Process for the monitoring and diagnostics of data from a remote asset
AssigneeGeneral Electric Company
InventorsAidan Thomas Cardella, Evelyn Varner
Life of this patent
Estimating the term…
Abstract
A method for processing monitored data from a remote asset to optimize maintenance and operation schedules, the method comprising the steps of collecting data from the remote asset, building a data set based on the data collected, applying statistical scripts to the data set to create a statistical model, comparing the statistical model to the data set, creating a standardization model from the compared statistical model and the data set, applying a trending algorithm to the data, deriving statistical based control limits, and applying the control limits to a new set of collected data.
Claims23
A method for processing monitored data from a remote asset to optimize maintenance and operation schedules, the method comprising:
- collecting data from the remote asset;
- building a data set based on the data collected;
- applying statistical scripts to the data set to create a statistical model;
- comparing the statistical model to the data set;
- creating a standardization model from the compared statistical model and the data set;
- applying a trending algorithm to the data;
- deriving statistical based control limits;
- applying the control limits to a new set of collected data;
- trending information using a time series modeling optimization technique for determining the remote asset's maintenance and operation schedules;
- developing optimized maintenance and operation schedules based on the trended information;
- reporting the schedules to a user.
A system for processing monitored data from a remote asset to evaluate and determine a status of the remote asset with minimum user interface, the system comprising:
- a remote asset;
- a data gathering module located at the remote asset to collect data about the remote asset;
- a monitoring and diagnostic service center;
- respective network interfaces located at the remote asset and the monitoring and diagnostic service center;
- a processor to manage sending, evaluating, and receiving the data;
- a process residing in the processor which uses algorithms to build a data set based on the data gathered uses statistical scripts on the data to determine a statistical model, and uses a time series modeling optimization technique to trend information to determine the remote asset's maintenance and operation schedules.
A method for processing monitored data from a remote asset to determine whether the data is within a predetermined operating threshold, the method comprising:
- collecting monitored data from the remote asset;
- providing a processor;
- supplying the monitored data to the processor;creating an anomaly definition which comprises acceptable parameters;
- identifying a first variable;
- identifying a second set of variables which are used to monitor the first variable;
- deleting data that is outside of a specified parameter;
- centering data about a specified variable;
- running a stepwise regression algorithm;
- determining whether data is within acceptable parameters;
- un-centering data if data are within acceptable parameters;
- running the stepwise regression algorithm on the un-centered data;
- calculating residuals based on a calculated first variable compared to a predicted first variable;
- building a standardized variable based on calculated residuals;
- assessing data before and after standardization to determine whether results are within a predetermined limit;
- trending the data to determine whether the assessed data is within the predetermined operating threshold;
- developing optimized maintenance and operation schedules based on the trended data;
- reporting the schedules to a user.
Dependencies are inferred from the claim text.