Novelty Detection under Changing Environmental Conditions

The primary objective of novelty detection is to examine a system’s dynamic response to determine if the system significantly deviates from an initial baseline condition. In reality, the system is often subject to changing environmental and operation conditions that affect its dynamic characteristics. Such variations include changes in loading, boundary conditions, temperature, and moisture. Most damage diagnosis techniques, however, generally neglect the effects of these changing ambient conditions. Here, a novelty detection technique is developed explicitly taking into account these natural variations of the system in order to minimize false positive indications of true system changes. Auto-associative neural networks are employed to discriminate system changes of interest such as structural deterioration and damage from the natural variations of the system.