3881 -- A Neural-Network-Based Identifier/Controller for Modern HVAC Control
Conference Proceeding published 1995 by ASHRAE
Written By So, A.T. P., Chan, W.L., Chow, T.T., Tse, W. L.
Conference Proceeding published 1995 by ASHRAE
Written By So, A.T. P., Chan, W.L., Chow, T.T., Tse, W. L.
Reports the application of an artificial neural network (ANN) to serve both as a system identifier and as an intelligent controller for an air-handling system. A comprehensive software model has been established based on the specifications of a standard air-handling unit (AHU) on the market. The model is appropriate for testing various control algorithms including the new ANN identifier/controller. The ANN behaves as an identifier by continuously keeping track of all real-time parameters associated with the whole air-handling system. Five actuating signals are produced based on the nonlinear error optimisation of the outputs of the ANN, now served as a controller. The control target involves the minimisation of two weighted factors - the errors between setpoints and control variables and the total energy consumption. The excellent performance of the ANN identifier/controller is illustrated by comparing it with that of a conventional proportional-integral-derivative (PID) controller.
KEYWORDS: year 1995, expert systems, building services, controls, automatic, comparing, programmable controllers, air handling units, testing, algorithms, performance
Citation: ASHRAE Trans. 1995, Vol.101, Part 2, Paper number 3881, 14-31, figs., tabs., refs.