A novel approach to feature extraction, capable of generating a number of robust features in an automated way, is introduced. Although the proposed method focuses on features on the frequency domain for vibration data, it can be extended on different types of features. The method comprises of two simple models for the feature generation and a Particle Swarm Optimization system for establishing optimum or near optimum parameters for these models. The generated features are evaluated with a number of metrics, before they are used for diagnosis purposes.

Accurate and reliable fault diagnosis and prognosis of safety or mission critical components/ subsystems in complex engineering systems present major challenges to the Condition-Based Maintenance (CBM) or Prognostic and Health Management (PHM) designer. A crucial step in the development of CBM/PHM strategies relates to the designer’s ability to understand and model the incipient failure or fault modes and mechanisms. A single fault growth model might not be often capable to capture a sequence of fault behaviors.