Artificial neural network-based adaptive fluid temperature regulation of extravehicular activity suit

Abstract The extravehicular activity (EVA) suit is an important component of the life-support system for astronauts working outside of a space craft. In view of the problem that the EVA suit's thermal control system cannot be reliably operated by the astronaut during extravehicular activity, scientists are working to develop a thermal comfort prediction model based on existing physiological monitoring indicators. This model could be used as the basis for an automated thermal control system for EVA suits. For this experiment, we collected physiological data (i.e. heart rate, respiration frequency, oxygen consumption and CO2 expiratory volume) from 10 male subjects (ages 24–40) as they performed various working tasks. Subjects performed tasks wearing a simulated liquid cooling suit under 12 working conditions. We developed and applied a BP neural network prediction model to examine the relationship between thermal comfort, metabolic rate and cooling based on the human body's heat balance equation. The correlation between heart rate (HR) and metabolic rate was 0.71 ​± ​0.53, while that of respiration frequency and metabolic rate was 0.90 ​± ​0.05, that of partial CO2 pressure and metabolic rate was 0.51 ​± ​0.25, and that of skin temperature and metabolic rate was 0.30 ​± ​0.27. The BP neural network model was 91% accurate in predicting the metabolic rate, and the astronaut thermal comfort model was 89% accurate. The thermal comfort prediction model, developed based on the human body heat balance equation, provides a rapid and simple quantitative judgement of the thermal comfort status of the EVA suit microenvironment. In addition, the BP neural network model, constructed based on heart rate, respiration frequency and CO2 expiratory volume, allows for dynamic predictions of the body's metabolic rate.