3 research outputs found
METHODOLOGY FOR FLEET UNCERTAINTY REDUCTION WITH UNSUPERVISED LEARNING
No full textOperational and environmental variance can skew reliability metrics and increase uncertainty around lifetime estimates. For this reason, fleet-wide analysis is often too general for accurate predictions on heterogeneous populations. Also, modern sensor based reliability and maintainability field and test data provide a higher level of specialization and disaggregation to relevant integrity metrics (e.g., amount of damage, remaining useful life). Modern advances, like Dynamic Bayesian Networks, reduce uncertainty on a unit-by-unit basis to apply condition-based maintenance. This thesis presents a methodology for leveraging covariate information to identify sub- populations. This population segmentation based methodology reduces fleet uncertainty for more practical resource allocation and scheduled maintenance. First, the author proposes, validates, and demonstrates a clustering based methodology. Afterwards, the author proposes the application of the Student-T Mixture Model (SMM) within the methodology as a versatile tool for modeling fleets with unclear sub-population boundaries. SMM’s fully Bayesian formulation, which is approximated with Variational Bayes (VB), is motivated and discussed. The scope of this research includes a new modeling approach, a proposed algorithm, and example applications
Convolutional neural networks for automated damage recognition and damage type identification
No full textRecurring expenses associated with preventative maintenance and inspectionproduce operational inefficiencies and unnecessary spending. Human inspec-tors may submit inaccurate damage assessments and physically inaccessiblelocations, like underground mining structures, and pose additional logisticalchallenges. Automated systems and computer vision can significantly reducethese challenges and streamline preventative maintenance and inspection.The authors propose a convolutional neural network (CNN)‐based approachto identify the presence and type of structural damage. CNN is a deep feed‐for-ward artificial neural network that utilizes learnable convolutional filters toidentify distinguishing patterns present in images. CNN is invariant to imagescale, location, and noise, which makes it robust to classify damage of differentsizes or shapes. The proposed approach is validated with synthetic data of acomposite sandwich panel with debonding damage, and crack damage recogni-tion is demonstrated on real concrete bridge crack images. CNN outperformsseveral other machine learning algorithms in completing the same task. Theauthors conclude that CNN is an effective tool for the detection and typeidentification of damage
