CN109765570A - A kind of Auto-rectification Device for Belt Conveyer detection method based on laser radar - Google Patents
A kind of Auto-rectification Device for Belt Conveyer detection method based on laser radar Download PDFInfo
- Publication number
- CN109765570A CN109765570A CN201811395287.7A CN201811395287A CN109765570A CN 109765570 A CN109765570 A CN 109765570A CN 201811395287 A CN201811395287 A CN 201811395287A CN 109765570 A CN109765570 A CN 109765570A
- Authority
- CN
- China
- Prior art keywords
- belt
- cluster
- point cloud
- cloud data
- laser radar
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 42
- 230000011218 segmentation Effects 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 13
- 238000000605 extraction Methods 0.000 claims abstract description 9
- 238000012360 testing method Methods 0.000 claims abstract description 6
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000009434 installation Methods 0.000 claims description 4
- 230000004069 differentiation Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 239000003245 coal Substances 0.000 description 7
- 238000005065 mining Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000010985 leather Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The Auto-rectification Device for Belt Conveyer detection method based on laser radar that the invention discloses a kind of, step 1, using the point cloud data of laser radar acquisition testing belt of belt conveyor front surface;Step 2, cluster segmentation processing is carried out to the point cloud data of laser radar acquisition;Step 3, the cluster segmentation of the point cloud data based on step 2 carries out feature extraction to the point cloud after cluster segmentation, since ideal belt edges are straight lines, therefore fitting a straight line method is used to carry out feature extraction to point cloud data;Beneficial effects of the present invention use non-contact detection, can constantly active detecting and processing, detection efficiency is high, and the working sensor service life is long;Meanwhile detection, without being bound by the influence of the factors such as detection ambient light, weather, detection reliability significantly improves.
Description
Technical field
The present invention relates to a kind of belt conveyor fault detection methods, and in particular to a kind of belt based on laser radar is defeated
Send machine sideslip detection method.
Background technique
As the crucial transporting equipment of coal mine production system, belt conveyor be widely used in China coal digging,
In production, transhipment and process.Compared with other transporting equipments and transporting pattern, belt conveyor has continuative transport amount
Greatly, carrying capacity is strong, longer or extra long distance continuative transport may be implemented, operational efficiency is high, working environment adaptability is good, easy
In realize automatically control the advantages that.Thereby it is ensured that belt conveyor is continuous uninterruptedly, safety, normally carries out transport, it is
The important leverage of the work such as coal mining, processing.
However, due to the severe and complexity of coal mining and transportation environment, and the conditions such as continuity of its work because
Element, the normal work ability of belt conveyor is by serious test, in actual production Coal Transport, many belt conveyors
It breaks down, gently then influences the normal operation of coal mining transport, the security of the lives and property that is heavy then injuring coal worker.Wherein,
Sideslip is one of the fault type of maximum probability in type that belt conveyor breaks down.The sideslip of conveyer belt refers to conveyer belt
Traffic direction center line deviates the phenomenon that belt conveyor intrinsic center line, the reason is that the resultant direction for acting on conveyer belt is inclined
From caused by calibration hub of communication line direction, the sideslip of conveyer belt easily cause the material of transport along sideslip opposite direction it is unrestrained and
The abrasion of conveyer belt local edge.In addition, belt deflection is also possible to cause other failures such as transport belt slippery, tearing.Therefore, must
Must the deviation fault to conveyer belt constantly detected.
In current technical solution, Chinese invention patent 201110247700.7 discloses one kind and entangles from prosecution amount formula belt
Deflection device, but belt deviation detecting device therein does not provide specific enforceable technical solution and states in detail.
Chinese invention patent 201410578638.3 announces a kind of automatic sideslip detection of mining belt conveyor and corrects dress
It sets, wherein the detection of automatic sideslip is by being embedded the pressure sensor in the inside of the return pin, to sense the mine leather belt
Then offset signals are issued controller by the belt deviation of conveyer.Such detection device and principle are examined using contact
It surveys, the disadvantage is that the installation site of the examined sensor of the detection range of running deviation value limits, after sensor position, which is installed, fixes,
The sideslip range of detection just can not be adjustable, can not adapt to changeable working environment and transport task requirement, and the detection of contact
Mode makes pressure sensor by biggish pressure and friction, and working life is affected.
Chinese invention patent 201210009836.9 discloses a kind of belt deflection On-line Fault based on machine vision
Detection method.It acquires conveyer belt operation image using linear array CCD camera, and conveyer belt binary map is obtained after binary conversion treatment
Then picture hints obliquely at bianry image for one-dimensional fault signature function, then extract from one-dimensional fault signature function sideslip angle and partially
Shifting amount carries out deviation fault identification.Although this method is shone due to camera by ambient light using being non-contact detection
It is affected, and the amount of image information of camera is more and complicated, brings many problems to the processing in information later period, furthermore by light
The reliability for taking the picture machine testing of influence can reduce.
Summary of the invention
For the defect for solving the prior art, the Auto-rectification Device for Belt Conveyer detection based on laser radar that the present invention provides a kind of
Method, comprising the following steps:
Step 1, using the point cloud data of laser radar acquisition testing belt of belt conveyor front surface;
Step 2, cluster segmentation processing, the cluster segmentation processing, tool are carried out to the point cloud data of laser radar acquisition
Body the following steps are included:
(1) it selectes and calculates in cluster process, maximum the number of iterations is K, calculates the effective maximal distance threshold of iteration and is
D, the initial center for selecting cluster calculation point is Oi(i=1,2 ..., k), k are the number of cluster centre, wherein Oi={ Oi1,
Oi2,…,Oin};
(2) each point cloud data is calculated to the center Euclidean distance of setting cluster, and the point of cloud is merged into distance
Near nearest cluster centre.Wherein, Euclidean distance calculation formula:
Wherein, d (xi,Oj) it is the distance for representing i-th point to j-th cluster centre, come to n point cloud data point.
(3) cluster obtained according to step (2) recalculates the central value P of clusteri(i=1,2 ..., k), calculation formula
It is as follows:
(4) when the number of interative computation is equal to K, end is calculated, and otherwise calculates the convergence distance of each cluster of iteration, such as
Fruit is both less than D, terminates to calculate;Otherwise, (2) are jumped to, continue to calculate.The calculation formula of convergence distance is as follows:
(5) cluster to point cloud data is completed by above (1)-(4), when being unsatisfactory for cluster the number of iterations and apart from threshold
The point cloud of value is kicked out of, and the cluster segmentation of point cloud data is realized;
Step 3, the cluster segmentation of the point cloud data based on step 2 carries out feature extraction to the point cloud after cluster segmentation, by
In ideal belt edges be straight line, therefore use fitting a straight line method to point cloud data carry out feature extraction, step
It is as follows:
Using the vertical, horizontal of conveyer belt surface as two-dimensional coordinate system, cluster segmentation point cloud data is transformed into zone face coordinate system
Under two-dimensional coordinate (xi,yi) (i=1,2 ..., m) (m is the point cloud number for needing to be fitted), pass through Points cloud Fitting conveyer belt
The straight trip equation of one side edge: y=ax+b,
(1) selected distance cost functionIt, need to be to cost to solve parameter a and b
Function carries out seeking local derviation, enables:
(2) parameter a and b are solved according to (2):
Step 4, according to the actual motion orientation of the installation site of laser radar and belt conveyor, step can be derived
Under the conveyer belt areal coordinate system referred in 3, belt centerline equation y=kx+l of the ideal without sideslip, therefore can be according to two
The angle formulae of straight line calculates the operation angle theta between actual fed band and ideal conveyer belt:
That is angle theta:
Step 5, according to the angle theta calculated value of step 4, carry out belt of belt conveyor whether the differentiation of sideslip.
In the step 5, determines that the angle threshold value of belt deflection is 8 °, when θ > 8 °, determine that conveyer belt is run
Partially, otherwise, conveyer belt is without sideslip.
Beneficial effect is: the present invention uses the detection method based on laser radar, due to being non-contact detection, relative to
The detection method of pressure sensor, can constantly active detecting and processing, detection efficiency is high, and the working sensor service life is long;Meanwhile
Since the detection of laser radar is without being bound by the influence of the factors such as detection ambient light, weather, either daytime or night, nothing
By being fine day or rainy weather, the detection of laser radar is unaffected always, and compared to vision-based inspection, detection is reliable
Property significantly improves.
Detailed description of the invention
Fig. 1 is algorithm flow chart of the invention;
Fig. 2 is schematic diagram when left avertence occurs for present invention detection conveyer belt;
Fig. 3 is schematic diagram when right avertence occurs for present invention detection conveyer belt.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention more comprehensible, the present invention is carried out further specifically
It is bright.
As shown, a kind of Auto-rectification Device for Belt Conveyer detection method based on laser radar, comprising the following steps:
Step 1, using the point cloud data of laser radar acquisition testing belt of belt conveyor front surface;
Step 2, cluster segmentation processing, the cluster segmentation processing, tool are carried out to the point cloud data of laser radar acquisition
Body the following steps are included:
(1) it selectes and calculates in cluster process, maximum the number of iterations is K, calculates the effective maximal distance threshold of iteration and is
D, the initial center for selecting cluster calculation point is Oi(i=1,2 ..., k), k are the number of cluster centre, wherein Oi={ Oi1,
Oi2,…,Oin};
(2) each point cloud data is calculated to the center Euclidean distance of setting cluster, and the point of cloud is merged into distance
Near nearest cluster centre.Wherein, Euclidean distance calculation formula:
Wherein, d (xi,Oj) it is the distance for representing i-th point to j-th cluster centre, come to n point cloud data point.
(3) cluster obtained according to step (2) recalculates the central value P of clusteri(i=1,2 ..., k), calculation formula
It is as follows:
(4) when the number of interative computation is equal to K, end is calculated, and otherwise calculates the convergence distance of each cluster of iteration, such as
Fruit is both less than D, terminates to calculate;Otherwise, (2) are jumped to, continue to calculate.The calculation formula of convergence distance is as follows:
(5) cluster to point cloud data is completed by above (1)-(4), when being unsatisfactory for cluster the number of iterations and apart from threshold
The point cloud of value is kicked out of, and the cluster segmentation of point cloud data is realized;
Step 3, the cluster segmentation of the point cloud data based on step 2 carries out feature extraction to the point cloud after cluster segmentation, by
In ideal belt edges be straight line, therefore use fitting a straight line method to point cloud data carry out feature extraction, step
It is as follows:
Using the vertical, horizontal of conveyer belt surface as two-dimensional coordinate system, cluster segmentation point cloud data is transformed into zone face coordinate system
Under two-dimensional coordinate (xi,yi) (i=1,2 ..., m) (m is the point cloud number for needing to be fitted), pass through Points cloud Fitting conveyer belt
The straight trip equation of one side edge: y=ax+b,
(1) selected distance cost functionIt, need to be to cost to solve parameter a and b
Function carries out seeking local derviation, enables:
(2) parameter a and b are solved according to (2):
Step 4, according to the actual motion orientation of the installation site of laser radar and belt conveyor, step can be derived
Under the conveyer belt areal coordinate system referred in 3, belt centerline equation y=kx+l of the ideal without sideslip, therefore can be according to two
The angle formulae of straight line calculates the operation angle theta between actual fed band and ideal conveyer belt:
That is angle theta:
Step 5, according to the angle theta calculated value of step 4, carry out belt of belt conveyor whether the differentiation of sideslip.
In the step 5, determines that the angle threshold value of belt deflection is 8 °, when θ > 8 °, determine that conveyer belt is run
Partially, otherwise, conveyer belt is without sideslip.
Beneficial effect is: the present invention uses the detection method based on laser radar, due to being non-contact detection, relative to
The detection method of pressure sensor, can constantly active detecting and processing, detection efficiency is high, and the working sensor service life is long;Meanwhile
Since the detection of laser radar is without being bound by the influence of the factors such as detection ambient light, weather, either daytime or night, nothing
By being fine day or rainy weather, the detection of laser radar is unaffected always, and compared to vision-based inspection, detection is reliable
Property significantly improves.
Above embodiments are only to illustrate the present invention and not limit the technical scheme described by the invention;Therefore, although
The present invention has been described in detail referring to above-mentioned each embodiment for this specification, still, the ordinary skill of this field
Personnel should be appreciated that and still can modify to the present invention or equivalent replacement;And all do not depart from spirit and model of the invention
The technical solution and its improvement enclosed, should all cover within the scope of the claims of the present invention.
Claims (4)
1. a kind of Auto-rectification Device for Belt Conveyer detection method based on laser radar, which is characterized in that method includes the following steps:
Step 1, using the point cloud data of laser radar acquisition testing belt of belt conveyor front surface;
Step 2, cluster segmentation processing is carried out to the point cloud data of laser radar acquisition;
Step 3, the cluster segmentation of the point cloud data based on step 2 carries out feature extraction to the point cloud after cluster segmentation, due to reason
The belt edges thought are straight lines, therefore fitting a straight line method is used to carry out feature extraction to point cloud data;
Step 4, it according to the actual motion orientation of the installation site of laser radar and belt conveyor, can derive in step 3
Under the conveyer belt areal coordinate system referred to, belt centerline equation y=kx+l of the ideal without sideslip, therefore can be according to two straight lines
Angle formulae calculate the operation angle theta between actual fed band and ideal conveyer belt:
That is angle theta
Step 5, according to the angle theta calculated value of step 4, carry out belt of belt conveyor whether the differentiation of sideslip.
2. at the cluster segmentation of the Auto-rectification Device for Belt Conveyer detection method according to claim 1 based on laser radar
Reason, which is characterized in that specifically includes the following steps:
(1) it selectes and calculates in cluster process, maximum the number of iterations is K, and the calculating effective maximal distance threshold of iteration is D, choosing
The initial center for determining cluster calculation point is Oi(i=1,2 ..., k), k are the number of cluster centre, wherein Oi={ Oi1,Oi2,…,
Oin};
(2) each point cloud data is calculated to the center Euclidean distance of setting cluster, and the point of cloud is merged into distance recently
Cluster centre near.Wherein, Euclidean distance calculation formula:
Wherein, d (xi,Oj) it is the distance for representing i-th point to j-th cluster centre, come to n point cloud data point;
(3) cluster obtained according to step (2) recalculates the central value P of clusteri(i=1,2 ..., k), calculation formula is as follows:
(4) when the number of interative computation is equal to K, end is calculated, and the convergence distance of each cluster of iteration is otherwise calculated, if all
Less than D, terminate to calculate;Otherwise, (2) are jumped to, continue to calculate.The calculation formula of convergence distance is as follows:
The cluster to point cloud data is completed by above (1)-(4), when the point for being unsatisfactory for cluster the number of iterations and distance threshold
Cloud is kicked out of, and the cluster segmentation of point cloud data is realized.
3. the fitting a straight line method pair of the Auto-rectification Device for Belt Conveyer detection method according to claim 1 based on laser radar
Point cloud data carries out feature extraction, which is characterized in that using the vertical, horizontal of conveyer belt surface as two-dimensional coordinate system, by cluster segmentation
Point cloud data is transformed into the two-dimensional coordinate (x under zone face coordinate systemi,yi) (i=1,2 ..., m) (m is the point cloud number for needing to be fitted),
Pass through the straight trip equation of Points cloud Fitting conveyer belt one side edge: y=ax+b,
(1) selected distance cost functionIt, need to be to cost function to solve parameter a and b
It carries out seeking local derviation, enable:
(2) parameter a and b are solved according to (2):
4. a kind of Auto-rectification Device for Belt Conveyer detection method based on laser radar according to claim 1, which is characterized in that
In the step 5, determines that the angle threshold value of belt deflection is 8 °, when θ > 8 °, determine that sideslip occurs for conveyer belt, otherwise,
Conveyer belt is without sideslip.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811395287.7A CN109765570A (en) | 2018-11-22 | 2018-11-22 | A kind of Auto-rectification Device for Belt Conveyer detection method based on laser radar |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811395287.7A CN109765570A (en) | 2018-11-22 | 2018-11-22 | A kind of Auto-rectification Device for Belt Conveyer detection method based on laser radar |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109765570A true CN109765570A (en) | 2019-05-17 |
Family
ID=66449614
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811395287.7A Pending CN109765570A (en) | 2018-11-22 | 2018-11-22 | A kind of Auto-rectification Device for Belt Conveyer detection method based on laser radar |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109765570A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112027565A (en) * | 2020-09-28 | 2020-12-04 | 武汉科技大学 | Belt deviation alarming scram method for belt edge detection |
CN112027566A (en) * | 2020-09-30 | 2020-12-04 | 武汉科技大学 | Conveying belt deviation type judging and deviation measuring and calculating system based on laser scanning |
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 |
CN112254651A (en) * | 2020-09-28 | 2021-01-22 | 武汉科技大学 | Transverse deviation detection method based on laser scanning of central line of conveying belt |
CN112278776A (en) * | 2020-10-16 | 2021-01-29 | 福建龙净环保智能输送工程有限公司 | Detection device of belt conveyor |
CN113772364A (en) * | 2021-09-18 | 2021-12-10 | 中国矿业大学 | Deviation detection device for belt conveyor and automatic adjustment method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202575325U (en) * | 2012-03-05 | 2012-12-05 | 南京三埃工控股份有限公司 | Device for detecting deviation of conveyor belt of belt scale |
CN105512665A (en) * | 2015-12-11 | 2016-04-20 | 中国测绘科学研究院 | Airborne laser radar point cloud data edge extraction method |
CN106429301A (en) * | 2016-11-07 | 2017-02-22 | 中国矿业大学(北京) | Belt monitoring early warning device based on ultrasonic waves |
-
2018
- 2018-11-22 CN CN201811395287.7A patent/CN109765570A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202575325U (en) * | 2012-03-05 | 2012-12-05 | 南京三埃工控股份有限公司 | Device for detecting deviation of conveyor belt of belt scale |
CN105512665A (en) * | 2015-12-11 | 2016-04-20 | 中国测绘科学研究院 | Airborne laser radar point cloud data edge extraction method |
CN106429301A (en) * | 2016-11-07 | 2017-02-22 | 中国矿业大学(北京) | Belt monitoring early warning device based on ultrasonic waves |
Non-Patent Citations (3)
Title |
---|
张涛等: "带式输送机故障巡检机器人系统设计", 《工矿自动化》 * |
谭宝成等: "基于激光雷达的道路边界检测的研究", 《电子设计工程》 * |
龚亮等: "基于强度信息聚类的机载LiDAR点云道路提取", 《测绘通报》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112027565A (en) * | 2020-09-28 | 2020-12-04 | 武汉科技大学 | Belt deviation alarming scram method for belt edge detection |
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 |
CN112254651A (en) * | 2020-09-28 | 2021-01-22 | 武汉科技大学 | Transverse deviation detection method based on laser scanning of central line of conveying belt |
CN112254651B (en) * | 2020-09-28 | 2022-03-25 | 武汉科技大学 | Transverse deviation detection method based on laser scanning of central line of conveying belt |
CN112213317B (en) * | 2020-09-28 | 2024-02-09 | 武汉科技大学 | Conveyer belt tearing detection system and detection method based on three-dimensional laser scanning technology |
CN112027566A (en) * | 2020-09-30 | 2020-12-04 | 武汉科技大学 | Conveying belt deviation type judging and deviation measuring and calculating system based on laser scanning |
CN112278776A (en) * | 2020-10-16 | 2021-01-29 | 福建龙净环保智能输送工程有限公司 | Detection device of belt conveyor |
CN112278776B (en) * | 2020-10-16 | 2022-04-26 | 福建龙净环保智能输送工程有限公司 | Detection device of belt conveyor |
CN113772364A (en) * | 2021-09-18 | 2021-12-10 | 中国矿业大学 | Deviation detection device for belt conveyor and automatic adjustment method |
CN113772364B (en) * | 2021-09-18 | 2022-10-18 | 中国矿业大学 | Automatic adjusting method of belt conveyor deviation detecting device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109765570A (en) | A kind of Auto-rectification Device for Belt Conveyer detection method based on laser radar | |
Yang et al. | On-line conveyor belts inspection based on machine vision | |
CN107043000A (en) | A kind of belt conveyer safe and intelligent safeguards system based on machine vision | |
CN103150556B (en) | For the securing band automatic testing method of traffic monitoring | |
CN113724258B (en) | Conveyor belt tearing detection method and system based on image processing | |
CN103292714B (en) | Based on the belt conveyor coal piling state testing method of image technique | |
CN106290388A (en) | A kind of insulator breakdown automatic testing method | |
CN114155494B (en) | Belt conveyor deviation monitoring method based on deep learning | |
CN107804226A (en) | Trailer lane departur warning and wave alarm | |
CN104828517A (en) | Belt deviation detecting method based on visual sense | |
CN103869819A (en) | Belt conveyor automatic inspection system and method based on multi-rotor unmanned aerial vehicle | |
CN110697373A (en) | Conveying belt deviation fault detection method based on image recognition technology | |
CN102673979B (en) | Method and device for judging deviation of conveying belt | |
CN105083342B (en) | Hazard space monitoring at railway intersection | |
CN110065790A (en) | A kind of coal mine leather belt transhipment head choke detecting method of view-based access control model algorithm | |
CN104858155A (en) | Multi-line Internet of Things visual detection method for relay package sorting and system device | |
CN110288032A (en) | A kind of vehicle driving trace type detection method and device | |
US20200339171A1 (en) | Vehicle control system | |
CN204689038U (en) | The belt deviation detecting device of view-based access control model | |
CN108801172B (en) | Non-contact pantograph dynamic envelope measurement method and device | |
CN105045314A (en) | Stockyard environmental-friendly monitoring and sprinkling dust reduction pre-control system | |
CN103760903A (en) | Intelligent tracking conveying management system for warehouses | |
CN103425764A (en) | Vehicle matching method based on videos | |
CN104157160A (en) | Vehicle drive control method and device as well as vehicle | |
CN105222752A (en) | A kind of portable road face pick-up unit and method using structured light |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190517 |
|
RJ01 | Rejection of invention patent application after publication |