Intelligent anti-pinch system for door of urban rail vehicle

Abstract

The invention belongs to the technical field of vehicle intelligent anti-pinch, and discloses an urban rail vehicle door intelligent anti-pinch system which comprises a bioelectricity monitoring module, a multi-mode sensor fusion module, a virtual reality warning module and an intelligent control center. The bioelectricity monitoring module detects human body bioelectricity signals through an electrode type sensor to judge the human clamping risk. The multi-mode sensor fusion module is combined with pressure, infrared and ultrasonic sensors, and the detection accuracy is improved through data preprocessing and a fusion algorithm. The intelligent control center processes data, judges risks and generates control instructions, and can communicate with a train and station system to achieve remote monitoring. And the virtual reality warning module projects warning images and information, so that the safety awareness of passengers is improved. The system has the advantages of innovative detection mode, visual warning and multi-sensor fusion, and can effectively improve the safety and operation efficiency of the door of the urban rail vehicle. The method has a wide application prospect, and can provide safety guarantee for more fields.

Description

Technical Field

[0001] The invention relates to the technical field of vehicle intelligent anti-pinch technology, and in particular to an intelligent anti-pinch system for doors of urban rail vehicles. Background Art

[0002] The anti-pinch system of urban rail vehicle doors is a safety device that detects obstacles during the door closing process through sensors, and automatically stops closing or reverses opening when it detects that the pressure exceeds the safety threshold to prevent passengers from being pinched or objects from being damaged. This system is usually controlled by a door control unit (door controller), combined with intelligent fault diagnosis technology, and can monitor and respond in real time to ensure passenger safety and stable system operation.

[0003] At present, the anti-pinch technology of urban rail vehicle doors mainly relies on traditional sensors, such as pressure sensors, infrared sensors, etc. However, these traditional sensors have some obvious problems.

[0004] First, limited accuracy and reliability: Traditional sensors may be interfered by the external environment when detecting the risk of people being trapped, resulting in misjudgment or missed detection. For example, pressure sensors may not accurately detect people being trapped due to the small contact area between the door and the object or uneven pressure distribution; infrared sensors may be affected by factors such as strong light and dust, reducing the accuracy of detection.

[0005] Secondly, lack of intuitiveness: the existing door anti-pinch system usually only warns through sound or light, making it difficult for passengers to intuitively understand the dangerous situation of the door. This may cause some passengers to fail to notice the warning signal in time due to negligence, increasing the probability of pinching accidents.

[0006] Finally, the limitations of a single sensor: a single type of sensor can often only detect specific situations and cannot fully respond to various complex risks of people being trapped. For example, a pressure sensor can only detect the pressure change between an object and a car door, but cannot detect the obstruction of the object; an infrared sensor can only detect the obstruction of infrared rays by an object, but cannot detect the distance between the object and the car door. Summary of the invention

[0007] The main purpose of the present invention is to provide an intelligent anti-pinch system for urban rail vehicle doors, which can effectively solve the problems mentioned in the background technology.

[0008] To achieve the above object, the technical solution adopted by the present invention is: The intelligent anti-pinch system for urban rail vehicle doors includes a bioelectric monitoring module, a multimodal sensor fusion module, a virtual reality warning module and an intelligent control center. Specifically: The bioelectric monitoring module includes an electrode-type bioelectric sensor installed on the door handle and armrest. When the passenger touches these parts, the sensor can detect the bioelectric signal of the human body and upload the bioelectric signal to the intelligent control center; The multimodal sensor fusion module includes a pressure sensor, an infrared sensor and an ultrasonic sensor, wherein the pressure sensor is installed at the edge of the door and the door frame to detect the pressure change caused by the contact with the object when the door is closed; the infrared sensor is a beam-type infrared sensor installed on both sides of the door to detect whether there is an object blocking the infrared light in the closed area of ​​the door; the ultrasonic sensor is installed on the door to measure the distance between the door and the obstacle; after the data of the above three sensors are transmitted to the intelligent control center, they are first pre-processed and then processed by the fusion algorithm; The intelligent control center includes a microprocessor, a memory, an input / output interface, a communication module, and a power management module, wherein the microprocessor processes sensor data and makes decisions; the memory stores program code and data; the input / output interface connects various sensors; the communication module communicates with the train control system and the station monitoring center for remote monitoring and management; the power management module is powered by a battery and supplies power to the entire system in the event of a power outage; The virtual reality warning module includes a projector, a projection screen, an image generating unit and a control unit, wherein the projector is installed near the vehicle door, the projection screen is a wall or ground near the vehicle door, the image generating unit generates warning images and information under the instruction of the control unit, and the control unit receives instructions from the intelligent control center and controls the operation of the projector.

[0009] Preferably, the electrode-type bioelectric sensor is composed of electrodes, a signal conditioning circuit and a housing. The electrodes are in contact with the human body to collect the bioelectric signals of the human body, such as the potential changes on the skin surface. The signal conditioning circuit amplifies, filters and digitizes the collected bioelectric signals for subsequent analysis and processing. The housing protects and fixes the sensor. If a passenger's hand or other body part touches the door during the closing process, the bioelectric signal will change significantly, and the sensor will send a signal to the intelligent control center to trigger the anti-pinch mechanism.

[0010] Preferably, the pressure sensor is a piezoresistive pressure sensor, which is composed of a sensitive element, a conversion circuit and a housing. The sensitive element is a thin film made of metal or semiconductor material. When subjected to pressure, the film will deform, resulting in a change in resistance value. The conversion circuit converts the change in resistance value into an electrical signal output, and the housing plays a role in protecting and fixing the sensor. When the pressure exceeds the set threshold, the sensor will send a signal to the intelligent control center to trigger the anti-pinch mechanism.

[0011] Preferably, the infrared sensor is composed of an infrared transmitting tube and an infrared receiving tube. The infrared transmitting tube transmits infrared rays of a specific wavelength. When the infrared rays encounter an obstacle, they are reflected back and received by the infrared receiving tube. The infrared receiving tube converts the received infrared signals into electrical signals for output. The infrared sensor detects whether there is an object blocking the infrared rays in the closed area of ​​the door by a counter-beam method. When an object blocks the infrared rays, the infrared sensor sends a signal to the intelligent control center to trigger the anti-pinch mechanism.

[0012] Preferably, the ultrasonic sensor is composed of an ultrasonic transmitter, an ultrasonic receiver and a control circuit. The ultrasonic transmitter transmits an ultrasonic signal. When the ultrasonic wave encounters an obstacle, it is reflected back and received by the ultrasonic receiver. The control circuit processes the ultrasonic signal and calculates the distance between the door and the obstacle. The ultrasonic sensor is installed on the door and can measure the distance between the door and the obstacle in real time. When the distance is less than the set value, the sensor sends a signal to the intelligent control center to trigger the anti-pinch mechanism.

[0013] Preferably, the multimodal sensor fusion module preprocesses the data of the three sensors including the following steps: S1. Noise removal: For pressure sensor data, digital filtering technology is used to remove high-frequency noise caused by environmental interference or sensor noise itself; for infrared sensor data, noise signals caused by ambient light interference or other infrared source interference are removed; for ultrasonic sensor data, echo interference signals are removed through filtering algorithms; S2. Data normalization: For each sensor data, first calculate its mean and standard deviation, then subtract the mean from the original data and divide it by the standard deviation to normalize the data to a distribution with a mean of 0 and a variance of 1, so that data from different sensors are comparable; S3, feature extraction: for pressure sensors, extract amplitude, rate and peak time; for infrared sensors, extract duration and frequency; for ultrasonic sensors, extract trend, relationship with speed and fluctuation amplitude. Specifically: Pressure sensor feature extraction: Pressure change amplitude: Calculate the difference between the maximum and minimum values ​​of the normalized pressure data within a period of time to reflect the severity of the pressure change when the door contacts the object. Pressure change rate: By calculating the difference between the normalized pressure values ​​at adjacent time points and dividing it by the time interval, the pressure change rate is obtained, which can be used to determine the dynamic characteristics of the contact between the object and the door. Pressure peak occurrence time: Record the time point when the normalized pressure reaches the maximum value, and analyze the timing of the contact between the object and the door in combination with the time process of the door closing.

[0014] Infrared sensor feature extraction: Occlusion duration: Count the duration of the normalized infrared sensor being blocked. A longer occlusion duration may mean that the object is larger or the contact between the object and the door is more stable. Occlusion frequency: Calculate the number of times the normalized infrared sensor switches between blocked and unblocked states over a period of time, which can reflect the movement characteristics of the object or the passage of multiple small objects.

[0015] Ultrasonic sensor feature extraction: Distance change trend: Analyze the change trend of the distance value measured by the normalized ultrasonic sensor at continuous time points. For example, a gradual decrease indicates that the object is close to the door, and a gradual increase indicates that the object is far away from the door. Relationship between distance and door closing speed: Correlate the distance value measured by the normalized ultrasonic sensor with the door closing speed. For example, when the distance decreases rapidly and the door closes quickly, there may be a high risk of people being trapped. Distance fluctuation range: Calculate the difference between the maximum and minimum values ​​of the normalized ultrasonic distance measurement over a period of time to reflect the stability of the obstacle position.

[0016] Preferably, the fusion algorithm in the multimodal sensor fusion module selects the weighted average method, assuming that the measurement value of the pressure sensor is , whose weight is ; The measured value of the infrared sensor is , whose weight is ;The measured value of the ultrasonic sensor is , whose weight is , fusion results ,in =1, ensuring that the sum of the weights is 1, so that the fusion result is within a reasonable range; and 1, 1, 1, indicating that each weight is in the range of 0 to 1, that is, non-negative and does not exceed 1.

[0017] Preferably, the control logic of the intelligent control center includes: ①. Data processing: receiving data from the bioelectric monitoring module and the multimodal sensor fusion module and performing preprocessing; ② Risk judgment: Use fusion algorithms to process multimodal sensor data and combine changes in bioelectric signals to determine whether there is a risk of people or objects being trapped; ③. Command generation and execution: If there is a risk, a control command is generated, such as stopping door closing, adjusting speed and sensitivity, etc., and transmitted to the door control system, and the status information is displayed; ④. Communication: Communicate with the train and station systems through the communication module to achieve remote monitoring and issue alarms in case of accidents.

[0018] Preferably, the virtual reality warning module uses a projection screen with high brightness and high resolution, and adds a flashing dynamic effect.

[0019] Compared with the prior art, the present invention has the following beneficial effects: Bioelectric monitoring is adopted. The bioelectric monitoring module determines the risk of pinching by detecting the bioelectric signals of the human body. It is a unique detection method, which is more accurate and reliable than traditional sensors and is not affected by the external environment. The intuitiveness of virtual reality warnings. The virtual reality warning module projects warning images and information to allow passengers to more intuitively understand the dangerous conditions of the car doors, improve their safety awareness, and reduce pinching accidents caused by negligence. Multimodal sensor fusion,The multimodal sensor fusion module combines the advantages of multiple sensors, processes the data of different sensors through fusion algorithms, improves the accuracy and reliability of detection, and can better cope with various complex situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of the composition architecture flow of the present invention. DETAILED DESCRIPTION

[0021] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0022] like Figure 1 As shown, the system includes a bioelectric monitoring module, a multimodal sensor fusion module, a virtual reality warning module and an intelligent control center.

[0023] Bioelectric monitoring module installation: Electrode-type bioelectric sensors are installed on the door handles and handrails of urban rail vehicles. The electrode part fits tightly with the surface that passengers may touch, ensuring that human bioelectric signals can be accurately collected. For example, the electrode can be made of soft conductive material, which does not affect the passenger's touch and can effectively collect signals.

[0024] The signal conditioning circuit and the housing are installed at a suitable position inside the door, which protects the circuit and facilitates the connection with the intelligent control center. The signal conditioning circuit amplifies, filters and digitizes the collected bioelectric signals, and transmits the processed signals to the intelligent control center through a wired connection.

[0025] Multimodal sensor fusion module installation: Pressure sensor installation: Install the piezoresistive pressure sensor on the door edge and door frame. The sensitive element (metal or semiconductor film) is installed at a position where it may come into contact with an object to ensure that the pressure change can be accurately sensed. The conversion circuit and housing are installed inside the door to transmit the output signal of the pressure sensor to the intelligent control center. For example, when the door is closed, if an object is sandwiched between the door and the door frame, the sensitive element will be deformed by the pressure, resulting in a change in resistance value. The conversion circuit converts this change in resistance value into an electrical signal, such as "0.5V ​​indicates a certain pressure", and transmits it to the intelligent control center.

[0026] Infrared sensor installation: Install the infrared sensors on both sides of the car door. The infrared transmitting tube and the infrared receiving tube are installed on both sides of the car door to ensure that the infrared rays can be reflected in the closed area of ​​the car door. When an object blocks the infrared rays, the infrared receiving tube cannot receive the infrared signal, resulting in a change in the electrical signal. For example, "when the light intensity received by the infrared receiving tube is lower than a certain threshold, it is judged that an object blocks the infrared rays" and the signal is transmitted to the intelligent control center.

[0027] Ultrasonic sensor installation: Install the ultrasonic sensor on the car door. You can choose to install it on the top or side of the car door. The ultrasonic transmitter emits an ultrasonic signal, which is reflected back after encountering an obstacle and received by the ultrasonic receiver. The control circuit processes the ultrasonic signal, calculates the distance between the car door and the obstacle, and transmits the distance information to the intelligent control center. For example, "the ultrasonic sensor emits an ultrasonic signal 10 times per second to measure the distance between the car door and the obstacle. When the distance is less than 30 cm, it is judged that there may be a risk of pinching people."

[0028] Smart Control Center Installation: The components of the intelligent control center are installed in the control room of the urban rail vehicle. The microprocessor is used as the core processor. A high-performance microprocessor, such as an ARM architecture processor, is selected, which has powerful computing and processing capabilities. The memory includes flash memory and random access memory (RAM). The appropriate storage capacity is selected according to the function and complexity of the system.

[0029] The input / output interface connects various sensors and door control systems.

[0030] The communication module includes a wireless communication module and a wired communication module. The wireless communication module uses wireless communication technologies such as Bluetooth, Wi-Fi or ZigBee to communicate with the train control system and the station monitoring center to achieve remote monitoring and management. The wired communication module uses communication technologies such as CAN bus or RS485 bus to communicate with other devices, such as obtaining the operating status information of the vehicle. For example, "through the wireless communication module, the status information of the door is transmitted to the station monitoring center in real time so that the staff can understand the status of the door in time."

[0031] The power management module is powered by batteries and provides power to the entire system in the event of a power outage. The power chip converts the input power into various voltages required by the system, providing a stable power supply for components such as microprocessors, sensors, and communication modules. The battery management module manages battery charging and monitors power to ensure that the system can still work normally in the event of a power outage.

[0032] Virtual reality warning module installation: Install the projector at a suitable location near the door to ensure that clear warning images and information can be projected in the door area. For example, you can choose to install it on the ceiling above the door or on the wall next to the door. The projector uses a high-brightness, high-resolution micro projector that can provide clear projection effects under different environmental conditions.

[0033] The projection screen can be a wall or floor near the car door. If you choose a wall as the projection screen, you need to ensure that the surface of the wall is flat and the color is uniform to improve the projection effect. If you choose the floor as the projection screen, you need to consider the flatness and cleanliness of the floor to avoid affecting the projection effect. For example, "Choose the white wall next to the car door as the projection screen. The wall is flat and can provide a clear projection effect."

[0034] The image generation unit consists of a graphics processor and an image storage unit. The graphics processor is responsible for generating warning images and information. Selecting a processor with strong graphics processing capabilities can quickly generate high-quality images. The image storage unit is used to store templates for warning images and information, and can use storage devices such as flash memory and hard disks. For example, "the image storage unit stores a variety of warning templates, such as a text template of 'The door is about to close, please pay attention to safety', a flashing warning sign template, etc. The graphics processor selects the appropriate template for generation according to different situations."

[0035] The control unit consists of a microprocessor and a communication interface. The microprocessor receives instructions from the intelligent control center and controls the operation of the virtual reality projection device. The communication interface uses wired or wireless communication to communicate with the intelligent control center to ensure stable and reliable data transmission. For example, "the communication interface uses wireless communication to communicate with the intelligent control center in real time. When the intelligent control center determines that there is a risk of pinching, it immediately sends instructions to the control unit, and the control unit controls the projector to project the corresponding warning image and information."

[0036] Data collection and preprocessing: Bioelectric monitoring module: When a passenger touches a door handle or armrest, the electrodes of the electrode-type bioelectric sensor collect bioelectric signals from the human body, such as changes in the potential on the skin surface. The signal conditioning circuit amplifies, filters, and digitizes the collected bioelectric signals to remove high-frequency noise caused by environmental interference or the sensor's own noise, and obtains a clear bioelectric signal. For example, "the signal conditioning circuit uses a low-pass filter to remove noise signals with a frequency higher than 100Hz to obtain a more stable bioelectric signal." The processed bioelectric signal is transmitted to the intelligent control center.

[0037] Multimodal sensor fusion module: Pressure sensor: The pressure sensor detects in real time the pressure changes caused by the contact with the object when the car door is closed. When an object contacts the car door, the sensitive element is deformed by the pressure, resulting in a change in resistance. The conversion circuit converts the change in resistance value into an electrical signal output, such as "the electrical signal range of the pressure sensor output is 0-5V, and the corresponding pressure range is 0-100N". After the data of the pressure sensor is transmitted to the intelligent control center, noise removal is first performed. Digital filtering technology is used to remove high-frequency noise caused by environmental interference or sensor noise itself. For example, "a median filter is used to remove spike noise in the pressure sensor data."

[0038] Infrared sensor: The infrared sensor detects whether there is an object blocking the infrared light in the door closing area by means of a counter-beam method. The infrared transmitting tube emits infrared light of a specific wavelength. When the infrared light encounters an obstacle, it is reflected back and received by the infrared receiving tube. The infrared receiving tube converts the received infrared signal into an electrical signal output, such as "the electrical signal output by the infrared receiving tube is a high level indicating that there is an object blocking the infrared light, and a low level indicating that there is no object blocking the infrared light". After the data of the infrared sensor is transmitted to the intelligent control center, the noise signal caused by ambient light interference or other infrared source interference is removed. For example, "the threshold judgment method is used to remove the noise signal caused by ambient light interference. When the light intensity received by the infrared receiving tube is higher than a certain threshold, it is judged that there is an object blocking the infrared light".

[0039] Ultrasonic sensor: Ultrasonic sensor measures the distance between the car door and the obstacle in real time. The ultrasonic transmitter emits an ultrasonic signal. When the ultrasonic wave encounters an obstacle, it is reflected back and received by the ultrasonic receiver. The control circuit processes the ultrasonic signal and calculates the distance between the car door and the obstacle, such as "the distance value output by the ultrasonic sensor ranges from 0 to 5 meters with an accuracy of 1 cm". After the data of the ultrasonic sensor is transmitted to the intelligent control center, the echo interference signal is removed through the filtering algorithm. For example, "the Kalman filter is used to remove the echo interference signal in the ultrasonic sensor data to obtain a more accurate distance value".

[0040] Data normalization and feature extraction: Data normalization: For each sensor data, first calculate its mean and standard deviation, then normalize the data to a distribution with a mean of 0 and a variance of 1 by subtracting the mean from the original data and dividing by the standard deviation, so that data from different sensors are comparable. For example, "the mean of the pressure sensor data is 2.5V, the standard deviation is 1.5V, and the measured value of a certain pressure sensor is 3.5V, which is (3.5-2.5) / 1.5=0.67 after normalization."

[0041] Feature extraction: Pressure sensor feature extraction: Pressure change amplitude: Calculate the difference between the maximum and minimum values ​​of the normalized pressure data within a period of time, reflecting the severity of the pressure change when the door contacts the object. For example, "In 1 second, the maximum value of the normalized data of the pressure sensor is 0.8, the minimum value is -0.5, and the pressure change amplitude is 0.8-(-0.5)=1.3".

[0042] Pressure change rate: By calculating the difference between the normalized pressure values ​​at adjacent time points and dividing it by the time interval, the pressure change rate can be obtained to determine the dynamic characteristics of the object in contact with the door. For example, "the normalized pressure values ​​at two adjacent time points are 0.6 and 0.8 respectively, the time interval is 0.1 seconds, and the pressure change rate is (0.8-0.6) / 0.1=2".

[0043] Peak pressure occurrence time: record the time point when the normalized pressure reaches the maximum value, and analyze the timing of the object contacting the door in combination with the time process of the door closing. For example, "the normalized pressure reaches the maximum value at 0.5 seconds, and the total door closing time is 2 seconds, indicating that the object contacts the door early in the door closing process."

[0044] Infrared sensor feature extraction: Occlusion duration: The normalized duration of the infrared sensor being blocked. A longer occlusion duration may mean that the object is larger or the contact between the object and the door is more stable. For example, "the infrared sensor was blocked for 0.8 seconds, indicating that the object stayed in the door closing area for a long time."

[0045] Blockage frequency: Counts the number of times the normalized infrared sensor switches between blocked and unblocked states over a period of time, which can reflect the motion characteristics of an object or the passage of multiple small objects. For example, "within 1 second, the infrared sensor's blocked state switches 3 times, indicating that multiple small objects may pass quickly in the door closing area."

[0046] Ultrasonic sensor feature extraction: Distance change trend: Analyze the change trend of the distance value measured by the normalized ultrasonic sensor at consecutive time points. For example, a gradual decrease indicates that the object is approaching the door, and a gradual increase indicates that the object is moving away from the door. For example, "Over a period of time, the normalized distance value of the ultrasonic sensor gradually decreases from 0.5 to 0.2, indicating that the object is approaching the door."

[0047] Relationship between distance and door closing speed: The normalized ultrasonic distance value is correlated with the door closing speed. For example, when the distance decreases rapidly and the door closes quickly, there may be a higher risk of people getting stuck. For example, "the door closing speed is 0.5 meters per second, and the normalized distance value of the ultrasonic sensor decreases from 0.5 to 0.3 in 0.2 seconds. The speed of the object approaching the door is calculated to be 1 meter per second, which is higher than the door closing speed. There may be a risk of people getting stuck."

[0048] Distance fluctuation amplitude: Calculate the difference between the maximum and minimum values ​​of the normalized ultrasonic measurement distance over a period of time to reflect the stability of the obstacle position. For example, "In 1 second, the maximum normalized distance value of the ultrasonic sensor is 0.6, the minimum is 0.4, and the distance fluctuation amplitude is 0.6-0.4=0.2".

[0049] Multi-sensor fusion and risk assessment: The fusion algorithm selects the weighted average method: Assume that the measurement value of the pressure sensor is , whose weight is ; The measured value of the infrared sensor is , whose weight is ;The measured value of the ultrasonic sensor is , whose weight is , fusion results ,in =1, and 1, 1, 1. For example, "Based on experimental data and actual experience, the weight of the pressure sensor is determined to be 0.4, the weight of the infrared sensor is 0.3, and the weight of the ultrasonic sensor is 0.3. When the measurement value of the pressure sensor is 0.7, the measurement value of the infrared sensor is 0.5, and the measurement value of the ultrasonic sensor is 0.4, the fusion result is ”.

[0050] Risk judgment based on changes in bioelectric signals: The intelligent control center simultaneously receives bioelectric signals from the bioelectric monitoring module. If a passenger's hand or other body part touches the door while the door is closing, the bioelectric signal will change significantly. For example, "under normal circumstances, the amplitude of the bioelectric signal fluctuates within a certain range. When a passenger touches the door, the amplitude of the bioelectric signal will suddenly increase. When it exceeds a certain threshold, it is judged that there may be a risk of pinching someone." The intelligent control center combines the multimodal sensor fusion results and bioelectric signal changes to determine whether there is a risk of pinching someone or something. Set the corresponding threshold, and when the fusion result exceeds the threshold, it is judged that there is a risk. For example, "Set the threshold of the fusion result to 0.6. When the fusion result is greater than 0.6, it is judged that there is a risk of pinching someone or something."

[0051] Control instruction generation and execution: Generate control instructions: If the intelligent control center determines that there is a risk of people or objects being trapped, it will immediately generate control instructions. Control instructions include stopping the door closing action, reducing the door closing speed, adjusting the anti-pinch sensitivity, etc. For example, "when it is determined that there is a risk, generate an instruction to stop the door closing action, reduce the door closing speed to 0.1 meters per second, and increase the anti-pinch sensitivity."

[0052] Execute control instructions: The control instructions are transmitted to the door control system. The door control interface communicates with the door motor driver to achieve precise control of the door. For example, "After receiving the instruction to stop closing the door, the door motor driver immediately stops closing the door and adjusts the door closing speed to 0.1 meters per second". At the same time, the intelligent control center transmits the door status information to the display interface, connects to the display screen to display the door status information and alarm prompts, so that passengers and staff can understand the door status in time. For example, "The display screen shows the text prompt 'Door closing pause, please pay attention to safety' and a flashing warning sign".

[0053] Virtual Reality Warning: Image generation and projection: When the intelligent control center determines that there is a risk of people or objects being trapped, it sends instructions to the virtual reality warning module. After receiving the instructions, the microprocessor of the control unit controls the graphics processor of the image generation unit to generate warning images and information. For example, "the graphics processor calls the text template of 'The door is about to close, please pay attention to safety' and the flashing warning sign template from the image storage unit according to the instructions, and generates corresponding warning images and information." The control unit controls the projector to project the warning image and information onto the projection screen, such as the wall or ground near the door. For example, "the projector uses high-brightness and high-resolution projection to clearly project the warning image and information onto the white wall next to the door, allowing passengers to more intuitively understand the dangerous situation of the door."

[0054] Enhanced warning effect: To enhance the warning effect, high-brightness and high-resolution projection images can be used, and flashing dynamic effects can be added. For example, "warning images and information use high-brightness red and yellow colors, with a flashing frequency of 2 times per second, to enhance the warning effect and attract the attention of passengers."

[0055] Communication and remote monitoring: Wireless communication: The intelligent control center communicates with the train control system and the station monitoring center through the wireless communication module. The door status information, risk situation and other data are transmitted to the remote monitoring center to achieve remote monitoring and management. For example, "through Wi-Fi wireless communication technology, the door status information is transmitted to the station monitoring center in real time. The staff can see the status of each car door on the monitoring screen and promptly understand whether there is a risk of people or objects being trapped." In the event of a person or object trapping accident, an alarm can be issued to the station staff in time so that emergency rescue measures can be taken. For example, "when the intelligent control center determines that a person trapping accident has occurred, it immediately sends an alarm signal to the station monitoring center through the wireless communication module, and the staff can quickly rush to the scene to deal with it."

[0056] Wired communication: The intelligent control center communicates with other devices through the wired communication module, such as communicating with the vehicle bus to obtain the vehicle's operating status information. This information can help the intelligent control center better adjust the door control strategy and improve the system's adaptability and safety. For example, "Communicate with the vehicle bus through the CAN bus to obtain the vehicle's speed, acceleration and other operating status information. When the vehicle is in an acceleration or deceleration state, the intelligent control center can adjust the door's anti-pinch sensitivity based on this information to ensure that pinching accidents can be effectively prevented under different operating conditions."

[0057] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. The intelligent anti-pinch system for urban rail vehicle doors is characterized by: The system includes a bioelectric monitoring module, a multimodal sensor fusion module, a virtual reality warning module and an intelligent control center. Specifically: The bioelectric monitoring module includes an electrode-type bioelectric sensor installed on the door handle and armrest. When the passenger touches these parts, the sensor can detect the bioelectric signal of the human body and upload the bioelectric signal to the intelligent control center; The multimodal sensor fusion module includes a pressure sensor, an infrared sensor and an ultrasonic sensor, wherein the pressure sensor is installed at the edge of the door and the door frame to detect the pressure change caused by the contact with the object when the door is closed; the infrared sensor is a beam-type infrared sensor installed on both sides of the door to detect whether there is an object blocking the infrared light in the closed area of ​​the door; the ultrasonic sensor is installed on the door to measure the distance between the door and the obstacle; after the data of the above three sensors are transmitted to the intelligent control center, they are first pre-processed and then processed by the fusion algorithm; The intelligent control center includes a microprocessor, a memory, an input / output interface, a communication module, and a power management module, wherein the microprocessor processes sensor data and makes decisions; the memory stores program code and data; the input / output interface connects various sensors; the communication module communicates with the train control system and the station monitoring center for remote monitoring and management; the power management module is powered by a battery and supplies power to the entire system in the event of a power outage; The virtual reality warning module includes a projector, a projection screen, an image generating unit and a control unit, wherein the projector is installed near the vehicle door, the projection screen is a wall or ground near the vehicle door, the image generating unit generates warning images and information under the instruction of the control unit, and the control unit receives instructions from the intelligent control center and controls the operation of the projector.

2. The intelligent anti-pinch system for urban rail vehicle doors according to claim 1 is characterized in that: The electrode-type bioelectric sensor consists of electrodes, a signal conditioning circuit and a shell, wherein the electrodes are in contact with the human body to collect the human body's bioelectric signals, the signal conditioning circuit amplifies, filters and digitizes the collected bioelectric signals, and the shell protects and fixes the sensor.

3. The intelligent anti-pinch system for urban rail vehicle doors according to claim 1 is characterized in that: The pressure sensor is a piezoresistive pressure sensor, which consists of a sensitive element, a conversion circuit and a housing. The sensitive element is a thin film made of metal or semiconductor material. When subjected to pressure, the film will deform, resulting in a change in resistance value. The conversion circuit converts the change in resistance value into an electrical signal output, and the housing serves to protect and fix the sensor.

4. The intelligent anti-pinch system for urban rail vehicle doors according to claim 4 is characterized in that: The infrared sensor is composed of an infrared transmitting tube and an infrared receiving tube. The infrared transmitting tube transmits infrared rays of a specific wavelength. When the infrared rays encounter an obstacle, they are reflected back and received by the infrared receiving tube. The infrared receiving tube converts the received infrared signals into electrical signals for output.

5. The intelligent anti-pinch system for urban rail vehicle doors according to claim 5 is characterized in that: The ultrasonic sensor is composed of an ultrasonic transmitter, an ultrasonic receiver and a control circuit. The ultrasonic transmitter transmits an ultrasonic signal. When the ultrasonic wave encounters an obstacle, it is reflected back and received by the ultrasonic receiver. The control circuit processes the ultrasonic signal and calculates the distance between the vehicle door and the obstacle.

6. The intelligent anti-pinch system for urban rail vehicle doors according to claim 5, characterized in that: The multimodal sensor fusion module preprocesses the data of the three sensors including the following steps: S1. Noise removal: For pressure sensor data, digital filtering technology is used to remove high-frequency noise caused by environmental interference or sensor noise itself; for infrared sensor data, noise signals caused by ambient light interference or other infrared source interference are removed; for ultrasonic sensor data, echo interference signals are removed through filtering algorithms; S2. Data normalization: For each sensor data, first calculate its mean and standard deviation, then subtract the mean from the original data and divide it by the standard deviation to normalize the data to a distribution with a mean of 0 and a variance of 1, so that data from different sensors are comparable; S3. Feature extraction: For pressure sensors, extract amplitude, rate and peak time; for infrared sensors, extract duration and frequency; for ultrasonic sensors, extract trend, relationship with speed and fluctuation amplitude.

7. The intelligent anti-pinch system for urban rail vehicle doors according to claim 6 is characterized in that: The fusion algorithm in the multimodal sensor fusion module selects the weighted average method, assuming that the measurement value of the pressure sensor is , whose weight is ; The measured value of the infrared sensor is , whose weight is ;The measured value of the ultrasonic sensor is , whose weight is , fusion results ,in =1, and 1, 1, 1.

8. The intelligent anti-pinch system for urban rail vehicle doors according to claim 7, characterized in that: The control logic of the intelligent control center includes: ①. Data processing: receiving data from the bioelectric monitoring module and the multimodal sensor fusion module and performing preprocessing; ② Risk judgment: Use fusion algorithms to process multimodal sensor data and combine bioelectric signal changes to determine whether there is a risk of people or objects being trapped; ③. Command generation and execution: If there is a risk, a control command is generated, such as stopping door closing, adjusting speed and sensitivity, etc., and transmitted to the door control system, and the status information is displayed; ④. Communication: Communicate with the train and station systems through the communication module to achieve remote monitoring and issue alarms in case of accidents.

9. The intelligent anti-pinch system for urban rail vehicle doors according to claim 8, characterized in that: The virtual reality warning module uses a high-brightness and high-resolution projection image and adds a flickering dynamic effect.

Images