Exploration of Collaborative Optimization Strategy for Oxygen Production System and Interior Environment Control of Railway Locomotives

With the increasing requirements of passenger comfort, safety and energy efficiency in railway transportation, the existing in-car environment control and oxygen production systems still have problems such as response lag, low energy efficiency and poor robustness in terms of multi-objective coordination, dynamic response capability and energy consumption control. To this end, this paper introduces the fusion technology of artificial intelligence and the Internet of Things to construct a collaborative optimization strategy based on the Model Predictive Control (MPC) framework to improve the comprehensive performance of the locomotive oxygen production system and the in-car temperature, humidity and air quality control. Specific methods include: building a multi-source sensor network to achieve real-time perception and data fusion of multiple parameters such as oxygen concentration, CO₂ level, temperature and humidity, using AI models to predict environmental conditions, and achieving coordinated control of oxygen concentration, temperature and humidity, and ventilation intensity based on MPC optimization objective functions. The experimental results in typical operation scenarios show that, in contrast, under the PID control strategy, the changes in oxygen concentration and temperature are large and exceed the limit. For example, at 180 seconds, the oxygen concentration dropped to 20.5% and the temperature is 22.9°C, both exceeding the set safety range. This paper provides theoretical support and technical paths for the low-carbon and intelligent operation of the intelligent locomotive environmental system.