Expert system for the analysis of building energy consumption

Thesis/Dissertation · Wed Jan 01 04:00:00 EST 1986

OSTI ID:5224373

Haberl, J S

A significant portion of unnecessary energy consumption in a building can often be attributed to specific operational events, especially in large institutional buildings with complex energy consuming subsystems. Once identified, these events can be tracked automatically with regression techniques and an expert system on a desk top microcomputer using information and observations from daily on-site visits. A prototype methodology, using these techniques, was able to reduce energy consumption for a pilot building by 15%. The pilot building for the application of the methodology is the University of Colorado Recreation Center. The methodology uses multivariate linearized regression, and the expert system was developed with an available proprietary expert-system shell. The expert system contains a previously assembled knowledge base which represents the expertise of on-site maintenance personnel, as well as that of the author gained over the six years the building has been under study. The methodology developed, the Building Energy Analysis CONsultant (BEACON) system, has two main components, an energy consumption predictor, and an expert system that analyzes abnormal consumption according to predefined IF-THEN rules.

• Research Organization: Colorado Univ., Boulder (USA)
• OSTI ID: 5224373
• Country of Publication: United States
• Language: English

Related Subjects

29 ENERGY PLANNING, POLICY, AND ECONOMY
290100 -- Energy Planning & Policy-- Energy Analysis & Modeling
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION
320100* -- Energy Conservation
Consumption
& Utilization-- Buildings
99 GENERAL AND MISCELLANEOUS
990220 -- Computers
Computerized Models
& Computer Programs-- (1987-1989)
BUILDINGS
ENERGY ANALYSIS
ENERGY CONSUMPTION
ENERGY MANAGEMENT
EXPERT SYSTEMS
MANAGEMENT
MATHEMATICS
REGRESSION ANALYSIS
STATISTICS