Search

A visual recognition method for appearance defects of mine hoist steel wire ropes based on computer vision and deep learning is proposed to address the problems of difficult deployment for detecting multiple steel wire ropes, low image acquisition quality of steel wire ropes, poor adaptability and accuracy of visual detection methods. Firstly, an online monitoring system for the steel wire rope of the mine hoist is constructed. Secondly, the steel wire rope images are collected by the ground mobile inspection platform and the underground intrinsic safety high-speed camera, and a steel wire rope image dataset is established. Considering the effects of underground dust, susceptibility of camera lenses to contamination, uneven lighting, and high light reflection of steel wire ropes, image denoising methods based on Retinex algorithm and homomorphic filtering are used to denoise the steel wire rope images. The processing results show that the automated multi-scale Retinex with color restoration (AutoMSRCR) algorithm based on color gain weighting is the optimal solution. The defect detection process is based on convolutional neural networks, and a defect detection model based on YOLOv5s is constructed. In order to reduce the influence of human factors and the workload of parameter tuning, a Focus structure is added to YOLOv5s for optimization. The improved YOLOv5s model is used as a pre training model for steel wire rope defect detection to further reduce the memory usage of the model and improve the loading and detection speed of the model. The experimental results show that the proposed method has detection errors of 1.61% and 1.35% for wire breakage at 2 positions of the steel wire rope, and detection errors of 2.43%, 3.44%, 2.11%, and 3.39% for wear at 4 positions of the steel wire rope. In response to the problem that the detection precision of the original steel wire rope safety monitoring system for the main shaft hoist of Gubei Coal Mine, Huaihe Energy Holding Group, cannot meet the on-site requirements, the proposed method is adopted to improve the original system. The on-site application results show that the accuracy of wire rope breakage detection is increased from 80% to 96%, the damage positioning error is reduced from 500 mm to within 300 mm. The damage positioning accuracy is increased from 75% to 98%, the real-time detection rate of damage is increased from 76% to 90%, and the tail rope distortion detection rate is increased from 70% to 85%.

The machining accuracy of cycloidal tooth surface is the key factor affecting the motion performance of RV reducer,and the reverse correction of grinding parameters according to the data of tooth surface error detection is an important link in the manufacturing process of the cycloidal gear. Through the analysis of the cycloidal gear generating grinding principle,the complex motion relationship between the grinding wheel and the cycloidal gear is clarified and the model of the movement relation of the cycloidal tooth surface is established.Besides,based on the gear meshing theory and the principle of space coordinate conversion,the mathematical expression of the cycloidal gear theoretical tooth surface and the normal vector with the parameters of the grinding adjustment are deduced,which provides a theoretical basis for correcting the tooth profile error after testing.Then according to the cycloidal generating grinding model,the influence of main grinding parameters on the tooth surface error is discussed. Finally,a comparison is made with the cycloidal tooth profile obtained by generation principle,which proves that the equation and its establishment method is correct. It can not only provide the necessary theoretical data for the machining error detection of the cycloidal gear,but also have important significance for the correction of the grinding parameters and the accuracy improvement of the cycloidal tooth surface.

The meshing backlash of cycloidal-pin wheel drive in RV reducer is the key factor that affects the transmission performance. At present,the formula method is adopted mainly to calculate the initial meshing backlash of cycloidal-pin wheel. But there are some differences between the theoretical result and the actual value because the formula method did not consider the change of node position in the process of drive. Taking the distance between the profiles in the direction of the common normal as the accurate meshing backlash is proposed. The traditional initial meshing backlash calculation method is analyzed and the tooth contact model of cycloidal-pin wheel is established,then the accurate meshing backlash at any angle is obtained. A theoretical basis for calculating and analyzing the exact meshing backlash of cycloidal-pin wheel drive in RV reducer is provided.

Aiming at the tooth surface error measurement results distortion of straight bevel gear which consisted of the of modification error and machining error based on gear measuring center,a method which is proposed to obtain the theoretical coordinates for tooth surface measurement based on the solid modeling.According to the design of the gear structure,the origin of the coordinate system and datum plane can be determined by installation distance,then the rotating projection line model can be established based on the calculated mesh nodes coordinates,a series of points are converted to the tooth surface,combined with UG Open programming technology,the attribute analysis of the points on the tooth surface can be extracted,then the coordinates and unit vector of the tooth surface measurement points can be obtained,which provides a new way for the acquisition of the tooth surface error measurement based on gear measuring center.

A new measuring method setting the node as single tooth reference point for manufacturing error of cycloid wheel is proposed. The theoretical model and error measurement model of the cycloid wheel drive are established. The measurement path is planned,and measurement driver software is developed. By using the meshing principle of the pin-swing drive and the measuring theory of the complex surface,the manufacturing error of the cycloidal wheel is obtained. The tooth profile and pitch deviation of the fact cycloidal profile are measured on the domestic gear measuring center. The measurement results under different reference points are compared and the correctness of the new method is verified.