Efficiency analysis of mechanical reducer equipment of material handling industry using Sunflower Optimization Algorithm and Material Generation Algorithm

The mechanical reducer gear has the advantages of good meshing performance, strong bearing capacity and smooth transmission, which has been widely used in the mechanical transmission system. But the traditional design cycle of mechanical reducer gear parameters is long, especially the gear calibration analysis, the calculation process is cumbersome and labor intensity is high, which leads to the incomplete interface of mechanical reducer gear model. In order to improve the analysis accuracy, a lot of correction work is needed. Therefore, based on particle swarm optimization algorithm for mechanical reducer gear parametric modeling research. Based on SolidWorks 3D software, the parametric development of spur gear, modified helical gear, bevel gear, internal gear, tooth root transition curve and helix is carried out. The finite element contact theory is introduced to calculate the contact problem of two cylinders, and compared with the classical Hertz theory, the correctness of the theory is verified. On this basis, the influence of friction on the contact stress and meshing strength of gears is obtained by setting different sliding friction coefficients, and compared with the theoretical calculation results, the correctness of the finite element analysis is verified.

Parametric modeling of mechanical reducer gear based on particle swarm optimization

In order to better improve the effect of mechanical motion trajectory tracking control and ensure the quality and safety of mechanical operation, a mechanical motion trajectory tracking control method based on convolution neural network is proposed. In the process of mechanical motion trajectory tracking control, due to the influence of small disturbance piecewise linear error, the mechanical system will produce multivariable nonlinear motion phenomenon in the operation process. Boundary layer tracking error is easy to occur. In order to solve the above problem, the convolution neural network is used to optimize the mechanical trajectory tracking control algorithm, and the simulation model of mechanical motion environment is established. The spatial coordinates of the trajectory are abstracted as the virtual world of genetic population, and the spatial grid structure characteristics are obtained. According to the matching conditions and parameters of convolution neural network, an error tracking integral term is designed and improved. By accurately tracking the mechanical trajectory, the accuracy of path planning and autonomous positioning is effectively improved. The experimental results show that the control method based on convolution neural network has the advantages of fast convergence speed, high accuracy and high calculation accuracy.

Research on trajectory tracking control of mechanical motion based on convolution neural network

For the problem of Direction-Of-Arrival (DOA) Estimation using sensor arrays, we present a DOA estimation algorithm, called Joint-Sparse DOA. Firstly, DOA estimation is cast as the joint-sparse recovery problem. Then, norm is approximated by arctan function to express joint sparsity and DOA estimation can be obtained by minimizing approximate norm. Finally, the minimization problem is solved by quasi-Newton method to estimate DOA. Simulation results show that our algorithm has some advantages over most existing methods: it needs a small number of snapshots to estimate DOA, while the number of sources need not be known a priori. Besides, it improves the probability of resolution, and it can also handle the correlated sources well.

Gengle Zheng

Papers

Parametric modeling of mechanical reducer gear based on particle swarm optimization

Research on trajectory tracking control of mechanical motion based on convolution neural network

Direction-Of-Arrival Estimation Based On Joint Sparse Recovery