Narrow Results

The impact localization in composite panels is assessed using two machine learning techniques: least square support vector machines (LSSVM) and artificial neural networks (ANN) with local strain signals from piezoelectric sensors. Sensor signals from impact experiments on a composite plate as well as signals simulated by a finite element model are used to train and test models. A comparative study shows that LSSVM achieves better accuracy than ANN on identifying location of impacts for a combination of large mass impact and small mass impact, in particular when less data is available for training which is more appropriate for real aeronautical application. Additionally, LSSVM is more capable of identifying new impact events which have not been considered in the training process.

Artificial Neural Networks (ANNs) are modelling tools having the ability to adapt to and learn complex topologies of inter-correlated multidimensional data. ANNs are inspired by biological neuron processing, have been widely used in different field of science and technology incorporating time series forecasting, pattern recognition and process control. ANN has been successfully used for forecasting of groundwater table and quality parameters like nitrate, total dissolved solids. In case of groundwater quality prediction, availability of good quality data of better precision is required. ANNs are classified as Feed-forward neural networks (FFNNs), Recurrent neural networks (RNNs), Elman Backpropagation Neural Networks, Input Delay feed-forward Backpropagation Neural Network, Hopfield Network. The artificial neural networks (ANNs) ability to extract significant information provides valuable framework for the representation of relationships present in the structure of the data. The evaluation of the output error after the retraining of an ANN shows us that this procedure can substantially improve the achieved results. Through this review work it is observed that in most hydrological modeling cases FFNN and LM algorithm performed well till today's published research work.