CN114379294A - OBD (on-board diagnostics) combined type tire pressure monitoring method and system - Google Patents
OBD (on-board diagnostics) combined type tire pressure monitoring method and system Download PDFInfo
- Publication number
- CN114379294A CN114379294A CN202210291577.7A CN202210291577A CN114379294A CN 114379294 A CN114379294 A CN 114379294A CN 202210291577 A CN202210291577 A CN 202210291577A CN 114379294 A CN114379294 A CN 114379294A
- Authority
- CN
- China
- Prior art keywords
- tire pressure
- wheel
- pressure value
- abnormal
- obd
- 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.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60C—VEHICLE TYRES; TYRE INFLATION; TYRE CHANGING; CONNECTING VALVES TO INFLATABLE ELASTIC BODIES IN GENERAL; DEVICES OR ARRANGEMENTS RELATED TO TYRES
- B60C23/00—Devices for measuring, signalling, controlling, or distributing tyre pressure or temperature, specially adapted for mounting on vehicles; Arrangement of tyre inflating devices on vehicles, e.g. of pumps or of tanks; Tyre cooling arrangements
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60C—VEHICLE TYRES; TYRE INFLATION; TYRE CHANGING; CONNECTING VALVES TO INFLATABLE ELASTIC BODIES IN GENERAL; DEVICES OR ARRANGEMENTS RELATED TO TYRES
- B60C23/00—Devices for measuring, signalling, controlling, or distributing tyre pressure or temperature, specially adapted for mounting on vehicles; Arrangement of tyre inflating devices on vehicles, e.g. of pumps or of tanks; Tyre cooling arrangements
- B60C23/02—Signalling devices actuated by tyre pressure
- B60C23/04—Signalling devices actuated by tyre pressure mounted on the wheel or tyre
Abstract
The invention discloses an OBD composite tire pressure monitoring method and system, wherein the method comprises the following steps: acquiring the rotating speed of each wheel in the running process of the vehicle, and calculating to obtain the tire pressure value of each wheel; judging whether the tire pressure of each wheel is abnormal or not; constructing a recurrent neural network model based on the wheel rotating speed; outputting the predicted tire pressure value of the abnormal wheel at the next moment by using a recurrent neural network model; calculating the variation between the predicted tire pressure value of the abnormal wheel at the next moment and the detected tire pressure value of the abnormal wheel at the current moment; and comparing and analyzing the variable quantity with a preset threshold value, and judging the tire pressure descending trend of the abnormal wheel. The invention can not only judge the tire pressure abnormity of the automobile in time, but also early warn the tire pressure descending trend of the abnormal tire in advance, and can generate corresponding prompt instructions and emergency brake treatment, thereby effectively improving the driving safety of the automobile.
Description
Technical Field
The invention relates to the technical field of automobiles, in particular to an OBD (on-board diagnostics) combined type tire pressure monitoring method and system.
Background
With the popularization of automobiles, the holding quantity of the automobiles is larger and larger, and the problem of safe driving of the automobiles becomes more and more important. The tire is an important part for automobile driving, the safety of the tire is guaranteed to be a precondition for the safe driving of the automobile, the air pressure is the hit door of the tire, and the service life of the tire is influenced by overhigh or overlow air pressure. Therefore, people hope to know the tire pressure of the automobile in real time during the driving process so as to avoid the over-pressure or under-pressure of the automobile tire.
At present, two systems for monitoring the air pressure of tires are available, one is an indirect tire pressure monitoring (WSB) system, the system compares the rotation Speed difference between the tires through a Wheel Speed sensor of an automobile ABS system, and the working principle is that when the air pressure of a certain tire is reduced, the rolling radius of the Wheel is reduced by the weight of a vehicle, so that the rotation Speed of the Wheel is faster than that of other wheels, and the purpose of monitoring the tire pressure is achieved by comparing the rotation Speed difference between the tires. The other is a direct-Pressure-Based TPMS (PSB) system, which uses a Pressure Sensor installed in each tire to directly measure the air Pressure of the tire, uses a wireless transmitter to transmit Pressure information from the inside of the tire to a central receiver module, displays the air Pressure data of each tire, and automatically alarms when the air Pressure of the tire is too low or air leaks.
However, both for the indirect tire pressure monitoring system and for the direct tire pressure monitoring system, the real-time monitoring effect can be achieved only for the tire pressure of the tire of the automobile, when the tire pressure of the automobile wheel is abnormal, the conventional monitoring method can only monitor that the tire is in an abnormal state, and cannot predict the change trend of the tire pressure of the abnormal tire in advance, so that the conventional tire pressure monitoring method cannot achieve the early warning effect on the change trend of the abnormal tire in advance, and therefore, the invention provides the OBD composite tire pressure monitoring method and the OBD composite tire pressure monitoring system.
Disclosure of Invention
The invention provides an OBD composite tire pressure monitoring method and system aiming at the problems in the related art, and aims to overcome the technical problems in the prior related art.
Therefore, the invention adopts the following specific technical scheme:
according to one aspect of the present invention, there is provided an OBD hybrid tire pressure monitoring method, comprising the steps of:
s1, acquiring the rotating speed of each wheel in the running process of the vehicle through the vehicle-mounted OBD interface, and calculating the tire pressure value of each wheel based on the rotating speed of each wheel;
s2, comparing and analyzing the tire pressure value of each wheel obtained by calculation with the safety standard tire pressure value, and judging whether the tire pressure of each wheel is abnormal or not;
s3, constructing a recurrent neural network model based on the wheel rotation speed, and training and testing the recurrent neural network model;
s4, acquiring the detected tire pressure value of the abnormal wheel at the current moment by using a tire pressure sensor, and outputting the predicted tire pressure value of the abnormal wheel at the next moment by using the trained recurrent neural network model;
s5, calculating the variation between the predicted tire pressure value of the abnormal wheel at the next moment and the detected tire pressure value of the abnormal wheel at the current moment;
and S6, comparing the variation between the predicted tire pressure value at the next moment and the detected tire pressure value at the current moment with a preset threshold value, and analyzing, and judging the tire pressure descending trend of the abnormal wheel.
Further, in S1, acquiring the rotation speed of each wheel during the running of the vehicle through the on-board OBD interface, and calculating the tire pressure value of each wheel based on the rotation speed of each wheel includes the following steps:
s11, acquiring the rotating speed of each wheel in the running process of the vehicle through the vehicle-mounted OBD interface;
and S12, analyzing and outputting the tire pressure value corresponding to the wheel rotating speed by using a pre-constructed tire pressure searching table.
Further, the tire pressure retrieval table is a corresponding relation table of a plurality of groups of tire rotating speeds and tire pressure values of tires, and is obtained by performing test analysis and summarization in advance.
Further, the step of comparing and analyzing the tire pressure value of each wheel obtained by calculation with the safety standard tire pressure value in S2, and determining whether the tire pressure of each wheel is abnormal includes the following steps:
s21, comparing and analyzing the tire pressure value of each wheel obtained by calculation with the safety standard tire pressure value;
and S22, judging whether the tire pressure value of each wheel exceeds the range of the safe standard tire pressure value, if not, neglecting, and if so, outputting prompt information of the abnormal tire of the wheel.
Further, the step of constructing a recurrent neural network model based on the wheel rotation speed in S3, and the step of training and testing the recurrent neural network model includes the steps of:
s31, constructing a recurrent neural network model, and obtaining an expression of the recurrent neural network model as follows:
wherein, U, W, V, b, c are parameters of the model needing to be learned and updated, and xtIndicating wheel speed, S, input at time ttRepresenting the hidden layer state at time t as input to the next layer, i.e. two for each layer of the model, one being xtOne is the state S of the previous layert-1，OtThe predicted tire pressure value of the tire output at the time t is represented, and f is a nonlinear activation function tanh;
s32, performing network training on the recurrent neural network model, and updating model parameters by adopting a minimum loss function, wherein the formula of the loss function is as follows:
further, the network training of the recurrent neural network model further includes the following steps:
for the condition of insufficient training, the training effect is achieved by increasing nodes in the network or increasing the training period of the network;
for the over-fitting condition, the training period is reduced or controlled, and the training on the network is stopped before the inflection point appears in the data, so that the training effect is achieved.
Further, the calculating of the amount of change between the predicted tire pressure value at the next time of the abnormal wheel and the detected tire pressure value at the current time in S5 includes the steps of:
s51, respectively acquiring the detected tire pressure value of the abnormal wheel at the current moment and the predicted tire pressure value of the abnormal wheel at the next moment;
and S52, calculating the difference value between the detected tire pressure value of the abnormal wheel at the current moment and the predicted tire pressure value of the abnormal wheel at the next moment.
Further, in S6, the step of comparing the variation between the predicted tire pressure value at the next time and the detected tire pressure value at the current time with the preset threshold value for analysis, and determining the tire pressure decrease trend of the abnormal wheel includes the following steps:
s61, acquiring the variation between the predicted tire pressure value at the next moment and the detected tire pressure value at the current moment;
and S62, judging whether the variation in the S61 exceeds a preset threshold value, if so, analyzing to obtain that the tire pressure of the abnormal wheel has a rapid descending trend, and if not, analyzing to obtain that the tire pressure of the abnormal wheel has a slow descending trend.
Further, in S6, the step of comparing the variation between the predicted tire pressure value at the next time and the detected tire pressure value at the current time with the preset threshold value for analysis, and determining the tire pressure decrease trend of the abnormal wheel further includes the following steps:
when the tire pressure of the abnormal wheel is judged to have the rapid descending trend, an emergency braking instruction is generated and is sent to an OBD system through an OBD interface to be displayed on an instrument panel disc of the automobile, and the automobile is controlled to be braked emergently;
and when the tire pressure of the abnormal wheel is judged to have a slow descending trend, generating a tire pressure slow descending prompt instruction, and sending the instruction to an OBD system through an OBD interface to be displayed on an instrument panel disc of the automobile.
According to another aspect of the invention, an OBD composite tire pressure monitoring system is provided, which comprises a tire pressure analysis and calculation module, a tire pressure abnormity judgment module, a recurrent neural network model construction module, an abnormal wheel tire pressure prediction module, an abnormal wheel tire pressure variation calculation module and an abnormal tire pressure descending trend analysis module;
the tire pressure analyzing and calculating module is used for acquiring the rotating speed of each wheel in the running process of the vehicle through the vehicle-mounted OBD interface and calculating the tire pressure value of each wheel based on the rotating speed of each wheel;
the tire pressure abnormity judgment module is used for comparing and analyzing the tire pressure value of each wheel obtained by calculation with the safety standard tire pressure value and judging whether the tire pressure of each wheel is abnormal or not;
the recurrent neural network model building module is used for building a recurrent neural network model based on the wheel rotating speed and training and testing the recurrent neural network model;
the abnormal wheel tire pressure prediction module is used for acquiring the detected tire pressure value of the abnormal wheel at the current moment by using a tire pressure sensor and outputting the predicted tire pressure value of the abnormal wheel at the next moment by using the trained recurrent neural network model;
the abnormal wheel tire pressure variation calculating module is used for calculating the variation between the predicted tire pressure value of the abnormal wheel at the next moment and the detected tire pressure value of the abnormal wheel at the current moment;
the abnormal tire pressure descending trend analysis module is used for comparing and analyzing the variation between the predicted tire pressure value at the next moment and the detected tire pressure value at the current moment with a preset threshold value and judging the tire pressure descending trend of the abnormal wheel.
The invention has the beneficial effects that: the method comprises the steps of calculating the rotating speed of each wheel acquired by a vehicle-mounted OBD interface to obtain a corresponding tire pressure value of each wheel, judging whether the tire pressure of each wheel is abnormal or not by combining the safety standard tire pressure value of each wheel, outputting the predicted tire pressure value of the abnormal wheel at the next moment by using a pre-constructed recurrent neural network model, judging the tire pressure descending trend of the abnormal wheel by using the variation between the predicted tire pressure value at the next moment and the detected tire pressure value at the current moment and combining a preset variation threshold value to obtain the descending trend of the abnormal wheel, realizing early warning of the tire pressure descending trend of the abnormal wheel, and performing corresponding prompt instruction generation and emergency braking treatment. And can generate corresponding prompt instructions and emergency braking treatment, thereby effectively improving the driving safety of the automobile.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flow chart of an OBD hybrid tire pressure monitoring method according to an embodiment of the present invention.
Detailed Description
For further explanation of the various embodiments, the drawings which form a part of the disclosure and which are incorporated in and constitute a part of this specification, illustrate embodiments and, together with the description, serve to explain the principles of operation of the embodiments, and to enable others of ordinary skill in the art to understand the various embodiments and advantages of the invention, and, by reference to these figures, reference is made to the accompanying drawings, which are not to scale and wherein like reference numerals generally refer to like elements.
According to the embodiment of the invention, an OBD composite tire pressure monitoring method and system are provided.
Referring now to the drawings and the detailed description, the invention is further illustrated, as shown in fig. 1, and according to one embodiment of the invention, there is provided an OBD hybrid tire pressure monitoring method, including the steps of:
s1, acquiring the rotating speed of each wheel in the running process of the vehicle through the vehicle-mounted OBD interface, and calculating the tire pressure value of each wheel based on the rotating speed of each wheel;
in S1, acquiring the rotation speed of each wheel during the running of the vehicle through the on-board OBD interface, and calculating the tire pressure value of each wheel based on the rotation speed of each wheel includes the following steps:
s11, acquiring the rotating speed of each wheel in the running process of the vehicle through the vehicle-mounted OBD interface;
specifically, the on-board diagnostic system (OBD) includes an automobile bus, a plurality of Electronic Control Units (ECUs) connected to the automobile bus, an on-board OBD interface, and a diagnostic bus connecting the automobile bus and the on-board OBD interface.
The automobile bus includes, but is not limited to, any one of a CAN bus, a K-line bus and a J1850 bus. The automotive bus comprises two data lines for data exchange. The ECU, also known as a traveling computer, is the brain of the vehicle and is responsible for controlling the normal operation of various components in the vehicle. All state data in the automobile are sent to the ECU through the automobile bus to be processed so as to control the associated units. The OBD interface is arranged in the vehicle and is an external interface of the vehicle-mounted diagnosis system.
And S12, analyzing and outputting the tire pressure value corresponding to the wheel rotating speed by using a pre-constructed tire pressure searching table.
Specifically, the tire pressure retrieval table is a correspondence table of a plurality of groups of tire rotating speeds and tire pressure values of tires, and is obtained by performing test analysis and summary in advance.
S2, comparing and analyzing the tire pressure value of each wheel obtained by calculation with the safety standard tire pressure value, and judging whether the tire pressure of each wheel is abnormal or not;
in S2, the step of comparing the tire pressure value of each wheel with the safety standard tire pressure value and analyzing the tire pressure value to determine whether the tire pressure of each wheel is abnormal includes the following steps:
s21, comparing and analyzing the tire pressure value of each wheel obtained by calculation with the safety standard tire pressure value;
and S22, judging whether the tire pressure value of each wheel exceeds the range of the safe standard tire pressure value, if not, neglecting, and if so, outputting prompt information of the abnormal tire of the wheel.
S3, constructing a recurrent neural network model based on the wheel rotation speed, and training and testing the recurrent neural network model;
the step of constructing a recurrent neural network model based on the wheel rotation speed in the step of S3, and the step of training and testing the recurrent neural network model includes the following steps:
s31, constructing a recurrent neural network model, and obtaining an expression of the recurrent neural network model as follows:
wherein, U, W, V, b, c are parameters of the model needing to be learned and updated, and xtIndicating wheel speed, S, input at time ttRepresenting the hidden layer state at time t as input to the next layer, i.e. two for each layer of the model, one being xtOne is the state S of the previous layert-1，OtThe predicted tire pressure value of the tire output at the time t is represented, and f is a nonlinear activation function tanh;
s32, performing network training on the recurrent neural network model, and updating model parameters by adopting a minimum loss function, wherein the formula of the loss function is as follows:
due to the uneven distribution of the rotation speed data of each wheel, training is insufficient and overfitting is caused because the training data is less or the discreteness is too high in the training process. Overfitting refers to the fact that the result of the model is not to find common characteristics of all data but only feature extraction is performed on training data because too little training data or too many times of training on a training set. In other words, this model already remembers all the training data, which is very good for prediction, but very poor for other data. Specifically, the network training of the recurrent neural network model further includes the following steps:
for the condition of insufficient training, the training effect is achieved by increasing nodes in the network or increasing the training period of the network;
for the over-fitting condition, the training period is reduced or controlled, and the training on the network is stopped before the inflection point appears in the data, so that the training effect is achieved.
S4, acquiring the detected tire pressure value of the abnormal wheel at the current moment by using a tire pressure sensor, and outputting the predicted tire pressure value of the abnormal wheel at the next moment by using the trained recurrent neural network model;
s5, calculating the variation between the predicted tire pressure value of the abnormal wheel at the next moment and the detected tire pressure value of the abnormal wheel at the current moment;
wherein the calculating of the amount of change between the predicted tire pressure value at the next time of the abnormal wheel and the detected tire pressure value at the current time in S5 includes the steps of:
s51, respectively acquiring the detected tire pressure value of the abnormal wheel at the current moment and the predicted tire pressure value of the abnormal wheel at the next moment;
and S52, calculating the difference value between the detected tire pressure value of the abnormal wheel at the current moment and the predicted tire pressure value of the abnormal wheel at the next moment.
And S6, comparing the variation between the predicted tire pressure value at the next moment and the detected tire pressure value at the current moment with a preset threshold value, and analyzing, and judging the tire pressure descending trend of the abnormal wheel.
In S6, the step of comparing the variation between the predicted tire pressure value at the next time and the detected tire pressure value at the current time with the preset threshold value for analysis, and determining the tire pressure decrease trend of the abnormal wheel includes the following steps:
s61, acquiring the variation between the predicted tire pressure value at the next moment and the detected tire pressure value at the current moment;
and S62, judging whether the variation in the S61 exceeds a preset threshold value, if so, analyzing to obtain that the tire pressure of the abnormal wheel has a rapid descending trend, and if not, analyzing to obtain that the tire pressure of the abnormal wheel has a slow descending trend.
Specifically, in S6, the step of comparing the variation between the predicted tire pressure value at the next time and the detected tire pressure value at the current time with the preset threshold value for analysis, and determining the tire pressure decrease trend of the abnormal wheel further includes the following steps:
when the tire pressure of the abnormal wheel is judged to have the rapid descending trend, an emergency braking instruction is generated and is sent to an OBD system through an OBD interface to be displayed on an instrument panel disc of the automobile, and the automobile is controlled to be braked emergently;
and when the tire pressure of the abnormal wheel is judged to have a slow descending trend, generating a tire pressure slow descending prompt instruction, and sending the instruction to an OBD system through an OBD interface to be displayed on an instrument panel disc of the automobile.
It can be understood that, in this embodiment, the prompt specification may include an indicator light display, and may further include a prompt tone prompt or other prompt display manners, so as to better prompt the driver.
According to another embodiment of the invention, an OBD composite tire pressure monitoring system is provided, which comprises a tire pressure analysis calculation module, a tire pressure abnormality judgment module, a recurrent neural network model construction module, an abnormal wheel tire pressure prediction module, an abnormal wheel tire pressure variation calculation module, and an abnormal tire pressure descent trend analysis module;
the tire pressure analyzing and calculating module is used for acquiring the rotating speed of each wheel in the running process of the vehicle through the vehicle-mounted OBD interface and calculating the tire pressure value of each wheel based on the rotating speed of each wheel;
the tire pressure abnormity judgment module is used for comparing and analyzing the tire pressure value of each wheel obtained by calculation with the safety standard tire pressure value and judging whether the tire pressure of each wheel is abnormal or not;
the recurrent neural network model building module is used for building a recurrent neural network model based on the wheel rotating speed and training and testing the recurrent neural network model;
the abnormal wheel tire pressure prediction module is used for acquiring the detected tire pressure value of the abnormal wheel at the current moment by using a tire pressure sensor and outputting the predicted tire pressure value of the abnormal wheel at the next moment by using the trained recurrent neural network model;
the abnormal wheel tire pressure variation calculating module is used for calculating the variation between the predicted tire pressure value of the abnormal wheel at the next moment and the detected tire pressure value of the abnormal wheel at the current moment;
the abnormal tire pressure descending trend analysis module is used for comparing and analyzing the variation between the predicted tire pressure value at the next moment and the detected tire pressure value at the current moment with a preset threshold value and judging the tire pressure descending trend of the abnormal wheel.
In summary, according to the above technical solution of the present invention, the tire pressure value of each wheel is obtained by calculating the rotation speed of each wheel acquired by the on-board OBD interface, and whether the tire pressure of each wheel is abnormal is determined by combining the safety standard tire pressure value of the automobile wheel, and meanwhile, the predicted tire pressure value of the abnormal wheel at the next moment is output by using the pre-established recurrent neural network model, and the tire pressure decreasing trend of the abnormal wheel is determined by using the variation between the predicted tire pressure value at the next moment and the detected tire pressure value at the current moment and combining the preset variation threshold, so as to obtain the tire pressure decreasing trend of the abnormal wheel, thereby early warning the variation trend of the abnormal tire pressure wheel is realized, and corresponding prompt instruction generation and emergency braking processing are performed, compared with the conventional automobile tire pressure monitoring method, the present invention can not only timely determine the tire pressure abnormality of the automobile, and the tire pressure descending trend of the abnormal tire can be early warned, and a corresponding prompt instruction and emergency braking treatment can be generated, so that the driving safety of the automobile can be effectively improved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. An OBD hybrid tire pressure monitoring method, comprising the steps of:
s1, acquiring the rotating speed of each wheel in the running process of the vehicle through the vehicle-mounted OBD interface, and calculating the tire pressure value of each wheel based on the rotating speed of each wheel;
s2, comparing and analyzing the tire pressure value of each wheel obtained by calculation with the safety standard tire pressure value, and judging whether the tire pressure of each wheel is abnormal or not;
s3, constructing a recurrent neural network model based on the wheel rotation speed, and training and testing the recurrent neural network model;
s4, acquiring the detected tire pressure value of the abnormal wheel at the current moment by using a tire pressure sensor, and outputting the predicted tire pressure value of the abnormal wheel at the next moment by using the trained recurrent neural network model;
s5, calculating the variation between the predicted tire pressure value of the abnormal wheel at the next moment and the detected tire pressure value of the abnormal wheel at the current moment;
and S6, comparing the variation between the predicted tire pressure value at the next moment and the detected tire pressure value at the current moment with a preset threshold value, and analyzing, and judging the tire pressure descending trend of the abnormal wheel.
2. The OBD composite tire pressure monitoring method according to claim 1, wherein the step of obtaining the rotation speed of each wheel during the running process of the vehicle through the on-board OBD interface in S1, and calculating the tire pressure value of each wheel based on the rotation speed of each wheel comprises the following steps:
s11, acquiring the rotating speed of each wheel in the running process of the vehicle through the vehicle-mounted OBD interface;
and S12, analyzing and outputting the tire pressure value corresponding to the wheel rotating speed by using a pre-constructed tire pressure searching table.
3. The OBD composite tire pressure monitoring method according to claim 2, wherein the tire pressure search table is a plurality of sets of corresponding relationship tables between tire rotation speed and tire pressure value of the tire, and the tire pressure search table is obtained by summarizing through a pre-performed test analysis.
4. The OBD composite tire pressure monitoring method according to claim 1, wherein the step of comparing the calculated tire pressure value of each wheel with the safety standard tire pressure value in S2 to determine whether the tire pressure of each wheel is abnormal includes the steps of:
s21, comparing and analyzing the tire pressure value of each wheel obtained by calculation with the safety standard tire pressure value;
and S22, judging whether the tire pressure value of each wheel exceeds the range of the safe standard tire pressure value, if not, neglecting, and if so, outputting prompt information of the abnormal tire of the wheel.
5. The OBD composite tire pressure monitoring method according to claim 1, wherein the step of constructing a recurrent neural network model based on the wheel rotation speed in S3, and the step of training and testing the recurrent neural network model comprises the steps of:
s31, constructing a recurrent neural network model, and obtaining an expression of the recurrent neural network model as follows:
wherein, U, W, V, b, c are parameters of the model needing to be learned and updated, and xtIndicating wheel speed, S, input at time ttRepresenting the hidden layer state at time t as input to the next layer, i.e. two for each layer of the model, one being xtOne is the state S of the previous layert-1，OtThe predicted tire pressure value of the tire output at the time t is represented, and f is a nonlinear activation function tanh;
s32, performing network training on the recurrent neural network model, and updating model parameters by adopting a minimum loss function, wherein the formula of the loss function is as follows:
6. the OBD composite tire pressure monitoring method according to claim 5, wherein the network training of the recurrent neural network model further comprises the steps of:
for the condition of insufficient training, the training effect is achieved by increasing nodes in the network or increasing the training period of the network;
for the over-fitting condition, the training period is reduced or controlled, and the training on the network is stopped before the inflection point appears in the data, so that the training effect is achieved.
7. The OBD hybrid tire pressure monitoring method according to claim 1, wherein the step of calculating the variation between the predicted tire pressure value at the next time of the abnormal wheel and the detected tire pressure value at the current time in S5 comprises the steps of:
s51, respectively acquiring the detected tire pressure value of the abnormal wheel at the current moment and the predicted tire pressure value of the abnormal wheel at the next moment;
and S52, calculating the difference value between the detected tire pressure value of the abnormal wheel at the current moment and the predicted tire pressure value of the abnormal wheel at the next moment.
8. The OBD combined tire pressure monitoring method according to claim 1, wherein the step of comparing the variation between the predicted tire pressure at the next time and the detected tire pressure at the current time with a preset threshold value and analyzing the variation, and determining the tire pressure decrease trend of the abnormal wheel in S6 includes the following steps:
s61, acquiring the variation between the predicted tire pressure value at the next moment and the detected tire pressure value at the current moment;
and S62, judging whether the variation in the S61 exceeds a preset threshold value, if so, analyzing to obtain that the tire pressure of the abnormal wheel has a rapid descending trend, and if not, analyzing to obtain that the tire pressure of the abnormal wheel has a slow descending trend.
9. The OBD composite tire pressure monitoring method according to claim 8, wherein the step of comparing the variation between the predicted tire pressure value at the next time and the detected tire pressure value at the current time with a preset threshold value and analyzing the variation, and determining the tire pressure decrease trend of the abnormal wheel in S6 further comprises the steps of:
when the tire pressure of the abnormal wheel is judged to have the rapid descending trend, an emergency braking instruction is generated and is sent to an OBD system through an OBD interface to be displayed on an instrument panel disc of the automobile, and the automobile is controlled to be braked emergently;
and when the tire pressure of the abnormal wheel is judged to have a slow descending trend, generating a tire pressure slow descending prompt instruction, and sending the instruction to an OBD system through an OBD interface to be displayed on an instrument panel disc of the automobile.
10. An OBD composite tire pressure monitoring system for realizing the OBD composite tire pressure monitoring method according to any one of claims 1-9, which is characterized by comprising a tire pressure analysis and calculation module, a tire pressure abnormity judgment module, a recurrent neural network model construction module, an abnormal tire pressure prediction module, an abnormal tire pressure variation calculation module and an abnormal tire pressure descending trend analysis module;
the tire pressure analyzing and calculating module is used for acquiring the rotating speed of each wheel in the running process of the vehicle through the vehicle-mounted OBD interface and calculating the tire pressure value of each wheel based on the rotating speed of each wheel;
the tire pressure abnormity judgment module is used for comparing and analyzing the tire pressure value of each wheel obtained by calculation with the safety standard tire pressure value and judging whether the tire pressure of each wheel is abnormal or not;
the recurrent neural network model building module is used for building a recurrent neural network model based on the wheel rotating speed and training and testing the recurrent neural network model;
the abnormal wheel tire pressure prediction module is used for acquiring the detected tire pressure value of the abnormal wheel at the current moment by using a tire pressure sensor and outputting the predicted tire pressure value of the abnormal wheel at the next moment by using the trained recurrent neural network model;
the abnormal wheel tire pressure variation calculating module is used for calculating the variation between the predicted tire pressure value of the abnormal wheel at the next moment and the detected tire pressure value of the abnormal wheel at the current moment;
the abnormal tire pressure descending trend analysis module is used for comparing and analyzing the variation between the predicted tire pressure value at the next moment and the detected tire pressure value at the current moment with a preset threshold value and judging the tire pressure descending trend of the abnormal wheel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210291577.7A CN114379294B (en) | 2022-03-24 | 2022-03-24 | OBD (on-Board diagnostics) combined type tire pressure monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210291577.7A CN114379294B (en) | 2022-03-24 | 2022-03-24 | OBD (on-Board diagnostics) combined type tire pressure monitoring method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114379294A true CN114379294A (en) | 2022-04-22 |
| CN114379294B CN114379294B (en) | 2022-06-14 |
Family
ID=81205107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210291577.7A Active CN114379294B (en) | 2022-03-24 | 2022-03-24 | OBD (on-Board diagnostics) combined type tire pressure monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114379294B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116890582A (en) * | 2023-09-11 | 2023-10-17 | 深圳富士伟业科技有限公司 | Tire pressure sensor upgrading verification method based on tire pressure detection |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104999865A (en) * | 2015-07-13 | 2015-10-28 | 杭州联云汽车科技有限公司 | Indirect tire pressure monitoring method based on OBD interface |
| CN107379899A (en) * | 2017-07-07 | 2017-11-24 | 淮阴工学院 | A kind of tire condition intelligent monitor system based on wireless sensor network |
| CN107867131A (en) * | 2016-09-27 | 2018-04-03 | 深圳联友科技有限公司 | A kind of vehicle safety monitoring method and system |
| CN109177661A (en) * | 2018-08-27 | 2019-01-11 | 深圳市雪锐科技有限公司 | tire pressure monitoring method and device |
| DE102020104928A1 (en) * | 2020-02-25 | 2021-08-26 | Bayerische Motoren Werke Aktiengesellschaft | Method and device for determining the condition of a vehicle tire |
| CN113547879A (en) * | 2021-08-17 | 2021-10-26 | 深圳市元征科技股份有限公司 | Tire leakage detection method and device, vehicle and computer storage medium |
| US20210394562A1 (en) * | 2018-03-01 | 2021-12-23 | The Goodyear Tire & Rubber Company | Model based tire wear estimation system and method |
-
2022
- 2022-03-24 CN CN202210291577.7A patent/CN114379294B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104999865A (en) * | 2015-07-13 | 2015-10-28 | 杭州联云汽车科技有限公司 | Indirect tire pressure monitoring method based on OBD interface |
| CN107867131A (en) * | 2016-09-27 | 2018-04-03 | 深圳联友科技有限公司 | A kind of vehicle safety monitoring method and system |
| CN107379899A (en) * | 2017-07-07 | 2017-11-24 | 淮阴工学院 | A kind of tire condition intelligent monitor system based on wireless sensor network |
| US20210394562A1 (en) * | 2018-03-01 | 2021-12-23 | The Goodyear Tire & Rubber Company | Model based tire wear estimation system and method |
| CN109177661A (en) * | 2018-08-27 | 2019-01-11 | 深圳市雪锐科技有限公司 | tire pressure monitoring method and device |
| DE102020104928A1 (en) * | 2020-02-25 | 2021-08-26 | Bayerische Motoren Werke Aktiengesellschaft | Method and device for determining the condition of a vehicle tire |
| CN113547879A (en) * | 2021-08-17 | 2021-10-26 | 深圳市元征科技股份有限公司 | Tire leakage detection method and device, vehicle and computer storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116890582A (en) * | 2023-09-11 | 2023-10-17 | 深圳富士伟业科技有限公司 | Tire pressure sensor upgrading verification method based on tire pressure detection |
| CN116890582B (en) * | 2023-09-11 | 2023-11-28 | 深圳富士伟业科技有限公司 | Tire pressure sensor upgrading verification method based on tire pressure detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114379294B (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3023761B1 (en) | Tire cornering stiffness estimation system and method | |
| US5483220A (en) | Detecting a deflated tire by comparing angular velocity data of all wheels, a data table, and the directly-measured pressure of a single tire | |
| EP2137010B1 (en) | Tire pressure classification based tire pressure monitoring | |
| JP4764933B2 (en) | Tire pressure drop detection device and method, and tire pressure drop detection program | |
| EP0729855B1 (en) | A method of determining the inflation pressure of a tyre on a moving vehicle | |
| WO2014079365A1 (en) | Improved method for passenger car tire pressure monitoring system | |
| CN109017741B (en) | Vehicle braking system failure prediction and processing method | |
| US9636956B2 (en) | Wheel diagnostic monitoring | |
| CN114379294B (en) | OBD (on-Board diagnostics) combined type tire pressure monitoring method and system | |
| CN111506048B (en) | Vehicle fault early warning method and related equipment | |
| CN112550262A (en) | Health state diagnosis method and system for automobile brake system | |
| CN100430246C (en) | Means for detecting loss of pneumatic pressure in tire and device for the purpose | |
| WO2001060644A1 (en) | System for detecting the optimum tyre inflation pressure | |
| CN114161888A (en) | Double-tire iTPMS tire pressure monitoring method and system | |
| US8868281B2 (en) | Understeer assessment for vehicles | |
| CN111483277A (en) | Tire underpressure identification method and system based on machine learning and storage medium | |
| US20210170812A1 (en) | Method for auto-locating positions of a plurality of wireless sensors on a vehicle and an apparatus therefor | |
| JP5126048B2 (en) | Tire pressure monitoring device | |
| DE102013225278A1 (en) | Method for detecting a fault condition of a chassis, chassis monitoring device and computer program product | |
| CN113715561B (en) | Motorcycle iTPMS tire pressure monitoring method and system | |
| EP1948454A1 (en) | Indirect tire pressure monitoring method | |
| US11312345B2 (en) | Systems and methods for detecting and controlling a fluid consumption detection warning | |
| US20090271127A1 (en) | System and method for monitoring vehicle residual integrity | |
| CN110789278A (en) | Tire pressure monitoring method and device | |
| CN110873649A (en) | Diagnostic method, diagnostic system and motor 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |