Paper Conference
Proceedings of SimBuild Conference 2012: 5th conference of IBPSA USA
![]() ![]() ![]() ![]() |
Efficient and Robust Training Methodology for Inverse Building Modeling
Jie Cai, James E. BraunRay W. Herrick Laboratory, Purdue University, USAbstract: This paper expands on a previous approach for inverse
building modeling that utilizes a simplified state-space
approach. The goal of the current effort is to provide an
efficient and robust parameter training methodology, to
which several elements are added. Some seasonal
effects, such as variation of window transmittance at
different times of the year, are taken into consideration
and captured during the training process. In addition, a
mixed-mode training approach is developed that allows
the use of a combination of data obtained when cooling
or heating is occurring with the zone temperature under
control at setpoint and when the zone temperature is
floating during periods of no load. Different search
algorithms were tested for learning a “nearly” global
optimal model. A multi-start search method was found
to be robust and provide good computational efficiency
and accurate results. At the end of this paper, this
training methodology is implemented for a single zone
case study and some results are provided. Pages: 456 - 461 Paper:simbuild2012_07b_3_Cai