Wheel falling early warning system

Abstract

The invention discloses a wheel falling-off early warning system, relates to the technical field of automobile safety, and solves the technical problem that the wheel falling-off early warning efficiency is low due to the fact that abnormal judgment is carried out by calculating a state coefficient of a wheel and comparing the state coefficient with a fixed threshold in the prior art to cause a false alarm condition in abnormal recognition of wheel falling-off. The method comprises the steps of obtaining wheel data, vehicle data and road surface data; calculating a wheel wear coefficient according to the historical wheel data and the historical vehicle data; calculating a comprehensive abnormal coefficient of the wheel after calculating an external abnormal coefficient according to the wheel data; generating an alarm signal according to the comprehensive abnormal coefficient; according to the technical scheme, a prompt is made according to the alarm signal, factors in the aspects of wheel abrasion, wheel vibration and the like are considered in factors affecting wheel falling, related threshold values are dynamically adjusted according to the running states of the wheels on different roads, the false alarm situation during running on bumpy roads can be reduced, and meanwhile the wheel falling early warning efficiency is improved.

Description

Technical Field

[0001] The present application belongs to the field of automobile safety technology, and specifically relates to a wheel fall-off warning system. Background Art

[0002] The invention of the wheel is one of the important milestones in human history. The earliest wheel may have originated in Mesopotamia around 4000 BC. Over time, the wheel has been gradually improved and perfected, becoming an indispensable part of modern cars. It supports the weight of the entire vehicle, bears the driving force, braking force and various forces from the ground to the wheels, and realizes the movement of the car through the contact between the tire and the road. At the same time, the steering wheel also has the task of guiding the direction of the car.

[0003] Wheel fall is a serious safety hazard during vehicle driving, which may lead to serious consequences such as vehicle loss of control and traffic accidents. In the prior art, the monitoring of wheel fall mainly relies on the driver's visual observation and vehicle maintenance, as well as the use of wheel state coefficients and fixed thresholds for abnormal judgment, which leads to false alarms in the abnormal identification of wheel fall, and thus leads to low efficiency of wheel fall warning; for example, on bumpy roads, the wheel state coefficient will be higher than that on normal roads. At this time, if a fixed threshold is used for abnormal judgment, the wheel in a normal state will be judged as abnormal; therefore, the wheel fall warning system still needs further improvement. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes a wheel detachment warning system, which is used to solve the problem that the prior art calculates the state coefficient of the wheel and compares it with a fixed threshold to make an abnormal judgment, resulting in false alarms in the abnormal identification of wheel detachment, which in turn leads to low efficiency of wheel detachment warning.

[0005] To achieve the above-mentioned purpose, the first aspect of the present application provides a wheel fall-off warning system, comprising: a data acquisition module, a data analysis module, a warning module and a database;

[0006] The data acquisition module is used to acquire wheel data, vehicle data and road surface data through data acquisition equipment;

[0007] The data analysis module calculates the wheel wear coefficient according to the historical wheel data and the historical vehicle data; calculates the wheel comprehensive abnormality coefficient after calculating the external abnormality coefficient according to the wheel data; and generates an alarm signal according to the comprehensive abnormality coefficient;

[0008] The early warning module: makes prompts according to the alarm signal and notifies relevant personnel.

[0009] The present application obtains wheel data, vehicle data and road surface data; calculates the wheel wear coefficient based on historical wheel data and historical vehicle data; calculates the external abnormality coefficient based on the wheel data and then calculates the comprehensive wheel abnormality coefficient; generates an alarm signal based on the comprehensive abnormality coefficient; makes a prompt based on the alarm signal, takes factors such as wheel wear and wheel vibration into consideration among the factors that affect wheel detachment, and dynamically adjusts relevant thresholds based on the operating status of the wheels on different roads, which can reduce false alarms when driving on bumpy roads and improve the efficiency of wheel detachment warning.

[0010] Further, the calculating of the wheel wear coefficient according to the historical wheel data and the historical vehicle data includes:

[0011] Obtain the load weight CZ in the historical wheel data and the high-speed driving mileage GXL and the low-speed driving mileage DXL in the corresponding historical vehicle data;

[0012] The wheel wear coefficient CMX is calculated by the formula CMX=1-exp(-(k1×∑(CZi / DZ×(α1×GXLi+α2×DXLi) / DL))); wherein i represents the number of the wheel weight carried each time, i=1, 2,…, M, M is the total number of wheel weight numbers; k1 is the proportional coefficient, k1∈(0,1); α1 and α2 are weight coefficients, α1 and α2∈(0,1); DZ is the unit weight, and DL is the unit mileage.

[0013] Furthermore, the mileage includes mileage on smooth roads and mileage on bumpy roads, including:

[0014] Obtain the smooth road mileage GPXL and the bumpy road mileage GDXL in the high-speed driving mileage, and the smooth road mileage DPXL and the bumpy road mileage DDXL in the low-speed driving mileage;

[0015] The high-speed driving mileage GXL is calculated by the formula GXL = β1 × GPXL + β2 × GDXL;

[0016] The low-speed driving mileage DXL is calculated by the formula DXL=β1×DPXL+β2×DDXL; wherein β1 and β2 are weight coefficients, and β1 and β2∈(0,1).

[0017] Further, the step of calculating the wheel comprehensive abnormality coefficient after calculating the external abnormality coefficient according to the wheel data includes:

[0018] Obtain wheel data and wheel wear coefficient CMX;

[0019] Calculate the external anomaly coefficient WYX based on the wheel data;

[0020] The comprehensive wheel abnormality coefficient CZYX is calculated by the formula CZYX=CMX^(1+β)×WYX; wherein β is an exponential coefficient, β∈(0,1).

[0021] Further, the calculation of the external abnormality coefficient WYX according to the wheel data includes:

[0022] Obtaining the vibration amplitude ZF and vibration frequency ZP as well as the standard vibration amplitude BZF and standard vibration frequency BZP in the wheel data;

[0023] When the vibration amplitude is greater than the standard vibration amplitude, the vibration amplitude influence value ZFY is set to the absolute value of the difference between the vibration amplitude and the standard vibration amplitude; otherwise, ZFY=0;

[0024] When the vibration frequency is greater than the standard vibration frequency, the vibration frequency influence value ZPY is set to the absolute value of the difference between the vibration frequency and the standard vibration frequency; otherwise, ZPY=0;

[0025] The external anomaly coefficient WYX is calculated by the formula WYX=1-exp(α3×ZFY / DZF+α4×ZPY / DZP); wherein α3 and α4 are weight coefficients, α3 and α4∈(0,1); DZF is the unit vibration amplitude, and DZP is the unit vibration frequency.

[0026] Furthermore, the generating of the alarm signal according to the comprehensive abnormal coefficient of the wheel includes:

[0027] S1: Obtain the wheel comprehensive abnormality coefficient, wheel wear coefficient and external abnormality coefficient, as well as the roughness index IRI in the road surface data;

[0028] S2: When IRI is less than the flatness index threshold BIRI, determine whether the wheel comprehensive abnormality coefficient is greater than the comprehensive threshold one;

[0029] Yes, generate a wheel-off warning signal;

[0030] If no, determine whether the wheel wear coefficient is greater than the wear threshold; if yes, generate a severe wheel wear alarm signal; if no, do nothing;

[0031] Determine whether the external abnormality coefficient is greater than the external abnormality threshold 1, if yes, generate a wheel fall-off warning signal; if no, do not perform any operation;

[0032] S3: When IRI is greater than or equal to the flatness index threshold BIRI, determine whether the wheel comprehensive abnormality coefficient is greater than comprehensive threshold 2;

[0033] Yes, generate a wheel-off warning signal;

[0034] If no, determine whether the wheel wear coefficient is greater than the wear threshold; if yes, generate a severe wheel wear alarm signal; if no, do nothing;

[0035] S4: Determine whether the external abnormality coefficient is greater than the external abnormality threshold value 2. If yes, generate a wheel fall-off warning signal; if no, do nothing.

[0036] Furthermore, the second external abnormality threshold and the second comprehensive threshold are calculated through road surface data, including:

[0037] Obtain the roughness index IRI, standard deviation s, external anomaly threshold WYY1 and comprehensive threshold ZY1 in the road surface data;

[0038] The external abnormal threshold value WYY2 is calculated by the formula WYY2=WYY1×(1+exp(-(α5×(IRI-BIRI) / DIRI+α6×(s-Bs) / Ds)));

[0039] The comprehensive threshold value ZY2 is calculated by the formula ZY2=ZY1×(1+exp(-(α5×(IRI-BIRI) / DIRI+α6×(s-Bs) / Ds))); wherein α5 and α6 are weight coefficients, α5 and α6∈(0,1); Bs is the standard deviation threshold, DIRI is the unit index, and Ds is the unit standard deviation.

[0040] The present application takes road surface data into consideration and dynamically adjusts the corresponding abnormal judgment threshold value, so that when making abnormal judgments on bumpy roads, wheel abnormalities caused by road surface factors are not judged as wheel detachment abnormalities, thereby reducing the occurrence of false alarms of wheel detachment warnings and improving the efficiency of wheel detachment warnings.

[0041] Compared with the prior art, the beneficial effects of this application are:

[0042] 1. The present application obtains wheel data, vehicle data and road surface data; calculates the wheel wear coefficient according to historical wheel data and historical vehicle data; calculates the external abnormality coefficient according to the wheel data and then calculates the comprehensive abnormality coefficient of the wheel; generates an alarm signal according to the comprehensive abnormality coefficient; makes a prompt according to the alarm signal, takes factors such as wheel wear and wheel vibration into consideration among the factors affecting wheel shedding, and dynamically adjusts relevant thresholds according to the operating status of the wheels on different roads, which can reduce false alarms when driving on bumpy roads and improve the efficiency of wheel shedding warning.

[0043] 2. This application takes road surface data into consideration and dynamically adjusts the corresponding abnormal judgment threshold value, so that when making abnormal judgments on bumpy roads, wheel abnormalities caused by road surface factors are not judged as wheel detachment abnormalities, thereby reducing the occurrence of false alarms of wheel detachment warnings and improving the efficiency of wheel detachment warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A schematic diagram of the principle of a wheel fall-off warning system of the present application;

[0046] Figure 2 This is a flow chart of a wheel fall-off warning method of the present application. DETAILED DESCRIPTION

[0047] The technical solution of the present application will be described clearly and completely in conjunction with the embodiments below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0048] See also Figure 1-Figure 2 , the first aspect of the present application provides a wheel fall-off warning system, including: a data acquisition module, a data analysis module, a warning module and a database;

[0049] Data acquisition module: wheel data, vehicle data and road surface data are acquired through data acquisition equipment; data acquisition equipment includes laser radar, various sensors, etc.; wheel data includes wheel load, vibration amplitude and vibration frequency, etc.; vehicle data includes high-speed mileage and low-speed mileage, etc.; road surface data includes flatness index and standard deviation, etc.;

[0050] Data analysis module: calculates the wheel wear coefficient based on historical wheel data and historical vehicle data. The wheel wear coefficient refers to the degree coefficient of wheel wear; calculates the external abnormality coefficient based on the wheel data and then calculates the wheel comprehensive abnormality coefficient. The external abnormality coefficient refers to the abnormality coefficient calculated due to factors such as vibration of the wheel. The wheel comprehensive abnormality coefficient refers to the abnormality coefficient of the entire wheel; generates an alarm signal based on the comprehensive abnormality coefficient;

[0051] Early warning module: Prompts are given based on alarm signals and relevant personnel are notified; alarm signals include wheel fall-off alarm signals, severe wheel wear alarm signals and abnormal wheel vibration alarm signals.

[0052] This embodiment obtains wheel data, vehicle data and road surface data; calculates the wheel wear coefficient based on historical wheel data and historical vehicle data; calculates the external abnormality coefficient based on the wheel data and then calculates the comprehensive wheel abnormality coefficient; generates an alarm signal based on the comprehensive abnormality coefficient; makes a prompt based on the alarm signal, takes factors such as wheel wear and wheel vibration into consideration as factors that affect wheel detachment, and dynamically adjusts relevant thresholds based on the operating status of the wheels on different roads, which can reduce false alarms when driving on bumpy roads and improve the efficiency of wheel detachment warning.

[0053] In this embodiment, the wheel wear coefficient is calculated based on the historical wheel data and the historical vehicle data, including:

[0054] Obtaining the bearing weight CZ in several historical wheel data and the high-speed driving mileage GXL and low-speed driving mileage DXL in the corresponding historical vehicle data;

[0055] The wheel wear coefficient CMX is calculated by the formula CMX=1-exp(-(k1×∑(CZi / DZ×(α1×GXLi+α2×DXLi) / DL))); wherein i represents the number of the wheel load each time, i=1, 2, ..., M, and M is the total number of wheel load numbers; k1 is the proportionality coefficient, k1∈(0, 1), and the specific value is set according to experience; α1 and α2 are weight coefficients, α1 and α2∈(0, 1), and the specific value is set according to experience; DZ is the unit weight, and DL is the unit mileage, and the specific value is set according to experience. In this embodiment, DZ is set to 1 ton and DL is set to 1 kilometer; the greater the wheel load and the more mileage the vehicle has traveled, the more serious the wheel wear will be; the greater the mileage of the wheel at high speed, the greater the impact on the wheel wear will be than the mileage at low speed, so in this embodiment, α1>α2; the wheel wear coefficient increases with the increase of the load and the mileage of the vehicle.

[0056] The driving mileage in this embodiment includes the smooth road section driving mileage and the bumpy road section driving mileage, including:

[0057] Obtain the smooth road mileage GPXL and the bumpy road mileage GDXL in the high-speed driving mileage, and the smooth road mileage DPXL and the bumpy road mileage DDXL in the low-speed driving mileage;

[0058] The high-speed driving mileage GXL is calculated by the formula GXL = β1 × GPXL + β2 × GDXL;

[0059] The low-speed driving mileage DXL is calculated by the formula DXL=β1×DPXL+β2×DDXL; wherein β1 and β2 are weight coefficients, and β1 and β2∈(0,1), and the specific values ​​are set based on experience; in the vehicle mileage, not only high-speed driving and low-speed driving have different effects on wheel wear, but the conditions of the driving section will also lead to different wheel wear conditions. For bumpy sections, the severity of wheel wear is higher than that for smooth sections; therefore, in this embodiment, β1<β2.

[0060] In this embodiment, the calculation of the wheel comprehensive abnormality coefficient after calculating the external abnormality coefficient according to the wheel data includes:

[0061] Obtain wheel data and wheel wear coefficient CMX;

[0062] Calculate the external anomaly coefficient WYX based on the wheel data;

[0063] The comprehensive wheel abnormality coefficient CZYX is calculated by the formula CZYX=CMX^(1+β)×WYX; wherein β is an exponential coefficient, β∈(0,1), and the specific value is set based on experience; the wheel wear coefficient will have a great influence on wheel falling off, and external abnormal conditions will also cause wheel falling off; therefore, the comprehensive wheel abnormality coefficient will increase with the increase of the wheel wear coefficient and the external abnormality coefficient.

[0064] In this embodiment, the external abnormality coefficient WYX is calculated according to the wheel data, including:

[0065] Obtaining the vibration amplitude ZF and vibration frequency ZP as well as the standard vibration amplitude BZF and standard vibration frequency BZP in the wheel data;

[0066] When the vibration amplitude is greater than the standard vibration amplitude, the vibration amplitude influence value ZFY is set to the absolute value of the difference between the vibration amplitude and the standard vibration amplitude; otherwise, ZFY=0; the vibration amplitude influence value refers to the influence value of the vibration amplitude on the external abnormal coefficient;

[0067] When the vibration frequency is greater than the standard vibration frequency, the vibration frequency influence value ZPY is set to the absolute value of the difference between the vibration frequency and the standard vibration frequency; otherwise, ZPY=0; the vibration frequency influence value refers to the influence value of the vibration frequency on the external abnormal coefficient;

[0068] The external abnormality coefficient WYX is calculated by the formula WYX=1-exp(α3×ZFY / DZF+α4×ZPY / DZP); wherein α3 and α4 are weight coefficients, α3 and α4∈(0,1), and the specific values ​​are set according to experience; DZF is the unit vibration amplitude, and DZP is the unit vibration frequency, and the specific values ​​are set according to experience; the greater the vibration frequency and the greater the vibration amplitude, the more the vibration of the wheel exceeds the normal range, and the possibility of the wheel falling off becomes very large; therefore, the external abnormality coefficient increases with the increase of the vibration amplitude influence value and the vibration frequency influence value.

[0069] In this embodiment, the alarm signal is generated according to the comprehensive abnormal coefficient of the wheel, including:

[0070] S1: Obtain the wheel comprehensive abnormality coefficient, wheel wear coefficient and external abnormality coefficient, as well as the roughness index IRI in the road surface data;

[0071] S2: When IRI is less than the flatness index threshold BIRI, BIRI is set based on experience. In this embodiment, BIRI is set to 8 m / km;

[0072] Determine whether the comprehensive abnormal coefficient of the wheel is greater than the comprehensive threshold value 1, which is set according to experience; if yes, generate a wheel fall-off warning signal;

[0073] If no, determine whether the wheel wear coefficient is greater than the wear threshold, which is set based on experience; if yes, generate a severe wheel wear alarm signal; if no, do nothing;

[0074] Determine whether the external abnormality coefficient is greater than the external abnormality threshold value 1, which is set based on experience; if yes, generate a wheel vibration abnormality alarm signal; if no, do nothing;

[0075] S3: When IRI is greater than or equal to the flatness index threshold BIRI, determine whether the wheel comprehensive abnormality coefficient is greater than comprehensive threshold 2;

[0076] Yes, generate a wheel-off warning signal;

[0077] If no, determine whether the wheel wear coefficient is greater than the wear threshold; if yes, generate a severe wheel wear alarm signal; if no, do nothing;

[0078] S4: Determine whether the external abnormality coefficient is greater than the external abnormality threshold value 2. If yes, generate a wheel vibration abnormality alarm signal; if no, do nothing.

[0079] The second external abnormality threshold and the second comprehensive threshold in this embodiment are calculated through road surface data, including:

[0080] Obtain the roughness index IRI, standard deviation s, external anomaly threshold WYY1 and comprehensive threshold ZY1 in the road surface data;

[0081] The external abnormal threshold value WYY2 is calculated by the formula WYY2=WYY1×(1+exp(-(α5×(IRI-BIRI) / DIRI+α6×(s-Bs) / Ds)));

[0082] The comprehensive threshold value two ZY2 is calculated by the formula ZY2=ZY1×(1+exp(-(α5×(IRI-BIRI) / DIRI+α6×(s-Bs) / Ds))); wherein α5 and α6 are weight coefficients, α5 and α6∈(0,1), and the specific values ​​are set according to experience; Bs is the standard deviation threshold, DIRI is the unit index, and Ds is the unit standard deviation, and the specific values ​​are set according to experience; when the IRI and s values ​​deviate from their corresponding thresholds, it means that the road condition is unfavorable for driving and there is a bumpy road surface. At this time, the vibration amplitude and vibration frequency of the wheel on the bumpy road surface will be higher than those on the smooth road surface, while the wheel state at this time is normal. Therefore, when considering the wheel falling off on the bumpy road surface, the road surface reason needs to be excluded; therefore, the external abnormality threshold value two and the comprehensive threshold value two increase with the increase of IRI and s.

[0083] This embodiment takes road surface data into consideration and dynamically adjusts the corresponding abnormal judgment threshold value, so that when making abnormal judgments on bumpy roads, wheel abnormalities caused by road surface factors are not judged as wheel detachment abnormalities, thereby reducing the occurrence of false alarms of wheel detachment warnings and improving the efficiency of wheel detachment warnings.

[0084] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0085] The working principle of the present application is as follows: by acquiring wheel data, vehicle data and road surface data; calculating the wheel wear coefficient according to historical wheel data and historical vehicle data; calculating the external abnormality coefficient according to the wheel data and then calculating the comprehensive abnormality coefficient of the wheel; generating an alarm signal according to the comprehensive abnormality coefficient; making a prompt and notifying relevant personnel according to the alarm signal, taking factors such as wheel wear and wheel vibration into consideration among the factors affecting wheel shedding, dynamically adjusting relevant thresholds according to the operating status of wheels on different roads, which can reduce false alarms when driving on bumpy roads, and at the same time improve the efficiency of wheel shedding warning, and avoid the problem that the prior art makes abnormal judgment by calculating the wheel status coefficient and comparing it with a fixed threshold, resulting in false alarms in the abnormal identification of wheel shedding, which in turn leads to low efficiency of wheel shedding warning.

[0086] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. A wheel fall-off warning system, characterized in that: include: Data collection module, data analysis module, early warning module and database; The data acquisition module is used to acquire wheel data, vehicle data and road surface data through data acquisition equipment; The data analysis module calculates the wheel wear coefficient according to the historical wheel data and the historical vehicle data; Calculate the wheel comprehensive abnormality coefficient after calculating the external abnormality coefficient according to the wheel data; generate an alarm signal according to the comprehensive abnormality coefficient; The early warning module: makes prompts according to the alarm signal and notifies relevant personnel.

2. A wheel fall-off warning system according to claim 1, characterized in that: The calculating of the wheel wear coefficient according to the historical wheel data and the historical vehicle data comprises: Obtain the load weight CZ in the historical wheel data and the high-speed driving mileage GXL and the low-speed driving mileage DXL in the corresponding historical vehicle data; The wheel wear coefficient CMX is calculated by the formula CMX=1-exp(-(k1×∑(CZi / DZ×(α1×GXLi+α2×DXLi) / DL))); wherein i represents the number of the wheel weight carried each time, i=1, 2,…, M, M is the total number of wheel weight numbers; k1 is the proportional coefficient, k1∈(0,1); α1 and α2 are weight coefficients, α1 and α2∈(0,1); DZ is the unit weight, and DL is the unit mileage.

3. A wheel fall-off warning system according to claim 2, characterized in that: The mileage includes smooth road mileage and bumpy road mileage, including: Obtain the smooth road mileage GPXL and the bumpy road mileage GDXL in the high-speed driving mileage, and the smooth road mileage DPXL and the bumpy road mileage DDXL in the low-speed driving mileage; The high-speed driving mileage GXL is calculated by the formula GXL = β1 × GPXL + β2 × GDXL; The low-speed driving mileage DXL is calculated by the formula DXL=β1×DPXL+β2×DDXL; wherein β1 and β2 are weight coefficients, and β1 and β2∈(0,1).

4. A wheel fall-off warning system according to claim 1, characterized in that: The step of calculating the wheel comprehensive abnormality coefficient after calculating the external abnormality coefficient according to the wheel data comprises: Obtain wheel data and wheel wear coefficient CMX; Calculate the external anomaly coefficient WYX based on the wheel data; The comprehensive wheel abnormality coefficient CZYX is calculated by the formula CZYX=CMX^(1+β)×WYX; wherein β is an exponential coefficient, β∈(0,1).

5. A wheel fall-off warning system according to claim 4, characterized in that: The calculation of the external abnormality coefficient WYX according to the wheel data includes: Obtaining the vibration amplitude ZF and vibration frequency ZP as well as the standard vibration amplitude BZF and standard vibration frequency BZP in the wheel data; When the vibration amplitude is greater than the standard vibration amplitude, the vibration amplitude influence value ZFY is set to the absolute value of the difference between the vibration amplitude and the standard vibration amplitude; otherwise, ZFY=0; When the vibration frequency is greater than the standard vibration frequency, the vibration frequency influence value ZPY is set to the absolute value of the difference between the vibration frequency and the standard vibration frequency; otherwise, ZPY=0; The external anomaly coefficient WYX is calculated by the formula WYX=1-exp(α3×ZFY / DZF+α4×ZPY / DZP); wherein α3 and α4 are weight coefficients, α3 and α4∈(0,1); DZF is the unit vibration amplitude, and DZP is the unit vibration frequency.

6. A wheel fall-off warning system according to claim 1, characterized in that: The generating of the alarm signal according to the comprehensive abnormal coefficient of the wheel comprises: S1: Obtain the wheel comprehensive abnormality coefficient, wheel wear coefficient and external abnormality coefficient, as well as the roughness index IRI in the road surface data; S2: When IRI is less than the flatness index threshold BIRI, determine whether the wheel comprehensive abnormality coefficient is greater than the comprehensive threshold one; Yes, generate a wheel-off warning signal; If no, determine whether the wheel wear coefficient is greater than the wear threshold; if yes, generate a severe wheel wear alarm signal; if no, do nothing; Determine whether the external abnormality coefficient is greater than the external abnormality threshold 1, if yes, generate a wheel fall-off warning signal; if no, do not perform any operation; S3: When IRI is greater than or equal to the flatness index threshold BIRI, determine whether the wheel comprehensive abnormality coefficient is greater than comprehensive threshold 2; Yes, generate a wheel-off warning signal; If no, determine whether the wheel wear coefficient is greater than the wear threshold; if yes, generate a severe wheel wear alarm signal; if no, do nothing; S4: Determine whether the external abnormality coefficient is greater than the external abnormality threshold value 2. If yes, generate a wheel fall-off warning signal; if no, do nothing.

7. A wheel fall-off warning system according to claim 6, characterized in that: The second external abnormality threshold and the second comprehensive threshold are calculated through road surface data, including: Obtain the roughness index IRI, standard deviation s, external anomaly threshold WYY1 and comprehensive threshold ZY1 in the road surface data; The external abnormal threshold value WYY2 is calculated by the formula WYY2=WYY1×(1+exp(-(α5×(IRI-BIRI) / DIRI+α6×(s-Bs) / Ds))); The comprehensive threshold value ZY2 is calculated by the formula ZY2=ZY1×(1+exp(-(α5×(IRI-BIRI) / DIRI+α6×(s-Bs) / Ds))); wherein α5 and α6 are weight coefficients, α5 and α6∈(0,1); Bs is the standard deviation threshold, DIRI is the unit index, and Ds is the unit standard deviation.

Images