CN114044325A - Coal conveying belt fault detection system - Google Patents
Coal conveying belt fault detection system Download PDFInfo
- Publication number
- CN114044325A CN114044325A CN202111347306.0A CN202111347306A CN114044325A CN 114044325 A CN114044325 A CN 114044325A CN 202111347306 A CN202111347306 A CN 202111347306A CN 114044325 A CN114044325 A CN 114044325A
- Authority
- CN
- China
- Prior art keywords
- image
- fault
- category
- module
- classification
- 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
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
- B65G43/00—Control devices, e.g. for safety, warning or fault-correcting
- B65G43/04—Control devices, e.g. for safety, warning or fault-correcting detecting slip between driving element and load-carrier, e.g. for interrupting the drive
-
- 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
- B65G2201/00—Indexing codes relating to handling devices, e.g. conveyors, characterised by the type of product or load being conveyed or handled
- B65G2201/04—Bulk
- B65G2201/045—Sand, soil and mineral ore
-
- 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
Abstract
The present disclosure relates to a coal conveyor belt fault detection system, comprising: the image acquisition device is configured to acquire image information above the coal conveying belt; and the image analysis module is configured to analyze the image information acquired by the image acquisition device, determine whether a preset fault occurs, and if so, send fault information to a remote monitoring center and/or a patrol inspection person. The coal conveying belt fault detection system provided by the invention can analyze the image information on the coal conveying belt through the neural network algorithm model, and confirms the fault type and fault classification based on different training sets.
Description
Technical Field
The invention relates to a production monitoring system, in particular to a coal conveying belt fault detection system.
Background
The working principle of the coal conveying belt is that a motor rotates to drive a transmission roller to rotate through a speed reducer, and a tensioning device provides tension required by the belt. According to the principle of friction transmission, the transmission roller drives the coal conveying belt to run, so that the coal materials carried on the transmission roller are conveyed to a destination. Generally, various faults of the coal conveying belt are inevitable during operation, wherein the main faults comprise belt deviation, belt slip, belt fracture, belt tearing, belt coal breakage and the like. Although various protection devices can be arranged to protect the coal conveying belt against the common faults, for example, a pull rope protection device of the coal conveying belt is mainly used for timely stopping the coal conveying belt when a worker finds any fault. For example, a run-off protection device for a coal belt and a slip protection device for a coal belt. However, various protection devices at present can only play an auxiliary role, most faults still need to be manually checked by operation and maintenance personnel, a large amount of manpower and material resources are consumed, and improvement is needed.
Disclosure of Invention
In view of the above problems of the prior art, an object of the present invention is to provide a coal belt failure detection system capable of assisting in detecting various types of failures of a coal belt while reducing labor input.
In order to achieve the above object, an aspect of the present invention provides a coal belt failure detection system, comprising:
the image acquisition device is configured to acquire image information above the coal conveying belt;
and the image analysis module is configured to analyze the image information acquired by the image acquisition device, determine whether a preset fault occurs, and if so, send fault information to a remote monitoring center and/or a patrol inspection person.
Preferably, the preset category has a preset first category, the system further includes an image classification module, the image classification module is configured to classify the image information acquired by the image acquisition device based on the first category before image analysis is performed, the image analysis module includes a plurality of image analysis sub-modules, and each image analysis sub-module corresponds to a fault category in the first category.
Preferably, the system further comprises an image preprocessing module configured to preprocess the image information acquired by the image acquisition device.
Preferably, when the image preprocessing module preprocesses the image information, the image preprocessing module includes:
removing blank image frames;
removing the overexposed or underexposed image frames;
the remaining image frames are constructed as a first test set.
Preferably, the image classification module, when classifying the image information, includes:
inputting the first test set into the image classification module;
dividing the first test set into a plurality of first test subsets corresponding to the first category according to the first category;
the image analysis module includes at least the image analysis sub-modules corresponding to the first test subset number.
Preferably, the method further comprises a neural network algorithm model, wherein the neural network algorithm model is trained by at least a first training set and a second training set, the first training set is formed by pre-classifying the fault pictures of different classes corresponding to the first classification, and the second training set is formed by determined fault classification pictures corresponding to the classes.
Preferably, the system further comprises a fault confirmation module, and the fault confirmation module is configured to additionally store the confirmed fault classification picture in the first training set according to the confirmation of the inspection staff.
Preferably, the fault confirming module is further configured to additionally store the picture of the confirmed fault classification to the second training set according to the confirmation of the inspection staff.
Compared with the prior art, the coal conveying belt fault detection system provided by the invention can analyze the image information on the coal conveying belt through the neural network algorithm model, and confirms the fault type and fault classification based on different training sets. In addition, in some improved schemes, the fault types and fault grades confirmed by the inspection personnel on the site can be further supplemented to a training set for self-learning, and higher fault detection accuracy is realized.
Drawings
FIG. 1 is a block diagram of a coal conveyor belt fault detection system according to the present invention.
Description of reference numerals:
1-a first training set; 2-a second training set; 3-neural network algorithm model; 4-an image preprocessing module; 5-an image classification module; 6-an image analysis module; 7-remote monitoring center; 8-inspection personnel; 9-a failure confirmation module; 10-an image acquisition device; 100-coal conveying belt.
Detailed Description
In order to make the technical solutions of the present invention better understood, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
Various aspects and features of the present invention are described herein with reference to the drawings.
These and other characteristics of the invention will become apparent from the following description of a preferred form of embodiment, given as a non-limiting example, with reference to the accompanying drawings.
It should also be understood that, although the invention has been described with reference to some specific examples, a person of skill in the art shall certainly be able to achieve many other equivalent forms of the invention, having the characteristics as set forth in the claims and hence all coming within the field of protection defined thereby.
The above and other aspects, features and advantages of the present invention will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.
As shown in fig. 1, an embodiment of the present invention provides a coal belt failure detection system according to an aspect of the present invention, including:
an image acquisition device 10 configured to acquire image information above the coal conveyor belt 100; this image acquisition device 10, the explosion-proof mining camera of specifically selectable double-circuit. It may be located directly above the coal belt 100 and may be wired to an upper computer (not shown in fig. 1) that deploys an algorithmic model for image recognition. In practical production, the image acquisition device 10 for implementing the method of the present invention may also comprise at least two industrial cameras of the same type, and a small workstation with an image acquisition card as an upper computer. Two cameras are fixed above a production line to be monitored, and the cameras are adjusted to be aligned to a specific area, so that the relative positions of the two cameras are fixed and the relative positions of the two cameras are not changed.
Specifically, referring to fig. 1, the system of the present invention further includes an image analysis module 6 configured to analyze the image information collected by the image collection device 10 to determine whether a preset fault occurs, and if so, send fault information to the remote monitoring center 7 and/or the inspection personnel 8. The image analysis module 6 may specifically be an artificial intelligence algorithm based on deep learning (of a neural network), and may also be other artificial intelligence algorithms (for example, Random Forest, Gradient Boosting Tree, etc.). The calculated result comprises the coal flow carried by the belt, the type and the size of foreign matters, the possibility of longitudinal tearing of the belt and the like. For example, the result may be that the image features show the probability that a certain type of fault appears on the carrier belt, and also a fault rating may be given. The relevant area refers to the region of interest. The relevant area may be marked by one or more images. Each pixel in the image may be a number value for a different region or a probability value that the pixel belongs to a region. The relevant area may also be an area enclosed by one or more computer graphics (e.g., lines, curves, boxes, circles).
Specifically, in the present invention, the preset category has a preset first category, the system further includes an image classification module 5, the image classification module 5 is configured to classify the image information acquired by the image acquisition device 10 based on the first category before performing image analysis, and the image analysis module 5 includes a plurality of image analysis sub-modules (not shown in the figure), each of the image analysis sub-modules corresponds to a fault category in the first category. In this step, the image classification module 5 and the image classification module for determining the fault category are preferably trained by a neural network algorithm model 3, the neural network algorithm model 3 is trained by at least a first training set 1 and a second training set 2, the first training set 1 is formed by pre-classifying the fault pictures of different categories corresponding to the first category, and the second training set 2 is formed by the determined fault classification pictures corresponding to the categories. Of course, the process can still adopt an image classification algorithm similar to the result of the neural network model algorithm, and can also reversely deduce the area bringing the decision in the image through a network reverse algorithm so as to locate the abnormal or specific attention area. The network inverse algorithm is to apply a descending Gradient value (Gradient value) for network parameter optimization to the variable value transmitted in the network in the reverse direction, so as to estimate the area (such as abnormal area) which has a forward influence on a certain decision.
In other embodiments, as shown in fig. 1, the system further preferably includes an image preprocessing module 4, and the image preprocessing module 4 is configured to preprocess the image information acquired by the image acquisition device 10. The pretreatment method may specifically include: removing blank image frames; removing the overexposed or underexposed image frames; the remaining image frames are constructed as a first test set. In the specific processing, the algorithm preferably includes: defogging, dedusting and synchronous denoising algorithms based on dark channel prior and a bilateral filter (DCBF); a self-adaptive background modeling and updating method based on a clustering technology; a single target tracking algorithm based on FLSVMIL; and (3) a multi-target tracking algorithm based on unscented Kalman filtering algorithm (UKF-MHT).
In addition, in the present invention, it is preferable that the image classification module 5 further includes, when classifying the image information: inputting the first test set into the image classification module; dividing the first test set into a plurality of first test subsets corresponding to the first category according to the first category; the image analysis module includes at least the image analysis sub-modules corresponding to the first test subset number.
Furthermore, the system further comprises a fault confirmation module 9, wherein the fault confirmation module 9 is configured to additionally store the confirmed fault classification picture to the first training set according to the confirmation of the inspection personnel. Similarly, the fault confirming module is further configured to additionally store the pictures with confirmed fault grades to the second training set according to the confirmation of the inspection personnel.
The above embodiments are only exemplary embodiments of the present invention, and are not intended to limit the present invention, and the scope of the present invention is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present invention, and such modifications and equivalents should also be considered as falling within the scope of the present invention.
Claims (8)
1. Defeated coal belt fault detection system includes:
the image acquisition device is configured to acquire image information above the coal conveying belt;
and the image analysis module is configured to analyze the image information acquired by the image acquisition device, determine whether a preset fault occurs, and if so, send fault information to a remote monitoring center and/or a patrol inspection person.
2. The system of claim 1, the preset category having a preset first category, the system further comprising an image classification module configured to classify image information captured by the image capture device based on the first category prior to image analysis, the image analysis module comprising a plurality of image analysis sub-modules, each of the image analysis sub-modules corresponding to a respective fault category in the first category.
3. The system of claim 1, further comprising an image pre-processing module configured to pre-process image information acquired by the image acquisition device.
4. The system of claim 3, the image pre-processing module, when pre-processing the image information, comprising:
removing blank image frames;
removing the overexposed or underexposed image frames;
the remaining image frames are constructed as a first test set.
5. The system of claim 1, the image classification module, in classifying the image information, comprising:
inputting the first test set into the image classification module;
dividing the first test set into a plurality of first test subsets corresponding to the first category according to the first category;
the image analysis module includes at least the image analysis sub-modules corresponding to the first test subset number.
6. The system of claim 1, further comprising a neural network algorithm model trained from at least a first training set consisting of pre-classified respective different classes of fault pictures for a first classification and a second training set consisting of determined fault classification pictures for the respective classification.
7. The system of claim 1, further comprising a fault confirmation module configured to additionally store a confirmed fault classification picture to the first training set based on confirmation by the inspector.
8. The system of claim 7, the fault confirmation module further configured to additionally store a picture of confirmed fault ratings to the second training set upon confirmation by the inspector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111347306.0A CN114044325A (en) | 2021-11-15 | 2021-11-15 | Coal conveying belt fault detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111347306.0A CN114044325A (en) | 2021-11-15 | 2021-11-15 | Coal conveying belt fault detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114044325A true CN114044325A (en) | 2022-02-15 |
Family
ID=80209071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111347306.0A Pending CN114044325A (en) | 2021-11-15 | 2021-11-15 | Coal conveying belt fault detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114044325A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108298273A (en) * | 2018-01-24 | 2018-07-20 | 孙成梁 | Belt feeder intelligent inspection system |
| CN207658605U (en) * | 2018-02-14 | 2018-07-27 | 北京广天夏科技有限公司 | Underground belt conveyer abnormal detector |
| KR20190036426A (en) * | 2017-09-27 | 2019-04-04 | 주식회사 포스코아이씨티 | System and Method for Recognizing Double Loading of Baggage |
| CN109614946A (en) * | 2018-12-18 | 2019-04-12 | 华能国际电力股份有限公司大连电厂 | Thermal power plant coal handling system personnel safety guard's method and system based on digital image recognition technology |
| CN112919050A (en) * | 2021-02-04 | 2021-06-08 | 华润电力技术研究院有限公司 | Conveyor belt monitoring method, device, equipment and computer readable storage medium |
| CN113086549A (en) * | 2021-03-01 | 2021-07-09 | 广东能源集团科学技术研究院有限公司 | Multi-agent cooperative monitoring system for coal conveying belt of thermal power plant |
| CN113283344A (en) * | 2021-05-27 | 2021-08-20 | 中国矿业大学 | Mining conveying belt deviation detection method based on semantic segmentation network |
-
2021
- 2021-11-15 CN CN202111347306.0A patent/CN114044325A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190036426A (en) * | 2017-09-27 | 2019-04-04 | 주식회사 포스코아이씨티 | System and Method for Recognizing Double Loading of Baggage |
| CN108298273A (en) * | 2018-01-24 | 2018-07-20 | 孙成梁 | Belt feeder intelligent inspection system |
| CN207658605U (en) * | 2018-02-14 | 2018-07-27 | 北京广天夏科技有限公司 | Underground belt conveyer abnormal detector |
| CN109614946A (en) * | 2018-12-18 | 2019-04-12 | 华能国际电力股份有限公司大连电厂 | Thermal power plant coal handling system personnel safety guard's method and system based on digital image recognition technology |
| CN112919050A (en) * | 2021-02-04 | 2021-06-08 | 华润电力技术研究院有限公司 | Conveyor belt monitoring method, device, equipment and computer readable storage medium |
| CN113086549A (en) * | 2021-03-01 | 2021-07-09 | 广东能源集团科学技术研究院有限公司 | Multi-agent cooperative monitoring system for coal conveying belt of thermal power plant |
| CN113283344A (en) * | 2021-05-27 | 2021-08-20 | 中国矿业大学 | Mining conveying belt deviation detection method based on semantic segmentation network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111432182B (en) | Safety supervision method and system for oil discharge place of gas station | |
| CN108038424B (en) | Visual automatic detection method suitable for high-altitude operation | |
| US10125001B2 (en) | Method for monitoring and controlling a filling system, and device for carrying out said method | |
| CN110015553B (en) | Foreign matter detection and protection method for conveyor belt system based on video analysis | |
| CN113658136B (en) | Deep learning-based conveyor belt defect detection method | |
| CN103383361A (en) | Steel wire core conveyer belt detection device and method | |
| CN107798336A (en) | A kind of infrared measurement of temperature image component recognition methods | |
| CN111289529A (en) | Conveying belt tearing detection system and detection method based on AI intelligent analysis | |
| CN111591715A (en) | Belt longitudinal tearing detection method and device | |
| CN113297885A (en) | Belt conveyor surface state detection method and device based on convolutional neural network | |
| CN114429544A (en) | Method, system and device for detecting damage of screen of vibrating screen based on computer vision | |
| CN116177146A (en) | Conveying belt detection system and method based on AI and laser monitoring technology | |
| CN115144399A (en) | Assembly quality detection method and device based on machine vision | |
| CN114772208A (en) | Non-contact belt tearing detection system and method based on image segmentation | |
| CN113297913B (en) | Identification method for dressing specification of distribution network field operators | |
| CN114044325A (en) | Coal conveying belt fault detection system | |
| CN115504187B (en) | Intelligent speed regulation and protection system and control method for mining belt | |
| CN115661707A (en) | Belt deviation identification algorithm based on inspection robot | |
| CN114120175A (en) | Method for identifying foreign matters on coal conveying belt based on computer vision | |
| CN114359779B (en) | Belt tearing detection method based on deep learning | |
| CN114757905A (en) | Vision-based rope winding abnormity detection device and method | |
| CN114418983A (en) | Equipment risk detection method based on intelligent Internet of things | |
| CN111666916B (en) | Kitchen violation identification method based on self-learning technology | |
| CN105057226A (en) | Melon agricultural product sorting method | |
| WO2024015545A1 (en) | Cable damage detection by machine vision |
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 |