RESUMEN
This paper presents a generic framework for fault prognosis using autoencoder-based deep learning methods. The proposed approach relies upon a semi-supervised extrapolation of autoencoder reconstruction errors, which can deal with the unbalanced proportion between faulty and non-faulty data in an industrial context to improve systems' safety and reliability. In contrast to supervised methods, the approach requires less manual data labeling and can find previously unknown patterns in data. The technique focuses on detecting and isolating possible measurement divergences and tracking their growth to signalize a fault's occurrence while individually evaluating each monitored variable to provide fault detection and prognosis. Additionally, the paper also provides an appropriate set of metrics to measure the accuracy of the models, which is a common disadvantage of unsupervised methods due to the lack of predefined answers during training. Computational results using the Commercial Modular Aero Propulsion System Simulation (CMAPSS) monitoring data show the effectiveness of the proposed framework.
Asunto(s)
Benchmarking , Redes Neurales de la Computación , Reproducibilidad de los Resultados , Pronóstico , Simulación por ComputadorRESUMEN
The prediction of partial discharges in hydrogenerators depends on data collected by sensors and prediction models based on artificial intelligence. However, forecasting models are trained with a set of historical data that is not automatically updated due to the high cost to collect sensors' data and insufficient real-time data analysis. This article proposes a method to update the forecasting model, aiming to improve its accuracy. The method is based on a distributed data platform with the lambda architecture, which combines real-time and batch processing techniques. The results show that the proposed system enables real-time updates to be made to the forecasting model, allowing partial discharge forecasts to be improved with each update with increasing accuracy.
