Abstract

 
 
 Every day large amounts of process data are recorded in a variety of industries. For nuclear power plants, these data are stored within the Plant Computer (PC). As parts begin to degrade and components fail, maintenance personnel are responsible for making repairs and recording these repairs in a Computerized Maintenance Management System (CMMS). By coupling the information in the PC and CMMS, failure data can be extracted and repurposed for lifecycle prognostic models. Existing prognostic methods can be utilized to develop lifecycle models and predict the Remaining Useful Life (RUL). These efforts are currently done manually and require substantial amounts of time to develop. This results in offline predictions, which can drastically reduce response time for preventative maintenance. This paper outlines an early concept that uses data mining based on Big Data efforts in order to couple the plant computer data with the CMMS so that prognostic information can be gathered, sorted, and analyzed automatically. The extracted failure data can be used to autonomously update or build prognostic models based on component failure times, stressor information, and signal/residual values. An effective future implementation of this concept means that the results could be used as a priori prognostic information in lifecycle prognostic models, and the updating and/or development of such models can be automated for improved response time.
 
 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have