General Electric Company

Bethany Hoogs

Christina Ann LaComb

Jason Wayne Black

Ming Cheng Li

John Alan Interrante

Weiwei Chen

Deniz Senturk

Thomas R Kiehl

Yi Zhang

Deniz Senturk-Doganaksoy

Murat Doganaksoy

Radu Eugen Neagu

Systems and methods for performing data anomaly detection and/or removal are usable to accurately assess baseline power consumption. According to one embodiment of the invention, a system can be provided. The system can be operable to receive energy consumption data of a location; select, based at least in part on a collection period of the energy consumption data, an algorithm for detecting anomalies in the energy consumption data; perform the algorithm on the energy consumption data to detect the anomalies in the energy consumption data; and determine an energy consumption baseline for the location based at least in part on a result of the algorithm.

Systems and methods for data anomaly detection

A technique for detecting anomalous values in a small set of financial metrics makes use of context data that is determined based upon the characteristics of the target company being evaluated. Context data is selected to represent the historical values of the financial metric for the target company or the simultaneous performance of peer companies. Using the context data, an anomaly score for the financial metric is calculated representing the degree to which the value of the financial metric is an outlier among the context data. This can be done using an exceptional statistical technique. The anomaly score can be used to evaluate the risks associated with business transactions related to the target company.

Methods and systems for anomaly detection in small datasets

A method for predicting or detecting an event in turbomachinery includes the steps of obtaining operational data from at least one machine and at least one peer machine. The operational data comprises a plurality of performance metrics. A genetic algorithm (GA) analyzes the operational data, and generates a plurality of clauses, which are used to characterize the operational data. The clauses are evaluated as being either 'true' or 'false'. A fitness function identifies a fitness value for each of the clauses. A perturbation is applied to selected clauses to create additional clauses, which are then added to the clauses group. The steps of applying a fitness function, selecting a plurality of clauses, and applying a perturbation can be repeated until a predetermined fitness value is reached. The selected clauses are then applied to the operational data from the machine to detect or predict a past, present or future event.

Method and system for predicting turbomachinery failure events employing genetic algorithm

Growing community of inventors

Niskayuna, NY, United States of America

Bethany Hoogs