Deadline: 
11 October 2006
Institution: 
General Electric Global Research Center, Niskayuna, NY 12309, USA
Speaker: 
Piero Bonissone

We propose the use of local fuzzy models, which are related to kernel-based regressions, continuous Case-based reasoning, and locally weighted learning, to determine the remaining life of a unit in a fleet of vehicles. Instead of developing individual models (based on the track history of each unit) or developing a global model (based on the collective track history of the fleet), we look for clusters of peers, similar units with comparable utilization and performance. For each cluster of peer we create a local fuzzy model. We combine the fuzzy peer-based approach for performance modeling with an evolutionary framework for model maintenance. Our process generates a collection of competing models based on different feature subsets, evaluates their performance in light of currently available data, refines the best models using evolutionary search, and after a finite number of iterations, selects the best one. This process is repeated periodically to automatically produce updated and improved versions of the model. To illustrate this methodology we chose an asset selection problem: given a fleet of industrial vehicles (diesel electric locomotives), we want to select the best subset (of fixed or variable size) for mission-critical utilization. To this end, we predict the remaining life for each unit in the fleet. We then sort the fleet using this prediction and select the highest ranked units. The model chosen to perform this prediction/selection task is a fuzzy instance based model. A series of experiments using data from locomotive operations were conducted and the results from an initial validation exercise are presented. The approach of constructing local predictive models using fuzzy similarity with neighboring points along appropriate dimensions is not specific to any asset type and may be applied to any problem where the premise of historical similarity along chosen dimensions implies similarity in future behavior.