Industrial Steam Turbine Generator Predictive Maintenance Based on Measurement Availability

Large steam turbine generators’ reliable operation is very important due to catastrophic consequences for factory safety and power grid availability in case of unexpected faults. Complexity of the large system and its synergistic nature with production provide a large number of highly nonlinear measurements from integrated monitoring systems. This creates a big data volume with difficulty in storage and real-time processing, resulting in loss of information or general amplitude threshold monitoring. In this work, journal bearing imbalance fault is investigated using the installed sensor data of a large steam turbine as received by the thermal power plant monitoring system. Based on a short review of relevant literature state-of-the-art, a vanilla Long Short-Term Memory Recurrent Neural Network as a time-series predictor is proposed to mitigate trips during start-up and investigate correlation between measurements and bearing remaining useful life.

I. Introduction

Large steam turbine (ST) synchronous generators (SGs) are essential in grid power generation. Reliable operation, durability, minimal shutdown, and a long-term lifespan, are essential for the flexibility demands of the modern energy market. This flexibility stems from an increased number and reduced time of start-ups, with numerous load changes and from varying thermal conditions. These operations also comprise the biggest thermomechanical stress source for large STs [1], which is also evident in the real data presented in this work. Therefore, real-time predictive monitoring is essential for minimization of costs related to maintenance, operation, and market fines of not meeting demands. Combination of the thermomechanical and electromechanical aspects of ST SGs results in mechanically interlinked fault mechanisms. Vibration monitoring is the premier industrial and literature approach, providing concise results with minimal cost due to the sensor nature [2]. This work investigates increased vibrations and displacement delaying start-up, using shaft and bearing displacement and vibration measurements, prominent in ST condition monitoring applications.