CN117473361A - Tire pressure determining method, model training method, device and electronic equipment - Google Patents

Tire pressure determining method, model training method, device and electronic equipment Download PDF

Info

Publication number
CN117473361A
CN117473361A CN202311257855.8A CN202311257855A CN117473361A CN 117473361 A CN117473361 A CN 117473361A CN 202311257855 A CN202311257855 A CN 202311257855A CN 117473361 A CN117473361 A CN 117473361A
Authority
CN
China
Prior art keywords
tire pressure
information sequence
prediction model
sample
tire
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
CN202311257855.8A
Other languages
Chinese (zh)
Inventor
杨佳宁
周建武
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.)
ZF Commercial Vehicle Systems Qingdao Co Ltd
Original Assignee
ZF Commercial Vehicle Systems Qingdao 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 ZF Commercial Vehicle Systems Qingdao Co Ltd filed Critical ZF Commercial Vehicle Systems Qingdao Co Ltd
Priority to CN202311257855.8A priority Critical patent/CN117473361A/en
Publication of CN117473361A publication Critical patent/CN117473361A/en
Pending legal-status Critical Current

Links

Classifications

    • 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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/10—Pre-processing; Data cleansing
    • G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G06N3/0455—Auto-encoder networks; Encoder-decoder 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation

Abstract

The application provides a tire pressure determining method, a model training method, a device and electronic equipment. The method comprises the following steps: acquiring a speed information sequence and a temperature information sequence of a preset time period in the running process of a target vehicle; after the speed information sequence and the temperature information sequence are mapped to the same data range, the speed information sequence and the temperature information sequence are input into the tire pressure prediction model, the tire pressure level output by the tire pressure prediction model is obtained, different tire pressure levels are used for indicating different tire pressure ranges, the tire pressure prediction model is obtained by training based on the speed information, the temperature information and the tire pressure level of a sample vehicle, and therefore the accuracy of tire pressure detection is improved.

Description

Tire pressure determining method, model training method, device and electronic equipment
Technical Field
The present disclosure relates to vehicle technologies, and in particular, to a tire pressure determining method, a model training method, a device, and an electronic apparatus.
Background
Tire pressure, i.e., tire pressure, is related to vehicle running resistance, running safety, etc., and it is critical to accurately detect tire pressure during vehicle running.
The most direct tire pressure detection method is to install a pressure sensor inside a tire, directly detect the tire pressure by the pressure sensor, and transmit the tire pressure to an electronic control unit (Electronic Control Unit, ECU) of the vehicle. However, for large commercial vehicles, such as trucks and trailers, the total number of tires may be more than 20, and if a pressure sensor is installed for each tire in practical use, the cost is quite high, so an indirect tire pressure detecting method is proposed in the related art.
The conventional indirect tire pressure detecting method detects by utilizing the difference of the rotational speeds of the tires, if the pressure of one tire is reduced, the radius of the tire is reduced, and the corresponding tire speed is higher, but the method needs a great amount of earlier calibration work to determine the mapping relation between the tire speed and the tire pressure, the calibration work is complex, and the calibration result is greatly influenced by the individual difference of the tires, so the accuracy is often lower.
Disclosure of Invention
The application provides a tire pressure determining method, a model training method, a device and electronic equipment, and the accuracy of tire pressure detection is improved.
In a first aspect, the present application provides a tire pressure determining method, including:
acquiring a speed information sequence and a temperature information sequence of a preset time period in the running process of a target vehicle;
and after the speed information sequence and the temperature information sequence are mapped to the same data range, the speed information sequence and the temperature information sequence are input into a tire pressure prediction model, the tire pressure level output by the tire pressure prediction model is obtained, different tire pressure levels are used for indicating different tire pressure ranges, and the tire pressure prediction model is obtained by training based on the speed information, the temperature information and the tire pressure level of a sample vehicle.
In one embodiment, the acquiring the speed information sequence and the temperature information sequence of the preset time period during the driving process of the target vehicle includes:
and in the running process of the target vehicle, carrying out data sampling for a preset time period according to preset frequencies corresponding to the speed information and the temperature information respectively to obtain the speed information sequence and the temperature information sequence.
In one embodiment, the speed information sequence includes a tire rotation speed sequence, or the speed information sequence includes a tire rotation speed sequence and a vehicle running speed sequence, where a sampling frequency corresponding to the tire rotation speed is higher than a tire resonance frequency;
the temperature information sequence includes a tire internal temperature sequence and/or a tire ambient temperature sequence.
In one embodiment, the method further comprises:
and acquiring the tire pressure prediction model sent by the service equipment, wherein the tire pressure prediction model is obtained by training the service equipment based on the speed information, the temperature information and the tire pressure level of the sample vehicle.
In one embodiment, the method further comprises:
in the running process of the target vehicle, acquiring a target tire pressure level in a preset time period, wherein the target tire pressure level is determined based on a tire pressure measured value, and the tire pressure measured value is detected by a pressure sensor arranged in a tire;
and updating parameters of the tire pressure prediction model based on the target tire pressure level and the tire pressure level output by the tire pressure prediction model to obtain an updated tire pressure prediction model.
In a second aspect, the present application provides a training method of a tire pressure prediction model, including:
acquiring a sample speed information sequence, a sample temperature information sequence and a sample target tire pressure level of a sample vehicle in a preset time period, wherein the sample target tire pressure level is determined based on a tire pressure measured value, and the tire pressure measured value is detected by a pressure sensor arranged in a tire;
after the sample speed information sequence and the sample temperature information sequence are mapped to the same data range, inputting the sample speed information sequence and the sample temperature information sequence into an initial prediction model to obtain a sample tire pressure level output by the initial prediction model, and updating parameters of the initial prediction model based on the sample tire pressure level and the sample target tire pressure level until a model convergence condition is reached to obtain the tire pressure prediction model;
and sending the tire pressure prediction model to a target vehicle, wherein the tire pressure prediction model is used for predicting the tire pressure level of the target vehicle based on a speed information sequence and a temperature information sequence of a preset time period in the running process of the target vehicle.
In one embodiment, the method further comprises:
receiving a speed information sequence, a temperature information sequence and a target tire pressure level of a preset time period in the running process sent by the target vehicle;
and mapping the speed information sequence and the temperature information sequence to the same data range, inputting the speed information sequence and the temperature information sequence into the tire pressure prediction model to obtain the tire pressure level output by the tire pressure prediction model, updating parameters of the tire pressure prediction model based on the tire pressure level and the target tire pressure level, and sending the updated tire pressure prediction model to the target vehicle.
In a third aspect, the present application provides a tire pressure determining apparatus, comprising:
the acquisition module is used for acquiring a speed information sequence and a temperature information sequence of a preset time period in the running process of the target vehicle;
the prediction module is used for mapping the speed information sequence and the temperature information sequence to the same data range, inputting the speed information sequence and the temperature information sequence into the tire pressure prediction model to obtain the tire pressure level output by the tire pressure prediction model, wherein different tire pressure levels are used for indicating different tire pressure ranges, and the tire pressure prediction model is obtained by training based on the speed information, the temperature information and the tire pressure level of a sample vehicle.
In one embodiment, the obtaining module is configured to:
and in the running process of the target vehicle, carrying out data sampling for a preset time period according to preset frequencies corresponding to the speed information and the temperature information respectively to obtain the speed information sequence and the temperature information sequence.
In one embodiment, the speed information sequence includes a tire rotation speed sequence, or the speed information sequence includes a tire rotation speed sequence and a vehicle running speed sequence, where a sampling frequency corresponding to the tire rotation speed is higher than a tire resonance frequency;
the temperature information sequence includes a tire internal temperature sequence and/or a tire ambient temperature sequence.
In one embodiment, the acquisition module is further configured to:
and acquiring the tire pressure prediction model sent by the service equipment, wherein the tire pressure prediction model is obtained by training the service equipment based on the speed information, the temperature information and the tire pressure level of the sample vehicle.
In one embodiment, the acquisition module is further configured to:
in the running process of the target vehicle, acquiring a target tire pressure level in a preset time period, wherein the target tire pressure level is determined based on a tire pressure measured value, and the tire pressure measured value is detected by a pressure sensor arranged in a tire;
the tire pressure determining apparatus further includes: training module for:
and updating parameters of the tire pressure prediction model based on the target tire pressure level and the tire pressure level output by the tire pressure prediction model to obtain an updated tire pressure prediction model.
In a fourth aspect, the present application provides a training device for a tire pressure prediction model, including:
the system comprises a sample acquisition module, a tire pressure detection module and a tire pressure detection module, wherein the sample acquisition module is used for acquiring a sample speed information sequence, a sample temperature information sequence and a sample target tire pressure level of a sample vehicle in a preset time period, wherein the sample target tire pressure level is determined based on a tire pressure measurement value, and the tire pressure measurement value is detected by a pressure sensor arranged in a tire;
the training module is used for mapping the sample speed information sequence and the sample temperature information sequence to the same data range, inputting the sample speed information sequence and the sample temperature information sequence into an initial prediction model to obtain a sample tire pressure level output by the initial prediction model, and updating parameters of the initial prediction model based on the sample tire pressure level and the sample target tire pressure level until a model convergence condition is reached to obtain the tire pressure prediction model;
and the transmitting module is used for transmitting the tire pressure prediction model to a target vehicle, and the tire pressure prediction model is used for predicting the tire pressure level of the target vehicle based on a speed information sequence and a temperature information sequence of a preset time period in the running process of the target vehicle.
In one embodiment, the training device further comprises:
the receiving module is used for receiving a speed information sequence, a temperature information sequence and a target tire pressure level of a preset time period in the running process sent by the target vehicle;
the training module is used for mapping the speed information sequence and the temperature information sequence to the same data range, inputting the speed information sequence and the temperature information sequence into the tire pressure prediction model to obtain the tire pressure level output by the tire pressure prediction model, and updating the parameters of the tire pressure prediction model based on the tire pressure level and the target tire pressure level;
the transmitting module is used for transmitting the updated tire pressure prediction model to the target vehicle.
In a fifth aspect, the present application provides an electronic device, comprising: memory, processor, and transceiver;
the memory is used for storing a computer program;
the processor is configured to implement the method according to the first or second aspect as described above when the computer program is executed.
In a sixth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method as described in the first or second aspect above.
In a seventh aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, implements the method according to the first or second aspect described above.
The tire pressure determining method, the model training method, the device and the electronic equipment can be used for determining the tire pressure based on the speed information and the temperature information, can replace a direct detection method by using a pressure sensor to reduce hardware cost, and can make up for the defects of other indirect detection methods by adopting a machine learning model method, does not depend on the prior calibration work, and improves the accuracy of the indirect detection method.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief description will be given below of the drawings that are needed in the embodiments or the prior art descriptions, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
Fig. 1 is a schematic flow chart of a tire pressure determining method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a tire pressure prediction model according to an embodiment of the present application;
fig. 3 is a flow chart of a training method of a tire pressure prediction model according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a tire pressure determining device according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a training device for a tire pressure prediction model according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The embodiment of the application provides an indirect tire pressure determining method, which considers that the tire pressure is related to the tire resonance frequency, the tire resonance frequency can be obtained from the tire rotating speed, and meanwhile, the temperature is another factor affecting the tire resonance frequency, so that the tire rotating speed and the temperature are taken as factors for determining the tire pressure, the predicted tire pressure level is determined by utilizing a machine learning model based on the tire rotating speed and the temperature, and the accuracy of tire pressure monitoring is improved.
The following will explain in detail specific examples. It is to be understood that the following embodiments may be combined with each other and that some embodiments may not be repeated for the same or similar concepts or processes.
Fig. 1 is a schematic flow chart of a tire pressure determining method according to an embodiment of the present application. The execution subject of the method is a tire pressure determining device, which may refer to a target vehicle, an in-vehicle apparatus or an in-vehicle system disposed in the target vehicle, or the like, or may refer to a module disposed in the in-vehicle apparatus or the in-vehicle system. The method comprises the following steps:
s101, acquiring a speed information sequence and a temperature information sequence of a preset time period in the running process of a target vehicle.
And in the running process of the target vehicle, sampling the speed information and the temperature information respectively to obtain a corresponding information sequence. Optionally, in the driving process of the target vehicle, data sampling is performed for a preset time period according to preset frequencies corresponding to the speed information and the temperature information respectively, so as to obtain a speed information sequence and a temperature information sequence.
Optionally, the speed information sequence includes a tire rotation speed sequence, or the speed information sequence includes a tire rotation speed sequence and a vehicle running speed sequence; the temperature information sequence includes a tire internal temperature sequence and/or a tire ambient temperature sequence. For example, the tire resonance frequency is generally below 100Hz, and the sampling frequency corresponding to the tire rotation speed needs to be higher than the tire resonance frequency, for example, the sampling frequency corresponding to the tire rotation speed may be set to 100Hz. The sampling frequency of the vehicle running speed, the tire internal temperature, and the tire ambient temperature may be relatively low, such as 1Hz. Assuming that the preset time period is 10s, the tire rotation speed is sampled for 10s at a frequency of 100Hz in the sampling process, and meanwhile, the vehicle running speed, the tire internal temperature and the tire environment temperature are sampled for 10s at a frequency of 1Hz.
The tire rotational speed, the vehicle running speed, the tire internal temperature and the tire environmental temperature can be obtained by the data of the existing sensors or devices in the vehicle, the method for obtaining the data is not limited in the embodiment of the application, the tire rotational speed can be detected by the wheel speed sensor mounted on the wheel hub or the wheel axle, the vehicle running speed can be obtained based on the data of the global positioning system (Global Positioning System, GPS) or the inertial sensor (InerTIal measurement unit, IMU), the tire internal temperature can be obtained by the special sensors mounted in the tire, the tire environmental temperature can be detected by the temperature sensor mounted on the vehicle and far from other heat sources, or the tire environmental temperature can also be provided by the weather temperature provided by other data sources.
S102, after the speed information sequence and the temperature information sequence are mapped to the same data range, the speed information sequence and the temperature information sequence are input into a tire pressure prediction model, tire pressure levels output by the tire pressure prediction model are obtained, different tire pressure levels are used for indicating different tire pressure ranges, and the tire pressure prediction model is obtained by training based on speed information, temperature information and tire pressure levels of a sample vehicle.
In this embodiment of the present application, the speed information and the temperature information are sampled sequence data, so a module capable of processing the sequence data is adopted in the tire pressure prediction model, as shown in fig. 2, a cyclic neural network (Recurrent Neural Network, RNN) or a transducer-Encoder is adopted to process the input sequence, so as to obtain multidimensional vectors corresponding to each sequence, then the multidimensional vectors corresponding to each sequence are spliced, the spliced multidimensional vectors are input into a Multi-Layer neural network (MLP) to obtain output tire pressure levels, and the number of output neurons of the model corresponds to the number of divided tire pressure levels. It should be understood that fig. 2 is only an exemplary model architecture, and the number and serial connection of the modules may be adjusted according to needs in practical applications, or other modules with the same or similar functions may be substituted for the modules, which is not limited in the embodiments of the present application.
Since the numerical ranges of the speed information and the temperature information may be greatly different, in order to eliminate the dimensional influence between the data features, the speed information sequence and the temperature information sequence are each normalized and mapped to the same data range, for example, the speed information sequence is mapped to [0,1] based on a first mapping coefficient, which may be determined based on the numerical range of the speed information, the temperature information sequence is mapped to [0,1] based on a second mapping coefficient, which may be determined based on the numerical range of the temperature information, and then the mapped speed information sequence and temperature information sequence are input into the tire pressure prediction model to obtain the tire pressure level output by the model. It is understood that the tire rotation speed input into the model and the tire pressure level output from the model correspond to the same tire, and that the tire pressure level of each tire can be obtained based on the tire rotation speed of the tire for a plurality of tires of the vehicle.
The method of the embodiment of the application adopts an indirect mode to determine the tire pressure, can replace a direct detection method by using a pressure sensor to reduce hardware cost, and adopts a machine learning model method, so that the defects of other indirect detection methods can be overcome, the method does not depend on the prior calibration work, and the accuracy of the indirect detection method is improved. In addition, the method can be used as a supplement of a direct detection method, and the reliability of the tire pressure detection result is improved.
The following describes a training process of the tire pressure prediction model. According to the tire pressure prediction model training method and device, the service equipment can be used for training the initial prediction model to obtain the tire pressure prediction model, namely the tire pressure prediction model is obtained by training the service equipment based on speed information, temperature information and tire pressure level of a sample vehicle. The service equipment deploys the tire pressure prediction model into the target vehicle, and in the running process of the target vehicle, the model can be updated by utilizing data in the running process of the vehicle, the model updating can be completed by the vehicle, or the data in the running process can be returned to the service equipment by the vehicle, and the service equipment deploys the updated model to the target vehicle again after the model updating is completed. The service device may be a local personal computer or server, or the service device may be a cloud device.
Fig. 3 is a flowchart of a training method of a tire pressure prediction model according to an embodiment of the present application. The execution subject of the method is a training device of the tire pressure prediction model, and the training device can be the service equipment. As shown in fig. 3, the method includes:
s301, acquiring a sample speed information sequence, a sample temperature information sequence and a sample target tire pressure level of a sample vehicle in a preset time period, wherein the sample target tire pressure level is determined based on a tire pressure measured value, and the tire pressure measured value is detected by a pressure sensor arranged inside a tire.
The process of acquiring the speed information and the temperature information of the sample vehicle is similar to that in the foregoing embodiment, and will not be described here again. The tire pressure level of the sample target is used as a tire pressure level reference value in the model training process, the tire pressure reference value is determined through a tire pressure measurement value, and the tire pressure measurement value is a more accurate value obtained based on detection of a pressure sensor, that is, for a sample vehicle, the pressure sensor is required to be arranged in the tire to obtain the tire pressure level of the sample target.
When the model is trained, the tire pressure levels are divided according to actual conditions, and the tire pressures in different ranges are divided into different tire pressure levels according to the values of the tire pressures. Exemplary, as shown in table 1 below:
TABLE 1
Tire pressure (bar) Tire pressure level
<2.0 Too low a pressure
[2.0,2.1) Level 1
[2.1,2.2) Level 2
[2.2,2.3) Level 3
[2.3,2.4) Level 4
[2.4,2.5) Level 5
[2.5,2.6) Level 6
[2.6,2.7) Level 7
[2.7,2.8) Level 8
[2.8,2.9) Level 9
[2.9,3.0) Level 10
≥3.0 Too high pressure
S302, after the sample speed information sequence and the sample temperature information sequence are mapped to the same data range, the sample speed information sequence and the sample temperature information sequence are input into an initial prediction model to obtain a sample tire pressure level output by the initial prediction model, and parameters of the initial prediction model are updated based on the sample tire pressure level and a sample target tire pressure level until a model convergence condition is reached to obtain the tire pressure prediction model.
And carrying out normalization processing on the sample speed information sequence and the sample temperature information sequence, mapping the sample speed information sequence and the sample temperature information sequence to the same data range, inputting the sample speed information sequence and the sample temperature information sequence into an initial prediction model of the framework shown in fig. 2, updating model parameters based on the sample tire pressure level and the sample target tire pressure level output by the model, and obtaining the tire pressure prediction model when the model convergence condition is reached through training of a large amount of sample data.
And S303, transmitting a tire pressure prediction model to the target vehicle, wherein the tire pressure prediction model is used for predicting the tire pressure level of the target vehicle based on the speed information sequence and the temperature information sequence of a preset time period in the running process of the target vehicle.
After the training of the tire pressure prediction model is completed, the tire pressure prediction model is sent to the target vehicle, so that the target vehicle can determine the tire pressure through the tire pressure prediction model based on data in the driving process.
In the training method of the tire pressure prediction model, the service equipment can train the model based on a large number of training samples, and the model can adapt to individual differences among tires and has higher accuracy.
On the basis of the above embodiment, in one implementation manner, the service device may receive a speed information sequence, a temperature information sequence, and a target tire pressure level of a preset time period in a driving process sent by the target vehicle; and mapping the speed information sequence and the temperature information sequence to the same data range, inputting the speed information sequence and the temperature information sequence into the tire pressure prediction model, obtaining the tire pressure level output by the tire pressure prediction model, updating the parameters of the tire pressure prediction model based on the tire pressure level and the target tire pressure level, and transmitting the updated tire pressure prediction model to the target vehicle. In this way, the service device can perform model update based on data in the running process of a large number of vehicles, so that model accuracy is higher.
In another implementation manner, after the target vehicle obtains the tire pressure prediction model sent by the service device, in the driving process, the target vehicle obtains a speed information sequence and a temperature information sequence of a preset time period, obtains a target tire pressure level of the preset time period based on the tire pressure prediction model, and the target tire pressure level is determined based on a tire pressure measured value, wherein the tire pressure measured value is detected by a pressure sensor arranged in the tire; and the target vehicle updates parameters of the tire pressure prediction model based on the target tire pressure level and the tire pressure level output by the tire pressure prediction model to obtain an updated tire pressure prediction model. In the mode, the target vehicle can quickly update the model based on the data in the driving process, so that the model is more in line with the actual situation of the target vehicle, and the accuracy is improved.
In the above two implementations, the precondition for updating the tire pressure prediction model based on the data during the driving of the target vehicle is that a pressure sensor is disposed in at least one tire of the target vehicle to obtain the target tire pressure level of the tire, so that the model update can be performed based on the data of the tire.
Fig. 4 is a schematic structural diagram of a tire pressure determining apparatus according to an embodiment of the present application, and as shown in fig. 4, the tire pressure determining apparatus 400 includes:
an acquisition module 401, configured to acquire a speed information sequence and a temperature information sequence of a preset time period during a driving process of a target vehicle;
the prediction module 402 is configured to map the speed information sequence and the temperature information sequence to the same data range, and then input the speed information sequence and the temperature information sequence to a tire pressure prediction model to obtain a tire pressure level output by the tire pressure prediction model, where different tire pressure levels are used to indicate different tire pressure ranges, and the tire pressure prediction model is obtained by training based on speed information, temperature information and tire pressure levels of a sample vehicle.
In one embodiment, the obtaining module 401 is configured to:
and in the running process of the target vehicle, carrying out data sampling for a preset time period according to preset frequencies corresponding to the speed information and the temperature information respectively to obtain a speed information sequence and a temperature information sequence.
In one embodiment, the speed information sequence includes a tire rotational speed sequence, or the speed information sequence includes a tire rotational speed sequence and a vehicle running speed sequence, wherein the tire rotational speed corresponds to a sampling frequency that is higher than a tire resonant frequency;
the temperature information sequence includes a tire internal temperature sequence and/or a tire ambient temperature sequence.
In one embodiment, the obtaining module 401 is further configured to:
the tire pressure prediction model sent by the service equipment is obtained by training the service equipment based on speed information, temperature information and tire pressure level of the sample vehicle.
In one embodiment, the obtaining module 401 is further configured to:
in the running process of a target vehicle, acquiring a target tire pressure level in a preset time period, wherein the target tire pressure level is determined based on a tire pressure measured value, and the tire pressure measured value is detected by a pressure sensor arranged in a tire;
the tire pressure determining apparatus 400 further includes: training module 403 for:
and updating parameters of the tire pressure prediction model based on the target tire pressure level and the tire pressure level output by the tire pressure prediction model to obtain an updated tire pressure prediction model.
The tire pressure determining device provided in the embodiment of the present application may be used to implement the tire pressure determining method in the foregoing method embodiment, and the implementation principle and technical effects are similar, and are not repeated here.
Fig. 5 is a schematic structural diagram of a training device for a tire pressure prediction model according to an embodiment of the present application, and as shown in fig. 5, a training device 500 for a tire pressure prediction model includes:
the sample acquiring module 501 is configured to acquire a sample speed information sequence, a sample temperature information sequence, and a sample target tire pressure level of a sample vehicle in a preset time period, where the sample target tire pressure level is determined based on a tire pressure measurement value, and the tire pressure measurement value is detected by a pressure sensor disposed inside a tire;
the training module 502 is configured to map the sample speed information sequence and the sample temperature information sequence to the same data range, and then input the sample speed information sequence and the sample temperature information sequence into an initial prediction model to obtain a sample tire pressure level output by the initial prediction model, and update parameters of the initial prediction model based on the sample tire pressure level and the sample target tire pressure level until a model convergence condition is reached, so as to obtain the tire pressure prediction model;
a sending module 503, configured to send the tire pressure prediction model to a target vehicle, where the tire pressure prediction model is configured to predict a tire pressure level of the target vehicle based on a speed information sequence and a temperature information sequence of a preset time period during a driving process of the target vehicle.
In one embodiment, the training device further comprises:
the receiving module 504 is configured to receive a speed information sequence, a temperature information sequence, and a target tire pressure level of a preset time period in a driving process sent by a target vehicle;
the training module 502 is configured to map the speed information sequence and the temperature information sequence to the same data range, and then input the speed information sequence and the temperature information sequence into the tire pressure prediction model to obtain a tire pressure level output by the tire pressure prediction model, and update parameters of the tire pressure prediction model based on the tire pressure level and the target tire pressure level;
a transmitting module 503, configured to transmit the updated tire pressure prediction model to the target vehicle.
The training device for the tire pressure prediction model provided by the embodiment of the application can be used for realizing the training method for the tire pressure prediction model in the embodiment of the method, and the implementation principle and the technical effect are similar, and are not repeated here.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 6, the electronic device 600 includes: a memory 601, a processor 602, a transceiver 603, wherein the memory 601 is in communication with the processor 602; illustratively, the memory 601, the processor 602 and the transceiver 603 may communicate via a communication bus 604, the memory 601 being for storing a computer program, the processor 602 executing the computer program to perform the methods of the above embodiments. The electronic device 600 may be the target vehicle, the in-vehicle device or the in-vehicle system disposed in the target vehicle, or the like in the foregoing embodiment, or a module disposed in the in-vehicle device or the in-vehicle system, or a service device.
Alternatively, the processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of an embodiment of a method disclosed in connection with the present application may be embodied directly in a hardware processor or in a combination of hardware and software modules in a processor.
Embodiments of the present application also provide a computer-readable storage medium, including: on which a computer program is stored which, when being executed by a processor, implements the method of any of the method embodiments described above.
Embodiments of the present application also provide a computer program product comprising a computer program which, when executed by a processor, implements the method of any of the above-described method embodiments.
All or part of the steps for implementing the method embodiments described above may be performed by hardware associated with program instructions. The foregoing program may be stored in a readable memory. The program, when executed, performs steps including the method embodiments described above; and the aforementioned memory (storage medium) includes: read-only memory (ROM), RAM, flash memory, hard disk, solid state disk, magnetic tape, floppy disk, optical disk (optical disc), and any combination thereof.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processing unit 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 processing unit 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.
It will be apparent to those skilled in the art that various modifications and variations can be made to the embodiments of the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the embodiments of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to encompass such modifications and variations.
In the present application, the term "include" and variations thereof may refer to non-limiting inclusion; the term "or" and variations thereof may refer to "and/or". The terms "first," "second," and the like in this application are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. In the present application, "plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship.

Claims (12)

1. A tire pressure determining method, characterized by comprising:
acquiring a speed information sequence and a temperature information sequence of a preset time period in the running process of a target vehicle;
and after the speed information sequence and the temperature information sequence are mapped to the same data range, the speed information sequence and the temperature information sequence are input into a tire pressure prediction model, the tire pressure level output by the tire pressure prediction model is obtained, different tire pressure levels are used for indicating different tire pressure ranges, and the tire pressure prediction model is obtained by training based on the speed information, the temperature information and the tire pressure level of a sample vehicle.
2. The method according to claim 1, wherein the acquiring the speed information sequence and the temperature information sequence for a preset period of time during the driving of the target vehicle includes:
and in the running process of the target vehicle, carrying out data sampling for a preset time period according to preset frequencies corresponding to the speed information and the temperature information respectively to obtain the speed information sequence and the temperature information sequence.
3. The method of claim 2, wherein the step of determining the position of the substrate comprises,
the speed information sequence comprises a tire rotating speed sequence, or the speed information sequence comprises a tire rotating speed sequence and a vehicle running speed sequence, wherein the sampling frequency corresponding to the tire rotating speed is higher than the tire resonant frequency;
the temperature information sequence includes a tire internal temperature sequence and/or a tire ambient temperature sequence.
4. A method according to any one of claims 1-3, further comprising:
and acquiring the tire pressure prediction model sent by the service equipment, wherein the tire pressure prediction model is obtained by training the service equipment based on the speed information, the temperature information and the tire pressure level of the sample vehicle.
5. The method as recited in claim 4, further comprising:
in the running process of the target vehicle, acquiring a target tire pressure level in a preset time period, wherein the target tire pressure level is determined based on a tire pressure measured value, and the tire pressure measured value is detected by a pressure sensor arranged in a tire;
and updating parameters of the tire pressure prediction model based on the target tire pressure level and the tire pressure level output by the tire pressure prediction model to obtain an updated tire pressure prediction model.
6. A training method of a tire pressure prediction model, comprising:
acquiring a sample speed information sequence, a sample temperature information sequence and a sample target tire pressure level of a sample vehicle in a preset time period, wherein the sample target tire pressure level is determined based on a tire pressure measured value, and the tire pressure measured value is detected by a pressure sensor arranged in a tire;
after the sample speed information sequence and the sample temperature information sequence are mapped to the same data range, inputting the sample speed information sequence and the sample temperature information sequence into an initial prediction model to obtain a sample tire pressure level output by the initial prediction model, and updating parameters of the initial prediction model based on the sample tire pressure level and the sample target tire pressure level until a model convergence condition is reached to obtain the tire pressure prediction model;
and sending the tire pressure prediction model to a target vehicle, wherein the tire pressure prediction model is used for predicting the tire pressure level of the target vehicle based on a speed information sequence and a temperature information sequence of a preset time period in the running process of the target vehicle.
7. The method as recited in claim 6, further comprising:
receiving a speed information sequence, a temperature information sequence and a target tire pressure level of a preset time period in the running process sent by the target vehicle;
and mapping the speed information sequence and the temperature information sequence to the same data range, inputting the speed information sequence and the temperature information sequence into the tire pressure prediction model to obtain the tire pressure level output by the tire pressure prediction model, updating parameters of the tire pressure prediction model based on the tire pressure level and the target tire pressure level, and sending the updated tire pressure prediction model to the target vehicle.
8. A tire pressure determining apparatus, characterized by comprising:
the acquisition module is used for acquiring a speed information sequence and a temperature information sequence of a preset time period in the running process of the target vehicle;
the prediction module is used for mapping the speed information sequence and the temperature information sequence to the same data range, inputting the speed information sequence and the temperature information sequence into the tire pressure prediction model to obtain the tire pressure level output by the tire pressure prediction model, wherein different tire pressure levels are used for indicating different tire pressure ranges, and the tire pressure prediction model is obtained by training based on the speed information, the temperature information and the tire pressure level of a sample vehicle.
9. A training device for a tire pressure prediction model, comprising:
the system comprises a sample acquisition module, a tire pressure detection module and a tire pressure detection module, wherein the sample acquisition module is used for acquiring a sample speed information sequence, a sample temperature information sequence and a sample target tire pressure level of a sample vehicle in a preset time period, wherein the sample target tire pressure level is determined based on a tire pressure measurement value, and the tire pressure measurement value is detected by a pressure sensor arranged in a tire;
the training module is used for mapping the sample speed information sequence and the sample temperature information sequence to the same data range, inputting the sample speed information sequence and the sample temperature information sequence into an initial prediction model to obtain a sample tire pressure level output by the initial prediction model, and updating parameters of the initial prediction model based on the sample tire pressure level and the sample target tire pressure level until a model convergence condition is reached to obtain the tire pressure prediction model;
and the transmitting module is used for transmitting the tire pressure prediction model to a target vehicle, and the tire pressure prediction model is used for predicting the tire pressure level of the target vehicle based on a speed information sequence and a temperature information sequence of a preset time period in the running process of the target vehicle.
10. An electronic device, comprising: memory, processor, and transceiver;
the memory is used for storing a computer program;
the processor is adapted to implement the method of any of the preceding claims 1-5 or 6-7 when the computer program is executed.
11. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method according to any of the preceding claims 1-5 or 6-7.
12. A computer program product comprising a computer program which, when executed by a processor, implements the method of any of claims 1-5 or 6-7.
CN202311257855.8A 2023-09-26 2023-09-26 Tire pressure determining method, model training method, device and electronic equipment Pending CN117473361A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311257855.8A CN117473361A (en) 2023-09-26 2023-09-26 Tire pressure determining method, model training method, device and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311257855.8A CN117473361A (en) 2023-09-26 2023-09-26 Tire pressure determining method, model training method, device and electronic equipment

Publications (1)

Publication Number Publication Date
CN117473361A true CN117473361A (en) 2024-01-30

Family

ID=89622925

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311257855.8A Pending CN117473361A (en) 2023-09-26 2023-09-26 Tire pressure determining method, model training method, device and electronic equipment

Country Status (1)

Country Link
CN (1) CN117473361A (en)

Similar Documents

Publication Publication Date Title
CN109808428B (en) System and method for vehicle tire pressure monitoring system location
US8515703B2 (en) Method for calibrating a wheel speed detection system
US7336161B2 (en) Tire pressure monitoring system
US10006895B2 (en) System and method for monitoring atmospheric pollution
US20180215391A1 (en) Methods and systems for detecting road surface using crowd-sourced driving behaviors
US11634148B2 (en) Method, apparatus, storage medium and electronic device for testing dynamic parameter of vehicle
CN109249934A (en) A kind of tire wear calculation method of parameters, system and device
CN109572334A (en) Combined type tire pressure monitoring method and tire pressure monitoring equipment
US10173691B2 (en) Vehicle sensor calibration using wireless network-connected sensors
CN107554529B (en) Method and system for calculating vehicle speed of commercial vehicle
CN110455549B (en) Diagnostic device, diagnostic system, and diagnostic method
CN108237848A (en) Tire location localization method and device
CN110431026A (en) For determining method, control device and the system of the pattern depth of tyre tread
US11668842B2 (en) Method for satellite-based determination of a vehicle position
US11124026B2 (en) Method, control device and system for ascertaining tread depths of tires on vehicles
WO2021194695A1 (en) Determining tread depth using data from a tire-mounted sensor
CN110143200A (en) A kind of vehicle status data acquisition methods, device, mobile unit and storage medium
CN114734762B (en) Tire pressure monitoring method, controller, system and electronic equipment
CN111947669A (en) Method for using feature-based positioning maps for vehicles
US20170210185A1 (en) Wheel position detecting device and tire air pressure detecting apparatus having the same
CN110456759A (en) Diagnostic device, diagnostic system and diagnostic method
CN117473361A (en) Tire pressure determining method, model training method, device and electronic equipment
CN110362059B (en) Diagnostic device and diagnostic method
JP2021070341A (en) Wear amount estimation system and arithmetic model generation system
CN111157018B (en) Detection method, detection device and automatic driving vehicle

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