Inductive Monitoring System Graphical User Interface (IMS GUI) for Processing, Analyzing, and Cleaning Datasets

摘要

The Inductive Monitoring System (IMS) software uses data mining techniques to automatically characterize nominal system operation by analyzing archived system data. These nominal characterizations are then used to perform near-realtime system health monitoring or analyze archived system data to detect anomalies in system behavior as compared with previous nominal behavior. To operate most effectively for system monitoring, the archived system data used to build the system models for IMS should contain only nominal operations data. Most available data sets contain contaminated data, data transients, or other data that does not represent nominal operations. Finding and removing these undesirable off-nominal data points manually is an error-prone and time-consuming task. Along with a variety of data extraction and program controls, the IMS graphical user interface (IMS GUI) allows the user to visually examine results of IMS monitoring analyses, and graphically select segments of data and outlier data points using a mouse or similar input device. The GUI will then automatically process the candidate dataset to remove undesired data points, leaving a clean dataset containing nominal data to use for building IMS system monitoring models.