Self-Tuning Routine Alarm Analysis of Vibration Signals in Steam Turbine Generators

Abstract

This version is available at https://strathprints.strath.ac.uk/41099/ Strathprints is designed to allow users to access the research output of the University of Strathclyde. Unless otherwise explicitly stated on the manuscript, Copyright © and Moral Rights for the papers on this site are retained by the individual authors and/or other copyright owners. Please check the manuscript for details of any other licences that may have been applied. You may not engage in further distribution of the material for any profitmaking activities or any commercial gain. You may freely distribute both the url (https://strathprints.strath.ac.uk/) and the content of this paper for research or private study, educational, or not-for-profit purposes without prior permission or charge.Any correspondence concerning this service should be sent to the Strathprints administrator: strathprints@strath.ac.ukThe Strathprints institutional repository (https://strathprints.strath.ac.uk) is a digital archive of University of Strathclyde research outputs. It has been developed to disseminate open access research outputs, expose data about those outputs, and enable the management and persistent access to Strathclyde's intellectual output. Abstract-This paper presents a self-tuning framework for the diagnosis of routine alarms in steam turbine generators utilizing a combination of inductive machine learning and knowledge-based heuristics. The techniques provide a novel basis for initializing and updating time series feature extraction parameters used in the automated decision support of vibration events due to operational transients. The data-driven nature of the algorithms allows for machine-specific characteristics of individual turbines to be learned and reasoned about. The paper provides a case study illustrating the routine alarm paradigm, and the applicability of systems using self-tuning techniques. The approaches discussed throughout are presented to provide useful diagnosis tools for the reliability and maintenance analysis of steam turbine generators.

Symbolic Representation of Knowledge for the Development of Industrial Fault Detection Systems

“…Splitting up the time series data into various timesteps, or segments, based on the information provided by the expert, each data stream/channel timestep is assigned a symbol which is either rising, falling, fluctuating or stable. The assigning of the symbols is performed using a technique based on Signal to Symbol transformation [8] which has been successfully used for rotating plant in the nuclear industry previously [3]. For this application, the symbols are assessed by first calculating the average of the first and last 10% of the timestep, a comparison is then performed to determine which of the following four categories best describes the timestep.…”

Semi-Automated Knowledge Capture and Representation for the Development of Knowledge Based Systems

“…2. The first step in the approach is to perform signal to symbol transformation (SST) [12] on the raw timeseries data for each datastream. This segments the data into discrete time intervals, each time interval is then assigned a symbol based on several calculations.…”

Improved Explicability for Pump Diagnostics in Nuclear Power Plants

“…Due to the individual rules being based on trends in the data it is necessary to have a pre-processing stage to calculate these trends. The approach adopted for this application was to use a signal-to-symbol transformation approach [1]. Splitting up the trace into various timesteps based on the information provided by the expert, each timestep is assigned a symbol which is either rising, falling, fluctuating or stable.…”