CN116319795B - Unmanned detection and identification system of subway train based on edge calculation - Google Patents
Unmanned detection and identification system of subway train based on edge calculation Download PDFInfo
- Publication number
- CN116319795B CN116319795B CN202310589454.6A CN202310589454A CN116319795B CN 116319795 B CN116319795 B CN 116319795B CN 202310589454 A CN202310589454 A CN 202310589454A CN 116319795 B CN116319795 B CN 116319795B
- Authority
- CN
- China
- Prior art keywords
- module
- data
- edge
- digital signal
- calculation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004364 calculation method Methods 0.000 title claims abstract description 225
- 238000001514 detection method Methods 0.000 title claims abstract description 57
- 230000007613 environmental effect Effects 0.000 claims description 59
- 231100000279 safety data Toxicity 0.000 claims description 50
- 230000004927 fusion Effects 0.000 claims description 46
- 238000007781 pre-processing Methods 0.000 claims description 43
- 238000000034 method Methods 0.000 claims description 19
- 230000008569 process Effects 0.000 claims description 11
- 238000007499 fusion processing Methods 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 230000007175 bidirectional communication Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 abstract description 9
- 230000003993 interaction Effects 0.000 abstract description 2
- 238000012545 processing Methods 0.000 description 19
- 238000004422 calculation algorithm Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 9
- 230000005540 biological transmission Effects 0.000 description 8
- 230000001133 acceleration Effects 0.000 description 5
- 239000000523 sample Substances 0.000 description 4
- 238000013480 data collection Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006854 communication Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning or like safety means along the route or between vehicles or trains
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/20—Trackside control of safe travel of vehicle or train, e.g. braking curve calculation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/14—Measuring arrangements characterised by the use of optical techniques for measuring distance or clearance between spaced objects or spaced apertures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B17/00—Measuring arrangements characterised by the use of infrasonic, sonic or ultrasonic vibrations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S11/00—Systems for determining distance or velocity not using reflection or reradiation
- G01S11/12—Systems for determining distance or velocity not using reflection or reradiation using electromagnetic waves other than radio waves
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S11/00—Systems for determining distance or velocity not using reflection or reradiation
- G01S11/14—Systems for determining distance or velocity not using reflection or reradiation using ultrasonic, sonic, or infrasonic waves
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/06—Systems determining position data of a target
- G01S13/08—Systems for measuring distance only
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
- G01S13/867—Combination of radar systems with cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
- H04L63/0428—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q9/00—Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Mechanical Engineering (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Mathematical Physics (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Electromagnetism (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention provides an edge calculation-based unmanned detection and identification system for a subway train, relates to the technical field of unmanned operation, and particularly relates to the technical field of edge calculation. The detection and identification system comprises a sensor group, an edge gateway module, an edge calculation module, a main control module and a cloud service platform; the connection and interaction between the sensor group, the edge gateway module, the edge computing module, the main control module and the cloud service platform improve the unmanned safety and stability of the subway train and reduce the accident rate; the running condition of the subway train is monitored in real time, faults are found and processed in time, and the running efficiency and the passenger transport quality are improved. The edge computing is used for computing the subway train edge equipment and the acquired detection identification information, so that timeliness of response to sudden accidents is enhanced; ensuring safe, stable and efficient operation of the train.
Description
Technical Field
The invention provides an edge calculation-based subway train unmanned detection and identification system, and relates to the technical field of unmanned operation, in particular to the technical field of edge calculation.
Background
At the today of the rapid development of science and technology, unmanned is widely applied to the field of trains, and the unmanned function of the trains effectively reduces manpower, utilizes automatic driving, effectively improves the safety of train driving, but also has some problems.
Traditional data processing and calculation are completed by cloud computing, and the calculation method has the advantages of delay, low response speed and long occupation time; the unmanned tracking recognition technology of subway trains needs to analyze and process a large number of edge devices such as sensors in real time, and is difficult to ensure the running safety and reliability of the trains when handling emergency events, but the traditional edge computing energy storage capacity and computing capacity cannot meet the requirement of a large number of real-time data processing.
Disclosure of Invention
The invention provides an edge calculation-based subway train unmanned detection and identification system, which is used for solving the problems of improving the calculation capability of an unmanned edge of a train and improving the response speed of edge equipment:
the invention provides an edge calculation-based unmanned detection and identification system for a subway train, which is characterized by comprising a sensor group, an edge gateway module, an edge calculation module, a main control module and a cloud service platform; the digital signal output end of the sensor group is connected with the digital signal input end of the edge gateway module, the digital signal output end of the edge gateway module is connected with the digital signal input end of the edge computing module, the digital signal output end of the edge computing module is respectively connected with the digital signal input ends of the main control module and the cloud service platform, and the digital signal output end of the cloud service platform is connected with the digital signal input end of the main control module. The edge gateway module comprises a data preprocessing module, a network connection module and a security authentication module; the method comprises the steps of collecting environmental data of a train surrounding environment through a sensor group, sending the environmental data to an edge gateway module, preprocessing and encrypting the environmental data through the edge gateway module to obtain safety data, sending the safety data to an edge computing module, carrying out preliminary computation on the safety data through the edge computing module, respectively sending preliminary computation results to a main control module and a cloud service platform, carrying out depth computation on the safety data through the cloud service platform to obtain a depth computation result, and controlling a detection recognition system by the main control module according to the preliminary computation result and the depth computation result.
Further, the sensor group comprises a laser sensor, an ultrasonic sensor, a camera and a radar sensor;
the digital signal output ends of the laser sensor, the ultrasonic sensor, the camera and the radar sensor are the digital signal output ends of the sensor group.
Further, the connection relationship among the data preprocessing module, the network connection module and the security authentication module of the edge gateway module is as follows: the digital signal input end of the data preprocessing module is the digital signal input end of the edge gateway module;
the digital signal output end of the data preprocessing module is the digital signal output end of the edge gateway module;
the data preprocessing module is in bidirectional communication connection with the safety authentication module;
further, the connection mode of the network connection module comprises WiFi, zigBee and Bluetooth.
The edge computing module comprises an edge device computing module and a data fusion module;
the digital signal input end of the edge equipment computing module is the digital signal input end of the edge computing module;
the digital signal output end of the edge equipment computing module is connected with the digital signal input end of the data fusion module;
The digital signal output end of the data fusion module is the digital signal output end of the edge calculation module.
Further, the main control module comprises a host memory, a host controller and a host executor;
the digital signal input end of the host memory is the digital signal input end of the main control module;
the digital signal output end of the host memory is connected with the digital signal input end of the host controller;
the control signal output end of the host controller is connected with the control signal input end of the host executor;
and the execution signal output end of the host executor is connected with the execution signal input end of the controlled equipment of the detection and identification system.
Further, the step of detecting and identifying by the detecting and identifying system includes:
s1, acquiring data of environmental information of a train by using the sensor group, and acquiring various environmental data corresponding to the environmental information of the train; and sending the environmental data to an edge gateway module;
s2, the edge gateway module performs preprocessing on the environmental data to obtain preprocessed environmental data, encrypts the preprocessed environmental data to obtain safety data, and sends the safety data to the edge computing module;
S3, the edge calculation module performs preliminary calculation on the safety data, in the process, the edge calculation module sends obstacle distance parameters acquired by the sensor group to the data fusion module, the data fusion module obtains a preliminary calculation result through data fusion processing, and the preliminary calculation result is respectively sent to the main control module and the cloud service platform;
s4, the cloud service platform performs comprehensive arrangement and depth calculation on the safety data to obtain a depth calculation result, and sends the depth calculation result to a main control module;
s5, the main control module generates a control instruction according to the preliminary calculation result and the depth calculation result to control the detection and identification system.
Further, the data acquisition of the environmental information of the train by using the sensor group includes:
s101, the sensor group respectively acquires data of four objects in the surrounding environment of the train through a laser sensor, an ultrasonic sensor, a camera and a radar sensor to obtain a laser signal, an ultrasonic signal, a camera signal and a radar signal;
s102, the sensor group sends the collected laser signals, ultrasonic signals, shooting signals and radar signals to the edge gateway module.
Further, the step of preprocessing and encrypting the environmental data by the edge gateway module includes:
s201, the edge gateway module performs preprocessing of cleaning, noise reduction, filtering, de-duplication and format conversion on environmental data of four objects in the train surrounding environment by using a data preprocessing module to obtain preprocessed environmental data, and sends the preprocessed environmental data to the security authentication module;
s202, the safety authentication module encrypts the preprocessed environment data to obtain the safety data, and the safety data is sent to the edge calculation module.
Further, the edge computing module performing preliminary computation on the security data includes:
s301, the edge computing module decrypts the safety data through the edge device computing module to obtain decrypted safety data;
s302, the edge computing module sequentially extracts obstacle distance parameters acquired by the laser sensor, the ultrasonic sensor, the camera and the radar sensor from the safety data through the edge equipment computing module, and sends the obstacle distance parameters to the data fusion module;
S303, the data fusion module carries out data fusion processing on the obstacle distance parameters acquired by the laser sensor, the ultrasonic sensor, the camera and the radar sensor through a data fusion model to acquire comprehensive distance parameters;
the comprehensive distance parameter is a preliminary calculation result, and the data fusion model is as follows:
；
wherein L represents a data fusion model, S 1 Indicating the detection time of the radar sensor,indicating radar sensor detection speed, +.>Representing the area taken by the camera of the obstacle in the photograph,/for example>Representing the pixel size of the object captured by the camera in pixels, < >>Representing the distance between the camera and the object, < >>Representing the time difference between the ultrasonic sensor and the obstacle, S 2 Representing the sound velocity of the ultrasonic wave; q represents the speed of light of the laser sensor; y is Y 2 Representing the time difference between the laser sensor and the obstacle, W 1 Weight of radar sensor, W 2 Weight of camera, W 3 Weight of ultrasonic sensor, W 4 Weights for the laser sensors;
s304, the data fusion module sends the comprehensive distance parameters to a main control module and a cloud service platform.
Further, the step of comprehensively arranging and deeply computing the security data by the cloud service platform includes:
S401, after receiving a preliminary calculation result, the cloud service platform performs depth calculation through a first depth calculation model to obtain a first depth calculation result;
；
wherein L is 1 C is radar for the first depth calculation resultIs the speed of light, t is the time of flight, m of the echo signal of the radar 2 Representing the area occupied by the camera taking the obstacle in the photograph,representing the pixel size of the object captured by the camera in pixels, < >>Representing the distance between the camera and the object s j Sound velocity, t, of ultrasonic wave j The detection time of the ultrasonic wave; q represents the speed of light of the laser sensor; y is Y 2 Representing the time difference between the laser sensor and the obstacle, W 1 Weight of radar sensor, W 2 Weight of camera, W 3 Weight of ultrasonic sensor, W 4 Weights for the laser sensors;
s402, after receiving the preliminary calculation result, the cloud service platform performs depth calculation through a second depth calculation model to obtain a second depth calculation result;
；
；
wherein L is 2 For the result of the second depth calculation,to compensate for time, t 0 For delay time, t 1 Time required for varying a distance unit;
s403, the cloud service platform sends the first depth calculation result and the second depth calculation result to a main control module.
The invention has the beneficial effects that:
the invention provides an unmanned detection and identification system of a subway train based on edge calculation, which improves the unmanned safety and stability of the subway train and reduces the accident rate through the connection and interaction among a sensor group, an edge gateway module, an edge calculation module, a main control module and a cloud service platform. The running condition of the subway train is monitored in real time, faults are found and processed in time, and the running efficiency and the passenger transport quality are improved. By calculating the subway train edge equipment and the acquired detection identification information by using edge calculation, timeliness of response to sudden accidents is enhanced. Ensuring safe, stable and efficient operation of the train.
Drawings
FIG. 1 is a schematic diagram of a detection and identification system;
fig. 2 is a schematic diagram of the steps of probe recognition by the probe recognition system.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The invention provides an edge calculation-based unmanned detection and identification system for a subway train, which is characterized by comprising a sensor group, an edge gateway module, an edge calculation module, a main control module and a cloud service platform; the digital signal output end of the sensor group is connected with the digital signal input end of the edge gateway module, the digital signal output end of the edge gateway module is connected with the digital signal input end of the edge computing module, the digital signal output end of the edge computing module is respectively connected with the digital signal input ends of the main control module and the cloud service platform, and the digital signal output end of the cloud service platform is connected with the digital signal input end of the main control module; the edge gateway module comprises a data preprocessing module, a network connection module and a security authentication module; the method comprises the steps of collecting environmental data of a train surrounding environment through a sensor group, sending the environmental data to an edge gateway module, preprocessing and encrypting the environmental data through the edge gateway module to obtain safety data, sending the safety data to an edge computing module, carrying out preliminary computation on the safety data through the edge computing module, respectively sending preliminary computation results to a main control module and a cloud service platform, carrying out depth computation on the safety data through the cloud service platform to obtain a depth computation result, and controlling a detection recognition system by the main control module according to the preliminary computation result and the depth computation result. The depth calculation results include a first depth calculation result and a second depth calculation result.
The sensor group comprises a laser sensor, an ultrasonic sensor, a camera and a radar sensor;
the digital signal output ends of the laser sensor, the ultrasonic sensor, the camera and the radar sensor are the digital signal output ends of the sensor group.
The working principle of the technical scheme is that the subway train unmanned detection and identification system based on edge calculation provided by the invention utilizes the mutual communication connection among a sensor group, an edge gateway module, an edge calculation module, a main control module and a cloud service platform to construct a frame of the subway train unmanned detection and identification system based on edge calculation;
various functions of data acquisition, edge calculation, data protection and comprehensive control are integrated, and support is provided for a specific detection and identification process.
The sensor module is used for collecting information of the surrounding environment of the train;
the sensor group acquires data of the surrounding environment of the train through the laser sensor, the ultrasonic sensor, the camera and the radar sensor to obtain a laser signal, an ultrasonic signal, a camera shooting signal and a radar signal;
and the sensor group sends the collected laser signals, ultrasonic signals, shooting signals and radar signals to the edge gateway module.
The technical effect of the technical scheme is that the system can improve the response speed of edge calculation, improve the safety and stability of the unmanned train and reduce the occurrence probability of accidents by using the edge calculation for the unmanned detection and identification system of the subway train;
fault information is found and collected in time through detection and identification, so that information collection efficiency is improved;
obstacle information of surrounding environments of the subway train is acquired through various different sensors, so that the data acquisition efficiency is improved, and the equipment is more automatic and intelligent.
Through mutually supporting between a plurality of sensors, make up for the shortages between laser sensor, ultrasonic sensor, camera and the radar sensor, strengthened the accuracy of sensor collection data greatly, reduced manual monitoring's cost and security risk.
The sensors are matched with each other for use, so that the data collection efficiency of the sensors is greatly improved, the omnibearing collection of data is realized, and strong data support is provided for edge calculation.
In one embodiment of the present invention, the connection relationships among the data preprocessing module, the network connection module and the security authentication module of the edge gateway module are as follows:
the digital signal input end of the data preprocessing module is the digital signal input end of the edge gateway module;
The digital signal output end of the data preprocessing module is the digital signal output end of the edge gateway module;
the data preprocessing module is in bidirectional communication connection with the safety authentication module;
the network connection module is connected in a manner of WiFi, zigBee and Bluetooth.
The working principle of the technical scheme is that the network connection module is used for preprocessing and encrypting the data acquired by the sensor;
the sensor module sends different data to the data preprocessing module through different sensors, the data preprocessing module cleans, reduces noise, filters, removes weight and converts formats, and the data preprocessing module processes the data by using a clustering algorithm.
The security authentication module encrypts the data preprocessed by the data through an asymmetric encryption algorithm.
The technical effect of the technical scheme is that the data preprocessing module performs preprocessing and analysis on the collected environmental data, reduces the burden for subsequent calculation, and improves the data processing efficiency.
The safety authentication module encrypts the preprocessed data, so that the safety of data transmission is improved, and the safety of a train is ensured;
The data preprocessing module and the security authentication module are mutually matched, so that the data is encrypted and protected before calculation, the risk of data leakage is radically avoided, and the security of the detection and identification system is greatly enhanced.
In one embodiment of the invention, the edge computing module comprises an edge device computing module and a data fusion module;
the digital signal input end of the edge equipment computing module is the digital signal input end of the edge computing module;
the digital signal output end of the edge equipment computing module is connected with the digital signal input end of the data fusion module;
the digital signal output end of the data fusion module is the digital signal output end of the edge calculation module.
The working principle of the technical scheme is that the edge equipment computing module comprises a compression computing module and a distributed computing module;
the compression calculation module comprises a discrete cosine transform method and a wavelet calculation method;
the data fusion module comprises a support vector machine, and the support vector machine comprises an SVM classifier.
The technical effect of the technical scheme is that the edge computing module can process the data in real time, so that the delay of data processing can be greatly reduced, and the data processing speed is improved.
The edge computing module can realize local processing and storage of data, and reduces the amount of transmitted data and improves the transmission efficiency by a distributed processing and storage method.
And the edge calculation module is used for processing the preprocessed environmental data, so that the transmission efficiency, the system reliability and the system stability are greatly improved.
The edge calculation calculates the data after preprocessing and encryption and transmits the data to the host controller in real time, so that timeliness of data calculation and processing is ensured, transmission delay is greatly reduced, and data processing efficiency is improved.
The data fusion module fuses various data, unnecessary and erroneous data are removed, the processing efficiency of the data is improved, and the data is more accurate.
The application of the data processing fusion module in the driving detection and identification system improves the data processing efficiency and the reliability.
In one embodiment of the invention, the main control module comprises a host memory, a host controller and a host executor;
the digital signal input end of the host memory is the digital signal input end of the main control module;
the digital signal output end of the host memory is connected with the digital signal input end of the host controller;
The control signal output end of the host controller is connected with the control signal input end of the host executor;
and the execution signal output end of the host executor is connected with the execution signal input end of the controlled equipment of the detection and identification system.
The working principle of the technical scheme is that the main controller is used for controlling the operation data of each device of the train and controlling the operation state of the train.
The host memory is used for storing the calculated environment data.
The host executor is used for executing the control instruction sent by the host controller and controlling the controlled object.
The host memory receives the data calculated by the edge calculation module, stores the data and sends the data to the host controller, and the host controller retrieves the data calculated in the host memory to generate a control instruction, so as to control the executor to execute the control instruction to act on the controlled equipment of the detection and identification system.
The technical effect of the technical scheme is that the safety, the reliability and the efficiency of the train can be improved by controlling all equipment of the train through the host controller.
Through the mutual cooperation of the host memory, the host controller and the host executor, excessive processing steps are omitted, the transmission speed of instructions is accelerated, and the response speed of a train is greatly accelerated.
In one embodiment of the present invention, the step of probe recognition of the probe recognition system includes:
s1, acquiring data of environmental information of a train by using the sensor group, and acquiring various environmental data corresponding to the environmental information of the train; and sending the environmental data to an edge gateway module;
s2, the edge gateway module performs preprocessing on the environmental data to obtain preprocessed environmental data, encrypts the preprocessed environmental data to obtain safety data, and sends the safety data to the edge computing module;
s3, the edge calculation module performs preliminary calculation on the safety data, in the process, the edge calculation module sends obstacle distance parameters acquired by the sensor group to the data fusion module, the data fusion module obtains a preliminary calculation result through data fusion processing, the preliminary calculation result is respectively sent to the main control module and the cloud service platform, and the edge calculation module also sends the safety data to the cloud service platform;
s4, the cloud service platform performs comprehensive arrangement and depth calculation on the safety data to obtain a depth calculation result, and sends the depth calculation result to a main control module;
S5, the main control module generates a control instruction according to the preliminary calculation result and the depth calculation result to control the detection and identification system.
The working principle of the technical scheme is that the sensor group is utilized to comprehensively collect environmental information of the train through various sensors, so as to obtain various environmental data corresponding to the environmental information of the train; and sending the environmental data to an edge gateway module; the data is preprocessed and encrypted by the edge gateway module.
The edge gateway module performs preprocessing on the environmental data through a data preprocessing module to obtain preprocessed environmental data, encrypts the preprocessed environmental data through a security authentication module to obtain security data, and sends the security data to the edge computing module;
the edge calculation module performs preliminary calculation on the safety data, in the process, the edge calculation module sends the obstacle distance parameters acquired by the sensor group to the data fusion module, the data fusion module obtains a preliminary calculation result through data fusion processing, and the preliminary calculation result is respectively sent to the main control module and the cloud service platform;
The cloud service platform performs comprehensive arrangement and depth calculation on the safety data to obtain a depth calculation result, and sends the depth calculation result to a main control module;
and the main control module generates a control instruction according to the preliminary calculation result and the depth calculation result to control the detection and identification system.
The technical effect of the technical scheme is that the sensor group is utilized to collect data of the environmental information of the train, multiple environmental data corresponding to the environmental information of the train are obtained, multiple collected data are fused, the multiple sensors are utilized to be fused, the data collection range is enlarged, the data collection precision is improved, inaccuracy of collected data caused by the fact that a certain sensor is affected by the environment is avoided, and the data are more accurate.
The edge gateway module performs preprocessing on the environmental data to obtain preprocessed environmental data, encrypts the preprocessed environmental data, improves the safety of the data, shares the task of data arrangement for the edge computing module, and reduces the burden of the edge computing module.
The edge calculation module performs preliminary calculation on the safety data, so that the data processing speed is increased, and the response time of the train is reduced.
The cloud service platform performs comprehensive arrangement and depth calculation on the safety data to obtain a depth calculation result, and sends the depth calculation result to a main control module; the data is more accurate, and the powerful data computing capacity of the cloud service platform is utilized to provide powerful data support for the detection and identification system.
In one embodiment of the present invention, the step of preprocessing and encrypting the environmental data by the edge gateway module includes:
s201, the edge gateway module performs preprocessing of cleaning, noise reduction, filtering, de-duplication and format conversion on environmental data of four objects in the train surrounding environment by using a data preprocessing module to obtain preprocessed environmental data, and sends the preprocessed environmental data to the security authentication module;
s202, the safety authentication module encrypts the preprocessed environment data to obtain the safety data, and the safety data is sent to the edge calculation module.
The working principle of the technical scheme is that the data preprocessing module comprises data cleaning, a noise reduction algorithm, a filter, a clustering algorithm and Python;
the clustering algorithm comprises K-means clustering;
The safety authentication module comprises an API interface, and the data preprocessing module encrypts data by calling the API interface;
the security authentication module comprises an asymmetric encryption algorithm, wherein the asymmetric encryption algorithm adopts an RSA algorithm;
the technical effect of the technical scheme is that the algorithm and the interface are utilized to process and preprocess the data, so that the data precision is improved;
the data is filtered, so that the data noise can be reduced, the easy understanding of the data is enhanced, and the subsequent calculation is more convenient.
The data is more confidential by using the security authentication, so that errors of calculation results caused by data tampering are prevented, the data can be backed up in the encryption process, and the security and reliability of the data are enhanced.
In one embodiment of the present invention, the edge calculation module performs preliminary calculation on the security data, including:
s301, the edge computing module decrypts the safety data through the edge device computing module to obtain decrypted safety data;
s302, the edge computing module sequentially extracts obstacle distance parameters acquired by the laser sensor, the ultrasonic sensor, the camera and the radar sensor from the safety data through the edge equipment computing module, and sends the obstacle distance parameters to the data fusion module;
S303, the data fusion module carries out data fusion processing on the obstacle distance parameters acquired by the laser sensor, the ultrasonic sensor, the camera and the radar sensor through a data fusion model to acquire comprehensive distance parameters;
the comprehensive distance parameter is a preliminary calculation result, and the data fusion model is as follows:
；
wherein L represents a data fusion model, S 1 Indicating the detection time of the radar sensor,indicating radar sensor detection speed, +.>Representing the area taken by the camera of the obstacle in the photograph,/for example>Representing the pixel size of the object captured by the camera in pixels, < >>Representing the distance between the camera and the object,/>representing the time difference between the ultrasonic sensor and the obstacle, S 2 Representing the sound velocity of the ultrasonic wave; q represents the speed of light of the laser sensor; y is Y 2 Representing the time difference between the laser sensor and the obstacle, W 1 Weight of radar sensor, W 2 Weight of camera, W 3 Weight of ultrasonic sensor, W 4 Weights for the laser sensors;
s304, the data fusion module sends the comprehensive distance parameters to a main control module and a cloud service platform.
The working principle of the technical scheme is that the edge computing module decrypts the safety data through the edge equipment computing module to obtain decrypted safety data; calculating the decrypted safety data;
The edge computing module sequentially extracts obstacle distance parameters acquired by the laser sensor, the ultrasonic sensor, the camera and the radar sensor from the safety data through the edge equipment computing module, and sends the obstacle distance parameters to the data fusion module;
the data fusion module performs data fusion processing on the obstacle distance parameters acquired by the laser sensor, the ultrasonic sensor, the camera and the radar sensor through a data fusion model to acquire comprehensive distance parameters;
and the data fusion module sends the comprehensive distance parameters to a main control module and a cloud service platform.
The laser sensor, the ultrasonic sensor, the camera and the radar sensor are respectively affected by the environment, the detection distance is short, the sensor is dependent on the environment brightness or affected by light, the measurement data is inaccurate, various different information is measured through the sensor, the data are fused through a data fusion model, and the comprehensive distance parameter, namely the primary calculation result, is obtained.
The technical effect of the technical scheme is that the edge calculation module calculates the obstacle parameters in real time on site, reduces the data volume of data transmitted to the cloud service platform, and avoids the problem of slow calculation speed caused by the influence of the network speed;
When an abnormal situation occurs, data is sent in time, so that the influence caused by delay is avoided, the dependence on a cloud server is reduced, and the cost of data transmission is reduced;
the data fusion model is used for fusing the data acquired by different sensors, so that errors of the acquired data of the sensors are reduced, the accuracy of the acquired obstacle is improved, and the data is more stable.
The laser sensor, the ultrasonic sensor, the camera and the radar sensor are respectively affected by the environment, the detection distance is short, the sensor is dependent on the environment brightness or is affected by light, the measurement data is inaccurate, various different information is measured through the sensor, the data is fused through a data fusion model, comprehensive distance parameters, namely a preliminary calculation result, data support is provided for subsequent depth calculation, uncertainty can be eliminated, noise is eliminated, the integrity of the data is improved, and the possibility of missing detection of data acquisition is reduced.
According to one embodiment of the invention, the cloud service platform performs comprehensive arrangement and depth calculation on the security data, and the method comprises the following steps:
s401, after receiving a preliminary calculation result, the cloud service platform performs depth calculation through a first depth calculation model to obtain a first depth calculation result;
；
Wherein L is 1 For the first depth calculation result, c is the speed of light of the radar, t is the flight time of the echo signal of the radar, m 2 Representing the area occupied by the camera taking the obstacle in the photograph,representing the pixel size of the object captured by the camera in pixels, < >>Representing the distance between the camera and the object s j Sound velocity, t, of ultrasonic wave j The detection time of the ultrasonic wave; q represents the speed of light of the laser sensor; y is Y 2 Representing the time difference between the laser sensor and the obstacle, W 1 Weight of radar sensor, W 2 Weight of camera, W 3 Weight of ultrasonic sensor, W 4 Weights for the laser sensors;
s402, after receiving the preliminary calculation result, the cloud service platform performs depth calculation through a second depth calculation model to obtain a second depth calculation result;
；
；
wherein L is 2 For the result of the second depth calculation,to compensate for time, t 0 For delay time, t 1 Time required for varying a distance unit;
s403, the cloud service platform sends the first depth calculation result and the second depth calculation result to a main control module.
According to the technical scheme, the cloud service platform performs comprehensive arrangement and depth calculation on the safety data, and the method comprises the following steps:
After receiving the preliminary calculation result, the cloud service platform performs depth calculation through a second depth calculation model to obtain a second depth calculation result;
the preliminary calculation result may be a trigger condition, and when the cloud service platform receives the preliminary calculation result, the cloud service platform is triggered to perform depth calculation. The preliminary calculation result can also be used as a parameter of the calculation depth calculation result, and a user can determine whether to use the preliminary calculation result as the parameter according to the need in the actual application process and adjust the formula.
Detecting time by a radar sensor, detecting speed by the radar sensor, taking the occupied area of an obstacle in a photo by a camera, the pixel size of an object in a pixel acquired by the camera, the distance between the camera and the object, the time difference between an ultrasonic sensor and the obstacle, and the sound velocity of ultrasonic waves; the speed of light of the laser sensor; the time difference from the laser sensor to the obstacle, the weight of the radar sensor, the weight of the camera, the weight of the ultrasonic sensor, the weight of the laser sensor calculates the first depth calculation result.
And the cloud service platform sends the first depth calculation result and the second depth calculation result to a main control module.
The second depth calculation result is calculated through the light speed of the radar, the flight time of an echo signal of the radar, the occupied area of an obstacle in a photo, the pixel size of an object in a pixel, the distance between the camera and the object, the sound speed of ultrasonic waves and the detection time of the ultrasonic waves, which are acquired by the camera;
obtaining a first depth calculation result by using a first depth calculation model calculation; the second depth calculation result is obtained by calculation by using the second depth calculation model, a relatively accurate depth calculation result can be obtained by calculating sensor data for a plurality of times by using different calculation models, a variable is continuously changed to obtain a changed calculation result, and the data can be calculated for a plurality of times by using the first depth calculation model and the second depth calculation model by adopting a variable changing method.
The technical effect of the technical scheme is that the first depth calculation result is calculated, calculation data are collected, the detection precision and reliability can be improved, the accuracy and reliability of the data are enhanced, more reliable results are provided in a complex environment, and the data are more reasonably utilized;
calculating a second depth calculation result, and calculating the data by using different parameters and calculation models to obtain the second depth calculation result, so that the data calculation result is further obtained, and the data is more accurate;
By calculating the compensation time, the first depth calculation model and the second depth calculation model, the safety of the train is greatly enhanced, the safety of the train is guaranteed, the delay is reduced, and the timely response speed of the train is enhanced.
The expansibility of edge calculation is improved, the data transmission distance is reduced by using a calculation mode of a calculation model, the speed of edge calculation is greatly enhanced, the power consumption is saved, and the waste of energy is reduced;
the efficiency of information transmission is ensured, so that resources are reasonably utilized; the edge calculation solves the problem of rapid calculation of a large amount of data in a complex environment of train data, and the delay of the train can be greatly reduced by adjusting parameters, so that the response speed of the train is improved, and the life safety of passengers is ensured.
Obtaining a first depth calculation result by using a first depth calculation model calculation; the second depth calculation result is obtained by calculating the second depth calculation model, the relatively accurate depth calculation result can be obtained by calculating sensor data for a plurality of times by using different calculation models, the changed calculation result can be obtained by continuously changing variables, the data can be calculated by adopting a variable changing method through the first depth calculation model and the second depth calculation model for a plurality of times so as to adjust the parameters required to control the detection recognition system, the calculation time and the complexity of the traditional edge calculation are effectively reduced, the accuracy of the data calculation is improved, the data accuracy can be effectively improved by carrying out weighting processing on the detection distance obtained by calculating the acquired data by using the laser sensor, the ultrasonic sensor, the camera and the radar sensor by multiplying the sensor weight, the redundant data can be reduced by setting the weight of the sensor, the data processing efficiency is improved, the self-adaption of the data processing is realized, and the influence of the data noise is reduced. The detection distance calculated by using the laser sensor, the ultrasonic sensor, the camera and the radar sensor to collect data is multiplied by the sensor weight and divided by the sensor weight, so that the detection distance of the sensor can accurately reflect the data collected by the sensor Is a function of (1); calculating a second depth calculation result by calculating a compensation time in combination with the first depth calculation result using t 0 -t 1 The compensation time can be calculated, and a second depth calculation result is calculated through the compensation time and the first depth calculation result; the first depth calculation result and the second depth calculation result are obtained by combining the preliminary calculation result, the multiple results are sent to the host controller, and the data are fused, so that the influence on the whole data when one or more data in the data are inaccurate can be reduced, the data are more robust, and the comprehensiveness of the calculation result is improved through fusion of the multiple data.
In one embodiment of the present invention, the control step of the main control module includes:
s501, the main control module stores a depth calculation result through the host memory;
s502, the host controller of the main control module compares the preliminary calculation result, the first depth calculation result and the second depth calculation result with the shortest braking distance to determine whether to start emergency braking, wherein the shortest braking distance is obtained through the following formula:
；
wherein L is H For the shortest braking distance, V S1 For braking initial speed S 4 For minimum braking time, V S2 Is braking acceleration;
s503, the host controller monitors the actual distance between the current train and the obstacle in real time, and when the actual distance between the train and the obstacle reaches the shortest braking distance, the host actuator is controlled to take braking measures on the train.
The working principle of the technical scheme is that the main control module stores the depth calculation result through the host memory;
and the host controller of the main control module determines whether to start emergency braking by comparing the primary calculation result, the first depth calculation result and the second depth calculation result with the shortest braking distance.
In the formula, 0.5V is calculated S2 The brake speed of the train is increased within 1 second, namely the average value of the brake acceleration of the train is obtained, S 4 The shortest braking time can also be used as the distance of the train moving in a period of time, the shortest braking distance can be calculated, the shorter the adjusting time is, the shorter the braking distance is, and the shortest braking distance is calculated by V S1 Initial braking speed S 4 For the shortest braking time and V S2 The shortest braking distance is calculated for the braking acceleration.
The technical effects of the technical scheme are that the host controller of the main control module utilizes the preliminary calculation result, the first depth calculation result and the second depth calculation result to compare with the shortest braking distance to determine whether to start emergency braking, the host controller detects the surrounding environment information of the train in real time through the sensor, and calculates the comprehensive distance parameter, the first depth calculation result and the second depth calculation result through the edge calculation module, so that compared with the shortest braking distance, the safety of train operation is greatly improved, and the accident risk is reduced;
by calculating the train S 4 The shortest braking time can be pre-judged in advance, the braking distance of the train is reduced, and the safety of the vehicle is ensured;
according to the shortest braking distance, the braking performance of the train can be optimized, and the running efficiency of the train is improved;
the abrasion of the brake is reduced, the service life of the train is prolonged, and the maintenance cost is reduced.
The shortest braking distance is calculated, so that the safe running of the train is ensured, the data processing capacity and accuracy are improved, and the maintenance and repair cost of the train is greatly reduced.
The formula can adjust the shortest braking distance of the sensor by adjusting the train parameters, so that the train braking is more accurate, the power consumption of the system is reduced, and the time required by calculation is shortened.
By calculation in the formulaThe brake speed of the train is increased within 1 second, namely the average value of the brake acceleration of the train is obtained, S 4 The shortest braking time can also be used as the distance of the train moving in a period of time, the shortest braking distance can be calculated, the shorter the adjusting time is, the shorter the braking distance is, and the shortest braking distance is calculated by V S1 Initial braking speed S 4 For the shortest braking time and V S2 The shortest braking distance is calculated for the braking acceleration, so that the sliding distance of the train can be reduced, the corresponding timeliness of the braking of the train is improved, and the occurrence rate of accidents is reduced; the braking distance of the train is shortened, the stopping time of the train is reduced, the congestion condition of personnel waiting for the train is reduced, the energy consumption of the train is reduced, the running cost of the train is reduced, and the running efficiency of the train is improved. When the preliminary calculation result, the first depth calculation result and the second calculation depth result are smaller than the shortest braking distance, the vehicle is not braked until the start, so that whether emergency braking is started or not is determined by combining the detection distance and the comparison of the shortest braking distance, and the running safety of the train can be greatly improved.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (8)
1. The subway train unmanned detection and identification system based on edge calculation is characterized by comprising a sensor group, an edge gateway module, an edge calculation module, a main control module and a cloud service platform; the digital signal output end of the sensor group is connected with the digital signal input end of the edge gateway module, the digital signal output end of the edge gateway module is connected with the digital signal input end of the edge computing module, the digital signal output end of the edge computing module is respectively connected with the digital signal input ends of the main control module and the cloud service platform, and the digital signal output end of the cloud service platform is connected with the digital signal input end of the main control module; the edge gateway module comprises a data preprocessing module, a network connection module and a security authentication module; collecting environmental data of the train surrounding environment through a sensor group, sending the environmental data to an edge gateway module, preprocessing and encrypting the environmental data through the edge gateway module to obtain safety data, sending the safety data to an edge computing module, performing preliminary computation on the safety data through the edge computing module, respectively sending the preliminary computation results to a main control module and a cloud service platform, performing depth computation on the safety data through the cloud service platform to obtain a depth computation result, and controlling a detection recognition system by the main control module according to the preliminary computation result and the depth computation result;
The edge computing module performs preliminary computation on the security data, including:
s301, the edge computing module decrypts the safety data through the edge device computing module to obtain decrypted safety data;
s302, the edge computing module sequentially extracts obstacle distance parameters acquired by a laser sensor, an ultrasonic sensor, a camera and a radar sensor from the safety data through an edge equipment computing module, and sends the obstacle distance parameters to a data fusion module;
s303, the data fusion module carries out data fusion processing on the obstacle distance parameters acquired by the laser sensor, the ultrasonic sensor, the camera and the radar sensor through a data fusion model to acquire comprehensive distance parameters;
the comprehensive distance parameter is a preliminary calculation result, and the data fusion model is as follows:
wherein L represents a data fusion model, S 1 Representing the detection time of the radar sensor, V 1 Representing the detection speed of the radar sensor, m 1 Representing the occupied area of the obstacle shot by the camera in the photo, Z represents the pixel size of the object acquired by the camera in the pixels, L S Representing the distance between the camera and the object, Y 1 Representing the time difference between the ultrasonic sensor and the obstacle, S 2 Representing the sound velocity of the ultrasonic wave; q represents the speed of light of the laser sensor; y is Y 2 Representing the time difference between the laser sensor and the obstacle, W 1 Weight of radar sensor, W 2 Weight of camera, W 3 Weight of ultrasonic sensor, W 4 Weights for the laser sensors;
and S304, the data fusion module sends the comprehensive distance parameters to the main control module and the cloud service platform.
2. The subway train unmanned detection and recognition system based on edge calculation according to claim 1, wherein the connection relation among the data preprocessing module, the network connection module and the security authentication module of the edge gateway module is as follows:
the digital signal input end of the data preprocessing module is the digital signal input end of the edge gateway module;
the digital signal output end of the data preprocessing module is the digital signal output end of the edge gateway module;
the data preprocessing module is in bidirectional communication connection with the safety authentication module;
the network connection module is connected in a manner of WiFi, zigBee and Bluetooth.
3. The subway train unmanned detection and recognition system based on edge calculation according to claim 1, wherein the edge calculation module comprises an edge equipment calculation module and a data fusion module;
The digital signal input end of the edge equipment computing module is the digital signal input end of the edge computing module;
the digital signal output end of the edge equipment computing module is connected with the digital signal input end of the data fusion module;
the digital signal output end of the data fusion module is the digital signal output end of the edge calculation module.
4. The edge calculation-based subway train unmanned detection and recognition system according to claim 1, wherein the main control module comprises a host memory, a host controller and a host executor;
the digital signal input end of the host memory is the digital signal input end of the main control module;
the digital signal output end of the host memory is connected with the digital signal input end of the host controller;
the control signal output end of the host controller is connected with the control signal input end of the host executor;
and the execution signal output end of the host executor is connected with the execution signal input end of the controlled equipment of the detection and identification system.
5. The edge calculation-based unmanned detection and identification system for subway trains according to claim 2, wherein the detection and identification step of the detection and identification system comprises the following steps:
S1, acquiring data of environmental information of a train by using the sensor group, and acquiring various environmental data corresponding to the environmental information of the train; and sending the environmental data to an edge gateway module;
s2, the edge gateway module performs preprocessing on the environmental data to obtain preprocessed environmental data, encrypts the preprocessed environmental data to obtain safety data, and sends the safety data to the edge computing module;
s3, the edge calculation module performs preliminary calculation on the safety data, in the process, the edge calculation module sends obstacle distance parameters acquired by the sensor group to the data fusion module, the data fusion module obtains a preliminary calculation result through data fusion processing, and the preliminary calculation result is respectively sent to the main control module and the cloud service platform;
s4, the cloud service platform performs comprehensive arrangement and depth calculation on the safety data to obtain a depth calculation result, and sends the depth calculation result to a main control module;
s5, the main control module generates a control instruction according to the preliminary calculation result and the depth calculation result to control the detection and identification system.
6. The system for detecting and identifying unmanned subway train on the basis of edge calculation according to claim 5, wherein the step of collecting the environmental information of the train by using the sensor group comprises the following steps:
s101, the sensor group respectively acquires data of four objects in the surrounding environment of the train through a laser sensor, an ultrasonic sensor, a camera and a radar sensor to obtain a laser signal, an ultrasonic signal, a camera signal and a radar signal;
s102, the sensor group sends the collected laser signals, ultrasonic signals, shooting signals and radar signals to the edge gateway module.
7. The edge computing-based subway train unmanned detection and recognition system according to claim 5, wherein the step of preprocessing and encrypting the environmental data by the edge gateway module comprises:
s201, the edge gateway module performs preprocessing of cleaning, noise reduction, filtering, de-duplication and format conversion on environmental data of four objects in the train surrounding environment by using a data preprocessing module to obtain preprocessed environmental data, and sends the preprocessed environmental data to the security authentication module;
S202, the safety authentication module encrypts the preprocessed environment data to obtain the safety data, and the safety data is sent to the edge calculation module.
8. The system for detecting and identifying unmanned subway train based on edge calculation according to claim 5, wherein the step of comprehensively sorting and calculating depth of the safety data by the cloud service platform comprises the following steps:
s401, after receiving a preliminary calculation result, the cloud service platform performs depth calculation through a first depth calculation model to obtain a first depth calculation result;
wherein L is 1 For the first depth calculation result, c is the speed of light of the radar, t is the flight time of the echo signal of the radar, m 2 Representing the occupied area of the obstacle shot by the camera in the photo, Z represents the pixel size of the object acquired by the camera in the pixels, L S Representing the distance between the camera and the object s j Sound velocity, t, of ultrasonic wave j The detection time of the ultrasonic wave; q represents the speed of light of the laser sensor; y is Y 2 Representing the time difference between the laser sensor and the obstacle, W 1 Weight of radar sensor, W 2 Weight of camera, W 3 Weight of ultrasonic sensor, W 4 Weights for the laser sensors;
s402, after receiving the preliminary calculation result, the cloud service platform performs depth calculation through a second depth calculation model to obtain a second depth calculation result;
L 2 ＝L 1 +ΔL；
wherein L is 2 Calculating a junction for a second depthIf DeltaL is the compensation time, t 0 For delay time, t 1 Time required for varying a distance unit;
s403, the cloud service platform sends the first depth calculation result and the second depth calculation result to a main control module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310589454.6A CN116319795B (en) | 2023-05-24 | 2023-05-24 | Unmanned detection and identification system of subway train based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310589454.6A CN116319795B (en) | 2023-05-24 | 2023-05-24 | Unmanned detection and identification system of subway train based on edge calculation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116319795A CN116319795A (en) | 2023-06-23 |
| CN116319795B true CN116319795B (en) | 2023-08-01 |
Family
ID=86818978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310589454.6A Active CN116319795B (en) | 2023-05-24 | 2023-05-24 | Unmanned detection and identification system of subway train based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116319795B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110989505A (en) * | 2019-10-28 | 2020-04-10 | 中国人民解放军96782部队 | Unmanned command and dispatch system based on ground equipment machine vision |
| CA3144397A1 (en) * | 2019-07-19 | 2021-01-28 | Mark GORSKI | An unmanned aerial vehicle (uav)-based system for collecting and distributing animal data for monitoring |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111556469A (en) * | 2020-04-08 | 2020-08-18 | 深圳供电局有限公司 | Computing system and computing method for artificial intelligence edge |
| AU2020103519A4 (en) * | 2020-11-18 | 2021-01-28 | Sanjay Bhaskar Zope | IFAC- Driver Less Vehicle: Driver Less Intelligent Fully Autonomous Controlled Vehicle |
| CN115035087A (en) * | 2022-06-28 | 2022-09-09 | 中车青岛四方车辆研究所有限公司 | Novel railway line image detection method and system |
| CN115661057A (en) * | 2022-10-18 | 2023-01-31 | 中海石油气电集团有限责任公司 | Industrial nondestructive testing system and method based on cloud edge cooperation and deep learning |
| CN115657600A (en) * | 2022-11-02 | 2023-01-31 | 重庆大学 | CNN-BLRNET thermal error prediction model and transfer learning method and intelligent integrated framework thereof |
-
2023
- 2023-05-24 CN CN202310589454.6A patent/CN116319795B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA3144397A1 (en) * | 2019-07-19 | 2021-01-28 | Mark GORSKI | An unmanned aerial vehicle (uav)-based system for collecting and distributing animal data for monitoring |
| CN110989505A (en) * | 2019-10-28 | 2020-04-10 | 中国人民解放军96782部队 | Unmanned command and dispatch system based on ground equipment machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116319795A (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111964922A (en) | Intelligent driving vehicle test system | |
| CN109084794B (en) | Path planning method | |
| CN108369645A (en) | Taxi operation monitoring method, device, storage medium and system | |
| CN105976450A (en) | Unmanned vehicle data processing method and device, and black box system | |
| CN113240909A (en) | Vehicle monitoring method, equipment, cloud control platform and vehicle road cooperative system | |
| US12030476B2 (en) | Safe driving support system based on mobile IoT agent and method for processing thereof | |
| CN102881162A (en) | Data processing and fusion method for large-scale traffic information | |
| CN106548630B (en) | A kind of detection method and device of driving behavior | |
| KR101837096B1 (en) | Proxy device for car and method for managing the data from car | |
| KR101564381B1 (en) | System for controlling overloaded vehicle using axle-load weighting machine | |
| CN113724531B (en) | Intersection human-vehicle road cooperation early warning system and method under Internet of vehicles environment | |
| CN108549862A (en) | Abnormal scene detection method and device | |
| JP5874553B2 (en) | Driving characteristic diagnosis system, driving characteristic diagnosis device | |
| CN110796869B (en) | Method and device for detecting illegal car following | |
| CN108389392A (en) | A kind of traffic accident responsibility identification system based on machine learning | |
| US9620029B2 (en) | Method and device for identifying behaviour of a vehicle driver | |
| CN117576920B (en) | Traffic control system based on unmanned aerial vehicle | |
| CN116319795B (en) | Unmanned detection and identification system of subway train based on edge calculation | |
| CN117690296A (en) | Intelligent lightning protection detection system for traffic road conditions | |
| CN108012119B (en) | Real-time video transmission method, transmission system and readable storage medium | |
| KR20140056674A (en) | Commnication service system, method and apparatus for supporting process of accident in the system | |
| Kidambi et al. | Sensitivity of automated vehicle Operational Safety Assessment (OSA) metrics to measurement and parameter uncertainty | |
| CN114333331B (en) | Method and system for identifying vehicle passing information and vehicle weight of multi-lane bridge | |
| KR102188567B1 (en) | System for monitoring the road using 3 dimension laser scanner | |
| KR20150125266A (en) | Incident monitoring system and method based on incident vehicle information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |