CN114803386B - Conveyor belt longitudinal tearing detection system and method based on binocular line laser camera - Google Patents
Conveyor belt longitudinal tearing detection system and method based on binocular line laser camera Download PDFInfo
- Publication number
- CN114803386B CN114803386B CN202210627532.2A CN202210627532A CN114803386B CN 114803386 B CN114803386 B CN 114803386B CN 202210627532 A CN202210627532 A CN 202210627532A CN 114803386 B CN114803386 B CN 114803386B
- Authority
- CN
- China
- Prior art keywords
- damage
- point cloud
- cloud data
- conveyor belt
- data
- 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
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G43/00—Control devices, e.g. for safety, warning or fault-correcting
- B65G43/02—Control devices, e.g. for safety, warning or fault-correcting detecting dangerous physical condition of load carriers, e.g. for interrupting the drive in the event of overheating
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G2203/00—Indexing code relating to control or detection of the articles or the load carriers during conveying
- B65G2203/04—Detection means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G2203/00—Indexing code relating to control or detection of the articles or the load carriers during conveying
- B65G2203/04—Detection means
- B65G2203/041—Camera
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a conveyor belt longitudinal tearing detection system and method based on a binocular line laser camera, and relates to the technical field of conveyor belt longitudinal tearing detection, wherein the system comprises: a data acquisition module and a back-end processor; the data acquisition module at least comprises a binocular line laser camera; the binocular line laser camera is arranged at the bottom of the target conveyer belt; the binocular line laser camera is used for acquiring point cloud data of the bottom of the target conveyor belt when the target conveyor belt runs; the back-end processor at least comprises a data processing module, wherein the data processing module is used for determining a characteristic extraction result corresponding to each frame of point cloud data and a characteristic extraction result of the whole target conveyer belt corresponding to the target conveyer belt when the target conveyer belt runs for one week according to the point cloud data at the bottom of the target conveyer belt and the transmission speed of the target conveyer belt. The invention can achieve the purpose of meeting the detection real-time performance and the detection accuracy.
Description
Technical Field
The invention relates to the technical field of conveyor belt longitudinal tearing detection, in particular to a conveyor belt longitudinal tearing detection system and method based on a binocular line laser camera.
Background
In the coal mine safety production process, the function of the conveying belt is important. In the coal flow transportation process, foreign matters such as gangue, I-steel and the like possibly scratch the conveyor belt, so that huge losses are caused. How to accurately detect the longitudinal tearing problem of the conveyor belt is an important object of attention of each coal mine production enterprise.
The existing detection method for longitudinal tearing of the conveyer belt is divided into a contact type detection method and a non-contact type detection method. Common contact detection methods include a force measurement method, an embedding method, a coil detection method, a tension detection method and the like; the non-contact detection method includes a closed coil method, an X-ray method, a machine vision method, and the like. The contact detection method is gradually replaced by the non-contact detection method due to lower accuracy and abrasion. The machine vision method in the non-contact detection method is getting more and more attention and research because of the advantages of small loss, higher accuracy, simple maintenance and the like.
Machine vision-based conveyor belt longitudinal tear detection methods are mainly divided into two types: the first type of method comprises the following steps: analysis is performed on visible or infrared images, and the second type of method is: analysis is performed for the linear assist laser image. The key of the first type of method is to accurately divide tearing damage on the conveyer belt image by adopting a maximum inter-class variance method, a threshold iteration method and a global threshold method. The second method judges whether tearing damage exists or not by means of linear laser stripe characteristic change projected on the surface of the conveyer belt, and specifically comprises the following steps: the method comprises the steps of projecting single-channel linear laser on the surface of a conveyer belt, extracting a light bar skeleton by using a maximum value method, determining the breakpoint position by using neighborhood difference, judging the fluctuation abnormal position by using a second derivative, detecting and marking the longitudinal tearing area of the conveyer belt, and identifying the longitudinal tearing by detecting the fracture characteristics of a single linear laser contour line projected on the surface of the conveyer belt.
When the first type of method is applied to underground coal mines, the acquired images are low in definition and even fuzzy due to the fact that illumination is weak and uneven, dust and humidity are large, the conveyor belt vibrates up and down in the running process and the surface abrasion degree is different, and tearing damage segmentation is difficult. When judging whether the tearing damage exists, the second method only focuses on whether the tearing damage exists in the longitudinal direction, does not relate to calculation of characteristic information such as the length, the width and the depth of the tearing damage, or cannot evaluate the characteristic information such as the length, the width and the depth of the tearing damage with high precision, and can evaluate the damage position only by auxiliary means such as an additional marker.
Disclosure of Invention
The invention aims to provide a conveyor belt longitudinal tearing detection system and method based on a binocular line laser camera, so as to achieve the aim of meeting detection instantaneity and detection accuracy.
In order to achieve the above object, the present invention provides the following solutions:
a conveyor belt longitudinal tear detection system based on a binocular line laser camera, comprising: a data acquisition module and a back-end processor;
the data acquisition module at least comprises a binocular line laser camera; the binocular line laser camera is arranged at the bottom of the target conveyor belt; the binocular line laser camera is used for acquiring point cloud data of the bottom of the target conveyor belt when the target conveyor belt runs;
The back-end processor at least comprises a data processing module, wherein the data processing module is used for:
acquiring point cloud data of the bottom of the target conveyer belt;
extracting damage characteristic information of the point cloud data, and determining a characteristic extraction result corresponding to each frame of the point cloud data; the feature extraction result comprises a nondestructive feature result and a damaged feature result; the damage characteristic result comprises the position, the category and the size of the damage; the categories include conveyor belt tearing crack damage and conveyor belt tearing deformation distortion folding damage; the dimensions include one or more of length, width, depth;
and based on the transmission speed of the target conveyor belt, fusing the feature extraction results corresponding to the point cloud data of multiple frames to determine the feature extraction result of the whole target conveyor belt corresponding to the target conveyor belt when the target conveyor belt runs for one week.
Optionally, the point cloud data are distributed in a linear array; before performing the extracting of the damage characteristic information of the point cloud data and determining the aspect of the characteristic extraction result corresponding to the point cloud data of each frame, the data processing module is further configured to:
and preprocessing the point cloud data by adopting a statistical outlier removal algorithm.
Optionally, in extracting the damage feature information of the point cloud data and determining a feature extraction result corresponding to the point cloud data of each frame, the data processing module is further configured to
Judging whether the preprocessed point cloud data has no damage, if so, determining that the feature extraction result corresponding to the preprocessed point cloud data is a nondestructive feature result, and if not, determining the damage type and the damage area according to the preprocessed point cloud data;
when the damage type is conveyor belt tearing crack damage, calculating damage length and damage width according to the damage area;
and when the damage type is tearing, deforming, twisting, folding and damaging of the conveying belt, calculating the damage length, the damage width and the damage depth according to the damage area.
Optionally, in judging whether the preprocessed point cloud data has no damage, if yes, determining that a feature extraction result corresponding to the preprocessed point cloud data is a non-damage feature result, and if not, determining a damage category and a damage area according to the preprocessed point cloud data, wherein the data processing module is further configured to:
judging that the distance between any adjacent data points in the preprocessed point cloud data is smaller than a first threshold value and the slope between any adjacent data points in the preprocessed point cloud data is smaller than a second threshold value, if so, determining that the feature extraction result corresponding to the preprocessed point cloud data is a nondestructive feature result, and if not, determining the damage category and the damage area according to the preprocessed point cloud data.
Optionally, in determining the damage category and the damage area according to the preprocessed point cloud data, the data processing module is further configured to:
when the distance between adjacent data points in the preprocessed point cloud data is larger than or equal to a first threshold value and the slope between any adjacent data points in the preprocessed point cloud data is smaller than a second threshold value, determining that damage exists in the preprocessed point cloud data, determining the damage category corresponding to the preprocessed point cloud data as tearing crack damage of a conveying belt, and determining an area surrounded by a first target data point as a damage area corresponding to the preprocessed point cloud data; the first target data point satisfies that a distance between the first target data point and a data point adjacent to the first target data point is greater than or equal to a first threshold;
when the distance between any adjacent data points in the preprocessed point cloud data is smaller than a first threshold value and the slope between the adjacent data points in the preprocessed point cloud data is larger than or equal to a second threshold value, determining that damage exists in the preprocessed point cloud data, determining the damage category corresponding to the preprocessed point cloud data as tearing, deforming, twisting and folding damage of the conveying belt, and determining the area surrounded by the second target data point as the damage area corresponding to the preprocessed point cloud data; the second target data point satisfies that a slope between the second target data point and a data point adjacent to the second target data point is greater than or equal to a second threshold.
Optionally, when the damage category is a conveyor belt tearing crack damage, calculating a damage length and a damage width according to the damage area, the data processing module is further configured to
When the damage type is conveyor belt tearing crack damage, according to the formulaCalculating the damage length; wherein Dis1 is the actual damage length, len1 is the damage length calculated by the preprocessed point cloud data, V is the transmission speed of the target conveyor belt, t is the time of single frame data, and num is the number of point cloud columns of the single frame preprocessed point cloud data;
when the damage type is conveyor belt tearing crack damage, according to the formulaCalculating the damage width; wherein, dis2 is the actual damage width, len2 is the damage width calculated by the preprocessed point cloud data.
Optionally, the method further comprises: a back-end control unit;
the input end of the rear end control unit is connected with the output end of the data processing module, and the output end of the rear end control unit is connected with the audible and visual alarm;
the back-end control unit is used for:
acquiring a feature extraction result corresponding to the point cloud data of each frame and a feature extraction result of the whole label conveying belt;
comparing the characteristic extraction result corresponding to the point cloud data and the characteristic extraction result of the whole target conveyer belt of each frame with alarm constraint conditions respectively, and outputting an audible and visual alarm instruction when the characteristic extraction result corresponding to the point cloud data and/or the characteristic extraction result of the whole target conveyer belt accords with any constraint condition of the alarm constraint conditions; the alarm constraint conditions comprise three constraint conditions, namely a damage length threshold value, a damage width threshold value and a damage depth threshold value.
Optionally, the method further comprises: an audible and visual alarm;
the audible and visual alarm is used for executing audible and visual alarm operation according to the received audible and visual alarm instruction.
Optionally, the binocular line laser camera is mounted at the bottom of the target conveyer belt in a 45 ° mounting manner obliquely upwards.
A conveyor belt longitudinal tearing detection method based on a binocular line laser camera comprises the following steps:
acquiring point cloud data of the bottom of a target conveyer belt; the point cloud data are acquired through a binocular line laser camera arranged at the bottom of the target conveyer belt;
extracting damage characteristic information of the point cloud data, and determining a characteristic extraction result corresponding to each frame of the point cloud data; the feature extraction result comprises a nondestructive feature result and a damaged feature result; the damage characteristic result comprises the position, the category and the size of the damage; the categories include conveyor belt tearing crack damage and conveyor belt tearing deformation distortion folding damage; the dimensions include one or more of length, width, depth;
and based on the transmission speed of the target conveyor belt, fusing the feature extraction results corresponding to the point cloud data of multiple frames to determine the feature extraction result of the whole target conveyor belt corresponding to the target conveyor belt when the target conveyor belt runs for one week.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides a conveyor belt longitudinal tearing detection system and method based on a binocular line laser camera. Firstly, identifying the point cloud characteristics of the binocular line laser projected on the bottom of a target conveyer belt on line in real time through a point cloud processing technology; secondly, determining multi-frame point cloud characteristics required in fusion based on data acquired by a speed sensor arranged on the belt conveyor; and then, based on a fusion technology, the required multi-frame point cloud features are fused, so that the longitudinal tearing feature identification of the whole target conveyor belt is realized, and the width, depth and length of damage are quantitatively analyzed integrally. Compared with single-channel linear laser and multi-channel linear laser, the binocular line laser adopted by the invention improves the damage detection precision and reduces the estimation error of the damage length.
The invention has low complexity, can be operated on site analysis and decision making of the mine intrinsic safety embedded equipment, does not need to transmit data to an upper computer, avoids time delay and meets the requirements of real-time performance and accuracy of detection.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic view of a shooting range of a binocular line laser camera according to an embodiment of the present invention;
fig. 2 is a block diagram of a conveyor belt longitudinal tear detection system based on a binocular line laser camera according to an embodiment of the present invention;
FIG. 3 is a graph of a conveyor belt tear crack provided by an embodiment of the present invention;
fig. 4 is a tearing, deforming, twisting and folding diagram of a conveyer belt according to an embodiment of the present invention;
FIG. 5 is an expanded view of a crack detection plane provided by an embodiment of the present invention;
FIG. 6 is a flowchart illustrating operation of a conveyor belt longitudinal tear detection system based on a binocular line laser camera according to an embodiment of the present invention;
fig. 7 is a flowchart of a method for detecting longitudinal tearing of a conveyor belt based on a binocular line laser camera according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. 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.
The invention aims to provide a conveyor belt longitudinal tearing detection system and method based on a binocular line laser camera, which mainly detect the conveyor belt longitudinal tearing by using a binocular distance technology, a point cloud processing technology and the like. The method comprises the following steps: the bottom point cloud data of the conveyor belt are obtained in real time by using the binocular line laser camera, single-frame point cloud data are processed to obtain relevant damage characteristic information of the conveyor belt, and the calculation of the longitudinal tearing damage size of the whole conveyor belt and the output of alarm signals are completed according to the multi-frame point cloud data fusion processing method. The invention can detect the damage defect and calculate the damage size of the conveyer belt in real time and output alarm information, and has great application value for intelligent detection and protection of the belt conveyer.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Example 1
Marking positions of conveyor belt transfer points, machine heads and the like, which are easy to cause longitudinal tearing, installing a binocular line laser camera below the conveyor belt marking positions, wherein the binocular line laser camera is obliquely upwards installed at 45 degrees to shoot the bottom of the conveyor belt, the shooting range is shown in figure 1, carrying out point cloud characteristic extraction analysis by utilizing point cloud data of the bottom of the conveyor belt, finishing longitudinal tearing detection according to conveyor belt crack defect characteristics and conveyor belt folding defect characteristics, and finally carrying out alarm discrimination according to counted continuous multi-frame damage information.
As shown in fig. 2, the conveyor belt longitudinal tear detection system based on the binocular line laser camera provided by the embodiment of the invention mainly comprises a data acquisition module and a rear-end processor.
The data acquisition module at least comprises a binocular line laser camera; the binocular line laser camera is arranged at the bottom of the target conveyor belt; the binocular line laser camera is used for acquiring point cloud data of the bottom of the target conveyor belt when the target conveyor belt runs; wherein the target conveyor belt is a conveyor belt to be measured. The binocular line laser camera operates at a fixed frequency.
Preferably, the data acquisition module further comprises a protective housing for protecting the binocular line laser camera.
The back-end processor comprises at least one data processing module. The data processing module is used for:
firstly, acquiring point cloud data of the bottom of the target conveyer belt; secondly, extracting damage characteristic information of the point cloud data, and determining characteristic extraction results corresponding to the point cloud data of each frame; the feature extraction result comprises a nondestructive feature result and a damaged feature result; the damage characteristic result comprises the position, the category and the size of the damage; the categories include conveyor belt tearing crack damage and conveyor belt tearing deformation distortion folding damage; the dimensions include one or more of length, width, depth; and finally, based on the transmission speed of the target conveyor belt, fusing the feature extraction results corresponding to the point cloud data of a plurality of frames to determine the feature extraction result of the whole target conveyor belt corresponding to the target conveyor belt when the target conveyor belt runs for one week.
The hardware structure of the data processing module is RV1126 development board.
Further, the back-end processor further comprises an auxiliary analog input module (the auxiliary analog input module is used for acquiring analog signals output by other platforms/devices and then loading the analog signals into the data processing module for carrying out algorithm simulation), an auxiliary analog output module (the auxiliary analog output module is used for outputting processing results output by the data processing module into analog quantities and then transmitting the analog quantities to an upper computer for alarming or controlling a target conveyor belt through a modbustcp protocol), a DC24V input module (the DC24V input module is used for providing 24V direct current for an RV1126 development board), a DC24V output module (the RV1126 development board is used for outputting 24V direct current for the expansion board through the DC24V output module), and a system management module (the system management module is used for setting various parameters of the back-end processor).
Related application algorithms and interactive interfaces are transplanted in the data processing module, and related feature extraction, longitudinal tearing detection processing and algorithm result expression of the point cloud data are completed. The algorithm result expression contains analog output and is compatible with common network communication output such as Modbustcp, TCP, databases and the like.
According to the conveyor belt longitudinal tearing detection system based on the binocular line laser camera, point cloud data at the bottom of the conveyor belt is obtained in real time by the binocular line laser camera, longitudinal tearing damage detection and multi-frame information fusion calculation are carried out on each frame of point cloud data, and compared with an image-based longitudinal tearing detection algorithm, a longitudinal tearing detection algorithm using single line laser and a longitudinal tearing detection algorithm using multi-line laser, the conveyor belt longitudinal tearing detection system based on the binocular line laser camera is higher in accuracy and higher in precision.
As a preferred implementation manner, the determining process of the feature extraction result according to the embodiment of the present invention is:
because the acquired point cloud data of the conveyor belt originate from the bottom of the conveyor belt, the acquired point cloud data are distributed in a linear array, and the point cloud data to be processed in the embodiment of the invention are based on rules.
Because of the problem of the field of view of the laser device, the field of view is larger, and the device other than the conveyor belt device can be extracted to enter point cloud data, therefore, the point cloud data needs to be preprocessed before feature extraction, and the outlier isolated local point cloud data can be removed, so that the processed point cloud data only comprises the point cloud data describing the conveyor belt device. The embodiment of the invention mainly uses a statistical outlier removal method to reject outlier isolated local point cloud data, and particularly uses a PCL point cloud library statistical_outlier_remote function to set the number of field points and standard deviation parameters to realize the functions.
Therefore, before performing the extracting of the damage characteristic information of the point cloud data and determining the aspect of the characteristic extracting result corresponding to the point cloud data of each frame, the data processing module is further configured to:
And preprocessing the point cloud data by adopting a statistical outlier removal algorithm.
The tearing damage of the conveyer belt is mainly represented by two conditions, namely a tearing crack of the conveyer belt caused by scratch and the like, and the tearing deformation, distortion and folding of the conveyer belt, as shown in fig. 3 and 4.
(1) Conveyer belt tearing crack damage detection
The method mainly shows that the distance between adjacent data points at the crack damage position of the conveyor belt is larger than the distance between normal adjacent points in the point cloud data structure characteristics, and based on the damage characteristics, the three-dimensional point cloud data of the conveyor belt are processed, so that the detection of the tear crack damage of the conveyor belt is realized, and the damage degree calculation is completed.
In order to more efficiently realize damage detection of the conveyor belt cracks, the point cloud depth information is insensitive to crack damage, so that the embodiment of the invention removes the point cloud data depth information and only retains two-dimensional plane information. Which are arranged in columns and at intervals according to the distance between the point clouds of each column, and are shown in fig. 5.
The main principle of crack detection is as follows: and calculating the distance between every two adjacent points, setting a crack detection threshold value at the same time, marking the point as a crack point if the distance between the adjacent points is larger than or equal to the crack detection threshold value, and connecting the found crack points in sequence to obtain the whole crack region. The size of the crack detection threshold directly influences the precision of crack detection, so the crack detection threshold needs to be reasonably set. The size of the crack detection threshold provided by the embodiment of the invention mainly depends on the density degree of the three-dimensional point cloud data and the average value of the distances between adjacent points. The crack detection threshold is generally selected as an average value of distances between all adjacent columns of k times, k is an adjustment coefficient, and the value of k is greater than or equal to 1; according to the selection of the degree of the density of the three-dimensional point cloud data, the smaller the k value is, the smaller the detected crack is, and k=1.3 is selected in the embodiment of the invention.
Calculating the damage degree of crack detection:
since the distance between each row of point clouds and the distance between each column of point clouds are known when the surface point cloud data of the conveyor belt is acquired, in the calculation of the damage degree of the crack, the width of the crack is equal to the average width of all adjacent upper and lower boundary crack points, as shown in fig. 5, AD and BC are the widths of two boundaries, and the length of the crack is equal to the distance from the starting crack boundary point to the ending crack boundary point, that is, the product of the distance between each row of point clouds h and the number of point clouds N in fig. 5. And recording the initial boundary point coordinate information and the final boundary point coordinate information of the crack detection area, and providing subsequent multi-frame information fusion processing. The actual distance length needs to be calculated according to the current conveyor belt speed data, namely:
wherein Dis is the actual distance length, len is the length calculated by the point cloud data, V is the speed of the conveyer belt, t is the time of single frame data, and num is the number of single frame point cloud data point cloud columns, namely the number of point cloud bars.
(2) Conveyer belt tearing deformation distortion folding damage detection
The tearing, deforming, twisting and folding damage of the conveyer belt is mainly characterized in that the conveyer belt has obvious corners in the point cloud data characteristic structure, the slope between adjacent points of the local point cloud is changed severely, and the obvious slope rising and falling processes between the adjacent point clouds are realized. Based on the damage characteristics, the embodiment of the invention realizes tearing deformation, twisting, folding and damage of the conveyer belt by processing the three-dimensional point cloud data of the conveyer belt, and completes damage degree calculation.
The main principle of tearing, deforming, twisting, folding and damaging the conveyer belt is as follows: calculating the slope between each group of adjacent points, setting a detection threshold value of the damage type, marking the point as the boundary point of the damage type if the slope change of the adjacent points is larger than the preset detection threshold value, and connecting the found boundary points of the type in sequence to obtain the integral region of the damage type. The size of the damage detection threshold directly influences the accuracy of tearing, deforming, twisting, folding and damaging the conveyer belt, so that the size of the detection threshold needs to be reasonably set. The size of the detection threshold value of the tearing deformation distortion folding damage of the conveyor belt is mainly determined by the density degree of the three-dimensional point cloud data and the slope value of the adjacent point data. The threshold value is selected as dynamic change, namely the slope between the current two adjacent points cannot be more than 2 times of the slope value between the clouds of the previous two adjacent points, otherwise, the threshold value is regarded as a damaged area point.
Calculating the tearing deformation, twisting, folding and damage degree of the conveying belt: and extracting the detected damage areas of the type to perform cube fitting to obtain an enveloping cube which is used for enveloping the damage point cloud areas at the minimum, and recording the coordinates, length, width and height of the outermost boundary points of the cube. The width is the width of the type of damage, the height is the depth of the type of damage, and the length is the single frame length of the type of damage. And the coordinate information of the outermost boundary point of the cube provides the subsequent multi-frame information fusion processing. The actual distance length needs to be calculated according to the current conveyor belt speed data, namely:
Dis is the actual distance length, len is the length calculated by the point cloud data, V is the speed of the conveyer belt, t is the time of single frame data, and num is the number of single frame point cloud data point cloud columns, namely the number of point cloud strips.
Therefore, in terms of extracting the damage characteristic information of the point cloud data and determining the characteristic extraction result corresponding to the point cloud data of each frame, the data processing module is further configured to:
judging whether the preprocessed point cloud data has no damage, if so, determining that the feature extraction result corresponding to the preprocessed point cloud data is a nondestructive feature result, and if not, determining the damage type and the damage area according to the preprocessed point cloud data.
And when the damage type is conveyor belt tearing crack damage, calculating damage length and damage width according to the damage area.
And when the damage type is tearing, deforming, twisting, folding and damaging of the conveying belt, calculating the damage length, the damage width and the damage depth according to the damage area.
Further, in judging whether the preprocessed point cloud data has no damage, if so, determining that the feature extraction result corresponding to the preprocessed point cloud data is a damage-free feature result, and if not, determining the damage category and the damage area according to the preprocessed point cloud data, wherein the data processing module is further used for:
Judging that the distance between any adjacent data points in the preprocessed point cloud data is smaller than a first threshold value and the slope between any adjacent data points in the preprocessed point cloud data is smaller than a second threshold value, if so, determining that the feature extraction result corresponding to the preprocessed point cloud data is a nondestructive feature result, and if not, determining the damage category and the damage area according to the preprocessed point cloud data.
Further, in determining the damage category and the damage area according to the preprocessed point cloud data, the data processing module is further configured to:
when the distance between adjacent data points in the preprocessed point cloud data is larger than or equal to a first threshold value and the slope between any adjacent data points in the preprocessed point cloud data is smaller than a second threshold value, determining that damage exists in the preprocessed point cloud data, determining the damage category corresponding to the preprocessed point cloud data as tearing crack damage of a conveying belt, and determining an area surrounded by a first target data point as a damage area corresponding to the preprocessed point cloud data; the first target data point satisfies that a distance between the first target data point and a data point adjacent to the first target data point is greater than or equal to a first threshold.
When the distance between any adjacent data points in the preprocessed point cloud data is smaller than a first threshold value and the slope between the adjacent data points in the preprocessed point cloud data is larger than or equal to a second threshold value, determining that damage exists in the preprocessed point cloud data, determining the damage category corresponding to the preprocessed point cloud data as tearing, deforming, twisting and folding damage of the conveying belt, and determining the area surrounded by the second target data point as the damage area corresponding to the preprocessed point cloud data; the second target data point satisfies that a slope between the second target data point and a data point adjacent to the second target data point is greater than or equal to a second threshold.
When the damage category is conveyor belt tearing crack damage, calculating damage length and damage width according to the damage area, wherein the data processing module is also used for
When the damage type is conveyor belt tearing crack damage, according to the formulaCalculating the damage length; wherein Dis1 is the actual damage length, len1 is the damage length calculated by the preprocessed point cloud data, V is the transmission speed of the target conveyor belt, t is the time of single frame data, and num is the number of point cloud columns of the single frame preprocessed point cloud data.
When the damage type is conveyor belt tearing crack damage, according to the formulaCalculating the damage width; wherein, dis2 is the actual damage width, len2 is the damage width calculated by the preprocessed point cloud data.
According to the same principleAnd the damage type is that the conveyer belt is torn, deformed, twisted and folded, and the damage length, the damage width and the damage depth are calculated according to the damage area.
As a preferred embodiment, the fusion process according to the embodiment of the present invention is:
when the relevant type of damage end point is detected, the partial damage detection and recording is completed. In order to obtain the characteristic values (including length, width and depth information) of the whole complete damage, multi-frame point cloud data from the start frame to the end frame of the damage needs to be analyzed.
When the damage detection termination points of the single-frame point cloud data are distributed at the tail part of the point cloud data, the point cloud data of the next frame need to be monitored, and when the starting position of the damage area detected by the latest point cloud data of one frame is overlapped with the termination position detected by the last frame (the distance between the two points is not more than 1.5 times of the distance between the point clouds), the two damage areas are combined, including length combination, maximum width and maximum depth.
(3) Alarm output detection
And aiming at the characteristic extraction result corresponding to the point cloud data of each frame and the characteristic extraction result of the whole target conveyer belt, whether the longitudinal tearing condition exceeding the alarm limiting threshold value occurs or not needs to be judged in real time, at the moment, the algorithm outputs application logic according to the judgment result, and transmits an analog signal to a rear-end control unit PLC, and the PLC performs subsequent linkage control according to the received signal, including conveyer belt shutdown control, audible and visual alarm control and the like. The alarm defining threshold may set the relevant threshold to be parameter configurable based on expert a priori knowledge and system flexibility.
The general case is configured as follows:
and (3) carrying out audible and visual alarm on the damage with the length exceeding 20m, the width exceeding 5mm and the depth of 5-20mm and carrying out relevant operations (stopping running of the conveyer belt and the like) according to the speed of 4.5m/s of the conveyer belt.
Based on this, the conveyor belt longitudinal tearing detection system based on the binocular line laser camera according to the embodiment of the invention further comprises: the rear end control unit and the audible and visual alarm; the input end of the back end control unit is connected with the output end of the data processing module, and the output end of the back end control unit is connected with the audible and visual alarm.
The back-end control unit is used for: acquiring a feature extraction result corresponding to the point cloud data of each frame and a feature extraction result of the whole item of target conveyer belt, comparing the feature extraction result corresponding to the point cloud data of each frame and the feature extraction result of the whole item of target conveyer belt with alarm constraint conditions respectively, and outputting an audible and visual alarm instruction when the feature extraction result corresponding to the point cloud data and/or the feature extraction result of the whole item of target conveyer belt accords with any constraint condition of the alarm constraint conditions; the alarm constraint conditions comprise three constraint conditions, namely a damage length threshold value, a damage width threshold value and a damage depth threshold value.
The audible and visual alarm is used for executing audible and visual alarm operation according to the received audible and visual alarm instruction.
Preferably, the back-end control unit is a PLC or other device.
Analog signals output by the back-end processor are transmitted to a back-end control unit (PLC) (corresponding values are input at the back end in a Modbustcp communication protocol mode and transmitted to the PLC through a protocol), and the PLC performs linkage control or alarm output. The linkage control comprises stop control and audible and visual alarm control of the conveyer belt, and once an algorithm detects that the conveyer belt is longitudinally torn and reaches a relevant set alarm limit, audible and visual alarm is immediately carried out, and stop operation is carried out on the conveyer belt, so that larger loss is avoided.
Further, the back-end processor is connected with the back-end control unit through an electric cable or an optical cable.
As a preferred implementation manner, the conveyor belt longitudinal tear detection system based on the binocular line laser camera according to the embodiment of the present invention further includes: control and display parts (including various control communication interfaces, management platforms, executors, decoders, etc.), and data storage parts (including servers, disks, etc.).
Data storage and optimization
And storing point cloud data and the like of the longitudinal tearing damage of the bottom of the historical conveyor belt in a server, checking the historical alarm record to form a report, and continuously optimizing and adjusting algorithm parameters through data analysis.
The data processing flow of the conveyor belt longitudinal tearing detection system based on the binocular line laser camera is shown in fig. 6, and specifically comprises the following steps:
point cloud data acquisition, point cloud data processing (conveyor belt damage characteristic information extraction), conveyor belt damage defect detection, multi-frame data fusion calculation, alarm threshold judgment and application logic output (a rear end control unit).
As shown in fig. 6, the system provided by the embodiment of the invention mainly comprises two parts of data analysis and multi-frame information fusion. The data analysis is mainly carried out on single-frame laser point cloud data of the conveyer belt so as to extract tearing damage characteristics of the single-frame laser point cloud data of the conveyer belt and point cloud position, width and depth information of the single-frame laser point cloud data of the conveyer belt; the multi-frame information fusion is mainly used for carrying out fusion calculation on tearing damage detection results of continuous multi-frame point cloud data of the conveyor belt so as to count damage information (including damage length, width and depth) of the whole continuous multi-frame conveyor belt through the information, and finally, comparing the counted damage information with a longitudinal tearing alarm threshold of the conveyor belt set by expert experience, and carrying out audible and visual alarm and corresponding appointed actions when the counted damage information exceeds the set alarm threshold.
Example two
In order to achieve the above objective, the present invention further provides a method for detecting longitudinal tear of a conveyor belt based on a binocular line laser camera, as shown in fig. 7, including:
step 100: acquiring point cloud data of the bottom of a target conveyer belt; the point cloud data are acquired through a binocular line laser camera arranged at the bottom of the target conveyer belt;
step 200: extracting damage characteristic information of the point cloud data, and determining a characteristic extraction result corresponding to each frame of the point cloud data; the feature extraction result comprises a nondestructive feature result and a damaged feature result; the damage characteristic result comprises the position, the category and the size of the damage; the categories include conveyor belt tearing crack damage and conveyor belt tearing deformation distortion folding damage; the dimensions include one or more of length, width, depth;
step 300: and based on the transmission speed of the target conveyor belt, fusing the feature extraction results corresponding to the point cloud data of multiple frames to determine the feature extraction result of the whole target conveyor belt corresponding to the target conveyor belt when the target conveyor belt runs for one week.
Compared with the prior art, the invention has the following advantages:
The laser equipment can set the density and the quantity of the acquisition point clouds according to the precision and the timeliness, and can realize the longitudinal tearing detection of the conveying belt by matching with the idea of concurrent block processing, the detection speed can be realized within 500ms, the accuracy rate is up to 99%, and the false alarm rate is less than 1%.
The core algorithm is deployed on an RV1126 board of the side equipment, and the equipment is mining intrinsic safety type equipment, so that the system stability is good, the fault tolerance is high, and the equipment is not interfered by the electromagnetic environment of the environment; the embedded algorithm is transplanted, edge calculation is supported, the operation pressure of a central server can be greatly reduced, normal operation is still maintained when a problem occurs in the underground looped network, and the stability of the system is improved.
The system longitudinal tearing alarm threshold is flexible and configurable, can be used interactively with any other equipment, has strong system compatibility, and covers the longitudinal tearing detection of the multi-scene multi-type conveyer belt.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (8)
1. Conveyor belt longitudinal tear detecting system based on binocular line laser camera, characterized by comprising: a data acquisition module and a back-end processor;
the data acquisition module at least comprises a binocular line laser camera; the binocular line laser camera is arranged at the bottom of the target conveyor belt; the binocular line laser camera is used for acquiring point cloud data of the bottom of the target conveyor belt when the target conveyor belt runs;
the back-end processor at least comprises a data processing module, wherein the data processing module is used for:
acquiring point cloud data of the bottom of the target conveyer belt;
extracting damage characteristic information of the point cloud data, and determining a characteristic extraction result corresponding to each frame of the point cloud data; the feature extraction result comprises a nondestructive feature result and a damaged feature result; the damage characteristic result comprises the position, the category and the size of the damage; the categories include conveyor belt tearing crack damage and conveyor belt tearing deformation distortion folding damage; the dimensions include one or more of length, width, depth;
Based on the transmission speed of the target conveyor belt, fusing the feature extraction results corresponding to the point cloud data of multiple frames to determine the feature extraction result of the whole target conveyor belt corresponding to the target conveyor belt when the target conveyor belt runs for one week;
in the aspect of extracting the damage characteristic information of the point cloud data and determining the characteristic extraction result corresponding to the point cloud data of each frame, the data processing module is further used for
Judging whether the preprocessed point cloud data has no damage, if so, determining that the feature extraction result corresponding to the preprocessed point cloud data is a nondestructive feature result, and if not, determining the damage type and the damage area according to the preprocessed point cloud data;
when the damage type is conveyor belt tearing crack damage, calculating damage length and damage width according to the damage area;
when the damage type is tearing, deforming, twisting, folding and damaging of the conveying belt, calculating damage length, damage width and damage depth according to the damage area;
and if not, determining the damage category and the damage area according to the preprocessed point cloud data, wherein the data processing module is also used for:
Judging that the distance between any adjacent data points in the preprocessed point cloud data is smaller than a first threshold value and the slope between any adjacent data points in the preprocessed point cloud data is smaller than a second threshold value, if so, determining that the feature extraction result corresponding to the preprocessed point cloud data is a nondestructive feature result, and if not, determining the damage category and the damage area according to the preprocessed point cloud data.
2. The conveyor belt longitudinal tear detection system based on a binocular line laser camera of claim 1, wherein the point cloud data is distributed in a line array; before performing the extracting of the damage characteristic information of the point cloud data and determining the aspect of the characteristic extraction result corresponding to the point cloud data of each frame, the data processing module is further configured to:
and preprocessing the point cloud data by adopting a statistical outlier removal algorithm.
3. The conveyor belt longitudinal tear detection system based on a binocular line laser camera of claim 1, wherein the data processing module is further configured to, in determining a damage category and a damage area from the preprocessed point cloud data:
when the distance between adjacent data points in the preprocessed point cloud data is larger than or equal to a first threshold value and the slope between any adjacent data points in the preprocessed point cloud data is smaller than a second threshold value, determining that damage exists in the preprocessed point cloud data, determining the damage category corresponding to the preprocessed point cloud data as tearing crack damage of a conveying belt, and determining an area surrounded by a first target data point as a damage area corresponding to the preprocessed point cloud data; the first target data point satisfies that a distance between the first target data point and a data point adjacent to the first target data point is greater than or equal to a first threshold;
When the distance between any adjacent data points in the preprocessed point cloud data is smaller than a first threshold value and the slope between the adjacent data points in the preprocessed point cloud data is larger than or equal to a second threshold value, determining that damage exists in the preprocessed point cloud data, determining the damage category corresponding to the preprocessed point cloud data as tearing, deforming, twisting and folding damage of the conveying belt, and determining the area surrounded by the second target data point as the damage area corresponding to the preprocessed point cloud data; the second target data point satisfies that a slope between the second target data point and a data point adjacent to the second target data point is greater than or equal to a second threshold.
4. The conveyor belt longitudinal tear detection system based on a binocular line laser camera of claim 1, wherein the data processing module is further configured to, when the damage category is conveyor belt tearing crack damage, calculate a damage length and a damage width from the damage area
When the damage type is conveyor belt tearing crack damage, according to the formulaCalculating the damage length; wherein Dis1 is the actual damage length, len1 is the damage length calculated by the preprocessed point cloud data, V is the transmission speed of the target conveyor belt, t is the time of single frame data, and num is the number of point cloud columns of the single frame preprocessed point cloud data;
When the damage type is conveyor belt tearing crack damage, according to the formulaCalculating the damage width; wherein, dis2 is the actual damage width, len2 is the damage width calculated by the preprocessed point cloud data.
5. The conveyor belt longitudinal tear detection system based on a binocular line laser camera of claim 1, further comprising: a back-end control unit;
the input end of the rear end control unit is connected with the output end of the data processing module, and the output end of the rear end control unit is connected with the audible and visual alarm;
the back-end control unit is used for:
acquiring a feature extraction result corresponding to the point cloud data of each frame and a feature extraction result of the whole label conveying belt;
comparing the characteristic extraction result corresponding to the point cloud data and the characteristic extraction result of the whole target conveyer belt of each frame with alarm constraint conditions respectively, and outputting an audible and visual alarm instruction when the characteristic extraction result corresponding to the point cloud data and/or the characteristic extraction result of the whole target conveyer belt accords with any constraint condition of the alarm constraint conditions; the alarm constraint conditions comprise three constraint conditions, namely a damage length threshold value, a damage width threshold value and a damage depth threshold value.
6. The conveyor belt longitudinal tear detection system based on a binocular line laser camera of claim 5, further comprising: an audible and visual alarm;
the audible and visual alarm is used for executing audible and visual alarm operation according to the received audible and visual alarm instruction.
7. The conveyor belt longitudinal tear detection system based on a binocular line laser camera of claim 1, wherein the binocular line laser camera is mounted at the bottom of the target conveyor belt in a 45 ° upward mounting.
8. The conveyor belt longitudinal tearing detection method based on the binocular line laser camera is characterized by comprising the following steps of:
acquiring point cloud data of the bottom of a target conveyer belt; the point cloud data are acquired through a binocular line laser camera arranged at the bottom of the target conveyer belt;
extracting damage characteristic information of the point cloud data, and determining a characteristic extraction result corresponding to each frame of the point cloud data; the feature extraction result comprises a nondestructive feature result and a damaged feature result; the damage characteristic result comprises the position, the category and the size of the damage; the categories include conveyor belt tearing crack damage and conveyor belt tearing deformation distortion folding damage; the dimensions include one or more of length, width, depth;
Based on the transmission speed of the target conveyor belt, fusing the feature extraction results corresponding to the point cloud data of multiple frames to determine the feature extraction result of the whole target conveyor belt corresponding to the target conveyor belt when the target conveyor belt runs for one week;
extracting damage characteristic information of the point cloud data, and determining a characteristic extraction result corresponding to each frame of the point cloud data, wherein the method specifically comprises the following steps of:
judging whether the preprocessed point cloud data has no damage, if so, determining that the feature extraction result corresponding to the preprocessed point cloud data is a nondestructive feature result, and if not, determining the damage type and the damage area according to the preprocessed point cloud data;
when the damage type is conveyor belt tearing crack damage, calculating damage length and damage width according to the damage area;
when the damage type is tearing, deforming, twisting, folding and damaging of the conveying belt, calculating damage length, damage width and damage depth according to the damage area;
judging whether the preprocessed point cloud data has no damage, if so, determining that the feature extraction result corresponding to the preprocessed point cloud data is a nondestructive feature result, and if not, determining the damage category and the damage area according to the preprocessed point cloud data, wherein the method specifically comprises the following steps:
Judging that the distance between any adjacent data points in the preprocessed point cloud data is smaller than a first threshold value and the slope between any adjacent data points in the preprocessed point cloud data is smaller than a second threshold value, if so, determining that the feature extraction result corresponding to the preprocessed point cloud data is a nondestructive feature result, and if not, determining the damage category and the damage area according to the preprocessed point cloud data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210627532.2A CN114803386B (en) | 2022-06-06 | 2022-06-06 | Conveyor belt longitudinal tearing detection system and method based on binocular line laser camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210627532.2A CN114803386B (en) | 2022-06-06 | 2022-06-06 | Conveyor belt longitudinal tearing detection system and method based on binocular line laser camera |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114803386A CN114803386A (en) | 2022-07-29 |
| CN114803386B true CN114803386B (en) | 2023-08-25 |
Family
ID=82522174
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210627532.2A Active CN114803386B (en) | 2022-06-06 | 2022-06-06 | Conveyor belt longitudinal tearing detection system and method based on binocular line laser camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114803386B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115690098B (en) * | 2022-12-16 | 2023-04-07 | 中科海拓(无锡)科技有限公司 | Method for detecting breakage and loss of iron wire |
| CN117208511B (en) * | 2023-11-08 | 2024-02-02 | 山西赛安自动控制有限公司 | Mining conveyer belt tearing detection device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102275723A (en) * | 2011-05-16 | 2011-12-14 | 天津工业大学 | Machine-vision-based online monitoring system and method for conveyer belt |
| CN104692078A (en) * | 2015-02-03 | 2015-06-10 | 赵磊 | Method for monitoring running state of belt-type conveyer |
| CN111661590A (en) * | 2020-06-08 | 2020-09-15 | 天地（常州）自动化股份有限公司 | Method for detecting tearing damage of conveying belt of mining belt conveyor |
| CN112213317A (en) * | 2020-09-28 | 2021-01-12 | 武汉科技大学 | Conveying belt tearing detection system based on three-dimensional laser scanning technology and detection method thereof |
| CN112325794A (en) * | 2020-10-12 | 2021-02-05 | 武汉万集信息技术有限公司 | Method, device and system for determining overall dimension of vehicle |
| CN112830189A (en) * | 2019-11-25 | 2021-05-25 | 山西戴德测控技术有限公司 | Conveyer belt tears prevention detection device based on binocular vision |
| WO2022101104A1 (en) * | 2020-11-16 | 2022-05-19 | Thyssenkrupp Industrial Solutions Ag | Method for identifying a distance-related running frictional resistance of a belt conveyor system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220171068A1 (en) * | 2020-12-02 | 2022-06-02 | Allstate Insurance Company | Damage detection and analysis using three-dimensional surface scans |
-
2022
- 2022-06-06 CN CN202210627532.2A patent/CN114803386B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102275723A (en) * | 2011-05-16 | 2011-12-14 | 天津工业大学 | Machine-vision-based online monitoring system and method for conveyer belt |
| CN104692078A (en) * | 2015-02-03 | 2015-06-10 | 赵磊 | Method for monitoring running state of belt-type conveyer |
| CN112830189A (en) * | 2019-11-25 | 2021-05-25 | 山西戴德测控技术有限公司 | Conveyer belt tears prevention detection device based on binocular vision |
| CN111661590A (en) * | 2020-06-08 | 2020-09-15 | 天地（常州）自动化股份有限公司 | Method for detecting tearing damage of conveying belt of mining belt conveyor |
| CN112213317A (en) * | 2020-09-28 | 2021-01-12 | 武汉科技大学 | Conveying belt tearing detection system based on three-dimensional laser scanning technology and detection method thereof |
| CN112325794A (en) * | 2020-10-12 | 2021-02-05 | 武汉万集信息技术有限公司 | Method, device and system for determining overall dimension of vehicle |
| WO2022101104A1 (en) * | 2020-11-16 | 2022-05-19 | Thyssenkrupp Industrial Solutions Ag | Method for identifying a distance-related running frictional resistance of a belt conveyor system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114803386A (en) | 2022-07-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114803386B (en) | Conveyor belt longitudinal tearing detection system and method based on binocular line laser camera | |
| CN109230351B (en) | Method for identifying abnormal operation of belt conveyor | |
| CN110171691B (en) | Belt tearing state detection method and detection system for belt conveyor | |
| KR102022496B1 (en) | Process management and monitoring system using vision image detection and a method thereof | |
| CN111661590B (en) | Method for detecting tearing damage of conveying belt of mining belt conveyor | |
| US11583951B2 (en) | Method for collision avoidance and laser machining tool | |
| CN101986143B (en) | Machine vision belt tear detection and protective device | |
| EP3196863A1 (en) | System and method for aircraft docking guidance and aircraft type identification | |
| AU2017349631B2 (en) | Belt inspection system and method | |
| EP2562688A2 (en) | Method of Separating Object in Three Dimensional Point Cloud | |
| CN113658136B (en) | Deep learning-based conveyor belt defect detection method | |
| CN103033476A (en) | Equipment and method for online detecting tobacco leaves with stems based on infrared imaging | |
| WO2021249406A1 (en) | Cargo box extraction and device, system, robot, and storage medium | |
| CN114359246A (en) | Conveyor belt detection method, device, system, electronic device and medium | |
| CN112233120B (en) | Off-square detection method and system based on point cloud data processing | |
| CN115144399B (en) | Assembly quality detection method and device based on machine vision | |
| CN111597857A (en) | Logistics package detection method, device and equipment and readable storage medium | |
| CN112069912A (en) | Optical cable channel construction threat event identification method based on phi-OTDR | |
| KR20210122429A (en) | Method and System for Artificial Intelligence based Quality Inspection in Manufacturing Process using Machine Vision Deep Learning | |
| US7844416B2 (en) | Intelligent modular transport system with object behavioral pattern recognition and traffic management | |
| CN115417067A (en) | Belt deviation monitoring system and method based on binocular line laser camera | |
| CN111105395B (en) | AI intelligent cradle head for monitoring power transmission operation | |
| CN112488056A (en) | Linear track foreign matter intrusion detection method and device based on computer vision | |
| CN111940171A (en) | Workpiece three-dimensional modeling system and three-dimensional modeling method thereof | |
| CN117358615B (en) | Automatic code-spraying printing defect detection method and 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 |