Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386013590> ?p ?o ?g. }
Showing items 1 to 54 of
54
with 100 items per page.
- W4386013590 abstract "The Deep Q_Network (DQN) algorithm in reinforcement learning is introduced to main engine fault diagnosis to improve the accuracy and efficiency of fault diagnosis by using the optimized DQN network algorithm to compensate for the lack of data imbalance for unbalanced fault data that are close to the real situation. The optimization of the DQN network algorithm is reflected in three aspects: firstly, the ɛ-greedy algorithm is optimized using the Upper Confidence Bound (UCB) algorithm, which makes the algorithm achieve a better balance between experience and exploratory in the selection of fault types; secondly, the fully connected network of the basic DQN is optimized using the triple-formed layer CNN network layer is optimized to improve the algorithm operation efficiency; meanwhile, the reward function for unbalanced data is set according to the balance rate, and the problem of reward value bias and local optimum for small amount of data is considered, so that the optimized DQN network algorithm gets improved accuracy in fault diagnosis of unbalanced data. Finally, the optimized DQN network, the base DQN network, the DCNN, and the ResNet18 are run for diagnosis on the unbalanced data set. Compared with other algorithmic networks, the optimized DQN improved 5.18%∼18.58% in accuracy. The results show that the DQN algorithm model can be applied with main engine unbalanced data fault diagnosis, and the improved DQN algorithm achieves good results in the efficiency and stability of diagnosis." @default.
- W4386013590 created "2023-08-21" @default.
- W4386013590 creator A5019550931 @default.
- W4386013590 creator A5023124128 @default.
- W4386013590 creator A5062722309 @default.
- W4386013590 date "2023-07-21" @default.
- W4386013590 modified "2023-09-27" @default.
- W4386013590 title "Study on the fault diagnosis method of ship main engine unbalanced data based on improved DQN" @default.
- W4386013590 cites W1966621789 @default.
- W4386013590 cites W3186409582 @default.
- W4386013590 doi "https://doi.org/10.1145/3611450.3611453" @default.
- W4386013590 hasPublicationYear "2023" @default.
- W4386013590 type Work @default.
- W4386013590 citedByCount "0" @default.
- W4386013590 crossrefType "proceedings-article" @default.
- W4386013590 hasAuthorship W4386013590A5019550931 @default.
- W4386013590 hasAuthorship W4386013590A5023124128 @default.
- W4386013590 hasAuthorship W4386013590A5062722309 @default.
- W4386013590 hasConcept C112972136 @default.
- W4386013590 hasConcept C11413529 @default.
- W4386013590 hasConcept C119857082 @default.
- W4386013590 hasConcept C127313418 @default.
- W4386013590 hasConcept C165205528 @default.
- W4386013590 hasConcept C175551986 @default.
- W4386013590 hasConcept C177264268 @default.
- W4386013590 hasConcept C199360897 @default.
- W4386013590 hasConcept C41008148 @default.
- W4386013590 hasConcept C51823790 @default.
- W4386013590 hasConceptScore W4386013590C112972136 @default.
- W4386013590 hasConceptScore W4386013590C11413529 @default.
- W4386013590 hasConceptScore W4386013590C119857082 @default.
- W4386013590 hasConceptScore W4386013590C127313418 @default.
- W4386013590 hasConceptScore W4386013590C165205528 @default.
- W4386013590 hasConceptScore W4386013590C175551986 @default.
- W4386013590 hasConceptScore W4386013590C177264268 @default.
- W4386013590 hasConceptScore W4386013590C199360897 @default.
- W4386013590 hasConceptScore W4386013590C41008148 @default.
- W4386013590 hasConceptScore W4386013590C51823790 @default.
- W4386013590 hasLocation W43860135901 @default.
- W4386013590 hasOpenAccess W4386013590 @default.
- W4386013590 hasPrimaryLocation W43860135901 @default.
- W4386013590 hasRelatedWork W2014379760 @default.
- W4386013590 hasRelatedWork W2082153276 @default.
- W4386013590 hasRelatedWork W2104055432 @default.
- W4386013590 hasRelatedWork W2293063927 @default.
- W4386013590 hasRelatedWork W2313526331 @default.
- W4386013590 hasRelatedWork W2353460016 @default.
- W4386013590 hasRelatedWork W2355215981 @default.
- W4386013590 hasRelatedWork W2386767533 @default.
- W4386013590 hasRelatedWork W2787412873 @default.
- W4386013590 hasRelatedWork W2953093056 @default.
- W4386013590 isParatext "false" @default.
- W4386013590 isRetracted "false" @default.
- W4386013590 workType "article" @default.