CN110902315A - Belt deviation state detection method and system - Google Patents
Belt deviation state detection method and system Download PDFInfo
- Publication number
- CN110902315A CN110902315A CN201911256921.3A CN201911256921A CN110902315A CN 110902315 A CN110902315 A CN 110902315A CN 201911256921 A CN201911256921 A CN 201911256921A CN 110902315 A CN110902315 A CN 110902315A
- Authority
- CN
- China
- Prior art keywords
- belt
- straight line
- belt deviation
- image
- deviation
- 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.)
- Granted
Links
Images
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
- B65G2203/02—Control or detection
- B65G2203/0266—Control or detection relating to the load carrier(s)
- B65G2203/0283—Position of the load carrier
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a belt deviation state detection method and a system, wherein the method comprises the following steps: collecting real-time belt transmission images; detecting the belt transmission image frame by frame through Hough line detection, and screening out a belt edge line by using an SVM classification algorithm; acquiring historical sample data, and calculating to obtain a threshold interval of belt deviation; comparing the belt edge straight line obtained by screening with a threshold value space of belt deviation, and calculating the belt deviation degree; meanwhile, a corresponding system is disclosed. The invention calculates the belt deviation condition in a mode of combining the visual algorithm analysis processing and the statistical analysis, can judge whether the conveying belt deviates in real time, triggers alarm information in time, informs workers and achieves correction maintenance or predictive maintenance in time.
Description
Technical Field
The invention relates to the technical field of conveying, in particular to a belt deviation state detection method and system.
Background
Belts, i.e., conveyor belts, are indispensable transport vehicles that are widely used in various factory lines and in article transfer rooms. The conveyor belt generally comprises: the device comprises a traction piece, a bearing member, a driving device, a tensioning device, a direction changing device, a supporting piece and the like. The supporting part is used for supporting the traction part or the bearing component and can adopt a carrier roller, a roller and the like; the traction piece is used for transmitting traction force and can adopt a conveying belt, a traction chain or a steel wire rope.
In actual use, the conveyor belt is influenced by the rolling shaft, materials, objects and the like, and the conveyor belt deviates in operation, so that normal production transportation is influenced.
The deviation of the conveying belt is one of the most common faults when the conveying belt runs, and the deviation of the conveying belt can influence normal production and transportation. The deviation of the conveying belt is various, and the common deviation reasons are deviation of installation positions, uneven materials, overweight and the like.
The existing deviation detection method mainly comprises the steps of fixing a traditional mechanical lifting type press wheel (see patent CN209112920U), detecting through fluorescence (see patent CN209009521U) and the like. The pressure wheel machine presses the belt back to the belt frame by utilizing the pressure wheel, so that the relative height of the belt and the belt frame is greatly adjusted, the limiting wheels are fixed on two sides of the belt and limit the left and right deviation of the belt, the mechanical responsibility of a conveying part is increased by the detection mode, and meanwhile, the abrasion of the belt is increased when the left and right deviation is limited; although the possibility that the conveying belt is abraded by the outside is reduced by fluorescence detection, the detection effect is affected by uneven materials, object deviation, even sand and dust shielding and the like during some conveying, and omission or false alarm occurs.
Disclosure of Invention
The invention provides a belt deviation state detection method and a belt deviation state detection system to solve the technical problems.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
according to a first aspect of the embodiments of the present invention, there is provided a belt offset state detection method, including the steps of:
102, detecting a belt transmission image frame by frame through Hough line detection, and screening out a belt edge line by using an SVM classification algorithm;
103, acquiring historical sample data, and calculating to obtain a threshold interval of belt deviation;
and 104, comparing the belt edge straight line obtained by screening with a threshold value space of belt deviation, and calculating the belt deviation degree.
Preferably, the step 102 includes:
step 1021, reading the image by frame, and intercepting a frame for analysis;
step 1022, acquiring a straight line in each frame of image through hough straight line detection;
and step 1023, screening out the belt edge straight line in each frame of image.
Preferably, the method for truncating a frame in step 1021 is truncating by frame according to the FFmpeg method.
Preferably, the step 1022 includes the steps of:
step 10221, converting the read image from RGB color value picture into corresponding gray image;
step 10222, using Canny edge detection to identify the actual edge in the image, and obtaining the straight line in the image through hough straight line detection.
Preferably, the step 1023 includes the following steps:
step 10231, screening out a transverse straight line, wherein the direction of the transverse straight line is consistent with the direction of a belt, and the transverse straight line is screened out according to whether Y values corresponding to two end points of the straight line obtained by Hough straight line detection are close or not;
step 10232, two end points of the straight line obtained by Hough straight line detection are a (x) respectively1,y1)、b(x2,y2) According to the coordinate x1、x2Screening out straight lines at the edge and inside of the belt according to the relationship between the two belts;
and step 10233, screening out two straight lines at the edge of the belt by using an SVM classification algorithm.
Preferably, the step 103 comprises the following steps:
and carrying out classification statistics on historical sample data, detecting straight lines of edges of two sides of the belt of each sample through Hough straight line detection, and carrying out mean value calculation on position data of the straight lines of the edges of the belt to obtain an interval of a belt central line, namely a threshold interval of belt deviation.
Preferably, step 104 is followed by:
and 105, transmitting the belt transmission image marked with the belt deviation degree to a storage mechanism, an actuating mechanism and a display device which are connected with the belt.
According to a second aspect of the embodiments of the present invention, there is provided a belt offset detection system, including:
the image acquisition module is used for acquiring a real-time belt transmission image;
the edge straight line analysis module is used for detecting the belt transmission image frame by frame through Hough straight line detection and screening out a belt edge straight line by using an SVM classification algorithm;
the threshold interval calculation module is used for acquiring historical sample data and calculating to obtain a threshold interval of belt deviation;
and the deviation degree calculation module is used for comparing the belt edge straight line obtained by screening with the threshold value space of belt deviation and calculating the belt deviation degree.
Preferably, the method further comprises the following steps:
and the result output module is used for transmitting the belt transmission image marked with the belt deviation degree to the storage mechanism, the actuating mechanism and the display device which are connected with the belt.
Preferably, the method further comprises the following steps:
and the alarm module is used for triggering alarm information when the belt deviation degree exceeds a limit value.
Compared with the prior art, the method calculates the belt deviation condition in a mode of combining visual algorithm analysis processing and statistical analysis, can judge whether the conveying belt deviates in real time, triggers alarm information in time, informs workers, and achieves correction maintenance or predictive maintenance in time.
Drawings
FIG. 1 is a flow chart of a belt deflection condition detection method of the present invention;
FIG. 2 is a flowchart of step 102 of the belt deflection condition detection method of the present invention;
FIG. 3 is a block diagram of a belt deflection condition detection system according to the present invention;
FIG. 4 is a block diagram of another embodiment of the belt deviation detecting system of the present invention; .
In the figure, 201-an image acquisition module, 202-an edge straight line analysis module, 203-a threshold interval calculation module, 204-an offset degree calculation module, 205-a result output module and 206-an alarm module.
Detailed Description
The present invention will be described in detail below with reference to specific embodiments shown in the drawings. These embodiments are not intended to limit the present invention, and structural, methodological, or functional changes made by those skilled in the art according to these embodiments are included in the scope of the present invention.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
As shown in fig. 1, a belt deviation state detecting method includes the following steps:
102, detecting a belt transmission image frame by frame through Hough line detection, and screening out a belt edge line by using an SVM classification algorithm;
103, acquiring historical sample data, and calculating to obtain a threshold interval of belt deviation;
and 104, comparing the belt edge straight line obtained by screening with a threshold value space of belt deviation, and calculating the belt deviation degree.
Each step is described in further detail below.
The acquisition in step 101 may be performed by an external camera, for example, a camera for acquiring images in real time is installed, and the cost is low compared to a dedicated device and a large mechanical facility. In particular, cameras are erected in some factory workshops for monitoring the transmission facilities, so that the original cameras can be transmitted to the equipment for analysis and calculation through a network without increasing additional cost.
As shown in fig. 2, the step 102 may specifically include:
step 1021, reading the image frame by frame, and capturing a frame for analysis.
And step 1022, acquiring a straight line in each frame of image through hough straight line detection.
And step 1023, screening out the belt edge straight line in each frame of image.
The method comprises the following steps that according to different connection modes of analysis and calculation equipment and collected equipment, reading is carried out through mobile storage equipment or network transmission; the method of truncating a frame in the step 1021 may be truncated by a frame according to the FFmpeg method.
Specifically, the step 1022 may include the following steps:
step 10221, convert the read image from RGB color value picture to corresponding gray scale image.
Step 10222, using Canny edge detection to identify the actual edge in the image, and obtaining the straight line in the image through hough straight line detection.
Specifically, the step 1023 may include the following steps:
and 10231, screening out a transverse straight line, wherein the direction of the transverse straight line is consistent with the direction of the belt, and the transverse straight line is screened out according to whether Y values corresponding to two end points of the straight line obtained by Hough straight line detection are close or not.
Step 10232, two end points of the straight line obtained by Hough straight line detection are a (x) respectively1,y1)、b(x2,y2) According to the coordinate x1、x2BetweenThe relationship (2) is to screen out the straight line at the edge and inside of the belt.
And step 10233, screening out two straight lines at the edge of the belt by using an SVM classification algorithm. The straight line associated with the belt is screened out through the first two steps, while the remaining are the detected belt edge and the internal straight line.
The hough line detection principle is simply that rectangular coordinates and polar coordinates are transformed, straight lines are mapped through points, all pixel points are traversed, and intersection points of polar coordinate curves are detected possible straight lines.
In a practical analysis of the present invention, two sidelines of the belt were found. Because the belt obtained in the actually obtained image is not a real straight line, but the polar diameter and the polar angle of the polar coordinate intersection point of each straight line are obtained through Hough line detection, and then the straight line drawn by the corresponding straight line end point is solved by using a formula, the edge straight line detection cannot directly and accurately obtain an accurate belt side line, and therefore SVM classification is required for analysis.
A Support Vector Machine (SVM) is a generalized linear classifier (generalized linear classifier) that performs binary classification on data in a supervised learning (supersupervisory) manner, and a decision boundary of the SVM is a maximum-margin hyperplane (maximum-margin hyperplane) for solving a learning sample. The SVM is a classifier with sparsity and robustness, which calculates empirical risk (empirical risk) by using hinge loss function (change loss) and adds regularization term to the solving system to optimize structural risk (structural risk). And setting a function to quantitatively measure the quality of any one W, wherein the function is a loss function by taking the W as an input and the score as an output. In the invention, the slope of the straight line left in the image is obtained as an input parameter, and the maximum positive direction or the maximum negative direction is used as an output parameter. The loss function used in the invention is as follows:
loss function:
the hinge loss function l (p) ═ max (0, 1-p).
Due to the fact thatThe sample set used for analysis is non-linearly separable, so the SVM non-linear classification is selected. SVMs can be classified non-linearly by a kernel method, which is one of the common kernel learning (kernel learning) methods. The feature space has a hyper-surface (hyper-surface) separating the positive and negative classes. The nonlinear separable problem can be mapped from the original feature space to a higher dimensional Hilbert space (Hilbert space) using a nonlinear function, thus transforming into a linear separable problem, where the hyperplane as a decision boundary is represented as follows: omegaTPhi (x) + b is 0, where phi:
is a mapping function. Since the mapping function has a complex form and it is difficult to calculate its inner product, a kernel method (kernel method) is adopted in the present invention, that is, the inner product of the mapping function is defined as a kernel function:
Therefore, dimension transformation can be bypassed, and the inner product of the points at high latitude can be solved by directly utilizing the kernel function for transformation. In the selection of kernel functions, the Gaussian kernel has the advantages of mapping to infinite dimension, various decision boundaries, only using one parameter and the like, and the formula is
Where σ is a hyperparameter of the kernel function.
Transforming the samples into a kernel function matrix by using a kernel function, wherein the step is equivalent to mapping the input data to a high-dimensional feature space through a nonlinear function; then, implementing various linear algorithms on the kernel function matrix in the feature space; a non-linear model in the input space is obtained. Therefore, the Gaussian kernel function is adopted as the kernel function of the SVM nonlinear classification in the invention.
In order to further retain the edge straight line, the invention adopts SVM classification.
There will be a division into a training sample set and a test sample set,labeling the sample image to obtain category labels Y of all samplesnAnd n is the total number of samples: and (3) obtaining the slope of the actual edge straight line of the belt by using a tool, marking the slope as a positive sample, marking the class label as +1, and marking the residual non-edge straight line, namely the straight line in the belt, which is obtained by screening the straight line as a negative sample, and marking the class label as-1.
And (3) training the SVM classifier to obtain a corresponding model by using the positive and negative sample extractor characteristic categories marked by the training sample set and the sample characteristics, and obtaining the classification accuracy, namely the required belt edge straight line by using the test sample set.
According to the training result, analysis can be carried out according to each frame, and according to the test result of the SVM analysis, the edge straight line in each frame of image is obtained and can be used for real-time analysis and prediction in the subsequent video stream reading process.
Calculating a belt deviation threshold interval according to historical sample data, wherein step 103 may include the following steps:
and carrying out classification statistics on historical sample data, detecting straight lines of edges of two sides of the belt of each sample through Hough straight line detection, and carrying out mean value calculation on position data of the straight lines of the edges of the belt to obtain an interval of a belt central line, namely a threshold interval of belt deviation.
In combination with statistical analysis, a large amount of historical sample data is required for analysis, and the historical sample data within one month can be acquired to improve the detection accuracy. The acquisition of historical sample data may be synchronized with step 101.
Finally, comparing the belt edge straight line obtained by screening in the step 102 with the belt deviation threshold space obtained by calculation in the step 103, calculating the belt deviation degree in the step 104, and judging whether the belt central line is in a normal threshold interval.
For process visualization, step 104 may further include:
and 105, transmitting the belt transmission image marked with the belt deviation degree to a storage mechanism, an actuating mechanism and a display device which are connected with the belt.
For example, the lower right hand corner of the resulting belt-conveyed image may be captured in step 101, with visual information added via any auxiliary means for user and expert verification.
In addition, in order to alarm in time when the belt transmission is abnormal, step 104 may further include: and triggering alarm information when the belt deviation degree exceeds a limit value. The limit value can be set in advance according to actual needs.
Based on the above method, as shown in fig. 3, the present invention further provides a belt deviation detecting system, including:
an image acquisition module 201, configured to acquire a real-time belt-conveyed image;
the edge straight line analysis module 202 is used for detecting the belt transmission image frame by frame through Hough straight line detection and screening out a belt edge straight line by using an SVM classification algorithm;
a threshold interval calculation module 203, configured to obtain historical sample data, and calculate to obtain a threshold interval of belt deviation;
and the deviation degree calculation module 204 is configured to compare the screened belt edge straight line with a threshold space of belt deviation, and calculate a belt deviation degree.
For process visualization, as shown in fig. 4, the belt deviation calculation system may further include:
and a result output module 205 for transmitting the belt transmission image marked with the belt deviation degree to a storage mechanism, an actuating mechanism and a display device connected with the belt.
In order to alarm in time when the belt transmission is abnormal, as shown in fig. 4, the belt deviation detecting system may further include:
and the alarm module 206 is used for triggering alarm information when the belt deviation degree exceeds a limit value.
With regard to the system in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (10)
1. The belt deviation state detection method is characterized by comprising the following steps:
step 101, collecting real-time belt transmission images;
102, detecting a belt transmission image frame by frame through Hough line detection, and screening out a belt edge line by using an SVM classification algorithm;
103, acquiring historical sample data, and calculating to obtain a threshold interval of belt deviation;
and 104, comparing the belt edge straight line obtained by screening with a threshold value space of belt deviation, and calculating the belt deviation degree.
2. The belt deviation state detecting method according to claim 1, wherein the step 102 includes:
step 1021, reading the image by frame, and intercepting a frame for analysis;
step 1022, acquiring a straight line in each frame of image through hough straight line detection;
and step 1023, screening out the belt edge straight line in each frame of image.
3. The belt deviation detecting method as claimed in claim 2, wherein said step 1021 is a method of truncating a frame according to FFmpeg method.
4. The belt deviation state detecting method as claimed in claim 2, wherein said step 1022 comprises the steps of:
step 10221, converting the read image from RGB color value picture into corresponding gray image;
step 10222, using Canny edge detection to identify the actual edge in the image, and obtaining the straight line in the image through hough straight line detection.
5. The belt deviation state detecting method according to claim 4, wherein the step 1023 includes the steps of:
step 10231, screening out a transverse straight line, wherein the direction of the transverse straight line is consistent with the direction of a belt, and the transverse straight line is screened out according to whether Y values corresponding to two end points of the straight line obtained by Hough straight line detection are close or not;
step 10232, two end points of the straight line obtained by Hough straight line detection are a (x) respectively1,y1)、b(x2,y2) According to the coordinate x1、x2Screening out straight lines at the edge and inside of the belt according to the relationship between the two belts;
and step 10233, screening out two straight lines at the edge of the belt by using an SVM classification algorithm.
6. The belt deviation state detecting method according to claim 1, wherein said step 103 comprises the steps of:
and carrying out classification statistics on historical sample data, detecting straight lines of edges of two sides of the belt of each sample through Hough straight line detection, and carrying out mean value calculation on position data of the straight lines of the edges of the belt to obtain an interval of a belt central line, namely a threshold interval of belt deviation.
7. The belt deviation detecting method as claimed in claim 1, further comprising, after step 104:
and 105, transmitting the belt transmission image marked with the belt deviation degree to a storage mechanism, an actuating mechanism and a display device which are connected with the belt.
8. A belt deflection calculation system, comprising:
the image acquisition module is used for acquiring a real-time belt transmission image;
the edge straight line analysis module is used for detecting the belt transmission image frame by frame through Hough straight line detection and screening out a belt edge straight line by using an SVM classification algorithm;
the threshold interval calculation module is used for acquiring historical sample data and calculating to obtain a threshold interval of belt deviation;
and the deviation degree calculation module is used for comparing the belt edge straight line obtained by screening with the threshold value space of belt deviation and calculating the belt deviation degree.
9. The belt deviation state detecting system according to claim 8, further comprising:
and the result output module is used for transmitting the belt transmission image marked with the belt deviation degree to the storage mechanism, the actuating mechanism and the display device which are connected with the belt.
10. The belt deviation state detecting system according to claim 8, further comprising:
and the alarm module is used for triggering alarm information when the belt deviation degree exceeds a limit value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911256921.3A CN110902315B (en) | 2019-12-10 | 2019-12-10 | Belt deviation state detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911256921.3A CN110902315B (en) | 2019-12-10 | 2019-12-10 | Belt deviation state detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110902315A true CN110902315A (en) | 2020-03-24 |
| CN110902315B CN110902315B (en) | 2022-04-01 |
Family
ID=69823999
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911256921.3A Active CN110902315B (en) | 2019-12-10 | 2019-12-10 | Belt deviation state detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110902315B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112124900A (en) * | 2020-08-28 | 2020-12-25 | 西安科技大学 | Visual detection method for underground belt deviation |
| CN113112485A (en) * | 2021-04-20 | 2021-07-13 | 中冶赛迪重庆信息技术有限公司 | Belt conveyor deviation detection method, system, equipment and medium based on image processing |
| CN113184449A (en) * | 2021-04-29 | 2021-07-30 | 广东华于科技股份有限公司 | Intelligent conveying management and control system for metal powder products |
| CN113343834A (en) * | 2021-06-02 | 2021-09-03 | 华电邹县发电有限公司 | Belt deviation diagnosis method based on machine vision and laser line |
| CN113378952A (en) * | 2021-06-22 | 2021-09-10 | 中冶赛迪重庆信息技术有限公司 | Method, system, medium and terminal for detecting deviation of belt conveyor |
| CN113763376A (en) * | 2021-09-17 | 2021-12-07 | 深圳市赛为智能股份有限公司 | Conveyor belt deviation detection method and device, computer equipment and storage medium |
| CN113844857A (en) * | 2021-08-02 | 2021-12-28 | 上海大学 | Method for identifying six types of running states of belt conveyor carrier roller based on sound wave signals |
| CN114234815A (en) * | 2021-11-22 | 2022-03-25 | 深圳江行联加智能科技有限公司 | Laser coal conveying belt deviation monitoring method, device, equipment and storage medium |
| CN114313883A (en) * | 2022-02-08 | 2022-04-12 | 深圳市铁越电气有限公司 | Belt deviation automatic detection method and system based on image processing technology |
| CN114742864A (en) * | 2022-03-18 | 2022-07-12 | 国能网信科技(北京)有限公司 | Belt deviation detection method and device |
| CN115082456A (en) * | 2022-07-27 | 2022-09-20 | 煤炭科学研究总院有限公司 | Coal mine belt conveyor fault diagnosis method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003327317A (en) * | 2002-05-14 | 2003-11-19 | Fuji Conveyor Kk | Belt conveyer |
| CN101738224A (en) * | 2008-11-04 | 2010-06-16 | 任安祥 | Working condition detecting method, device and system |
| 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 |
| CN203728114U (en) * | 2014-01-14 | 2014-07-23 | 北京富力通能源软件技术有限公司 | Belt deviation early warning device |
| CN105083912A (en) * | 2015-07-07 | 2015-11-25 | 青岛科技大学 | Conveyer belt deviation detecting method based on image identification |
| CN109284658A (en) * | 2017-07-23 | 2019-01-29 | 北京遥感设备研究所 | The straight way rail detection method that a kind of support vector machines and Hough transform combine |
| CN109969736A (en) * | 2019-01-17 | 2019-07-05 | 上海大学 | A kind of large size carrier strip deviation fault intelligent detecting method |
| CN110040470A (en) * | 2019-05-21 | 2019-07-23 | 精英数智科技股份有限公司 | A kind of monitoring method of artificial intelligence video identification belt deviation |
-
2019
- 2019-12-10 CN CN201911256921.3A patent/CN110902315B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003327317A (en) * | 2002-05-14 | 2003-11-19 | Fuji Conveyor Kk | Belt conveyer |
| CN101738224A (en) * | 2008-11-04 | 2010-06-16 | 任安祥 | Working condition detecting method, device and system |
| 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 |
| CN203728114U (en) * | 2014-01-14 | 2014-07-23 | 北京富力通能源软件技术有限公司 | Belt deviation early warning device |
| CN105083912A (en) * | 2015-07-07 | 2015-11-25 | 青岛科技大学 | Conveyer belt deviation detecting method based on image identification |
| CN109284658A (en) * | 2017-07-23 | 2019-01-29 | 北京遥感设备研究所 | The straight way rail detection method that a kind of support vector machines and Hough transform combine |
| CN109969736A (en) * | 2019-01-17 | 2019-07-05 | 上海大学 | A kind of large size carrier strip deviation fault intelligent detecting method |
| CN110040470A (en) * | 2019-05-21 | 2019-07-23 | 精英数智科技股份有限公司 | A kind of monitoring method of artificial intelligence video identification belt deviation |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112124900B (en) * | 2020-08-28 | 2022-05-20 | 西安科技大学 | Visual detection method for underground belt deviation |
| CN112124900A (en) * | 2020-08-28 | 2020-12-25 | 西安科技大学 | Visual detection method for underground belt deviation |
| CN113112485A (en) * | 2021-04-20 | 2021-07-13 | 中冶赛迪重庆信息技术有限公司 | Belt conveyor deviation detection method, system, equipment and medium based on image processing |
| CN113184449B (en) * | 2021-04-29 | 2022-03-01 | 广东华于科技股份有限公司 | Intelligent conveying management and control system for metal powder products |
| CN113184449A (en) * | 2021-04-29 | 2021-07-30 | 广东华于科技股份有限公司 | Intelligent conveying management and control system for metal powder products |
| CN113343834A (en) * | 2021-06-02 | 2021-09-03 | 华电邹县发电有限公司 | Belt deviation diagnosis method based on machine vision and laser line |
| CN113378952A (en) * | 2021-06-22 | 2021-09-10 | 中冶赛迪重庆信息技术有限公司 | Method, system, medium and terminal for detecting deviation of belt conveyor |
| CN113844857A (en) * | 2021-08-02 | 2021-12-28 | 上海大学 | Method for identifying six types of running states of belt conveyor carrier roller based on sound wave signals |
| CN113763376A (en) * | 2021-09-17 | 2021-12-07 | 深圳市赛为智能股份有限公司 | Conveyor belt deviation detection method and device, computer equipment and storage medium |
| CN113763376B (en) * | 2021-09-17 | 2024-03-01 | 深圳市赛为智能股份有限公司 | Conveyor belt offset detection method, conveyor belt offset detection device, computer equipment and storage medium |
| CN114234815A (en) * | 2021-11-22 | 2022-03-25 | 深圳江行联加智能科技有限公司 | Laser coal conveying belt deviation monitoring method, device, equipment and storage medium |
| CN114313883A (en) * | 2022-02-08 | 2022-04-12 | 深圳市铁越电气有限公司 | Belt deviation automatic detection method and system based on image processing technology |
| CN114313883B (en) * | 2022-02-08 | 2024-03-12 | 深圳市铁越电气有限公司 | Automatic detection method and system for belt deviation based on image processing technology |
| CN114742864A (en) * | 2022-03-18 | 2022-07-12 | 国能网信科技(北京)有限公司 | Belt deviation detection method and device |
| CN115082456A (en) * | 2022-07-27 | 2022-09-20 | 煤炭科学研究总院有限公司 | Coal mine belt conveyor fault diagnosis method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110902315B (en) | 2022-04-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110902315B (en) | Belt deviation state detection method and system | |
| CN110390691B (en) | Ore dimension measuring method based on deep learning and application system | |
| CN109255787B (en) | System and method for detecting scratch of silk ingot based on deep learning and image processing technology | |
| CN109550712B (en) | Chemical fiber filament tail fiber appearance defect detection system and method | |
| CN109969736B (en) | Intelligent detection method for deviation fault of large carrying belt | |
| Yang et al. | On-line conveyor belts inspection based on machine vision | |
| CN103913468B (en) | Many defects of vision checkout equipment and the method for large-scale LCD glass substrate on production line | |
| CN110490842B (en) | Strip steel surface defect detection method based on deep learning | |
| CN106548111B (en) | A kind of two dimensional code open defect detection method and device | |
| KR20200087297A (en) | Defect inspection method and apparatus using image segmentation based on artificial neural network | |
| CN112001878A (en) | Deep learning ore scale measuring method based on binarization neural network and application system | |
| CN117635565A (en) | Semiconductor surface defect detection system based on image recognition | |
| CN111161292A (en) | Ore size measurement method and application system | |
| CN114772208B (en) | Non-contact belt tearing detection system and method based on image segmentation | |
| CN111398287A (en) | Battery pole piece scratch detection system and detection method | |
| CN108804987A (en) | Door open and-shut mode detection method and device and stream of people's detecting system | |
| CN107610119A (en) | The accurate detection method of steel strip surface defect decomposed based on histogram | |
| CN111968082A (en) | Product packaging defect detection and identification method based on machine vision | |
| US12002196B2 (en) | Electronic device and method for marking defects of products | |
| CN117689651A (en) | Coal mine belt deviation detection method based on semantic segmentation and target detection | |
| CN109682445B (en) | Method for measuring instantaneous relative conveying capacity of belt conveyor based on video analysis | |
| CN114972349B (en) | Carrier roller running state detection method and system based on image processing | |
| CN114820582B (en) | Mobile phone surface defect accurate grading method based on mixed attention deformation convolutional neural network | |
| CN115988175A (en) | Vending machine material channel monitoring system based on machine vision | |
| CN114092410B (en) | Mobile phone surface defect accurate identification method based on multi-scale convolutional neural network |
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 | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: Room 1-1-180, No. 150, Changpu Road, Jishigang Town, Haishu District, Ningbo, Zhejiang 315016 Patentee after: Lanzhuo Digital Technology Co.,Ltd. Address before: Room 150 (1-1-180), Changpu Road, jishigang Town, Haishu District, Ningbo City, Zhejiang Province Patentee before: ZHEJIANG LANZHUO INDUSTRIAL INTERNET INFORMATION TECHNOLOGY Co.,Ltd. |