The paper proposes a power-split hybrid electric vehicle control strategy that combines a rule-based controller, including a state-of-charge controller and engine start–stop logic, with a precisely formulated equivalent consumption minimization strategy. A one-dimensional directional search-based instantaneous equivalent consumption minimization strategy optimization and a two-dimensional directional search-based instantaneous equivalent consumption minimization strategy optimization are used to find optimal powertrain points in high-efficiency engine map regions that are previously determined by an offline optimization approach. The simulation results confirm that the rule-based controller performance can be significantly improved when extended with the proposed equivalent consumption minimization strategy formulation, without requiring an adaptive empirical penalty factor to satisfy the state-of-charge sustainability condition. The proposed rule-based + equivalent consumption minimization strategy control strategies were verified against a dynamic-programming-based optimization benchmark for different certification driving cycles.
Fault diagnosis is considered as an essential task in rotary machinery as possibility of an early detection and diagnosis of the faulty condition can save both time and money. This work presents developed and novel technique for deep-learning-based data-driven fault diagnosis for rotary machinery. The proposed technique input raw three axes accelerometer signal as high definition 1D image into deep learning layers which automatically extract signal features, enabling high classification accuracy. Unlike the researches carried out by other researchers, accelerometer data matrix with dimensions 6400 × 1 × 3 is used as input for convolutional neural network training. Since convolutional neural networks can recognize patterns across input matrix, it is expected that wide input matrix containing vibration data should yield good classification performance. Using convolutional neural networks (CNN) trained model, classification in one of the four classes can be performed. Additionally, number of kernels of CNN is optimized using grid search, as preliminary studies show that alternating number of kernels impacts classification results. This study accomplished the effective classification of different rotary machinery states using convolutional artificial neural network for classification of raw three axis accelerometer signal input.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.