A warning system and device for a shield tunnel battery car

Abstract

The application provides a warning system and device for a shield tunnel electric vehicle, wherein the warning system comprises a monitoring sensor subsystem, a data transmission subsystem, a data processing subsystem, a safety warning subsystem and an auxiliary support subsystem; the monitoring sensor subsystem is used for calculating the real-time position of the electric vehicle, measuring the real-time speed and mileage of the electric vehicle and collecting real-time images of the driving environment; the data processing subsystem is used for determining the real-time distance between the electric vehicle and the tunnel opening based on the data collected by the monitoring sensor subsystem, identifying whether there are obstacles and / or pedestrians around the electric vehicle based on the real-time images and controlling the safety warning subsystem to display and warn the driving state of the electric vehicle. The application can realize the positioning of the electric vehicle, identify the obstacles and pedestrians in the driving environment of the electric vehicle, prompt and warn the driving state of the electric vehicle, reduce the hidden dangers of the electric vehicle overspeed and visual blind area and improve the efficiency and safety of tunnel operation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of traffic safety warning, in particular to a warning system and device for shield tunnel battery car. BACKGROUND

[0002] In the tunnel operation, shield tunnel battery car is usually used to transport building materials, for example, in the segment assembly and muck transportation link, shield tunnel battery car is used to transport segments and muck.

[0003] In practice, when driving the shield tunnel battery car, the driver's driving vision is not open because the track of the shield tunnel battery car is usually winding and the lighting condition in the tunnel is limited. In addition, the battery car has large volume and mass, resulting in large running inertia. When there are pedestrians or sundries in front of the battery car, the battery car is prone to have extended braking distance or coasting phenomenon, causing construction accidents and affecting construction progress.

[0004] Therefore, there is an urgent need for a warning system for shield tunnel battery car to warn the running state and running environment of the battery car. SUMMARY

[0005] Therefore, the purpose of the embodiments of the present application is to provide a warning system and device for shield tunnel battery car, which processes the monitored real-time position, real-time speed, and real-time image of the running environment of the shield tunnel battery car, realizes the positioning of the battery car, the identification of obstacles and pedestrians in the running environment of the battery car, and the real-time prompt and warning of the running state of the battery car, reduces the hidden dangers of shield tunnel battery car overspeed and visual blind area, and improves the efficiency and safety of tunnel operation.

[0006] In a first aspect, the embodiments of the present application provide a warning system for shield tunnel battery car, which comprises a monitoring sensor subsystem, a data transmission subsystem, a data processing subsystem, a safety warning subsystem, and an auxiliary support subsystem; the monitoring sensor subsystem is connected with the data processing subsystem through the data transmission subsystem, the data processing subsystem is connected with the safety warning subsystem through the data transmission subsystem, and the monitoring sensor subsystem, the data transmission subsystem, the data processing subsystem, the safety warning subsystem, and the auxiliary support subsystem are all connected with a construction center through a data communication network;

[0007] The monitoring sensor subsystem comprises a vehicle-mounted positioning sensor, a portal positioning sensor, a speed measuring sensor and a monitoring camera; wherein the vehicle-mounted positioning sensor is fixed on the front of the shield tunnel electric car in a way of roof magnetic attraction using two strong magnets below the shell of the vehicle-mounted positioning sensor; the portal positioning sensor is installed on the segment by bolts, comprising a first portal positioning sensor installed in the tunnel portal area and second fixed portal positioning sensors uniformly distributed in other positions of the tunnel, and the vehicle-mounted positioning sensor and the portal positioning sensor are provided with a uwb receiver, and the fixed portal positioning sensors are connected through the uwb receiver;

[0008] The vehicle-mounted positioning sensor is configured to obtain a positioning signal of the portal positioning sensor through communication with the portal positioning sensor, and calculate a real-time position of the shield tunnel electric car based on the positioning signal.

[0009] The speed measuring sensor is installed at the wheel part of the shield tunnel electric car, and is configured to measure a real-time speed and a mileage of the shield tunnel electric car.

[0010] The monitoring camera is installed in front of, behind, left of and right of the shield tunnel electric car in a way of roof magnetic attraction or side attraction of the vehicle body, and is configured to collect real-time images in each specified shooting area.

[0011] The data processing subsystem is configured to receive the real-time position, the real-time speed, the mileage, the real-time images of the shield tunnel electric car and the positioning signal of the portal positioning sensor sent by the monitoring sensor subsystem through the data transmission subsystem, determine a real-time distance between the shield tunnel electric car and the portal based on the real-time position, the real-time speed and the positioning signal, identify whether there are obstacles and / or pedestrians around the shield tunnel electric car based on the real-time images, and send the real-time position, the real-time speed, the mileage, the real-time images, the identification result of the real-time images, the real-time distance, and the first control command corresponding to the real-time speed and the identification result of the real-time images to the safety warning subsystem, so that the safety warning subsystem displays and warns the driving state of the shield tunnel electric car.

[0012] In a possible implementation, the safety warning subsystem comprises a data display platform and a warning platform, and the data display platform and the warning platform are connected with the construction center through a data communication network.

[0013] The data display platform is configured to display the received real-time position, real-time speed, mileage, real-time images, identification result of real-time images and real-time distance.

[0014] The early warning platform is used for early warning of the driving state of the shield tunnel battery car based on receiving the first control instruction corresponding to the identification result of the real-time speed and the real-time image.

[0015] In a possible implementation, the auxiliary support subsystem includes a vehicle-mounted alarm device, power distribution and an uninterruptible power supply, and the vehicle-mounted alarm device, the power distribution and the uninterruptible power supply are all installed on the shield tunnel battery car.

[0016] The data processing subsystem is further configured to send a second control instruction corresponding to the identification result of the real-time speed and the real-time image to the vehicle-mounted alarm device.

[0017] The vehicle-mounted alarm device is configured to issue an audible and visual alarm after receiving the second control instruction.

[0018] In a possible implementation, the vehicle-mounted positioning sensor and the portal positioning sensor are connected with the data transmission subsystem through the uwb receiver, the uwb receiver is provided with a receiver antenna, the receiver antenna is matched with the data transmission subsystem, and the speed measurement sensor and the monitoring camera are connected with the data transmission subsystem through a data communication cable.

[0019] In a possible implementation, the data transmission subsystem includes a cable communication module and a data communication network module, the communication mode of the cable communication module is a coaxial cable communication mode, the communication mode of the data communication network module is an Ethernet communication mode, the vehicle-mounted positioning sensor, the portal positioning sensor, the speed measurement sensor and the monitoring camera are connected with the data communication network module through the uwb receiver and the data communication cable respectively, the uwb receiver communicates with the data processing subsystem through the data communication network module, and the data processing subsystem communicates with the safety early warning subsystem and the shield machine cab through the data communication network module.

[0020] In a possible implementation, the safety early warning subsystem includes a display screen, a PC terminal and a mobile terminal.

[0021] The safety early warning subsystem is further configured to store the received information in a database, find information matched with a query instruction sent by a first query terminal from the database after receiving the query instruction, and send the found information to the first query terminal; and / or export the information stored in the database to a second query terminal after receiving an export instruction sent by the second query terminal.

[0022] In a possible implementation, the data processing subsystem is further configured to input the received real-time image into a target detection model, and send an identification result of the real-time image output by the target detection model to the safety warning subsystem.

[0023] In a possible implementation, the target detection model determines the identification result of the real-time image in the following manner:

[0024] Step 1: Preprocessing the real-time image, including: converting the color space of the real-time image, converting the real-time image into a grayscale image, and performing downsizing processing and gradient calculation on the grayscale image;

[0025] Step 2: performing operation on the preprocessed real-time image through a convolution layer that strengthens sparsity, obtaining a part detection map and marking the obstacles and / or pedestrians; converting the structure of a subsampling layer into a deformation processing layer, processing the deformation of the obstacles and / or pedestrians, and obtaining a detection score of the obstacles and / or pedestrians;

[0026] Step 3: inputting the detection score into an occlusion processing model to process the occluded obstacle and / or pedestrian data;

[0027] Step 4: inputting the processing result of the occlusion processing model into a label classification layer to determine the identification result of the real-time image.

[0028] In a possible implementation, the target detection model is trained in the following manner:

[0029] Step 1: acquiring a historical image dataset inside the tunnel by using the monitoring camera;

[0030] Step 2: labeling the obstacles and / or pedestrians included in each picture in the historical image dataset as training samples of a deep learning algorithm;

[0031] Step 3: training the target detection model based on the training samples.

[0032] In a second aspect, an early warning device for a shield tunnel electric car is provided, which includes a monitoring sensor, a data transmission module, a data processing module, a safety warning module, and an auxiliary support module. The monitoring sensor is connected to the data processing module through the data transmission module. The data processing module is connected to the safety warning module through the data transmission module. The monitoring sensor, the data transmission module, the data processing module, the safety warning module, and the auxiliary support module are all connected to a construction center through a data communication network.

[0033] The monitoring sensor comprises a vehicle-mounted positioning sensor, a portal positioning sensor, a speed measuring sensor and a monitoring camera; wherein the vehicle-mounted positioning sensor is fixed on the front of the shield tunnel electric vehicle in a way of roof magnetic attraction using two strong magnets below the shell of the vehicle-mounted positioning sensor; the portal positioning sensor is installed on the segment by bolts, comprising a first portal positioning sensor installed in the tunnel portal area and a second fixed portal positioning sensor uniformly distributed in other positions of the tunnel, and a uwb receiver is arranged on the vehicle-mounted positioning sensor and the portal positioning sensor, and the fixed portal positioning sensors are connected through the uwb receiver;

[0034] The vehicle-mounted positioning sensor is used to obtain the positioning signal of the portal positioning sensor through communication with the portal positioning sensor, and calculate the real-time position of the shield tunnel electric vehicle based on the positioning signal;

[0035] The speed measuring sensor is installed at the wheel part of the shield tunnel electric vehicle, and is used to measure the real-time speed and mileage of the shield tunnel electric vehicle;

[0036] The monitoring camera is installed in the front, rear, left and right directions of the vehicle body of the shield tunnel electric vehicle in a way of roof magnetic attraction or side attraction of the vehicle body, and is used to collect real-time images in each specified shooting area;

[0037] The data processing module is used to receive the real-time position, real-time speed, mileage, real-time images of the shield tunnel electric vehicle and the positioning signal of the portal positioning sensor sent by the monitoring sensor through the data transmission module, determine the real-time distance between the shield tunnel electric vehicle and the portal based on the real-time position, real-time speed and positioning signal, and identify whether there are obstacles and / or pedestrians around the shield tunnel electric vehicle based on the real-time images, send the real-time position, real-time speed, mileage, real-time images, identification result of the real-time images, real-time distance, and first control command corresponding to the real-time speed and identification result of the real-time images to the safety warning module, so that the safety warning module displays and warns the driving state of the shield tunnel electric vehicle.

[0038] The early warning system and device for the shield tunnel electric car provided by the embodiment of the application, wherein the early warning system comprises a monitoring sensor subsystem, a data transmission subsystem, a data processing subsystem, a safety early warning subsystem and an auxiliary support subsystem; the monitoring sensor subsystem is used for calculating the real-time position of the electric car, measuring the real-time speed and mileage of the electric car and collecting the real-time image of the driving environment; the data processing subsystem is used for determining the real-time distance between the electric car and the tunnel entrance based on the data collected by the monitoring sensor subsystem, identifying whether there are obstacles and / or pedestrians around the electric car based on the real-time image and controlling the safety early warning subsystem to display and warn the driving state of the electric car. The embodiment of the application realizes the positioning of the electric car, the identification of the obstacles and pedestrians in the driving environment of the electric car and the real-time prompting and warning of the driving state of the electric car by processing the monitored real-time position, real-time speed and real-time image of the driving environment of the shield tunnel electric car, reduces the hidden dangers of overspeed and visual blind area of the shield tunnel electric car and improves the efficiency and safety of tunnel operation.

[0039] In order to make the above objectives, characteristics and advantages of the application more apparent, clear and easy to understand, the following will specifically describe the preferred embodiments of the application with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the application, and therefore should not be regarded as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0041] Figure 1 Fig. 1 shows the structural schematic diagram of the early warning system for the shield tunnel electric car provided by the embodiment of the application;

[0042] Figure 2 Fig. 2 shows the position schematic diagram of the vehicle positioning sensor and the tunnel entrance positioning sensor in the early warning system provided by the embodiment of the application;

[0043] Figure 3 Fig. 3 shows the flowchart of the real-time image identification by the target detection model provided by the embodiment of the application;

[0044] Figure 4 Fig. 4 shows the flowchart of the training of the target detection model provided by the embodiment of the application;

[0045] Figure 5 Fig. 5 shows the structural schematic diagram of the early warning device for the shield tunnel electric car provided by the embodiment of the application. DETAILED DESCRIPTION

[0046] To make the purposes, technical solutions, and advantages of the embodiments of the present application clearer, the following will be combined with the accompanying drawings in the embodiments of the present application to make a clear and complete description of the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work belong to the scope of protection of the present application.

[0047] Currently, when tunnel operation is performed, shield tunnel electric vehicles are usually used to transport building materials, for example, shield tunnel electric vehicles are used to transport segments and carry out muck transportation.

[0048] In practice, when a driver drives a shield tunnel electric vehicle, since the tracks on which the shield tunnel electric vehicle travels are usually winding and tortuous, combined with the limited lighting conditions in the tunnel, the driver's driving vision is not wide, and the electric vehicle has a large volume and mass, resulting in a large driving inertia. When there are pedestrians or sundries in front of the electric vehicle, the electric vehicle is prone to have a prolonged braking distance or a coasting phenomenon, causing a construction accident and affecting the construction progress.

[0049] Therefore, there is an urgent need for a warning system for a shield tunnel electric vehicle to warn the driving state and the driving environment of the electric vehicle.

[0050] Based on the above problems, the embodiments of the present application provide a warning system and device for a shield tunnel electric vehicle, wherein the warning system comprises a monitoring sensor subsystem, a data transmission subsystem, a data processing subsystem, a safety warning subsystem, and an auxiliary support subsystem. The monitoring sensor subsystem is used to calculate the real-time position of the electric vehicle, measure the real-time speed and mileage of the electric vehicle, and collect real-time images of the driving environment. The data processing subsystem is used to determine the real-time distance between the electric vehicle and the tunnel opening based on the data collected by the monitoring sensor subsystem, and to identify whether there are obstacles and / or pedestrians around the electric vehicle based on the real-time images, and to control the safety warning subsystem to display and warn the driving state of the electric vehicle. The embodiments of the present application process the monitored real-time position, real-time speed, and real-time images of the driving environment of the shield tunnel electric vehicle, realize the positioning of the electric vehicle, the identification of obstacles and pedestrians in the driving environment of the electric vehicle, and the real-time prompting and warning of the driving state of the electric vehicle, reduce the hidden dangers of overspeed and visual blind area of the shield tunnel electric vehicle, and improve the efficiency and safety of tunnel operation.

[0051] The above-mentioned defects are the results of the inventors' practice and careful research, and thus the discovery process of the above-mentioned problems and the solutions proposed by the present application below should be the contributions of the inventors to the present application.

[0052] The technical solutions in the present application will be described clearly and completely below in conjunction with the accompanying drawings in the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. The components of the present application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0053] It should be noted that similar reference numerals and letters represent similar items in the following drawings, and thus, once an item is defined in one drawing, it need not be further defined and explained in subsequent drawings.

[0054] In order to facilitate the understanding of the present embodiment, first, a kind of early warning system for shield tunnel electric car disclosed in the embodiments of the present application is introduced in detail.

[0055] Referring to Figure 1 As shown in the drawings, Figure 1 A structure schematic view of an early warning system for shield tunnel electric car provided by the embodiments of the present application is shown, which comprises a monitoring sensor subsystem 101, a data transmission subsystem 102, a data processing subsystem 103, a safety warning subsystem 104 and an auxiliary support subsystem 105; the monitoring sensor subsystem 101 is connected with the data processing subsystem 103 through the data transmission subsystem 102, the data processing subsystem 103 is connected with the safety warning subsystem 104 through the data transmission subsystem 102, and the monitoring sensor subsystem 101, the data transmission subsystem 102, the data processing subsystem 103, the safety warning subsystem 104 and the auxiliary support subsystem 105 are all connected with the construction center through a data communication network.

[0056] The monitoring sensor subsystem 101 comprises a vehicle-mounted positioning sensor, a portal positioning sensor, a speed measuring sensor and a monitoring camera; wherein the vehicle-mounted positioning sensor is fixed on the front of the shield tunnel electric car in a roof magnetic manner using two strong magnets below the shell of the vehicle-mounted positioning sensor; the portal positioning sensor is bolted on the segment, comprising a first portal positioning sensor installed in the tunnel portal area and a second fixed portal positioning sensor uniformly distributed in other positions of the tunnel, and the vehicle-mounted positioning sensor and the portal positioning sensor are provided with a uwb receiver, and the fixed portal positioning sensors are connected through the uwb receiver.

[0057] Referring to Figure 2 as shown, Figure 2 The position diagram of the vehicle-mounted positioning sensor and the portal positioning sensor in the early warning system provided by the embodiment is shown, wherein A0, A1, A2, A3 and A4 are portal positioning sensors, B0 is a shield tunnel electric car in running, C0 is a vehicle-mounted positioning sensor installed on the front of the shield tunnel electric car, two solid curves represent a tunnel through which the shield tunnel electric car passes, and a dashed curve represents a running track of the shield tunnel electric car in the tunnel.

[0058] It should be noted that the vehicle-mounted positioning sensor and the portal positioning sensor are connected with the data transmission subsystem 102 through the uwb receiver, the uwb receiver is provided with a receiver antenna, the receiver antenna is matched with the data transmission subsystem 102, and the speed measuring sensor and the monitoring camera are connected with the data transmission subsystem 102 through a data communication cable.

[0059] Further, the data transmission subsystem 102 comprises a cable communication module and a data communication network module; the communication mode of the cable communication module is a coaxial cable communication mode, and the communication mode of the data communication network module is an Ethernet communication mode; the vehicle-mounted positioning sensor, the portal positioning sensor, the speed measuring sensor and the monitoring camera are connected with the data communication network module through the uwb receiver and the data communication cable respectively; the uwb receiver communicates with the data processing subsystem through the data communication network module; and the data processing subsystem 103 communicates with the safety early warning subsystem 104 and the shield machine cab respectively through the data communication network module.

[0060] The vehicle-mounted positioning sensor is configured to acquire a positioning signal of the portal positioning sensor through communication with the portal positioning sensor, and calculate a real-time position of the shield tunnel electric car based on the positioning signal.

[0061] The speed measuring sensor is installed at a wheel part of the shield tunnel electric vehicle, and is used for measuring real-time speed and mileage of the shield tunnel electric vehicle.

[0062] The monitoring camera is installed at four directions of front, back, left and right of the shield tunnel electric vehicle body in a way of roof magnetic attraction or body side attraction, and is used for collecting real-time images in each designated shooting area.

[0063] It should be noted that the early warning system can display the surrounding situation of the shield tunnel electric vehicle in real time, and the monitoring camera installed at four directions of front, back, left and right of the shield tunnel electric vehicle body is respectively used for shield tunnel electric vehicle rear view video monitoring, pedestrian recognition and double side rear view monitoring.

[0064] The data processing subsystem 103 is used for receiving the real-time position, real-time speed, mileage, real-time image of the shield tunnel electric vehicle and the positioning signal of the hole positioning sensor sent by the monitoring sensor subsystem 101 through the data transmission subsystem 102, determining the real-time distance between the shield tunnel electric vehicle and the hole based on the real-time position, the real-time speed and the positioning signal, identifying whether there is an obstacle and / or a pedestrian around the shield tunnel electric vehicle based on the real-time image, and sending the real-time position, the real-time speed, the mileage, the real-time image, the identification result of the real-time image, the real-time distance, and the first control instruction corresponding to the real-time speed and the identification result of the real-time image respectively to the safety early warning subsystem 104, so that the safety early warning subsystem 104 displays and warns the driving state of the shield tunnel electric vehicle.

[0065] Further, the safety early warning subsystem 104 includes a data display platform and an early warning platform, and the data display platform and the early warning platform are connected with the construction center through a data communication network.

[0066] The data display platform is used for displaying the received real-time position, real-time speed, mileage, real-time image, identification result of real-time image and real-time distance.

[0067] It should be noted that the safety early warning subsystem includes a display screen, which can display the real-time position, real-time speed, mileage, real-time image, identification result of real-time image and real-time distance of the shield tunnel electric vehicle in a digital / textual manner, or can display the real-time position, real-time speed and other data in a graphical manner after graphical processing. Here, the data display platform and the early warning platform are connected with the construction center.

[0068] The pre-warning platform is used for pre-warning the driving state of the shield tunnel electric vehicle based on receiving the first control instruction corresponding to the real-time speed and the identification result of the real-time image.

[0069] It should be noted that by monitoring the real-time speed of the shield tunnel electric vehicle, timely reminders can be given when the shield tunnel electric vehicle is overspeeding. When the real-time speed of the shield tunnel electric vehicle is greater than the preset speed threshold, the data processing subsystem 103 sends a first control instruction indicating that the shield tunnel electric vehicle has overspeeded to the pre-warning platform, so that the pre-warning platform pre-warns the current situation that the shield tunnel electric vehicle has overspeeded. Here, the preset speed threshold can be set according to actual conditions, and the preset speed threshold is the maximum safe driving speed of the shield tunnel electric vehicle.

[0070] In addition, the real-time image of the driving environment of the shield tunnel electric vehicle can also be identified to determine whether there are obstacles and / or pedestrians in the driving environment of the shield tunnel electric vehicle. If the identification result of the real-time image is that there are obstacles and / or pedestrians in the driving environment, the data processing subsystem 103 sends a first control instruction indicating that there are obstacles and / or pedestrians in the driving environment to the pre-warning platform, so that the pre-warning platform pre-warns the current situation.

[0071] Further, the auxiliary support subsystem 105 includes a vehicle-mounted alarm device, power distribution and an uninterruptible power supply, and the vehicle-mounted alarm device, the power distribution and the uninterruptible power supply are all installed on the shield tunnel electric vehicle.

[0072] The data processing subsystem 103 is further configured to send a second control instruction corresponding to the real-time speed and the identification result of the real-time image to the vehicle-mounted alarm device.

[0073] The vehicle-mounted alarm device is used for sounding an audible and visual alarm after receiving the second control instruction.

[0074] It should be noted that the vehicle-mounted alarm device includes a vehicle-mounted alarm sound installed on the front of the shield tunnel electric vehicle and a vehicle-mounted warning light installed on the body of the shield tunnel electric vehicle. The vehicle-mounted alarm sound and the vehicle-mounted warning light are both connected to the data processing subsystem 103 through the data transmission subsystem 102. The vehicle-mounted alarm device controls the vehicle-mounted alarm sound and / or the vehicle-mounted warning light to give a prompt after receiving the second control instruction sent by the data processing subsystem 103. For example, if the real-time speed of the shield tunnel electric vehicle is greater than the preset speed threshold, the vehicle-mounted alarm sound is controlled to give a prompt, and if there are obstacles and / or pedestrians in the driving environment of the shield tunnel electric vehicle, the vehicle-mounted warning light is controlled to give a prompt.

[0075] Further, the safety pre-warning subsystem 104 includes a display screen, a PC terminal and a mobile terminal.

[0076] The security warning subsystem 104 is also used to store the received information into a database, and after receiving a query instruction sent by the first query terminal, to search for information matching the query instruction in the database and send the queried information to the first query terminal; and / or, after receiving an export instruction sent by the second query terminal, to export the information stored in the database to the second query terminal.

[0077] It should be noted that the safety early warning subsystem 104, also known as the monitoring cloud platform, can not only display or warn about the driving status of the shield tunnel battery vehicle, but also has the functions of storing, querying, and exporting data. Before data querying and exporting, the identities of the first and second query terminals can be legally verified to ensure data security.

[0078] Furthermore, the data processing subsystem 103 is also used to input the received real-time image into the target detection model, and send the recognition result of the real-time image output by the target detection model to the security warning subsystem 104.

[0079] For details, see Figure 3 As shown, Figure 3 A flowchart for real-time image recognition using a target detection model provided in this application embodiment includes:

[0080] S301: Preprocess the real-time image, including: converting the color space of the real-time image, converting the real-time image into a grayscale image, and performing reduction processing and gradient calculation on the grayscale image.

[0081] S302: The preprocessed real-time image is processed by a convolutional layer with enhanced sparsity to obtain a part detection map and mark obstacles and / or pedestrians; the structure of the subsampling layer is converted into a deformation processing layer to process the deformation of obstacles and / or pedestrians and obtain the detection scores of obstacles and / or pedestrians.

[0082] It should be noted that in step S302, convolution and subsampling operations are performed on the preprocessed real-time image to complete the processing of real-time image features. In the convolutional layer, in order to make full use of more potential information in the image, the sparsity of the convolutional layer feature extraction is enhanced. After the convolution operation of the last layer, a part detection map is generated and obstacles and / or pedestrians are marked. The structure of the subsampling layer that should have been there is replaced by a deformation processing layer to process the possible deformation of the obstacle and / or pedestrian parts, and finally the corresponding obstacle and / or pedestrian part detection scores are obtained.

[0083] S303: Input the detection score into the occlusion processing model to process the occluded obstacle and / or pedestrian data.

[0084] S304: input the processing result of the occlusion processing model into a label classification layer to determine the recognition result of the real-time image.

[0085] Further, referring to Figure 4 as shown, Figure 4 a flowchart for training a target detection model provided by the embodiment of the present application, comprising:

[0086] S401: using the monitoring camera to acquire a historical image dataset inside the tunnel.

[0087] S402: labeling the obstacles and / or pedestrians included in each picture in the historical image dataset as training samples for a deep learning algorithm.

[0088] S403: training the target detection model based on the training samples.

[0089] The early warning system for the battery car in the shield tunnel provided by the embodiment of the present application processes the real-time position, real-time speed, and real-time image of the driving environment of the monitored battery car in the shield tunnel, realizes the positioning of the battery car, the recognition of the obstacles and pedestrians in the driving environment of the battery car, and the real-time prompting and early warning of the driving state of the battery car, reduces the hidden dangers of overspeed and visual blind area of the battery car in the shield tunnel, and improves the efficiency and safety of tunnel operation.

[0090] Based on the same inventive concept, the embodiment of the present application also provides an early warning device for the battery car in the shield tunnel, which corresponds to the early warning system for the battery car in the shield tunnel. Since the principle of solving problems in the device of the embodiment of the present application is similar to the early warning system for the battery car in the shield tunnel described above, the implementation of the device can be referred to the implementation of the system, and the repeated parts will not be described here.

[0091] Referring to Figure 5 as shown, Figure 5 a structural schematic diagram of the early warning device for the battery car in the shield tunnel provided by the embodiment of the present application, the early warning device comprising a monitoring sensor 501, a data transmission module 502, a data processing module 503, a safety warning module 504, and an auxiliary support module 505; the monitoring sensor 501 is connected with the data processing module 503 through the data transmission module 502, the data processing module 503 is connected with the safety warning module 504 through the data transmission module 502, and the monitoring sensor 501, the data transmission module 502, the data processing module 503, the safety warning module 504, and the auxiliary support module 505 are all connected with the construction center through a data communication network;

[0092] The monitoring sensor 501 comprises a vehicle-mounted positioning sensor, a portal positioning sensor, a speed measuring sensor and a monitoring camera; wherein the vehicle-mounted positioning sensor is fixed on the front of the shield tunnel electric car in a way of roof magnetic attraction using two strong magnets below the shell of the vehicle-mounted positioning sensor; the portal positioning sensor is installed on the segment by bolts, comprising a first portal positioning sensor installed in the tunnel portal area and second fixed portal positioning sensors uniformly distributed in other positions of the tunnel, and the vehicle-mounted positioning sensor and the portal positioning sensor are provided with a uwb receiver, and the fixed portal positioning sensors are connected through the uwb receiver;

[0093] The vehicle-mounted positioning sensor is configured to obtain a positioning signal of the portal positioning sensor through communication with the portal positioning sensor, and calculate a real-time position of the shield tunnel electric car based on the positioning signal.

[0094] The speed measuring sensor is installed at a wheel part of the shield tunnel electric car, and is configured to measure a real-time speed and a mileage of the shield tunnel electric car.

[0095] The monitoring camera is installed in front of, behind, left of and right of the body of the shield tunnel electric car in a way of roof magnetic attraction or body side suction, and is configured to collect real-time images in each specified shooting area.

[0096] The data processing module 503 is configured to receive the real-time position, the real-time speed, the mileage, the real-time images of the shield tunnel electric car and the positioning signal of the portal positioning sensor sent by the monitoring sensor 501 through the data transmission module 502, determine a real-time distance between the shield tunnel electric car and the portal based on the real-time position, the real-time speed and the positioning signal, identify whether there are obstacles and / or pedestrians around the shield tunnel electric car based on the real-time images, and send the real-time position, the real-time speed, the mileage, the real-time images, the identification result of the real-time images, the real-time distance, and first control instructions corresponding to the real-time speed and the identification result of the real-time images to the safety warning module 504, so that the safety warning module 504 displays and warns the driving state of the shield tunnel electric car.

[0097] In a possible implementation, the safety warning module 504 comprises a data display platform and a warning platform, and the data display platform and the warning platform are connected with the construction center through a data communication network.

[0098] The data display platform is configured to display the received real-time position, real-time speed, mileage, real-time images, identification result of the real-time images and real-time distance.

[0099] The early warning platform is used for early warning of the driving state of the shield tunnel electric car based on receiving the first control instruction corresponding to the identification result of the real-time speed and the real-time image.

[0100] In a possible implementation, the auxiliary support module 505 includes a vehicle-mounted alarm device, power distribution and an uninterruptible power supply, all of which are installed on the shield tunnel electric car.

[0101] The data processing module 503 is further configured to send a second control instruction corresponding to the identification result of the real-time speed and the real-time image to the vehicle-mounted alarm device.

[0102] The vehicle-mounted alarm device is configured to issue an audible and visual alarm after receiving the second control instruction.

[0103] In a possible implementation, the vehicle-mounted positioning sensor and the portal positioning sensor are connected to the data transmission module 502 through the uwb receiver, the uwb receiver is provided with a receiver antenna that is matched with the data transmission module 502, and the speed measurement sensor and the monitoring camera are connected to the data transmission module 502 through a data communication cable.

[0104] In a possible implementation, the data transmission module 502 includes a cable communication module and a data communication network module; the communication mode of the cable communication module is coaxial cable communication, and the communication mode of the data communication network module is Ethernet communication; the vehicle-mounted positioning sensor, the portal positioning sensor, the speed measurement sensor and the monitoring camera are connected to the data communication network module through the uwb receiver and the data communication cable respectively; the uwb receiver communicates with the data sub-processing system through the data communication network module; and the data processing module 503 communicates with the safety early warning module 504 and the shield machine cab respectively through the data communication network module.

[0105] In a possible implementation, the safety early warning module 504 includes a display screen, a PC terminal and a mobile terminal.

[0106] The safety early warning module 504 is further configured to store the received information in a database, find information matching the query instruction from the database after receiving the query instruction sent by the first query terminal, and send the found information to the first query terminal; and / or export the information stored in the database to the second query terminal after receiving the export instruction sent by the second query terminal.

[0107] In a possible implementation, the data processing module 503 is further configured to input the received real-time image into a target detection model, and send an identification result of the real-time image output by the target detection model to the safety warning module 504.

[0108] In a possible implementation, the target detection model determines the identification result of the real-time image in the following manner:

[0109] Step 1: Preprocessing the real-time image, including: converting the color space of the real-time image, converting the real-time image into a grayscale image, and performing downsizing processing and gradient calculation on the grayscale image;

[0110] Step 2: performing operation on the preprocessed real-time image through a convolution layer that strengthens sparsity, obtaining a part detection map and marking the obstacles and / or pedestrians; converting the structure of a subsampling layer into a deformation processing layer, processing the deformation of the obstacles and / or pedestrians, and obtaining a detection score of the obstacles and / or pedestrians;

[0111] Step 3: inputting the detection score into an occlusion processing model to process the occluded obstacle and / or pedestrian data;

[0112] Step 4: inputting the processing result of the occlusion processing model into a label classification layer to determine the identification result of the real-time image.

[0113] In a possible implementation, the target detection model is trained in the following manner:

[0114] Step 1: acquiring a historical image data set inside the tunnel by using the monitoring camera;

[0115] Step 2: labeling the obstacles and / or pedestrians included in each picture in the historical image data set as training samples of a deep learning algorithm;

[0116] Step 3: training the target detection model based on the training samples.

[0117] The early warning device for the shield tunnel electric car provided by the embodiment of the application processes the monitored real-time position, real-time speed, and real-time image of the driving environment of the shield tunnel electric car, realizes positioning of the electric car, identification of obstacles and pedestrians in the driving environment of the electric car, and real-time prompting and early warning of the driving state of the electric car, reduces the hidden dangers of overspeed and visual blind area of the shield tunnel electric car, and improves the efficiency and safety of tunnel operation.

[0118] Finally, it should be noted that the above-described embodiments are merely specific embodiments of the present application, which are used to illustrate the technical solutions of the present application, but not to limit the same. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that any person skilled in the art can make modifications or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some of the technical features within the technical scope disclosed by the present application. The modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A warning system for a battery-powered vehicle used in a tunnel boring machine, characterized in that, The early warning system includes a monitoring sensor subsystem, a data transmission subsystem, a data processing subsystem, a safety early warning subsystem, and an auxiliary support subsystem. The monitoring sensor subsystem is connected to the data processing subsystem through the data transmission subsystem, and the data processing subsystem is connected to the safety early warning subsystem through the data transmission subsystem. All four subsystems—the monitoring sensor subsystem, the data transmission subsystem, the data processing subsystem, the safety early warning subsystem, and the auxiliary support subsystem—are connected to the construction center via a data communication network. The monitoring sensor subsystem includes a vehicle-mounted positioning sensor, a tunnel entrance positioning sensor, a speed measurement sensor, and a monitoring camera. The vehicle-mounted positioning sensor is fixed to the front of the shield tunneling vehicle using two strong magnets on its underside via magnetic attraction. The tunnel entrance positioning sensor is bolted to the tunnel lining segments and includes a first tunnel entrance positioning sensor installed in the tunnel entrance area and second fixed tunnel entrance positioning sensors evenly distributed in other locations within the tunnel. The vehicle-mounted positioning sensor and the tunnel entrance positioning sensor are equipped with UWB receivers, and the fixed tunnel entrance positioning sensors are connected to each other via the UWB receivers. The vehicle-mounted positioning sensor is used to obtain the positioning signal of the tunnel entrance positioning sensor by communicating with the tunnel entrance positioning sensor, and to calculate the real-time position of the shield tunnel battery vehicle based on the positioning signal. The speed measurement sensor is installed on the wheel of the shield tunnel battery vehicle and is used to measure the real-time speed and mileage of the shield tunnel battery vehicle. The monitoring cameras are installed on the front, rear, left, and right sides of the shield tunnel battery vehicle using either a magnetic suction method on the roof or a suction method on the side of the vehicle, and are used to collect real-time images of each designated shooting area. The data processing subsystem is used to receive the real-time position, real-time speed, mileage, and real-time image of the shield tunnel battery vehicle sent by the monitoring sensor subsystem through the data transmission subsystem, as well as the positioning signal of the tunnel entrance positioning sensor. Based on the real-time position, the real-time speed, and the positioning signal, it determines the real-time distance between the shield tunnel battery vehicle and the tunnel entrance. Based on the real-time image, it identifies whether there are obstacles and / or pedestrians around the shield tunnel battery vehicle. It sends the first control commands corresponding to the real-time position, the real-time speed, the mileage, the real-time image, the recognition result of the real-time image, the real-time distance, and the recognition result of the real-time speed and the real-time image to the safety warning subsystem, so that the safety warning subsystem can display and warn the driving status of the shield tunnel battery vehicle. The data processing subsystem is also used to input the received real-time image into the target detection model, and send the recognition result of the real-time image output by the target detection model to the security early warning subsystem; The target detection model determines the recognition result of the real-time image in the following way: Step 1: Preprocess the real-time image, including: converting the color space of the real-time image to a grayscale image, and performing reduction processing and gradient calculation on the grayscale image; Step 2: Perform calculations on the preprocessed real-time image through a convolutional layer with enhanced sparsity to obtain a part detection map and mark obstacles and / or pedestrians; convert the structure of the subsampling layer into a deformation processing layer to process the deformation of obstacles and / or pedestrians and obtain the detection scores of obstacles and / or pedestrians; Step 3: Input the detection score into the occlusion processing model to process the occluded obstacle and / or pedestrian data; Step 4: Input the processing result of the occlusion processing model into the label classification layer to determine the recognition result of the real-time image.

2. The early warning system for a battery-powered vehicle used in a tunnel boring machine according to claim 1, characterized in that, The safety early warning subsystem includes a data display platform and an early warning platform, both of which are connected to the construction center via a data communication network. The data display platform is used to display the received real-time location, real-time speed, mileage, real-time image, recognition result of the real-time image, and real-time distance; The early warning platform is used to provide early warnings about the driving status of the shield tunnel battery vehicle based on the first control command corresponding to the received real-time speed and the recognition result of the real-time image.

3. The early warning system for a battery-powered vehicle used in a tunnel boring machine according to claim 1, characterized in that, The auxiliary support subsystem includes an on-board alarm device, a power distribution system, and an uninterruptible power supply. The on-board alarm device, the power distribution system, and the uninterruptible power supply are all installed on the shield tunnel battery vehicle. The data processing subsystem is also used to send the second control command corresponding to the real-time speed and the recognition result of the real-time image to the vehicle alarm device; The vehicle alarm device is used to issue an audible and visual alarm after receiving the second control command.

4. The early warning system for a battery-powered vehicle used in a shield tunnel according to claim 1, characterized in that, The vehicle-mounted positioning sensor and the opening positioning sensor are connected to the data transmission subsystem via the UWB receiver. The UWB receiver is equipped with a receiver antenna that is matched with the data transmission subsystem. The speed measurement sensor and the monitoring camera are connected to the data transmission subsystem via a data communication cable.

5. The early warning system for a battery-powered vehicle used in a tunnel boring machine according to claim 1, characterized in that, The data transmission subsystem includes a cable communication module and a data communication network module; the cable communication module uses coaxial cable communication, and the data communication network module uses Ethernet communication; the vehicle positioning sensor, the opening positioning sensor, the speed measurement sensor, and the monitoring camera are respectively connected to the data communication network module via the UWB receiver and the data communication cable; the UWB receiver communicates with the data processing subsystem through the data communication network module; The data processing subsystem transmits data to the safety early warning subsystem and the tunnel boring machine cab via a data communication network module.

6. The early warning system for a battery-powered vehicle used in a tunnel boring machine according to claim 1, characterized in that, The security warning subsystem includes a display screen, a PC, and a mobile device; The security early warning subsystem is also used to store the received information into the database, and after receiving a query instruction sent by the first query terminal, to search for information that matches the query instruction from the database and send the queried information to the first query terminal; And / or, upon receiving an export instruction from the second query terminal, export the information stored in the database to the second query terminal.

7. The early warning system for a battery-powered vehicle used in a shield tunnel according to claim 1, characterized in that, The target detection model is trained in the following manner: Step 1: Use the monitoring camera to acquire a historical image dataset of the tunnel interior; Step 2: Label the obstacles and / or pedestrians in each image in the historical image dataset as training samples for the deep learning algorithm; Step 3: Based on the training samples, train the target detection model.

8. A warning device for a battery-powered vehicle used in a shield tunnel, characterized in that, The early warning device includes a monitoring sensor, a data transmission module, a data processing module, a safety early warning module, and an auxiliary support module. The monitoring sensor is connected to the data processing module through the data transmission module, and the data processing module is connected to the safety early warning module through the data transmission module. The monitoring sensor, the data transmission module, the data processing module, the safety early warning module, and the auxiliary support module are all connected to the construction center through a data communication network. The monitoring sensors include a vehicle-mounted positioning sensor, a tunnel entrance positioning sensor, a speed measurement sensor, and a monitoring camera. The vehicle-mounted positioning sensor is fixed to the front of the shield tunneling vehicle using two strong magnets on its underside via magnetic attraction. The tunnel entrance positioning sensor is bolted to the tunnel lining segments and includes a first tunnel entrance positioning sensor installed in the tunnel entrance area and second fixed tunnel entrance positioning sensors evenly distributed in other locations within the tunnel. The vehicle-mounted positioning sensor and the tunnel entrance positioning sensor are equipped with UWB receivers, and the fixed tunnel entrance positioning sensors are connected to each other via the UWB receivers. The vehicle-mounted positioning sensor is used to obtain the positioning signal of the tunnel entrance positioning sensor by communicating with the tunnel entrance positioning sensor, and to calculate the real-time position of the shield tunnel battery vehicle based on the positioning signal. The speed measurement sensor is installed on the wheel of the shield tunnel battery vehicle and is used to measure the real-time speed and mileage of the shield tunnel battery vehicle. The monitoring cameras are installed on the front, rear, left, and right sides of the shield tunnel battery vehicle using either a magnetic suction method on the roof or a suction method on the side of the vehicle, and are used to collect real-time images of each designated shooting area. The data processing module is used to receive the real-time position, real-time speed, mileage, and real-time image of the shield tunnel battery vehicle sent by the monitoring sensor through the data transmission module, as well as the positioning signal of the tunnel entrance positioning sensor. Based on the real-time position, the real-time speed, and the positioning signal, it determines the real-time distance between the shield tunnel battery vehicle and the tunnel entrance. Based on the real-time image, it identifies whether there are obstacles and / or pedestrians around the shield tunnel battery vehicle. The module sends the first control commands corresponding to the real-time position, the real-time speed, the mileage, the real-time image, the recognition result of the real-time image, the real-time distance, and the recognition result of the real-time speed and the real-time image to the safety warning module, so that the safety warning module can display and warn the driving status of the shield tunnel battery vehicle. The data processing module is also used to input the received real-time image into the target detection model, and send the recognition result of the real-time image output by the target detection model to the security warning module; The target detection model determines the recognition result of the real-time image in the following way: Step 1: Preprocess the real-time image, including: converting the color space of the real-time image to a grayscale image, and performing reduction processing and gradient calculation on the grayscale image; Step 2: Perform calculations on the preprocessed real-time image through a convolutional layer with enhanced sparsity to obtain a part detection map and mark obstacles and / or pedestrians; convert the structure of the subsampling layer into a deformation processing layer to process the deformation of obstacles and / or pedestrians and obtain the detection scores of obstacles and / or pedestrians; Step 3: Input the detection score into the occlusion processing model to process the occluded obstacle and / or pedestrian data; Step 4: Input the processing result of the occlusion processing model into the label classification layer to determine the recognition result of the real-time image.

Images