CN116118813B - Intelligent monitoring and early warning method and system for running safety of railway locomotive - Google Patents
Intelligent monitoring and early warning method and system for running safety of railway locomotive Download PDFInfo
- Publication number
- CN116118813B CN116118813B CN202310041435.XA CN202310041435A CN116118813B CN 116118813 B CN116118813 B CN 116118813B CN 202310041435 A CN202310041435 A CN 202310041435A CN 116118813 B CN116118813 B CN 116118813B
- Authority
- CN
- China
- Prior art keywords
- control
- result
- locomotive
- information
- early warning
- 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
- 230000003137 locomotive effect Effects 0.000 title claims abstract description 213
- 238000012544 monitoring process Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000011156 evaluation Methods 0.000 claims abstract description 66
- 230000002159 abnormal effect Effects 0.000 claims abstract description 50
- 238000012545 processing Methods 0.000 claims abstract description 6
- 230000004044 response Effects 0.000 claims description 69
- 238000012795 verification Methods 0.000 claims description 68
- 230000003993 interaction Effects 0.000 claims description 30
- 238000012216 screening Methods 0.000 claims description 19
- 238000003709 image segmentation Methods 0.000 claims description 14
- 238000001514 detection method Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 10
- 230000008569 process Effects 0.000 abstract description 7
- 230000005856 abnormality Effects 0.000 description 8
- 230000001133 acceleration Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 4
- 210000000744 eyelid Anatomy 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 210000001747 pupil Anatomy 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000000873 masking effect Effects 0.000 description 2
- 230000015654 memory Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 206010041349 Somnolence Diseases 0.000 description 1
- 208000003443 Unconsciousness Diseases 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000007665 sagging Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61C—LOCOMOTIVES; MOTOR RAILCARS
- B61C17/00—Arrangement or disposition of parts; Details or accessories not otherwise provided for; Use of control gear and control systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/06—Alarms for ensuring the safety of persons indicating a condition of sleep, e.g. anti-dozing alarms
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Emergency Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention provides an intelligent monitoring and early warning method and system for railway locomotive running safety, which relate to the technical field of data processing, wherein an image acquisition device is used for controlling video acquisition of a user, an abnormal action recognition feature set is used for carrying out feature recognition of the video acquisition set to obtain a feature recognition result, and actual control information is read to obtain a control information reading result; and comparing the control accuracy according to the control information reading result and the locomotive control information, generating a control evaluation result, evaluating the driving state of a control user according to the characteristic recognition result and the control evaluation result, and generating early warning information of driving safety according to the driving state evaluation result. The method solves the technical problems that in the prior art, the driving state of a locomotive driver is monitored to be mechanically dead, so that the driving risk of the locomotive is avoided, and the effectiveness is insufficient. The technical effect of improving the monitoring effectiveness of the driving state of the locomotive driver and the effectiveness of risk avoidance in the running process of the locomotive is achieved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an intelligent monitoring and early warning method and system for running safety of a railway locomotive.
Background
Railway traffic has the advantages of large carrying capacity, strong transportation capacity and low long-distance transportation cost, and is widely paved in countries around the world for transportation, and along with continuous innovation and speed improvement of railway technology, the railway transportation time interval is also continuously shortened.
Along with the speed increase of the railway locomotive, the track traffic has more strict requirements on the driving concentration of locomotive drivers and the response capability of emergency conditions. The current method for keeping the concentration of locomotive drivers is that the locomotive is provided with a pedal as an early warning device, the driver is required to step on the pedal every 30 seconds when driving the locomotive, so that the driver is in a clear and normal state when driving the locomotive, and the method loses the reminding function after the driver forms muscle memory.
In the prior art, the driving state of a locomotive driver is monitored to be mechanically dead, so that the technical problem of insufficient effectiveness in avoiding the driving risk of the locomotive is caused.
Disclosure of Invention
The application provides an intelligent monitoring and early warning method and system for running safety of a railway locomotive, which are used for solving the technical problem that the running risk avoidance effectiveness of the locomotive is insufficient due to the fact that the driving state of a locomotive driver is monitored to be mechanically dead in the prior art.
In view of the problems, the application provides an intelligent monitoring and early warning method and system for running safety of a railway locomotive.
The application provides an intelligent monitoring and early warning method for running safety of a railway locomotive, which comprises the following steps: acquiring locomotive control information of a target locomotive and basic information of a control user; the image acquisition device is adjusted and arranged according to the basic information, and video acquisition of the control user is carried out through the image acquisition device, so that a video acquisition set is obtained; constructing an abnormal action recognition feature set, and carrying out feature recognition of the video acquisition set through the abnormal action recognition feature set to obtain a feature recognition result; reading actual control information of the target locomotive through the data interaction device to obtain a control information reading result; performing control accuracy comparison according to the control information reading result and the locomotive control information to generate a control evaluation result; and carrying out driving state evaluation of the control user according to the characteristic recognition result and the control evaluation result, and generating early warning information of driving safety according to the driving state evaluation result.
In a second aspect of the present application, there is provided an intelligent monitoring and early warning system for running safety of a railway locomotive, the system comprising: the basic information acquisition module is used for acquiring locomotive control information of the target locomotive and basic information of a control user; the video acquisition execution module is used for adjusting the layout image acquisition device according to the basic information, and carrying out video acquisition of the control user through the image acquisition device to obtain a video acquisition set; the feature recognition executing module is used for constructing an abnormal action recognition feature set, and carrying out feature recognition of the video acquisition set through the abnormal action recognition feature set to obtain a feature recognition result; the control information reading module is used for reading the actual control information of the target locomotive through the data interaction device to obtain a control information reading result; the control evaluation obtaining module is used for comparing the control accuracy according to the control information reading result and the locomotive control information to generate a control evaluation result; and the early warning information generation module is used for carrying out driving state evaluation of the control user according to the characteristic identification result and the control evaluation result and generating early warning information of driving safety according to the driving state evaluation result.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
The method provided by the embodiment of the application acquires locomotive control information of the target locomotive and basic information of a control user through acquisition, wherein the basic information is used for later reference layout and can be used for more clearly and accurately acquiring the image of the real-time dynamic driving action of the control user driving the target locomotive; the image acquisition device is adjusted and arranged according to the basic information, video acquisition of the control user is carried out through the image acquisition device, a video acquisition set is obtained, and a user of the video acquisition set subsequently extracts image frames to judge whether a driving state abnormality exists in an analysis target user or not; an abnormal action recognition feature set is constructed, feature recognition of the video acquisition set is carried out through the abnormal action recognition feature set, and a feature recognition result is obtained, so that whether the user has driving fatigue or is not concentrated or not can be judged and controlled scientifically and accurately; reading actual control information of the target locomotive through the data interaction device to obtain a control information reading result; performing control accuracy comparison according to the control information reading result and the locomotive control information to generate a control evaluation result; and carrying out driving state evaluation of the control user according to the characteristic recognition result and the control evaluation result, and generating early warning information of driving safety according to the driving state evaluation result. The technical effects of improving the monitoring effectiveness of the driving state of a locomotive driver, improving the risk avoidance effectiveness in the running process of the locomotive and improving the running safety of the locomotive are achieved.
Drawings
FIG. 1 is a schematic flow chart of an intelligent monitoring and early warning method for running safety of a railway locomotive according to an embodiment;
FIG. 2 is a schematic flow chart of obtaining feature recognition results in an intelligent monitoring and early warning of railway locomotive driving safety in one embodiment;
FIG. 3 is a schematic flow chart of obtaining hierarchical speed control information in an intelligent monitoring and early warning of railway locomotive driving safety in one embodiment;
FIG. 4 is a block diagram of an intelligent monitoring and early warning system for safety of a railroad locomotive in one embodiment.
Reference numerals illustrate: the system comprises a basic information acquisition module 1, a video acquisition execution module 2, a feature recognition execution module 3, a control information reading module 4, a control evaluation acquisition module 5 and an early warning information generation module 6.
Detailed Description
The application provides an intelligent monitoring and early warning method and system for running safety of a railway locomotive, which are used for solving the technical problem that the running risk avoidance effectiveness of the locomotive is insufficient due to the fact that the driving state of a locomotive driver is monitored to be mechanically dead in the prior art. The technical effects of improving the monitoring effectiveness of the driving state of a locomotive driver, improving the risk avoidance effectiveness in the running process of the locomotive and improving the running safety of the locomotive are achieved.
The technical scheme of the invention obtains, stores, uses, processes and the like the data, which all meet the relevant regulations of national laws and regulations.
In the following, the technical solutions of the present invention will be clearly and completely described with reference to the accompanying drawings, and it should be understood that the described embodiments are only some embodiments of the present invention, but not all embodiments of the present invention, and that the present invention is not limited by the exemplary embodiments described herein. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention. It should be further noted that, for convenience of description, only some, but not all of the drawings related to the present invention are shown.
Example 1
As shown in fig. 1, the application provides an intelligent monitoring and early warning method for running safety of a railway locomotive, the method is applied to an intelligent monitoring and early warning system, the intelligent monitoring and early warning system is in communication connection with an image acquisition device and a data interaction device, and the method comprises the following steps:
s100, acquiring locomotive control information and basic information of a control user of a target locomotive;
specifically, it should be appreciated that a railroad locomotive is operating in normal weather and track conditions to perform passenger freight tasks according to a locomotive consist schedule, and thus in this embodiment, a locomotive schedule for the target locomotive is obtained based on the locomotive number of the target locomotive, and the locomotive control information is obtained based on the locomotive schedule, the locomotive control information including a plurality of railroad section speed control information, such as Beijing-Tianjin section 212km/h.
In an ideal state, a control user, namely a locomotive driver, carries out driving control on the target locomotive based on the locomotive control information, so that the target locomotive can pass through each along-road station strictly according to a locomotive schedule.
The control user is a locomotive driver, the basic information comprises sitting height data and posture data of the locomotive driver in a working state, and the basic information is used for subsequent reference layout and can be used for clearly and accurately acquiring the real-time dynamic driving action image of the locomotive of the control user driving target.
S200, adjusting and arranging the image acquisition device according to the basic information, and acquiring video of the control user through the image acquisition device to obtain a video acquisition set;
Specifically, in this embodiment, the image capturing device is a monitoring camera that is pre-arranged in the cab of the target locomotive, and based on the basic information, the sitting height and posture data of the control user in the cab of the locomotive are obtained, and the height angle adjustment and correction of the image capturing device are correspondingly performed, so as to ensure that the image capturing device can completely and clearly capture the facial dynamic image of the control user. And in the running process of the control user driving target locomotive, the image acquisition device synchronously acquires the video of the control user, mainly acquires the face video of the control user, and obtains a video acquisition set, and the video acquisition set user subsequently extracts image frames to judge and analyze whether the driving state of the target user is abnormal, for example, analyze the eye characteristics and the mouth characteristics of the control user, and identify and judge whether the fatigue driving possibility exists for the target user.
S300, constructing an abnormal action recognition feature set, and carrying out feature recognition of the video acquisition set through the abnormal action recognition feature set to obtain a feature recognition result;
in one embodiment, as shown in fig. 2, the method steps provided by the present application further include:
s310, extracting video frames from the video acquisition set, and screening key frames of video frame extraction results according to detection characteristics to obtain key frame screening results;
s320, performing image segmentation on the key frame screening result according to the layout result of the image acquisition device and the detection characteristic to obtain a plurality of characteristic image segmentation results;
S330, feature similarity matching is carried out on the plurality of feature image segmentation results through the abnormal action recognition feature set, and matching features and matching similarity data are counted;
and S340, obtaining the feature recognition result according to the matching feature and the matching similarity data.
Specifically, it should be appreciated that since the control user is relatively reluctant to perform the target locomotive driving control process, it is necessary to ensure that the control user is focused and is in a state of normal conscious reaction throughout the target locomotive driving.
In this embodiment, the method for controlling the driving state recognition of the user is to construct an abnormal motion recognition feature set including a state feature in which eyes are abnormally opened and closed (eye pupils are shielded by the upper eyelid by 25%) and in which the mouth is abnormally opened and closed (upper and lower lips are spaced by 3 cm), that is, in which eyes are involuntarily hard to be completely opened and involuntarily yawned when the human is drowsy. And carrying out feature recognition on the video acquisition set based on preset abnormal action recognition features to obtain feature recognition results, wherein the feature recognition results are the similarity between the real-time eye mouth image of the control user and the abnormal action features, and the higher the similarity is, the more likely the control user is in a drowned or inattentive state.
The method comprises the steps that a railway bureau stipulates that a locomotive is required to be provided with a pedal as an early warning device, a driver steps on the pedal every 30 seconds while driving the locomotive, so that the condition that the driver wakes up normally when driving the locomotive is confirmed as a reference.
The key frame refers to a frame where a key action in the motion change of an object is located, and in this embodiment, the key frame is a frame which controls the eyelid sagging of a user to close eyes and a frame which controls the mouth opening of the user to merge.
And presetting detection characteristics, namely blink characteristics and mouth opening characteristics, for carrying out key frame screening and extraction on the video frame extraction result. And carrying out key frame screening on the video frame extraction result according to the detection characteristics to obtain a key frame screening result, wherein the key frame screening result is a plurality of image frames for controlling blink images and/or opening and closing mouth images of the user.
In this embodiment, in order to improve the feature recognition of the key frame screening result based on the abnormal action recognition feature, the accuracy of the feature recognition result is obtained, and before the abnormal action recognition of the key frame screening result is performed, the image area of the image of the key frame screening result is divided, and the abnormal opening and closing of the eyes and the abnormal opening and closing of the mouth are respectively performed.
Specifically, the position of the face of the user in the image acquisition picture is determined and controlled according to the layout result of the image acquisition device, the image region segmentation is performed on the key frame screening result, a plurality of characteristic image segmentation results are obtained, for example, the key frame screening result is processed according to the following 5:5 or 6:4 are divided horizontally into two parts, the upper image only controls the eye region image of the user, and the lower image only controls the mouth region image of the user.
And respectively carrying out feature similarity matching on the plurality of feature image segmentation results through the abnormal action recognition feature set, specifically, based on the feature image segmentation result recognition, calculating and controlling the masking proportion of the pupil of the user to the upper eyelid, and based on the feature image segmentation result recognition, calculating and controlling the distance between the upper lip and the lower lip of the user.
And taking the abnormal opening and closing feature data of the eyes and the abnormal opening and closing feature data of the mouth as denominators, controlling the masking proportion of the pupil of the user by the upper eyelid and controlling the distance between the upper lip and the lower lip of the user to be a numerator, calculating to obtain eye matching similarity data and mouth matching similarity data, and adding the two matching similarity data serving as the screening result of the same key frame to generate the feature recognition result. The feature recognition result reflects the similarity between the eye mouth and the abnormal action recognition feature of the drowsiness state characterization at a certain time node of the control user. The larger the feature recognition result value, the higher the likelihood that the controlling user is in an unconscious or inattentive state.
According to the embodiment, the technical effects of scientifically and accurately judging whether the control user has driving fatigue or is not concentrated or not are achieved by acquiring the facial image video of the control user and extracting the key frame to execute image region segmentation to conduct abnormal action recognition feature comparison.
S400, reading actual control information of the target locomotive through the data interaction device to obtain a control information reading result;
Specifically, in this embodiment, the data interaction device is a data sensor connected to the cab of the target locomotive, and is configured to collect and acquire data information of the target locomotive in real time, including, but not limited to, real-time vehicle speed, locomotive acceleration, and braking conditions.
And reading actual control information of the target locomotive through the data interaction device to obtain a control information reading result, wherein the control information reading result comprises the current speed per hour of the locomotive, the acceleration of the locomotive and the state of a braking device, such as 53km/h, -5km/h, and the target locomotive slides in neutral.
S500, comparing control accuracy according to the control information reading result and the locomotive control information to generate a control evaluation result;
And acquiring a railway section where the target locomotive corresponding to the control information reading result is positioned, extracting railway section speed control information from the locomotive control information, and comparing accuracy of speed data and acceleration data to generate the control evaluation result, wherein the control evaluation result is the deviation percentage of the actual target locomotive running speed and the theoretical target locomotive running speed.
And S600, carrying out driving state evaluation of the control user according to the characteristic identification result and the control evaluation result, and generating early warning information of driving safety according to the driving state evaluation result.
Specifically, in this embodiment, the driving state evaluation of the control user is performed according to the feature recognition result and the control evaluation result, the early warning information of driving safety is generated according to the driving state evaluation result, and the control user is prompted and controlled to improve the concentration of driving attention and perform vehicle speed control based on the early warning information, so that the driving speed of the target locomotive is adjusted to be close to the locomotive control information.
The embodiment acquires locomotive control information of the target locomotive and basic information of a control user through acquisition, wherein the basic information is used for subsequent reference layout, and the image acquisition device can acquire and control real-time dynamic driving action images of the user driving the target locomotive more clearly and accurately; the image acquisition device is adjusted and arranged according to the basic information, video acquisition of the control user is carried out through the image acquisition device, a video acquisition set is obtained, and a user of the video acquisition set subsequently extracts image frames to judge whether a driving state abnormality exists in an analysis target user or not; an abnormal action recognition feature set is constructed, feature recognition of the video acquisition set is carried out through the abnormal action recognition feature set, and a feature recognition result is obtained, so that whether the user has driving fatigue or is not concentrated or not can be judged and controlled scientifically and accurately; reading actual control information of the target locomotive through the data interaction device to obtain a control information reading result; performing control accuracy comparison according to the control information reading result and the locomotive control information to generate a control evaluation result; and carrying out driving state evaluation of the control user according to the characteristic recognition result and the control evaluation result, and generating early warning information of driving safety according to the driving state evaluation result. The technical effects of improving the monitoring effectiveness of the driving state of a locomotive driver, improving the risk avoidance effectiveness in the running process of the locomotive and improving the running safety of the locomotive are achieved.
In one embodiment, as shown in fig. 3, the intelligent monitoring and early warning system is in communication connection with an information interaction sensor, and the method comprises:
S710, acquiring railway information through the information interaction sensor to obtain an information acquisition result;
s720, obtaining real-time speed information of the target locomotive through the data interaction device;
S730, inputting the real-time speed information and the information acquisition result into a multi-stage speed regulation control model to obtain stage speed control information;
and S740, sending the information acquisition result and the grading speed control information to the target locomotive.
Specifically, in this embodiment, the information interaction sensor is a comprehensive sensor disposed near a driving rail of the target locomotive, and may perform image acquisition of the rail in a certain section and real-time speed acquisition of the target locomotive.
And the information interaction sensor is used for acquiring railway surrounding image information to obtain an information acquisition result, and rail passing faults such as whether the rail has a protection network leak, whether the rail has animal passing, whether the rail has derailment fracture faults and the like can be intuitively obtained based on the information acquisition result.
And acquiring real-time speed information of the target locomotive through the data interaction device, wherein the real-time speed information is actual running speed data of the target locomotive on a rail after running speed control is performed based on a control user.
And constructing a multistage speed regulation control model, wherein the multistage speed regulation control model is an image data analysis model which can judge whether rail passing faults which cannot normally pass exist in the rail according to rail images and is generated by combining the rail passing fault rail distance of the target locomotive from the rail passing faults.
The multistage speed regulation control model comprises an image recognition sub-module and a speed regulation control scheme generation sub-module, wherein the image recognition sub-module is a traditional image recognition model, and the image recognition sub-module is used for recognizing and judging whether a rail which is passed by a target locomotive in the future has the defect of no passing or not based on an information acquisition result. When the recognition output result of the image recognition sub-module is that the rail has the defect of preventing the target locomotive from passing normally, the distance coordinate of the rail is input into the speed regulation control scheme generation sub-module, and the speed regulation control scheme generation sub-module generates the grading speed control information according to the distance coordinate of the rail, the current distance coordinate of the target locomotive and the real-time speed information.
The grading speed control information is related to the real-time speed of the target locomotive and the distance between the target locomotive and the position where the rail passing fault exists, the slower the real-time speed of the target locomotive is, the farther the distance between the target locomotive and the position where the rail passing fault exists is, the smaller the control acceleration of the target locomotive of the grading speed control information is, and the larger the time interval reserved for the control user to respond and carry out the control and adjustment of the speed of the target locomotive is.
And sending the information acquisition result and the grading speed control information to the target locomotive, and obtaining a rail passing fault of a track through which the target locomotive is about to run by a control user of the driving target locomotive based on the information acquisition result, and obtaining a target locomotive speed control reference safely stopped before passing obstruction based on the grading speed control information. The method and the device have the advantages that the obstruction of the passage of the railway in front of the control user is realized, so that the control user can know and change the scheduled driving control reason, and the control user can be supplied with a target locomotive speed control reference scheme, so that the technical effects of improving the knowledge degree of the control user on the driving prospect of the target locomotive and improving the obstacle avoidance effectiveness of the driving control of the target locomotive are achieved.
In one embodiment, the method steps provided by the application further comprise:
S750, matching a response verification window according to the grading speed control information and the driving state evaluation result;
s760, performing response verification of the control user through the response verification window to obtain a response verification result;
s770, judging whether the response verification result meets a preset control threshold value;
S780, when the response verification result cannot meet the preset control threshold, generating an early warning automatic control instruction;
s790, performing early warning control on the target locomotive through the early warning automatic control instruction.
In one embodiment, the method steps provided by the application further comprise:
S781, the response verification window is sent to the multi-stage speed regulation control model;
S782, obtaining a model output result of the multi-stage speed regulation control model, wherein the model output result comprises adjustment grading speed control information;
And S783, early warning control of the target locomotive is carried out based on the model output result according to the early warning automatic control instruction.
In particular, it should be understood that, in theory, after the information collection result and the classification speed control information are sent to the target locomotive, the target locomotive can be safely stopped at the rail passing fault by means of the speed control adjustment of the target locomotive performed by the control user, but when the situation is urgent, the classification speed control information is reserved for the control user to respond and perform the speed control adjustment of the target locomotive, that is, the distance between the rail passing fault and the target locomotive is smaller, and when the control user is in inattention or tired driving, there is a speed control execution delay, and the control user cannot perform the speed control adjustment of the target locomotive according to the original classification speed control information so that the target locomotive stops before reaching the rail passing fault.
Thus, in this embodiment, a plurality of response verification windows are preset, where the response verification windows are used to verify whether the control user reacts within the reserved response time, so that the speed control of the target locomotive needs to be performed based on the hierarchical speed control information. The verification duration of each response verification window in the response verification windows, namely the preset control threshold value is different, and has a corresponding relation with a time interval reserved for the control user to respond and perform target locomotive speed control adjustment in the grading speed control information. The longer the time interval of the hierarchical speed control information reserved for the control user to respond and carry out target locomotive speed control adjustment, the longer the time interval of the preset control threshold value of the corresponding response verification window, and vice versa, the shorter the time interval.
In this embodiment, a response verification window is obtained by extracting and obtaining a time interval reserved for the control user to respond and performing target locomotive speed control adjustment according to the hierarchical speed control information. And carrying out response verification of the control user through the response verification window to obtain a response verification result.
And judging whether the response verification result meets the preset control threshold value of the corresponding response verification interval or not, namely judging whether a control user reacts in the reserved response time length to need to control the speed of the target locomotive and starting to execute the speed control.
And when the response verification result cannot meet the preset control threshold value, generating an early warning automatic control instruction, and calling the data interaction device to secondarily obtain real-time speed information of the target locomotive and distance information between the target locomotive and a rail passing fault based on the early warning automatic control instruction.
And transmitting the response verification window, the real-time speed information and the current distance coordinates of the target locomotive and the target locomotive to the multi-stage speed regulation control model based on the early warning automatic control instruction, and generating the grading speed control information again by combining the current distance coordinates of the target locomotive and the real-time speed information according to the distance coordinates of the rail by the speed regulation control scheme generation submodule based on the multi-stage speed regulation control model, namely, adjusting the grading speed control information. And controlling the early warning speed of the target locomotive by a control user based on the model output result.
The embodiment realizes the technical effects that the secondary adjustment of the grading speed control information is carried out according to the response state of the control user to the grading speed control information so as to avoid the risk that the target locomotive can not be safely stopped by the target locomotive control based on the original grading speed control information after the target locomotive has traveled a longer distance on the track when the control user responds to the need of the target locomotive brake control.
In one embodiment, the method steps provided by the application further comprise:
s910, judging whether the driving state evaluation result meets a preset driving state evaluation threshold value;
S920, when the driving state evaluation result cannot meet the preset driving state evaluation threshold, carrying out emergency response verification on the response verification window;
and S930, when the response verification window is an emergency response window, controlling the target locomotive through the grading speed control information.
Specifically, it should be understood that if the driving state of the control user is poor, the reaction force and the control force on the target locomotive are both in a weak state, and the fault distance between the target locomotive and the rail passing is small, the speed adjustment control of the target locomotive cannot be completed by the control user to avoid the rail passing fault.
Thus, in the present embodiment, the preset is used to evaluate whether or not the preset driving state evaluation threshold value, which can be defined based on the characteristic recognition result values when the response force of the plurality of control users is low, can be controlled based on the control user execution target locomotive speed.
Judging whether the driving state evaluation result meets a preset driving state evaluation threshold value, when the driving state evaluation result cannot meet the preset driving state evaluation threshold value, indicating that a current control user does not have the working capacity of controlling the emergency obstacle avoidance of the target locomotive, performing emergency response verification on the response verification window, wherein the emergency response verification is that the response verification result cannot meet the preset control threshold value and the target locomotive is controlled by the control user without generating the adjustment grading speed control information when the response verification result is verification that the control user cannot meet the preset control threshold value in the current driving state, and the target locomotive is driven to reach the railway passing fault position.
And when the response verification window is an emergency response window, the speed control of the target locomotive is directly carried out by the control user instead of the hierarchical speed control information.
According to the embodiment, when the fault distance between the target locomotive and the track passing fault is short and the driving state of the control user is poor, and the control user cannot respond to the traffic risk and control the target locomotive, the control user directly adopts the hierarchical speed control to execute the control of the target locomotive instead of the control user, so that the technical effect of improving the driving safety of the target locomotive is achieved.
In one embodiment, the method steps provided by the application further comprise:
S810, acquiring locomotive monitoring data of the target locomotive through the data interaction device;
S820, constructing an associated monitoring feature set of abnormal features, wherein the associated monitoring feature set comprises associated feature values;
S830, carrying out abnormal recognition on the locomotive monitoring data through the associated monitoring feature set;
And S840, generating state early warning information of the target locomotive according to the abnormal recognition result.
Specifically, it should be understood that when the rail locomotive has equipment operation faults, a plurality of related abnormal operation phenomena such as abnormal rise of the axle box temperature, abnormal noise of wheels and rails, abnormal wheel rotation and the like occur.
In this embodiment, therefore, according to the abnormal phenomenon when the rail locomotive has the equipment operation fault, an association monitoring feature set of abnormal features is constructed, where the association monitoring feature set includes an axle box temperature feature, an abnormal noise feature, a wheel rotation speed feature, and a feature value for judging whether each association feature meets the equipment operation fault;
and acquiring locomotive monitoring data of the target locomotive through the data interaction device, wherein the locomotive monitoring data comprise axle box temperature data, abnormal noise decibel data and wheel rotating speed data.
And carrying out one-to-one traversal comparison on the locomotive monitoring data through the association monitoring feature set, carrying out abnormality recognition, judging whether the axle box temperature data, abnormal noise decibel data and wheel rotating speed data meet fault feature values of all association features, if so, generating an abnormality recognition result, representing that equipment abnormality exists in the current target locomotive, generating state early warning information of the target locomotive according to the abnormality recognition result, reminding a target locomotive worker to carry out operation and maintenance management of the target locomotive to realize equipment fault elimination, and realizing the technical effect of improving the running safety of the target locomotive.
In one embodiment, as shown in fig. 4, there is provided an intelligent monitoring and early warning system for running safety of a railway locomotive, comprising: the system comprises a basic information acquisition module 1, a video acquisition execution module 2, a feature identification execution module 3, a control information reading module 4, a control evaluation acquisition module 5 and an early warning information generation module 6, wherein:
the basic information acquisition module 1 is used for acquiring locomotive control information of a target locomotive and basic information of a control user;
The video acquisition execution module 2 is used for adjusting and arranging the image acquisition device according to the basic information, and carrying out video acquisition of the control user through the image acquisition device to obtain a video acquisition set;
the feature recognition executing module 3 is used for constructing an abnormal action recognition feature set, and carrying out feature recognition of the video acquisition set through the abnormal action recognition feature set to obtain a feature recognition result;
The control information reading module 4 is used for reading the actual control information of the target locomotive through the data interaction device to obtain a control information reading result;
The control evaluation obtaining module 5 is used for comparing the control accuracy according to the control information reading result and the locomotive control information to generate a control evaluation result;
and the early warning information generation module 6 is used for evaluating the driving state of the control user according to the characteristic identification result and the control evaluation result and generating early warning information of driving safety according to the driving state evaluation result.
In one embodiment, the system further comprises:
the railway information acquisition unit is used for acquiring railway information through the information interaction sensor to obtain an information acquisition result;
The real-time speed acquisition unit is used for acquiring real-time speed information of the target locomotive through the data interaction device;
The grading speed control obtaining unit is used for inputting the real-time speed information and the information acquisition result into a multistage speed regulation control model to obtain grading speed control information;
And the information transmission executing unit is used for sending the information acquisition result and the grading speed control information to the target locomotive.
In one embodiment, the system further comprises:
The verification window matching unit is used for matching a response verification window according to the grading speed control information and the driving state evaluation result;
the response verification execution unit is used for carrying out response verification of the control user through the response verification window to obtain a response verification result;
the verification result judging unit is used for judging whether the response verification result meets a preset control threshold value or not;
the judging result processing unit is used for generating an early warning automatic control instruction when the response verification result cannot meet the preset control threshold value;
and the early warning control execution unit is used for carrying out early warning control on the target locomotive through the early warning automatic control instruction.
In one embodiment, the judgment result processing unit further includes:
The verification window sending unit is used for sending the response verification window to the multi-stage speed regulation control model;
The model output obtaining unit is used for obtaining a model output result of the multistage speed regulation control model, wherein the model output result comprises adjustment stage speed control information;
and the early warning control application unit is used for carrying out early warning control on the target locomotive based on the model output result according to the early warning automatic control instruction.
In one embodiment, the feature recognition execution module 3 further includes:
The key frame extraction unit is used for extracting video frames from the video acquisition set, and screening key frames of video frame extraction results according to the detection characteristics to obtain key frame screening results;
The image segmentation execution unit is used for carrying out image segmentation on the key frame screening result according to the layout result of the image acquisition device and the detection characteristic to obtain a plurality of characteristic image segmentation results;
The feature similarity matching unit is used for identifying feature similarity matching of the feature set to the plurality of feature image segmentation results through the abnormal actions, and counting matching features and matching similarity data;
and the identification result obtaining unit is used for obtaining the feature identification result according to the matching feature and the matching similarity data.
In one embodiment, the system further comprises:
The evaluation threshold comparison unit is used for judging whether the driving state evaluation result meets a preset driving state evaluation threshold;
the response verification execution unit is used for carrying out emergency response verification on the response verification window when the driving state evaluation result cannot meet the preset driving state evaluation threshold;
And the locomotive control executing unit is used for controlling the target locomotive according to the grading speed control information when the response verification window is an emergency response window.
In one embodiment, the system further comprises:
The monitoring data acquisition unit is used for acquiring locomotive monitoring data of the target locomotive through the data interaction device;
The feature set construction unit is used for constructing an associated monitoring feature set of the abnormal feature, wherein the associated monitoring feature set comprises associated feature values;
The abnormality identification execution unit is used for carrying out abnormality identification on the locomotive monitoring data through the associated monitoring feature set;
And the early warning information generation unit is used for generating state early warning information of the target locomotive according to the abnormal recognition result.
Any of the methods or steps described above may be stored as computer instructions or programs in various non-limiting types of computer memories, and identified by various non-limiting types of computer processors, thereby implementing any of the methods or steps described above.
Based on the above-mentioned embodiments of the present invention, any improvements and modifications to the present invention without departing from the principles of the present invention should fall within the scope of the present invention.
Claims (5)
1. The intelligent monitoring and early warning method for the running safety of the railway locomotive is characterized by being applied to an intelligent monitoring and early warning system, wherein the intelligent monitoring and early warning system is in communication connection with an image acquisition device and a data interaction device, and the method comprises the following steps:
Acquiring locomotive control information of a target locomotive and basic information of a control user;
The image acquisition device is adjusted and arranged according to the basic information, and video acquisition of the control user is carried out through the image acquisition device, so that a video acquisition set is obtained;
Constructing an abnormal action recognition feature set, and carrying out feature recognition of the video acquisition set through the abnormal action recognition feature set to obtain a feature recognition result;
Reading actual control information of the target locomotive through the data interaction device to obtain a control information reading result;
Performing control accuracy comparison according to the control information reading result and the locomotive control information to generate a control evaluation result;
performing driving state evaluation of the control user according to the characteristic recognition result and the control evaluation result, and generating early warning information of driving safety according to the driving state evaluation result;
The intelligent monitoring and early warning system is in communication connection with the information interaction sensor, and the method comprises the following steps:
railway information acquisition is carried out through the information interaction sensor, and an information acquisition result is obtained;
Acquiring real-time speed information of the target locomotive through the data interaction device;
inputting the real-time speed information and the information acquisition result into a multi-stage speed regulation control model to obtain hierarchical speed control information;
Transmitting the information acquisition result and the grading speed control information to the target locomotive;
the method further comprises the steps of:
Matching a response verification window according to the grading speed control information and the driving state evaluation result;
Response verification of the control user is carried out through the response verification window, and a response verification result is obtained;
Judging whether the response verification result meets a preset control threshold value or not;
when the response verification result cannot meet the preset control threshold, generating an early warning automatic control instruction;
Performing early warning control on the target locomotive through the early warning automatic control instruction;
when the response verification result cannot meet the preset control threshold, generating an early warning automatic control instruction, which specifically comprises the following steps:
transmitting the response verification window to the multi-stage speed regulation control model;
Obtaining a model output result of the multi-stage speed regulation control model, wherein the model output result comprises adjustment grading speed control information;
And performing early warning control on the target locomotive based on the model output result according to the early warning automatic control instruction.
2. The method of claim 1, wherein the method comprises:
extracting video frames from the video acquisition set, and screening key frames of video frame extraction results according to detection characteristics to obtain key frame screening results;
image segmentation of the key frame screening result is carried out according to the layout result of the image acquisition device and the detection characteristic, and a plurality of characteristic image segmentation results are obtained;
feature similarity matching is carried out on the plurality of feature image segmentation results through the abnormal action recognition feature set, and matching features and matching similarity data are counted;
and obtaining the feature recognition result according to the matching feature and the matching similarity data.
3. The method of claim 1, wherein the method comprises:
judging whether the driving state evaluation result meets a preset driving state evaluation threshold value or not;
When the driving state evaluation result cannot meet the preset driving state evaluation threshold, carrying out emergency response verification on the response verification window;
And when the response verification window is an emergency response window, controlling the target locomotive through the grading speed control information.
4. The method of claim 1, wherein the method comprises:
acquiring locomotive monitoring data of the target locomotive through the data interaction device;
constructing an associated monitoring feature set of abnormal features, wherein the associated monitoring feature set comprises associated feature values;
performing abnormal recognition on the locomotive monitoring data through the association monitoring feature set;
and generating state early warning information of the target locomotive according to the abnormal recognition result.
5. An intelligent monitoring and early warning system for running safety of a railway locomotive, which is characterized by comprising:
The basic information acquisition module is used for acquiring locomotive control information of the target locomotive and basic information of a control user;
The video acquisition execution module is used for adjusting the layout image acquisition device according to the basic information, and carrying out video acquisition of the control user through the image acquisition device to obtain a video acquisition set;
the feature recognition executing module is used for constructing an abnormal action recognition feature set, and carrying out feature recognition of the video acquisition set through the abnormal action recognition feature set to obtain a feature recognition result;
The control information reading module is used for reading the actual control information of the target locomotive through the data interaction device to obtain a control information reading result;
The control evaluation obtaining module is used for comparing the control accuracy according to the control information reading result and the locomotive control information to generate a control evaluation result;
The early warning information generation module is used for carrying out driving state evaluation of the control user according to the characteristic identification result and the control evaluation result and generating early warning information of driving safety according to the driving state evaluation result;
The system further comprises:
the railway information acquisition unit is used for acquiring railway information through the information interaction sensor to obtain an information acquisition result;
The real-time speed acquisition unit is used for acquiring real-time speed information of the target locomotive through the data interaction device;
The grading speed control obtaining unit is used for inputting the real-time speed information and the information acquisition result into a multistage speed regulation control model to obtain grading speed control information;
The information transmission executing unit is used for sending the information acquisition result and the grading speed control information to the target locomotive; the verification window matching unit is used for matching a response verification window according to the grading speed control information and the driving state evaluation result;
the response verification execution unit is used for carrying out response verification of the control user through the response verification window to obtain a response verification result;
the verification result judging unit is used for judging whether the response verification result meets a preset control threshold value or not;
the judging result processing unit is used for generating an early warning automatic control instruction when the response verification result cannot meet the preset control threshold value;
The early warning control execution unit is used for carrying out early warning control on the target locomotive through the early warning automatic control instruction;
the judgment result processing unit further includes:
The verification window sending unit is used for sending the response verification window to the multi-stage speed regulation control model;
The model output obtaining unit is used for obtaining a model output result of the multistage speed regulation control model, wherein the model output result comprises adjustment stage speed control information;
and the early warning control application unit is used for carrying out early warning control on the target locomotive based on the model output result according to the early warning automatic control instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310041435.XA CN116118813B (en) | 2023-01-12 | 2023-01-12 | Intelligent monitoring and early warning method and system for running safety of railway locomotive |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310041435.XA CN116118813B (en) | 2023-01-12 | 2023-01-12 | Intelligent monitoring and early warning method and system for running safety of railway locomotive |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116118813A CN116118813A (en) | 2023-05-16 |
| CN116118813B true CN116118813B (en) | 2024-07-19 |
Family
ID=86295151
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310041435.XA Active CN116118813B (en) | 2023-01-12 | 2023-01-12 | Intelligent monitoring and early warning method and system for running safety of railway locomotive |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116118813B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109544985A (en) * | 2017-09-22 | 2019-03-29 | 极光飞行科学公司 | Detection system for the vehicles |
| CN109747658A (en) * | 2017-11-07 | 2019-05-14 | 丰田自动车株式会社 | vehicle controls |
| CN114822034A (en) * | 2022-05-06 | 2022-07-29 | 郑州铁路职业技术学院 | Train safe driving method and system |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002123894A (en) * | 2000-10-16 | 2002-04-26 | Hitachi Ltd | Probe car control method and apparatus, and traffic control system using probe car |
| JP4367254B2 (en) * | 2004-06-16 | 2009-11-18 | 日産自動車株式会社 | VEHICLE DRIVE OPERATION ASSISTANCE DEVICE AND VEHICLE HAVING VEHICLE DRIVE OPERATION ASSISTANCE DEVICE |
| JP5332356B2 (en) * | 2008-07-08 | 2013-11-06 | 日産自動車株式会社 | Vehicle driving support device |
| EP2752348A1 (en) * | 2013-01-04 | 2014-07-09 | Continental Automotive Systems, Inc. | Adaptive emergency brake and steer assist system based on driver focus |
| CN205706706U (en) * | 2016-04-29 | 2016-11-23 | 北京蓝天多维科技有限公司 | A kind of locomotive wireless system for transmitting data |
| CN106651910A (en) * | 2016-11-17 | 2017-05-10 | 北京蓝天多维科技有限公司 | Intelligent image analysis method and alarm system for abnormal driver behavior state |
| DE102017006589A1 (en) * | 2017-07-12 | 2018-03-01 | Daimler Ag | Method for operating a driver assistance system |
| US20190092337A1 (en) * | 2017-09-22 | 2019-03-28 | Aurora Flight Sciences Corporation | System for Monitoring an Operator |
| CN107819553B (en) * | 2017-09-28 | 2020-10-30 | 青岛海信网络科技股份有限公司 | Control instruction feedback method and device |
| CN108650418B (en) * | 2018-05-09 | 2021-04-20 | 广东小天才科技有限公司 | Fatigue reminder method, device, smart terminal and storage medium |
| CN110751835B (en) * | 2019-11-06 | 2024-05-07 | 中国人民解放军战略支援部队航天工程大学士官学校 | Vehicle monitoring and early warning system and method based on Beidou navigation technology |
| CN111862565A (en) * | 2020-06-29 | 2020-10-30 | 广州小鹏车联网科技有限公司 | Vehicle remote control method and system and vehicle |
-
2023
- 2023-01-12 CN CN202310041435.XA patent/CN116118813B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109544985A (en) * | 2017-09-22 | 2019-03-29 | 极光飞行科学公司 | Detection system for the vehicles |
| CN109747658A (en) * | 2017-11-07 | 2019-05-14 | 丰田自动车株式会社 | vehicle controls |
| CN114822034A (en) * | 2022-05-06 | 2022-07-29 | 郑州铁路职业技术学院 | Train safe driving method and system |
Non-Patent Citations (1)
| Title |
|---|
| "基于DSP的轨道车运行监控装置研究";张道苏;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》;20150315(第03期);2.2节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116118813A (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7792328B2 (en) | Warning a vehicle operator of unsafe operation behavior based on a 3D captured image stream | |
| CN108791299A (en) | A kind of driving fatigue detection of view-based access control model and early warning system and method | |
| CN108764034A (en) | A kind of driving behavior method for early warning of diverting attention based on driver's cabin near infrared camera | |
| CN107126224A (en) | A kind of real-time monitoring of track train driver status based on Kinect and method for early warning and system | |
| CN102393989B (en) | Real-time monitoring system of driver working state | |
| CN105575150A (en) | Driving safety behavior analysis method, driving safety early-warning method, driving safety behavior analysis device and driving safety early-warning device | |
| US12094252B2 (en) | Occlusion-aware prediction of human behavior | |
| CN116168508B (en) | A driving fatigue detection and early warning control method and device for human-machine co-driving | |
| CN106529496A (en) | Locomotive driver real-time video fatigue detection method | |
| CN118323191A (en) | Automobile automatic cruising driving auxiliary system and using method thereof | |
| CN117400927A (en) | Dynamic real-time monitoring user driving risk assessment method and system | |
| CN113085888A (en) | Intelligent networked automobile driving-assisting safety information detection system | |
| Avizzano et al. | Real-time embedded vision system for the watchfulness analysis of train drivers | |
| CN116118813B (en) | Intelligent monitoring and early warning method and system for running safety of railway locomotive | |
| Li et al. | Vision-based estimation of driver drowsiness with ORD model using evidence theory | |
| CN114882452B (en) | Track line safety monitoring method, train operation control method and control system | |
| CN117162955A (en) | Passenger safety protection method, device, equipment and storage medium | |
| Hans et al. | Identification and classification of human performance related challenges during remote driving | |
| CN116229677A (en) | Comprehensive service interaction system and method based on intelligent robot | |
| CN115240174A (en) | A driver's operation behavior recognition method, device and vehicle monitoring system | |
| CN113807181A (en) | Detection and identification method, device and system for fatigue driving | |
| Li et al. | Reliability-based driver drowsiness detection using dempster-shafer theory | |
| Babu et al. | Real time alert system to prevent Car Accident | |
| CN113327409A (en) | Driving behavior analysis system based on intelligent recognition monitoring | |
| CN119418706B (en) | A safety control method and device for intelligent cockpit voice interaction system |
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 |