CN111738286A - Fault determination and model training method, device, equipment and storage medium thereof - Google Patents
Fault determination and model training method, device, equipment and storage medium thereof Download PDFInfo
- Publication number
- CN111738286A CN111738286A CN202010187453.5A CN202010187453A CN111738286A CN 111738286 A CN111738286 A CN 111738286A CN 202010187453 A CN202010187453 A CN 202010187453A CN 111738286 A CN111738286 A CN 111738286A
- Authority
- CN
- China
- Prior art keywords
- fault
- sample data
- vehicle
- target sample
- model
- 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.)
- Pending
Links
- 238000012549 training Methods 0.000 title claims abstract description 100
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000004590 computer program Methods 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 4
- 230000000875 corresponding effect Effects 0.000 description 24
- 238000001514 detection method Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 238000013145 classification model Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 125000004122 cyclic group Chemical group 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a fault judgment and model training method, a fault judgment and model training device, equipment and a storage medium, wherein the fault judgment model training method comprises the following steps: obtaining original sample data of a plurality of vehicles with reported fault information; selecting a preset amount of target sample data from the original sample data; marking a real fault label for the target sample data according to a determination result of whether the vehicle corresponding to the target sample data is a real fault vehicle; and training according to the target sample data and the real fault label to obtain a fault judgment model. The failure judgment cost is reduced by only selecting part of samples to determine whether the corresponding vehicle is a real failure vehicle; the accuracy of fault determination is improved by training according to the real fault label.
Description
Technical Field
The embodiment of the invention relates to the technical field of machine learning, in particular to a fault judgment and model training method, a fault judgment and model training device, equipment and a storage medium.
Background
An Automated Guided Vehicle (AGV), also commonly referred to as an AGV cart, is a transport Vehicle equipped with an electromagnetic or optical automatic guide device, capable of traveling along a predetermined guide path, having safety protection and various transfer functions, and is applicable as a transfer robot to an unmanned cabin.
Currently, AGV carts often report various failures in operation, such as derailment, navigation sensor interruption, or left and right servo error. Of these reported failures, there is a substantial percentage that is actually caused not by the failure of the AGV itself but by external causes such as irregularities in field operations, for example, due to the presence of foreign objects on the site. Therefore, the AGV that actually has the fault needs to be found out from the AGV that reports the fault, so as to perform subsequent detection and maintenance on the AGV.
The conventional AGV fault judgment method is to judge whether the AGV has a fault or not through a classification model. In the process of implementing the invention, the inventor finds that at least the following technical problems exist in the prior art: in the process of training the classification model, if all AGV trolleys with reported faults are used as real fault trolleys to train the classification model, the model obtained by training is easy to judge the trolleys without self faults as fault trolleys, and the judgment accuracy rate is low; if all AGV trolleys with reported faults are subjected to vehicle dismantling detection so as to train the classification model according to real fault trolleys, the workload of vehicle dismantling detection in the model training process can be increased, time and labor are consumed, and the fault judgment cost is high.
Disclosure of Invention
The embodiment of the invention provides a fault judgment method, a fault judgment device, a fault judgment model training method, a fault judgment device, equipment and a storage medium, which are used for improving the fault judgment accuracy and reducing the fault judgment cost.
In a first aspect, an embodiment of the present invention provides a method for training a fault determination model, including:
obtaining original sample data of a plurality of vehicles with reported fault information;
selecting a preset amount of target sample data from the original sample data;
marking a real fault label for the target sample data according to a determination result of whether the vehicle corresponding to the target sample data is a real fault vehicle;
and training according to the target sample data and the real fault label to obtain a fault judgment model.
In a second aspect, an embodiment of the present invention provides a fault determination method, including:
receiving vehicle data of reported faults;
and inputting the vehicle data with the reported fault into a fault judgment model obtained by training based on the training method provided by any embodiment of the invention, and outputting to obtain a judgment result.
In a third aspect, an embodiment of the present invention provides a fault determination model training apparatus, including:
the sampling module is used for acquiring original sample data of a plurality of vehicles with reported fault information;
the target sample selecting module is used for selecting a preset amount of target sample data from the original sample data;
the real fault marking module is used for marking a real fault label for the target sample data according to a determination result of whether the vehicle corresponding to the target sample data is a real fault vehicle;
and the training module is used for obtaining a fault judgment model according to the target sample data and the real fault label training.
In a fourth aspect, an embodiment of the present invention provides a fault determination apparatus, including:
the data receiving module is used for acquiring vehicle data of the vehicle reporting the fault;
and the judging module is used for inputting the vehicle data into a fault judging model trained on the training method of any one of claims 1-5 and determining whether the vehicle has a fault according to the output of the fault judging model.
In a fifth aspect, an embodiment of the present invention provides a terminal device, including:
one or more processors;
a memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors implement the fault determination model training method according to any embodiment of the present invention, or the fault determination method according to any embodiment of the present invention.
In a sixth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a fault determination model training method according to any embodiment of the present invention or a fault determination method according to any embodiment of the present invention.
The embodiment of the invention provides a fault judgment and model training method, a fault judgment and model training device, equipment and a storage medium, wherein the fault judgment model training method comprises the following steps: the fault judgment model training device acquires original sample data of a plurality of vehicles with reported fault information; selecting target sample data with preset quantity from original sample data; marking a real fault label for the target sample data according to a determination result of whether the vehicle corresponding to the target sample data is a real fault vehicle; and training according to the target sample data and the real fault label to obtain a fault judgment model. The failure judgment cost is reduced by only selecting part of samples to determine whether the corresponding vehicle is a real failure vehicle; the accuracy of fault judgment is improved by training according to the real fault label.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below of the drawings required for the embodiments or the technical solutions in the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flowchart illustrating a method for training a fault determination model according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for training a fault determination model according to a second embodiment of the present invention;
fig. 3 is a flowchart illustrating a fault determination method according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram illustrating a fault determination model training apparatus according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram illustrating a fault determination device according to a fifth embodiment of the present invention;
fig. 6 shows a schematic diagram of a hardware structure of a terminal device according to a sixth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described through embodiments with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. In the following embodiments, optional features and examples are provided in each embodiment, and various features described in the embodiments may be combined to form a plurality of alternatives, and each numbered embodiment should not be regarded as only one technical solution.
Example one
Fig. 1 shows a flowchart of a fault determination model training method according to an embodiment of the present invention, and the fault determination model training method according to the embodiment of the present invention is applicable to a situation of training a fault determination model, for example, a situation of training an AGV cart fault determination model. The method may be performed by a fault determination model training apparatus (which may be referred to simply as a training apparatus) implemented in software and/or hardware, preferably configured in an electronic device, for example, in a server of a fault determination platform. As shown in fig. 1, the method for training a fault determination model provided in the embodiment of the present invention includes the following steps:
s110, obtaining original sample data of a plurality of vehicles with reported fault information.
In the embodiment of the invention, the training device acquires a plurality of vehicle original sample data of the reported fault information, specifically, the vehicle original sample data of the reported fault in a preset warehouse, a preset vehicle type and a preset time period, and the vehicle original sample data of the normal operation are acquired. Specifically, the preset warehouse may be a logistics warehouse in which vehicles operate, the preset vehicle types may be different generations or different models of the vehicles, and the preset time period may be set according to factors such as an original sample data acquisition speed in an actual scene and/or the number of vehicles with expected reporting failures in the original sample data, for example, for original sample data acquisition of an AGV in the logistics warehouse, and the preset time period may be one month.
Optionally, the vehicle is an automated guided vehicle, AGV.
Compared with other vehicles, the AGV has the advantages that the condition that the reported fault is not the fault of the AGV, but the situation that the operation environment of the logistics warehouse is not standard and the false alarm is caused is easier to occur, and the AGV is more necessary to carry out fault judgment model training so as to judge whether the AGV which reports the fault is the real fault or not. For original sample data acquired by the AGV, the data type of the original sample data is a characteristic variable that can reflect whether the AGV fails, and the data type may include current, voltage, and/or motor parameters, for example. The original sample data types collected for other vehicles are also characteristic variables which can reflect whether the vehicles are in failure, and are not limited to current, voltage and/or motor parameters. Furthermore, the number of types of original sample data may affect the number of original samples required to some extent, the greater the number of original samples required when the number of types is greater, e.g. the number of original samples required may be at least 10 times the number of types.
And S120, selecting a preset amount of target sample data from the original sample data.
In the embodiment of the invention, the importance degrees of each original sample data to the training of the fault determination model are different, for example, the vehicle fault can be directly determined according to some sample data which are obviously abnormal in the original sample data, and the data have small effect on the determination of parameters in the fault determination model. By selecting a preset number of target sample data from the original sample data, namely selecting partial sample data which has a great effect on determining parameters in the fault judgment model, the vehicle-dismantling detection is further performed on the sample data, so that the problem of high vehicle-dismantling cost caused by vehicle-dismantling detection on all samples is solved.
Optionally, selecting a preset number of target sample data from the original sample data includes: training according to original sample data to obtain a preliminary fault judgment model, and obtaining fault probability corresponding to the original sample data according to the preliminary fault judgment model; and selecting a preset amount of target sample data from the original sample data based on the fault probability and the maximum entropy strategy of the fault probability.
The models of the preliminary fault determination model and the final fault determination model may both be classification models, and the types of the preliminary fault determination model and the final fault determination model may be the same or different. The specific type of the classification model is, for example, a discriminant analysis model, an SVM model, a logistic model, a decision tree model, or the like.
The initial fault judgment model is obtained by training according to original sample data, the training device marks original sample data of a vehicle with a fault reported in the original sample data as a fault type, marks the original sample data of the vehicle which normally runs as a non-fault type, and fits a classification model of a preset type based on a marking result and the original sample data to obtain the initial fault judgment model. Based on the preliminary fault judgment model, the fault probability corresponding to each original sample data can be reversely obtained, and the fault probability can be a decimal between [0 and 1 ]. Target sample data is selected based on the fault probability and the maximum entropy strategy of the fault probability, namely the target sample data with the fault probability close to the limit probability for judging whether the fault occurs is selected, and whether the fault occurs is least determined in the fault judging process of the vehicle corresponding to the sample data. The preset number may be positively correlated to the number of original samples, and when the number of original samples is large, the large preset number may be set accordingly. By selecting partial sample data which is least determined whether the partial sample data is in fault in the judging process, further vehicle dismantling detection is carried out on the partial sample data, and judging model training is carried out according to the vehicle dismantling result and the partial sample data, the judging accuracy of the model training can be improved.
S130, marking a real fault label for the target sample data according to a determination result whether the vehicle corresponding to the target sample data is a real fault vehicle.
In the embodiment of the invention, after partial sample data (namely target sample data) which has a large function of determining parameters in the fault determination model is selected from all original sample data, only the vehicle corresponding to the partial sample data needs to be disassembled manually so as to determine whether the vehicle has a real fault. If the vehicle corresponding to the target sample data is a real fault vehicle, marking the target sample data with a fault label; and if the vehicle corresponding to the target sample data is a non-fault vehicle, marking the target sample data with a non-fault label. By means of vehicle dismantling detection on a small number of vehicles, the judging effect of the trained fault judging model can be optimal, the manual vehicle dismantling cost is reduced, and the fault judging accuracy is improved.
And S140, training according to the target sample data and the real fault label to obtain a fault judgment model.
In the embodiment of the invention, the training device fits the classification model of the preset type according to the target sample data corresponding to the marked fault label and the marked non-fault label to obtain the final fault judgment model, so that the judgment accuracy of the fault judgment model is improved.
According to the fault judgment model training method provided by the embodiment of the invention, a training device acquires original sample data of a plurality of vehicles with reported fault information; selecting target sample data with preset quantity from original sample data; marking a real fault label for the target sample data according to a determination result of whether the vehicle corresponding to the target sample data is a real fault vehicle; and training according to the target sample data and the real fault label to obtain a fault judgment model. The failure judgment cost is reduced by only selecting part of samples to determine whether the corresponding vehicle is a real failure vehicle; the accuracy of fault determination is improved by training according to the real fault label.
Example two
In this embodiment, on the basis of the above embodiment, the target sample selection step is optimized, so that a part of target sample data in the original sample, which is most blurred in fault determination, can be selected, and targeted vehicle removal detection is performed on the selected target sample data to determine whether a fault is true, so that the accuracy of a fault determination model trained based on the target sample data and the true vehicle removal result is higher. The present embodiment is the same inventive concept as the fault determination and the model training method thereof proposed in the above embodiments, and reference may be made to the above embodiments for technical details which are not described in detail in the present embodiment.
Fig. 2 shows a flowchart of a fault determination model training method according to a second embodiment of the present invention. Referring to fig. 2, the method for training the fault determination model provided in the embodiment of the present invention includes:
s210, obtaining original sample data of a plurality of vehicles with reported fault information;
s220, training according to original sample data to obtain a preliminary fault judgment model, and obtaining a fault probability corresponding to the original sample data according to the preliminary fault judgment model;
s230, determining at least one target sample data from the original sample data based on the fault probability and the fault probability maximum entropy strategy;
s240, removing target sample data from the original sample data, retraining according to the original sample data from which the target sample data are removed to obtain an updated preliminary fault judgment model, and obtaining the target sample data again according to the updated preliminary fault judgment model until the number of the target sample data reaches a preset number;
s250, marking a real fault label for the target sample data according to a determination result of whether the vehicle corresponding to the target sample data is a real fault vehicle;
and S260, training according to the target sample data and the real fault label to obtain a fault judgment model.
In the embodiment of the invention, after at least one target sample data is determined, the training device performs a cyclic operation of target sample data selection, specifically, the determined at least one target sample data is removed from the original sample data, and then retraining is performed according to the original sample data from which the target sample data is removed to obtain an updated preliminary fault judgment model; and obtaining the fault probability of the existing original sample data again according to the updated preliminary fault judgment model, and determining at least one target sample data from the existing original sample data again based on the fault probability and the maximum entropy strategy of the fault probability until the number of the target sample data reaches the preset number after cyclic processing. Target sample data with a large function of determining parameters in the fault determination model are selected in a cyclic mode through a gradual learning mode, and vehicle dismantling detection is further performed on the sample data, so that the problem of high vehicle dismantling cost caused by vehicle dismantling detection on all samples is solved. Meanwhile, a fault judgment model trained on target original data and real fault labels thereof can achieve a better judgment effect in the using process.
Optionally, determining at least one target sample data from the original sample data based on the failure probability and the maximum entropy policy of the failure probability includes: and taking the original sample data corresponding to the fault probability closest to the preset probability as target sample data.
Specifically, the preset probability may be considered as a limit probability for determining whether to fail, where the limit probability is different for different types of failure determination models, for example, if the type of the failure determination model is a logistic model, the preset probability is 0.5. In this embodiment, one original sample data closest to the preset probability may be selected each time in the process of cyclically selecting the target sample data, so that the selected target sample data is the sample data that has the greatest effect on determining the parameters in the determination model, and the determination effect of the fault determination model is improved.
On the basis of the embodiment, the target sample selection step is optimized, a part of target sample data which is most fuzzy in fault judgment in the original sample can be selected, and the target sample data is subjected to targeted vehicle dismantling detection to determine whether the fault is real, so that the accuracy of a fault judgment model trained on the basis of the target sample data and the real vehicle dismantling result is higher. In addition, the embodiment of the present invention and the fault determination and the model training method proposed in the above embodiments belong to the same inventive concept, and the technical details that are not described in detail in the present embodiment can be referred to the above embodiments, and the present embodiment has the same beneficial effects as the above embodiments.
EXAMPLE III
Fig. 3 is a flowchart illustrating a fault determination method according to a third embodiment of the present invention, where the fault determination method according to the third embodiment of the present invention is applicable to a fault determination situation, for example, an AGV cart fault determination situation. The method may be performed by a fault determination device implemented in software and/or hardware, preferably configured in an electronic device, such as a server of a fault determination platform. As shown in fig. 3, the method for determining a fault provided in the embodiment of the present invention includes the following steps:
s310, vehicle data of the vehicle with the reported fault are obtained.
In the embodiment of the invention, the vehicle data corresponding to the vehicle reporting the fault, which is acquired by the fault determination device, can be the vehicle data with the same type as the preset warehouse and/or the preset vehicle, which is acquired in the training process of the fault determination model, and the data type of the vehicle data reporting the fault can also be the same as the type of original sample data in the training process of the fault determination model, so that the effect of fault determination efficiency is improved.
And S320, inputting the vehicle data into a fault judgment model obtained by training based on the training method provided by any embodiment of the invention, and determining whether the vehicle has a fault according to the output of the fault judgment model.
In the embodiment of the invention, the fault judgment model obtained by training by using the training method provided by any embodiment of the invention is used for judging the vehicle data with reported faults, and the judgment result is output to be a fault or a non-fault, so that the fault judgment of the vehicle can be realized, and a better judgment effect can be achieved.
According to the fault judgment method provided by the embodiment of the invention, the fault judgment device inputs the received vehicle data of the reported fault into the fault judgment model so as to realize the fault judgment of the vehicle, the fault judgment model is obtained by training based on the training method provided by any embodiment of the invention, and the fault judgment cost is reduced by only selecting part of samples to determine whether the corresponding vehicle is a real fault vehicle; the accuracy of fault determination is improved by training according to the real fault label.
Example four
Fig. 4 is a schematic structural diagram of a fault determination model training device according to a fourth embodiment of the present invention, which is applicable to a situation of fault determination model training, for example, a situation of training an AGV cart fault determination model. The fault determination model training method provided by the embodiment can be realized by the fault determination model training device provided by the invention.
As shown in fig. 4, the apparatus for determining a fault and training a model thereof according to an embodiment of the present invention includes:
the sampling module 410 is used for acquiring original sample data of a plurality of vehicles with reported fault information;
a target sample selecting module 420, configured to select a preset number of target sample data from the original sample data;
a real fault marking module 430, configured to mark a real fault label for the target sample data according to a determination result of whether the vehicle corresponding to the target sample data is a real fault vehicle;
and the training module 440 is configured to obtain a fault determination model according to the target sample data and the real fault label training.
Optionally, the target sample selecting module includes:
the primary fault model training submodule is used for obtaining a primary fault judgment model according to the training of original sample data and obtaining fault probability corresponding to the original sample data according to the primary fault judgment model;
and the sample selection submodule is used for selecting a preset amount of target sample data from the original sample data based on the fault probability and the fault probability maximum entropy strategy.
Optionally, the sample selection submodule is specifically configured to:
determining at least one target sample data from the original sample data based on the fault probability and the maximum entropy strategy of the fault probability;
and removing the target sample data from the original sample data, retraining according to the original sample data from which the target sample data is removed to obtain an updated preliminary fault judgment model, and obtaining the target sample data again according to the updated preliminary fault judgment model until the number of the target sample data reaches a preset number.
Optionally, the sample selection submodule is further specifically configured to: and taking the original sample data corresponding to the fault probability closest to the preset probability as target sample data.
Optionally, the sampling module is specifically configured to: the method comprises the steps of obtaining original sample data of a vehicle with a fault reported in a preset warehouse, a preset vehicle type and a preset time period, and original sample data of a vehicle with normal operation.
Optionally, the vehicle is an automated guided vehicle, AGV.
Optionally, the type of the original sample data includes at least one of: current, voltage, and motor parameters.
Optionally, the fault determination model is a discriminant analysis model, an SVM model, a logistic model, or a decision tree model.
The fault determination model training device provided by the embodiment of the invention belongs to the same inventive concept as the fault determination model training method provided by the embodiment, and technical details which are not described in detail in the embodiment of the invention can be referred to the embodiment, and the embodiment of the invention has the same beneficial effects as the embodiment.
EXAMPLE five
Fig. 5 is a schematic structural diagram illustrating a fault determination device according to a fifth embodiment of the present invention, where the fifth embodiment of the present invention is applicable to fault determination, for example, fault determination of an AGV. The fault determination method provided by the embodiment can be realized by the fault determination device provided by the invention.
As shown in fig. 5, the failure determination device according to the embodiment of the present invention includes:
the data receiving module 510 is configured to obtain vehicle data of a vehicle reporting a fault;
and the determining module 520 is configured to input the vehicle data into a fault determination model trained based on the training method provided by any embodiment of the present invention, and determine whether the vehicle has a fault according to an output of the fault determination model.
The fault determination device provided by the embodiment of the invention belongs to the same inventive concept as the fault determination method provided by the embodiment, and technical details which are not described in detail in the embodiment of the invention can be referred to the embodiment, and the embodiment of the invention has the same beneficial effects as the embodiment.
EXAMPLE six
Fig. 6 shows a schematic diagram of a hardware structure of a terminal device according to a sixth embodiment of the present invention. The terminal device in the embodiments of the present invention may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal (e.g., a car navigation terminal), and the like, and a fixed terminal such as a digital TV, a desktop computer, and the like. The terminal device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 6, the terminal device 600 may include a processing means (e.g., a central processing unit, a graphic processor, etc.) 601, which may perform various appropriate actions and processes according to a program stored in a Read-Only Memory (ROM) 602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data necessary for the operation of the terminal apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the terminal device 600 to perform wireless or wired communication with other devices to exchange data. While fig. 6 illustrates a terminal apparatus 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
In particular, according to an embodiment of the present invention, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the invention include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 609, or may be installed from the storage means 608, or may be installed from the ROM 602. The computer program, when executed by the processing means 601, performs the above-described functions defined in the method of an embodiment of the invention.
The terminal provided by the embodiment of the present invention and the fault determination and model training method provided by the embodiment of the present invention belong to the same inventive concept, and the technical details that are not described in detail in the embodiment of the present invention can be referred to the embodiment of the present invention, and the embodiment of the present invention has the same beneficial effects as the embodiment of the present invention.
EXAMPLE seven
An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, where the computer program, when executed by a processor, implements the fault determination model training method or the fault determination method provided in the above-described embodiments.
It should be noted that the computer readable storage medium mentioned above in the embodiments of the present invention may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM) or FLASH Memory (FLASH), an optical fiber, a portable compact disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In embodiments of the invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In yet another embodiment of the invention, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText transfer protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer-readable storage medium may be included in the terminal device or may be separately present without being incorporated in the terminal device.
The terminal device stores one or more programs, and when the one or more programs are executed by the terminal device, the terminal device is enabled to: obtaining original sample data of a plurality of vehicles with reported fault information; selecting target sample data with preset quantity from original sample data; marking a real fault label for the target sample data according to a determination result of whether the vehicle corresponding to the target sample data is a real fault vehicle; training according to target sample data and a real fault label to obtain a fault judgment model; or, receiving vehicle data of reported faults; and inputting the vehicle data with reported faults into a fault judgment model obtained by training based on the training method provided by any embodiment of the invention, and outputting to obtain a judgment result.
Alternatively, the computer readable medium carries one or more programs which, when executed by the terminal device, cause the terminal device to: obtaining original sample data of a plurality of vehicles with reported fault information; selecting target sample data with preset quantity from original sample data; marking a real fault label for the target sample data according to a determination result of whether the vehicle corresponding to the target sample data is a real fault vehicle; training according to target sample data and a real fault label to obtain a fault judgment model; or, receiving vehicle data of reported faults; and inputting the vehicle data with reported faults into a fault judgment model obtained by training based on the training method provided by any embodiment of the invention, and outputting to obtain a judgment result.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present invention may be implemented by software or hardware. Where the name of an element does not in some cases constitute a limitation on the element itself.
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments illustrated herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A fault determination model training method is characterized by comprising the following steps:
acquiring original sample data of a plurality of vehicles with reported fault information;
selecting a preset amount of target sample data from the original sample data;
marking a real fault label for the target sample data according to a determination result of whether the vehicle corresponding to the target sample data is a real fault vehicle;
and training according to the target sample data and the real fault label to obtain a fault judgment model.
2. The method of claim 1, wherein said selecting a predetermined number of target sample data from said original sample data comprises:
training according to the original sample data to obtain a preliminary fault judgment model, and obtaining a fault probability corresponding to the original sample data according to the preliminary fault judgment model;
and selecting a preset amount of target sample data from the original sample data based on the fault probability and the maximum entropy strategy of the fault probability.
3. The method of claim 2, wherein selecting a preset number of target sample data from the original sample data based on the failure probability and the maximum entropy policy of failure probability comprises:
determining at least one target sample data from the original sample data based on the fault probability and the maximum entropy strategy of the fault probability;
and removing the target sample data from the original sample data, retraining according to the original sample data from which the target sample data are removed to obtain an updated preliminary fault judgment model, and obtaining the target sample data again according to the updated preliminary fault judgment model until the number of the target sample data reaches a preset number.
4. The method of claim 3, wherein determining at least one target sample data from the original sample data based on the failure probability and a failure probability maximum entropy policy comprises:
and taking the original sample data corresponding to the fault probability closest to the preset probability as target sample data.
5. The method according to any of the claims 1-4, characterized in that the vehicle is an automatic guided transport AGV.
6. A failure determination method, characterized by comprising:
acquiring vehicle data of a vehicle reporting a fault;
inputting the vehicle data into a fault determination model trained based on the training method of any one of claims 1-5, and determining whether the vehicle is in fault according to the output of the fault determination model.
7. A failure determination model training device, characterized by comprising:
the sampling module is used for acquiring original sample data of a plurality of vehicles with reported fault information;
the target sample selecting module is used for selecting a preset amount of target sample data from the original sample data;
the real fault marking module is used for marking a real fault label for the target sample data according to a determination result of whether the vehicle corresponding to the target sample data is a real fault vehicle;
and the training module is used for obtaining a fault judgment model according to the target sample data and the real fault label training.
8. A failure determination device characterized by comprising:
the data receiving module is used for acquiring vehicle data of the vehicle reporting the fault;
and the judging module is used for inputting the vehicle data into a fault judging model trained on the training method of any one of claims 1-5 and determining whether the vehicle has a fault according to the output of the fault judging model.
9. A terminal device, characterized in that the terminal comprises:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the fault determination model training method of any one of claims 1-5 or the fault determination method of claim 6.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method for training a fault determination model according to any one of claims 1 to 5, or carries out a method for fault determination according to claim 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010187453.5A CN111738286A (en) | 2020-03-17 | 2020-03-17 | Fault determination and model training method, device, equipment and storage medium thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010187453.5A CN111738286A (en) | 2020-03-17 | 2020-03-17 | Fault determination and model training method, device, equipment and storage medium thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111738286A true CN111738286A (en) | 2020-10-02 |
Family
ID=72646446
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010187453.5A Pending CN111738286A (en) | 2020-03-17 | 2020-03-17 | Fault determination and model training method, device, equipment and storage medium thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111738286A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104778162A (en) * | 2015-05-11 | 2015-07-15 | 苏州大学 | Subject classifier training method and system based on maximum entropy |
| CN105372528A (en) * | 2015-11-24 | 2016-03-02 | 湖南大学 | Power transformer internal fault condition maintenance method |
| CN105631473A (en) * | 2015-12-24 | 2016-06-01 | 大连理工大学 | Camera source identification method in finite labeled sample condition |
| CN108693868A (en) * | 2018-05-25 | 2018-10-23 | 深圳市轱辘车联数据技术有限公司 | The method of failure predication model training, the method and device of vehicle trouble prediction |
| CN109035242A (en) * | 2018-08-09 | 2018-12-18 | 长安大学 | A kind of HF-ERW welded condition detection method and device based on deep learning |
| CN109344905A (en) * | 2018-10-22 | 2019-02-15 | 王子蕴 | A kind of transmission facility automatic fault recognition methods based on integrated study |
| CN110084148A (en) * | 2019-04-09 | 2019-08-02 | 东南大学 | A kind of Mechanical Failure of HV Circuit Breaker diagnostic method |
| CN110675959A (en) * | 2019-08-19 | 2020-01-10 | 平安科技（深圳）有限公司 | Intelligent data analysis method and device, computer equipment and storage medium |
-
2020
- 2020-03-17 CN CN202010187453.5A patent/CN111738286A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104778162A (en) * | 2015-05-11 | 2015-07-15 | 苏州大学 | Subject classifier training method and system based on maximum entropy |
| CN105372528A (en) * | 2015-11-24 | 2016-03-02 | 湖南大学 | Power transformer internal fault condition maintenance method |
| CN105631473A (en) * | 2015-12-24 | 2016-06-01 | 大连理工大学 | Camera source identification method in finite labeled sample condition |
| CN108693868A (en) * | 2018-05-25 | 2018-10-23 | 深圳市轱辘车联数据技术有限公司 | The method of failure predication model training, the method and device of vehicle trouble prediction |
| CN109035242A (en) * | 2018-08-09 | 2018-12-18 | 长安大学 | A kind of HF-ERW welded condition detection method and device based on deep learning |
| CN109344905A (en) * | 2018-10-22 | 2019-02-15 | 王子蕴 | A kind of transmission facility automatic fault recognition methods based on integrated study |
| CN110084148A (en) * | 2019-04-09 | 2019-08-02 | 东南大学 | A kind of Mechanical Failure of HV Circuit Breaker diagnostic method |
| CN110675959A (en) * | 2019-08-19 | 2020-01-10 | 平安科技（深圳）有限公司 | Intelligent data analysis method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113765928B (en) | Internet of things intrusion detection method, equipment and medium | |
| CN110704491B (en) | Data query method and device | |
| CN115357470B (en) | Information generation method and device, electronic equipment and computer readable medium | |
| CN115326099A (en) | Local path planning method and device, electronic equipment and computer readable medium | |
| CN115272182B (en) | Lane line detection method, lane line detection device, electronic equipment and computer readable medium | |
| CN117690063B (en) | Cable line detection method, device, electronic equipment and computer readable medium | |
| CN110287817B (en) | Target recognition and target recognition model training method and device and electronic equipment | |
| CN112507265B (en) | Method and device for abnormality detection based on tree structure and related products | |
| CN115546767B (en) | Data transmission method, device, equipment and computer readable medium | |
| CN111738286A (en) | Fault determination and model training method, device, equipment and storage medium thereof | |
| CN110782117A (en) | Driving risk detection method and device, storage medium and electronic equipment | |
| CN112685996B (en) | Text punctuation prediction method and device, readable medium and electronic equipment | |
| CN114004313A (en) | Fault GPU prediction method and device, electronic equipment and storage medium | |
| CN112712070A (en) | Question judging method and device for bead calculation questions, electronic equipment and storage medium | |
| US20240221359A1 (en) | Image processing method and electronic device | |
| CN117092933B (en) | Rotating machinery control method, apparatus, device and computer readable medium | |
| CN116125961B (en) | Vehicle control index generation method, device, equipment and computer readable medium | |
| CN115309739B (en) | Vehicle-mounted data retrieval method and device, electronic equipment, medium and product | |
| CN113572768B (en) | Analysis method for abnormal change of number of botnet family propagation sources | |
| CN115941357B (en) | Industrial safety-based flow log detection method and device and electronic equipment | |
| CN116541251B (en) | Display device state early warning method, device, equipment and computer readable medium | |
| CN117978612B (en) | Network fault detection method, storage medium and electronic equipment | |
| CN115471708B (en) | Lane line type information generation method, device, equipment and computer readable medium | |
| CN116703263B (en) | Power equipment distribution method, device, electronic equipment and computer readable medium | |
| CN112328341B (en) | Model display method, device, electronic equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201002 |