Artificial Intelligence Applications in Engineering (MUH-920), week 1 of 14: interactive lab
Prof. Dr. Utku Kose, Süleyman Demirel University
Part A compares four heating agents on the same winter week: a simple reflex agent, a model-based reflex agent with hysteresis, a proportional controller and a predictive agent that preheats before cold nights. Insulation, heater power, set point and dead band can be changed, and a scoreboard reports comfort error, energy and switching cycles, so that the trade-offs of the lecture become numbers [1, 2]. Part B asks for the environment properties of six engineering systems and explains each answer.
All agents see the same outdoor temperature profile. The room follows a first-order thermal model: Heat leaks to the outside with the insulation time constant and the heater adds heat when it is on.
Run each agent once. Every run is added to the table, so the agents can be compared under the same weather.
| Agent | Weather | Mean |error| (°C) | Energy (kWh) | Switching cycles |
|---|
For each system, choose the property that fits better. Feedback explains the engineering reason.
Six questions with instant feedback. Rate your confidence before checking each answer.
Answers are saved in this browser only. The export creates a Markdown learning log for your portfolio.
After the export, continue with the discipline challenge and the weekly task in the week overview.
[1] Russell, S., & Norvig, P. (2021). Artificial Intelligence: A Modern Approach (4th ed.). Pearson.
[2] Åström, K. J., & Murray, R. M. (2021). Feedback Systems: An Introduction for Scientists and Engineers (2nd ed.). Princeton University Press.