Research on the Integration of Automation Technology Teaching Strategy and Intelligent Manufacturing Model Based on Differential Evolutionary Algorithm

This paper combines test paper quality indicators to construct a test paper assembly mathematical model and uses an improved differential evolution algorithm to solve the model. It generates an initial population through uniform search of the question bank and dynamically adjusts the mutation rate and crossover rate based on the fitness values of the population. Building on this, the paper adopts a backward design approach based on the OBE philosophy, focusing on three aspects—curriculum content, instructional organization, and instructional feedback—to construct an educational reform strategy and intelligent manufacturing-oriented teaching model that integrates automation technology, characterized by “two increases, two decreases, and one improvement.” Finally, the model was tested on students from a certain school, leading to the conclusion that among the experimental data on difficulty level score distributions of test papers generated by different algorithms, the algorithm proposed in this paper had the smallest distribution at the difficult level, with a minimum of 7.89, indicating that the paper's test paper generation strategy is more effective. Through empirical research, it was found that after applying the teaching model proposed in this paper, students in the experimental class achieved higher average scores on each question in the test compared to the control class. Additionally, as teaching progressed, students in the experimental class demonstrated a gradually superior trend in their mastery of computational concepts compared to students in the control class.