http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
공조 AUTO 사용성 개선을 위한 운전자 맞춤형 학습 제어기 개발
이정훈(Jeonghoon Lee),신기영(Kiyoung Shin),김중재(Joongjae Kim),권동호(Dongho Kwon),이성제(Sungje Lee),황동우(Dongwoo Hwang) 한국자동차공학회 2018 한국자동차공학회 학술대회 및 전시회 Vol.2018 No.11
An ‘auto’ mode on conventional FATC system provides climate control automatically based on the map which is preset. The values preset on the map are setting temperature, ambient temperature, in-car temperature, sun-road, evaporator temperature, coolant temperature, and etc. Those various values are regarded as inputs to calculate Td; thermal index. Calculated Td determines output values for discharging air temperature, Mode selection, AC on/off, blower steps, or compressor capacity to control internal cabin climate environment. The output values; however, does not always guarantee to satisfy every passengers’ climate comfort in cabin. Therefore, customized or passenger climate preference reflection on FATC are needed to provide better climate comfort to passenger in cabin area. To reflect a user climate preference into FATC, machine learning algorithm has been incorporated into FATC logic. Its machine learning algorithm is based on frequency of climate operation setting and lasting time. It is suitable for vehicle climate control because of no need for high performance CPU and heavy memory compared with deep learning and others. This is demonstrated in a bench test and vehicle experiments.