Metallic cylinders are widely used in various fields of industrial production, and the automatic detection of surface microcracks is of great significance to the subsequent grinding process. In this paper, laser-excited surface acoustic waves (SAW) are used to detect surface microcracks. Due to the dispersion of SAWs on the cylinder surface, the SAWs exhibit different polarities at different positions. In order to improve the consistency of signals and the accuracy of the modeling, the angle at which the polarity is completely reversed is selected as the detection point. A laser ultrasonic automatic detection system is established to obtain signals, and the B-scan image is drawn to determine the location of the microcrack. By comparing the time–frequency diagrams of the reflected SAWs and transmitted SAWs, the transmitted wave is chosen to establish the microcrack depth prediction model. In addition, according to the trajectory of the grinding wheel, a prediction model based on the absolute depth of the microcracks is established, and the influence of the orientation of the microcracks on the signal energy is considered. The method proposed in this paper can provide a reference for the rapid grinding of microcracks on the surface of metallic cylinders; it has the characteristics of visualization and high efficiency, and overcomes the shortcomings of the currently used eddy current testing that provides information on the depth of microcracks with difficulty.

Aiming at the robotization of the grinding process in the steel bar finishing process, the steel bar grinding robot can achieve the goal of fast, efficient, and accurate online grinding operation, a multi-layer forward propagating deep neural network (DNN) method is proposed to efficiently predict the kinematic solution of grinding robot. The process and kinematics model of the grinding robot are introduced. Based on the proposed method, simulations of the end position and orientation, and joint angle of the grinding robot are given. Three different methods, including SGD + tanh, Nadam + tanh, Nadam + ELU, are used to test the DNN calculation process results show that the method combining Nadam with ELU function has the fastest solution speed and higher accuracy can be obtained with the increase in iteration times. Finally, the Nadam optimizer is used to optimize the calculation results of the example. The optimization results show that this method accelerates the convergence rate of trajectory prediction error and improves the accuracy of trajectory prediction. Thus, the proposed method in this paper is an effective method to predict the kinematic solution when the grinding robot works online.

In order to solve coupled fractional differential-integral equations more effectively and to deal with the problem that the huge algebraic equations lead to considerable computational complexity and large data storage requirements in the calculation process, this paper approximates the function of the unknown solution based on the Chebyshev wavelet of the second kind and then combines the collocation method to solve the numerical solution of nonlinear fractional Fredholm integral-differential equations. By using the proposed method, the original problem can be reduced to a system of linear algebraic equations, which can be easily solved by some mathematical techniques. In addition, the convergence analysis of the system based on the second kind of Chebyshev wavelet is studied. Several numerical test problems are presented, and the absolute error values under different fractional orders are given, which proves the superiority and effectiveness of the proposed method. It provides support for improving the precision and reliability of the system.

An end face attitude detection system for special steel bars is designed to solve the problem of defect localization for steel bar grinding. A circle detection method based on improved Density-Based Spatial Clustering of Applications with Noise (DBSCAN) is proposed for calculating special steel bars’ end face attitude. Firstly, the images are subjected to edge detection, connected region marking, and improved DBSCAN in accordance with the image characteristics. After that, the arcs belonging to the same circle are clustered into the same category to create virtual connected regions. Then, circle parameters of a virtual connected region are clustered using an improved DBSCAN algorithm. The actual circle parameter is obtained by calculating the centroid of each category. Finally, the vector is generated under the set coordinate system, passing through the center of the circumcircle of the steel bar end and one endpoint of the two-dimensional code, and the angle of the vector is calculated to determine the attitude of the special steel bar’s end face. The experimental results demonstrate that the method can obtain an attitude angle resolution of 0.2 degrees with an error range of ±0.1 degrees. This will provide accurate defect localization support for the digitization and intelligence of the grinding platform on the special steel bar production line.