Manhong Li

With the deep integration of informatization and industrialization, neural network technology has gradually penetrated into the field of mechanical design due to the characteristics of self-adaptive, self-organization and self-learning. Through the combination of mechanical design theory, the process of machinery and equipment design gradually tends to be intelligent and automated. First, from neural network technology and its construction of network models in mechanical equipment design, the solution to mechanical optimization design issues will be described in two models of the BP neural network and the Hopfield neural network. For the three main directions of machine tool body, typical components, and industrial robot design, this paper introduces the design and application of neural network technology in machine tool structure optimization and error compensation, gear transmission device and spindle, industrial robot structure and system. On this basis, the future development trend of the neural network technology in the field of mechanical equipment design is discussed, which provides theoretical support for the future intelligent mechanical equipment design.

In order to reduce the radiation dose of operators and the labor intensity of staff during the nuclear reactor operation, a remote operation nuclear multifunction robot was designed by service for salvage operation in the nuclear reactor pool. The purpose of this paper is making the robot to be a remote control tool to help staff in the nuclear reactor pool. Firstly, the kinematics analysis of the robot's six-wheeled mobile platform and four-degree-of-freedom manipulator are carried out. Then, based on the whole results of kinematics analysis, the overall mechanical structure of the robot is designed radiation-resistant and compact.

To investigate the influence of surface features, in the form of pits, on the wear resistance of grey cast iron (GCI), a finite element model of the pin‐on‐disc friction system, with pits distributed in a curved radial direction, was developed using APDL programming and the tribological behavior of textured surfaces was studied. The influence of relative rotation direction between the disc and the pin on the thermal behavior of the friction system under dry wear conditions was researched. GCI and C30E steel samples with pit textured surfaces were manufactured using laser marking equipment and tested using a tribology wear testing rig. The mass losses were measured and the worn surfaces were characterized. The influence of different rotation directions on the tribological behavior of the pit textured surfaces was also investigated. The simulation and test results revealed that rotation direction was a crucial parameter in determining the tribological behavior of surfaces with these features, regardless of the material. Under the conditions tested, when the pin rotated anticlockwise, the samples showed better friction and wear behavior than when the pin rotated clockwise. These results can provide important guidance for the optimization of the design of heavy‐load brake systems and other similar applications.