Emergency train braking control system and method based on brain waves

Abstract

The invention discloses a train emergency braking control system and method based on brain waves. Electroencephalogram signals of a left frontal polar region of a driver are collected in real time to assist the driver in implementing emergency braking operation; a brain wave intelligent safety helmet integrating a brain wave module, a microprocessor and a Bluetooth module is adopted to collect driver stress brain electrical signals in a train operation scene; processing the driver stress electroencephalogram signal by adopting a wavelet decomposition method, and based on a wavelet decomposition coefficient, in combination with the characteristics of a signal time domain, a frequency domain and an entropy domain, extracting a characteristic signal that a driver decides to press an emergency braking button; an online training and cloud edge cooperation method is adopted, the system updates feature extraction parameters and classification standards used in a microprocessor according to real-time electroencephalogram signals of a driver and cloud historical data, and different users set different parameters to deal with individual differences of feature signals in stress response of the driver; and according to the characteristic signal, the decision intention of the driver is judged in real time, so that the response speed and safety of dealing with an emergency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of auxiliary train braking, and in particular to a train emergency braking control system and method based on brain waves. Background Art

[0002] As train speeds continue to increase, the train driver's ability to respond in emergency situations has become one of the key factors affecting train safety. In emergencies such as strong winds, heavy rain, heavy snow, and foreign objects intruding, train drivers need to respond quickly and take emergency braking measures to avoid accidents. However, the driver's reaction speed and judgment ability are affected by many factors such as physiological and psychological state. Especially under stress or fatigue, the reaction time to trigger the emergency brake button will increase, resulting in an increased risk of collision. EEG signals, as a direct manifestation of brain activity, can reflect the driver's emotions, cognitive state, and stress response. Real-time analysis and processing of EEG signals can predict the train driver's intentions before the actual action is completed, thereby providing a faster response time for emergency braking.

[0003] One of the prior art solutions (CN104802800B) is the closest prior art to the present invention, which discloses a driver state recognition system based on steering wheel detection, including a steering wheel motion sensor, a brain wave detection helmet, a wireless communication interface and a Freescale IMX6 processor, wherein the steering wheel motion sensor is used to detect the motion state of the car steering wheel, the brain wave detection helmet is used to detect the driver's brain wave characteristics, the IMX6 processor is connected to the steering wheel motion sensor, the brain wave detection helmet and the wireless communication interface respectively, and determines whether to start the detection operation of the brain wave detection helmet based on the motion state, and after starting the detection operation, determines the driver's current driving state according to the analysis result of the brain wave characteristics, and sends the current driving state to the wireless communication interface. Through the present invention, it is possible to start the analysis of the driver's state based on the judgment of the motion state of the car steering wheel, thereby reducing unnecessary system power consumption while ensuring detection efficiency.

[0004] One of the existing technical solutions (CN107015489B) provides a vehicle braking control method and system, wherein the method includes the following steps: collecting the driver's brain wave signal, processing and identifying the driver's brain wave signal to obtain the driver's braking intention signal; receiving the braking intention signal, and performing calculation processing on the braking intention signal to obtain a vehicle braking instruction; and braking control of the vehicle according to the vehicle braking instruction. The method of the present invention can quickly control the braking of the vehicle according to the driver's brain wave signal, effectively reducing the driver's manual operation reaction process, shortening the operation execution time, and effectively solving the problem of mistaking the accelerator for the brake, thereby improving driving safety.

[0005] There is a patent (patent number: 202311403600.8) that integrates the automatic braking of cars into smart glasses, and proposes a car braking system based on brain wave smart glasses. Provided is a car braking system based on brain wave smart glasses, which includes a brain wave TGAM module, a microprocessor STM32F103C8T6 module and a Bluetooth module; the brain wave TGAM module: used to collect brain wave data and transmit the data to the microprocessor STM32F103C8T6; the microprocessor STM32F103C8T6 module: used to process and monitor brain wave data, and when the brain wave data is detected to be abnormal, the microprocessor transmits this state to the car system via Bluetooth; the present invention combines human brain wave data with the braking technology of the car, which can avoid the untimely braking in many emergency scenarios in reality, and can avoid many driving operation errors in emergency scenarios in reality.

[0006] At present, some systems can monitor the driver's cognitive load and emotional state by collecting EEG signals, but most of these systems are limited to simple signal monitoring and cannot accurately capture the decision-making intentions of train drivers under stress in real time in complex train operation scenarios. In addition, existing EEG data processing methods usually only focus on the single-dimensional features of EEG signals and do not fully utilize the multi-dimensional features of the signals to improve recognition accuracy.

[0007] Disadvantages of existing technologies: 1. Currently, there is no relevant technology to associate brain waves with train braking. 2. Most existing technologies are limited to simple signal monitoring and cannot capture the decision-making intentions of train drivers under stress in real time and accurately.

[0008] In view of the above-mentioned deficiencies in the prior art, the present invention is proposed. Summary of the invention

[0009] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a brain wave-based train emergency braking control method and system, a brain wave intelligent helmet structure and a host, which combine human EEG data with train emergency braking to avoid the train driver's inability to trigger the emergency brake button in a timely and effective manner in real-life emergencies such as strong winds, heavy rains, heavy snow, and foreign object intrusion.

[0010] In order to achieve the above object, the present invention adopts the following technical solutions:

[0011] A train emergency brake control system based on brain waves, comprising a smart helmet worn by a train driver with a function of real-time monitoring of the train driver's brain waves, and a host connected to a train traction brake control system by wire.

[0012] The intelligent EEG cap comprises a circuit mainboard, monitoring electrodes, reference electrodes and an adjustment rod;

[0013] The circuit mainboard includes a brain wave TGAM module, a microprocessor STM32F103C8T6 and a JDY31 Bluetooth module;

[0014] The EEG TGAM module is used to collect the train driver's brain wave data in real time and transmit the pre-processed data to the microprocessor STM32F103C8T6 through the Bluetooth module;

[0015] The microprocessor STM32F103C8T6 is used to receive, process and monitor brain wave data in real time. When the characteristic signal obtained after processing is successfully compared with the braking command characteristic signal stored in the database, the microprocessor STM32F103C8T6 sends a traction removal command to the host through the JDY31 Bluetooth module;

[0016] JDY31 Bluetooth module is used to realize bidirectional data transmission between the EEG TGAM module and the microprocessor STM32F103C8T6, and between the microprocessor STM32F103C8T6 and the host;

[0017] The monitoring electrode is connected to the circuit main board. By adjusting the deformation of the adjustment rod, the position and tightness of the monitoring electrode and the left frontal pole of the train driver's brain are adjusted to monitor the train driver's brain wave data in real time.

[0018] The reference electrodes are located on the left and right sides of the smart helmet, measuring the potential of the left and right ears respectively, and are used to remove interference from power frequency and physiological noise;

[0019] The host computer displays the train driver's brain waves in real time and is connected to the circuit main board via Bluetooth wireless to receive real-time brain wave data and traction removal instructions;

[0020] The host transmits the received traction removal instruction to the train traction brake control system to realize automatic braking of the train in an emergency.

[0021] Preferably, the host also has a cloud-edge collaboration function, which can upload the real-time collected EEG data to the cloud for analysis and optimization;

[0022] More preferably, the host dynamically adjusts the personalized settings of the brain wave characteristic signal parameters through the analysis of historical data in the cloud, thereby optimizing the generation and judgment process of the traction command, ensuring that the system can adapt to the individual brain wave differences of the driver and improving the accuracy of traction removal when responding to emergencies.

[0023] The present invention also provides a train emergency braking control method based on brain waves, comprising the following steps:

[0024] Step S1, the train starts and the detection system runs;

[0025] The circuit mainboard of the smart helmet is internally connected to data and externally connected to the host via Bluetooth; the host is wiredly connected to the train traction and braking control system;

[0026] After the train starts, the driver wears a safety helmet and adjusts the adjustment rod to adjust the position and tightness of the monitoring electrode of the circuit main board on the train driver's forehead; the reference electrode of the circuit main board is connected to the train driver's ears to ensure stable signal acquisition;

[0027] Step S2, the helmet collects brain wave data;

[0028] The smart helmet starts working, and the brain wave TGAM module collects the driver's brain wave signals in real time and performs preliminary denoising processing;

[0029] Step S3, Bluetooth data transmission;

[0030] The brain wave data is transmitted to the microprocessor STM32F103C8T6 in real time through the JDY31 Bluetooth module;

[0031] Step S4, the single chip microcomputer processes the brain wave data;

[0032] The microprocessor STM32F103C8T6 performs wavelet decomposition on the received EEG signal and extracts the wavelet coefficients of the β and γ frequency bands;

[0033] The STM32F103C8T6 single-chip microprocessor extracts signal features from brain wave signals, trains brake command data based on machine learning, and combines online training with cloud-edge collaboration technology to process and monitor brain wave real-time data, including:

[0034] Step S41: extracting wavelet coefficients of the β and γ frequency bands of EEG waves in different scenarios from the EEG database through wavelet decomposition, and combining the characteristics of the original EEG data in the time domain, frequency domain and entropy domain as input to the machine learning model;

[0035] Step S42: using a random forest-based machine learning classification algorithm to perform semi-supervised learning on the data in the brain wave signal database to extract characteristic signals of brain waves under stress scenarios, and converting the machine learning model trained by TensorFlow into a model suitable for the microprocessor STM32F103C8T6;

[0036] Step S5, input the features of time domain, frequency domain, wavelet domain and entropy domain into the TensorFlow Lite model in the microprocessor STM32F103C8T6 to classify the brain wave feature signals in the real-time scenario;

[0037] Step 6: Based on the results of the model operation in step 5, determine whether the monitored brain wave signal data is abnormal; by comparing it with the braking command characteristic signal in the database, determine whether the driver is in an emergency braking state;

[0038] If the data is abnormal, execute steps S7 and S8;

[0039] If the data is normal, the process returns to step S5 to continue data monitoring;

[0040] Step S7: When the driver's brain wave signal is detected to be abnormal, that is, the characteristic signal successfully matches the brake command characteristic signal in the database, the microprocessor STM32F103C8T6 sends a traction cut-off instruction to the host through the JDY31 Bluetooth module, and the host transmits the traction cut-off instruction to the train traction brake control system through wired transmission, and immediately performs emergency braking;

[0041] Step S8: After waiting for the train driver to restart the device for monitoring, return to step 5 to re-monitor the data, and the system starts to receive, process and monitor the train driver's brain waves again.

[0042] in,

[0043] In step S42, the construction of the machine learning model trained by TensorFlow includes the following steps:

[0044] Step S421, using the EEG TGAM module to collect EEG data of the train driver in normal driving and different stress scenarios, and construct an EEG signal database;

[0045] Step S422, data preprocessing stage, using wavelet decomposition method to extract wavelet domain features of EEG signals, and combining time domain, frequency domain and entropy domain features to form a multi-dimensional feature vector;

[0046] Step S423, using a random forest classification algorithm to train the brain wave data;

[0047] Step S424, training a model that can accurately identify the driver's stress state by classifying the stress state and normal state data in the database;

[0048] Step S425, the model for identifying the driver's stress state in step S424 is implemented under the TensorFlow framework, and the finally generated model is optimized and converted into the TensorFlow Lite format suitable for the microprocessor STM32F103C8T6;

[0049] Step S426, the model in the TensorFlow Lite format finally generated in step S425 is updated online synchronously to the microprocessor STM32F103C8T6, and the microprocessor STM32F103C8T6 stores the latest 1 second, 2 seconds and 3 seconds of brain wave data in three circular buffers respectively, and uses the wavelet decomposition method to extract the wavelet domain features of the three segments of data with different time lengths;

[0050] In step S427, the system evaluates the three sets of features based on the analysis of real-time data by the microprocessor STM32F103C8T6 and the cloud training results provided by the host, and selects the data that best matches the user's EEG signal characteristics at the time as one of the inputs of the model in TensorFlow Lite format in step S426.

[0051] Beneficial effects:

[0052] 1. Through real-time monitoring and analysis of brain waves, the system can automatically trigger the braking mechanism when the driver is in a state of stress, reducing human delays and ensuring that the train can quickly take stress measures in dangerous situations;

[0053] 2. The present invention uses wavelet decomposition technology, combined with the characteristics of frequency domain, time domain and entropy domain, to accurately extract the driver's EEG characteristic signals under different stress scenarios. The multi-dimensional feature extraction method can effectively improve the system's recognition accuracy of the driver's stress state and reduce the possibility of misjudgment;

[0054] 3. Through online training and cloud-edge collaboration technology, the system can dynamically update the model parameters in the microprocessor according to the individual characteristics of the driver after receiving real-time EEG data, so that the system can better adapt to the differences in original EEG data of different drivers and ensure a rapid and accurate response to stress situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the brain wave-based train emergency braking control method and system. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0056] Figure 1 A schematic diagram of the structure of the smart helmet provided in this embodiment;

[0057] Figure 2 A schematic diagram of information transmission of a train emergency braking control method and system based on brain waves provided in this embodiment;

[0058] Figure 3A system flow chart of a train emergency braking control method and system based on brain waves provided in this embodiment;

[0059] Description of the symbols of the accompanying drawings:

[0060] 1 Train driver, 2 Smart helmet, 3 Circuit board,

[0061] 4 monitoring electrode, 5 reference electrode, 6 adjustment rod,

[0062] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0063] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be interpreted as limiting the present invention.

[0064] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless defined as herein.

[0065] To facilitate understanding of the embodiments of the present invention, two specific embodiments are taken as examples for further explanation below, and these two embodiments do not constitute limitations on the embodiments of the present invention.

[0066] Embodiment 1:

[0067] The present invention proposes a train emergency braking control method and system based on brain waves. Figure 1 , Figure 1It is a structural schematic diagram of a smart helmet provided in this embodiment. In order to realize the emergency braking control of the train, the present invention provides a smart helmet with real-time monitoring of the train driver's brain waves for the train driver 1. The smart EEG helmet 2 includes a circuit mainboard 3, a monitoring electrode 4, a reference electrode 5 and an adjustment rod 6. The circuit mainboard 3 includes a brain wave TGAM module, a microprocessor STM32F103C8T6 and a JDY31 Bluetooth module; the brain wave TGAM module is used to collect the brain wave data of the train driver in real time, and transmit the pre-processed data to the microprocessor STM32F103C8T6 through the Bluetooth module; the microprocessor STM32F103C8T6 is used to receive, process and monitor the brain wave data in real time. When the characteristic signal obtained after processing is successfully compared with the braking instruction characteristic signal stored in the database, the microprocessor STM32F103C8T6 sends the information to the monitoring device 1 through the JDY31 Bluetooth module. The host sends a traction and resection instruction; the JDY31 Bluetooth module is used to realize two-way data transmission between the EEG TGAM module and the microprocessor STM32F103C8T6, and between the microprocessor STM32F103C8T6 and the host; the monitoring electrode 4 is connected to the circuit main board 3, and the position and tightness of the monitoring electrode 4 and the left frontal pole area of ​​the brain of the train driver 1 can be adjusted by adjusting the deformation of the adjustment rod 6, so as to monitor the EEG data of the train driver in real time; the reference electrode 5 is located on the left and right sides of the smart helmet, and measures the left and right ear potentials respectively, so as to remove the interference of power frequency and physiological noise.

[0068] Please refer to Figure 2 , Figure 2 This is a schematic diagram of information transmission of a train emergency brake control method and system based on brain waves provided in this embodiment. The circuit board of the smart helmet transmits real-time brain wave data and traction instructions to the host through the JDY31 Bluetooth module, and the host displays the working status of the smart brain wave helmet and the brain waves of the train driver in real time; the host transmits the received traction removal instruction to the train traction brake control system through a wired connection with the train traction brake control system, realizing automatic braking of the train in an emergency.

[0069] Please refer to Figure 3 , Figure 3It is a system flow chart of a train emergency braking control method and system based on brain waves provided in this embodiment; after the train starts, the smart helmet starts working, and the brain wave TGAM module collects the driver's brain wave signals in real time and performs preliminary denoising. The TGAM module transmits the preprocessed data to the microprocessor STM32F103C8T6 module through the JDY31 Bluetooth module. The microprocessor STM32F103C8T6 performs wavelet decomposition on the received brain wave signal and extracts the wavelet coefficients of the β and γ frequency bands. Combined with the characteristics of the time domain and entropy domain, it is input into the TensorFlow Lite model in the microprocessor STM32F103C8T6, which is based on the random forest classification algorithm to classify the brain wave characteristic signals under stress scenarios. By comparing with the braking command characteristic signal in the database, it is determined whether the driver is in an emergency braking state. When the driver's brain wave signal is detected to be abnormal, that is, the characteristic signal successfully matches the brake command characteristic signal in the database, the microprocessor STM32F103C8T6 immediately sends a traction cut-off instruction to the host PC through the JDY31 Bluetooth module. After the host PC transmits the signal to the train traction brake control system, it immediately performs emergency braking. After waiting for the train driver to restart the smart helmet device, the system starts to receive, process and monitor the train driver's brain waves again.

[0070] Embodiment 2:

[0071] The embodiment of the present invention describes how to perform model training through machine learning methods during brain wave signal analysis and apply the model to a brain wave smart helmet system.

[0072] The brain wave TGAM module is used to collect brain wave data of train drivers in normal driving and different stress scenarios, and an EEG signal database is constructed. In the data preprocessing stage, the wavelet decomposition method is used to extract the frequency domain features of the EEG signal, and the time domain and entropy domain features are combined to form a multidimensional feature vector. The random forest classification algorithm is used to train the EEG data. By classifying the stress state and normal state data in the database, a model that can accurately identify the driver's stress state is trained. The model is implemented under the TensorFlow framework, and the final generated model is optimized and converted into the TensorFlow Lite format suitable for the microprocessor STM32F103C8T6. The model is updated online and synchronously to the microprocessor STM32F103C8T6. The microprocessor STM32F103C8T6 stores the latest 1 second, 2 seconds and 3 seconds of EEG data in three circular buffers respectively, and uses the wavelet decomposition method to extract the wavelet domain features of the three different time lengths of data, and then combines the time domain, frequency domain and entropy domain features as feature input. Based on the analysis of real-time data by the microprocessor STM32F103C8T6 and the cloud training results provided by the host, the system evaluates the three sets of features, selects the data that best matches the user's EEG signal characteristics at the time as the input of the model, and determines whether the characteristic signals of brain waves in stressful scenarios are detected; in actual use, the microprocessor STM32F103C8T6 uses the model to judge the driver's brain wave characteristics through the received real-time EEG data, and determines whether to trigger an emergency braking command.

[0073] In summary, the embodiment of the present invention collects the brain wave signals of the train driver in real time, combines the time domain, frequency domain, wavelet domain and entropy domain features, uses a machine learning model to identify and judge the stress state, and constructs a mapping relationship between the brain wave signal features and the emergency braking command. Through the data processing inside the smart helmet and the external Bluetooth communication connection system, the automatic cutting off and recovery of the train traction is realized. After many tests, the present invention can accurately judge the emergency braking needs in real time according to the driver's brain wave signals, automatically send traction cutting commands, effectively improve the safety response speed and operation accuracy of the train under stress conditions, and realize intelligent safety control during the operation of the train.

[0074] In addition, an embodiment of the present application also proposes a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, on which a behavior recognition program is stored, and when the behavior recognition program is executed by a processor, the method of the present application as described above is implemented.

[0075] The various embodiments of the electronic device and computer-readable storage medium of the present application can all refer to the various embodiments of the behavior recognition method of the present application, which will not be repeated here.

[0076] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0077] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0078] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for an electronic device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0079] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A train emergency braking control system based on brain waves, characterized in that: It includes a smart helmet worn by the train driver that monitors the train driver's brain waves in real time, and a host computer that is wired to the train's traction and braking control system. The intelligent EEG cap comprises a circuit mainboard, monitoring electrodes, reference electrodes and an adjustment rod; The circuit mainboard includes a brain wave TGAM module, a microprocessor STM32F103C8T6 and a JDY31 Bluetooth module; The EEG TGAM module is used to collect the train driver's brain wave data in real time and transmit the pre-processed data to the microprocessor STM32F103C8T6 through the Bluetooth module; The microprocessor STM32F103C8T6 is used to receive, process and monitor brain wave data in real time. When the characteristic signal obtained after processing is successfully compared with the braking command characteristic signal stored in the database, the microprocessor STM32F103C8T6 sends a traction removal command to the host through the JDY31 Bluetooth module; JDY31 Bluetooth module is used to realize bidirectional data transmission between the EEG TGAM module and the microprocessor STM32F103C8T6, and between the microprocessor STM32F103C8T6 and the host; The monitoring electrode is connected to the circuit main board. By adjusting the deformation of the adjustment rod, the position and tightness of the monitoring electrode and the left frontal pole of the train driver's brain are adjusted to monitor the train driver's brain wave data in real time. The reference electrodes are located on the left and right sides of the smart helmet, measuring the potential of the left and right ears respectively, and are used to remove interference from power frequency and physiological noise; The host computer displays the train driver's brain waves in real time and is connected to the circuit main board via Bluetooth wireless to receive real-time brain wave data and traction removal instructions; The host transmits the received traction removal instruction to the train traction brake control system to realize automatic braking of the train in an emergency.

2. A train emergency braking control system based on brain waves according to claim 1, characterized in that: The host also has a cloud-edge collaboration function, which can upload real-time collected EEG data to the cloud for analysis and optimization.

3. A train emergency brake control system based on brain waves according to claim 2, characterized in that: Specifically: the host dynamically adjusts the personalized settings of brain wave characteristic signal parameters through the analysis of historical data in the cloud, thereby optimizing the generation and judgment process of traction instructions, ensuring that the system can adapt to the individual brain wave differences of the driver and improving the accuracy of traction removal when responding to emergencies.

4. A train emergency braking control method based on brain waves as claimed in any one of claims 1 to 3, characterized in that: The following steps are involved: Step S1, the train starts and the detection system runs; The circuit mainboard of the smart helmet is internally connected to data and externally connected to the host via Bluetooth; the host is wiredly connected to the train traction and braking control system; After the train starts, the driver wears a safety helmet and adjusts the adjustment rod to adjust the position and tightness of the monitoring electrode of the circuit main board on the train driver's forehead; the reference electrode of the circuit main board is connected to the train driver's ears to ensure stable signal acquisition; Step S2, the helmet collects brain wave data; The smart helmet starts working, and the brain wave TGAM module collects the driver's brain wave signals in real time and performs preliminary denoising processing; Step S3, Bluetooth data transmission; The brain wave data is transmitted to the microprocessor STM32F103C8T6 in real time through the JDY31 Bluetooth module; Step S4, the single chip microcomputer processes the brain wave data; The microprocessor STM32F103C8T6 performs wavelet decomposition on the received EEG signal and extracts the wavelet coefficients of the β and γ frequency bands; The STM32F103C8T6 single-chip microprocessor extracts signal features from brain wave signals, trains brake command data based on machine learning, and combines online training with cloud-edge collaboration technology to process and monitor brain wave real-time data, including: Step S41: extracting wavelet coefficients of the β and γ frequency bands of EEG waves in different scenarios from the EEG database through wavelet decomposition, and combining the characteristics of the original EEG data in the time domain, frequency domain and entropy domain as input to the machine learning model; Step S42: using a random forest-based machine learning classification algorithm to perform semi-supervised learning on the data in the brain wave signal database to extract characteristic signals of brain waves under stress scenarios, and converting the machine learning model trained by TensorFlow into a model suitable for the microprocessor STM32F103C8T6; Step S5, input the features of time domain, frequency domain, wavelet domain and entropy domain into the TensorFlow Lite model in the microprocessor STM32F103C8T6 to classify the brain wave feature signals in the real-time scenario; Step 6: Based on the results of the model operation in step 5, determine whether the monitored brain wave signal data is abnormal; by comparing it with the braking command characteristic signal in the database, determine whether the driver is in an emergency braking state; If the data is abnormal, execute steps S7 and S8; If the data is normal, the process returns to step S5 to continue data monitoring; Step S7: When the driver's brain wave signal is detected to be abnormal, that is, the characteristic signal successfully matches the brake command characteristic signal in the database, the microprocessor STM32F103C8T6 sends a traction cut-off instruction to the host through the JDY31 Bluetooth module, and the host transmits the traction cut-off instruction to the train traction brake control system through wired transmission, and immediately performs emergency braking; Step S8: After waiting for the train driver to restart the device for monitoring, return to step 5 to re-monitor the data, and the system starts to receive, process and monitor the train driver's brain waves again.

5. The train emergency braking control method based on brain waves according to claim 4 is characterized in that: The following steps are involved: In step S42, the construction of the machine learning model trained by TensorFlow includes the following steps: Step S421, using the EEG TGAM module to collect EEG data of the train driver in normal driving and different stress scenarios, and construct an EEG signal database; Step S422, data preprocessing stage, using wavelet decomposition method to extract wavelet domain features of EEG signals, and combining time domain, frequency domain and entropy domain features to form a multi-dimensional feature vector; Step S423, using a random forest classification algorithm to train the brain wave data; Step S424, training a model that can accurately identify the driver's stress state by classifying the stress state and normal state data in the database; Step S425, the model for identifying the driver's stress state in step S424 is implemented under the TensorFlow framework, and the finally generated model is optimized and converted into the TensorFlow Lite format suitable for the microprocessor STM32F103C8T6; Step S426, the model in the TensorFlow Lite format finally generated in step S425 is updated online synchronously to the microprocessor STM32F103C8T6, and the microprocessor STM32F103C8T6 stores the latest 1 second, 2 seconds and 3 seconds of brain wave data in three circular buffers respectively, and uses the wavelet decomposition method to extract the wavelet domain features of the three segments of data with different time lengths; In step S427, the system evaluates the three sets of features based on the analysis of real-time data by the microprocessor STM32F103C8T6 and the cloud training results provided by the host, and selects the data that best matches the user's EEG signal characteristics at the time as one of the inputs of the model in TensorFlow Lite format in step S426.

Images