CN113988192A - Hydraulic transmission gear shifting fault identification method, model training method and device - Google Patents

Hydraulic transmission gear shifting fault identification method, model training method and device Download PDF

Info

Publication number
CN113988192A
CN113988192A CN202111276881.6A CN202111276881A CN113988192A CN 113988192 A CN113988192 A CN 113988192A CN 202111276881 A CN202111276881 A CN 202111276881A CN 113988192 A CN113988192 A CN 113988192A
Authority
CN
China
Prior art keywords
fault
evaluation index
stage
gear shifting
preset
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
Application number
CN202111276881.6A
Other languages
Chinese (zh)
Inventor
周慎
杨蕾
蔡仲昌
李春风
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Special Vehicle Technology Center of Hubei Aerospace Technology Research Institute
Hubei Sanjiang Space Wanshan Special Vehicle Co Ltd
Original Assignee
Special Vehicle Technology Center of Hubei Aerospace Technology Research Institute
Hubei Sanjiang Space Wanshan Special Vehicle Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Special Vehicle Technology Center of Hubei Aerospace Technology Research Institute, Hubei Sanjiang Space Wanshan Special Vehicle Co Ltd filed Critical Special Vehicle Technology Center of Hubei Aerospace Technology Research Institute
Priority to CN202111276881.6A priority Critical patent/CN113988192A/en
Publication of CN113988192A publication Critical patent/CN113988192A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24133—Distances to prototypes
    • G06F18/24137—Distances to cluster centroïds
    • G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
    • G06F18/256—Fusion techniques of classification results, e.g. of results related to same input data of results relating to different input data, e.g. multimodal recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computational Linguistics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Evolutionary Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Control Of Transmission Device (AREA)

Abstract

The embodiment of the specification discloses a hydraulic transmission gear shifting fault identification method, a model training method and a device, wherein the method comprises the following steps: acquiring a total evaluation index and a stage evaluation index of the hydraulic transmission in a gear shifting process, wherein the total evaluation index is an index for representing the overall performance of the gear shifting process, and the stage evaluation index is an index for representing the stage performance of each gear shifting stage in the gear shifting process; inputting the overall evaluation index into a first preset fault recognition model to obtain a first fault recognition result, wherein the first fault recognition result is used for representing whether a fault affecting driving safety occurs in the gear shifting process; and if the first fault identification result shows that the fault influencing the driving safety does not occur in the gear shifting process, inputting the overall evaluation index and the stage evaluation index into a second preset fault identification model to obtain a second fault identification result. This scheme can be more comprehensive and accurate discernment trouble of shifting to improve the reliability that hydraulic transmission used.

Description

Hydraulic transmission gear shifting fault identification method, model training method and device
Technical Field
The embodiment of the specification relates to the field of vehicles, in particular to a hydraulic transmission gear shifting fault identification method, a model training method and a device.
Background
A hydraulic Transmission (AT) is one of the most complicated parts for modern vehicle automation, and the reliability of the operation of the AT directly affects the reliability and safety of the whole vehicle, so that the requirement for fault diagnosis of the Transmission AT night is higher and higher. The electro-hydraulic automatic gear shifting is a core technology of the AT, belongs to a typical electromechanical hydraulic control complex technology, has high failure probability due to frequent work and complex and variable working conditions, and directly influences the working reliability of the AT.
In the prior art, the AT fault diagnosis technology is biased to diagnose hardware systems such as communication, electrical components, hydraulic components and circuits, and dynamic characteristic research on faults in the gear shifting process is lacked, so that the problems of incomplete fault identification and false identification are caused, and the reliability of AT use is further influenced.
Disclosure of Invention
The embodiment of the specification provides a hydraulic transmission gear shifting fault identification method, a model training method and a device.
In a first aspect, an embodiment of the present specification provides a shift fault identification method for a hydraulic transmission, including:
acquiring a total evaluation index and a stage evaluation index of a hydraulic transmission in a gear shifting process, wherein the total evaluation index is an index for representing the overall performance of the gear shifting process, and the stage evaluation index is an index for representing the stage performance of each gear shifting stage included in the gear shifting process;
inputting the overall evaluation index into a first preset fault recognition model to obtain a first fault recognition result, wherein the first fault recognition result is used for representing whether a fault affecting driving safety occurs in the gear shifting process;
and if the first fault identification result shows that the fault influencing the driving safety does not occur in the gear shifting process, inputting the overall evaluation index and the stage evaluation index into a second preset fault identification model to obtain a second fault identification result.
Optionally, the overall evaluation index comprises one or more of the following: the gear shifting method comprises the following steps of shifting time length in the gear shifting process, a peak value of the rotating speed change rate of a turbine shaft in the gear shifting process and a peak value of the rotating speed change rate of an output shaft in the gear shifting process.
Optionally, the shifting process comprises the following stages in chronological order: pre-charging oil, torque, slow reduction of turbine speed, fast reduction of turbine speed and synchronization;
the stage evaluation index comprises one or more of the following indexes: the total reduction amount of the turbine rotating speed in the pre-oil filling stage, the total reduction amount of the turbine rotating speed in a response period after the pre-oil filling stage is ended, the actual time of the torque stage, the total reduction amount of the turbine rotating speed in the torque stage, the actual time of the slow reduction stage of the turbine rotating speed, the total reduction amount of the turbine rotating speed in a response period after the slow reduction stage of the turbine rotating speed, and the actual time of the fast reduction stage of the turbine rotating speed.
Optionally, the first preset fault identification model and the second preset fault identification model are obtained by:
acquiring a training sample set, wherein each sample data in the training sample set comprises a total evaluation index and a stage evaluation index in a one-time gear shifting process;
determining the fault type of each sample data as the label information of each sample data based on the corresponding relation between the preset evaluation index and the fault type;
constructing a first initial fault identification model and a second initial fault identification model;
training the first initial fault recognition model based on the overall cost performance index corresponding to each sample data and the label information of each sample data to obtain the trained first preset fault recognition model;
and training the second initial fault recognition model based on the overall evaluation index and the staged evaluation index corresponding to each sample data and the label information of each sample data to obtain the trained second preset fault recognition model.
In a second aspect, the present specification provides a fault recognition model training method, where the fault recognition model is used to recognize a shift fault of a hydraulic transmission, and the fault recognition model includes a first preset fault recognition model and a second preset fault recognition model, and includes:
acquiring a training sample set, wherein each sample data in the training sample set comprises a total evaluation index and a stage evaluation index in a one-time gear shifting process, the total evaluation index is an index for representing the overall performance of the gear shifting process, and the stage evaluation index is an index for representing the stage performance of each gear shifting stage in the gear shifting process;
constructing a first initial fault identification model and a second initial fault identification model;
training the first initial fault recognition model based on the overall cost performance index corresponding to each sample data and the label information of each sample data to obtain the trained first preset fault recognition model;
and training the second initial fault recognition model based on the overall evaluation index and the staged evaluation index corresponding to each sample data and the label information of each sample data to obtain the trained second preset fault recognition model.
Optionally, after the acquiring the training sample set, the method further comprises:
and determining the fault type of each sample data as the label information of each sample data based on the corresponding relation between the preset evaluation index and the fault type.
Optionally, the overall evaluation index comprises one or more of the following: the gear shifting method comprises the following steps of shifting time length in the gear shifting process, a peak value of the rotating speed change rate of a turbine shaft in the gear shifting process and a peak value of the rotating speed change rate of an output shaft in the gear shifting process.
Optionally, the shifting process comprises the following stages in chronological order: pre-charging oil, torque, slow reduction of turbine speed, fast reduction of turbine speed and synchronization;
the stage evaluation index comprises one or more of the following indexes: the total reduction amount of the turbine rotating speed in the pre-oil filling stage, the total reduction amount of the turbine rotating speed in a response period after the pre-oil filling stage is ended, the actual time of the torque stage, the total reduction amount of the turbine rotating speed in the torque stage, the actual time of the slow reduction stage of the turbine rotating speed, the total reduction amount of the turbine rotating speed in a response period after the slow reduction stage of the turbine rotating speed, and the actual time of the fast reduction stage of the turbine rotating speed.
In a third aspect, embodiments of the present specification provide a shift fault recognition apparatus for a hydraulic transmission, the apparatus including:
the hydraulic transmission control method comprises an acquisition module, a transmission control module and a transmission control module, wherein the acquisition module is used for acquiring a total evaluation index and a stage evaluation index of a hydraulic transmission in a gear shifting process, the total evaluation index is an index for representing the overall performance of the gear shifting process, and the stage evaluation index is an index for representing the stage performance of each gear shifting stage in the gear shifting process;
the first processing module is used for inputting the overall evaluation index into a first preset fault recognition model to obtain a first fault recognition result, and the first fault recognition result is used for representing whether a fault affecting driving safety occurs in the gear shifting process;
and the second processing module is used for inputting the overall evaluation index and the stage evaluation index into a second preset fault recognition model to obtain a second fault recognition result when the first fault recognition result shows that the fault influencing the driving safety does not occur in the gear shifting process.
Optionally, the overall evaluation index comprises one or more of the following: the gear shifting method comprises the following steps of shifting time length in the gear shifting process, a peak value of the rotating speed change rate of a turbine shaft in the gear shifting process and a peak value of the rotating speed change rate of an output shaft in the gear shifting process.
Optionally, the shifting process comprises the following stages in chronological order: pre-charging oil, torque, slow reduction of turbine speed, fast reduction of turbine speed and synchronization;
the stage evaluation index comprises one or more of the following indexes: the total reduction amount of the turbine rotating speed in the pre-oil filling stage, the total reduction amount of the turbine rotating speed in a response period after the pre-oil filling stage is ended, the actual time of the torque stage, the total reduction amount of the turbine rotating speed in the torque stage, the actual time of the slow reduction stage of the turbine rotating speed, the total reduction amount of the turbine rotating speed in a response period after the slow reduction stage of the turbine rotating speed, and the actual time of the fast reduction stage of the turbine rotating speed.
Optionally, the first preset fault identification model and the second preset fault identification model are obtained by:
acquiring a training sample set, wherein each sample data in the training sample set comprises a total evaluation index and a stage evaluation index in a one-time gear shifting process;
determining the fault type of each sample data as the label information of each sample data based on the corresponding relation between the preset evaluation index and the fault type;
constructing a first initial fault identification model and a second initial fault identification model;
training the first initial fault recognition model based on the overall cost performance index corresponding to each sample data and the label information of each sample data to obtain the trained first preset fault recognition model;
and training the second initial fault recognition model based on the overall evaluation index and the staged evaluation index corresponding to each sample data and the label information of each sample data to obtain the trained second preset fault recognition model.
In a fourth aspect, the present specification provides a fault recognition model training device, where the fault recognition model is used to recognize a shift fault of a hydraulic transmission, and the fault recognition model includes a first preset fault recognition model and a second preset fault recognition model, the device includes:
the system comprises a sample acquisition module, a shift execution module and a shift execution module, wherein the sample acquisition module is used for acquiring a training sample set, and each sample data in the training sample set comprises a total evaluation index and a stage evaluation index in a one-time shift process, the total evaluation index is an index for representing the overall performance of the shift process, and the stage evaluation index is an index for representing the stage performance of each shift stage in the shift process;
the model construction module is used for constructing a first initial fault identification model and a second initial fault identification model;
the first model training module is used for training the first initial fault recognition model based on the overall cost performance index corresponding to each sample data and the label information of each sample data to obtain the trained first preset fault recognition model;
and the second model training module is used for training the second initial fault recognition model based on the overall evaluation index and the stage evaluation index corresponding to each sample data and the label information of each sample data to obtain the trained second preset fault recognition model.
Optionally, the apparatus further comprises:
and the label determining module is used for determining the fault type of each sample data as the label information of each sample data based on the corresponding relation between the preset evaluation index and the fault type.
Optionally, the overall evaluation index comprises one or more of the following: the gear shifting method comprises the following steps of shifting time length in the gear shifting process, a peak value of the rotating speed change rate of a turbine shaft in the gear shifting process and a peak value of the rotating speed change rate of an output shaft in the gear shifting process.
Optionally, the shifting process comprises the following stages in chronological order: pre-charging oil, torque, slow reduction of turbine speed, fast reduction of turbine speed and synchronization;
the stage evaluation index comprises one or more of the following indexes: the total reduction amount of the turbine rotating speed in the pre-oil filling stage, the total reduction amount of the turbine rotating speed in a response period after the pre-oil filling stage is ended, the actual time of the torque stage, the total reduction amount of the turbine rotating speed in the torque stage, the actual time of the slow reduction stage of the turbine rotating speed, the total reduction amount of the turbine rotating speed in a response period after the slow reduction stage of the turbine rotating speed, and the actual time of the fast reduction stage of the turbine rotating speed.
In a fifth aspect, embodiments of the present specification provide an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor performs the steps of any one of the methods described above.
In a sixth aspect, the present specification provides a computer readable storage medium, on which a computer program is stored, and the computer program is used for implementing the steps of any one of the above methods when executed by a processor.
The embodiment of the specification has the following beneficial effects:
according to the gear shifting fault identification method of the hydraulic transmission, provided by the embodiment of the specification, by acquiring the overall evaluation index and the stage evaluation index of the hydraulic transmission in the gear shifting process, all stages and overall performance in the gear shifting process are comprehensively considered, whether a fault affecting driving safety occurs or not is determined through the first preset fault identification model, and when the fault affecting driving safety does not occur, whether a fault reducing product reliability or service life exists or not is determined through the second preset fault identification model. It is thus clear that in this scheme, through monitoring the index of the in-process that shifts gears comprehensively, can discern the trouble of multiple in-process of shifting gears for the discernment of the trouble of shifting gears is more comprehensive and accurate, and then has improved the reliability that hydraulic transmission used.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the specification. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart of a shift fault identification method for a hydraulic transmission according to an embodiment of the present disclosure;
FIG. 2 is a schematic illustration of staging a shift process provided by an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a neural network model provided in an embodiment of the present disclosure;
FIG. 4 is a flowchart of a fault recognition model training method provided by an embodiment of the present disclosure;
FIG. 5 is a schematic diagram illustrating a shift fault identification apparatus for a hydraulic transmission according to an embodiment of the present disclosure;
FIG. 6 is a schematic diagram of a fault recognition model training apparatus provided in an embodiment of the present disclosure;
fig. 7 is a schematic view of an electronic device provided in an embodiment of the present disclosure.
Detailed Description
In order to better understand the technical solutions, the technical solutions of the embodiments of the present specification are described in detail below with reference to the drawings and specific embodiments, and it should be understood that the specific features of the embodiments and embodiments of the present specification are detailed descriptions of the technical solutions of the embodiments of the present specification, and are not limitations of the technical solutions of the present specification, and the technical features of the embodiments and embodiments of the present specification may be combined with each other without conflict.
The embodiment of the present specification provides a shift fault identification method for a hydraulic transmission, and as shown in fig. 1, is a flowchart of the shift fault identification method for a hydraulic transmission provided by the embodiment of the present specification, and the method includes the following steps:
step S11: acquiring a total evaluation index and a stage evaluation index of a hydraulic transmission in a gear shifting process, wherein the total evaluation index is an index for representing the overall performance of the gear shifting process, and the stage evaluation index is an index for representing the stage performance of each gear shifting stage included in the gear shifting process;
step S12: inputting the overall evaluation index into a first preset fault recognition model to obtain a first fault recognition result, wherein the first fault recognition result is used for representing whether a fault affecting driving safety occurs in the gear shifting process;
step S13: and if the first fault identification result shows that the fault influencing the driving safety does not occur in the gear shifting process, inputting the overall evaluation index and the stage evaluation index into a second preset fault identification model to obtain a second fault identification result.
The shift fault identification method for the hydraulic transmission provided by the embodiment of the specification can be applied to a vehicle controller, and can also be applied to independent electronic equipment capable of communicating with a vehicle, for example, the vehicle sends collected data for shift fault identification to the electronic equipment, so that the electronic equipment analyzes the received data to obtain a shift fault identification result.
In order to identify a malfunction during shifting, various indexes of the hydraulic transmission during shifting are acquired through step S11. In the embodiment of the present disclosure, the shift process may be a shift under any operating condition, for example, a power upshift, a power downshift, an unpowered upshift, an unpowered downshift, and the like. In order to fully detect the gear shifting process, in the embodiment of the present specification, for one gear shifting process, it is necessary to obtain a total evaluation index and a stage evaluation index in the gear shifting process. The overall evaluation index and the stage evaluation index can be obtained by extracting the rotating speeds of the input shaft, the turbine shaft and the output shaft of the AT, so that the identification of the gear shifting fault can get rid of the dependence on an oil pressure signal, the potential hazards of nonlinearity and instability of the oil pressure signal are eliminated, the range and the accuracy of the identification of the gear shifting fault are improved, meanwhile, the number of oil pressure sensors on an AT product can be reduced, and the control cost is facilitated.
In a specific implementation, the overall evaluation index, as an index for evaluating the overall performance of the shift process, may include one or more of the following indexes: time length of shiftingwholePeak value of change rate of turbine shaft rotation speed in gear shifting process
Figure BDA0003329731470000091
Peak value of output shaft speed change rate in gear shifting process
Figure BDA0003329731470000092
In order to obtain the stage index, as shown in fig. 2, in the embodiment of the present specification, the shift process is divided into the following stages according to the chronological order: the method comprises a pre-charging oil stage, a torque stage, a slow reduction stage of the rotating speed of a turbine, a fast reduction stage of the rotating speed of the turbine and a synchronization stage.
The pre-charging oil stage is a stage of sending a gear shifting command from a controller to a stage of pushing a piston to eliminate a clearance between friction plates of a clutch or a brake after a gear shifting valve is opened; the torque stage is a stage in which the clutch or the brake starts to transmit torque, but the transmission still keeps the original gear speed ratio; a slow turbine speed reduction stage for transmitting torque to the clutch or the brake, and a stage in which the speed ratio of the transmission is slowly changed (for example, a stage in which the speed ratio change rate is less than a threshold value); a stage in which the turbine speed rapidly drops, torque is transmitted to the clutch or the brake, and the speed ratio of the transmission is rapidly changed (for example, a stage in which the speed ratio change rate is greater than a threshold value), and the stage is usually accompanied with rapid release of inertia energy of a transmission system and is most prone to shift shock; and the synchronization stage is a stage in which the speed ratio of the transmission reaches and stabilizes at the speed ratio of the target gear. It should be noted that, when the slow turbine speed decreasing stage and the fast turbine speed decreasing stage are divided, the threshold value may be set according to actual needs, and is not limited herein.
After the gear shifting process is divided into stages, a staged evaluation index may be determined according to each divided stage, and in a specific implementation process, the staged evaluation index may include one or more of the following indexes: gross turbine speed reduction in the pre-charge stage
Figure BDA0003329731470000093
Total reduction in turbine speed in a response period after the end of the pre-charge phase
Figure BDA0003329731470000094
Actual time of moment phase ttorqueTotal amount of turbine speed reduction in torque phase
Figure BDA0003329731470000095
Actual time t of slow reduction stage of turbine speedslowThe total reduction amount of the turbine speed in a response period after the slow reduction stage of the turbine speed is finished
Figure BDA0003329731470000096
And the actual time t of the rapid turbine speed reduction stagefast。
It should be noted that, since the response of the hydraulic system requires a certain time, the total amount of the turbine speed reduction in a response period after the pre-charging period is completed needs to be passed
Figure BDA0003329731470000097
To characterize the delayed response of the hydraulic system. Similarly, in consideration of the response delay of the hydraulic system, the total decrease amount of the turbine speed in a response period after the slow decrease stage of the turbine speed needs to be obtained
Figure BDA0003329731470000098
Therefore, indexes in the gear shifting process can be comprehensively monitored in the embodiment of the specification, and the accuracy of final fault identification is further ensured.
In the embodiment of the present specification, for the severity of the shift fault, the shift process fault may be divided into two types: the first type is a fault which can cause the product to lose function or drive safety; the second type is that the function of the transmission is not affected, but the frequent occurrence of the faults for a long time can reduce the reliability and the service life of products, such as the reliability of transmission system parts and friction plates. Because the first type of fault is serious and measures need to be taken in time to prevent driving danger, the first type of fault can be identified in real time. For the second type of fault, since the current driving is not greatly affected, in order to save the computing resources, the second type of fault may be identified offline, for example, a fault identification period is set for the identification of the second type of fault, for example, the second type of fault is calculated once every day, or once every week, and the like. Of course, the second type of fault may also be identified in real time, which is not limited herein.
In a specific implementation process, the first type of fault can be identified through a first preset fault identification model, and the second type of fault can be identified through a second preset fault identification model. The first type of fault can be identified based on the overall evaluation index, and the second type of fault can be identified based on the overall evaluation index and the stage evaluation index. Of course, what kind of indexes are used to identify what kind of faults may be set according to actual needs, for example, identification of the second kind of faults is performed through a staged evaluation index, identification of the first kind of faults is performed through a part of the overall evaluation index and a part of the staged evaluation index, or identification of specific faults included in the first kind of faults or the second kind of faults is performed through a specified evaluation index, and the like, which is not limited herein. For convenience of explanation, the first type of fault is identified by the overall evaluation index, and the second type of fault is identified by the overall evaluation index and the staged evaluation index.
In the embodiment of the present specification, the faults in the AT shift process include the following: normal shift, power intervention, power interruption, high impact, normal impact, high scrub and normal scrub. Next, for each of the above-described failures, a change in a parameter corresponding to the failure during the upshift and downshift will be specifically described.
And (4) normal gear shifting: in the gear-up process, the angular acceleration of the output shaft is smaller than the first preset angular acceleration of the output shaft, and the output rotating speed is basically unchanged; in the downshift process, the output angular acceleration is smaller than the first preset output shaft angular acceleration, and the rotating speed of the turbine rises stably.
Dynamic interference: in the gear-up process, the angular acceleration of the output shaft is greater than or equal to a second preset angular acceleration of the output shaft, and the output rotating speed is abnormally reduced; in the gear-shifting process, the angular acceleration of the output shaft is greater than or equal to a second preset angular acceleration of the output shaft, and the rotating speed of the turbine is abnormally reduced.
Power interruption: in the gear-up process, the gear-shifting duration is longer than a first preset gear-shifting duration, and the angular acceleration of the output shaft is smaller than a third preset angular acceleration of the output shaft; in the downshift process, the gear shifting duration is longer than the preset gear shifting duration, and the output shaft angular acceleration is smaller than a third preset output shaft angular acceleration.
Large impact: in the gear-up process, the ratio of the angular acceleration of the turbine shaft to the angular acceleration of the output shaft is larger than a first preset ratio, and the rotating speed of the output shaft is abnormally reduced; in the downshift process, the ratio of the angular acceleration of the turbine shaft to the angular acceleration of the output shaft is larger than a first preset ratio, and the actual time of the torque phase is larger than a first preset duration.
General impact: in the gear-up process, the ratio of the angular acceleration of the turbine shaft to the angular acceleration of the output shaft is larger than a second preset ratio, and the rotating speed of the output shaft is abnormally reduced; in the downshift process, the ratio of the angular acceleration of the turbine shaft to the angular acceleration of the output shaft is larger than a second preset ratio, and the actual time of the torque phase is larger than a second preset duration. The second preset ratio is smaller than the first preset ratio, and the second preset time length is smaller than the first preset time length.
Large sliding friction: in the gear-up process, the gear-shifting duration is longer than a second preset gear-shifting duration, and the ratio of the angular acceleration of the turbine shaft to the angular acceleration of the output shaft is smaller than a third preset ratio; in the downshift process, the gear shifting duration is longer than a second preset gear shifting duration, and the ratio of the angular acceleration of the turbine shaft to the angular acceleration of the output shaft is smaller than a third preset ratio.
General rubbing: in the gear-up process, the gear-shifting duration is longer than a third preset gear-shifting duration, and the ratio of the angular acceleration of the turbine shaft to the angular acceleration of the output shaft is smaller than a fourth preset ratio; in the downshift process, the gear shifting duration is longer than a third preset gear shifting duration, and the ratio of the angular acceleration of the turbine shaft to the angular acceleration of the output shaft is smaller than a fourth preset ratio. The third preset gear shifting duration is smaller than the second preset gear shifting duration, and the fourth preset ratio is smaller than the third preset ratio.
It should be noted that specific values of the first preset output shaft angular acceleration, the second preset output shaft angular acceleration, the third preset output shaft angular acceleration, the first preset gear shifting time, the second preset gear shifting time, the third preset gear shifting time, the first preset ratio, the second preset ratio, the third preset ratio, the fourth preset ratio, the first preset time and the second preset time may be set according to actual needs, and specific values of the parameters may be different for different manufacturers and different vehicle types.
In the embodiment of the present specification, the first type of fault includes: power interference and power interruption; the second type of failure includes: greater impact, normal impact, greater friction, and normal friction.
Regarding the first type of fault, the first type of fault may be identified through a first preset fault identification model, and in step S12, a total evaluation index in the gear shifting process is obtained, the total evaluation index in the gear shifting process is input into the first fault identification model, and a first fault identification result is output, where the first fault identification result is used to indicate whether the first type of fault occurs in the gear shifting process. Specifically, the first failure recognition result may include three cases: normal gear shifting, power interference and power interruption. When the first fault identification result is power interference or power interruption, it indicates that the first type of fault always occurs in the gear shifting process, and at this time, an active fault protection measure can be implemented directly through a Transmission Control Unit (TCU). When the first fault recognition result is normal gear shifting, the first fault is shown not to appear in the gear shifting process, the gear shifting process can be further evaluated through a second preset fault, whether the second fault exists or not is judged, the part with poor gear shifting quality is located based on the recognized second fault, a basis is provided for the correction direction of the gear shifting index, and the system reliability is improved.
Specifically, when the fault of the shift process is identified in step S13, since the second preset fault identification model is more complex, in the embodiment of the present specification, the overall evaluation index and the stage evaluation index may be used as inputs of the second preset fault identification model, so as to obtain the second fault identification result. Wherein the second fault identification result comprises one of the 4 second-type faults.
In addition, since the first type of fault affects driving safety, the first type of fault needs to be detected in real time, that is, the first type of fault in the gear shifting process is identified in real time by the first preset fault identification model. Since the second type of fault has little influence on driving safety, the second preset fault identification model can identify the second fault offline to save computing resources, and certainly, the second preset fault identification model can also identify the second type of fault in real time, which is not limited herein.
In order to describe the first preset fault recognition model and the second preset fault recognition model provided in the embodiments of the present specification, a forming process of the first preset fault recognition model and the second preset fault recognition model is described below.
In a specific implementation process, the first preset fault identification model and the second preset fault identification model are obtained in the following way: acquiring a training sample set, wherein each sample data in the training sample set comprises a total evaluation index and a stage evaluation index in a one-time gear shifting process; determining the fault type of each sample data as the label information of each sample data based on the corresponding relation between the preset evaluation index and the fault type; constructing a first initial fault identification model and a second initial fault identification model; training the first initial fault recognition model based on the overall cost performance index corresponding to each sample data and the label information of each sample data to obtain a trained first preset fault recognition model; and training the second initial fault recognition model based on the overall evaluation index and the stage evaluation index corresponding to each sample data and the label information of each sample data to obtain a trained second preset fault recognition model.
Specifically, each sample in the training sample set corresponds to a total evaluation index and a stage evaluation index in a gear shifting process, specifically, the total evaluation index and the stage evaluation index of the target vehicle in each gear shifting process are counted, for example, each gear shifting process of the target vehicle in half a year, including each index in an upshift process and a downshift process, is recorded, and each index corresponding to each gear shifting process is used as one sample data.
In the embodiment of the present specification, model training is performed in a supervised manner, and therefore, marking needs to be performed on each sample. In the specific implementation process, a set of standard overall evaluation indexes and stage indexes can be set for each vehicle type, and the label information of each sample is determined by comparing the indexes in the actually measured sample data with the standard indexes. The standard overall evaluation index and the standard stage evaluation index may be indexes determined according to empirical values or experimental values when the gear shifting is normally performed. In the embodiment of the specification, label information can be marked for each sample data through a preset corresponding relation between an evaluation index and a fault type. The correspondence between the preset evaluation index and the type of failure is shown in table 1.
TABLE 1
Figure BDA0003329731470000141
Wherein too small in table 1 indicates that the corresponding index in the sample is smaller than the standard index and the difference between the standard index and the index of the sample is smaller than the first preset value, corresponding to "too small", and too large in table 1 indicates that the corresponding index in the sample is larger than the standard index and the difference between the index of the sample and the standard index is larger than the second preset value. "small" in table 1 indicates that the corresponding index in the sample is smaller than the standard index and the difference between the standard index and the index of the sample is smaller than the third preset value, corresponding to "small", and "large" in table 1 indicates that the corresponding index in the sample is larger than the standard index and the difference between the index of the sample and the standard index is larger than the fourth preset value. "large" in table 1 indicates that the corresponding index in the sample is larger than the standard index and the difference between the index of the sample and the standard index is larger than the fifth preset value, corresponding to "large", and "small" in table 1 indicates that the corresponding index in the sample is smaller than the standard index and the difference between the index of the standard index and the index of the sample is smaller than the sixth preset value. It should be noted that specific values of the first preset value to the sixth preset value may be set according to actual needs, and are not limited herein.
For example, if each index of one sample data is compared with the standard index, if the fault type of the dynamic interference is met, the label information of the sample is marked as the dynamic interference. In this way, label information for each training sample may be determined.
Before model training, initial models are required to be built, namely a first initial fault recognition model and a second initial fault recognition model are built. The type of the model may be selected according to actual needs, and is not limited herein, and for convenience of description, in the embodiment of the present specification, the first initial fault identification model and the second initial fault identification model are both explained as an example of a neural network model.
FIG. 3 is a schematic diagram of a neural network model, where X is an m-dimensional vector of an input layer, H is a k-dimensional vector of a hidden layer, Y is an n-dimensional vector of an output layer, and W is a1Is a weight matrix (size is l x m), b from input layer to hidden layer1For an I-dimensional threshold vector of input layer to hidden layer, W2Is a weight matrix (size is n x l) from the hidden layer to the output layer, b2For an n-dimensional threshold vector from the hidden layer to the output layer,
Figure BDA0003329731470000151
the function is activated for logsig.
For the input layer of the neural network, the number of input layer nodes depends on the dimension m of the input vector. In the embodiment of the present specification, the first type of fault is identified based on three overall evaluation indexes, and the second type of fault is identified based on three overall evaluation indexes and seven stage evaluation indexes. Therefore, for the first initial fault identification model, three overall evaluation indexes are taken as the input of the model, namely, m is 3; for the second initial fault identification model, three overall evaluation indexes and seven stage evaluation indexes are used as the input of the model, namely m is 10. Of course, the number of input nodes of the model may be adjusted according to actual situations, and is not limited herein.
For a hidden layer of a neural network, the number of stages of the hidden layer can be adjusted according to error performance in a training process, in the embodiment of the description, a first initial fault identification model selects 4 node numbers, and a second initial fault identification model selects 9 node numbers. Of course, the number of nodes in the hidden layer may also be set to other values according to actual needs, and is not limited here.
For the output layer of the neural network, a multi-output type may be selected in the embodiments of the present specification, that is, the number of output nodes is equal to the number of types. And aiming at the first initial fault identification model, the model identifies the first type of fault, and further fault identification is carried out by utilizing a second preset fault identification model under the condition that the model does not identify the first type of fault. Thus, the output of the first initial fault identification model includes three categories: normal gear shifting, power intervention and power interruption, i.e. the output dimension of the first initial fault identification model is 3. For the second initial fault identification model, since the model identifies the second type of fault, the second type of fault includes four types: large impact, general impact, large sliding friction, general sliding friction, and therefore, the output dimension of the second initial fault identification model is 4.
After the initial model is constructed, the first initial fault recognition model and the second initial fault recognition model are trained based on the training sample set, and it should be noted that, in order to ensure the final training effect of the model, the more the number of samples included in the training sample set is, the better, in the embodiment of the present specification, the sample data of each fault type in the training sample set is not less than 100 groups. In a specific model training process, training precision and classification accuracy can be set according to actual needs, in the embodiment of the description, the training precision can be set to 0.1, and the output accuracy is set to be greater than 85%.
After the initial model training is completed, a first preset fault recognition model and a second preset fault recognition model are obtained, and the first preset fault recognition model and the second preset fault recognition model can be applied to fault recognition in the gear shifting process. Different output results correspond to different types, for example, if the output result of the first preset fault identification model is 001, the corresponding type is normal gear shifting; if the output result of the first preset fault identification model is 010, the corresponding type is power interference; and if the output result of the first preset fault identification model is 100, the corresponding type is power interruption. If the output result of the second preset fault identification model is 0001, the corresponding type is large impact; if the output result of the second preset fault identification model is 0010, the corresponding type is general impact; if the output result of the second preset fault identification model is 0100, the corresponding type is large sliding friction; if the output result of the second predetermined fault identification model is 1000, the corresponding type is general sliding friction.
Based on the same inventive concept, the embodiment of the present specification provides a fault recognition model training method, where the fault recognition model is used to recognize a shift fault of a hydraulic transmission, and the fault recognition model includes a first preset fault recognition model and a second preset fault recognition model, as shown in fig. 4, the method includes:
step S41: acquiring a training sample set, wherein each sample data in the training sample set comprises a total evaluation index and a stage evaluation index in a one-time gear shifting process, the total evaluation index is an index for representing the overall performance of the gear shifting process, and the stage evaluation index is an index for representing the stage performance of each gear shifting stage in the gear shifting process;
step S42: constructing a first initial fault identification model and a second initial fault identification model;
step S43: training the first initial fault recognition model based on the overall cost performance index corresponding to each sample data and the label information of each sample data to obtain the trained first preset fault recognition model;
step S44: and training the second initial fault recognition model based on the overall evaluation index and the staged evaluation index corresponding to each sample data and the label information of each sample data to obtain the trained second preset fault recognition model.
Optionally, after the acquiring the training sample set, the method further comprises:
and determining the fault type of each sample data as the label information of each sample data based on the corresponding relation between the preset evaluation index and the fault type.
Optionally, the overall evaluation index comprises one or more of the following: the gear shifting method comprises the following steps of shifting time length in the gear shifting process, a peak value of the rotating speed change rate of a turbine shaft in the gear shifting process and a peak value of the rotating speed change rate of an output shaft in the gear shifting process.
Optionally, the shifting process comprises the following stages in chronological order: pre-charging oil, torque, slow reduction of turbine speed, fast reduction of turbine speed and synchronization;
the stage evaluation index comprises one or more of the following indexes: the total reduction amount of the turbine rotating speed in the pre-oil filling stage, the total reduction amount of the turbine rotating speed in a response period after the pre-oil filling stage is ended, the actual time of the torque stage, the total reduction amount of the turbine rotating speed in the torque stage, the actual time of the slow reduction stage of the turbine rotating speed, the total reduction amount of the turbine rotating speed in a response period after the slow reduction stage of the turbine rotating speed, and the actual time of the fast reduction stage of the turbine rotating speed.
With regard to the above method, the specific implementation manner of each step has been described in detail in the embodiment of the method for identifying a failure of a hydraulic transmission provided in the embodiment of the present specification, and will not be elaborated herein.
Based on the same inventive concept as the shift fault identification method of the hydraulic transmission, the embodiment of the present specification provides a shift fault identification device of the hydraulic transmission, as shown in fig. 5, the device includes:
an obtaining module 51, configured to obtain a total evaluation index and a stage evaluation index of a hydraulic transmission during a gear shifting process, where the total evaluation index is an index representing overall performance of the gear shifting process, and the stage evaluation index is an index representing stage performance of each gear shifting stage included in the gear shifting process;
the first processing module 52 is configured to input the overall evaluation index into a first preset fault identification model to obtain a first fault identification result, where the first fault identification result is used to represent whether a fault affecting driving safety occurs in the gear shifting process;
and the second processing module 53 is configured to, when the first fault identification result indicates that no fault affecting driving safety occurs in the gear shifting process, input the overall evaluation index and the periodic evaluation index into a second preset fault identification model to obtain a second fault identification result.
Optionally, the overall evaluation index comprises one or more of the following: the gear shifting method comprises the following steps of shifting time length in the gear shifting process, a peak value of the rotating speed change rate of a turbine shaft in the gear shifting process and a peak value of the rotating speed change rate of an output shaft in the gear shifting process.
Optionally, the shifting process comprises the following stages in chronological order: pre-charging oil, torque, slow reduction of turbine speed, fast reduction of turbine speed and synchronization;
the stage evaluation index comprises one or more of the following indexes: the total reduction amount of the turbine rotating speed in the pre-oil filling stage, the total reduction amount of the turbine rotating speed in a response period after the pre-oil filling stage is ended, the actual time of the torque stage, the total reduction amount of the turbine rotating speed in the torque stage, the actual time of the slow reduction stage of the turbine rotating speed, the total reduction amount of the turbine rotating speed in a response period after the slow reduction stage of the turbine rotating speed, and the actual time of the fast reduction stage of the turbine rotating speed.
Optionally, the first preset fault identification model and the second preset fault identification model are obtained by:
acquiring a training sample set, wherein each sample data in the training sample set comprises a total evaluation index and a stage evaluation index in a one-time gear shifting process;
determining the fault type of each sample data as the label information of each sample data based on the corresponding relation between the preset evaluation index and the fault type;
constructing a first initial fault identification model and a second initial fault identification model;
training the first initial fault recognition model based on the overall cost performance index corresponding to each sample data and the label information of each sample data to obtain the trained first preset fault recognition model;
and training the second initial fault recognition model based on the overall evaluation index and the staged evaluation index corresponding to each sample data and the label information of each sample data to obtain the trained second preset fault recognition model.
With regard to the above-described apparatus, the specific functions of the respective modules have been described in detail in the embodiment of the shift fault identification method of the hydraulic transmission provided in the embodiment of the present specification, and will not be elaborated herein.
Based on the same inventive concept as the fault recognition model training method, the embodiment of the present specification provides a fault recognition model training device, where the fault recognition model is used to recognize a shift fault of a hydraulic transmission, and the fault recognition model includes a first preset fault recognition model and a second preset fault recognition model, as shown in fig. 6, the device includes:
the system comprises a sample obtaining module 61, a calculating module and a calculating module, wherein the sample obtaining module 61 is used for obtaining a training sample set, and each sample data in the training sample set comprises a total evaluation index and a stage evaluation index in a one-time gear shifting process, the total evaluation index is an index for representing the overall performance of the gear shifting process, and the stage evaluation index is an index for representing the stage performance of each gear shifting stage in the gear shifting process;
a model construction module 62 for constructing a first initial fault identification model and a second initial fault identification model;
a first model training module 63, configured to train the first initial fault identification model based on the total cost performance index corresponding to each sample data and the label information of each sample data, to obtain the trained first preset fault identification model;
and a second model training module 64, configured to train the second initial fault recognition model based on the total evaluation index, the periodic evaluation index, and the label information of each sample data corresponding to each sample data, to obtain the trained second preset fault recognition model.
Optionally, the apparatus further comprises:
and the label determining module is used for determining the fault type of each sample data as the label information of each sample data based on the corresponding relation between the preset evaluation index and the fault type.
Optionally, the overall evaluation index comprises one or more of the following: the gear shifting method comprises the following steps of shifting time length in the gear shifting process, a peak value of the rotating speed change rate of a turbine shaft in the gear shifting process and a peak value of the rotating speed change rate of an output shaft in the gear shifting process.
Optionally, the shifting process comprises the following stages in chronological order: pre-charging oil, torque, slow reduction of turbine speed, fast reduction of turbine speed and synchronization;
the stage evaluation index comprises one or more of the following indexes: the total reduction amount of the turbine rotating speed in the pre-oil filling stage, the total reduction amount of the turbine rotating speed in a response period after the pre-oil filling stage is ended, the actual time of the torque stage, the total reduction amount of the turbine rotating speed in the torque stage, the actual time of the slow reduction stage of the turbine rotating speed, the total reduction amount of the turbine rotating speed in a response period after the slow reduction stage of the turbine rotating speed, and the actual time of the fast reduction stage of the turbine rotating speed.
With regard to the above-described apparatus, the specific functions of the respective modules have been described in detail in the embodiment of the shift fault identification method of the hydraulic transmission provided in the embodiment of the present specification, and will not be elaborated herein.
Based on the same inventive concept as the gear shift fault identification method and the fault identification model training method of the hydraulic transmission illustrated in the foregoing embodiments, the present specification further provides an electronic device, as illustrated in fig. 7, including a memory 404, a processor 402, and a computer program stored in the memory 404 and executable on the processor 402, wherein the processor 402 implements the steps of any one of the gear shift fault identification method and the fault identification model training method of the hydraulic transmission described above when executing the program.
Where in fig. 7 a bus architecture (represented by bus 400) is shown, bus 400 may include any number of interconnected buses and bridges, with bus 400 linking together various circuits including one or more processors, represented by processor 402, and memory, represented by memory 404. The bus 400 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 406 provides an interface between the bus 400 and the receiver 401 and transmitter 403. The receiver 401 and the transmitter 403 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 402 is responsible for managing the bus 400 and general processing, while the memory 404 may be used for storing data used by the processor 402 in performing operations.
Based on the inventive concepts of the hydraulic transmission-based gear shift fault identification method and the fault identification model training method in the foregoing embodiments, the present specification further provides a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements the steps of any one of the hydraulic transmission-based gear shift fault identification method and the fault identification model training method described above.
The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present specification have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all changes and modifications that fall within the scope of the specification.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present specification without departing from the spirit and scope of the specification. Thus, if such modifications and variations of the present specification fall within the scope of the claims of the present specification and their equivalents, the specification is intended to include such modifications and variations.

Claims (10)

1. A shift fault identification method of a hydraulic transmission, characterized by comprising:
acquiring a total evaluation index and a stage evaluation index of a hydraulic transmission in a gear shifting process, wherein the total evaluation index is an index for representing the overall performance of the gear shifting process, and the stage evaluation index is an index for representing the stage performance of each gear shifting stage included in the gear shifting process;
inputting the overall evaluation index into a first preset fault recognition model to obtain a first fault recognition result, wherein the first fault recognition result is used for representing whether a fault affecting driving safety occurs in the gear shifting process;
and if the first fault identification result shows that the fault influencing the driving safety does not occur in the gear shifting process, inputting the overall evaluation index and the stage evaluation index into a second preset fault identification model to obtain a second fault identification result.
2. The method of claim 1, wherein the overall evaluation index comprises one or more of the following: the gear shifting method comprises the following steps of shifting time length in the gear shifting process, a peak value of the rotating speed change rate of a turbine shaft in the gear shifting process and a peak value of the rotating speed change rate of an output shaft in the gear shifting process.
3. Method according to claim 1 or 2, characterized in that the shifting process comprises the following phases in chronological order: pre-charging oil, torque, slow reduction of turbine speed, fast reduction of turbine speed and synchronization;
the stage evaluation index comprises one or more of the following indexes: the total reduction amount of the turbine rotating speed in the pre-oil filling stage, the total reduction amount of the turbine rotating speed in a response period after the pre-oil filling stage is ended, the actual time of the torque stage, the total reduction amount of the turbine rotating speed in the torque stage, the actual time of the slow reduction stage of the turbine rotating speed, the total reduction amount of the turbine rotating speed in a response period after the slow reduction stage of the turbine rotating speed, and the actual time of the fast reduction stage of the turbine rotating speed.
4. The method according to claim 1, characterized in that the first and second preset fault identification models are obtained by:
acquiring a training sample set, wherein each sample data in the training sample set comprises a total evaluation index and a stage evaluation index in a one-time gear shifting process;
determining the fault type of each sample data as the label information of each sample data based on the corresponding relation between the preset evaluation index and the fault type;
constructing a first initial fault identification model and a second initial fault identification model;
training the first initial fault recognition model based on the overall cost performance index corresponding to each sample data and the label information of each sample data to obtain the trained first preset fault recognition model;
and training the second initial fault recognition model based on the overall evaluation index and the staged evaluation index corresponding to each sample data and the label information of each sample data to obtain the trained second preset fault recognition model.
5. A fault recognition model training method is characterized in that a fault recognition model is used for recognizing a gear shifting fault of a hydraulic transmission, the fault recognition model comprises a first preset fault recognition model and a second preset fault recognition model, and the method comprises the following steps:
acquiring a training sample set, wherein each sample data in the training sample set comprises a total evaluation index and a stage evaluation index in a one-time gear shifting process, the total evaluation index is an index for representing the overall performance of the gear shifting process, and the stage evaluation index is an index for representing the stage performance of each gear shifting stage in the gear shifting process;
constructing a first initial fault identification model and a second initial fault identification model;
training the first initial fault recognition model based on the overall cost performance index corresponding to each sample data and the label information of each sample data to obtain the trained first preset fault recognition model;
and training the second initial fault recognition model based on the overall evaluation index and the staged evaluation index corresponding to each sample data and the label information of each sample data to obtain the trained second preset fault recognition model.
6. The method of claim 5, wherein after the obtaining of the set of training samples, the method further comprises:
and determining the fault type of each sample data as the label information of each sample data based on the corresponding relation between the preset evaluation index and the fault type.
7. A shift failure recognition device of a hydraulic transmission, characterized by comprising:
the hydraulic transmission control method comprises an acquisition module, a transmission control module and a transmission control module, wherein the acquisition module is used for acquiring a total evaluation index and a stage evaluation index of a hydraulic transmission in a gear shifting process, the total evaluation index is an index for representing the overall performance of the gear shifting process, and the stage evaluation index is an index for representing the stage performance of each gear shifting stage in the gear shifting process;
the first processing module is used for inputting the overall evaluation index into a first preset fault recognition model to obtain a first fault recognition result, and the first fault recognition result is used for representing whether a fault affecting driving safety occurs in the gear shifting process;
and the second processing module is used for inputting the overall evaluation index and the stage evaluation index into a second preset fault recognition model to obtain a second fault recognition result when the first fault recognition result shows that the fault influencing the driving safety does not occur in the gear shifting process.
8. A fault recognition model training apparatus, wherein the fault recognition model is used for recognizing a shift fault of a hydraulic transmission, the fault recognition model includes a first preset fault recognition model and a second preset fault recognition model, the apparatus includes:
the system comprises a sample acquisition module, a shift execution module and a shift execution module, wherein the sample acquisition module is used for acquiring a training sample set, and each sample data in the training sample set comprises a total evaluation index and a stage evaluation index in a one-time shift process, the total evaluation index is an index for representing the overall performance of the shift process, and the stage evaluation index is an index for representing the stage performance of each shift stage in the shift process;
the model construction module is used for constructing a first initial fault identification model and a second initial fault identification model;
the first model training module is used for training the first initial fault recognition model based on the overall cost performance index corresponding to each sample data and the label information of each sample data to obtain the trained first preset fault recognition model;
and the second model training module is used for training the second initial fault recognition model based on the overall evaluation index and the stage evaluation index corresponding to each sample data and the label information of each sample data to obtain the trained second preset fault recognition model.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of any one of claims 1-6 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
CN202111276881.6A 2021-10-29 2021-10-29 Hydraulic transmission gear shifting fault identification method, model training method and device Pending CN113988192A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111276881.6A CN113988192A (en) 2021-10-29 2021-10-29 Hydraulic transmission gear shifting fault identification method, model training method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111276881.6A CN113988192A (en) 2021-10-29 2021-10-29 Hydraulic transmission gear shifting fault identification method, model training method and device

Publications (1)

Publication Number Publication Date
CN113988192A true CN113988192A (en) 2022-01-28

Family

ID=79744858

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111276881.6A Pending CN113988192A (en) 2021-10-29 2021-10-29 Hydraulic transmission gear shifting fault identification method, model training method and device

Country Status (1)

Country Link
CN (1) CN113988192A (en)

Similar Documents

Publication Publication Date Title
CN110633905B (en) Intelligent Che Yun platform reliability calculation method and system
US20220101666A1 (en) Method and Apparatus for Determining a Residual Service Life based on a Predictive Diagnosis of Components of an Electric Drive System Using Artificial Intelligence Techniques
DE102013209013A1 (en) A method of detecting fluid loss or blockage in a hydraulic circuit using an exponentially weighted moving average filter
CN114662954A (en) Vehicle performance evaluation system
KR101565030B1 (en) Decision system for error of car using the data analysis and method therefor
CN111949496B (en) Data detection method and device
CN113988192A (en) Hydraulic transmission gear shifting fault identification method, model training method and device
CN102116371B (en) Stochastic detection of torque converter slip speed and related control
CN103953665A (en) Automatic learning system and method for stroke critical value of clutch
CN104216397A (en) Failure recognition and detection method for intelligent drive axle system
CN108799360B (en) Method for determining the condition of a clutch
CN112065983B (en) Method, device and equipment for detecting abnormal fault of clutch pressure and storage medium
CN112253746B (en) Double-clutch fault detection method and device and storage medium
CN106679967B (en) A kind of detection method and system of torque management device
EP3144565B1 (en) Method for intelligent quick bed-in of an automatic transmission
CN114858110B (en) Detection method and device of clutch position sensor and vehicle
CN115045928B (en) Clutch torque transmission abnormality detection method and device, medium and electronic equipment
Bock et al. Analytical test effort estimation for multisensor driver assistance systems
DE102008004028A1 (en) Method for monitoring the operation of a motor vehicle
Lyu et al. Active fault tolerant approach based on pressure optimal prediction and H∞ control
JP4749951B2 (en) Identification method and program for simulation model
CN111751111A (en) Engine parameter monitoring device and method and vehicle
CN114851778A (en) Drive axle assembly control method and device, medium and electronic equipment
CN115307899A (en) Method and device for detecting and processing slip of torque-limiting shock absorber
CN116085463A (en) Clutch solenoid valve P-I curve self-learning method and system of hybrid transmission

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