(LPNN) is employed to select the model parameters of fixed basis signals,and annealed linear programming neural network(ALPNN) is proposed to estimate the model parameters of parametric dependent basis signals.The utility of the neural network approach is illustrated by two simulation results which ...
Neural network modeling of torque estimation and d-q transformation for induction machine This paper presents a neural network approach in modeling of torque estimation and Parks 鈥 transformation for an open-loop induction machine. The nonlinea... KM Woodley,H Li,SY Foo - 《Engineering Application...
A Neural Network for Parameter Estimation of a DC Motor for Feed-Drives As the Artificial Neural Networks (ANNs) are able to model nonlinear process, they might be able to model a parameter estimator. We hope to estimate the physical parameters of feed-drives or spindles by a neural estimator...
The initial stage called input layer, is in essence an inlet for the flow of data into the network; the second stage is the hidden layer, which accepts input units and extrapolates the most relevant data bits based on weights; and the third stage is the output layer, where selected data...
Neural network Yes No Neural assembly/ensemble Yes Yes The neural network framework has been successfully applied to study cognitive operations, including motor control [6], motor learning [10], working memory [11–17], timing estimation [15,16,18,19], and decision-making [20,21]. The excit...
This paper presents a physics-informed neural network (PINN) approach for monitoring the health of diesel engines. The aim is to evaluate the engine dynamics, identify unknown parameters in a “mean value” model, and anticipate maintenance requirements. The PINN model is applied to diesel engines...
Structural pruning of neural network parameters reduces computational, energy, and memory transfer costs during inference. We propose a novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively removes those with smaller scores. We describe two variations of ...
There have been several works which used the embeddings created from neural network methods for link prediction. The evaluation metrics mentioned here are explained in the “Meaningful evaluation metrics” section. To the best of our knowledge, none of these works included time-sliced datasets. Grove...
Estimating the best set of weights for a neural network is a numeric minimization problem. Two common alternatives to using back-propagation are using a real-valued genetic algorithm (also called an evolutionary optimization algorithm), and using particle swarm optimization. Each es...
1850. The prediction of vibration and noise for the high-speed train based on neural network and boundary element method The vibration acceleration of the high-speed train is an important parameter reflecting the state of track irregularities and the quality of contact between wheel and rail. A ...