Research On Mining Conveyor Belt Longitudinal Tear Detection System Based On Vision

In the coal mine transportation system,the conveyor belt is often impacted by schist,gangue,bolt and other sharp hard impurities in the coal flow,and it is easy to tear lengthwise.Once the conveyor belt longitudinal tear,if not found in time and shut down will cause great economic losses,and even casualties.In view of the problems existing in the visual detection of longitudinal tearing of conveyor belt,such as easy contamination,low detection accuracy and low automation intelligence of industrial camera or line laser transmitter,this thesis developed a set of mining conveyor belt longitudinal tearing detection system based on vision.The main research contents are as follows:(1)Based on the actual condition of underground coal mine,the overall structure of the longitudinal tear detection system of mine conveyor belt is designed.According to the system requirements and downhole environment requirements,hardware design and selection.Aiming at the problems of not obvious longitudinal tear feature and high false positive rate of single-line laser detection,the layout scheme of multi-line laser emitter and industrial camera was designed to highlight and highlight the longitudinal tear feature and improve the accuracy of longitudinal tear detection.The optimal layout scheme was determined by experiments.Finally,according to the overall structure of the inspection system,the inspection process of vision system and the system software developed are summarized.(2)A new type of automatic dedusting protection device for line laser transmitter and industrial camera is developed in order to solve the pollution problem caused by harsh environment in coal mine.Firstly,aiming at the problems existing in the dustproof device,the structure of the device is improved,and the automatic dustproof protection device is designed.Secondly,the 3D model of the automatic dust removal protection device is established,and the statics analysis of its key components is carried out by ABAQUS software.The results show that the strength and stiffness of the device meet the practical working requirements.Thirdly,the modal analysis of the key components of the automatic dust removal protection device is carried out.The results show that there is no resonance between the natural frequency and the external excitation frequency,which is in line with the actual working requirements.Finally,the automatic dust removal protection device is tested.The test results show that the automatic dust removal protection device has better dust removal and cleaning effect than the existing dust removal device.(3)Aiming at the problem of high false positive rate of single-line laser longitudinal tear detection method,a mining conveyor belt longitudinal tear detection method based on multi-line laser was proposed.Firstly,an image enhancement algorithm combining piecewise linear transformation and CLAHE is proposed to improve the quality of the acquired image.Secondly,the image stitching algorithm based on SIFT feature extraction and weighted average fusion algorithm were used to obtain high quality and complete laser images of the lower surface lines of the conveyor belt.Thirdly,a multi-line laser center line extraction algorithm based on improved OTSU is proposed.Through experimental comparison,it is proved that the center line extracted by this algorithm can reflect the linear characteristics of laser line more accurately.Secondly,a morphological based feature extraction and detection algorithm for mining conveyor belt longitudinal tear is proposed,and the number of connected domains is used to judge whether the conveyor belt has longitudinal tear.Finally,the experimental platform for longitudinal tear detection of mine conveyor belt was built,and the experimental comparison and verification were carried out in the laboratory environment without dust fog and simulated dust fog.The experimental results show that the longitudinal tear detection method based on multi-line laser has higher accuracy and better environmental adaptability than that based on single-line laser.(4)The software platform of mine conveyor belt longitudinal tear detection system is designed and developed.On the basis of the longitudinal tear detection method based on multi-line laser,the system software is developed through the Visual Studio 2019 development platform combined with Halcon,Open CV visual development tools and My SQL database.The module functions of image processing algorithm,man-machine interaction,hierarchical alarm control,data storage and reading are realized.There are 78 figures,21 tables,and 80 references in the thesis.