CN115063903A - Railway freight train compartment body abnormity monitoring method and system - Google Patents
Railway freight train compartment body abnormity monitoring method and system Download PDFInfo
- Publication number
- CN115063903A CN115063903A CN202210649714.XA CN202210649714A CN115063903A CN 115063903 A CN115063903 A CN 115063903A CN 202210649714 A CN202210649714 A CN 202210649714A CN 115063903 A CN115063903 A CN 115063903A
- Authority
- CN
- China
- Prior art keywords
- abnormal
- image
- characteristic points
- image recognition
- freight train
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000002159 abnormal effect Effects 0.000 claims abstract description 233
- 238000012545 processing Methods 0.000 claims abstract description 73
- 238000001514 detection method Methods 0.000 claims abstract description 59
- 229910000831 Steel Inorganic materials 0.000 claims description 17
- 239000010959 steel Substances 0.000 claims description 17
- 238000006073 displacement reaction Methods 0.000 claims description 15
- 239000003086 colorant Substances 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 3
- 230000002547 anomalous effect Effects 0.000 claims 1
- 238000007689 inspection Methods 0.000 description 8
- 238000009434 installation Methods 0.000 description 8
- 230000005856 abnormality Effects 0.000 description 7
- 230000000007 visual effect Effects 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
-
- 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
-
- 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
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Abstract
The invention discloses a railway freight train carriage body abnormity monitoring method and system, wherein each freight train carriage body is provided with at least one AI image recognition sensor so as to collect the detection object of the abnormal item of the freight train carriage body, all the AI image recognition sensors are connected with a central monitoring processing unit, the invention adopts the AI image recognition sensors to obtain the freight train carriage body image in real time, the detection is that the carriage is a whole body (surface) rather than a point, the detection result of various abnormal items is obtained by comparing the real-time obtained freight train carriage body image with the preset target image through the image processing comparison mode which is pre-selected for various abnormal items, the dynamic monitoring of the abnormal state of the freight train carriage body is realized, various abnormal items are found in time, the AI image recognition sensors are flexibly and conveniently installed, the requirement of the vertical position of a measuring point or the flatness of the detection object is not needed, the train is easy to meet the requirement of the train circumference.
Description
Technical Field
The invention relates to the field of railway freight train maintenance, in particular to a method and a system for monitoring abnormity of a railway freight train carriage body.
Background
The railway plays an important role in modern logistics systems as an important national infrastructure, a main artery of national economy and a popular transportation tool. For example, the current business mileage of the railway in China is 7.3 kilometers, more than 20 hundred million tons of goods are sent every year, and the ton sending index is the first in the world. Railway freight is transported in a unique train mode, and freight is attached and moves together along with the running of a truck to complete the change of the position. The safety of goods transportation is an important characteristic of the quality of railway transportation products, and most of goods, particularly scattered goods, are collected and placed in a carriage body for transportation. Therefore, the firmness of the wagon box body and the firmness and reliability of the box door in the transportation process are important factors for guaranteeing the safety of the transportation of the goods and are also monitoring objects of the wagon monitoring system.
After the railway freight train carriage body is loaded with goods in a freight yard, the freight train carriage body is inspected after the goods are loaded and before the goods are dispatched, and the freight train carriage body can be in an abnormal state due to factors such as acceleration and deceleration, uphill and downhill, turning, vibration and the like during the progress of the freight train. Such as abnormal states of door opening, roof opening, foreign matters on the side, abnormal tarpaulin ropes, steel coil displacement and the like. The abnormal occurrence is sudden and random, which can cause exposure of the transported goods (such as rain), dropping and loss, and the like, and directly affect the driving safety and the goods safety. Therefore, measures are required to be taken during the travel of the cargo train to monitor and prevent such conditions from occurring, and to ensure the safety of the traveling and cargo.
Conventional countermeasures are mostly implemented regularly or before and after shipment, and the following tasks are routinely performed: checking the appearance of the box body, checking the box body and a top cover connecting piece, locking a box door, a tarpaulin rope hook and the like; the wearing condition of the vulnerable parts such as a box door connecting piece, a locking piece and the like is checked, and the box door connecting piece and the locking piece are repaired or replaced by new products in time; management system measures prevention-information base establishment, vehicle inspection information (including box) registration and input, use time mastering, timely replacement of vehicles exceeding the age limit, and vehicle annual inspection arrangement near the time limit of the yearbook.
Conventional approaches are based on off-line, empirical and periodic inspections and are difficult to achieve including all-weather, real-time dynamic monitoring during train transportation. At present, a patent technology (CN105730331B) discloses a system and a method for monitoring the state of a boxcar, which is directed at a highway boxcar, and includes an ultrasonic device arranged in the boxcar and a control device connected with the ultrasonic device, and provides the installation positions of three ultrasonic devices, and utilizes the reflected wave of ultrasonic waves emitted by the ultrasonic devices at different positions as a detection signal to monitor the state of the boxcar. Although the method has the advantages of simple detection, low cost and the like, the method is not suitable for railway freight train carriages because of the following reasons: firstly, the ultrasonic working principle is that reflected waves are received as detection signals, so that a certain (flatness) plane is required for a detection point (or surface) and is vertical to ultrasonic waves emitted by the device, and therefore, the detection of abnormality of a roof tarpaulin rope and a bow-shaped top cover facing a railway freight train carriage body is limited; secondly, the reflected wave of the receiving (detecting body) is a point or local (relative to a side door and a top cover of the box body) detection signal, so that the whole carriage is difficult to detect; thirdly, based on the ultrasonic working principle, the detection installation position of the ultrasonic device is required to be above the freight train box body (box cover detection) or at the vertical position of the side surface of the freight train box body, so that the limit of the periphery of the railway train and unsafe factors in operation are easily broken through.
Disclosure of Invention
The present invention provides a method and a system for monitoring an abnormality of a railway freight train car body, aiming at the above-mentioned defects of the prior art.
The technical scheme adopted by the invention for solving the technical problem is as follows:
in one aspect, a method for monitoring railway freight train carriage body abnormity is constructed, each freight train carriage body is provided with at least one AI image recognition sensor so as to collect detection objects of abnormal items of the freight train carriage body, and all the AI image recognition sensors are connected with a central monitoring processing unit, and the method comprises the following steps:
the method comprises the steps that each AI image recognition sensor obtains a cargo train carriage image in real time, and the cargo train carriage image and a preset target image are obtained in real time through comparison in an image processing comparison mode selected for various abnormal items in advance to obtain detection results of various abnormal items;
the central monitoring processing unit collects the detection results of all the AI image recognition sensors, and reports that the running states of the traffic safety monitoring system and the ground monitoring center are normal when the detection results of all the AI image recognition sensors are normal; and when the detection result of the abnormal AI image recognition sensor appears, displaying the abnormal carriage number and the abnormal item one by one, and reporting the abnormal carriage number and the abnormal item to a vehicle-mounted traffic safety monitoring system and a ground monitoring center in real time so as to facilitate emergency fault treatment.
Further, in the method of the present invention, the target image includes a normal target image or/and an abnormal target image, and the method further includes: the AI image recognition sensors collect a plurality of cargo train carriage images in advance, at least one image which represents that the carriage body is normal is selected from the images as a normal target image or/and at least one image which represents that the carriage body is abnormal is selected as an abnormal target image.
Further, in the method of the present invention, each box needs to be detected for at least one abnormal item, and the method further includes: an AI image recognition sensor is configured for each abnormal item of each box body in advance, all the abnormal items are classified in advance, and at least one image processing comparison mode is bound for each type of abnormal items.
Further, in the method of the present invention, the abnormal items include abnormal opening of a door, abnormal opening of a roof, abnormal decoupling of a side foreign object, abnormal unhooking of a tarpaulin rope, and displacement of a steel coil; the image processing comparison mode comprises a comparison mode of the area of a graph formed by the characteristic points, the edge pixels of the graph formed by the characteristic points, the size of the graph formed by the characteristic points, the color of the characteristic points and the positions of the characteristic points;
the pre-classifying all the abnormal items and binding at least one image processing comparison mode for each abnormal item specifically comprises: dividing the abnormal opening of the vehicle door and the abnormal opening of the top cover into one type, and binding one or more comparison modes of the area of a graph formed by the characteristic points, the edge pixels of the graph formed by the characteristic points and the size of the graph formed by the characteristic points; the method comprises the steps of dividing the foreign matters on the side of the vehicle, abnormal unhooking of the tarpaulin rope and displacement of the steel coil into one type, and binding one or more comparison modes of three comparison modes of edge pixels of a graph formed by the characteristic points, colors of the characteristic points and positions of the characteristic points.
Further, in the method of the present invention, the comparing, by using an image processing comparison mode pre-selected for various abnormal items, the real-time cargo train carriage image and the preset target image are obtained, so as to obtain the detection results of various abnormal items, specifically including:
the AI image recognition sensor finds an image processing comparison mode which is selected in advance for the abnormal item according to the abnormal item to be detected, respectively extracts characteristic points from the real-time acquired cargo train carriage image and a preset target image, compares the characteristic points according to the image processing comparison mode which is selected in advance based on the extracted characteristic points, and judges whether the abnormal item appears according to the deviation of the comparison result.
Further, in the method of the present invention, the determining whether an abnormal item occurs according to the deviation of the comparison result specifically includes:
if the characteristic points of the freight train carriage image acquired in real time and the characteristic points of the preset normal target image are compared according to a preselected image processing comparison mode, and the deviation of the comparison result exceeds the error range, judging that an abnormal item appears;
and if the characteristic points of the freight train carriage image acquired in real time and the characteristic points of the preset abnormal target image are compared according to the preselected image processing comparison mode, and the deviation of the comparison result is within the error range, judging that an abnormal item occurs.
In the second aspect, a railway freight train carriage body abnormity monitoring system is constructed, and comprises AI image identification sensors and a central monitoring processing unit, wherein all the AI image identification sensors are connected with the central monitoring processing unit, each freight train carriage body is provided with at least one AI image identification sensor so as to collect a detection object of an abnormal item of the freight train carriage body, and all the AI image identification sensors are connected with the central monitoring processing unit;
each AI image recognition sensor is used for acquiring a real-time acquired freight train carriage image, and comparing the real-time acquired freight train carriage image with a preset target image through an image processing comparison mode pre-selected for various abnormal items to obtain detection results of various abnormal items;
the central monitoring processing unit is used for summarizing the detection results of all the AI image recognition sensors, and reporting that the running states of the traffic safety monitoring system and the ground monitoring center are normal when the detection results of all the AI image recognition sensors are normal; and when the detection result of the abnormal AI image recognition sensor appears, displaying the abnormal carriage number and the abnormal item one by one, and reporting the abnormal carriage number and the abnormal item to a vehicle-mounted traffic safety monitoring system and a ground monitoring center in real time so as to facilitate emergency fault treatment.
Further, in the system of the present invention, the target image includes a normal target image or/and an abnormal target image, and each AI image recognition sensor is further configured to collect a plurality of freight train car images in advance, select at least one image indicating that the car is normal as the normal target image or/and select at least one image indicating that the car is abnormal as the abnormal target image;
each box body needs to detect at least one abnormal item, an AI image recognition sensor is configured for each abnormal item of each box body in advance, all the abnormal items are classified in advance, and at least one image processing comparison mode is bound for each type of abnormal item.
Further, in the system of the present invention, the abnormal items include abnormal opening of a door, abnormal opening of a roof, abnormal disconnection of a side foreign object, abnormal unhooking of a tarpaulin rope, and displacement of a steel coil; the image processing comparison mode comprises a comparison mode of the area of a graph formed by the characteristic points, the edge pixels of the graph formed by the characteristic points, the size of the graph formed by the characteristic points, the color of the characteristic points and the positions of the characteristic points;
the AI image recognition sensor is specifically configured to: dividing the abnormal opening of the vehicle door and the abnormal opening of the top cover into one type, and binding one or more comparison modes of the area of a graph formed by the characteristic points, the edge pixels of the graph formed by the characteristic points and the size of the graph formed by the characteristic points; the method comprises the steps of dividing the foreign matters on the side of the vehicle, abnormal unhooking of the tarpaulin rope and displacement of the steel coil into one type, and binding one or more comparison modes of three comparison modes of edge pixels of a graph formed by the characteristic points, colors of the characteristic points and positions of the characteristic points.
Further, in the system of the present invention, the AI image recognition sensor is specifically configured to: according to abnormal items to be detected, finding out an image processing comparison mode which is selected in advance for the abnormal items, respectively extracting characteristic points from the real-time acquired freight train carriage body image and a preset target image, comparing according to the image processing comparison mode which is selected in advance based on the extracted characteristic points, and judging whether the abnormal items appear according to the deviation of comparison results.
The method and the system for monitoring the abnormity of the railway freight train carriage body have the following beneficial effects: the AI image recognition sensor is adopted to obtain the freight train carriage body image in real time, the image of the freight train carriage body is detected to be a whole body (surface) of the carriage instead of a point, the detection result of various abnormal items is obtained by comparing the real-time freight train carriage body image with the preset target image through the image processing comparison mode selected in advance for various abnormal items, the abnormal state of the freight train carriage body is dynamically monitored, various abnormal items are found in time, the AI image recognition sensor is flexibly and conveniently installed, the requirement on the vertical position of a measuring point or the flatness of a detection object is not needed, and the requirement on the periphery of a train is easily met.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts:
FIG. 1 is a schematic view of the anomaly monitoring system for a railway freight train car of the present invention;
fig. 2 is a flow chart of the method for monitoring the abnormality of the railway freight train carriage according to the invention.
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully hereinafter with reference to the accompanying drawings. Exemplary embodiments of the invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the embodiments and specific features in the embodiments of the present invention are described in detail in the present application, but not limited to the present application, and the features in the embodiments and specific features in the embodiments of the present invention may be combined with each other without conflict.
Example one
Referring to fig. 1, the system for monitoring abnormality of a railway freight train carriage body of the present embodiment includes an AI image recognition sensor, a central monitoring processing unit, and a storage unit. All AI image recognition sensors are connected with the central monitoring processing unit, at least one AI image recognition sensor is installed on each cargo compartment body so as to collect detection objects of abnormal items of the cargo compartment bodies, and all AI image recognition sensors and the storage unit are connected with the central monitoring processing unit in a connection mode including but not limited to wired connection and wireless connection.
And each AI image recognition sensor is used for acquiring a real-time acquired freight train carriage image, and comparing the real-time acquired freight train carriage image with a preset target image through an image processing comparison mode selected in advance for various abnormal items to obtain detection results of various abnormal items.
The central monitoring processing unit is used for summarizing the detection results of all the AI image recognition sensors, and reporting that the running states of the traffic safety monitoring system and the ground monitoring center are normal when the detection results of all the AI image recognition sensors are normal; and when the detection result of the abnormal AI image recognition sensor appears, displaying the abnormal carriage number and the abnormal item one by one, and reporting the abnormal carriage number and the abnormal item to a vehicle-mounted traffic safety monitoring system and a ground monitoring center in real time so as to facilitate emergency fault treatment.
The storage unit may be implemented in the form of a ROM (read only memory), a static storage device, a dynamic storage device, or a RAM (random access memory). The storage unit stores cargo train body data such as basic parameters: -performance indicators, commissioning time, etc.; for example, regular maintenance records such as daily inspection, routing inspection, weekly inspection, monthly inspection, annual inspection and the like; for another example, the equipment maintenance condition (damage degree, frequency), replacement date, etc.; and the operation key parameters refer to parameters which can cause a cargo train accident and can represent the degradation state of equipment in operation, such as vibration parameters, corrosive cargos, abnormal coupler devices, abnormal lock parts, abnormal hooks and the like. The data storage mode is a database structure, and the database can be added, written and modified and updated according to the change of the equipment operation environment.
Conventional image capture sensors, such as Complementary Metal Oxide Semiconductor (CMOS) or charge coupled device image (CCD) sensors, output two-dimensional pixel data based on a "frame" of fixed frequency capture. For the recognition of the image and the extraction of the target image features, a large amount of background calculation processing is required. The Dynamic Vision Sensor (DVS) captures dynamic changes of pixel units in a scene by using an event-driven manner, and overcomes the defects of high redundancy, high background noise, high data volume and the like of the information of the conventional video camera, but the DVS camera outputs the coordinate position (x, y) of a pixel where a specific event occurs and the event that occurs, and a background processor needs to restore the event attribute and the address according to the received coordinate address and the time for receiving the code. The embodiment adopts an AI image recognition sensor, which is an image recognition sensor integrating a camera, illumination and a controller, namely shooting, detection and recognition are completed by embedded AI, the full built-in design of a lens and illumination does not need to carry out complicated equipment selection, and detection and target recognition are realized under the condition of difficult influence of ambient light; the ultra-small sensing head has an ultra-wide range with a set distance of 50-2000 mm, can also detect a visual field under an ultra-wide angle as high as 1822 x 1364mm, and is particularly suitable for high-speed operation scenes of railway freight.
The purpose of the system is to find abnormal items which may appear in the carriage in time. The abnormal items comprise abnormal opening of a vehicle door, abnormal opening of a top cover, abnormal unhooking of a vehicle side foreign body, abnormal unhooking of a tarpaulin rope and displacement of a steel coil. Each box body needs to detect at least one abnormal item, in order to ensure the timeliness of data processing, an AI image recognition sensor is configured for each abnormal item of each box body in advance, the installation position of the AI image recognition sensor is related to the abnormal item to be detected, for example, the detection of abnormal opening of a vehicle door, the AI image recognition sensor can be fixed in the vehicle compartment and faces the vehicle door; the top cover is opened abnormally, and the AI image recognition sensor can be fixed in the carriage or at the top of the carriage and faces the top cover; when the foreign matters on the car side and the tarpaulin rope are abnormally unhooked, the AI image recognition sensors can be fixed at the top of the whole carriage and obliquely downwards face the car side and the tarpaulin rope, and if a plurality of surfaces of a certain carriage need to be detected, a plurality of AI image recognition sensors are arranged; the steel coil displacement can fix the AI image recognition sensor on the frame and towards the steel coil.
It should be noted that the abnormal items that may occur in each car are not necessarily identical, and therefore the number and the installation positions of the AI image recognition sensors configured for each car are not necessarily identical, and the number and the installation positions of the AI image recognition sensors configured for each car are specifically determined according to the abnormal items of the current car. The position and the orientation of the AI image recognition sensor are adjusted, so that most of the shooting visual field of the AI image recognition sensor is covered by a detection object related to an abnormal item needing to be detected, for example, the detection of abnormal opening of the vehicle door needs to make most of the shooting visual field of the AI image recognition sensor occupied by the vehicle door.
Specifically, the target images include normal target images or/and abnormal target images, and each AI image recognition sensor is further configured to collect a plurality of freight train carriage images in advance, select at least one image indicating that the carriage is normal as a normal target image or/and select at least one image indicating that the carriage is abnormal as an abnormal target image. More specifically, the AI image recognition sensor has a setting interface, the output interface is connected with the central monitoring processing unit, and the central monitoring processing unit selects at least one target image from images collected by the AI image recognition sensor in advance through the setting interface (the preset number of target images is a summary of normal or abnormal conditions of the characterization target).
The AI image recognition sensor is specifically configured to: according to the abnormal items to be detected, finding out an image processing comparison mode selected in advance for the abnormal items, respectively extracting characteristic points from the real-time acquired freight train carriage body image and a preset target image (the extraction method of the characteristic points is not limited), comparing according to the image processing comparison mode selected in advance based on the extracted characteristic points, and judging whether the abnormal items appear according to the deviation of comparison results. For example, if the feature points of the freight train carriage image acquired in real time and the feature points of the preset normal target image are compared according to the preselected image processing comparison mode, and the deviation of the comparison result exceeds the error range, judging that an abnormal item appears; and if the characteristic points of the freight train carriage image acquired in real time and the characteristic points of the preset abnormal target image are compared according to the preselected image processing comparison mode, and the deviation of the comparison result is within the error range, judging that an abnormal item occurs.
In the embodiment, since it is considered that the change of the position or the size is mainly reflected by the change of the detection object of the abnormal item in the acquired image, all the abnormal items are classified in advance and at least one image processing comparison mode is bound to each type of abnormal item, and the image processing comparison mode includes the comparison mode of the area of the graph formed by the feature points, the edge pixels of the graph formed by the feature points, the size of the graph formed by the feature points, the color of the feature points and the position of the feature points.
For a brief explanation of each comparison mode, it is assumed that all feature points of the normal target image are denoted as a set a1, all feature points of the abnormal target image are denoted as a set a2, and all feature points of the freight train car image acquired in real time are denoted as a set B, and then the set a is obtained. The points of set a1 are connected in sequence to form a graph contour a1, the points of set a2 are connected in sequence to form a graph contour a2, and the points of set B are connected in sequence to form a graph contour B.
Comparison mode of the area of the graph composed of the feature points: comparing the areas enclosed by the graphic outlines a1 and b directly, and if the error range in the comparison mode is set to be 10%, if the deviation of the area enclosed by the outline b relative to the area enclosed by the outline a1 exceeds 10%, determining that the area is abnormal; alternatively, if the deviation of the area enclosed by the outline b from the area enclosed by the outline a2 is within 10%, it is considered that an abnormality has occurred.
The comparison mode of the edge pixels of the graph formed by the feature points is as follows: is the magnitude deviation of the pixel values of the points of set B compared to the points of set A1/A2. It will be appreciated that there are many characteristic points in the sets B, A1, a2, and thus a certain proportion of points may deviate in comparison to pixel values, and thus the deviation is considered to be global.
Comparison mode of the sizes of the graphs composed of the feature points: the sizes of the graphic outlines b, a1/a2 are compared, for example, the diameter can be compared if the outlines are circular, and the length and width sizes can be compared if the outlines are rectangular.
Comparison mode of colors of feature points: is the difference in magnitude of the color values compared between the points of set B and the points of set A1/A2. Similarly, there are many feature points in the sets B, A1 and A2, so when comparing the color values, the deviation can occur in a certain number of points, and the deviation is considered to occur in the whole.
Alignment pattern of positions of feature points: and comparing the coordinate values of the points in the set B with the coordinate values of the points in the set A1/A2. Similarly, there are many feature points in the sets B, A1 and a2, so when the coordinates are compared, the deviation can occur in a certain number of points, and the deviation is considered to occur in the whole.
In this embodiment, abnormal items, such as abnormal opening of a door and abnormal opening of a roof, which are mainly reflected by size changes in the captured image, may be classified into one category. For the abnormal items, one or more comparison modes of the area of the graph formed by the characteristic points, the edge pixels of the graph formed by the characteristic points and the size of the graph formed by the characteristic points can be bound.
In this embodiment, abnormal items that mainly reflect the change of the position in the acquired image, such as a car side foreign body, abnormal unhooking of a tarpaulin rope, and displacement of a steel coil, can be classified into one type. For the abnormal items, one or more comparison modes of three comparison modes of edge pixels of a graph formed by the feature points, colors of the feature points and positions of the feature points can be bound.
In summary, the present embodiment has the following beneficial effects: the AI image recognition sensor is adopted to obtain the freight train carriage body image in real time, the image of the freight train carriage body is detected to be a whole body (surface) of the carriage instead of a point, the detection result of various abnormal items is obtained by comparing the real-time freight train carriage body image with the preset target image through the image processing comparison mode selected in advance for various abnormal items, the abnormal state of the freight train carriage body is dynamically monitored, various abnormal items are found in time, the AI image recognition sensor is flexibly and conveniently installed, the requirement on the vertical position of a measuring point or the flatness of a detection object is not needed, and the requirement on the periphery of a train is easily met.
Example two
Based on the same inventive concept, referring to fig. 2, the present embodiment discloses a method for monitoring abnormality of railway freight train cars, each freight train car is installed with at least one AI image recognition sensor so as to collect detection objects of abnormal items of the freight train car, all the AI image recognition sensors are connected with a central monitoring processing unit, the method includes:
s101: the method comprises the steps that each AI image recognition sensor obtains a cargo train carriage image in real time, and the cargo train carriage image and a preset target image are obtained in real time through comparison in an image processing comparison mode selected for various abnormal items in advance to obtain detection results of various abnormal items;
s102: the central monitoring processing unit collects the detection results of all the AI image recognition sensors, and reports that the running states of the traffic safety monitoring system and the ground monitoring center are normal when the detection results of all the AI image recognition sensors are normal; and when the detection result of the abnormal AI image recognition sensor appears, displaying the abnormal carriage number and the abnormal item one by one, and reporting the abnormal carriage number and the abnormal item to a vehicle-mounted traffic safety monitoring system and a ground monitoring center in real time so as to facilitate emergency fault treatment.
The method aims to timely find abnormal items which may appear in the carriage. The abnormal items comprise abnormal opening of a vehicle door, abnormal opening of a top cover, abnormal unhooking of a vehicle side foreign body, abnormal unhooking of a tarpaulin rope and displacement of a steel coil. Each box body needs to detect at least one abnormal item, in order to ensure the timeliness of data processing, an AI image recognition sensor is configured for each abnormal item of each box body in advance, the installation position of the AI image recognition sensor is related to the abnormal item to be detected, for example, the detection of abnormal opening of a vehicle door, the AI image recognition sensor can be fixed in the vehicle compartment and faces the vehicle door; the top cover is opened abnormally, and the AI image recognition sensor can be fixed in the carriage or at the top of the carriage and faces the top cover; the abnormal unhooking of the foreign matters on the car side and the tarpaulin ropes can fix the AI image recognition sensors at the top of the whole carriage and obliquely and downwards face the car side and the tarpaulin ropes, and if a plurality of surfaces of a certain carriage need to be detected, a plurality of AI image recognition sensors are arranged; the steel coil displacement can fix the AI image recognition sensor on the frame and towards the steel coil.
It should be noted that the abnormal items that may occur in each car are not necessarily identical, and therefore the number and the installation positions of the AI image recognition sensors configured for each car are not necessarily identical, and the number and the installation positions of the AI image recognition sensors configured for each car are specifically determined according to the abnormal items of the current car. The position and the orientation of the AI image recognition sensor are adjusted, so that most of the shooting visual field of the AI image recognition sensor is covered by a detection object related to an abnormal item needing to be detected, for example, the detection of abnormal opening of the vehicle door needs to make most of the shooting visual field of the AI image recognition sensor occupied by the vehicle door.
Specifically, the target image includes a normal target image or/and an abnormal target image, and the method further includes S01: the AI image recognition sensors collect a plurality of cargo train carriage images in advance, at least one image which represents that the carriage body is normal is selected from the images as a normal target image or/and at least one image which represents that the carriage body is abnormal is selected as an abnormal target image. More specifically, the AI image recognition sensor has a setting interface, an output interface connected to the central monitoring processing unit, and the central monitoring processing unit selects at least one target image from the images collected by the AI image recognition sensor in advance through the setting interface (the preset number of target images is a summary of the normal or abnormal conditions of the representation target).
Specifically, the step S101 of comparing the freight train carriage image obtained in real time with the preset target image through the image processing comparison mode preselected for the various abnormal items to obtain the detection results of the various abnormal items includes: the AI image recognition sensor finds an image processing comparison mode which is selected in advance for the abnormal item according to the abnormal item to be detected, respectively extracts characteristic points from the real-time acquired cargo train carriage image and a preset target image, compares the characteristic points according to the image processing comparison mode which is selected in advance based on the extracted characteristic points, and judges whether the abnormal item appears according to the deviation of the comparison result. For example, if the feature points of the freight train carriage image acquired in real time and the feature points of the preset normal target image are compared according to the preselected image processing comparison mode, and the deviation of the comparison result exceeds the error range, judging that an abnormal item appears; and if the characteristic points of the freight train carriage image acquired in real time and the characteristic points of the preset abnormal target image are compared according to the preselected image processing comparison mode, and the deviation of the comparison result is within the error range, judging that an abnormal item occurs.
Since the change in the position or size is mainly reflected in the acquired image in consideration of the change in the detection object of the abnormal item, the method further includes S02: an AI image recognition sensor is configured for each abnormal item of each box body in advance, all the abnormal items are classified in advance, and at least one image processing comparison mode is bound for each type of abnormal items. The image processing comparison mode comprises a comparison mode of the area of the graph formed by the characteristic points, the edge pixels of the graph formed by the characteristic points, the size of the graph formed by the characteristic points, the color of the characteristic points and the positions of the characteristic points.
For a brief explanation of each comparison mode, it is assumed that all feature points of the normal target image are denoted as a set a1, all feature points of the abnormal target image are denoted as a set a2, and all feature points of the freight train car image acquired in real time are denoted as a set B, and then the set a is obtained. The points of set a1 are connected in sequence to form a graph contour a1, the points of set a2 are connected in sequence to form a graph contour a2, and the points of set B are connected in sequence to form a graph contour B.
Comparison mode of the area of the graph composed of the feature points: comparing the areas enclosed by the graphic outlines a1 and b directly, and if the error range in the comparison mode is set to be 10%, if the deviation of the area enclosed by the outline b relative to the area enclosed by the outline a1 exceeds 10%, determining that the area is abnormal; alternatively, if the deviation of the area enclosed by the outline b from the area enclosed by the outline a2 is within 10%, it is considered that an abnormality has occurred.
Comparing the edge pixels of the graph formed by the feature points: is the difference in pixel values between the points of set B and the points of set A1/A2. It will be appreciated that there are many characteristic points in the sets B, A1, a2, and thus a certain proportion of points may deviate in comparison to pixel values, and thus the deviation is considered to be global.
Comparison mode of the sizes of the graphs composed of the feature points: the sizes of the graphic outlines b, a1/a2 are compared, for example, the diameter can be compared if the outlines are circular, and the length and width sizes can be compared if the outlines are rectangular.
Comparison mode of colors of feature points: is the difference in magnitude of the color values compared between the points of set B and the points of set A1/A2. Similarly, there are many feature points in the sets B, A1 and A2, so when comparing the color values, the deviation can occur in a certain number of points, and the deviation is considered to occur in the whole.
Alignment pattern of positions of feature points: and comparing the coordinate values of the points in the set B with the coordinate values of the points in the set A1/A2. Similarly, there are many feature points in the sets B, A1 and a2, so when the coordinates are compared, the deviation can occur in a certain number of points, and the deviation is considered to occur in the whole.
The pre-classifying all the abnormal items and binding at least one image processing comparison mode for each abnormal item specifically comprises:
1) abnormal items such as abnormal opening of a door and abnormal opening of a roof, which mainly reflect changes in size in the captured image, can be classified into one category. For the abnormal items, one or more than one comparison modes of the area of the graph formed by the characteristic points, the edge pixels of the graph formed by the characteristic points and the size of the graph formed by the characteristic points can be bound.
2) Abnormal items mainly reflecting position changes in the acquired images, such as the foreign matters on the car side, abnormal unhooking of a tarpaulin rope and displacement of a steel coil, can be classified into one type. For the abnormal items, one or more comparison modes of three comparison modes of edge pixels of a graph formed by the feature points, colors of the feature points and positions of the feature points can be bound.
Further details may be found in the embodiments and will not be described herein.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "or/and" includes any and all combinations of one or more of the associated listed items.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A railway freight train carriage body abnormity monitoring method is characterized in that each freight train carriage body is provided with at least one AI image recognition sensor so as to collect detection objects of abnormal items of the freight train carriage body, and all the AI image recognition sensors are connected with a central monitoring processing unit, and the method comprises the following steps:
the method comprises the steps that each AI image recognition sensor obtains a cargo train carriage image in real time, and the cargo train carriage image and a preset target image are obtained in real time through comparison in an image processing comparison mode selected for various abnormal items in advance to obtain detection results of various abnormal items;
the central monitoring processing unit collects the detection results of all the AI image recognition sensors, and reports that the running states of the traffic safety monitoring system and the ground monitoring center are normal when the detection results of all the AI image recognition sensors are normal; and when the detection result of the abnormal AI image recognition sensor appears, displaying the abnormal carriage number and the abnormal item one by one, and reporting the abnormal carriage number and the abnormal item to a vehicle-mounted traffic safety monitoring system and a ground monitoring center in real time so as to facilitate emergency fault treatment.
2. The method of claim 1, wherein the target image comprises a normal target image or/and an abnormal target image, the method further comprising: the AI image recognition sensors collect a plurality of cargo train carriage images in advance, at least one image which represents that the carriage body is normal is selected from the images as a normal target image or/and at least one image which represents that the carriage body is abnormal is selected as an abnormal target image.
3. The method of claim 1, wherein each bin is required to be tested for at least one anomalous item, the method further comprising: an AI image recognition sensor is configured for each abnormal item of each box body in advance, all the abnormal items are classified in advance, and at least one image processing comparison mode is bound for each type of abnormal items.
4. The method according to claim 3, wherein the abnormal items include abnormal opening of a door, abnormal opening of a roof, abnormal opening of a side wall, abnormal unhooking of a tarpaulin rope, displacement of a steel coil; the image processing comparison mode comprises a comparison mode of the area of a graph formed by the characteristic points, the edge pixels of the graph formed by the characteristic points, the size of the graph formed by the characteristic points, the color of the characteristic points and the positions of the characteristic points;
the pre-classifying all the abnormal items and binding at least one image processing comparison mode for each abnormal item specifically comprises: dividing the abnormal opening of the vehicle door and the abnormal opening of the top cover into one type, and binding one or more comparison modes of the area of a graph formed by the characteristic points, the edge pixels of the graph formed by the characteristic points and the size of the graph formed by the characteristic points; the method comprises the steps of dividing the foreign matters on the side of the vehicle, abnormal unhooking of the tarpaulin rope and displacement of the steel coil into one type, and binding one or more comparison modes of three comparison modes of edge pixels of a graph formed by the characteristic points, colors of the characteristic points and positions of the characteristic points.
5. The method according to claim 3, wherein the comparing real-time obtaining of the cargo train carriage image and the preset target image through the image processing comparison mode selected in advance for various abnormal items to obtain the detection results of various abnormal items specifically comprises:
the AI image recognition sensor finds an image processing comparison mode which is selected in advance for the abnormal item according to the abnormal item to be detected, respectively extracts characteristic points from the real-time acquired cargo train carriage image and a preset target image, compares the characteristic points according to the image processing comparison mode which is selected in advance based on the extracted characteristic points, and judges whether the abnormal item appears according to the deviation of the comparison result.
6. The method according to claim 5, wherein the determining whether the abnormal item occurs according to the deviation of the comparison result specifically comprises:
if the characteristic points of the freight train carriage image acquired in real time and the characteristic points of the preset normal target image are compared according to a preselected image processing comparison mode, and the deviation of the comparison result exceeds the error range, judging that an abnormal item appears;
and if the characteristic points of the freight train carriage image acquired in real time and the characteristic points of the preset abnormal target image are compared according to the preselected image processing comparison mode, and the deviation of the comparison result is within the error range, judging that an abnormal item occurs.
7. A railway freight train carriage body abnormity monitoring system is characterized by comprising AI image identification sensors and a central monitoring processing unit, wherein all the AI image identification sensors are connected with the central monitoring processing unit, each freight train carriage body is provided with at least one AI image identification sensor so as to collect a detection object of an abnormal item of the freight train carriage body, and all the AI image identification sensors are connected with the central monitoring processing unit;
each AI image recognition sensor is used for acquiring a real-time acquired freight train carriage image, and comparing the real-time acquired freight train carriage image with a preset target image through an image processing comparison mode pre-selected for various abnormal items to obtain detection results of various abnormal items;
the central monitoring processing unit is used for summarizing the detection results of all the AI image recognition sensors, and reporting that the running states of the traffic safety monitoring system and the ground monitoring center are normal when the detection results of all the AI image recognition sensors are normal; and when the detection result of the abnormal AI image recognition sensor appears, displaying the abnormal carriage number and the abnormal item one by one, and reporting the abnormal carriage number and the abnormal item to a vehicle-mounted traffic safety monitoring system and a ground monitoring center in real time so as to facilitate emergency fault treatment.
8. The system of claim 7, wherein the target image comprises a normal target image and/or an abnormal target image, each AI image recognition sensor is further configured to pre-capture a plurality of freight train carriage images, select at least one image indicative of a normal carriage as the normal target image and/or select at least one image indicative of an abnormal carriage as the abnormal target image;
each box body needs to detect at least one abnormal item, an AI image recognition sensor is configured for each abnormal item of each box body in advance, all the abnormal items are classified in advance, and at least one image processing comparison mode is bound for each type of abnormal item.
9. The system of claim 8, wherein the abnormal items include abnormal opening of a door, abnormal opening of a roof, abnormal opening of a side wall, abnormal unhooking of a tarpaulin rope, displacement of a steel coil; the image processing comparison mode comprises a comparison mode of the area of a graph formed by the characteristic points, the edge pixels of the graph formed by the characteristic points, the size of the graph formed by the characteristic points, the color of the characteristic points and the positions of the characteristic points;
the AI image recognition sensor is specifically configured to: dividing the abnormal opening of the vehicle door and the abnormal opening of the top cover into one type, and binding one or more comparison modes of the area of a graph formed by the characteristic points, the edge pixels of the graph formed by the characteristic points and the size of the graph formed by the characteristic points; the method comprises the steps of dividing the foreign matters on the side of the vehicle, abnormal unhooking of the tarpaulin rope and displacement of the steel coil into one type, and binding one or more comparison modes of three comparison modes of edge pixels of a graph formed by the characteristic points, colors of the characteristic points and positions of the characteristic points.
10. The system of claim 8, wherein the AI image recognition sensor is specifically configured to: according to abnormal items to be detected, finding out an image processing comparison mode which is selected in advance for the abnormal items, respectively extracting characteristic points from the real-time acquired freight train carriage body image and a preset target image, comparing according to the image processing comparison mode which is selected in advance based on the extracted characteristic points, and judging whether the abnormal items appear according to the deviation of comparison results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210649714.XA CN115063903A (en) | 2022-06-08 | 2022-06-08 | Railway freight train compartment body abnormity monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210649714.XA CN115063903A (en) | 2022-06-08 | 2022-06-08 | Railway freight train compartment body abnormity monitoring method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115063903A true CN115063903A (en) | 2022-09-16 |
Family
ID=83200937
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210649714.XA Pending CN115063903A (en) | 2022-06-08 | 2022-06-08 | Railway freight train compartment body abnormity monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115063903A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102941864A (en) * | 2012-11-09 | 2013-02-27 | 武汉翔翼科技有限公司 | Train loading state high-definition monitoring and overloading detection method |
| US20170106885A1 (en) * | 2015-09-03 | 2017-04-20 | Sameer Singh | Railroad track survey system |
| CN109740410A (en) * | 2018-11-07 | 2019-05-10 | 中国铁路总公司 | A kind of train groups fault recognition method and device without presetting template |
| CN109858456A (en) * | 2019-02-18 | 2019-06-07 | 中国铁路沈阳局集团有限公司科学技术研究所 | A kind of rolling stock status fault analysis system |
| CN110135383A (en) * | 2019-05-22 | 2019-08-16 | 辽宁鼎汉奇辉电子系统工程有限公司 | Loading goods train video intelligent monitoring system |
| CN112464846A (en) * | 2020-12-03 | 2021-03-09 | 武汉理工大学 | Automatic identification method for abnormal fault of freight train carriage at station |
| CN112508034A (en) * | 2020-11-03 | 2021-03-16 | 精英数智科技股份有限公司 | Freight train fault detection method and device and electronic equipment |
| CN114241476A (en) * | 2021-12-20 | 2022-03-25 | 山东矩阵软件工程股份有限公司 | Train condition checking method, system and related device |
-
2022
- 2022-06-08 CN CN202210649714.XA patent/CN115063903A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102941864A (en) * | 2012-11-09 | 2013-02-27 | 武汉翔翼科技有限公司 | Train loading state high-definition monitoring and overloading detection method |
| US20170106885A1 (en) * | 2015-09-03 | 2017-04-20 | Sameer Singh | Railroad track survey system |
| CN109740410A (en) * | 2018-11-07 | 2019-05-10 | 中国铁路总公司 | A kind of train groups fault recognition method and device without presetting template |
| CN109858456A (en) * | 2019-02-18 | 2019-06-07 | 中国铁路沈阳局集团有限公司科学技术研究所 | A kind of rolling stock status fault analysis system |
| CN110135383A (en) * | 2019-05-22 | 2019-08-16 | 辽宁鼎汉奇辉电子系统工程有限公司 | Loading goods train video intelligent monitoring system |
| CN112508034A (en) * | 2020-11-03 | 2021-03-16 | 精英数智科技股份有限公司 | Freight train fault detection method and device and electronic equipment |
| CN112464846A (en) * | 2020-12-03 | 2021-03-09 | 武汉理工大学 | Automatic identification method for abnormal fault of freight train carriage at station |
| CN114241476A (en) * | 2021-12-20 | 2022-03-25 | 山东矩阵软件工程股份有限公司 | Train condition checking method, system and related device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102941864B (en) | Train loading state high-definition monitoring and overloading detection method | |
| CN107122747B (en) | Non-contact detection device and method for railway vehicle carriage state | |
| CN103077526B (en) | There is train method for detecting abnormality and the system of depth detection function | |
| US9214016B2 (en) | Pantograph monitoring system and method | |
| CN107314741A (en) | Measurement of cargo measuring method | |
| CN107103654A (en) | A kind of Cargo Inspection safety detection controlling and management and method | |
| CN101424510B (en) | Detecting method and system for overrun of train | |
| CN105115605A (en) | Track train infrared detection system and detection method | |
| CN111942434A (en) | Intelligent fault image detection device for key parts of railway wagon | |
| CN113933856A (en) | System, method and device for detecting residues at bottom of railway wagon | |
| CN113516629A (en) | Intelligent detection system for TFDS passing operation | |
| CN109858456A (en) | A kind of rolling stock status fault analysis system | |
| CN113788051A (en) | Train on-station running state monitoring and analyzing system | |
| CN102592452B (en) | Container port vehicle multisource sensing device | |
| CN115063903A (en) | Railway freight train compartment body abnormity monitoring method and system | |
| CN111950531A (en) | Vehicle detection system and method for highway side inspection | |
| CN116309371A (en) | Train part abnormality detection method and device, electronic equipment and medium | |
| CN116026441A (en) | Method, device, equipment and storage medium for detecting abnormal load capacity of vehicle | |
| CN116164984A (en) | Road test device and test method for speed limit sign auxiliary system | |
| CN111114587A (en) | Station train receiving and dispatching early warning system and image preprocessing method thereof | |
| CN115743195A (en) | Mining intelligent flatbed | |
| CN109978879B (en) | Box corner in-groove state detection method based on railway wagon loading video monitoring | |
| CN213365779U (en) | Off-site law enforcement detection system | |
| CN114022537A (en) | Vehicle loading rate and unbalance loading rate analysis method for dynamic weighing area | |
| CN113919703A (en) | Block chain service platform for state analysis |
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 |