Double DQN method for object detection

Zuo, Guoyu; Du, Tao; Lu, Jiahao

doi:10.1109/cac.2017.8243989

Cited by 14 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For a specific power transformer, we should consider the different conditions and adapt the weights more inclined to predict the main fault of that one. For this reason, we employ the idea of experience replay, which is used in the reinforcement learning model DQN [29].…”

Section: Experience Replaymentioning

confidence: 99%

Fault Diagnosis for Power Transformers through Semi-Supervised Transfer Learning

Mao

Wei

et al. 2022

Sensors

View full text Add to dashboard Cite

The fault diagnosis of power transformers is a challenging problem. The massive multisource fault is heterogeneous, the type of fault is undetermined sometimes, and one device has only met a few kinds of faults in the past. We propose a fault diagnosis method based on deep neural networks and a semi-supervised transfer learning framework called adaptive reinforcement (AR) to solve the above limitations. The innovation of this framework consists of its enhancement of the consistency regularization algorithm. The experiments were conducted on real-world 110 kV power transformers’ three-phase fault grounding currents of the iron cores from various devices with four types of faults: Phases A, B, C and ABC to ground. We trained the model on the source domain and then transferred the model to the target domain, which included the unbalanced and undefined fault datasets. The results show that our proposed model reaches over 95% accuracy in classifying the type of fault and outperforms other popular networks. Our AR framework fits target devices’ fault data with fewer dozen epochs than other novel semi-supervised techniques. Combining the deep neural network and the AR framework helps diagnose the power transformers, which lack diagnosis knowledge, with much less training time and reliable accuracy.

show abstract

Section: Experience Replaymentioning

confidence: 99%

Fault Diagnosis for Power Transformers through Semi-Supervised Transfer Learning

Mao

Wei

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The DoubleDQN is an extension of the DQN where the Q-value estimation and action selection is decoupled by using separate neural networks to solve the inherent problem of overestimating Qvalues. In essence, the DoubleDQN improves the stability and convergence rate of the RL agent, as presented by [70,277].…”

Section: Training Algorithmsmentioning

confidence: 99%