A tire anti-burst early warning method and system based on wheel rotational speed recognition

Abstract

The application relates to a tire anti-burst early warning method and system based on wheel speed recognition, and belongs to the technical field of automobile safety. The method comprises the following steps: acquiring a wheel speed signal, correcting the wheel speed signal through a signal correction model to obtain a wheel speed time domain signal; converting the wheel speed time domain signal to obtain a wheel speed frequency domain signal; extracting wheel speed signal features from the wheel speed time domain signal and the wheel speed frequency domain signal; identifying the converted wheel speed signal features through an indirect monitoring model to obtain a tire pressure state; acquiring a current environment image; and processing the tire pressure state and the current environment image through a multi-element coupling model to output tire anti-burst early warning information. The tire anti-burst early warning based on wheel speed recognition is realized.

Description

Technical Field

[0001] This invention belongs to the field of automotive safety technology, specifically relating to a tire explosion prevention warning method and system based on wheel rotation speed recognition. Background Technology

[0002] In recent years, with the continuous increase in car ownership, while enjoying the convenience brought by cars, people are also paying more and more attention to safety during driving. As the only contact part between the vehicle and the road, tires play a crucial role in overall vehicle safety. Once the internal tire pressure is abnormal, it can easily lead to serious traffic accidents such as tire blowouts. Therefore, how to achieve real-time monitoring and abnormal warning of tire pressure has become an important research direction for improving the level of active safety in automobiles. In particular, indirect pressure measurement and warning through wheel speed signals has advantages such as not relying on external sensors and rapid response, and has attracted widespread attention.

[0003] Traditional tire pressure monitoring (TPM) methods based on radius estimation primarily determine tire pressure indirectly by estimating the mapping relationship between tire radius, relative radius, or effective rolling radius and tire pressure. However, this method typically only identifies anomalies in 1 to 3 tires, limiting its accuracy and adaptability. In contrast, TPM identification methods based directly on wheel speed signals are more accurate and real-time. However, due to the highly dynamic nature of the vehicle's environment, effectively integrating environmental data and wheel speed characteristics to achieve rapid perception and accurate warning of tire blowout risks under complex operating conditions remains a critical issue that urgently needs to be addressed. Summary of the Invention

[0004] To address the aforementioned problems in the existing technology, this invention provides a tire blowout warning method and system based on wheel speed recognition.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] A tire blowout warning method based on wheel speed recognition includes:

[0007] S1: Obtain the wheel speed signal, and correct the wheel speed signal using a signal correction model to obtain the wheel speed time domain signal;

[0008] S2: Convert the wheel speed time-domain signal to obtain the wheel speed frequency-domain signal; extract wheel speed signal features from the wheel speed time-domain signal and the wheel speed frequency-domain signal;

[0009] S3: Tire pressure status is obtained by identifying and converting the wheel speed signal characteristics through an indirect monitoring model;

[0010] S4: Acquire the current environmental image, process the tire pressure status and the current environmental image through a multivariate coupling model, and output tire explosion prevention warning information.

[0011] Preferably, the correction process for the wheel speed signal in step S1 includes:

[0012] S101: The gear ring error is obtained by calculating the wheel speed signal error using the least squares method;

[0013] S102: Obtain a reference wheel speed signal by correcting the wheel speed signal using the gear ring error;

[0014] S103: Linearly interpolate the reference wheel speed signal to obtain a reconstructed reference wheel speed signal;

[0015] S104: Obtain the time-domain signal of the wheel speed by reconstructing the reference wheel speed signal through adaptive weight gradient.

[0016] Preferably, the mathematical expression for the transformation in step S2 is:

[0017]

[0018] Where X(k) is the frequency domain signal of the wheel speed, n represents the time domain index variable, i.e. the current sampling point position, N is the total number of sampling points, i.e. the length of the wheel speed time domain signal, x(n) is the wheel speed time domain signal, k represents the frequency index variable, and j is the imaginary unit.

[0019] Preferably, the identification and conversion process of the indirect monitoring model in step S3 is as follows:

[0020] S301: Obtain normal wheel speed signal characteristics by identifying the wheel speed signal characteristics through the tire pressure recognition network;

[0021] S302: The tire pressure state is obtained by predicting and converting the characteristics of the normal wheel speed signal.

[0022] Preferably, the tire pressure recognition network identification process in step S301 is as follows:

[0023] S301-1: Obtain the reference frequency band resonance features by processing the wheel speed signal features through adaptive wavelet threshold denoising;

[0024] S301-2: Obtain the normal wheel speed signal features by classifying the resonance features of the reference frequency band through a decision tree.

[0025] Preferably, the specific process of prediction transformation in step S302 is as follows:

[0026] S302-1: Obtain the initial state of tire pressure by predicting the characteristics of the normal wheel speed signal;

[0027] S302-2: Preset the tire stiffness compensation factor and environmental compensation weight, and correct the initial state of the tire pressure to obtain the tire pressure reference state;

[0028] S302-3: Add a timestamp to the tire pressure reference state to obtain a time-series tire pressure reference state; obtain the verification coefficient by linearly calculating the time-series tire pressure reference state;

[0029] S302-4: The tire pressure state is obtained by verifying the verification coefficients through multi-time-domain consistency verification.

[0030] Preferably, the method for multi-time-domain consistency verification in step S302-4 is as follows:

[0031] A preset verification threshold is used to determine whether the verification coefficient is less than the verification threshold based on the verification coefficient and the verification threshold.

[0032] Yes, then the timing tire pressure reference state is the tire pressure state;

[0033] If not, the intelligent agent confirms the time-series tire pressure reference state.

[0034] Preferably, the modeling process of the multi-element coupling model in step S4 is as follows:

[0035] S401: Obtain environmental features by feature extraction from the current environmental image;

[0036] S402: Obtain the environmental scene category by classifying the environmental features using a classifier;

[0037] S403: Map the environmental scene categories to obtain an environmental risk factor matrix, and calculate the weight adjustment factor by dot product fusion of the environmental risk factor matrix;

[0038] S404: Obtain the risk assessment coefficient by combining the weighting adjustment factor and the tire pressure condition risk assessment;

[0039] S405: A preset risk threshold is used to determine the tire explosion prevention warning information by multi-factor coupling, and the risk threshold and the risk assessment coefficient are used to determine the risk threshold. The risk threshold includes an upper limit and a lower limit.

[0040] Preferably, the multi-element coupling determination method in step S405 is as follows:

[0041] Determine whether the risk assessment coefficient is greater than the upper threshold:

[0042] Yes, then the tire explosion prevention warning information is a "red warning";

[0043] If not, then further compare whether the risk assessment coefficient is greater than the lower limit of the threshold. If it is greater, the tire explosion prevention warning information is "yellow warning"; if it is less, the tire explosion prevention warning information is "normal".

[0044] A tire blowout warning system based on wheel speed recognition includes a signal correction module, a feature extraction module, a tire pressure conversion module, and a coupling evaluation module, comprising:

[0045] The signal correction module is used to acquire the wheel speed signal and correct the wheel speed signal through the signal correction model to obtain the wheel speed time domain signal;

[0046] The feature extraction module is used to convert the wheel rotation time domain signal into a wheel rotation frequency domain signal; and to obtain wheel speed signal features by extracting features from the wheel rotation time domain signal and the wheel rotation frequency domain signal.

[0047] The tire pressure conversion module is used to identify and convert the wheel speed signal characteristics through an indirect monitoring model to obtain the tire pressure status;

[0048] The coupling evaluation module is used to acquire the current environmental image, process the tire pressure status and the current environmental image through a multivariate coupling model, and output tire explosion prevention warning information.

[0049] The beneficial effects of this invention are as follows:

[0050] (1) By correcting the wheel speed signal through the signal correction model and combining frequency domain and time domain feature extraction, the stability and accuracy of wheel speed features are effectively improved, thereby achieving more accurate indirect tire pressure identification and making up for the delay and drift problems of traditional tire pressure sensors.

[0051] (2) Introduce a multi-coupling model, combine it with environmental image recognition, dynamically extract environmental scene risk factors, form a weight adjustment mechanism that adapts to different driving scenarios, and improve the early warning system’s adaptability and sensitivity to complex road conditions.

[0052] (3) By using the multi-level coupling judgment of risk assessment coefficient and upper and lower limit thresholds, the red warning, yellow warning and normal state can be clearly distinguished, so as to realize the refined management of tire status, improve the accuracy of tire explosion prevention warning, and enhance the driving safety level and driving decision support ability. Attached Figure Description

[0053] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0054] Figure 1This is a flowchart illustrating a tire explosion prevention warning method based on wheel speed recognition according to the present invention. Detailed Implementation

[0055] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided.

[0056] Please see Figure 1 A tire blowout warning method based on wheel speed recognition includes:

[0057] S1: Obtain the wheel speed signal, and correct the wheel speed signal using a signal correction model to obtain the wheel speed time domain signal;

[0058] S2: Convert the wheel rotation time domain signal to obtain the wheel rotation frequency domain signal; extract wheel speed signal features from the wheel rotation time domain signal and the wheel rotation frequency domain signal, the wheel speed signal features including wheel speed signal time domain features and wheel speed signal frequency domain features;

[0059] S3: Tire pressure status is obtained by identifying and converting the wheel speed signal characteristics through an indirect monitoring model;

[0060] S4: Acquire the current environmental image, process the tire pressure status and the current environmental image through a multivariate coupling model, and output tire explosion prevention warning information.

[0061] Specifically, in step S1, the process by which the signal correction model corrects the wheel speed signal includes:

[0062] S101: The gear ring error is obtained by calculating the wheel speed signal error using the least squares method;

[0063] S102: Obtain a reference wheel speed signal by correcting the wheel speed signal using the gear ring error;

[0064] S103: Linearly interpolate the reference wheel speed signal to obtain a reconstructed reference wheel speed signal;

[0065] S104: Obtain the time-domain signal of the wheel speed by reconstructing the reference wheel speed signal through adaptive weight gradient.

[0066] In this embodiment, the time-domain signal of wheel speed obtained after correction by the signal correction model is discrete and uniformly distributed. Therefore, it is necessary to convert the time-domain signal of wheel speed to the frequency domain for subsequent feature analysis of the frequency domain wheel speed signal.

[0067] Specifically, the mathematical expression transformed in step S2 is:

[0068]

[0069] Where X(k) is the frequency domain signal of the wheel speed, n represents the time domain index variable, i.e. the current sampling point position, N is the total number of sampling points, i.e. the length of the wheel speed time domain signal, x(n) is the wheel speed time domain signal, k represents the frequency index variable, and j is the imaginary unit.

[0070] In this embodiment, normal wheel speed signal characteristics refer to wheel speed signal characteristics suitable for indirect monitoring, while problematic wheel speed signal characteristics refer to wheel speed signal characteristics unsuitable for indirect monitoring. Normal and problematic wheel speed signal characteristics can be distinguished by the magnitude of fluctuations in the wheel speed time-domain signal characteristics and the amplitude-frequency characteristics of the wheel speed frequency-domain signal characteristics. Problematic wheel speed signal characteristics include: excessively low wheel speed, excessive wheel speed fluctuations, and the presence of periodic noise. The average wheel speed of a normal wheel speed signal is 51 km / h, with a fluctuation amplitude of approximately 0.5 km / h. Problematic wheel speed signal characteristics with excessively low wheel speed exhibit a sudden change at regular intervals, with no resonance peaks reflecting wheel speed signal characteristics across the entire frequency domain; problematic wheel speed signal characteristics with excessive fluctuations have a fluctuation amplitude of 0.8 km / h. Problematic wheel speed signal characteristics with periodic noise are caused by incomplete elimination of wheel speed sensor errors. Therefore, problematic wheel speed signal characteristics are unsuitable for indirect tire pressure monitoring.

[0071] Specifically, the identification and conversion process of the indirect monitoring model in step S3 is as follows:

[0072] S301: Obtain normal wheel speed signal characteristics by identifying the wheel speed signal characteristics through the tire pressure recognition network;

[0073] S302: The tire pressure state is obtained by predicting and converting the characteristics of the normal wheel speed signal.

[0074] Specifically, the tire pressure recognition network in step S301 is modeled as follows:

[0075] S301-1: Obtain the reference frequency band resonance features by processing the wheel speed signal features through adaptive wavelet threshold denoising;

[0076] S301-2: Obtain the normal wheel speed signal features by classifying the resonance features of the reference frequency band through a decision tree.

[0077] Specifically, the prediction transformation process in step S302 is as follows:

[0078] S302-1: The characteristic drift is obtained by analyzing the characteristic curve of the normal wheel speed signal; the initial state of tire pressure is obtained by predicting the normal wheel speed signal characteristics using a deep regression network.

[0079] S302-2: Preset the tire stiffness compensation factor and environmental compensation weight, and correct the initial state of the tire pressure to obtain the tire pressure reference state;

[0080] The corrected expression is:

[0081] P t =P0·(1+α) s ·tanh(Δs)-β e ·cos(ω e t)),

[0082] Among them, P t P0 represents the tire pressure reference state, and α represents the initial tire pressure state. s β is the tire stiffness compensation factor, Δs is the characteristic drift, and β is the characteristic drift. e Let ω be the environmental compensation weight. e Here, t represents the current sampling time, tanh is the tangent function, and cos is the cosine function;

[0083] S302-3: Add a timestamp to the tire pressure reference state to obtain a time-series tire pressure reference state; obtain the verification coefficient by linearly calculating the time-series tire pressure reference state;

[0084] The expression for calculating the verification coefficient is as follows:

[0085]

[0086] Wherein, Δp is the verification coefficient, W is the number of time-series tire pressure reference states, i represents the i-th time-series tire pressure reference state, Pt(i) is the i-th time-series tire pressure reference state, and Pt(i-1) represents the (i-1)-th time-series tire pressure reference state.

[0087] S302-4: The tire pressure state is obtained by verifying the verification coefficients through multi-time-domain consistency verification;

[0088] The multi-time-domain consistency verification method is as follows: A verification threshold is preset, and a verification coefficient is determined based on the verification threshold to determine whether the verification coefficient is less than the verification threshold.

[0089] Yes, then the timing tire pressure reference state is the tire pressure state;

[0090] If not, the intelligent agent confirms the time-series tire pressure reference state.

[0091] In this embodiment, the deep regression network includes an input layer, a hidden layer, and an output layer. The hidden layer includes three gated recurrent units (GRUs) to process temporal features, with 64 neurons in each layer.

[0092] Specifically, the current environmental image includes, but is not limited to, current temperature, road surface humidity, load weight, tire age, and vehicle speed.

[0093] Specifically, the modeling process of the multi-element coupling model in step S4 is as follows:

[0094] S401: Obtain environmental features by feature extraction from the current environmental image;

[0095] S402: Obtain the environmental scene category based on the environmental characteristics;

[0096] S403: Map the environmental scene categories to obtain an environmental risk factor matrix, and calculate the weight adjustment factor by dot product fusion of the environmental risk factor matrix;

[0097] S404: Obtain the risk assessment coefficient by combining the weighting adjustment factor and the tire pressure condition risk assessment;

[0098] The functional expression for the risk assessment is:

[0099] R f =σ(μ·|P ref -P est |+η·D f +γ·R env ),

[0100] Among them, R f The risk assessment coefficient is σ, where σ represents the normalization process, μ, η, and γ are adjustable weighting coefficients, and P is the weighting coefficient. ref P is the reference tire pressure value. est D represents the tire pressure state. f R represents the characteristic drift. env The weight adjustment factor;

[0101] S405: A preset risk threshold is used to determine the tire explosion prevention warning information by multi-factor coupling, and the risk threshold and the risk assessment coefficient are used to determine the tire explosion prevention warning information. The risk threshold includes an upper limit and a lower limit. The tire explosion prevention warning information includes red warning, yellow warning and normal.

[0102] Specifically, the multi-coupling determination method is as follows:

[0103] Determine whether the risk assessment coefficient is greater than the upper threshold:

[0104] Yes, then the tire explosion prevention warning information is a "red warning";

[0105] If not, then further compare whether the risk assessment coefficient is greater than the lower limit of the threshold. If it is greater, the tire explosion prevention warning information is "yellow warning"; if it is less, the tire explosion prevention warning information is "normal".

[0106] Specifically, the environmental scenario categories include slippery road surfaces, gravel roads, urban roads, and highways; taking slippery road surfaces as an example, when the environmental scenario category is slippery road surfaces, the environmental risk factor matrix is ​​mapped to W. env ={β t =1.3,ω t =1.1}, where W env Let β be the environmental risk factor matrix. t ω is the threshold value for tire deformation. t This is an enhancement item for environmental factors.

[0107] Example 1: Taking a vehicle traveling at a constant speed of 60 km / h on a highway, with normal wheel speed signals, an ambient temperature of 33℃, and a load of 80% as an example, this invention collects wheel speed signals and extracts the main peak frequency in the frequency domain as 3.2 Hz, with a feature drift of 0.03. The initial predicted tire pressure is P0 = 2.25 Bar, and after correction, Pt = 2.18 Bar. The warning model outputs a risk level of 0.72, triggering a red warning.

[0108] Example 2: A tire blowout warning system based on wheel speed recognition, comprising a signal correction module, a feature extraction module, a tire pressure conversion module, and a coupling evaluation module, including:

[0109] The signal correction module is used to acquire the wheel speed signal and correct the wheel speed signal through the signal correction model to obtain the wheel speed time domain signal;

[0110] The feature extraction module is used to convert the wheel rotation time domain signal into a wheel rotation frequency domain signal; and to obtain wheel speed signal features by extracting features from the wheel rotation time domain signal and the wheel rotation frequency domain signal.

[0111] The tire pressure conversion module is used to identify and convert the wheel speed signal characteristics through an indirect monitoring model to obtain the tire pressure status;

[0112] The coupling evaluation module is used to acquire the current environmental image, process the tire pressure status and the current environmental image through a multivariate coupling model, and output tire explosion prevention warning information.

[0113] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A tire blowout prevention and early warning method based on wheel rotational speed recognition, characterized in that, The method comprises the following steps: S1: acquiring a wheel speed signal, correcting the wheel speed signal through a signal correction model to obtain a wheel speed time domain signal; S2: converting the wheel speed time domain signal to obtain a wheel speed frequency domain signal; extracting features of the wheel speed time domain signal and the wheel speed frequency domain signal to obtain a wheel speed signal feature; S3: identifying and converting the wheel speed signal feature through an indirect monitoring model to obtain a tire pressure state; S4: acquiring a current environment image, processing the tire pressure state and the current environment image through a multi-element coupling model to output tire anti-blast warning information; The modeling process of the multi-element coupling model is as follows: S401: extracting features of the current environment image to obtain an environment feature; S402: classifying the environment feature through a classifier to obtain an environment scene category; S403: mapping the environment scene category to obtain an environment risk factor matrix, and calculating the environment risk factor matrix through dot product fusion to obtain a weight adjustment factor; S404: obtaining a risk assessment coefficient by combining the weight adjustment factor and the tire pressure state risk assessment; S405: presetting a risk threshold, and outputting the tire anti-blast warning information by judging the risk threshold and the risk assessment coefficient through multi-element coupling, wherein the risk threshold comprises an upper threshold and a lower threshold.

2. The method of claim 1, wherein the method further comprises: The correction process of the wheel speed signal in step S1 comprises: S101: calculating the error of the wheel speed signal through a least square method to obtain a gear ring error; S102: correcting the wheel speed signal through the gear ring error to obtain a reference wheel speed signal; S103: linearly interpolating the reference wheel speed signal to obtain a reference wheel speed reconstruction signal; S104: reconstructing the reference wheel speed reconstruction signal through an adaptive weight gradient to obtain the wheel speed time domain signal.

3. The method of claim 1, wherein the method further comprises: The mathematical expression of the conversion in step S2 is as follows: ， wherein X(k) is the wheel rotational speed frequency domain signal, n denotes a time domain index variable, i.e. the currently processed sample position, N is the total number of samples, i.e. the wheel rotational speed time domain signal length, x(n) is the wheel rotational speed time domain signal, k denotes a frequency index variable, j is the imaginary unit.

4. The method for identifying a tire blowout according to claim 1, wherein The identification and conversion process of the indirect monitoring model in step S3 is as follows: S301: identifying the wheel speed signal feature through a tire pressure identification network to obtain a normal wheel speed signal feature; S302: predicting and converting the normal wheel speed signal feature to obtain the tire pressure state.

5. The method of claim 4, wherein the tire burst prevention warning based on wheel speed recognition is characterized by, The identification process of the tire pressure identification network in step S301 is as follows: S301-1: denoising the wheel speed signal feature through an adaptive wavelet threshold to obtain a reference frequency band resonance feature; S301-2: classifying the reference frequency band resonance feature through a decision tree to obtain the normal wheel speed signal feature.

6. The method of claim 4, wherein the method further comprises: The specific process of the prediction conversion in step S302 is as follows: S302-1: predicting the normal wheel speed signal feature to obtain a tire pressure initial state; S302-2: presetting a tire stiffness compensation factor and an environment compensation weight and correcting the tire pressure initial state to obtain a tire pressure reference state; S302-3: adding a time stamp to the tire pressure reference state to obtain a time sequence tire pressure reference state; calculating the time sequence tire pressure reference state through linear calculation to obtain a verification coefficient; S302-4: verifying the verification coefficient through multi-time domain consistency to obtain the tire pressure state.

7. The method of claim 6, wherein the method further comprises: The method of multi-time domain consistency verification in the step S302-4 is: A preset verification threshold is set, and whether the verification coefficient is less than the verification threshold is judged according to the verification coefficient and the verification threshold: Yes, the time sequence tire pressure reference state is the tire pressure state; No, the intelligent agent confirms the time sequence tire pressure reference state.

8. The method of claim 1, wherein the method further comprises: The method of multi-element coupling judgment in the step S405 is: Whether the risk assessment coefficient is greater than the upper threshold is judged: Yes, the tire explosion prevention early warning information is "red early warning"; No, whether the risk assessment coefficient is greater than the lower threshold is further compared, and when greater than, the tire explosion prevention early warning information is "yellow early warning"; when less than, the tire explosion prevention early warning information is "normal".

9. A tire burst prevention early warning system based on wheel speed recognition, comprising a signal correction module, a feature extraction module, a tire pressure conversion module, a coupling evaluation module, a multi-coupling model module, for executing the method according to any one of claims 1-8, characterized in that, Comprise: The signal correction module is used for acquiring a wheel speed signal, correcting the wheel speed signal through a signal correction model to obtain a wheel speed time domain signal; The feature extraction module is used for converting the wheel speed time domain signal to obtain a wheel speed frequency domain signal; wheel speed signal features are obtained by feature extraction of the wheel speed time domain signal and the wheel speed frequency domain signal; The tire pressure conversion module is used for identifying and converting the wheel speed signal features to obtain a tire pressure state through an indirect monitoring model; The coupling evaluation module is used for acquiring a current environment image, processing the tire pressure state and the current environment image through a multi-element coupling model to output tire explosion prevention early warning information; The multi-element coupling model module is used for modeling the multi-element coupling model, and the process is: S401: environment features are obtained by feature extraction of the current environment image; S402: an environment scene category is obtained by classifier classification of the environment features; S403: an environment risk factor matrix is obtained by mapping the environment scene category, and a weight adjustment factor is obtained by dot product fusion calculation of the environment risk factor matrix; S404: a risk assessment coefficient is obtained by combining the weight adjustment factor and the tire pressure state risk assessment; S405: a risk threshold is preset, and the tire explosion prevention early warning information is output by multi-element coupling judgment of the risk threshold and the risk assessment coefficient, wherein the risk threshold comprises an upper threshold and a lower threshold.

Images