Intelligent Computer-Aided Instruction Modeling and a Method to Optimize Study Strategies for Parallel Robot Instruction

Parallel robots are known for their strong bearing capability and high kinematic accuracy, but they are relatively difficult to design and to teach. This paper addresses this difficulty by presenting an intelligent computer-aided instruction (ICAI) modeling method for parallel robot instruction. The paper analyzes, with reference to their incoming educational profile, Mechatronics students' cognitive processes while acquiring knowledge of parallel robots; it also compares the educational benefits of various methods of teaching this topic. The ICAI model for teaching parallel robots is rooted in machine learning, using information fusion methods based on an artificial neural network (ANN). Two terms of using the ICAI model have validated the method's effectiveness in teaching parallel robots, providing a rational study strategy and improving the students' learning process.

I. Introduction

Industrial robots have applications in many areas, such as manufacturing, monitoring, and transporting. Parallel robots are new generation robots that have the advantages of perfect structural stiffness, strong bearing capability, and high kinematic accuracy [1]. Research on parallel robots can be divided into two categories. The first of these is parallel mechanism analysis, which includes mechanism, dynamics, and path planning. Due to the high complexity of parallel robots, most researchers concentrate on the mechanism design and optimization. The other category is parallel mechanism synthesis, where innovative work relies on the designers' experience and inspiration. As a result, mechanism synthesis has become the hotspot of parallel robot research [2], with many scholars working to find a mechanism synthesis method with universal significance.