The accurate identification of the real-time thermal state of personnel working indoors has been the focus of researchers. In this study, a detailed examination of the entire process of developing a personal comfort model, from theory to practice, is conducted. In particular, the subject of this investigation is a smart air conditioner capable of predicting thermal sensation based on an infrared (IR) sensor that measures the skin temperature of personnel and then implements automatic control. Random forest algorithm was employed to establish a thermal sensation prediction model, which accepts skin and air temperatures as input parameters. The model achieves a high prediction accuracy value of 0.84. Given the measurement errors of low-cost IR sensors, a simulated temperature measurement experiment based on the manikin was conducted, and an error calibration method based on multiple linear regression was developed through the experiment. 30 subjects participated in another prototype test experiment, which proved that the air conditioner can accomplish effective automatic control based on the prediction of thermal sensation, avoid the occurrence of extreme temperatures, and ensure the thermal comfort of personnel. The possible causes of remaining problems and potential improvement schemes are discussed in detail.
Read full abstract