Exploring the Application of Large Language Models in Instrumentation and Control Engineering Education: A Questionnaire Survey and Examination Performance Analysis

Abstract

This study investigates the use of Large Language Models (LLMs) by undergraduates majoring in Instrumentation and Control Engineering (ICE) at University of Shanghai for Science and Technology. We conducted a questionnaire survey to assess the awareness and usage habits of these LLMs among ICE undergraduates in ICE courses, focusing on the model types, frequency, self-study tasks and post-usage feedback. The survey results indicate that ChatGPT is the most frequently used model among ICE undergraduates. Furthermore, we evaluated the performance of GPT-3.5 and GPT-4 on a set of 342 ICE questions sourced from the China MOOC platform. The results reveal significant performance differences between GPT-3.5 and GPT-4 across various ICE sub-disciplines and question types. GPT-4 shows particular proficiency in understanding control technology and system, achieving an accuracy of 82.16%, compared to 68.42% for GPT-3.5. Finally, we explore the factors influencing students use LLMs for ICE self-study and propose strategies for teachers to incorporate LLMs into ICE courses. This study highlights the potential of LLMs to enhance ICE education and provides concrete examples of their application in engineering coursework.