For access to this article, please select a purchase option:
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Your recommendation has been sent to your librarian.
Diesel generator is complex and often operated in extreme environments. Faults are inevitable and the fault mechanism is not quite clear yet. What's worse is the lack of sufficient fault data accumulated, which brings big challenges to data-driven fault diagnosis methods. This paper adopts the transfer learning and deep learning methods for fault diagnosis of diesel generator. The source fault data were collected from a 35 kW diesel generator simulation system. The target is a 70 kW diesel generator with sparse fault data. Through the transfer learning of fault knowledge and the use of a deep belief networks for pre-training and reverse fine-tuning, an accurate fault diagnosis neural network is obtained for the new diesel generator. Simulation results can show the feasibility and effectiveness of the proposed deep transfer learning based fault diagnosis method for diesel generators.
Inspec keywords: power engineering computing; convolutional neural nets; deep learning (artificial intelligence); diesel-electric generators; learning (artificial intelligence); power system faults
Subjects: Neural nets; Power engineering computing; Diesel power stations and plants