Urban rail transit fire rescue inspection vehicle

Abstract

The invention relates to the field of inspection vehicles, and discloses an urban rail transit fire rescue inspection vehicle which comprises a compartment, second electric holders are fixedly connected to the four corners of the compartment, a high-definition camera is arranged at one end of each second electric holder, and a smoke sensor is fixedly connected to one side of the top of the compartment. A mounting plate is fixedly connected to the other side of the top of the compartment, a pantograph is mounted at the top of the mounting plate, connecting boxes are symmetrically and fixedly connected to the bottom of the compartment, audio acquisition equipment is arranged on the sides, away from each other, of the connecting boxes, and ultrasonic radars and single-line laser radar sensors are evenly arranged at the bottom of the compartment. The smoke sensor is used for detecting the smoke concentration in the compartment and the surrounding environment in real time, an alarm is given out in time, the first electric holders symmetrically arranged on the top of the compartment, the fire-fighting lance, the fire-fighting hose, the electromagnetic valve and the water storage tank form a fire-fighting system, and meanwhile an audible and visual alarm is used for sending out an audible and visual signal when an abnormal condition is detected.

Description

Technical Field

[0001] The present invention relates to the technical field of patrol vehicles, in particular to a fire rescue patrol vehicle for urban rail transit. Background Art

[0002] A patrol vehicle is a vehicle specially designed for patrol tasks. It integrates a variety of advanced technologies and equipment and can conduct patrol inspections in different environments according to set routes and requirements. In urban rail transit, subway operations focus on safety and punctuality, and have gradually become the first choice for urban residents to travel.

[0003] The line design of urban subways is mostly a two-way single-line design, and most of the lines are located underground. Due to limited construction space and conditions, and the influence of many factors such as urban planning and construction investment, it is impossible to design and arrange multiple distribution lines or auxiliary lines like ground railways. Therefore, after an accident occurs in a certain rail train, other normal trains cannot be organized to pass or detour like railway traffic organization, which leads to blockage of operating lines and failure to rescue in time, causing huge economic losses and bad social impacts. Therefore, an urban rail transit fire rescue inspection vehicle is proposed to improve the above situation. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an urban rail transit fire rescue inspection vehicle to solve the problem of being unable to provide timely rescue after an accident occurs on a rail train.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an urban rail transit fire rescue inspection vehicle, comprising a carriage, wherein the four corners of the carriage are fixedly connected with a second electric pan-tilt platform, one end of the second electric pan-tilt platform is provided with a high-definition camera, one side of the top of the carriage is fixedly connected with a smoke sensor, the other side of the top of the carriage is fixedly connected with a mounting plate, the top of the mounting plate is installed with a pantograph, the bottom of the carriage is symmetrically fixedly connected with a connection box, the side away from the connection box is provided with an audio acquisition device, the bottom of the carriage is evenly provided with ultrasonic radar and single-line laser radar sensors, the top of the carriage is symmetrically fixedly connected with a first electric pan-tilt platform, one end of the first electric pan-tilt platform is provided with a fire hose, one end of the fire hose is fixedly connected with a fire hose, an electromagnetic valve is installed on the top of the fire hose, the end of the fire hose away from the fire hose is fixedly connected with a water tank, and an audible and visual alarm is fixedly provided on the top of the carriage.

[0006] Preferably, a control console is provided at the bottom of the inner wall of the carriage, seats are fixedly connected to both sides of the inner wall of the carriage, a fire extinguisher is connected to one side of the bottom of the inner wall of the carriage, and lighting lamps are symmetrically fixedly connected to the top of the inner wall of the carriage.

[0007] Preferably, the bottom of the water tank is fixedly connected to the other side of the bottom of the inner wall of the carriage, the top of the water tank is fixedly connected to a connecting plate, one side of the top of the connecting plate is fixedly connected to a medical bed, the other side of the top of the connecting plate is connected to a defibrillator, the side of the top of the connecting plate away from the defibrillator is connected to a ventilator, and a folding stretcher is provided on the side of the top of the connecting plate away from the medical bed.

[0008] Preferably, a driving motor is fixedly provided on one side of the inner wall of the connecting box, a first pulley is fixedly provided on the output end of the driving motor, a belt is provided on the outer wall of the first pulley, a second pulley is connected to the inner wall of the belt, a wheel axle is fixedly connected to the middle part of the second pulley, and track wheels are evenly fixedly connected to both ends of the wheel axle.

[0009] Preferably, a battery compartment is provided inside the carriage, a spare battery is provided in the battery compartment inside the carriage, doors are installed on the front and rear sides of the carriage, observation windows are evenly provided on the outer wall of the carriage, and lights are installed on the left and right sides of the carriage.

[0010] A rail flaw detection method for a fire rescue inspection vehicle for urban rail transit comprises the following steps:

[0011] S1. Acoustic flaw detection: Use the ultrasonic radar on the inspection vehicle to transmit ultrasonic signals to the track and receive the reflected signals. The nature and size of the internal defects of the track are determined by analyzing the amplitude, sound speed, main frequency and waveform changes of the reflected signals. Combined with the B-display image, the type and location of the track damage are identified. At the same time, the normal structural waveform data of the track is collected to train the YOLO neural network model. The real-time track waveform data is input into the trained model to filter out the complete set of damaged waveforms. The complete set of damaged waveforms is processed using an image processing algorithm to obtain the mileage and depth information of suspected defects.

[0012] S2, Audio flaw detection: Use the audio acquisition equipment on the inspection vehicle to collect wheel-rail vibration noise data, enhance the audio data through high-pitched conversion, extract the short-time average energy, short-time average zero-crossing rate, 1 / 3 octave spectrum sound pressure and MFCC feature vector of the enhanced audio data, input its vector into the pre-established and trained XGboost model, and judge the defects of the track based on the model output;

[0013] S3, auxiliary flaw detection: start the single-line laser radar sensor on the inspection vehicle to collect track point cloud data, detect the key points on the top of the rail according to the occlusion characteristics of the track to the surrounding environment and the height jump, build a track cross-section model and match to determine the final track position, and use Kalman filtering to associate the detection points on the top of the rail; at the same time, use the camera to collect track images, use the deep learning target detection algorithm to identify the track surface information in the image, combine the information obtained by the infrared rangefinder, temperature and humidity sensor with the audio flaw detection results and the acoustic flaw detection results to perform data fusion, and determine the type and location of faults and potential faults through the decision fusion model

[0014] Preferably, in the step S1 of using an image processing algorithm to process the entire set of damage waveforms to obtain mileage and depth information of suspected diseases, the image processing algorithm includes an edge detection algorithm, a gray-level co-occurrence matrix calculation, and a Fourier transform, wherein the edge detection algorithm is used to extract the edge contour of the damaged area, the gray-level co-occurrence matrix calculation is used to obtain the texture features of the damaged area, the Fourier transform is used to analyze the frequency domain features to determine the damage depth, and the damage depth d and the propagation speed v of the ultrasonic wave in the track and the time difference t of the ultrasonic wave from transmission to reception through the damaged area satisfy the relationship d=v×t.

[0015] Preferably, in step S2, the wheel-rail vibration noise data is collected by using an audio collection device, and in the step of enhancing the audio data by using a high-pitched conversion method, the high-pitched conversion method is calculated by the formula y(n)=x(n)×a n Where x(n) is the original audio signal, y(n) is the transformed audio signal, a is the pitch conversion factor, and n is the sampling point number.

[0016] Preferably, in step S2, the vector is input into a pre-established and trained XGboost model, and in the step of judging whether the track has defects according to the model output, the objective function of the XGboost model is: in is the loss function, measuring the predicted value and the true value y i The difference between Ω(f k ) is the regularization term, and K is the number of decision trees.

[0017] Preferably, in the step S3 of capturing a track image using a camera and identifying track surface information in the image using a deep learning target detection algorithm, the output of the deep learning target detection algorithm is O(x, y, c, p), wherein x and y are the coordinates of the detection target in the image, c is the category of the detection target, and p is the confidence level of the detection target.

[0018] Working principle: The driving motor drives the first pulley and the belt, and then drives the second pulley to rotate, and then the rail wheels at both ends of the axle rotate, so that the inspection vehicle moves on the track. The control console provides operators with a platform to control vehicle operation and equipment operation. The ultrasonic radar transmits ultrasonic signals to the track and receives reflected signals. The audio acquisition equipment is used to collect wheel-rail vibration and noise data. The single-line laser radar sensor is used to collect track point cloud data. Therefore, the rail vehicle can perform all-round flaw detection on the track. Through the second electric pan-tilt head and high-definition camera, It can capture the surrounding environment of the carriage in all directions and angles, so as to monitor the track and surrounding conditions in real time. The smoke sensor can detect the smoke concentration in the carriage and the surrounding environment in real time and issue an alarm in time. The first electric pan / tilt symmetrically arranged on the top of the carriage and the fire hose, fire hose, solenoid valve and water tank constitute a fire protection system. At the same time, the sound and light alarm will send out sound and light signals when an abnormal situation is detected. Medical beds, defibrillators, ventilators and folding stretchers are arranged on the connecting board to form a medical rescue area. The inspection vehicle integrates fire rescue, medical rescue and track flaw detection, which enhances its practicality.

[0019] The present invention provides a fire rescue inspection vehicle for urban rail transit, which has the following beneficial effects:

[0020] 1. The present invention detects the smoke concentration in the carriage and the surrounding environment in real time through the smoke sensor, and issues an alarm in time. The fire protection system is formed by the first electric pan / tilt symmetrically arranged on the top of the carriage, a fire hose, a solenoid valve and a water tank. At the same time, the sound and light alarm sends out sound and light signals when an abnormal situation is detected, thereby improving the speed of emergency response. A medical bed, a defibrillator, a ventilator and a folding stretcher are arranged on the connecting plate to form a medical rescue area, thereby solving the problem of being unable to provide timely rescue after an accident occurs in a rail train.

[0021] 2. The present invention transmits ultrasonic signals to the track through ultrasonic radar and receives reflected signals, uses audio acquisition equipment to collect wheel-rail vibration noise data, and collects track point cloud data through a single-line laser radar sensor, so that the track can be fully inspected by a rail vehicle, thereby enhancing the practicality of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a schematic diagram of the front right side structure of the present invention;

[0023] Figure 2 It is a schematic diagram of the front end bottom side structure of the present invention;

[0024] Figure 3 It is a schematic diagram of the internal structure of the carriage of the present invention;

[0025] Figure 4It is a schematic diagram of the local structure of the control console of the present invention;

[0026] Figure 5 It is a schematic diagram of the local structure of the driving motor of the present invention;

[0027] Figure 6 The present invention provides a flow chart of a method for detecting rail flaws in an urban rail transit fire rescue inspection vehicle.

[0028] Among them, 1. Carriage; 2. Track wheel; 3. Observation window; 4. Door; 5. Mounting plate; 6. Pantograph; 7. First electric pan-tilt head; 8. Fire hose; 9. Fire hose; 10. Solenoid valve; 11. Sound and light alarm; 12. Smoke sensor; 13. High-definition camera; 14. Second electric pan-tilt head; 15. Headlight; 16. Connection box; 17. Audio acquisition equipment; 18. Seat; 19. Control panel; 20. Fire extinguisher; 21. Backup battery; 22. Lighting; 23. Single-line laser radar sensor; 24. Ultrasonic radar; 25. Water tank; 26. Connection plate; 27. Medical bed; 28. Defibrillator; 29. ​​Respirator; 30. Folding stretcher; 31. Battery compartment; 32. Drive motor; 33. First pulley; 34. Belt; 35. Second pulley; 36. Axle. DETAILED DESCRIPTION

[0029] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] Example:

[0031] Please see attached Figure 1 -Attached Figure 5The embodiment of the present invention provides an urban rail transit fire rescue inspection vehicle, including a carriage 1, the four corners of the carriage 1 are fixedly connected with a second electric pan-tilt platform 14, one end of the second electric pan-tilt platform 14 is provided with a high-definition camera 13, one side of the top of the carriage 1 is fixedly connected with a smoke sensor 12, the other side of the top of the carriage 1 is fixedly connected with a mounting plate 5, the top of the mounting plate 5 is installed with a pantograph 6, the bottom of the carriage 1 is symmetrically fixedly connected with a connection box 16, the side away from the connection box 16 is provided with an audio acquisition device 17, the bottom of the carriage 1 is evenly provided with an ultrasonic radar 24 and a single-line laser radar sensor 23, the top of the carriage 1 is symmetrically fixedly connected with a first electric pan-tilt platform 7, one end of the first electric pan-tilt platform 7 is provided with a fire hose 8, one end of the fire hose 8 is fixedly connected with a fire hose 9, the top of the fire hose 9 is installed with a solenoid valve 10, the end of the fire hose 9 away from the fire hose 8 is fixedly connected with a water storage tank 25, and the top of the carriage 1 is fixedly provided with an audible and visual alarm 11.

[0032] Specifically, the second electric pan-tilt platform 14 and the high-definition camera 13 are arranged at the four corners of the carriage 1. Through the flexible rotation of the second electric pan-tilt platform 14, the high-definition camera 13 can shoot the surrounding environment of the carriage in all directions and at multiple angles, so as to monitor the track and the surrounding conditions in real time, and timely discover possible safety hazards, such as foreign objects on the track, personnel intrusion, etc., and realize visual monitoring of the track environment;

[0033] The smoke sensor 12 can detect the smoke concentration in the car and the surrounding environment in real time, so that the smoke signal can be quickly sensed at the initial stage of the fire, and the alarm can be issued in time to buy precious time for the evacuation of personnel and the fire fighting. The first electric pan-tilt platform 7 symmetrically arranged on the top of the car 1 and the fire hose 8, the fire hose 9, the solenoid valve 10 and the water storage tank 25 constitute a fire fighting system. The spray angle of the fire hose 8 is adjusted by the first electric pan-tilt platform 7. Combined with the water source provided by the water storage tank 25, when a fire occurs, water can be quickly transported to the fire source for fire fighting. The solenoid valve 10 can control the flow of water, so as to achieve precise fire fighting and effectively deal with rail fires. At the same time, the sound and light alarm 11 sends out sound and light signals when abnormal conditions (such as fire, rail failure, etc.) are detected, so as to warn the surrounding personnel to pay attention to safety and assist the personnel to quickly locate the accident scene, thereby realizing effective reminders to the surrounding personnel, improving the speed of emergency response, and solving the problem of being unable to rescue in time after an accident on a rail train.

[0034] The ultrasonic radar 24 transmits ultrasonic signals to the track and receives reflected signals, the audio acquisition device 17 collects wheel-rail vibration noise data, and the single-line laser radar sensor 23 collects track point cloud data, so as to detect defects on the track, thereby enhancing the practicality of the inspection vehicle.

[0035] Please see attached Figure 1 -Attached Figure 5 A control console 19 is provided at the bottom of the inner wall of the carriage 1, seats 18 are fixedly connected to both sides of the inner wall of the carriage 1, a fire extinguisher 20 is connected to one side of the bottom of the inner wall of the carriage 1, and a lighting lamp 22 is symmetrically fixedly connected to the top of the inner wall of the carriage 1; the bottom of the water tank 25 is fixedly connected to the other side of the bottom of the inner wall of the carriage 1, and the top of the water tank 25 is fixedly connected to a connecting plate 26, one side of the top of the connecting plate 26 is fixedly connected to a medical bed 27, the other side of the top of the connecting plate 26 is connected to a defibrillator 28, a ventilator 29 is connected to the top side of the connecting plate 26 away from the defibrillator 28, and a folding stretcher 30 is provided on the top side of the connecting plate 26 away from the medical bed 27.

[0036] Specifically, the control console 19 is arranged at the bottom of the inner wall of the carriage 1, providing a platform for the operator to control the operation of the vehicle and the operation of the equipment. The fire extinguisher 20 is connected to one side of the bottom of the inner wall of the carriage, and can be quickly used for extinguishing the fire in the early stage of the fire or a small-scale fire. A medical bed 27, a defibrillator 28, a ventilator 29 and a folding stretcher 30 are arranged on the connecting plate 26 to form a medical rescue area. When an accident occurs and causes injuries to people, these devices can be used to provide on-site medical treatment and emergency treatment to the injured, such as using a defibrillator to provide first aid to patients with cardiac arrest and ventilator-assisted breathing, etc., thereby improving the survival rate of the injured.

[0037] Please see attached Figure 1 -Attached Figure 5 A driving motor 32 is fixedly provided on one side of the inner wall of the connecting box 16, a first pulley 33 is fixedly provided on the output end of the driving motor 32, a belt 34 is provided on the outer wall of the first pulley 33, a second pulley 35 is connected to the inner wall of the belt 34, a wheel axle 36 is fixedly connected to the middle of the second pulley 35, and both ends of the wheel axle 36 are evenly fixedly connected to the track wheel 2; a battery compartment 31 is provided inside the carriage 1, a spare battery 21 is provided in the battery compartment 31 inside the carriage 1, doors 4 are installed on the front and rear sides of the carriage 1, observation windows 3 are evenly provided on the outer wall of the carriage 1, and lights 15 are installed on the left and right sides of the carriage 1.

[0038] Specifically, by driving the motor 32, the first pulley 33 and the belt 34 are driven to rotate, and at the same time, the second pulley 35 is driven to rotate, and then the track wheels 2 at both ends of the axle 36 are rotated, thereby realizing the movement of the inspection vehicle on the track, and the inspection vehicle travels according to the predetermined route. The backup battery 21 in the battery compartment 31 provides emergency power for the vehicle when there is no external power supply or the power supply is abnormal, thereby ensuring the normal operation of the vehicle's key equipment (such as lighting, communication, and some detection equipment).

[0039] Please see attached Figure 6 , a rail flaw detection method for a fire rescue inspection vehicle for urban rail transit, comprising the following steps:

[0040] S1. Acoustic flaw detection: Use the ultrasonic radar 24 on the inspection vehicle to transmit ultrasonic signals to the track and receive reflected signals. By analyzing the amplitude, sound speed, main frequency and waveform changes of the reflected signals, the nature and size of the internal defects of the track are determined. Combined with the B-display image, the type and location of the track damage are determined. At the same time, the normal structural waveform data of the track is collected to train the YOLO neural network model. The real-time track waveform data is input into the trained model to filter out the complete set of damaged waveforms, and the complete set of damaged waveforms is processed using an image processing algorithm to obtain the mileage and depth information of suspected defects.

[0041] Specifically, the ultrasonic radar 24 transmits ultrasonic signals to the track and receives reflected signals. By utilizing the differences in the propagation characteristics of ultrasonic waves in different media, and based on the amplitude, sound velocity, main frequency and waveform changes of the reflected signals, analysts can determine the nature and size of internal defects in the track. Combined with the B-display image, the type and location of track damage can be intuitively determined, thereby achieving high-precision detection of the internal structure of the track.

[0042] S2, audio flaw detection: The wheel-rail vibration noise data is collected by using the audio acquisition device 17 on the inspection vehicle, and the audio data is enhanced by high-pitched conversion. The short-time average energy, short-time average zero-crossing rate, 1 / 3 octave spectrum sound pressure and MFCC feature vector of the enhanced audio data are extracted, and the vector is input into the pre-established and trained XGboost model, and the defects of the track are judged according to the model output;

[0043] Specifically, the wheel-rail vibration noise data is collected using the audio acquisition device 17. Since the vibration noise characteristics of the track are different in different states (normal or defective), the audio data is enhanced by high-pitch conversion, which can expand the data sample size and improve the generalization ability of the model. The short-time average energy, short-time average zero-crossing rate, 1 / 3 octave spectrum sound pressure and MFCC feature vectors of the enhanced audio data are extracted, and these feature vectors are input into the pre-established and trained XGboost model. The defects of the track are judged according to the model output, thereby realizing rapid and accurate judgment of the track status using audio features.

[0044] S3, auxiliary flaw detection: start the single-line laser radar sensor 23 on the inspection vehicle to collect track point cloud data, detect the key points on the rail top according to the occlusion characteristics of the track to the surrounding environment and the height jump, build a track cross-section model and match to determine the final track position, and use Kalman filtering to associate the rail top detection points; at the same time, use the camera to collect track images, use the deep learning target detection algorithm to identify the track surface information in the image, combine the information obtained by the infrared rangefinder, temperature and humidity sensor, and the audio flaw detection results and acoustic flaw detection results to perform data fusion, and determine the type and location of faults and potential faults through the decision fusion model.

[0045] Specifically, the track point cloud data is collected by a single-line laser radar sensor 23, the key points of the track top are detected according to the occlusion characteristics of the track to the surrounding environment and the height jump, the track cross-section model is constructed and matched to determine the final track position, and the Kalman filter is used to associate the track top detection points, so as to accurately obtain the geometric shape and position information of the track, and realize high-precision modeling and real-time monitoring of the track structure.

[0046] In the step of using an image processing algorithm to process the entire set of damage waveforms to obtain mileage and depth information of suspected diseases in step S1, the image processing algorithm includes an edge detection algorithm, gray-level co-occurrence matrix calculation, and Fourier transform, wherein the edge detection algorithm is used to extract the edge contour of the damaged area, the gray-level co-occurrence matrix calculation is used to obtain the texture features of the damaged area, and the Fourier transform is used to analyze the frequency domain features to determine the damage depth, and the damage depth d satisfies the relationship d=v×t with the propagation speed v of the ultrasonic wave in the track and the time difference t of the ultrasonic wave from transmission to reception through the damaged area.

[0047] In step S2, the wheel-rail vibration noise data is collected by using an audio collection device, and the audio data is enhanced by using a high-pitched conversion method. The high-pitched conversion method is calculated by the formula y(n)=x(n)×a n Where x(n) is the original audio signal, y(n) is the transformed audio signal, a is the pitch conversion factor, and n is the sampling point number.

[0048] In step S2, its vector is input into the pre-established and trained XGboost model. In the step of judging whether the track has defects according to the model output, the objective function of the XGboost model is: in is the loss function, measuring the predicted value and the true value y i The difference between Ω(f k ) is the regularization term, and K is the number of decision trees.

[0049] In step S3, a track image is captured by a camera, and a deep learning target detection algorithm is used to identify the track surface information in the image. The output of the deep learning target detection algorithm is O(x, y, c, p), where x and y are the coordinates of the detection target in the image, c is the category of the detection target, and p is the confidence level of the detection target.

[0050] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An urban rail transit fire rescue inspection vehicle, comprising a carriage (1), characterized in that: The four corners of the carriage (1) are all fixedly connected to a second electric pan-tilt platform (14), one end of the second electric pan-tilt platform (14) is provided with a high-definition camera (13), one side of the top of the carriage (1) is fixedly connected to a smoke sensor (12), the other side of the top of the carriage (1) is fixedly connected to a mounting plate (5), the top of the mounting plate (5) is provided with a pantograph (6), the bottom of the carriage (1) is symmetrically fixedly connected to a connection box (16), the side of the connection box (16) away from the connection box (16) is provided with an audio collection device (17), and the Ultrasonic radars (24) and single-line laser radar sensors (23) are evenly arranged at the bottom, a first electric pan-tilt platform (7) is symmetrically fixedly connected to the top of the carriage (1), a fire hose (8) is arranged at one end of the first electric pan-tilt platform (7), a fire hose (9) is fixedly connected to one end of the fire hose (8), a solenoid valve (10) is installed on the top of the fire hose (9), and a water tank (25) is fixedly connected to one end of the fire hose (9) away from the fire hose (8), and a sound and light alarm (11) is fixedly arranged on the top of the carriage (1).

2. The urban rail transit fire rescue inspection vehicle according to claim 1, characterized in that: A control console (19) is provided at the bottom of the inner wall of the carriage (1), seats (18) are fixedly connected to both sides of the inner wall of the carriage (1), a fire extinguisher (20) is connected to one side of the bottom of the inner wall of the carriage (1), and a lighting lamp (22) is symmetrically fixedly connected to the top of the inner wall of the carriage (1).

3. The urban rail transit fire rescue inspection vehicle according to claim 1, characterized in that: The bottom of the water storage tank (25) is fixedly connected to the other side of the bottom of the inner wall of the carriage (1); the top of the water storage tank (25) is fixedly connected to a connecting plate (26); one side of the top of the connecting plate (26) is fixedly connected to a medical bed (27); the other side of the top of the connecting plate (26) is connected to a defibrillator (28); the side of the top of the connecting plate (26) away from the defibrillator (28) is connected to a ventilator (29); and the side of the top of the connecting plate (26) away from the medical bed (27) is provided with a folding stretcher (30).

4. The urban rail transit fire rescue inspection vehicle according to claim 1, characterized in that: A driving motor (32) is fixedly arranged on one side of the inner wall of the connection box (16); a first pulley (33) is fixedly arranged on the output end of the driving motor (32); a belt (34) is arranged on the outer wall of the first pulley (33); a second pulley (35) is connected to the inner wall of the belt (34); a wheel shaft (36) is fixedly connected to the middle of the second pulley (35); and track wheels (2) are evenly fixedly connected to both ends of the wheel shaft (36).

5. The urban rail transit fire rescue inspection vehicle according to claim 1, characterized in that: A battery compartment (31) is provided inside the carriage (1), a spare battery (21) is provided in the battery compartment (31) inside the carriage (1), doors (4) are installed on both the front and rear sides of the carriage (1), observation windows (3) are evenly provided on the outer wall of the carriage (1), and lights (15) are installed on both the left and right sides of the carriage (1).

6. A rail flaw detection method for a fire rescue inspection vehicle for urban rail transit, characterized in that: An urban rail transit fire rescue inspection vehicle applied to any one of claims 1 to 5 comprises the following steps: S1. Acoustic flaw detection: using the ultrasonic radar (24) on the inspection vehicle to transmit ultrasonic signals to the track and receive reflected signals, the nature and size of internal defects of the track are determined by analyzing the amplitude, sound velocity, main frequency and waveform change of the reflected signals, and the type and location of the track damage are determined by combining the B-display image; at the same time, the normal structural waveform data of the track is collected to train the YOLO neural network model, the real-time collected track waveform data is input into the trained model to filter out the complete set of damaged waveforms, and the complete set of damaged waveforms is processed by using an image processing algorithm to obtain the mileage and depth information of the suspected defects; S2, audio flaw detection: using the audio acquisition device (17) on the inspection vehicle to collect wheel-rail vibration noise data, the audio data is enhanced by high-frequency conversion, the short-time average energy, short-time average zero-crossing rate, 1 / 3 octave spectrum sound pressure and MFCC feature vector of the enhanced audio data are extracted, and the vector is input into the pre-established and trained XGboost model, and the defects of the track are judged according to the model output; S3, auxiliary flaw detection: start the single-line laser radar sensor (23) on the inspection vehicle to collect track point cloud data, detect the key points on the rail top according to the occlusion characteristics of the track to the surrounding environment and the height jump, build a track cross-section model and match to determine the final track position, and use Kalman filtering to associate the rail top detection points; at the same time, use the camera to collect track images, use the deep learning target detection algorithm to identify the track surface information in the image, combine the information obtained by the infrared rangefinder, temperature and humidity sensor with the audio flaw detection results and the acoustic flaw detection results to perform data fusion, and determine the type and location of faults and potential faults through the decision fusion model.

7. A rail flaw detection method for an urban rail transit fire rescue inspection vehicle according to claim 6, characterized in that: In the step S1 of using an image processing algorithm to process the entire set of damage waveforms to obtain mileage and depth information of suspected diseases, the image processing algorithm includes an edge detection algorithm, gray-level co-occurrence matrix calculation, and Fourier transform, wherein the edge detection algorithm is used to extract the edge contour of the damaged area, the gray-level co-occurrence matrix calculation is used to obtain the texture features of the damaged area, and the Fourier transform is used to analyze the frequency domain features to determine the damage depth, and the damage depth d and the propagation speed ν of the ultrasonic wave in the track and the time difference t of the ultrasonic wave from transmission to reception through the damaged area satisfy the relationship d=ν×t.

8. A rail flaw detection method for a fire rescue inspection vehicle for urban rail transit according to claim 6, characterized in that: In the step S2, the wheel-rail vibration noise data is collected by using an audio collection device, and in the step of enhancing the audio data by using a high-pitched conversion method, the high-pitched conversion method is calculated by the formula y(n)=x(n)×a n Where x(n) is the original audio signal, y(n) is the transformed audio signal, a is the pitch conversion factor, and n is the sampling point number.

9. A rail flaw detection method for a fire rescue inspection vehicle for urban rail transit according to claim 6, characterized in that: In step S2, the vector is input into the pre-established and trained XGboost model. In the step of judging whether the track has defects according to the model output, the objective function of the XGboost model is: in is the loss function, measuring the predicted value and the true value y i The difference between Ω(f k ) is the regularization term, and K is the number of decision trees.

10. A rail flaw detection method for a fire rescue inspection vehicle for urban rail transit according to claim 6, characterized in that: In the step S3 of capturing a track image using a camera and identifying track surface information in the image using a deep learning target detection algorithm, the output of the deep learning target detection algorithm is O(x, y, c, p), where x and y are the coordinates of the detection target in the image, c is the category of the detection target, and p is the confidence level of the detection target.

Images