Danger alarm method and device for rail transit and rail vehicle

Abstract

The invention relates to the technical field of rail transit, in particular to a danger alarm method and device for rail transit and a rail vehicle, and the method comprises the steps: obtaining the heartbeat sound of a driver in the vehicle driving process in real time; the heartbeat sound is input into a preset self-adaptive filter to be processed, a heartbeat signal output by the self-adaptive filter is obtained, and the coefficient of the self-adaptive filter is adjusted by minimizing the mean square error between an input signal and an expected signal; feature extraction is carried out on the heartbeat signal, the driving state of the driver is evaluated based on a feature extraction result, and the driving state comprises dangerous driving and normal driving; and under the condition that the evaluation result of the driving state is dangerous driving, alarm information is sent out, and the alarm information comprises the identification and position information of the vehicle. According to the invention, dangerous events can be detected in real time, and an alarm is automatically sent, so that the safety of rail transit is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of rail transit, and in particular to a danger alarm method, device and rail vehicle for rail transit. Background Art

[0002] Currently, most driver health monitoring systems rely on wearable devices, such as heart rate monitoring watches or health tracking bands. Although these devices can provide accurate physiological data, there is a possibility that users forget to wear them and they may cause discomfort to the driver.

[0003] Some high-end vehicles already integrate biosensors in seats or steering wheels to monitor the driver's heart rate and other physiological indicators. However, these technologies are usually expensive and need to be integrated during vehicle manufacturing. Summary of the invention

[0004] The present invention provides a danger alarm method, device and rail vehicle for rail transit, so as to solve the defects of the prior art that the danger detection system has high cost and needs to be integrated during vehicle manufacturing, and captures the heartbeat sound in a contactless manner to reduce the invasiveness and cost of the system.

[0005] The present invention provides a danger alarm method for rail transit, comprising the following steps: Real-time acquisition of the driver's heartbeat sound during vehicle driving; Inputting the heartbeat sound into a preset adaptive filter for processing to obtain a heartbeat signal output by the adaptive filter, wherein the coefficient of the adaptive filter is adjusted by minimizing the mean square error between the input signal and the expected signal; Extracting features from the heartbeat signal, and evaluating the driver's driving state based on the feature extraction result, wherein the driving state includes dangerous driving and normal driving; When the evaluation result of the driving state is dangerous driving, an alarm message is issued, and the alarm message includes the identification and location information of the vehicle.

[0006] According to the danger alarm method for rail transit provided by the present invention, the step of obtaining the heartbeat sound of the driver in real time during vehicle driving specifically includes: A high-sensitivity directional microphone is deployed near the chest on the back of the seat to capture the driver's heartbeat sound; the output data format of the directional microphone is a dual-channel 16-bit digital audio signal with a sampling frequency of 44.1Khz.

[0007] According to the danger alarm method for rail transit provided by the present invention, before the heartbeat sound is input into a preset adaptive filter for processing, the method further includes: The heartbeat sound is preprocessed using a bandpass filter to remove signals that are not within the heartbeat frequency range.

[0008] According to the danger alarm method for rail transit provided by the present invention, the adaptive filter uses a minimum mean square algorithm to process the heartbeat sound, wherein the iterative update formula of the minimum mean square algorithm is: , Where w(n) is the filter weight vector at the nth step; μ is the learning rate, which is used to control the convergence speed and stability of the algorithm; e(n) is the error signal at the nth step, , where d(n) is the desired signal, y(n) is the output of the filter, and x(n) is the input signal.

[0009] According to the danger alarm method for rail transit provided by the present invention, the expected signal is obtained by simulating the periodic fluctuation of the heart, which specifically includes: The key wavebands of the heartbeat signal are set to be P wave, QRS complex wave, T wave and U wave, wherein the P wave represents atrial contraction, the QRS complex wave represents ventricular contraction, the T wave represents ventricular recovery, and the U wave represents a waveband related to the post-recovery process of the ventricle; The Gaussian function is used to simulate the QRS complex wave of the heartbeat signal. The calculation formula is: , Where A is the amplitude, μ is the center position of the Gaussian function, and σ is used to control the width of the waveform; The Gaussian function is combined with a P-wave simulation function and a T-wave simulation function to generate a desired signal s(t): , in, , , They represent P wave, QRS complex and T wave respectively.

[0010] According to the danger alarm method for rail transit provided by the present invention, the P-wave simulation function and the T-wave simulation function adopt a Gaussian function or a sine wave with a smaller amplitude.

[0011] According to the danger alarm method for rail transit provided by the present invention, the step of extracting features from the heartbeat signal specifically includes: Extracting features from the heartbeat signal to identify characteristic peaks of the heartbeat signal; Calculating the interval time of each heartbeat based on the characteristic peak of the heartbeat signal; Based on the heartbeat intervals, an average heart rate is calculated.

[0012] According to the danger alarm method for rail transit provided by the present invention, the step of evaluating the driving state of the driver based on the feature extraction result specifically includes: Based on the calculated interval time of each heartbeat, performing heart rate variability analysis on the heartbeat signal; Comparing the result of the heart rate variability analysis and the average heart rate with a preset heart rate threshold and HRV threshold range, and evaluating the driving state of the driver according to the comparison result; Among them, the indicators of heart rate variability analysis include standard deviation SDNN, root mean square deviation RMSSD, NN50, pNN 50 and LF / HF ratio.

[0013] The present invention also provides a danger alarm device for rail transit, comprising the following modules: An acquisition module is used to acquire the driver's heartbeat sound in real time during vehicle driving; A filtering module, used for inputting the heartbeat sound into a preset adaptive filter for processing, and obtaining a heartbeat signal output by the adaptive filter, wherein the coefficient of the adaptive filter is adjusted by minimizing the mean square error between the input signal and the expected signal; A feature extraction module, used to extract features from the heartbeat signal, and based on the feature extraction result, evaluate the driver's driving state, wherein the driving state includes dangerous driving and normal driving; The alarm module is used to issue an alarm message when the evaluation result of the driving state is dangerous driving, and the alarm message includes the identification and location information of the vehicle.

[0014] The present invention also provides a rail vehicle, comprising the danger alarm device for rail transportation as described above.

[0015] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the danger alarm method for rail transit as described in any one of the above is implemented.

[0016] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the danger alarm method for rail transit as described in any one of the above is implemented.

[0017] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned danger alarm methods for rail transit.

[0018] The danger alarm method, device and rail vehicle for rail transit provided by the present invention obtain the heartbeat sound of the driver in real time during the driving of the vehicle; input the heartbeat sound into a preset adaptive filter for processing to obtain a heartbeat signal output by the adaptive filter; extract features from the heartbeat signal, and evaluate the driving state of the driver based on the feature extraction result; and send an alarm message when the evaluation result of the driving state is dangerous driving; the present invention prevents potential accidents caused by health problems or emotional problems. Once a potential accident is detected, it will immediately send an alarm message to the alarm platform, including vehicle identification and location information, detect dangerous events in real time, and automatically send an alarm, thereby improving the safety of rail transit. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 This is one of the flow charts of the danger alarm method for rail transit provided by the present invention.

[0021] Figure 2 This is the second flow chart of the danger alarm method for rail transit provided by the present invention.

[0022] Figure 3 It is a schematic structural diagram of a danger alarm device for rail transit provided by the present invention.

[0023] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] The present invention is described in detail below in conjunction with the accompanying drawings of the specification. The specific operating method in the method embodiment can also be applied to the device embodiment or the system embodiment. In the description of the present invention, unless otherwise specified, "at least one" includes one or more. "Multiple" refers to two or more. For example, at least one of A, B and C includes: A exists alone, B exists alone, A and B exist at the same time, A and C exist at the same time, B and C exist at the same time, and A, B and C exist at the same time. In the present invention, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a kind of association relationship that describes the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0026] The present invention will be described in detail below in conjunction with specific implementation modes.

[0027] In some specific embodiments of the present invention, Figure 1 As shown, the present invention provides a danger alarm method for rail transit, comprising: Step 100: Acquire the driver's heartbeat sound in real time during vehicle driving; Step 200: input the heartbeat sound into a preset adaptive filter for processing, and obtain a heartbeat signal output by the adaptive filter, wherein the coefficient of the adaptive filter is adjusted by minimizing the mean square error between the input signal and the expected signal; Step 300: extracting features from the heartbeat signal, and evaluating the driver's driving state based on the feature extraction result, wherein the driving state includes dangerous driving and normal driving; Step 400: When the driving state is evaluated as dangerous driving, an alarm message is issued, wherein the alarm message includes the identification and location information of the vehicle.

[0028] It should be noted that the existing hazard alarm solutions cannot avoid the system’s intrusiveness or high cost when detecting hazards, and the detection results are unreliable and cannot meet the safety requirements of rail transit.

[0029] Therefore, the present invention obtains the heartbeat sound of the driver during vehicle driving, processes the heartbeat sound, evaluates the driver's driving status based on the feature extraction result of the obtained heartbeat signal, and issues an alarm message when the driving status is dangerous, thereby improving the safety of rail transit.

[0030] In some possible implementations of the present invention, the step of acquiring the heartbeat sound of the driver in real time during vehicle driving specifically includes: A high-sensitivity directional microphone is deployed near the chest on the back of the seat to capture the driver's heartbeat sound; the output data format of the directional microphone is a dual-channel 16-bit digital audio signal with a sampling frequency of 44.1Khz.

[0031] Specifically, this embodiment provides an implementation method for acquiring the heartbeat sound of the driver in real time during vehicle driving, by selecting a high-sensitivity directional microphone to optimize the capture effect of the heartbeat sound and reduce the interference of background noise.

[0032] In a possible embodiment, the user deploys the microphone close to the user's heart, on the back of the seat close to the chest, so as to better capture the sound of the heartbeat; and sets the output format to a dual-channel 16-bit digital audio signal with a sampling frequency of 44.1Khz to optimize the capture of the heartbeat sound and reduce the interference of background noise.

[0033] In some possible implementations of the present invention, before inputting the heartbeat sound into a preset adaptive filter for processing, the method further includes: The heartbeat sound is preprocessed using a bandpass filter to remove signals that are not within the heartbeat frequency range.

[0034] Specifically, this embodiment provides an implementation method for preprocessing heartbeat sounds, in which the acquired heartbeat signal is preprocessed by a bandpass filter to remove signals that are not within the heartbeat frequency range.

[0035] In a possible embodiment, the user uses a bandpass filter to remove signals that are not within the heartbeat frequency range, such as low-frequency rumbles and high-frequency squeals.

[0036] Furthermore, a bandpass filter is implemented to process a dual-channel 16-bit digital audio signal with a sampling frequency of 44.1 kHz to extract the heartbeat frequency (usually between 20 Hz and 200 Hz). A second-order IIR (Infinite Impulse Response) bandpass filter can be used. In digital signal processing, this filter is widely used because of its high efficiency and ease of implementation. For a second-order bandpass IIR filter, the core parameter is the center frequency f 0 And bandwidth Δf. For the heartbeat sound, the center frequency can be taken as 110 Hz and the frequency range is 20 Hz~200 Hz, that is, f 0 =110 Hz and Δf=180 Hz.

[0037] In some possible implementations of the present invention, the adaptive filter uses a minimum mean square algorithm to process the heartbeat sound, wherein the iterative update formula of the minimum mean square algorithm is: (1) Where w(n) is the filter weight vector at the nth step; μ is the learning rate, which is used to control the convergence speed and stability of the algorithm; e(n) is the error signal at the nth step, , where d(n) is the desired signal, y(n) is the output of the filter, and x(n) is the input signal.

[0038] Specifically, this embodiment provides an implementation method of an adaptive filter, which implements the filtering function of the adaptive filter by adopting a least mean square algorithm and setting an iterative update formula of the least mean square algorithm.

[0039] In a possible embodiment, after the acquired heartbeat signal is preprocessed, it is necessary to further perform noise suppression on the preprocessed heartbeat signal.

[0040] In a possible embodiment, dynamic noise suppression technology, such as an adaptive filter, may be applied to further remove background noise and preserve the heartbeat signal.

[0041] Specifically, an adaptive filter is used to further remove background noise and retain the heartbeat signal. The method used is to use the LMS (least mean square) algorithm. The LMS algorithm is a simple and effective adaptive filtering method that is widely used in noise elimination and echo suppression. The LMS algorithm adjusts the filter coefficients by minimizing the mean square error between the input signal and the expected signal. Its iterative update formula is: Where: w(n) is the filter weight vector at the nth step; μ is the learning rate, which controls the convergence speed and stability of the algorithm; e(n) is the error signal at the nth moment, calculated as , where d(n) is the desired signal, y(n) is the output of the filter; x(n) is the input signal.

[0042] In some possible implementations of the present invention, the desired signal is obtained by simulating the periodic fluctuation of the heart, specifically including: The key wavebands of the heartbeat signal are set to be P wave, QRS complex wave, T wave and U wave, wherein the P wave represents atrial contraction, the QRS complex wave represents ventricular contraction, the T wave represents ventricular recovery, and the U wave represents a waveband related to the post-recovery process of the ventricle; The Gaussian function is used to simulate the QRS complex wave of the heartbeat signal. The calculation formula is: Where A is the amplitude, μ is the center position of the Gaussian function, and σ is used to control the width of the waveform; The Gaussian function is combined with a P-wave simulation function and a T-wave simulation function to generate a desired signal s(t): in, , , They represent P wave, QRS complex and T wave respectively.

[0043] Specifically, this embodiment provides an implementation method for obtaining a desired signal by simulating the periodic fluctuation of the heart, and generates a synthetic heartbeat signal by simulating the periodic fluctuation of the heart.

[0044] In a possible embodiment, since the real heartbeat signal is difficult to measure directly, this embodiment adopts constructing a mathematical model to generate a synthetic heartbeat signal, that is, the expected signal d(n) of the above-mentioned adaptive filter. How to generate the expected signal is the key point of the present invention.

[0045] Specifically, building a mathematical model to generate a synthetic heartbeat signal requires a deep understanding of the physiological characteristics of the heartbeat and converting this knowledge into a form that can be described mathematically. The model of the heartbeat signal can be based on the periodic fluctuations of the heart, which reflect the basic characteristics of heart activity. The following is a detailed description of the implementation steps: The heartbeat signal is mainly generated by the contraction and relaxation of the heart, and its waveform is called an electrocardiogram (ECG) signal, which includes several key bands: P wave, QRS complex wave, T wave and U wave. These bands reflect different stages of cardiac electrophysiological activity: P wave: indicates atrial contraction.

[0046] QRS complex: indicates ventricular contraction.

[0047] T wave: indicates ventricular recovery.

[0048] U wave (uncommon): usually associated with the post-ventricular recovery process.

[0049] Based on the above embodiment, due to the characteristics of the rapid rise and fall of the QRS complex wave, a Gaussian function can be used to simulate the QRS complex wave of the heartbeat, and the model can be expressed as: (2) Where A is the amplitude, μ is the center position of the Gaussian function, and σ controls the width of the waveform.

[0050] The above Gaussian function is combined with other functions that simulate P and T waves to generate a complete heartbeat signal.

[0051] In some possible implementations of the present invention, the P-wave simulation function and the T-wave simulation function use a Gaussian function or a sine wave with a smaller amplitude.

[0052] Specifically, the P wave simulation function and the T wave simulation function use, for example, a Gaussian function or a sine wave with a relatively small amplitude. On this basis, the simulation of the desired signal can be achieved by superimposing functions of different bands: (3) in, , , They represent P wave, QRS complex and T wave respectively.

[0053] In some possible implementations of the present invention, the step of extracting features from the heartbeat signal specifically includes: Extracting features from the heartbeat signal to identify characteristic peaks of the heartbeat signal; Calculating the interval time of each heartbeat based on the characteristic peak of the heartbeat signal; Based on the heartbeat intervals, an average heart rate is calculated.

[0054] Specifically, this embodiment provides an implementation method for extracting features from a heartbeat signal, by extracting features from the heartbeat signal output by an adaptive filter to calculate the heartbeat interval and average heart rate.

[0055] In a possible embodiment, feature extraction of heartbeat signals includes heartbeat recognition and heart rate calculation. For heartbeat recognition, characteristic peaks of the heartbeat are identified through an algorithm, and the interval time of each heartbeat is calculated; for heart rate calculation, the average heart rate is calculated based on the heartbeat interval.

[0056] In some possible implementations of the present invention, the step of evaluating the driver's driving state based on the feature extraction result specifically includes: Based on the calculated interval time of each heartbeat, performing heart rate variability analysis on the heartbeat signal; Comparing the result of the heart rate variability analysis and the average heart rate with a preset heart rate threshold and HRV threshold range, and evaluating the driving state of the driver according to the comparison result; Among them, the indicators of heart rate variability analysis include standard deviation SDNN, root mean square deviation RMSSD, NN50, pNN50 and LF / HF ratio.

[0057] Specifically, this embodiment provides an implementation method for evaluating the driver's driving status based on feature extraction results, and analyzes the variation of heartbeat intervals based on the feature extraction results, thereby providing data support for the driver's driving status evaluation.

[0058] In a possible embodiment, the evaluation of the driver's driving state can be understood as the health evaluation of the driver during the driving of the vehicle. Heart rate variability analysis HRV is an important indicator for evaluating the activity of the autonomic nervous system and is closely related to stress level and heart health. HRV analyzes the variation of heartbeat intervals and evaluates the driver's health status through indicators such as standard deviation SDNN, root mean square deviation RMSSD, NN50, pNN 50 and LF / HF ratio.

[0059] Specifically, SDNN (standard deviation) is used to describe the standard deviation of all normal heartbeat intervals (NN intervals). The specific formula is: (4) in, is the ith heartbeat interval, is the average of the heartbeat intervals, and N is the total number of heartbeat intervals.

[0060] RMSSD (root mean square deviation) is used to describe the root mean square of the difference between consecutive heartbeat intervals, which mainly reflects the parasympathetic nerve activity. The calculation formula is: (5) NN50 is used to indicate the number of times the difference between adjacent heartbeat intervals exceeds 50 milliseconds, and pNN50 is used to indicate the ratio of NN50 to the total number of heartbeat intervals. The calculation formula is: (6) The LF / HF ratio is used to express the ratio of LF and HF power values ​​and is used to assess the balance of the sympathetic and parasympathetic nervous systems. The calculation formula is: (7) Furthermore, normal ranges for heart rate and HRV are set, and any abnormal heart rate pattern, such as a heart rate that is too fast, too slow, or irregular, is detected and alerted to achieve abnormality detection.

[0061] Specifically, SDNN reflects the fluctuation of all heartbeat intervals and is an indicator of the overall cardiac autonomic nervous system activity. This indicator is used to evaluate the driver's status: a lower SDNN value may indicate lower cardiac variability, which is usually associated with high stress, fatigue or poor heart health; a persistently low SDNN may indicate that the driver is unfit to drive.

[0062] RMSSD mainly reflects parasympathetic nerve activity and is an indicator of short-term heart rate variability. This indicator is used to evaluate the driver's status: a lower RMSSD indicates a decrease in parasympathetic nerve activity, which is common in stress states. This may indicate that the driver is experiencing stress, and if this state persists, driving safety may be affected.

[0063] The LF / HF ratio is considered an indicator of the balance between the sympathetic and parasympathetic nervous systems. This indicator is used to assess the driver's status: a higher LF / HF ratio is usually associated with increased sympathetic nerve activity and may indicate that the driver is under stress or tension. A persistently high ratio may increase cardiovascular risk, and drivers are advised to avoid driving for long periods of time or working in a high-stress environment.

[0064] pNN50 is a measure of the percentage of heartbeat intervals that vary by more than 50 milliseconds, reflecting an aspect of heart rate variability. This indicator is used to assess the driver's status: a lower pNN50 value may indicate reduced heart rate variability, which may be related to high stress, fatigue or poor heart health. Monitoring pNN50 can help identify situations where a break may be needed or when it is not appropriate to continue driving.

[0065] By using the above-mentioned HRV indicators, the embodiments of the present invention can provide real-time, non-invasive feedback on the driver's psychological and physiological state; by continuously monitoring these indicators, the driver's possible health problems or high stress levels can be identified in a timely manner, so that appropriate measures can be taken to avoid potential safety risks.

[0066] In a possible embodiment, the user can provide real-time feedback on the above detection data through the user interface, such as displaying important indicators such as real-time heart rate and HRV through a real-time monitoring interface; or provide health reports and suggestions, provide regular health reports, and give lifestyle or medical advice based on the monitoring data.

[0067] In some possible embodiments of the present invention, Figure 2 As shown, the danger alarm method for rail transit provided by the present invention can be divided into the following steps: Step 201: sound capture; In this step, a high-sensitivity directional microphone can be selected to optimize the capture of heartbeat sounds and reduce interference from background noise; the microphone can be deployed close to the user's heart, on the back of the seat close to the chest, to better capture the heartbeat sound.

[0068] Preferably, the output format of the microphone can be set to a dual-channel 16-bit digital audio signal with a sampling frequency of 44.1Khz.

[0069] Step 202: signal processing; In this step, a bandpass filter may be used to pre-process the heartbeat sound signal to remove signals that are not within the heartbeat frequency range, such as low-frequency rumbling sounds and high-frequency sharp sounds.

[0070] Furthermore, dynamic noise suppression technology, such as an adaptive filter, may be applied to perform noise suppression on the processed heartbeat sound signal to further remove background noise and retain the heartbeat signal.

[0071] Through the above settings of this step, an accurate heartbeat signal can be obtained, thereby providing reliable and accurate data support for subsequent health assessment.

[0072] Step 203: feature extraction; In this step, based on the heartbeat signal output in step 202, the characteristic peaks of the heartbeat are identified through an algorithm, and the interval time of each heartbeat is calculated, so as to realize heartbeat recognition; and the average heart rate is calculated according to the heartbeat interval to realize the heart rate calculation process.

[0073] Step 204: health assessment; In this step, the variation of heartbeat intervals is analyzed by performing heart rate variability analysis HRV to characterize the activity of the autonomic nervous system, thereby evaluating the driver's stress level and heart health status. By using these HRV indicators, this embodiment can provide real-time, non-invasive feedback on the driver's psychological and physiological state. By continuously monitoring these indicators, possible health problems or high stress levels of the driver can be identified in a timely manner, so that appropriate measures can be taken to avoid potential safety risks.

[0074] Step 205: User interface and feedback.

[0075] In this step, the real-time monitoring interface can display important indicators such as real-time heart rate and HRV. On this basis, health reports and suggestions can be further provided, such as providing regular health reports and giving lifestyle or medical advice based on monitoring data.

[0076] The danger alarm method for rail transit provided by the embodiment of the present invention, through reasonable configuration and layout of the microphone, and provides a method specifically for processing and analyzing heartbeat sound signals, the driver's heartbeat sound is captured in real time, and the driver's health and emotions are accurately evaluated based on the heartbeat data. The present invention uses a microphone system to monitor the driver's heartbeat sound in real time, and evaluates the driver's health and emotional state by analyzing the heartbeat data, aiming to improve road safety by preventing potential accidents caused by health problems or emotional problems. Once a potential accident is detected, an alarm message will be immediately sent to the alarm platform, including vehicle identification and location information. The above-mentioned settings of the present invention can detect dangerous events in real time and automatically send alarms, thereby improving the safety of rail transit.

[0077] In some specific embodiments of the present invention, the present scheme provides a danger alarm device for rail transit. The danger alarm device for rail transit provided by the present invention is described below. The danger alarm device for rail transit described below and the danger alarm method for rail transit described above can be referenced to each other.

[0078] Figure 3 Schematic diagram of the structure of the danger alarm device for rail transit provided by the present invention. Figure 3 As shown, the device comprises: An acquisition module 31 is used to acquire the heartbeat sound of the driver in real time during the driving of the vehicle; A filtering module 32, configured to input the heartbeat sound into a preset adaptive filter for processing, and obtain a heartbeat signal output by the adaptive filter, wherein the coefficient of the adaptive filter is adjusted by minimizing the mean square error between the input signal and the expected signal; A feature extraction module 33 is used to extract features from the heartbeat signal and evaluate the driver's driving state based on the feature extraction result, wherein the driving state includes fatigue driving and normal driving; The alarm module 34 is used to issue an alarm message when the evaluation result of the driving state is fatigue driving, and the alarm message includes the identification and location information of the vehicle.

[0079] The implementation principle and beneficial effects of the danger alarm device for rail transit provided in the embodiment of the present invention are similar to the implementation principle and beneficial effects of the danger alarm method for rail transit shown in the above embodiment. Please refer to the implementation principle and beneficial effects of the danger alarm method for rail transit shown in the above embodiment, and no further details will be given here.

[0080] In some specific embodiments of the present invention, a rail vehicle is further provided, wherein the rail vehicle comprises the danger alarm device for rail transit as described in the above embodiment.

[0081] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the danger alarm method for rail transit, the method comprising: obtaining the heartbeat sound of the driver in real time during the vehicle driving process; inputting the heartbeat sound into a preset adaptive filter for processing to obtain a heartbeat signal output by the adaptive filter, wherein the coefficient of the adaptive filter is adjusted by minimizing the mean square error between the input signal and the expected signal; extracting features from the heartbeat signal, and based on the feature extraction result, evaluating the driving state of the driver, the driving state includes fatigue driving and normal driving; in the case where the evaluation result of the driving state is fatigue driving, issuing an alarm message, the alarm message includes the identification and location information of the vehicle.

[0082] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0083] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the danger alarm method for rail transit provided by the above-mentioned methods, the method including: acquiring the heartbeat sound of the driver in real time during vehicle driving; inputting the heartbeat sound into a preset adaptive filter for processing to obtain a heartbeat signal output by the adaptive filter, wherein the coefficient of the adaptive filter is adjusted by minimizing the mean square error between the input signal and the expected signal; performing feature extraction on the heartbeat signal, and based on the feature extraction result, evaluating the driver's driving state, the driving state including fatigue driving and normal driving; when the evaluation result of the driving state is fatigue driving, issuing an alarm message, the alarm message including the vehicle's identification and location information.

[0084] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the danger alarm method for rail transit provided by the above-mentioned methods, the method comprising: acquiring the heartbeat sound of the driver in real time during vehicle driving; inputting the heartbeat sound into a preset adaptive filter for processing to obtain a heartbeat signal output by the adaptive filter, wherein the coefficient of the adaptive filter is adjusted by minimizing the mean square error between the input signal and the expected signal; performing feature extraction on the heartbeat signal, and based on the feature extraction result, evaluating the driving state of the driver, the driving state including fatigue driving and normal driving; when the evaluation result of the driving state is fatigue driving, issuing an alarm message, the alarm message including the identification and location information of the vehicle.

[0085] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0086] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0087] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A danger alarm method for rail transit, characterized in that: include: Real-time acquisition of the driver's heartbeat sound during vehicle driving; Inputting the heartbeat sound into a preset adaptive filter for processing to obtain a heartbeat signal output by the adaptive filter, wherein the coefficient of the adaptive filter is adjusted by minimizing the mean square error between the input signal and the expected signal; Extracting features from the heartbeat signal, and evaluating the driver's driving state based on the feature extraction result, wherein the driving state includes dangerous driving and normal driving; When the evaluation result of the driving state is dangerous driving, an alarm message is issued, and the alarm message includes the identification and location information of the vehicle.

2. The danger alarm method for rail transit according to claim 1, characterized in that: The steps of obtaining the driver's heartbeat sound in real time during vehicle driving specifically include: A high-sensitivity directional microphone is deployed near the chest on the back of the seat to capture the driver's heartbeat sound; the output data format of the directional microphone is a dual-channel 16-bit digital audio signal with a sampling frequency of 44.1Khz.

3. The danger alarm method for rail transit according to claim 2, characterized in that: Before inputting the heartbeat sound into a preset adaptive filter for processing, the method further includes: The heartbeat sound is preprocessed using a bandpass filter to remove signals that are not within the heartbeat frequency range.

4. The danger alarm method for rail transit according to any one of claims 1 to 3, characterized in that: The adaptive filter uses a minimum mean square algorithm to process the heartbeat sound, wherein the iterative update formula of the minimum mean square algorithm is: ， Where w(n) is the filter weight vector at the nth step; μ is the learning rate, which is used to control the convergence speed and stability of the algorithm; e(n) is the error signal at the nth step, , where d(n) is the desired signal, y(n) is the output of the filter, and x(n) is the input signal.

5. The danger alarm method for rail transit according to claim 4, characterized in that: The desired signal is obtained by simulating the periodic fluctuation of the heart, specifically including: The key wavebands of the heartbeat signal are set to be P wave, QRS complex wave, T wave and U wave, wherein the P wave represents atrial contraction, the QRS complex wave represents ventricular contraction, the T wave represents ventricular recovery, and the U wave represents a waveband related to the post-recovery process of the ventricle; The Gaussian function is used to simulate the QRS complex wave of the heartbeat signal. The calculation formula is: ， Where A is the amplitude, μ is the center position of the Gaussian function, and σ is used to control the width of the waveform; The Gaussian function is combined with a P-wave simulation function and a T-wave simulation function to generate a desired signal s(t): ， in, , , They represent P wave, QRS complex and T wave respectively.

6. The danger alarm method for rail transit according to claim 5, characterized in that: The P-wave simulation function and the T-wave simulation function use a Gaussian function or a sine wave with a smaller amplitude.

7. The danger alarm method for rail transit according to claim 5, characterized in that: The step of extracting features from the heartbeat signal specifically includes: Extracting features from the heartbeat signal to identify characteristic peaks of the heartbeat signal; Calculating the interval time of each heartbeat based on the characteristic peak of the heartbeat signal; Based on the heartbeat intervals, an average heart rate is calculated.

8. The danger alarm method for rail transit according to claim 7, characterized in that: The steps of evaluating the driver's driving state based on the feature extraction result specifically include: Based on the calculated interval time of each heartbeat, performing heart rate variability analysis on the heartbeat signal; Comparing the result of the heart rate variability analysis and the average heart rate with a preset heart rate threshold and HRV threshold range, and evaluating the driving state of the driver according to the comparison result; Among them, the indicators of heart rate variability analysis include standard deviation SDNN, root mean square deviation RMSSD, NN50, pNN 50 and LF / HF ratio.

9. A danger alarm device for rail transit, characterized in that: include: An acquisition module is used to acquire the driver's heartbeat sound in real time during vehicle driving; A filtering module, used for inputting the heartbeat sound into a preset adaptive filter for processing, and obtaining a heartbeat signal output by the adaptive filter, wherein the coefficient of the adaptive filter is adjusted by minimizing the mean square error between the input signal and the expected signal; A feature extraction module, used to extract features from the heartbeat signal, and based on the feature extraction result, evaluate the driver's driving state, wherein the driving state includes dangerous driving and normal driving; The alarm module is used to issue an alarm message when the evaluation result of the driving state is dangerous driving, and the alarm message includes the identification and location information of the vehicle.

10. A rail vehicle, characterized in that: Including the danger alarm device for rail transit as described in claim 9.

Images