Omnibearing intelligent anti-collision system for underground trackless equipment

Abstract

The utility model provides an omni-directional intelligent anti-collision system for underground trackless equipment, which relates to the technical field of anti-collision of underground trackless equipment and comprises an edge computing and processing unit, a signal input and output unit, a handheld positioning card, a ranging radar unit, an infrared camera light supplementing unit and a 360-degree omni-directional positioning base station unit. The edge calculation processing unit is respectively connected with the signal input and output unit, the ranging radar unit, the infrared camera light supplement unit and the 360-degree omnidirectional positioning base station unit, the handheld positioning card transmits narrow pulse signals to the 360-degree omnidirectional positioning base station unit, and the handheld positioning card and the 360-degree omnidirectional positioning base station unit transmit communication signals to each other. According to the technical scheme of the utility model, the problems of misjudgment and erroneous judgment caused by incapability of accurately sensing approaching personnel or fixed roadways in the prior art are solved.

Description

Technical Field

[0001] The utility model relates to the technical field of anti-collision of underground trackless equipment, in particular to an all-round intelligent anti-collision system for underground trackless equipment. Background Art

[0002] In underground operations, underground trackless transport equipment plays a vital role as an important means of transportation. However, the underground operating environment is complex and changeable, and there are many safety hazards. Among them, vehicle collision accidents are one of the more common safety issues. Although the underground trackless vehicle transportation system has the advantages of improving work efficiency and enhancing safety, there are major safety hazards in actual application, which can easily cause various safety accidents. The underground working space is narrow, the tunnels are crisscrossed, and the vision is severely obstructed. Trackless vehicles can easily collide with tunnel walls, other vehicles, and staff during driving. This will not only cause equipment damage and property loss, but may also lead to casualties, bringing huge economic losses and negative impacts to mining companies. In addition, traditional anti-collision measures mainly rely on the driver's experience and attention, but they have great limitations and cannot effectively cope with the complex and changing underground environment.

[0003] At present, the anti-collision system of underground trackless transportation equipment uses lidar to sense the surrounding environment of the vehicle, and then sends alarm signals to locomotives and other transportation equipment. This system has difficulty in sensing approaching people and fixed lanes, and is prone to misjudgment and miscalculation.

[0004] Therefore, there is a need for an all-round intelligent anti-collision system for underground trackless equipment that can accurately sense approaching personnel or fixed tunnels. Utility Model Content

[0005] The main purpose of the utility model is to provide an all-round intelligent anti-collision system for underground trackless equipment to solve the problem that the existing technology cannot accurately sense approaching personnel or fixed lanes, which easily leads to misjudgment and miscalculation.

[0006] To achieve the above-mentioned objectives, the present invention provides an all-round intelligent collision avoidance system for underground trackless equipment, comprising: an edge computing processing unit, a signal input and output unit, a handheld positioning card, a ranging radar unit, an infrared camera fill light unit and a 360° omnidirectional positioning base station unit; the edge computing processing unit is respectively connected to the signal input and output unit, the ranging radar unit, the infrared camera fill light unit and the 360° omnidirectional positioning base station unit, the handheld positioning card transmits a narrow pulse signal to the 360° omnidirectional positioning base station unit, and the handheld positioning card and the 360° omnidirectional positioning base station unit transmit communication signals to each other, an image detection algorithm is integrated in the image acquisition and processing module, the image acquisition and processing module collects the driver's behavior information and the environment information in front and behind the vehicle, and performs abnormal behavior detection and environmental analysis through the image detection algorithm.

[0007] Furthermore, the edge computing processing unit includes: a switch input module, a wireless communication module, a data storage module, a switch output module, a bus chip, a control mainboard, a cooling fan, a power supply processing module, a deep learning computing power card, an image acquisition processing module, an Ethernet module, a 485 module, and a CAN to 485 chip;

[0008] Among them, the switch input module, switch output module and 485 module are connected to the bus chip respectively;

[0009] The wireless communication module, data storage module, power supply processing module, deep learning computing power card, Ethernet module and bus chip are respectively connected to the control mainboard;

[0010] The cooling fan dissipates heat for the power processing module;

[0011] The CAN to 485 chip is connected to the bus chip via the 485 module;

[0012] The Ethernet module is also connected to the deep learning computing power card through the image acquisition and processing module.

[0013] Furthermore, the signal input and output unit includes: a cancel parking button, a current limiting resistor R1, a reset button, a current limiting resistor R2, a parking relay, a current limiting resistor R3, an alarm light, a current limiting resistor R4, an alarm horn, a power amplifier unit and a touch screen display;

[0014] Among them, the cancel stop button transmits the signal to the switch input module through the current limiting resistor R1;

[0015] The reset button transmits the signal to the switch input module through the current limiting resistor R2;

[0016] The switch output module transmits the stop command to the parking relay through the current limiting resistor R3;

[0017] The switch output module transmits the alarm signal to the alarm light through the current limiting resistor R4, and the switch output module also transmits the alarm signal to the alarm speaker through the power amplifier unit;

[0018] The touch screen communicates with the bus chip through the 485 module.

[0019] Furthermore, the handheld positioning card includes: a power indicator module, a positioning card power supply module, an audible and visual alarm module, a vibration alarm module, a positioning card power management module, a pulse transmitter, a positioning card main chip, a power amplifier, a sleep wake-up chip and a positioning card handshake communication chip;

[0020] Among them, the sound and light alarm module, vibration alarm module, positioning card power management module, sleep wake-up chip and pulse transmitter are respectively connected to the positioning card main chip;

[0021] The positioning card power supply module supplies power to the power indicator module and supplies power to the micro positioning card main chip through the positioning card power management module;

[0022] The handshake communication chip of the positioning card transmits the signal to the main chip of the positioning card through the sleep wake-up chip;

[0023] The pulse transmitter is also connected to a power amplifier.

[0024] Furthermore, the ranging radar unit includes: a CAN interface, a radar power supply, a radar conversion circuit, a radar main chip, a PMIC module, a pulse receiving module, a radio frequency front-end component, a transmitting module, a receiving antenna, and a transmitting antenna;

[0025] Among them, the CAN interface, PMIC module and radar conversion circuit are respectively connected to the radar main chip, and the radar conversion circuit is also connected to the RF front-end component;

[0026] The radar power supply provides power to the PMIC module;

[0027] The receiving antenna transmits the signal to the RF front-end component through the receiving module, and then transmits it to the transmitting antenna through the transmitting module.

[0028] Furthermore, the 360° omnidirectional positioning base station unit includes: a base station network interface, a first antenna, a first pulse receiver, a second antenna, a second pulse receiver, a third antenna, a third pulse receiver, a base station handshake communication chip, a positioning main control chip, a base station controller, a positioning base station power management module, a power detection module and a synchronizer;

[0029] The first antenna, second antenna, and third antenna simultaneously capture the pulse signal emitted by the handheld positioning card and jointly obtain distance, direction, and angle information. The first antenna, second antenna, and third antenna transmit the signal to the positioning main control chip for analysis through the first pulse receiver, second pulse receiver, and third pulse receiver respectively;

[0030] The positioning main control chip is connected to the Ethernet module through the base station network interface;

[0031] The base station handshake communication chip, the base station controller, the positioning base station power management module, the power detection module and the synchronizer are respectively connected to the positioning main control chip.

[0032] Furthermore, the infrared fill light camera unit includes: a camera network interface, a DSP processing chip, a CCD chip, an infrared LED fill light, a video filter, a video memory card and a high-definition camera;

[0033] The infrared LED fill light projects infrared light onto the object, so that the infrared light is reflected by the object and enters the high-definition camera for imaging. The image is then transmitted to the DSP processing chip through the video filter and CCD chip in sequence. The DSP processing chip is connected to the camera network interface and video memory card respectively.

[0034] Furthermore, the image acquisition and processing module collects the driver's behavior information and the environment in front and behind the vehicle, and transmits the collected information to the convolutional neural network CNN in the image detection algorithm for feature extraction, multi-scale feature fusion and target detection, and activates the system alarm or parking function according to the detection results.

[0035] The utility model has the following beneficial effects:

[0036] This utility model utilizes UWB technology, image detection technology and millimeter wave radar technology to realize intelligent perception of people, vehicles and objects and illegal operations of drivers, effectively realizing all-round intelligent collision avoidance of trackless equipment, filling the domestic and foreign gaps in intelligent collision avoidance of underground trackless equipment, and has great market application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0038] Figure 1 The utility model shows a structural diagram of an all-round intelligent anti-collision system for underground trackless equipment.

[0039] The reference numerals in the above drawings are:

[0040] 101. Switch input module; 102. Wireless communication module; 103. Data storage module; 104. Switch output module; 105. Bus chip; 106. Control mainboard; 107. Cooling fan; 108. Power supply processing module; 109. Deep learning computing card; 110. Image acquisition and processing module; 111. Ethernet module; 112. 485 module; 113. CAN to 485 chip; 201. Cancel stop button; 202. Current limiting resistor R1; 203. Reset button; 204, current limiting resistor R2; 205, parking relay; 206, current limiting resistor R3; 207, warning light; 208, current limiting resistor R4; 209, warning horn; 210, power amplifier unit; 211 touch screen; 301, power indicator module; 302, positioning card power supply module; 303, sound and light alarm module; 304, vibration alarm module; 305, positioning card power management module; 306, pulse transmitter; 307, positioning card main chip; 308, power amplifier 309, sleep wake-up chip; 310, positioning card handshake communication chip; 402, CAN interface; 403, radar power supply; 404, radar conversion circuit; 405 radar main chip; 406 PMIC module; 407 receiving module; 408 RF front-end components; 409 transmitting module; 410 receiving antenna; 411 transmitting antenna components; 502, camera network interface; 503, DSP processing chip; 504, CCD chip; 505, infrared LED fill light; 50 6. Video filter; 507. Video storage card; 508. High-definition camera; 601. Base station network interface; 602. First antenna; 603. First pulse receiver; 604. Second antenna; 605. Second pulse receiver; 606. Third antenna; 607. Third pulse receiver; 608. Base station handshake communication chip; 609. Positioning main control chip; 610. Base station controller; 612. Positioning base station power management module; 613. Power detection module; 614. Synchronizer. DETAILED DESCRIPTION

[0041] The following is a clear and complete description of the technical solution of the present invention in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of the present invention.

[0042] like Figure 1The illustrated system comprises an all-round intelligent collision avoidance system for underground trackless equipment, comprising an edge computing processing unit, a signal input and output unit, a handheld positioning card, a ranging radar unit, an infrared camera fill light unit and a 360° omnidirectional positioning base station unit. The edge computing processing unit is connected to the signal input and output unit, the ranging radar unit, the infrared camera fill light unit and the 360° omnidirectional positioning base station unit respectively. The handheld positioning card transmits a narrow pulse signal to the 360° omnidirectional positioning base station unit, and the handheld positioning card and the 360° omnidirectional positioning base station unit transmit communication signals to each other. An image detection algorithm is integrated in an image acquisition and processing module, which collects information on the driver's behavior and the environment in front and behind the vehicle, and performs abnormal behavior detection and environmental analysis through the image detection algorithm.

[0043] Specifically, the edge computing processing unit includes: a switch input module, a wireless communication module, a data storage module, a switch output module, a bus chip, a control motherboard, a cooling fan, a power supply processing module, a deep learning computing power card, an image acquisition and processing module, an Ethernet module, a 485 module, and a CAN-to-485 chip. The switch input module, switch output module, and 485 module are each connected to the bus chip; the wireless communication module, data storage module, power supply processing module, deep learning computing power card, Ethernet module, and bus chip are each connected to the control motherboard; the cooling fan dissipates heat from the power supply processing module; the CAN-to-485 chip is connected to the bus chip via the 485 module; and the Ethernet module is also connected to the deep learning computing power card via the image acquisition and processing module.

[0044] The edge computing processing unit consists of a switch input module 101; a wireless communication module 102; a data storage module 103; a switch output module 104; a bus chip 105; a control mainboard 106; a cooling fan 107; a power supply processing module 108; a deep learning computing power card 109; an image acquisition and processing module 110; an Ethernet module 111; a 485 module 112; and a CAN to 485 chip 113.

[0045] The edge computing processing unit's primary function is to work closely with the ranging radar unit, infrared camera unit, and 360° omnidirectional positioning base station unit. The CAN-to-485 chip and 485 module convert the CAN signals output by the ranging radar unit into 485 signals, which are then uploaded to the control board via the bus chip. This information provides distance information between the vehicle and the obstacle. If a dangerous distance is detected, the edge computing processing unit transmits an alarm / stop signal via the bus chip to the switch output module, which then triggers an alarm or stop command via a current-limiting resistor.

[0046] Deep learning computing power cards are specifically designed to accelerate deep learning tasks and support intelligent system detection capabilities. They provide computing resources, accelerate model inference, and improve computing efficiency, greatly ensuring the stable operation of detection tasks. The specific model of deep learning computing power card is INVIDIA nx.

[0047] The Ethernet module is the receiving end of data transmission between the infrared fill light camera unit and the 360° omnidirectional positioning base station unit. It sends information about the driver's behavior and the surrounding environment to the image acquisition and processing module, which uses image detection algorithms to detect abnormal behavior and analyze the environment. If the driver violates regulations or abnormal behavior is detected, the system will automatically alarm or stop the vehicle. The edge computing processing unit also works in conjunction with the 360° omnidirectional positioning base station unit to determine the location of personnel and equipment based on positioning data, ensuring timely warning and handling of any entry into dangerous areas. In addition, all sensor data and system status are stored in the data storage module and connected to the local area network via the wireless communication module, allowing managers to easily view equipment operation logs and alarm information.

[0048] The power supply processing module of the edge computing processing unit provides stable power support for each module to ensure the continuous operation of the system.

[0049] When the temperature of the edge computing device reaches 50 degrees Celsius or above, the cooling fan can start in time to dissipate heat and ensure the stable operation of the entire device.

[0050] Specifically, the signal input and output unit includes: a cancel parking button, a current limiting resistor R1, a reset button, a current limiting resistor R2, a parking relay, a current limiting resistor R3, an alarm light, a current limiting resistor R4, an alarm horn, a power amplifier unit and a touch display screen; wherein, the cancel parking button transmits the signal to the switch input module through the current limiting resistor R1; the reset button transmits the signal to the switch input module through the current limiting resistor R2; the switch output module transmits the parking instruction to the parking relay through the current limiting resistor R3; the switch output module transmits the alarm signal to the alarm light through the current limiting resistor R4, and the switch output module also transmits the alarm signal to the alarm horn through the power amplifier unit; the touch display screen communicates with the bus chip through the 485 module.

[0051] The signal input and output unit includes a cancel parking button 201 , a current limiting resistor R1 202 , a reset button 203 , a current limiting resistor R2 204 , a parking relay 205 , a current limiting resistor R3 206 , an alarm light 207 , a current limiting resistor R4 208 , an alarm horn 209 , a power amplifier unit 210 , and a touch screen display 211 .

[0052] The signal input and output unit is mainly responsible for receiving the user's control instructions and transmitting them to the control motherboard. It is also responsible for feeding back the information detected by the motherboard to the user.

[0053] Each current-limiting resistor can complete the voltage division task required by the entire circuit, ensure the voltage safety and stability of the switching input and output modules, and enable the devices connected to the switching input and output modules to function normally.

[0054] When the driver wants to cancel parking while working (the driver sometimes remotely controls the vehicle, and when there is no one in the cab, the system will determine that the vehicle has left the seat and parked, so the parking needs to be canceled; or there are many obstacles around the work scene, and the radar will alarm to stop, which will also affect the work), the cancel parking button will transmit the signal to the switch input module through the current limiting resistor R1. The command is then transmitted to the edge computing processing unit through the bus chip. The control motherboard parses and releases the parking state. When the work is completed and the vehicle wants to resume parking, the reset button signal is transmitted to the switch input module through the current limiting resistor R2. The bus chip then transmits the command to the control motherboard to resume parking.

[0055] When the control main board detects an abnormal situation (the driver leaves the seat, the UWB level 3 alarm means parking) and the vehicle needs to be parked, the parking command is transmitted to the switch output module through the bus chip, and finally enters the parking relay through the current limiting resistor R3. The parking relay activates the vehicle's emergency stop button to stop the vehicle.

[0056] When the control main board detects an abnormal situation (the driver's cabin crew leans forward or extends their hand, the radar is too close, there are people in front or behind, UWB level 1 or level 2 alarm) and an alarm is required, the control main board will send out an alarm signal, which will be transmitted to the switch output module through the bus chip, and finally enter the alarm light and alarm speaker through the current limiting resistor R4 and the power amplifier unit, realizing a dual sound and light alarm.

[0057] The touch screen displays system status, alarm information, and execution feedback to operators in real time. It communicates with the bus chip via the 485 module, visually presenting the edge computing processing unit's processing results to the user.

[0058] Specifically, the handheld positioning card includes: a power indicator module, a positioning card power supply module, an audio and visual alarm module, a vibration alarm module, a positioning card power management module, a pulse transmitter, a positioning card main chip, a power amplifier, a sleep wake-up chip, and a positioning card handshake communication chip;

[0059] Among them, the sound and light alarm module, vibration alarm module, positioning card power management module, sleep wake-up chip and pulse transmitter are respectively connected to the positioning card main chip;

[0060] The positioning card power supply module supplies power to the power indicator module and supplies power to the micro positioning card main chip through the positioning card power management module;

[0061] The handshake communication chip of the positioning card transmits the signal to the main chip of the positioning card through the sleep wake-up chip;

[0062] The pulse transmitter is also connected to a power amplifier.

[0063] The handheld positioning card consists of a battery indicator module 301; a positioning card power supply module 302; an audible and visual alarm module 303; a vibration alarm module 304; a positioning card power management module 305; a pulse transmitter 306; a positioning card main chip 307; a power amplifier 308; a sleep / wakeup chip 309; and a positioning card handshake communication chip 310. The handheld positioning card is the mobile positioning module in the system, responsible for real-time tracking of the cardholder's specific location and working in conjunction with the 360° omnidirectional positioning base station unit.

[0064] The positioning card's main chip continuously transmits its unique identifier and related data. A pulse transmitter converts the chip's digital signal into a pulse signal suitable for wireless transmission. A power amplifier amplifies the signal before transmitting it to the positioning base station. The positioning card's handshake communication chip exchanges information with the base station's handshake communication chip, synchronizing the two. If the base station detects that the positioning card is too close, it transmits an alarm signal back to the main chip via the handshake communication chip. The sleep wakeup chip then calls the main chip, triggering the audio and visual alarm module and the vibration alarm module to alert the wearer.

[0065] The positioning card's power supply module provides stable power to its internal chips and transmitter modules. The positioning card's power management module intelligently monitors battery status and optimizes power consumption to extend battery life. When the battery is low, the battery indicator module displays a red light, reminding the operator to recharge the positioning card.

[0066] Specifically, the infrared fill light camera unit includes: a camera network interface, a DSP processing chip, a CCD chip, an infrared LED fill light, a video filter, a video memory card and a high-definition camera;

[0067] The infrared LED fill light projects infrared light onto the object, so that the infrared light is reflected by the object and enters the high-definition camera for imaging. The image is then transmitted to the DSP processing chip through the video filter and CCD chip in sequence. The DSP processing chip is connected to the camera network interface and video memory card respectively.

[0068] The infrared fill light camera unit includes a camera network interface 502, a DSP processing chip 503, a CCD chip 504, an infrared LED fill light 505, a video filter 506, a video memory card 507, and a high-definition camera 508. The infrared fill light camera unit provides an infrared light source for the camera, thereby capturing high-quality images.

[0069] In dark environments with no visible light or minimal light, infrared LED fill lights actively project infrared light onto objects, which then reflect off the object and enter the lens for imaging. After capturing the image, the HD camera uses a video filter to remove infrared light and trim the incoming light. The filtered image is then transmitted to the CCD chip, which converts the light into an electronic signal. The DSP processing chip processes the electronic signal captured by the image sensor and converts it into a visible, real-world image. The generated image is stored on a video memory card and transmitted to the edge computing processing unit via a network interface, enabling real-time access to the camera's video stream for video display and image processing. The network interface connects to the edge computing processing unit's Ethernet module, transmitting image data at 100 Mbps to support subsequent analysis.

[0070] Specifically, the ranging radar unit includes: a CAN interface, a radar power supply, a radar conversion circuit, a radar main chip, a PMIC module, a pulse receiving module, a radio frequency front-end component, a transmitting module, a receiving antenna, and a transmitting antenna. The CAN interface, the PMIC module, and the radar conversion circuit are respectively connected to the radar main chip, and the radar conversion circuit is also connected to the radio frequency front-end component. The radar power supply supplies power to the PMIC module. The receiving antenna transmits the signal to the radio frequency front-end component through the receiving module, and then transmits it to the transmitting antenna through the transmitting module.

[0071] The ranging radar unit consists of a CAN interface 402; a radar power supply 403; a radar conversion circuit 404; a radar main chip 405; a PMIC module 406; a pulse receiving module 407; a radio frequency front-end component 408; a transmitting module 409; a receiving antenna 410; and a transmitting antenna 411.

[0072] The ranging radar unit is primarily responsible for real-time monitoring of the surrounding environment and distance measurement, ensuring the system can accurately perceive the relative distances of surrounding obstacles during operation. The radar power supply features a snap-on design that securely connects to the radar conversion circuit inlet, providing stable power to the entire radar unit. The PMIC module provides voltage stabilization and manages power consumption to ensure stable power supply to the entire radar unit, protecting the entire radar circuitry in the event of voltage anomalies. High-frequency electromagnetic waves are emitted by the RF front-end components. When these waves hit surfaces, they are reflected, and the reflected signals are transmitted back to the radar main chip via the receiving antenna. The transmitting antennas are evenly spaced, improving radar system performance metrics such as gain and beamwidth. These antennas ensure stable signal reception within the radar unit, facilitating subsequent signal analysis. The radar main chip digitizes the echo signals and calculates the relative distance between the object and the system. The calculated data is transmitted via the CAN interface to the edge computing processing unit for further analysis and decision-making.

[0073] The core components of the ranging radar unit are the radar main chip and radar conversion circuit. The radar chip parses the collected echo signals into distance data and transmits this data to the edge computing processing unit. In certain special circumstances, such as when detecting an obstacle or reversing into a wall, if the ranging radar unit detects a target too close, it will send an alarm signal through the control board. The power amplifier unit drives the warning lights and alarm horn to alert the operator to potential dangers. If necessary, the radar main chip immediately transmits the data to the signal input and output unit via the CAN interface, triggering the parking relay to initiate an emergency stop, ensuring the safety of the equipment and operators.

[0074] The ranging radar unit also collaborates with other perception modules (such as infrared fill light camera units). In complex environments, the system can not only detect the presence of objects, but also classify targets based on the results of image recognition. The edge computing processing unit fuses the radar data and the image data captured by the camera to achieve more accurate target recognition and judgment. The radar signal is combined with the image information to achieve timely alarms and emergency stops when necessary, and in special circumstances, there will be no false alarms that hinder driving. The communication between the ranging radar unit and the 485 module is also particularly important. The data collected by the radar will be transmitted to other modules via the 485 module, giving the entire system multi-level information perception capabilities. In addition, the detection range of the ranging radar unit can be set through the touch screen, which is convenient for the driver to make corresponding adjustments according to different industrial and mining environments.

[0075] Specifically, the 360° omnidirectional positioning base station unit includes: a base station network interface, a first antenna, a first pulse receiver, a second antenna, a second pulse receiver, a third antenna, a third pulse receiver, a base station handshake communication chip, a positioning main control chip, a base station controller, a positioning base station power management module, a power detection module and a synchronizer; the first antenna, the second antenna and the third antenna simultaneously capture the pulse signal emitted by the handheld positioning card, and jointly obtain the distance, direction and angle information. The first antenna, the second antenna and the third antenna respectively transmit the signal to the positioning main control chip for analysis through the first pulse receiver, the second pulse receiver and the third pulse receiver; the positioning main control chip is connected to the Ethernet module through the base station network interface; the base station handshake communication chip, the base station controller, the positioning base station power management module, the power detection module and the synchronizer are respectively connected to the positioning main control chip.

[0076] The 360° omnidirectional positioning base station unit consists of a base station network interface 601; a first antenna 602; a first pulse receiver 603; a second antenna 604; a second pulse receiver 605; a third antenna 606; a third pulse receiver 607; a base station handshake communication chip 608; a positioning main control chip 609; a base station controller 610; a positioning base station power management module 612; a power detection module 613; and a synchronizer 614. The 360° omnidirectional positioning base station unit is primarily responsible for signal exchange with the card-holding positioning unit, achieving precise bidirectional positioning of personnel and equipment.

[0077] The first, second, and third antennas simultaneously capture the pulse signals emitted by the handheld positioning card, collectively obtaining distance, direction, and angle information. The first, second, and third pulse receivers transmit the signals to the positioning control chip for analysis. This analysis data is then uploaded to the edge computing processing unit via the base station network interface to determine the cardholder's precise location.

[0078] The base station controller is responsible for managing the received signal strength and quality, ensuring that the signals between antennas do not conflict, and monitoring the operating status of the entire base station to ensure that the system works continuously and stably.

[0079] The synchronizer is mainly responsible for time synchronization. It uses time-of-flight (TOF) and time-difference-of-arrival (TDOA) positioning algorithms to enable the pulse receiving module, antenna, and base station controller to process signals at the same time node, avoiding positioning errors caused by time differences and reducing signal delays.

[0080] The positioning base station power management module is responsible for properly scheduling power, while the positioning base station power detection module is responsible for monitoring power supply conditions and status. Together, they ensure the base station can operate normally with uninterrupted power supply. The base station handshake communication chip exchanges signals with the positioning card handshake communication chip, establishing two-way communication.

[0081] Specifically, the image acquisition and processing module collects the driver's behavior information and the environment in front and behind the vehicle, and transmits the collected information to the convolutional neural network CNN in the image detection algorithm for feature extraction, multi-scale feature fusion and target detection, and activates the system alarm or parking function based on the detection results.

[0082] Specifically, the image acquisition and processing module processes the vehicle's front and rear environmental information including the following steps:

[0083] Step 1: The system obtains the video stream as input data and preprocesses the video stream data, including: adjusting the image size, pixel normalization and format conversion.

[0084] Step 2: After preprocessing, the video stream is input into the convolutional neural network (CNN) module for feature extraction, multi-scale feature map fusion, and target detection.

[0085] Step 3: Determine whether pedestrians and turn signs are detected.

[0086] Step 4: If a pedestrian is detected, the real-time detection data of the millimeter-wave radar is immediately read for auxiliary judgment. When the radar data is less than 25 meters, the system alarm is activated. If a turn sign is detected, it means that the vehicle is about to enter the turning state. At this time, the parking function for obstacles less than 0.5 meters determined by the millimeter-wave radar detection distance is temporarily cancelled to ensure that the vehicle can pass through narrow corners smoothly.

[0087] Specifically, the image acquisition and processing module processes and collects the driver's behavior information, including the following steps:

[0088] Step 1: The system receives a video stream as input data and preprocesses it, including image resizing, pixel normalization, and format conversion. Image resizing involves scaling to 640x640 pixels, and pixel normalization involves mapping pixel values ​​to the range [0, 1] to ensure the data matches the model's input requirements.

[0089] Step 2: The preprocessed video stream is fed into a convolutional neural network (CNN) module for feature extraction, multi-scale feature map fusion, and object detection. The preprocessed image frames are then passed to the CNN. In a CNN, multiple layers of convolution are used to extract feature information at different levels, gradually aggregating low-level information such as edges and textures into high-level semantic features. The network utilizes multi-scale convolutions to simultaneously process objects of varying sizes, ensuring robust detection for both small and large objects. After inference, the network outputs information such as the object category and confidence level.

[0090] Step 3: Classify the detected targets and distinguish between normal and abnormal behaviors. After the detection is completed, the model classifies the identified targets and distinguishes between normal and abnormal behaviors as the basis for subsequent decision-making.

[0091] Step 4: In case of abnormal behavior, the system triggers an alarm or brakes the vehicle. The system executes the corresponding instructions based on the detection and classification results. For example, if the driver is detected probing their head or extending their hand in the cab, an abnormal behavior alarm is triggered; if the driver leaves their seat, the vehicle is braked. This workflow achieves end-to-end intelligent target detection, ensuring real-time and accuracy.

[0092] In this utility model, the edge computing processing unit continuously receives millimeter-wave radar signals and converts them into 485 signals for distance conversion. When the distance is less than a set value, the image detection algorithm is used to detect the front and rear of the vehicle. The system issues an alarm or controls the vehicle to make an emergency stop based on the detection results. The steps include:

[0093] Step 1: The edge computing processing unit continuously receives millimeter-wave radar signals, converts them into 485 signals for distance conversion, and analyzes the converted distance in real time.

[0094] Step 2: When the distance is greater than 1 meter, it is within the safe range; when the distance is less than 1 meter, the system continuously monitors and uses image detection algorithms to detect the front and rear of the vehicle. If a turning sign is detected and the vehicle is in a turning state, and the instant distance is less than 1 meter, the radar voice alarm is triggered to remind the driver that the distance is less than the safe distance; if no turning sign is detected, the system will issue an alarm when the distance is 0.5 meters < 1 meter; when the distance is < 0.5 meters, the control motherboard of the edge computing processing unit will send a stop signal to the relay, causing the relay to control the vehicle's emergency stop button for an emergency stop.

[0095] The edge computing processing unit continuously receives radar CAN signals, converts them into 485 signals for distance conversion, and analyzes the converted distance in real time. When the distance is greater than 1 meter, it is within the safe range. When the distance is less than 1 meter, the system continuously monitors and uses image detection algorithms to detect the front and rear of the vehicle. If a turn sign is detected (special turn signs are posted at the location where the turn is about to take place, and the system will detect this sign), it means that the vehicle is in a turning state. Even if the distance is less than 1 meter, the vehicle will not stop, but will trigger a radar voice alarm to remind the driver that the safe distance is less than 1 meter. If no turn sign is detected, then when the distance is less than 0.5 meters and less than 1 meter, the system will issue an alarm. When the distance is less than 0.5 meters, the control board of the edge computing processing unit will send a stop signal to the relay, causing the relay to control the vehicle's emergency stop button for an emergency stop.

[0096] The utility model uses UWB signals to calculate the position information between the base station and the handheld positioning card, and sends an alarm message based on the position information. Specifically, it includes the following steps:

[0097] Step 1: When processing UWB signals, the control motherboard of the edge computing processing unit will first detect whether the UWB signal has been received. If a UWB signal is detected, the distance, direction and angle between the base station and the handheld positioning card will be immediately analyzed.

[0098] If no UWB signal is detected, the image detection algorithm is used to detect people in the front and rear of the vehicle. If pedestrians are detected in the front and rear video streams, the edge computing processing unit will analyze the 485 signal converted from the millimeter-wave radar signal, and make auxiliary judgments based on the distance data analyzed by the 485 signal. When the distance of an object is less than 25 meters, a voice alarm is triggered to remind the driver that there may be pedestrians without UWB signal handheld positioning cards nearby. That is, if there are pedestrians behind the vehicle but the device has not received the UWB signal, and the radar data shows that there are objects within 25 meters, a warning will be sent to the driver, but the vehicle will not stop.

[0099] Step 2: If the distance between the base station and the handheld positioning card is not within the range of 25-30 meters, it means that it is within 25 meters. First determine whether the handheld positioning card is in the front, back, left, or right of the vehicle.

[0100] Step 3: When the person carrying the positioning card is in front of or behind the vehicle, if the distance is between the second limit and the third limit, the UWB first-level alarm will be triggered; if the distance is between the first limit and the second limit, the UWB second-level alarm will be triggered; if it is less than the first-level limit, stop the car immediately; when the person carrying the positioning card is on the left or right rear of the vehicle, the first-level alarm and the second-level alarm are the same, if it is less than half of the first-level limit, stop the car immediately.

[0101] When processing UWB signals, the control board will first detect whether it has received a UWB signal. If it has, it will immediately analyze the distance, direction, and angle between the base station and the positioning card and display them on the touch screen. If the distance between the base station and the positioning card is greater than 25 meters and less than 30 meters, it is in a safe distance and will be displayed as a blue dot on the touch screen; when the distance is less than 25, it will be displayed as a red dot. If it is not in the 25-30 meter range, it means that it is within 25 meters (the maximum communication distance between the base station and the positioning card is only 30 meters. If it exceeds 30 meters, no signal can be received, so it must be within 25 meters). At this time, it is necessary to first determine whether the positioning card is in front of, behind, or to the left or right of the vehicle (the parking distance in front of, behind, or to the left is larger, and the parking distance in front of, behind, or to the left is smaller. If the parking distance is set to 7 meters, the front and rear will stop when it is less than 7 meters, while the positioning cards on the left and right will only stop when it is less than half of the set threshold, that is, 3.5 meters. However, the distance between the first and second level alarms does not need to be halved. If the second level alarm is set to 10-15 meters, then the alarm will be 10-15 meters regardless of the front, behind, or left. When a person carrying a positioning card is in front of or behind the vehicle, if the distance is between the second and third limits, a UWB-based first-level alarm is triggered. If the distance is between the first and second limits, a UWB-based second-level alarm is triggered. If the distance is less than the first-level limit, the vehicle stops immediately (for example, if the third-level limit is 20, the second-level limit is 15, and the first-level limit is 10, then if the distance is greater than 15 but less than 20, the first-level alarm is triggered, if it is greater than 10 but less than 15, the second-level alarm is triggered, and if it is less than 10, the vehicle stops immediately). When a person carrying a positioning card is in the left or right rear of the vehicle, the first-level and second-level alarms are the same. If the distance is less than half of the first-level limit, the vehicle stops immediately. If the system cannot detect a UWB signal, to prevent people without positioning cards from appearing nearby, it uses image detection algorithms to detect people in front and behind the vehicle. If pedestrians are detected in the front or rear video streams, the radar data is read and used to assist in the judgment. If there are pedestrians in the rear and objects within 25 meters of the radar, a warning is sent to the person, but the vehicle does not stop.

[0102] Of course, the above description is not a limitation of the present invention, and the present invention is not limited to the above examples. Changes, modifications, additions or substitutions made by technicians in this technical field within the essential scope of the present invention should also fall within the scope of protection of the present invention.

Claims

1. An all-round intelligent anti-collision system for underground trackless equipment, characterized in that: include: Edge computing processing unit, signal input and output unit, handheld positioning card, ranging radar unit, infrared camera fill light unit and 360° omnidirectional positioning base station unit; the edge computing processing unit is respectively connected to the signal input and output unit, ranging radar unit, infrared camera fill light unit and 360° omnidirectional positioning base station unit, the handheld positioning card transmits the narrow pulse signal to the 360° omnidirectional positioning base station unit, and the handheld positioning card and the 360° omnidirectional positioning base station unit transmit communication signals to each other, the image acquisition and processing module integrates the image detection algorithm, the image acquisition and processing module collects the driver's behavior information and the front and rear environment information of the vehicle, and performs abnormal behavior detection and environmental analysis through the image detection algorithm.

2. The all-round intelligent anti-collision system for underground trackless equipment according to claim 1, characterized in that: The edge computing processing unit includes: switch input module, wireless communication module, data storage module, switch output module, bus chip, control mainboard, cooling fan, power supply processing module, deep learning computing power card, image acquisition processing module, Ethernet module, 485 module and CAN to 485 chip; Among them, the switch input module, switch output module and 485 module are connected to the bus chip respectively; The wireless communication module, data storage module, power supply processing module, deep learning computing power card, Ethernet module and bus chip are respectively connected to the control mainboard; The cooling fan dissipates heat for the power processing module; The CAN to 485 chip is connected to the bus chip via the 485 module; The Ethernet module is also connected to the deep learning computing power card through the image acquisition and processing module.

3. The all-round intelligent anti-collision system for underground trackless equipment according to claim 2, characterized in that: The signal input and output unit includes: a cancel parking button, a current limiting resistor R1, a reset button, a current limiting resistor R2, a parking relay, a current limiting resistor R3, an alarm light, a current limiting resistor R4, an alarm horn, a power amplifier unit and a touch screen; Among them, the cancel stop button transmits the signal to the switch input module through the current limiting resistor R1; The reset button transmits the signal to the switch input module through the current limiting resistor R2; The switch output module transmits the stop command to the parking relay through the current limiting resistor R3; The switch output module transmits the alarm signal to the alarm light through the current limiting resistor R4, and the switch output module also transmits the alarm signal to the alarm speaker through the power amplifier unit; The touch screen communicates with the bus chip through the 485 module.

4. The all-round intelligent anti-collision system for underground trackless equipment according to claim 3, characterized in that: The handheld positioning card includes: power indicator module, positioning card power supply module, sound and light alarm module, vibration alarm module, positioning card power management module, pulse transmitter, positioning card main chip, power amplifier, sleep wake-up chip and positioning card handshake communication chip; Among them, the sound and light alarm module, vibration alarm module, positioning card power management module, sleep wake-up chip and pulse transmitter are respectively connected to the positioning card main chip; The positioning card power supply module supplies power to the power indicator module and supplies power to the micro positioning card main chip through the positioning card power management module; The handshake communication chip of the positioning card transmits the signal to the main chip of the positioning card through the sleep wake-up chip; The pulse transmitter is also connected to a power amplifier.

5. The all-round intelligent anti-collision system for underground trackless equipment according to claim 4, characterized in that: The ranging radar unit includes: CAN interface, radar power supply, radar conversion circuit, radar main chip, PMIC module, pulse receiving module, RF front-end component, transmitting module, receiving antenna and transmitting antenna; Among them, the CAN interface, PMIC module and radar conversion circuit are respectively connected to the radar main chip, and the radar conversion circuit is also connected to the RF front-end component; The radar power supply provides power to the PMIC module; The receiving antenna transmits the signal to the RF front-end component through the receiving module, and then transmits it to the transmitting antenna through the transmitting module.

6. The all-round intelligent anti-collision system for underground trackless equipment according to claim 5, characterized in that: The 360° omnidirectional positioning base station unit includes: a base station network interface, a first antenna, a first pulse receiver, a second antenna, a second pulse receiver, a third antenna, a third pulse receiver, a base station handshake communication chip, a positioning main control chip, a base station controller, a positioning base station power management module, a power detection module and a synchronizer; The first antenna, second antenna, and third antenna simultaneously capture the pulse signal emitted by the handheld positioning card and jointly obtain distance, direction, and angle information. The first antenna, second antenna, and third antenna transmit the signal to the positioning main control chip for analysis through the first pulse receiver, second pulse receiver, and third pulse receiver respectively; The positioning main control chip is connected to the Ethernet module through the base station network interface; The base station handshake communication chip, the base station controller, the positioning base station power management module, the power detection module and the synchronizer are respectively connected to the positioning main control chip.

7. The all-round intelligent anti-collision system for underground trackless equipment according to claim 6, characterized in that: The infrared fill light camera unit includes: camera network interface, DSP processing chip, CCD chip, infrared LED fill light, video filter, video memory card and high-definition camera; The infrared LED fill light projects infrared light onto the object, so that the infrared light is reflected by the object and enters the high-definition camera for imaging. The image is then transmitted to the DSP processing chip through the video filter and CCD chip in sequence. The DSP processing chip is connected to the camera network interface and video memory card respectively.

8. The all-round intelligent anti-collision system for underground trackless equipment according to claim 7, characterized in that: The image acquisition and processing module collects information about the driver's behavior and the environment in front and behind the vehicle, and transmits the collected information to the convolutional neural network (CNN) in the image detection algorithm for feature extraction, multi-scale feature fusion, and target detection. The system alarm or parking function is activated based on the detection results.

Images