Fatigue driving early warning method and device based on tire pressure monitoring

Abstract

The invention discloses a fatigue driving early warning method based on tire pressure monitoring. The method comprises the following steps: acquiring tire acceleration data of a motor vehicle in real time through a plurality of tire sensors; detecting an engine vibration signal of the motor vehicle through a vibration detection module; receiving the tire acceleration data and a vibration signal of the motor vehicle through a tire pressure receiver; analyzing the frequency spectrum characteristics of the tire acceleration data and the engine vibration signal so as to judge whether the motor vehicle is in a parking state or a congestion state; counting the accumulated effective driving duration of the motor vehicle; and when the accumulated effective driving duration of the motor vehicle exceeds the driving duration threshold value, triggering an alarm. Meanwhile, the invention provides a fatigue driving early warning device based on tire pressure monitoring and a computer readable storage medium.

Description

Technical Field

[0001] This application relates to the field of vehicle safety monitoring technology, and more specifically, to a fatigue driving warning device, method, and storage medium based on tire pressure monitoring. Background Technology

[0002] Traditional fatigue driving monitoring technologies mainly rely on steering wheel angle sensors or driver facial recognition solutions, which have significant limitations in adaptability to different scenarios.

[0003] This is because the steering wheel monitoring solution generates a large number of false alarms when the vehicle is idling, as there is no steering input. Real-world testing data shows a false alarm rate as high as 89% in urban congestion scenarios, with 3.2 missed alarms per hour. This is because the steering wheel sensor cannot capture the micro-rotation characteristics of the tires at idle, while experiments have shown that tires still exhibit a dominant frequency vibration of 2-3 Hz in congested conditions, with an amplitude maintained in the range of 0.08-0.15g.

[0004] The evolution of current technologies shows that the development from mechanical odometers to electronic monitoring solutions has not effectively solved the problem of recognizing driving behavior when the vehicle is stationary. In particular, when the TPMS system is only used for tire pressure monitoring, its built-in high-precision acceleration sensor is not fully utilized.

[0005] Current technical solutions have shortcomings in terms of hardware resource reusability, accuracy in identifying complex road conditions, and control of system false alarm rate. There is an urgent need to develop a solution that can simultaneously meet the requirements of driving / parking status monitoring, high hardware reusability, and low false alarm rate. Summary of the Invention

[0006] The purpose of this invention is to solve the above-mentioned problems and provide a fatigue driving warning device and method based on tire pressure monitoring, which has the advantages of improving the accuracy of driving status recognition, reducing the false judgment rate, and effectively reusing the hardware resources of existing tire pressure monitoring systems.

[0007] To achieve the objectives of this invention, the following technical solution is adopted: A fatigue driving warning method based on tire pressure monitoring includes the following steps: The vehicle's tire acceleration data is collected in real time using multiple tire sensors; The vibration signal of the motor vehicle's engine is detected by a vibration detection module; The tire acceleration data and the vibration signal of the vehicle are received by the tire pressure receiver; By analyzing the spectral characteristics of the tire acceleration data and the engine vibration signal, it can be determined whether the vehicle is in a parked or congested state. The cumulative effective driving time of motor vehicles is calculated; and An alarm is triggered when the cumulative effective driving time of a motor vehicle exceeds the driving time threshold.

[0008] Preferably, analyzing the spectral characteristics of the tire acceleration data includes: performing a Fourier transform on the tire acceleration data to extract the 5-50Hz main frequency component; when the main frequency is continuously >5Hz and the amplitude is >0.2g, it is determined that the motor vehicle is in a driving state.

[0009] Preferably, the analysis of the engine vibration signal includes: when the engine vibration RMS value is >0.1g and lasts for 10 seconds or more, it is determined that the motor vehicle is in a congested state; when the engine vibration RMS is <0.05g, it is determined that the motor vehicle is in a stopped state.

[0010] Preferably, the cumulative effective driving time of the motor vehicle includes: the duration of the motor vehicle in driving state and in congested state; and the statistics are paused when the motor vehicle is in a parked state with the engine off.

[0011] Preferably, the real-time acquisition of tire acceleration data of the motor vehicle through multiple tire sensors includes: acquiring triaxial acceleration data through the tire sensors, with a sampling rate ≥100Hz. More preferably, the driving time threshold is 4 hours.

[0012] Simultaneously, a fatigue driving warning device based on tire pressure monitoring is provided, including: Multiple tire sensors are installed in the tires of two or more motor vehicles to collect tire acceleration data of the motor vehicle in real time. The vibration detection module is installed on the vehicle chassis or receiver PCB board to detect engine vibration signals of motor vehicles. A tire pressure receiver, which is communicatively connected to the plurality of tire sensors and the vibration detection module, comprises: The driving status determination unit is used to analyze the spectral characteristics of the tire acceleration data; The parking status analysis unit is used to distinguish whether the motor vehicle is in a parked state or a congested state by analyzing the engine vibration signal. A fatigue timer is used to count the cumulative effective driving time of a motor vehicle; and The early warning module is used to trigger an alarm when the cumulative effective driving time of a motor vehicle exceeds the driving time threshold.

[0013] Preferably, the driving state determination unit is configured to: perform Fourier transform on the tire acceleration data to extract the 5-50Hz main frequency component; when the main frequency is continuously >5Hz and the amplitude is >0.2g, it is determined that the motor vehicle is in a driving state.

[0014] Preferably, the parking status analysis unit includes: a vibration signal bandpass filter and an RMS calculation module; the vibration signal bandpass filter is configured to determine whether the vibration RMS value is 0.1g and lasts for 10 seconds or more, and if so, it is determined that the vehicle is in a congested state; the RMS calculation module is configured to determine whether the vibration RMS is 0.05g, and if so, it is determined that the vehicle is in a turned-off parking state.

[0015] This application also provides a computer-readable storage medium storing program instructions that, when executed by a processor, implement the steps of the above-described method.

[0016] As can be seen from the above, the fatigue driving warning device, method and storage medium based on tire pressure monitoring provided in this application accurately distinguishes between driving, parking and congestion states by collecting acceleration data in real time through tire sensors and combining it with vibration signal analysis. It dynamically accumulates the effective driving time and triggers graded warnings, which solves the problem of high misjudgment rate in idling and congestion scenarios of traditional solutions. It has the advantages of improving the accuracy of state recognition, reducing the misjudgment rate and effectively reusing the hardware resources of existing tire pressure monitoring systems.

[0017] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and will become apparent from the description or may be learned by practice of the invention. Attached Figure Description

[0018] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a structural block diagram of an embodiment of the fatigue driving warning method based on tire pressure monitoring according to the present invention. Detailed Implementation

[0019] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and should not be construed as limiting the present invention.

[0020] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, and / or components, nor does it exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connection or wireless coupling. The term “and / or” as used herein includes all or any unit and all combinations of one or more associated listed items.

[0021] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0022] In existing technologies, fatigue driving monitoring systems mostly rely on steering wheel angle or facial recognition technology, but these have blind spots when idling or driving at low speeds. For example, in urban traffic congestion scenarios, vehicles are in a stop-and-go state for extended periods, and traditional systems cannot effectively distinguish between stopped and low-speed driving, leading to a significant increase in false alarm rates. Existing solutions cannot obtain effective data in idling conditions, severely impacting the accuracy of fatigue timing.

[0023] To address the aforementioned issues, the inventors discovered that traditional monitoring methods suffer from signal loss when the vehicle is stationary or moving at low speeds, while tires still generate weak vibrations even at idle. By analyzing the correlation between tire acceleration data and engine vibration signals, they proposed reusing the hardware of the tire pressure monitoring system as a motion state perception platform. Further research revealed that by combining tire acceleration spectrum characteristics with vehicle body vibration energy values, a more accurate driving state judgment model can be established, thereby resolving the monitoring failure problem at idle speeds.

[0024] In existing technologies, traditional driver fatigue monitoring primarily relies on steering wheel angle sensors or driver facial recognition schemes. Steering wheel monitoring schemes generate numerous false alarms when the vehicle is idling due to the lack of steering input; real-world testing shows a high false alarm rate in congested urban environments. This is because steering wheel sensors cannot capture the micro-rotation characteristics of the tires at idle, while experiments have demonstrated that tires still vibrate at specific frequencies in congested conditions. The evolution of current technologies, from mechanical odometers to electronic monitoring solutions, has not effectively solved the problem of recognizing driving behavior when the vehicle is stationary, especially when tire pressure monitoring systems are only used for tire pressure monitoring, their built-in high-precision acceleration sensors are not fully utilized.

[0025] To address the aforementioned issues, a solution is needed that simultaneously meets the requirements of driving / parking status monitoring, high hardware reusability, and low false positive rate. Considering that tire pressure monitoring systems are already equipped with high-precision acceleration sensors, the key breakthrough lies in leveraging existing hardware resources to achieve driving status recognition. Analyzing the tire acceleration spectrum characteristics can effectively capture the vibration patterns of the vehicle during driving; combining this with engine vibration signal analysis can distinguish between parking and idling states. A composite judgment logic needs to be constructed to correlate the dominant frequency component of tire vibration with the engine vibration intensity, thereby establishing an accurate driving status determination mechanism.

[0026] Therefore, this application proposes to collect tire acceleration data of a motor vehicle in real time using multiple tire sensors 101; to detect engine vibration signals of the motor vehicle using a vibration detection module 102; to receive tire acceleration data and vibration signals of the motor vehicle using a tire pressure receiver 103; to analyze the spectral characteristics of the tire acceleration data and the engine vibration signals to determine whether the motor vehicle is in a parked or congested state; to calculate the cumulative effective driving time of the motor vehicle; and to trigger an alarm when the cumulative effective driving time of the motor vehicle exceeds a driving time threshold.

[0027] Among them, tire sensor 101 refers to a device installed inside the vehicle tire to collect acceleration data. Specifically, a triaxial accelerometer can be used, with a sampling frequency of at least 100Hz to meet vibration feature extraction requirements. Vibration detection module 102 refers to a device used to capture mechanical vibrations generated during engine operation. Specifically, a piezoelectric accelerometer combined with a signal conditioning circuit can be used. The preferred installation location is the vehicle chassis or the receiver PCB board. Spectrum feature analysis refers to frequency domain conversion processing of the acceleration data. Specifically, a fast Fourier transform algorithm can be used to extract the energy distribution characteristics in the 5-50Hz frequency band. Cumulative effective driving time statistics refer to the calculation of continuous driving time excluding stationary states. Specifically, this can be achieved by controlling the start and stop of a timer based on the state determination result.

[0028] Specifically, the tire sensor 101 continuously collects triaxial acceleration data and transmits the data wirelessly to the tire pressure receiver 103. The receiver performs spectrum analysis on the acceleration data, extracting the dominant frequency component and its amplitude characteristics in the 5-50Hz frequency band. When the dominant frequency component is detected to continuously exceed 5Hz and the amplitude is greater than 0.2g, the vehicle is determined to be in motion. Simultaneously, the vibration detection module 102 monitors the RMS value of the engine vibration signal in real time. When this value continuously exceeds 0.1g for more than 10 seconds, a congested state is determined; when it is below 0.05g, a stopped state is determined. The timer only accumulates time during both in-motion and congested states. When the accumulated time reaches a preset threshold, an audible and visual alarm is triggered.

[0029] Compared to existing technologies, traditional solutions rely on steering wheel angle or facial recognition, which have blind spots. This solution innovatively reuses existing sensor resources from the tire pressure monitoring system. By jointly analyzing tire vibration spectrum and engine vibration intensity, it can accurately identify the vehicle's actual driving status under complex conditions such as idling and traffic congestion. The problem of existing technologies being unable to distinguish between stationary and idling states is effectively solved, and the accuracy of timing statistics is significantly improved.

[0030] Through the above technical solution, this application achieves accurate determination of vehicle driving status, effectively avoiding the misjudgment problems of traditional solutions in idling and congested scenarios. By reusing the hardware resources of existing tire pressure monitoring systems, driving status monitoring is completed without adding new sensors, significantly improving system reliability and cost-effectiveness. The timing and statistics mechanism eliminates invalid parking time, ensuring that the accuracy of fatigue driving warning meets the needs of actual driving conditions.

[0031] This application further proposes to analyze the spectral characteristics of tire acceleration data, including: extracting the 5-50Hz main frequency component by performing Fourier transform on the tire acceleration data; when the main frequency is continuously greater than 5Hz and the amplitude is greater than 0.2g, it is determined that the motor vehicle is in motion. Fourier transform refers to the processing method of converting time-domain signals into frequency-domain signals. Specifically, it can be implemented using the Fast Fourier Transform algorithm to separate the vibration frequency components in tire acceleration data.

[0032] The dominant frequency component refers to the frequency component with the highest energy proportion in the spectrum. Specifically, it can be filtered by setting a frequency range of 5-50Hz, which covers the periodic vibration characteristics generated by the tires contacting the ground when a motor vehicle is in motion.

[0033] Amplitude refers to the magnitude of the acceleration signal in the frequency domain, which can be specifically achieved through the spectrum amplitude calculation module and is used to quantify the intensity of tire vibration. Specifically, after the tire acceleration data undergoes Fourier transform processing, its dominant frequency component is limited to the range of 5-50Hz. This range corresponds to the periodic vibration generated by the tire's contact with the ground during vehicle movement. When the dominant frequency component consistently exceeds 5Hz and the amplitude exceeds 0.2g, it indicates that the tire is in a regular rotational state, thus determining that the vehicle is in motion. For example, in idling or congested scenarios, if the tire generates a vibration component higher than 5Hz due to the vehicle's slow movement, and the amplitude exceeds 0.2g, it is still recognized as a valid driving state, thereby avoiding misjudgments caused by no steering wheel operation. Compared to existing technologies, traditional solutions rely on steering wheel sensors or visual recognition, which cannot capture the micro-rotation characteristics of the tires. This solution, however, directly correlates the tire's physical motion state by analyzing the spectral characteristics of tire acceleration. For example, existing technologies cannot detect the 2-3Hz micro-vibrations of the tires at idle speed, while this solution can effectively distinguish between a stationary tire and a micro-rotation state by extracting the dominant frequency component above 5Hz. Through the above technical solution, this application can accurately identify the driving behavior of motor vehicles in idling or congested conditions, avoiding misjudgments caused by no steering wheel operation or engine vibration interference. For example, when the vehicle is moving slowly, the main frequency vibration of the tires above 5Hz can be reliably detected, thereby ensuring the accuracy of the cumulative driving time statistics and reducing the false alarm rate of the fatigue driving monitoring system.

[0034] This application further proposes to analyze engine vibration signals, including determining that the motor vehicle is in a congested state when the engine vibration RMS value is greater than 0.1g and lasts for 10 seconds or more; and determining that the motor vehicle is in a stopped state when the engine vibration RMS value is less than 0.05g. The vibration RMS value refers to the effective vibration intensity quantification index of the engine vibration signal. Specifically, it can be implemented using an accelerometer combined with the RMS calculation module 10344 to characterize the energy level of the engine's operating state. The duration of 10 seconds or more refers to the time window condition for state determination, which can be implemented using a timer module in conjunction with a sliding time window algorithm to eliminate instantaneous vibration interference. Specifically, engine vibration signals are collected by an acceleration sensor installed on the vehicle chassis, and the effective frequency band signal is extracted after processing by a bandpass filter. The RMS calculation module 10344 calculates the root mean square value of the filtered signal. When the vibration RMS value remains above 0.1g for 10 consecutive seconds, it indicates that the engine is idling and the vehicle is not moving, which is determined to be a congested state. When the vibration RMS value is below 0.05g, it indicates that the engine has stopped working, which is determined to be a shut-off state. The state determination result is used to control the start and stop logic of the fatigue driving timer. Compared to existing technologies, traditional solutions relying on steering wheel angle sensors cannot identify stationary vehicle characteristics during idling. This solution, however, uses dynamic analysis of the RMS value of engine vibration signals to accurately distinguish whether the vehicle is moving, idling in traffic, or completely stationary. Experiments show that under engine idling conditions, the vibration RMS value remains stable within the range of 0.12-0.25g, showing a significant difference from the noise level when the engine is off. Through the above technical solution, this application achieves accurate identification of vehicle operating status, solving the problem of excessively high misjudgment rate in traditional solutions under idling conditions. In congested scenarios, it can correctly identify when a vehicle is not driving, avoiding the accumulation of invalid driving time and thus improving the reliability of the fatigue driving warning system.

[0035] This application further proposes to count the duration of motor vehicle data under driving and congested conditions; and to pause the data collection when the motor vehicle is turned off and parked. The cumulative effective driving time refers to the effective driving time of a motor vehicle in actual driving or idling while waiting to pass. Specifically, it can be achieved by using a timing module combined with status judgment signals. By distinguishing between driving and parking time statistics, the accumulation of invalid time when the vehicle is stationary can be avoided.

[0036] The pause in the statistics refers to stopping the timing operation when the engine is off or completely stopped. This can be achieved by combining vibration signal detection with timer control logic. By identifying changes in the engine's operating status, the system ensures that time is accumulated only when actual driving behavior occurs. Specifically, by monitoring the vehicle's driving status and engine vibration signals in real time, the vehicle's operating status is divided into three modes: driving, congestion, and parking. When the detected tire acceleration spectrum characteristics meet driving conditions or the engine vibration meets idling conditions, a timer is started to accumulate time; when the engine vibration signal is below a set threshold, it is determined to be a parking state and the timer is paused. This process controls the start and stop of the timer through state switching logic to ensure that only the effective time period when the driver is actually controlling the vehicle is counted. Compared to existing technologies, traditional solutions rely on steering wheel operation or a single driving signal to determine driving status, failing to effectively distinguish between idling and complete stops. This solution integrates a dual judgment mechanism based on tire motion characteristics and engine vibration status, enabling accurate identification of low-speed movement and complete stops in traffic congestion, thus avoiding the miscalculation of driver fatigue driving time during parking and waiting periods. Through the above technical solution, this application solves the problem of false alarms caused by the continuous accumulation of driving time when the vehicle is idling or temporarily parked in traditional monitoring systems. It realizes accurate statistics on the actual driving time of the driver and effectively reduces the probability of false triggers caused by the accumulation of invalid time.

[0037] This application further proposes to acquire triaxial acceleration data through tire sensor 101, with a sampling rate ≥100Hz. Among them, triaxial acceleration data refers to the simultaneous measurement of the acceleration components of the tire in the three spatial axes of X, Y and Z by a sensor. Specifically, it can be achieved by using a microelectromechanical system (MEMS) accelerometer, whose built-in triaxial sensing unit can synchronously output acceleration signals in each direction.

[0038] Among them, a sampling rate of ≥100Hz means that the sensor collects data no less than 100 times per second. This can be achieved by configuring the clock frequency of the analog-to-digital converter to ensure that high-frequency vibration signals can be completely captured. Specifically, the tire sensor 101 continuously outputs triaxial acceleration data during the acquisition process. Synchronous triaxial measurement eliminates signal distortion caused by installation angle deviations in single-axis sensors. Setting the sampling rate to at least 100Hz satisfies the Fourier transform's resolution requirements for the 5-50Hz main frequency components, preventing high-frequency signal aliasing due to insufficient sampling. For example, when the tire produces a 3Hz micro-rotation at idle, the radial component in the triaxial data can detect a periodic amplitude change of 0.08-0.15g, while a sensor with an insufficient sampling rate may misjudge due to signal truncation. Compared to existing technologies, traditional solutions rely solely on a single-axis accelerometer with a sampling rate below 50Hz, failing to effectively capture the multi-axis micro-vibration characteristics of tires during idling or congestion. This application significantly improves signal integrity and spectral analysis accuracy through triaxial data acquisition and a high sampling rate configuration. Through the above technical solution, this application solves the problem of missed detection of tire micro-motion characteristics caused by missing single-axis data or insufficient sampling rate in the prior art, so that the driving status judgment module can accurately distinguish the vehicle operating status based on more comprehensive high-frequency vibration data, thereby reducing the misjudgment rate.

[0039] This application further proposes a driving time threshold of 4 hours.

[0040] The driving time threshold refers to the cumulative effective driving time threshold that triggers a fatigue alarm. This can be achieved by linking a timer module with a status judgment unit; when the cumulative effective driving time reaches this threshold, an alarm is automatically triggered. This threshold is set based on the driver's tolerance limit for continuous driving in ergonomic research, and experimental verification has shown that it balances safety and false alarm rate.

[0041] Specifically, during vehicle operation or in congested conditions, the fatigue timer 1033 continuously tracks effective driving time. When the accumulated time reaches 4 hours, the warning module 1034 immediately activates the alarm function. During this process, if the engine is detected as off, the timer automatically stops counting, ensuring that only the time spent actually in driving mode is recorded. For example, in a long-distance transport scenario, if a driver drives continuously for 3 hours and 50 minutes and then stops at a service area for a rest, the timer pauses. The alarm will only be triggered after the vehicle is restarted and the remaining 10 minutes have elapsed.

[0042] Compared to existing technologies, traditional solutions lack a dynamic timing mechanism linked to driving status, failing to eliminate interference from parking periods in fatigue assessment. For example, steering wheel monitoring solutions using fixed-interval alarms continue timing even in congested or idling conditions, leading to premature false alarms. This solution, however, combines driving status assessment with pauseable timing logic, ensuring the alarm trigger timing more closely aligns with the actual patterns of driver fatigue.

[0043] Through the above technical solution, this application can accurately distinguish between actual driving operation periods and parking waiting periods, avoiding false alarms caused by the accumulation of non-driving time. At the same time, by setting threshold parameters that conform to human tolerance limits, the frequency of false alarms in urban congestion scenarios is significantly reduced while ensuring the effectiveness of safety warnings.

[0044] This application further proposes a fatigue driving warning device based on tire pressure monitoring, referencing... Figure 1 According to one embodiment, the device includes multiple tire sensors 101 installed in the tires of two or more motor vehicles for real-time acquisition of tire acceleration data; a vibration detection module 102 installed on the vehicle chassis or receiver PCB board for detecting engine vibration signals of the motor vehicle; a tire pressure receiver 103 communicatively connected to the multiple tire sensors 101 and the vibration detection module 102, the tire pressure receiver 103 including a driving state judgment unit 1031 for analyzing the spectral characteristics of tire acceleration data; a parking state analysis unit 1032 for distinguishing whether the motor vehicle is in a parked state or a congested state by analyzing the engine vibration signal; a fatigue timer 1033 for counting the cumulative effective driving time of the motor vehicle; and an early warning module 1034 for triggering an alarm when the effective driving time of the motor vehicle exceeds a driving time threshold.

[0045] Among them, tire sensor 101 refers to a triaxial acceleration acquisition device integrated inside the tire, which can be implemented using a MEMS accelerometer. Its sampling rate can be set to, for example, 100Hz or higher, to capture vibration signals generated when the tire rotates. Vibration detection module 102 refers to a vibration sensor installed on the vehicle chassis or receiver PCB board, which can be implemented using a piezoelectric sensor, to detect mechanical vibration characteristics in engine idling or off states. Driving state judgment unit 1031 refers to a signal processing module based on spectrum analysis, which can be implemented using an embedded DSP chip to implement a Fourier transform algorithm, to extract the main frequency component of tire acceleration. Parking state analysis unit 1032 refers to a composite module including a bandpass filter and an RMS calculator, which can be implemented using a digital signal processing circuit, to distinguish between engine idling vibration and off state. Fatigue timer 1033 refers to a timer with state triggering function, which can be implemented using a programmable logic controller, to accumulate time only in driving or congested states. Warning module 1034 refers to an alarm signal output device, which can be implemented using a buzzer or vehicle display screen, to issue a warning when a preset time is reached.

[0046] Specifically, the tire sensor 101 continuously collects triaxial acceleration data and transmits it wirelessly to the tire pressure receiver 103, while the vibration detection module 102 transmits engine vibration signals to the receiver. The driving state judgment unit 1031 performs spectrum analysis on the tire acceleration data, for example, by extracting the dominant frequency component in the 5-50Hz frequency band through fast Fourier transform. When the dominant frequency is detected to be continuously exceeding 5Hz and the amplitude is greater than 0.2g, the vehicle is determined to be in a driving state. The parking state analysis unit 1032 performs bandpass filtering and RMS value calculation on the engine vibration signal. When the vibration RMS value is continuously exceeding 0.1g for 10 seconds, it is determined to be a congested state; when the RMS value is below 0.05g, it is determined to be a stopped state. The fatigue timer 1033 continuously accumulates time in driving or congested states, and pauses the timer when the engine is stopped. When the accumulated time exceeds a preset threshold, the warning module 1034 alerts the driver through audible and visual signals.

[0047] Compared to existing technologies, traditional solutions relying on steering wheel sensors cannot detect subtle tire movements at idle speeds. This device, however, utilizes a high-precision accelerometer from the TPMS system, combined with a dual verification mechanism based on engine vibration signals, to accurately distinguish between driving, congested, and stationary states. Existing facial recognition solutions fail when lighting changes or when the driver is wearing sunglasses, while this device, based on objective monitoring of the vehicle's physical state, avoids environmental interference. Furthermore, by integrating existing hardware resources from the tire pressure monitoring system, the need for additional sensors is reduced.

[0048] Through the above technical solution, this application effectively solves the problem of high false alarm rate in steering wheel monitoring schemes under idling conditions, such as accurately identifying the actual driving state of the vehicle in urban congestion scenarios. By reusing the acceleration sensor resources of the TPMS system, hardware utilization is improved. At the same time, by utilizing the cross-verification mechanism of engine vibration signals and tire vibrations, the accuracy of parking state recognition is improved to the point that it can distinguish between engine shutdown and idling conditions. The final warning device reduces system complexity and false alarm rate while ensuring monitoring accuracy.

[0049] This application further proposes that the driving state judgment unit 1031 is configured to perform Fourier transform on the tire acceleration data to extract the 5-50Hz main frequency component. When the main frequency is continuously greater than 5Hz and the amplitude is greater than 0.2g, the vehicle is determined to be in a driving state. Fourier transform is an analytical method that converts a time-domain signal into a frequency-domain signal. Specifically, it can be implemented using the Fast Fourier Transform algorithm to separate the vibration frequency components related to driving from tire acceleration data.

[0050] The dominant frequency component refers to the frequency band with the most concentrated energy in the signal spectrum. It can be identified through a spectrum peak detection algorithm and is used to characterize the periodic vibration characteristics of the tire due to ground contact during driving.

[0051] Amplitude refers to the magnitude of the vibration signal in the time or frequency domain. It can be quantified by the spectrum amplitude calculation module and used to determine whether the tire vibration intensity has reached the threshold for driving conditions. Specifically, the driving state determination unit 1031 converts tire acceleration data into a frequency domain signal using Fourier transform and extracts the dominant frequency component within the 5-50Hz range. When the dominant frequency component is detected to continuously exceed 5Hz and the corresponding amplitude exceeds 0.2g, it indicates that the tire is in a rolling state with continuous contact with the ground, thus determining that the vehicle is in motion. For example, in scenarios such as vehicle idling or traffic jams, the tire may still generate low-frequency vibrations due to small displacements, but by limiting the range of the dominant frequency component and the amplitude threshold, the actual driving state can be effectively distinguished from other non-driving states. Compared to existing technologies, traditional solutions rely on steering wheel sensors or driver behavior recognition, failing to capture subtle tire movements. This solution, however, analyzes tire acceleration spectrum characteristics to directly correlate with the vehicle's physical state. For example, existing technologies may misjudge situations at idle due to the lack of steering input, while this solution detects the dominant frequency component of tire vibration, identifying subtle tire movements present even at idle and thus avoiding missed detections. Through the above technical solution, this application solves the problem of high misjudgment rate of traditional monitoring methods in idling or congested scenarios. By using dual criteria of spectrum analysis and vibration intensity, it accurately distinguishes between driving and non-driving states, providing a reliable time accumulation benchmark for fatigue driving warning.

[0052] This application further proposes a parking status analysis unit 1032, including a vibration signal bandpass filter 1032210322 and an RMS calculation module 10344; the vibration signal bandpass filter 1032210322 is configured to determine whether the vibration RMS value is 0.1g and lasts for 10 seconds or more, and if so, it is determined that the motor vehicle is in a congested state; the RMS calculation module 10344 is configured to determine whether the vibration RMS is 0.05g, and if so, it is determined that the motor vehicle is in a turned-off parking state. The vibration signal bandpass filter 10322 refers to an electronic circuit used to extract specific frequency band components from the engine vibration signal. Specifically, it can be implemented using a second-order active filter, and its cutoff frequency range can be set to cover typical vibration frequencies during engine idling and operation. This filter retains effective vibration signal components by suppressing high-frequency noise and low-frequency interference.

[0053] The RMS calculation module 10344 is a processing unit used to calculate the root mean square value of the vibration signal. Specifically, it can be implemented using an integral algorithm in a digital signal processor. It reflects the vibration intensity by calculating the square root of the average square of the signal within a fixed time window. This module provides a basis for state judgment by quantifying the vibration energy level. Specifically, the vibration signal bandpass filter 10322 preprocesses the engine vibration signal, filtering out interference signals unrelated to engine operation. The filtered signal is then input to the RMS calculation module 10344, which calculates the root mean square value of the vibration intensity in real time. When the RMS value continuously exceeds a set threshold, for example, reaching 0.1g and remaining there for more than 10 seconds, it indicates that the engine is idling, corresponding to a traffic jam. When the RMS value is below 0.05g, it indicates that the engine has stopped working, corresponding to a stopped vehicle. This solution achieves accurate differentiation between stopped and traffic jam states by processing the vibration signal in stages and combining it with a dual-threshold judgment mechanism. In some specific implementations, the passband range of the vibration signal bandpass filter 10322 can be set to 5-200Hz to cover the vibration characteristic frequencies at different engine speeds; the time window length of the RMS calculation module 10344 can be set to 10 seconds to balance response speed and anti-transient interference capability. Compared to existing technologies, traditional solutions rely on a single sensor or fail to perform joint frequency and energy analysis of vibration signals, making it impossible to distinguish between idling and stationary states. This solution eliminates the influence of environmental noise through bandpass filtering and combines it with dynamic monitoring of RMS values ​​to accurately identify changes in engine operating status, avoiding misjudgments caused by tire micro-movements or environmental vibrations. Through the above technical solution, this application effectively solves the problem of high misjudgment rate of traditional monitoring systems in idling state. By accurately distinguishing between parking and congestion states, it ensures the accuracy of cumulative driving time statistics, thereby reducing the probability of false triggering of fatigue driving warnings.

[0054] This application further proposes a computer-readable storage medium storing program instructions. When the instructions are executed by a processor, they enable the following actions: real-time acquisition of tire acceleration data of a motor vehicle via multiple tire sensors 101; detection of engine vibration signals of the motor vehicle via a vibration detection module 102; receipt of tire acceleration data and vibration signals of the motor vehicle via a tire pressure receiver 103; analysis of the spectral characteristics of the tire acceleration data and the engine vibration signals to determine whether the motor vehicle is in a parked or congested state; calculation of the cumulative effective driving time of the motor vehicle; and triggering an alarm when the cumulative effective driving time exceeds a driving time threshold. Computer-readable storage media refers to the physical carrier used to store executable code, which can be implemented using solid-state drives (SSDs) or embedded flash memory chips, and is used for persistent storage of program instructions. Program instructions are a set of machine code that can be parsed and executed by a processor, and can exist in the form of compiled binary files, used to control the processor to process sensor data according to preset logic. Processor execution refers to the behavior of reading and running instructions one by one through the central processing unit (CPU), which can be implemented using automotive-grade microcontrollers to complete the entire process control of data acquisition, status judgment, and alarm triggering. Specifically, the program instructions stored in the storage medium, after being loaded into the processor, control the vehicle system to perform real-time acquisition of tire acceleration data. This data is acquired through a triaxial accelerometer at a sampling rate of no less than 100Hz. The program instructions further control the Fourier transform processing of the acceleration data to extract the dominant frequency component in the 5-50Hz frequency band. When the dominant frequency component is detected to continuously exceed 5Hz and the amplitude exceeds 0.2g, a driving status marker is generated. Simultaneously, the program instructions control the analysis of the RMS value of the engine vibration signal. When this value is above 0.1g for 10 seconds, it is marked as a congested state; when it is below 0.05g, it is marked as an engine shutdown state. The effective driving time statistics module only accumulates time in driving and congested states. When the time exceeds a preset threshold, an audible and visual alarm device is triggered. Compared to existing technologies, traditional solutions rely on steering wheel sensors or facial recognition technology, which cannot accurately identify vehicle status at idle, resulting in a high false alarm rate. This solution reuses the high-precision acceleration sensor already present in the tire pressure monitoring system, combined with a dual verification mechanism of engine vibration signals, to accurately distinguish whether the vehicle is in motion, in traffic jams, or parked. The underutilized TPMS sensor resources in existing technologies become the core data source in this solution, avoiding additional hardware costs. Through the above technical solution, this application effectively solves the technical defect of misjudging driving status when the vehicle is stationary, and achieves accurate identification of driving status by utilizing existing sensor resources. The programmed data processing flow ensures that effective driving time statistics are only performed during actual driving, avoiding premature or delayed alarms caused by misjudgments in traditional solutions. The judgment mechanism based on the fusion of spectrum analysis and vibration signals significantly improves the reliability of status identification under complex road conditions.

[0055] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A fatigue driving early warning method based on tire pressure monitoring, characterized in that, Includes the following steps: The vehicle's tire acceleration data is collected in real time using multiple tire sensors; The vibration signal of the motor vehicle's engine is detected by a vibration detection module; The tire acceleration data and the vibration signal of the vehicle are received by the tire pressure receiver; By analyzing the spectral characteristics of the tire acceleration data and the engine vibration signal, it can be determined whether the vehicle is in a parked or congested state. Statistical analysis of the cumulative effective driving time of motor vehicles; and An alarm is triggered when the cumulative effective driving time of a motor vehicle exceeds the driving time threshold.

2. The method according to claim 1, characterized in that, The spectral characteristics of the tire acceleration data were analyzed, including: The tire acceleration data were subjected to Fourier transform to extract the 5-50Hz main frequency component; When the main frequency is consistently >5Hz and the amplitude is >0.2g, the vehicle is determined to be in motion.

3. The method according to claim 1, characterized in that, The analysis of the engine vibration signal includes: When the engine vibration RMS value is >0.1g and lasts for 10 seconds or more, the vehicle is determined to be in a congested state; when the engine vibration RMS value is <0.05g, the vehicle is determined to be in a stopped state with the engine off.

4. The method according to claim 1, characterized in that, The cumulative effective driving time of the motor vehicles mentioned in the statistics includes: The system tracks the duration of time a vehicle is in motion or in congestion; however, it pauses the tracking when the vehicle is stationary and its engine is off.

5. The method according to claim 1, characterized in that, The real-time acquisition of vehicle tire acceleration data through multiple tire sensors includes: acquiring triaxial acceleration data through the tire sensors, with a sampling rate ≥100Hz.

6. The method according to claim 1, characterized in that, The driving time threshold is 4 hours.

7. A fatigue driving warning device based on tire pressure monitoring, characterized in that, include: Multiple tire sensors (101) are installed in the tires of two-wheeled or more motor vehicles to collect tire acceleration data of the motor vehicles in real time. Vibration detection module (102), installed on vehicle chassis or receiver PCB board, is used to detect engine vibration signals of motor vehicles; A tire pressure receiver (103) is communicatively connected to the plurality of tire sensors (101) and the vibration detection module (102), the tire pressure receiver (103) comprising: The driving state determination unit (1031) is used to analyze the spectral characteristics of the tire acceleration data; The parking status analysis unit (1032) is used to distinguish whether the motor vehicle is in a parking state or a congested state by analyzing the engine vibration signal. A fatigue timer (1033) is used to count the cumulative effective driving time of a motor vehicle; and The early warning module (1034) is used to trigger an alarm when the cumulative effective driving time of a motor vehicle exceeds the driving time threshold.

8. The apparatus according to claim 7, characterized in that, The driving state determination unit (1031) is configured to: perform Fourier transform on the tire acceleration data to extract the 5-50Hz main frequency component; when the main frequency is continuously >5Hz and the amplitude is >0.2g, it is determined that the motor vehicle is in a driving state.

9. The apparatus according to claim 7, characterized in that, The parking status analysis unit (1032) includes: a vibration signal bandpass filter and an RMS calculation module; the vibration signal bandpass filter is set to determine whether the vibration RMS value is 0.1g and lasts for 10 seconds or more, and if so, it is determined that the motor vehicle is in a congested state; the RMS calculation module is set to determine whether the vibration RMS is 0.05g, and if so, it is determined that the motor vehicle is in a turned-off parking state.

10. A computer-readable storage medium storing program instructions, characterized in that, When the instructions are executed by the processor, they implement the steps of the method according to any one of claims 1-6.

Images