time period;
acquiring a fault prediction model, inputting state characteristic data and using the characteristic data into the fault prediction model to perform fault prediction to obtain a fault prediction result of the target vehicle, wherein the fault prediction result is used for representing the probability of occurrence of faults of the target vehicle in a preset time period;
And determining the target time for maintaining the target vehicle according to the fault prediction result, and maintaining the target vehicle according to the target time.
In one embodiment, the fault prediction model includes a state prediction model and a use prediction model, the state feature data and the use feature data are input into the fault prediction model to perform fault prediction, and a fault prediction result of the target vehicle is obtained, including:
inputting the state characteristic data into a state prediction model to obtain a state prediction result of the target vehicle in a preset time period;
inputting the usage characteristic data into a usage prediction model to obtain a usage prediction result of the target vehicle in a preset time period;
and fusing the state prediction result and the use prediction result to obtain a fault prediction result.
In one embodiment, fusing the state prediction result and the use prediction result to obtain a failure prediction result includes:
and combining elements with the same positions as those of the state prediction result and the use prediction result to obtain a fault prediction result.
In one embodiment, the state feature data includes continuous feature data and discrete feature data, and the state feature data is input into a state prediction model to obtain a state prediction result of the target vehicle in a preset time period, including:
Inputting the continuous characteristic data into a continuous variable state prediction model to obtain continuous variable prediction state characteristics of the target vehicle in a preset time period, and inputting the discrete characteristic data into a discrete variable state prediction model to obtain discrete variable prediction state characteristics of the target vehicle in the preset time period;
and splicing the continuous variable prediction state characteristics and the discrete variable prediction state characteristics to obtain a state prediction result.
In one embodiment, the discrete feature data comprises first order discrete feature data and second order discrete feature data, wherein the second order discrete feature data is obtained by cross-combining the first order discrete feature data.
In one embodiment, the feature dimension of the usage feature data includes at least one of a number of uses, a time of use, a distance of use, and a use rating; inputting the usage characteristic data into a usage prediction model to obtain a usage prediction result of the target vehicle in a preset time period, wherein the usage prediction result comprises the following steps:
determining target usage feature data in the usage feature data of the target vehicle according to the target feature dimension, acquiring a target usage prediction model corresponding to the target usage feature data, inputting the target usage feature into the target usage prediction model, and obtaining a usage prediction result of the target vehicle in a preset time period.
In one embodiment, maintaining a target vehicle according to a target time includes:
acquiring a target maintenance quantity upper limit of target time and the quantity of planned maintenance vehicles, and determining candidate maintenance vehicles according to the target maintenance quantity upper limit and the quantity of planned maintenance vehicles;
if the target vehicle is among the candidate maintenance vehicles, the target vehicle is maintained at the target time.
In a second aspect, the present application also provides a vehicle maintenance device. The device comprises:
the feature extraction module is used for acquiring state feature data and usage feature data of the target vehicle in a historical time period;
the prediction module is used for acquiring a fault prediction model, inputting state characteristic data and using the characteristic data into the fault prediction model for performing fault prediction to obtain a fault prediction result of the target vehicle, wherein the fault prediction result is used for representing the probability of the fault of the target vehicle in a preset time period;
and the vehicle maintenance module is used for determining the target time for maintaining the target vehicle according to the fault prediction result and maintaining the target vehicle according to the target time.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor executes the computer program to realize the following steps:
Acquiring state characteristic data and usage characteristic data of a target vehicle in a historical time period;
acquiring a fault prediction model, inputting state characteristic data and using the characteristic data into the fault prediction model to perform fault prediction to obtain a fault prediction result of the target vehicle, wherein the fault prediction result is used for representing the probability of occurrence of faults of the target vehicle in a preset time period;
and determining the target time for maintaining the target vehicle according to the fault prediction result, and maintaining the target vehicle according to the target time.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
acquiring state characteristic data and usage characteristic data of a target vehicle in a historical time period;
acquiring a fault prediction model, inputting state characteristic data and using the characteristic data into the fault prediction model to perform fault prediction to obtain a fault prediction result of the target vehicle, wherein the fault prediction result is used for representing the probability of occurrence of faults of the target vehicle in a preset time period;
and determining the target time for maintaining the target vehicle according to the fault prediction result, and maintaining the target vehicle according to the target time.
The vehicle maintenance method, the vehicle maintenance device, the computer equipment and the storage medium acquire state characteristic data and use characteristic data of the target vehicle in a historical time period; acquiring a fault prediction model, inputting state characteristic data and using the characteristic data into the fault prediction model to perform fault prediction to obtain a fault prediction result of the target vehicle, wherein the fault prediction result is used for representing the probability of occurrence of faults of the target vehicle in a preset time period; and determining the target time for maintaining the target vehicle according to the fault prediction result, and maintaining the target vehicle according to the target time. According to the method and the device, when the vehicle is maintained, the state characteristics and the use characteristics of the vehicle are predicted, the state conditions and the use conditions of the vehicle are combined in the fault prediction result, potential faults and damages of the vehicle can be timely found and solved, the fault rate and the off-line time of the vehicle are reduced, the maintenance efficiency and timeliness of the shared vehicle are improved, the reliability and the availability of the shared vehicle are improved, the user experience is also improved, and in addition, the maintenance cost and the operation cost of the vehicle are also reduced.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for a person having ordinary skill in the art.
FIG. 1 is an application environment diagram of a vehicle maintenance method in one embodiment;
FIG. 2 is a flow diagram of a method of vehicle maintenance in one embodiment;
FIG. 3 is a flow diagram of vehicle fault prediction in one embodiment;
FIG. 4 is a flow chart of a method of vehicle maintenance in another embodiment;
FIG. 5 is a block diagram of a vehicle maintenance device in one embodiment;
fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The vehicle maintenance method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process, such as data of a shared vehicle, where the shared vehicle may be a shared bicycle, a shared electric bicycle, a shared automobile. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server.
The server 104 acquires status feature data and usage feature data of the target vehicle in a history period; acquiring a fault prediction model, inputting state characteristic data and using the characteristic data into the fault prediction model to perform fault prediction to obtain a fault prediction result of the target vehicle, wherein the fault prediction result is used for representing the probability of occurrence of faults of the target vehicle in a preset time period; and determining the target time for maintaining the target vehicle according to the fault prediction result, and maintaining the target vehicle according to the target time. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In one embodiment, as shown in fig. 2, a vehicle maintenance method is provided, and the method is applied to the server 104 in fig. 1 for illustration, and includes the following steps 202 to 206. Wherein:
step 202, acquiring state characteristic data and usage characteristic data of a target vehicle in a historical time period.
Wherein the target vehicle represents a vehicle for which maintenance time needs to be determined. The historical time period represents a historical time period before the current time, and the historical time period can be one day, one week, one month or one year, etc. according to application requirements. The state characteristic data is characteristic data for characterizing the state of the vehicle, by which the state, performance and behavior of the vehicle can be analyzed. The usage characteristic data are characteristic data used for representing the usage condition of the vehicle, the behavior of the vehicle can be predicted through the usage characteristic data, and the usage condition of the vehicle in a preset time period is determined. The present embodiment determines a maintenance policy of the target vehicle by analyzing data of the target vehicle. In general, the usage characteristic data also belongs to status characteristic data, and the usage status of the vehicle can be obtained by analyzing the usage characteristic data.
For example, the acquired status feature data dimension may include vehicle attributes, vehicle usage, vehicle evaluations, and city attributes, where the vehicle attributes may include vehicle model number, vehicle delivery days, time interval of vehicle from last repair, whether the vehicle is a depreciated vehicle, etc.; the vehicle usage may include a total number of vehicle usage, a number of times of daily use of the vehicle, an average number of times of daily use of the vehicle in a city, a number of times the vehicle is scanned, a number of times of invalid scanning of the vehicle, an average history of vehicle travel, an average time of vehicle travel, and the like, over a time range; the vehicle rating may include a rating of the vehicle, a rating of the vehicle quality by the user, etc.; the city attributes may include the area of the city, the altitude of the city, whether the city is coastal, the number of various POIs (Point of Interest, points of interest) in the city, the average air temperature, average rainfall, etc. of the city over a time frame, wherein the area of the city may be eastern, north-south-China, etc. The interest point represents a specific position or place and is usually related to daily activities, trips and interests of people, the interest point can be commercial facilities, cultural places, tourist attractions, schools, hospitals and the like, and the interest point belongs to a densely populated area, and the utilization rate of vehicles nearby the interest point is high, so that the failure rate of the vehicles is related to the interest point. The feature dimension of the state feature data in the embodiment further comprises city attribute features on the basis of common feature dimensions, so that the state of the vehicle can be predicted more accurately.
For example, the original data such as all driving data of the target vehicle in the historical time period, vehicle maintenance information corresponding to the historical time period, city weather information and the like may be obtained first, and sample extraction is performed on the original data, where the extracted sample includes a positive sample and a negative sample, the positive sample is used to represent vehicle information generating faults in a preset time interval, the positive sample data includes a fault tag used to represent fault time, the fault tag may be a difference between the current time and the fault time, for example, the vehicle generates faults on the day before the current time, at this time, the difference between the current time and the fault time is 1, and the fault tag of the sample data is 1; the negative sample is used for indicating vehicle information that no fault is generated in a preset time interval, and the negative sample data also comprises a fault tag, and the fault tag in the negative sample data is 0 because each vehicle in the negative sample data does not generate a fault. And extracting the characteristics of all sample data to obtain state characteristic data and using the characteristic data.
And 204, acquiring a fault prediction model, inputting state characteristic data and using the characteristic data into the fault prediction model to perform fault prediction, and obtaining a fault prediction result of the target vehicle, wherein the fault prediction result is used for representing the probability of the target vehicle in a preset time period.
The fault prediction model is used for carrying out fault prediction on the target vehicle, the state characteristic data and the use characteristic data are used as input characteristics for training the fault prediction model, and through learning of the state characteristic data and the use characteristic data in a historical time period, the model can respectively capture the association between the state characteristic data and the use characteristic data and the target variable, so that a fault prediction result is obtained.
Illustratively, the failure prediction model of the present embodiment is constructed as a classification prediction model, and by analyzing and processing the characteristics of each dimension of the sample data, failure prediction results representing the failure probability occurring in a preset period of time are output. For example, the fault prediction model may be trained as an 11-output classification model, when the fault signature of the fault prediction result is 0, it indicates that no fault occurs for 10 days in the future, when the predicted fault signature is 1, it indicates that a fault occurs for 1 day in the future, and so on, when the predicted fault signature is 10, it indicates that a fault occurs for 10 days in the future in the vehicle.
And 206, determining the target time for maintaining the target vehicle according to the fault prediction result, and maintaining the target vehicle according to the target time.
The target time is determined according to the fault prediction result and is used for representing the parameter of the maintenance time of the target vehicle. Based on the failure tag in the failure prediction result, the time when the target vehicle may fail in a time zone may be determined.
Taking the foregoing example as an example, if the failure flag is 1, it indicates that the target vehicle will fail for 1 day in the future, and the target time is 1 day in the future. The vehicle maintenance personnel need to maintain the target vehicle according to the target time. The vehicle maintenance personnel can receive the vehicle maintenance strategy sent by the server through the terminal and carry out vehicle maintenance according to the received vehicle maintenance strategy. The terminal can be a smart phone, a notebook computer, a tablet personal computer, a smart watch, a smart bracelet, an Internet of things device and the like.
In the vehicle maintenance method, state characteristic data and usage characteristic data of a target vehicle in a historical time period are acquired; acquiring a fault prediction model, inputting state characteristic data and using the characteristic data into the fault prediction model to perform fault prediction to obtain a fault prediction result of the target vehicle, wherein the fault prediction result is used for representing the probability of occurrence of faults of the target vehicle in a preset time period; and determining the target time for maintaining the target vehicle according to the fault prediction result, and maintaining the target vehicle according to the target time. According to the method and the device, when the vehicle is maintained, the state characteristics and the use characteristics of the vehicle are predicted, the state conditions and the use conditions of the vehicle are combined in the fault prediction result, potential faults and damages of the vehicle can be timely found and solved, the fault rate and the off-line time of the vehicle are reduced, the maintenance efficiency and timeliness of the shared vehicle are improved, the reliability and the availability of the shared vehicle are improved, the user experience is also improved, and in addition, the maintenance cost and the operation cost of the vehicle are also reduced.
In one embodiment, the fault prediction model includes a state prediction model and a use prediction model, and as shown in fig. 3, inputting the state feature data and the use feature data into the fault prediction model to perform fault prediction, and obtaining a fault prediction result of the target vehicle includes the following steps 302 to 306. Wherein:
and 302, inputting the state characteristic data into a state prediction model to obtain a state prediction result of the target vehicle in a preset time period.
In this embodiment, two prediction models are respectively constructed to predict, the state of the vehicle is predicted by the state prediction model, and the use condition of the vehicle is predicted by using the prediction model. When predicting the state of the vehicle, the state characteristic data is input into a state prediction model, wherein the state characteristic data is all state data of the vehicle attribute, the vehicle use, the vehicle evaluation and the city attribute extracted according to the sample data.
In the use process of the vehicle, the service lives of the vehicles with different city attributes are different, for example, the probability of corrosion and the like of the vehicle is high in coastal areas due to high air humidity, and the starting influence on the vehicle is large in northwest areas due to possible dust and sand weather.
For example, all state feature data may be predicted by one state prediction model, and state data may be distinguished to achieve higher prediction accuracy. The state prediction model of the embodiment is constructed based on DNN (Deep Neural Network ), and features are extracted and classified through the constructed state prediction model, compared with the traditional machine learning method, DNN can automatically discover and utilize high-level abstract features in data, so that more accurate and complex pattern recognition and prediction tasks are realized. The DNN model is typically composed of multiple hidden layers, each containing multiple neurons, each connected to all neurons of the previous layer, with signaling and conversion by weights and biases. In the training process, the weight and bias are continuously optimized through a back propagation algorithm and a gradient descent method, so that the loss function of the model on training data reaches the minimum value.
And step 304, inputting the usage characteristic data into a usage prediction model to obtain a usage prediction result of the target vehicle in a preset time period.
In the prediction of the vehicle use condition, the use characteristic data may be input into the use prediction model. Based on the time characteristics of the usage characteristic data, a relationship between the usage state change of the vehicle and the vehicle failure can be obtained.
Illustratively, the use of the predictive model may be built based on a recurrent neural network (Recurrent Neural Network, RNN), which is a neural network model for processing sequence data. Compared with the traditional feedforward neural network which only considers the current input when processing a single input sample, the RNN transfers the past hidden state information to the current time step by introducing a circular connection, thereby effectively processing the data with the time sequence dependency relationship. The basic structure of the RNN includes one or more loop layers, each time step having a corresponding hidden state. At each time step, the RNN receives the current input and the hidden state at the previous time, outputs the hidden state at the current time after conversion of the activation function, and transmits the hidden state to the next time step. This loop connection enables the RNN to memorize previous information and use this information for calculation and prediction in the current time step.
When in prediction, the vehicle use characteristic data of the historical time interval is input into a use prediction model, so that a use prediction result of the target vehicle in a preset time period can be obtained. It should be noted that, the size of the usage feature data of the input usage prediction model is required to be the same as the size of the state feature data of the input state prediction model, so as to facilitate the subsequent fusion of the prediction results.
And 306, fusing the state prediction result and the use prediction result to obtain a fault prediction result.
And fusing the state prediction result and the use prediction result to obtain a fault prediction result which comprises vehicle state prediction data and vehicle use prediction data. The fault prediction result is not only predicted according to the use state of the vehicle, but also combined with the use state of the vehicle again, and the prediction accuracy is high.
In one embodiment, fusing the state prediction result and the use prediction result to obtain a failure prediction result includes: and combining elements with the same positions as those of the state prediction result and the use prediction result to obtain a fault prediction result.
Illustratively, the method of fusing the state prediction result and the use prediction result is to combine elements with the same positions in the state prediction result and the use prediction result, and finally obtain the fault prediction result. The combination method can be adding, multiplying, averaging or processing by functions and the like. Assuming that the state prediction result is a state prediction vector of B x 2N and the use prediction result is a use prediction vector of B x N, the fusion manner of this embodiment is to add the same elements of the state prediction vector and the use prediction vector to obtain a failure prediction result of B x N, where B represents the number of samples and N is set to 512.
Further, for the 11 classification of the foregoing example, the failure prediction result is further passed through a 2n x 11 linear layer, and the finally output prediction classification is obtained through, for example, a softmax activation function, where the obtained data dimension is B x, which respectively represents the probability of each failure label.
In one embodiment, the state characteristic data includes continuous characteristic data and discrete characteristic data, the state characteristic data is input into a state prediction model to obtain a state prediction result of the target vehicle in a preset time period, and the method includes: inputting the continuous characteristic data into a continuous variable state prediction model to obtain continuous variable prediction state characteristics of the target vehicle in a preset time period, and inputting the discrete characteristic data into a discrete variable state prediction model to obtain discrete variable prediction state characteristics of the target vehicle in the preset time period; and splicing the continuous variable prediction state characteristics and the discrete variable prediction state characteristics to obtain a state prediction result.
Wherein, since the status characteristic data includes both continuous characteristic data expressed as continuous values, such as the altitude of a city, the number of times of use of a vehicle, etc.; also included are discrete feature data represented as discrete values, such as whether the city is coastal, etc. According to the state characteristic data, the state of the target vehicle is predicted through the continuous characteristic data and the discrete characteristic data respectively. And then splicing the continuous variable prediction state characteristics obtained through continuous characteristic data prediction and the discrete variable prediction state characteristics obtained through discrete characteristic data prediction to obtain a state prediction result.
The continuous feature data is input into a continuous variable state prediction model, when the data dimension of the input continuous feature data is high, the feature data can be reduced to be operated through embedding, then feature extraction is carried out through a plurality of layers of feedforward neural networks and relu activation functions, finally the continuous variable prediction state features in B x N dimensions are output, and a deep hidden feature relation can be found from the continuous feature data through the continuous variable state prediction model, wherein the continuous variable state prediction model can be a continuous variable encoder.
And inputting the discrete feature data into a discrete variable state prediction model, and acquiring a relation between the discrete feature data through a linear model because the discrete feature data is a discrete value, and outputting the discrete variable prediction state features of B x N dimensions by the discrete variable state prediction model finally, wherein the discrete variable state prediction model can be a discrete variable encoder, and the discrete feature data with obvious correlation can be modeled through the discrete variable state prediction model.
In one embodiment, the discrete feature data comprises first order discrete feature data and second order discrete feature data, wherein the second order discrete feature data is derived by cross-combining the first order discrete feature data.
In order to improve the prediction accuracy of the discrete variable state prediction model and capture interaction between discrete features in the prediction of discrete feature data, a nonlinear effect is added. The discrete feature data includes, in addition to first-order discrete feature data, that is, original discrete feature data, second-order discrete feature data obtained by cross-combining the first-order discrete feature data. The discrete feature data input to the discrete variable state prediction model includes first order discrete feature data and second order discrete feature data.
For example, cross-combining of feature data may be performed by computing discrete feature data comprising first order discrete feature data and second order discrete feature data, where it is necessary to determine which combinations are best suited to solve the problem based on domain knowledge, data understanding, and experimental verification, and care is taken to avoid introducing excessive redundancy or extraneous features.
In one embodiment, the feature dimension of the usage feature data includes at least one of a number of uses, a time of use, a distance of use, and a use rating; inputting the usage characteristic data into a usage prediction model to obtain a usage prediction result of the target vehicle in a preset time period, wherein the usage prediction result comprises the following steps: determining target usage feature data in the usage feature data of the target vehicle according to the target feature dimension, acquiring a target usage prediction model corresponding to the target usage feature data, inputting the target usage feature into the target usage prediction model, and obtaining a usage prediction result of the target vehicle in a preset time period.
The feature data used in the prediction model may be feature data of a single feature dimension, or may be feature data of a plurality of feature dimensions, and the embodiment has no limitation on the feature dimensions of the feature data used in the vehicle, and the more feature dimensions of the feature data used in the vehicle, the higher the accuracy of the prediction under the allowable range of the prediction efficiency.
When the prediction model is used for predicting the vehicle use condition, the corresponding target use prediction model is determined according to the feature dimension of the use feature data, and the corresponding target use feature data is output to the target use prediction model for predicting the vehicle use condition.
For example, the target feature data of the target usage prediction model is the historical number of times of vehicle usage per month (30 days), the size of the input usage feature data is bxm, M is 30, B is the number of samples for each training, the input usage feature data is consistent with the state feature data input by the state prediction model, and the data size of the last hidden layer output by the target usage prediction model is B x n, n is 512. The data size of the target output by the prediction model is required to be consistent with the data size of the output by the state prediction model, so that the output results of the two models are fused, and a fault prediction result is obtained.
In one embodiment, maintaining a target vehicle according to a target time includes: acquiring a target maintenance quantity upper limit of target time and the quantity of planned maintenance vehicles, and determining candidate maintenance vehicles according to the target maintenance quantity upper limit and the quantity of planned maintenance vehicles; if the target vehicle is among the candidate maintenance vehicles, the target vehicle is maintained at the target time.
The method comprises the steps of determining target time according to fault labels in fault prediction results, obtaining expected fault occurrence time of each vehicle according to the sequence of the target time, obtaining priority of vehicle fault occurrence according to the expected fault occurrence time of each vehicle, and enabling vehicle maintenance personnel to schedule maintenance on vehicles with high fault occurrence priority. The present embodiment selects a vehicle with a higher failure occurrence priority for priority maintenance according to the target time on the basis of the existing vehicle maintenance schedule.
For example, if the target time is determined to be one day according to the fault tag, the upper limit of the target maintenance number of the vehicle and the planned maintenance vehicle number which is determined to be arranged and needs to be maintained by the vehicle maintainer after one day are obtained, and the number of candidate maintenance vehicles which can be subjected to maintenance operation in the current day is obtained according to the difference between the planned maintenance vehicle number and the upper limit of the target maintenance number. The predicted faulty vehicle matching the number of maintenance vehicle candidates is selected for maintenance from among the predicted faulty vehicles whose target time is one day later, that is, if the target vehicle is among the maintenance vehicle candidates of the target time, the maintenance of the target vehicle may be performed at the target time. If maintenance of the target vehicle cannot be satisfied on the same day due to a large vehicle maintenance pressure, the maintenance operation of the target vehicle may be prioritized at any time after the target time.
In one embodiment, if the maintenance personnel of the vehicle find that the target vehicle has no fault as a result of the maintenance of the target vehicle, the maintenance schedule of the target vehicle may be canceled and vehicle replacement selected in sequence among the candidate maintenance vehicles.
In one exemplary embodiment, as shown in FIG. 4, a vehicle maintenance method is provided, comprising the following steps 402 through 4XX, wherein:
in step 402, status feature data and usage feature data of the target vehicle over a historical period of time are acquired.
Firstly, acquiring original data of a target vehicle in a historical time period, and extracting a data sample from the original data. And obtaining state characteristic data and using characteristic data through characteristic extraction of the data samples.
And step 404, inputting the state characteristic data into a state prediction model to obtain a state prediction result of the target vehicle in a preset time period.
The state characteristic data comprises continuous characteristic data and discrete characteristic data, prediction is carried out through a continuous variable state prediction model and a discrete variable state prediction model respectively, and prediction results of the continuous variable state prediction model and the discrete variable state prediction model are spliced to obtain a state prediction result.
And step 406, inputting the usage characteristic data into a usage prediction model to obtain a usage prediction result of the target vehicle in a preset time period.
The prediction results are kept the same size as the state prediction results to facilitate subsequent fusion operations.
Step 408, fusing the state prediction result and the use prediction result to obtain a failure prediction result.
And step 410, maintaining the target vehicle according to the fault prediction result.
The fault prediction result comprises a fault label which indicates the probability of the fault of the vehicle, a maintenance strategy for the target vehicle is determined according to the fault label, and the target vehicle is maintained according to the obtained maintenance strategy.
According to the vehicle maintenance method, potential faults and damages are found and solved in time through predictive maintenance, the fault rate and the outage time of the vehicle are reduced, and the reliability and the usability of the sharing bicycle are improved. Secondly, the embodiment predicts the failure probability of the vehicle and maintains the failure probability in advance, so that further expansion of the failure of the vehicle and serious damage of the vehicle are avoided, and the maintenance cost and the maintenance period are reduced. After the faults and damage conditions of the sharing vehicles are reduced, the satisfaction degree and loyalty of users to the sharing vehicles are improved, and the user experience is improved.
It should be understood that, although the steps in the flowcharts related to the above-described embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a vehicle maintenance device for realizing the vehicle maintenance method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in one or more embodiments of the vehicle maintenance device provided below may refer to the limitation of the vehicle maintenance method hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 5, there is provided a vehicle maintenance apparatus including: a feature extraction module 502, a prediction module 504, and a vehicle maintenance module 506, wherein:
a feature extraction module 502, configured to obtain status feature data and usage feature data of a target vehicle in a historical period;
the prediction module 504 is configured to obtain a fault prediction model, input state feature data and use feature data into the fault prediction model to perform fault prediction, and obtain a fault prediction result of the target vehicle, where the fault prediction result is used to characterize a probability that the target vehicle fails within a preset time period;
the vehicle maintenance module 506 is configured to determine a target time for maintaining the target vehicle according to the failure prediction result, and maintain the target vehicle according to the target time.
In one embodiment, the fault prediction model includes a state prediction model and the prediction model is used, the prediction module 504 further being configured to: inputting the state characteristic data into a state prediction model to obtain a state prediction result of the target vehicle in a preset time period; inputting the usage characteristic data into a usage prediction model to obtain a usage prediction result of the target vehicle in a preset time period; and fusing the state prediction result and the use prediction result to obtain a fault prediction result.
In one embodiment, the prediction module 504 is further configured to: and combining elements with the same positions as those of the state prediction result and the use prediction result to obtain a fault prediction result.
In one embodiment, the prediction module 504 is further configured to: inputting the continuous characteristic data into a continuous variable state prediction model to obtain continuous variable prediction state characteristics of the target vehicle in a preset time period, and inputting the discrete characteristic data into a discrete variable state prediction model to obtain discrete variable prediction state characteristics of the target vehicle in the preset time period; and splicing the continuous variable prediction state characteristics and the discrete variable prediction state characteristics to obtain a state prediction result.
In one embodiment, the discrete feature data of the prediction module 504 includes first order discrete feature data and second order discrete feature data, wherein the second order discrete feature data is obtained by cross-combining the first order discrete feature data.
In one embodiment, the feature dimensions of the usage feature data in the prediction module 504 include at least one of a number of uses, a time of use, a distance of use, and a usage assessment; the prediction module 504 is further configured to: determining target usage feature data in the usage feature data of the target vehicle according to the target feature dimension, acquiring a target usage prediction model corresponding to the target usage feature data, inputting the target usage feature into the target usage prediction model, and obtaining a usage prediction result of the target vehicle in a preset time period.
In one embodiment, the vehicle maintenance module 506 is further configured to: acquiring a target maintenance quantity upper limit of target time and the quantity of planned maintenance vehicles, and determining candidate maintenance vehicles according to the target maintenance quantity upper limit and the quantity of planned maintenance vehicles; if the target vehicle is among the candidate maintenance vehicles, the target vehicle is maintained at the target time.
The respective modules in the above-described vehicle maintenance apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing vehicle history data and vehicle maintenance data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a vehicle maintenance method.
It will be appreciated by those skilled in the art that the structure shown in fig. 6 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the method embodiments described above.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
The user information (including, but not limited to, vehicle information of the user, personal information of the user, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples represent only a few embodiments of the present application, which are described in more detail and are not thereby to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A method of vehicle maintenance, the method comprising:
acquiring state characteristic data and usage characteristic data of a target vehicle in a historical time period;
acquiring a fault prediction model, inputting the state characteristic data and the usage characteristic data into the fault prediction model to perform fault prediction to obtain a fault prediction result of the target vehicle, wherein the fault prediction result is used for representing the probability of occurrence of faults of the target vehicle in a preset time period;
Determining a target time for maintaining the target vehicle according to the fault prediction result, and maintaining the target vehicle according to the target time;
the fault prediction model comprises a state prediction model and a use prediction model, the state characteristic data and the use characteristic data are input into the fault prediction model to perform fault prediction, and a fault prediction result of the target vehicle is obtained, and the fault prediction method comprises the following steps:
inputting the state characteristic data into the state prediction model to obtain a state prediction result of the target vehicle in the preset time period;
inputting the usage characteristic data into the usage prediction model to obtain a usage prediction result of the target vehicle in the preset time period;
fusing the state prediction result and the use prediction result to obtain the fault prediction result;
the step of fusing the state prediction result and the use prediction result to obtain the fault prediction result includes:
combining the elements with the same positions of the state prediction result and the use prediction result to obtain the fault prediction result;
the state characteristic data comprises continuous characteristic data and discrete characteristic data, the state characteristic data is input into the state prediction model to obtain a state prediction result of the target vehicle in the preset time period, and the method comprises the following steps:
Inputting the continuous characteristic data into a continuous variable state prediction model to obtain continuous variable prediction state characteristics of the target vehicle in the preset time period, and inputting the discrete characteristic data into a discrete variable state prediction model to obtain discrete variable prediction state characteristics of the target vehicle in the preset time period;
and splicing the continuous variable prediction state characteristics and the discrete variable prediction state characteristics to obtain the state prediction result.
2. The method of claim 1, wherein the discrete feature data comprises first order discrete feature data and second order discrete feature data, wherein the second order discrete feature data is derived by cross-combining the first order discrete feature data.
3. The method of claim 1, wherein the feature dimension of the usage feature data comprises at least one of a number of uses, a time of use, a distance of use, and a rating of use; the step of inputting the usage characteristic data into the usage prediction model to obtain a usage prediction result of the target vehicle in the preset time period, including:
determining target usage feature data in the usage feature data of the target vehicle according to the target feature dimension, acquiring a target usage prediction model corresponding to the target usage feature data, and inputting the target usage feature into the target usage prediction model to obtain a usage prediction result of the target vehicle in the preset time period.
4. The method of claim 1, wherein the maintaining the target vehicle according to the target time comprises:
acquiring a target maintenance quantity upper limit of target time and the quantity of planned maintenance vehicles, and determining candidate maintenance vehicles according to the target maintenance quantity upper limit and the quantity of planned maintenance vehicles;
and if the target vehicle is in the candidate maintenance vehicle, maintaining the target vehicle at the target time.
5. A vehicle maintenance device, characterized in that the device comprises:
the feature extraction module is used for acquiring state feature data and usage feature data of the target vehicle in a historical time period;
the prediction module is used for acquiring a fault prediction model, inputting the state characteristic data and the using characteristic data into the fault prediction model for fault prediction to obtain a fault prediction result of the target vehicle, wherein the fault prediction result is used for representing the probability of the fault of the target vehicle in a preset time period;
the fault prediction model includes a state prediction model and a use prediction model, the prediction module further configured to: inputting the state characteristic data into a state prediction model to obtain a state prediction result of the target vehicle in a preset time period; inputting the usage characteristic data into a usage prediction model to obtain a usage prediction result of the target vehicle in a preset time period; fusing the state prediction result and the use prediction result to obtain a fault prediction result;
The prediction module is also used for: combining elements with the same positions as those of the state prediction result and the use prediction result to obtain a fault prediction result;
the prediction module is also used for: inputting the continuous characteristic data into a continuous variable state prediction model to obtain continuous variable prediction state characteristics of the target vehicle in a preset time period, and inputting the discrete characteristic data into a discrete variable state prediction model to obtain discrete variable prediction state characteristics of the target vehicle in the preset time period; splicing the continuous variable prediction state characteristics and the discrete variable prediction state characteristics to obtain a state prediction result;
and the vehicle maintenance module is used for determining the target time for maintaining the target vehicle according to the fault prediction result and maintaining the target vehicle according to the target time.
6. The apparatus of claim 5, wherein the discrete feature data in the prediction module comprises first order discrete feature data and second order discrete feature data, wherein the second order discrete feature data is derived by cross-combining the first order discrete feature data.
7. The apparatus of claim 5, wherein the feature dimension of the usage feature data in the prediction module comprises at least one of a number of uses, a time of use, a distance of use, and a use rating; the prediction module is also used for: determining target usage feature data in the usage feature data of the target vehicle according to the target feature dimension, acquiring a target usage prediction model corresponding to the target usage feature data, inputting the target usage feature into the target usage prediction model, and obtaining a usage prediction result of the target vehicle in a preset time period.
8. The apparatus of claim 5, wherein the vehicle maintenance module is further to: acquiring a target maintenance quantity upper limit of target time and the quantity of planned maintenance vehicles, and determining candidate maintenance vehicles according to the target maintenance quantity upper limit and the quantity of planned maintenance vehicles; if the target vehicle is among the candidate maintenance vehicles, the target vehicle is maintained at the target time.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 4 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311194719.9A CN117114352B (en) | 2023-09-15 | 2023-09-15 | Vehicle maintenance method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311194719.9A CN117114352B (en) | 2023-09-15 | 2023-09-15 | Vehicle maintenance method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117114352A CN117114352A (en) | 2023-11-24 |
| CN117114352B true CN117114352B (en) | 2024-04-09 |
Family
ID=88802175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311194719.9A Active CN117114352B (en) | 2023-09-15 | 2023-09-15 | Vehicle maintenance method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117114352B (en) |
Citations (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104834579A (en) * | 2014-02-10 | 2015-08-12 | 富士施乐株式会社 | Failure predictive system and failure predictive apparatus |
| CN108228378A (en) * | 2018-01-05 | 2018-06-29 | 中车青岛四方机车车辆股份有限公司 | The data processing method and device of train groups failure predication |
| CN109489584A (en) * | 2018-12-03 | 2019-03-19 | 大连维德轨道装备有限公司 | A kind of tunnel clearance detection system and tunnel clearance recognition methods based on 3D technology |
| CN109634828A (en) * | 2018-12-17 | 2019-04-16 | 浪潮电子信息产业股份有限公司 | Failure prediction method, device, equipment and storage medium |
| CN109656239A (en) * | 2019-03-07 | 2019-04-19 | 长沙瑞纬电气有限公司 | A kind of rail locomotive network control system method for diagnosing faults and its diagnostic device |
| CN109828857A (en) * | 2018-12-29 | 2019-05-31 | 百度在线网络技术（北京）有限公司 | Vehicle trouble reason localization method, device, equipment and storage medium |
| CN110135629A (en) * | 2019-04-24 | 2019-08-16 | 中车青岛四方机车车辆股份有限公司 | A kind of prediction technique and device of train mean time between failures (MTBF) |
| CN110197288A (en) * | 2019-05-30 | 2019-09-03 | 重庆大学 | The remaining life prediction technique of equipment under the influence of failure |
| CN110232452A (en) * | 2019-06-12 | 2019-09-13 | 中国神华能源股份有限公司 | Repair method and system based on track car team state of the art |
| CN110263944A (en) * | 2019-05-21 | 2019-09-20 | 中国石油大学(华东) | A kind of multivariable failure prediction method and device |
| CN110288046A (en) * | 2019-07-02 | 2019-09-27 | 南京恩瑞特实业有限公司 | A kind of failure prediction method based on wavelet neural network and Hidden Markov Model |
| CN110422189A (en) * | 2019-08-27 | 2019-11-08 | 石家庄国祥运输设备有限公司 | The on-line prediction method of compressor fault in rail vehicle air conditioner group |
| CN110428170A (en) * | 2019-08-01 | 2019-11-08 | 优必爱信息技术（北京）有限公司 | A kind of automobile parts demand dynamic prediction method, system and storage medium |
| CN110457786A (en) * | 2019-05-06 | 2019-11-15 | 浙江工业大学 | Ship unloaders correlation rule fault prediction model method based on depth confidence network |
| CN110503217A (en) * | 2019-08-29 | 2019-11-26 | 新誉轨道交通科技有限公司 | A kind of slow leakage failure prediction technique of air conditioner coolant, device, equipment and system |
| CN110542867A (en) * | 2019-08-05 | 2019-12-06 | 燕山大学 | Battery health state evaluation method and device and storage medium |
| CN110633821A (en) * | 2018-10-29 | 2019-12-31 | 成都云科新能汽车技术有限公司 | Intelligent fleet management system and method |
| CN110796487A (en) * | 2019-10-18 | 2020-02-14 | 上海钧正网络科技有限公司 | Quantity prediction method, device, computer equipment and storage medium |
| CN110850847A (en) * | 2019-11-25 | 2020-02-28 | 北京锦鸿希电信息技术股份有限公司 | Method and device for monitoring faults of train-mounted equipment |
| CN111114519A (en) * | 2020-01-03 | 2020-05-08 | 中国铁路郑州局集团有限公司科学技术研究所 | Railway vehicle brake fault prediction method and health management system |
| CN111259737A (en) * | 2020-01-08 | 2020-06-09 | 科大讯飞股份有限公司 | Method and device for predicting vehicle steering wheel fault, electronic equipment and storage medium |
| CN111325257A (en) * | 2020-02-14 | 2020-06-23 | 逸驾智能科技有限公司 | Method and device for analyzing vehicle faults |
| CN111624908A (en) * | 2020-05-18 | 2020-09-04 | 武汉理工大学 | Intelligent refrigerator car vehicle-mounted data acquisition terminal system based on Internet of things technology |
| CN111661057A (en) * | 2019-03-07 | 2020-09-15 | 上海博泰悦臻网络技术服务有限公司 | Vehicle, vehicle equipment and vehicle lane changing road condition prompting method |
| CN111783856A (en) * | 2020-06-18 | 2020-10-16 | 杭州未名信科科技有限公司 | Equipment fault auxiliary diagnosis method and system for manufacturing industry |
| CN111881980A (en) * | 2020-07-29 | 2020-11-03 | 上海钧正网络科技有限公司 | Vehicle fault detection method and device, computer equipment and storage medium |
| CN111913458A (en) * | 2020-08-28 | 2020-11-10 | 华中科技大学 | Workshop control method and system based on deep learning |
| CN113371034A (en) * | 2021-06-11 | 2021-09-10 | 虞萍 | Blocking system and method based on train brake management |
| CN115936201A (en) * | 2022-11-25 | 2023-04-07 | 重庆长安新能源汽车科技有限公司 | Motor fault early warning method and device, vehicle and storage medium |
| CN116010882A (en) * | 2023-01-16 | 2023-04-25 | 重庆长安新能源汽车科技有限公司 | Vehicle maintenance center recommendation method and device, electronic equipment and storage medium |
| CN116128133A (en) * | 2023-02-01 | 2023-05-16 | 一汽解放汽车有限公司 | Method, device, computer equipment and storage medium for predicting vehicle faults |
| CN116186270A (en) * | 2023-03-31 | 2023-05-30 | 重庆长安汽车股份有限公司 | Vehicle fault cause diagnosis method, device, equipment and storage medium |
| CN116184981A (en) * | 2022-12-30 | 2023-05-30 | 东风商用车有限公司 | Accurate maintenance method and diagnosis system based on whole vehicle |
| CN116186106A (en) * | 2022-12-16 | 2023-05-30 | 国能铁路装备有限责任公司 | Railway wagon fault diagnosis method, device and equipment |
| CN116304620A (en) * | 2023-02-27 | 2023-06-23 | 中国第一汽车股份有限公司 | Electronic and electrical appliance fault prediction method and system based on deep learning and data mining |
| CN116384961A (en) * | 2023-02-27 | 2023-07-04 | 中国第一汽车股份有限公司 | Predictive application method and system based on vehicle electronic and electric appliance fault prediction model |
| CN116401549A (en) * | 2023-04-07 | 2023-07-07 | 中国第一汽车股份有限公司 | Vehicle track prediction model training method, device, equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8131456B2 (en) * | 2008-09-23 | 2012-03-06 | Honeywell International Inc. | Vehicle management system |
| US20180307231A1 (en) * | 2017-04-19 | 2018-10-25 | 4D Tech Solutions, Inc. | Intelligent electronic speed controller (iesc) |
| US11263835B2 (en) * | 2017-10-27 | 2022-03-01 | The Boeing Company | Vehicle fault detection system and method utilizing graphically converted temporal data |
| US10497185B2 (en) * | 2017-11-28 | 2019-12-03 | The Boeing Company | Apparatus and method for vehicle maintenance scheduling and fault monitoring |
| US11338940B2 (en) * | 2019-05-08 | 2022-05-24 | The Boeing Company | Predictive part maintenance |
-
2023
- 2023-09-15 CN CN202311194719.9A patent/CN117114352B/en active Active
Patent Citations (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104834579A (en) * | 2014-02-10 | 2015-08-12 | 富士施乐株式会社 | Failure predictive system and failure predictive apparatus |
| CN108228378A (en) * | 2018-01-05 | 2018-06-29 | 中车青岛四方机车车辆股份有限公司 | The data processing method and device of train groups failure predication |
| CN110633821A (en) * | 2018-10-29 | 2019-12-31 | 成都云科新能汽车技术有限公司 | Intelligent fleet management system and method |
| CN109489584A (en) * | 2018-12-03 | 2019-03-19 | 大连维德轨道装备有限公司 | A kind of tunnel clearance detection system and tunnel clearance recognition methods based on 3D technology |
| CN109634828A (en) * | 2018-12-17 | 2019-04-16 | 浪潮电子信息产业股份有限公司 | Failure prediction method, device, equipment and storage medium |
| CN109828857A (en) * | 2018-12-29 | 2019-05-31 | 百度在线网络技术（北京）有限公司 | Vehicle trouble reason localization method, device, equipment and storage medium |
| CN109656239A (en) * | 2019-03-07 | 2019-04-19 | 长沙瑞纬电气有限公司 | A kind of rail locomotive network control system method for diagnosing faults and its diagnostic device |
| CN111661057A (en) * | 2019-03-07 | 2020-09-15 | 上海博泰悦臻网络技术服务有限公司 | Vehicle, vehicle equipment and vehicle lane changing road condition prompting method |
| CN110135629A (en) * | 2019-04-24 | 2019-08-16 | 中车青岛四方机车车辆股份有限公司 | A kind of prediction technique and device of train mean time between failures (MTBF) |
| CN110457786A (en) * | 2019-05-06 | 2019-11-15 | 浙江工业大学 | Ship unloaders correlation rule fault prediction model method based on depth confidence network |
| CN110263944A (en) * | 2019-05-21 | 2019-09-20 | 中国石油大学(华东) | A kind of multivariable failure prediction method and device |
| CN110197288A (en) * | 2019-05-30 | 2019-09-03 | 重庆大学 | The remaining life prediction technique of equipment under the influence of failure |
| CN110232452A (en) * | 2019-06-12 | 2019-09-13 | 中国神华能源股份有限公司 | Repair method and system based on track car team state of the art |
| CN110288046A (en) * | 2019-07-02 | 2019-09-27 | 南京恩瑞特实业有限公司 | A kind of failure prediction method based on wavelet neural network and Hidden Markov Model |
| CN110428170A (en) * | 2019-08-01 | 2019-11-08 | 优必爱信息技术（北京）有限公司 | A kind of automobile parts demand dynamic prediction method, system and storage medium |
| CN110542867A (en) * | 2019-08-05 | 2019-12-06 | 燕山大学 | Battery health state evaluation method and device and storage medium |
| CN110422189A (en) * | 2019-08-27 | 2019-11-08 | 石家庄国祥运输设备有限公司 | The on-line prediction method of compressor fault in rail vehicle air conditioner group |
| CN110503217A (en) * | 2019-08-29 | 2019-11-26 | 新誉轨道交通科技有限公司 | A kind of slow leakage failure prediction technique of air conditioner coolant, device, equipment and system |
| CN110796487A (en) * | 2019-10-18 | 2020-02-14 | 上海钧正网络科技有限公司 | Quantity prediction method, device, computer equipment and storage medium |
| CN110850847A (en) * | 2019-11-25 | 2020-02-28 | 北京锦鸿希电信息技术股份有限公司 | Method and device for monitoring faults of train-mounted equipment |
| CN111114519A (en) * | 2020-01-03 | 2020-05-08 | 中国铁路郑州局集团有限公司科学技术研究所 | Railway vehicle brake fault prediction method and health management system |
| CN111259737A (en) * | 2020-01-08 | 2020-06-09 | 科大讯飞股份有限公司 | Method and device for predicting vehicle steering wheel fault, electronic equipment and storage medium |
| CN111325257A (en) * | 2020-02-14 | 2020-06-23 | 逸驾智能科技有限公司 | Method and device for analyzing vehicle faults |
| CN111624908A (en) * | 2020-05-18 | 2020-09-04 | 武汉理工大学 | Intelligent refrigerator car vehicle-mounted data acquisition terminal system based on Internet of things technology |
| CN111783856A (en) * | 2020-06-18 | 2020-10-16 | 杭州未名信科科技有限公司 | Equipment fault auxiliary diagnosis method and system for manufacturing industry |
| CN111881980A (en) * | 2020-07-29 | 2020-11-03 | 上海钧正网络科技有限公司 | Vehicle fault detection method and device, computer equipment and storage medium |
| CN111913458A (en) * | 2020-08-28 | 2020-11-10 | 华中科技大学 | Workshop control method and system based on deep learning |
| CN113371034A (en) * | 2021-06-11 | 2021-09-10 | 虞萍 | Blocking system and method based on train brake management |
| CN115936201A (en) * | 2022-11-25 | 2023-04-07 | 重庆长安新能源汽车科技有限公司 | Motor fault early warning method and device, vehicle and storage medium |
| CN116186106A (en) * | 2022-12-16 | 2023-05-30 | 国能铁路装备有限责任公司 | Railway wagon fault diagnosis method, device and equipment |
| CN116184981A (en) * | 2022-12-30 | 2023-05-30 | 东风商用车有限公司 | Accurate maintenance method and diagnosis system based on whole vehicle |
| CN116010882A (en) * | 2023-01-16 | 2023-04-25 | 重庆长安新能源汽车科技有限公司 | Vehicle maintenance center recommendation method and device, electronic equipment and storage medium |
| CN116128133A (en) * | 2023-02-01 | 2023-05-16 | 一汽解放汽车有限公司 | Method, device, computer equipment and storage medium for predicting vehicle faults |
| CN116304620A (en) * | 2023-02-27 | 2023-06-23 | 中国第一汽车股份有限公司 | Electronic and electrical appliance fault prediction method and system based on deep learning and data mining |
| CN116384961A (en) * | 2023-02-27 | 2023-07-04 | 中国第一汽车股份有限公司 | Predictive application method and system based on vehicle electronic and electric appliance fault prediction model |
| CN116186270A (en) * | 2023-03-31 | 2023-05-30 | 重庆长安汽车股份有限公司 | Vehicle fault cause diagnosis method, device, equipment and storage medium |
| CN116401549A (en) * | 2023-04-07 | 2023-07-07 | 中国第一汽车股份有限公司 | Vehicle track prediction model training method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117114352A (en) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yuan et al. | A survey of traffic prediction: from spatio-temporal data to intelligent transportation | |
| Zhou et al. | Predicting multi-step citywide passenger demands using attention-based neural networks | |
| Jiang et al. | DeepCrowd: A deep model for large-scale citywide crowd density and flow prediction | |
| Yu et al. | Prediction of highway tunnel pavement performance based on digital twin and multiple time series stacking | |
| CN114971748B (en) | Prediction data generation method, model training method, computer device, and storage medium | |
| CN112508265A (en) | Time and activity multi-task prediction method and system for business process management | |
| Sarkar et al. | Effective urban structure inference from traffic flow dynamics | |
| Xiao et al. | Understanding urban area attractiveness based on private car trajectory data using a deep learning approach | |
| Jiang et al. | Bi‐GRCN: A Spatio‐Temporal Traffic Flow Prediction Model Based on Graph Neural Network | |
| US11488083B2 (en) | Risk failure prediction for line assets | |
| US20230258461A1 (en) | Interactive analytical framework for multimodal transportation | |
| Ling et al. | STHAN: Transportation demand forecasting with compound spatio-temporal relationships | |
| Arisekola et al. | Digital twins for asset management: Social network analysis-based review | |
| Rohilla et al. | An Empirical Framework for Recommendation-based Location Services Using Deep Learning | |
| Liu et al. | Exploiting intra-and inter-region relations for sales prediction via graph convolutional network | |
| US10783287B2 (en) | Employing natural language processing to facilitate geospatial analysis | |
| CN117114352B (en) | Vehicle maintenance method, device, computer equipment and storage medium | |
| Hu et al. | An attention-mechanism-based traffic flow prediction scheme for smart city | |
| CN116127312A (en) | Emergency plan determining method, device, computer equipment and storage medium | |
| Suhartono et al. | Hybrid Machine Learning for Forecasting and Monitoring Air Pollution in Surabaya | |
| Singh et al. | Vehicle telematics: an internet of things and big data approach | |
| Shen et al. | Long-term multivariate time series forecasting in data centers based on multi-factor separation evolutionary spatial–temporal graph neural networks | |
| Qureshi et al. | A comparative analysis of traditional SARIMA and machine learning models for CPI data modelling in Pakistan | |
| CN112418260A (en) | Model training method, information prompting method, device, equipment and medium | |
| Su et al. | Deep learning-based real-time failure detection of storage devices |
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 |