A new neural network application for non-linear state control is described. One neural network is modelled to form a Kalmann predictor and trained to act as an optimal state observer for a non-linear process. Another neural network is modelled to form a state controller and trained to produce a minimum variance controller for the non-linear process. After training, tuning possibilities for the ...

In this paper, we develop a mathematical model of sprinting in which anaerobicmetabolism is included. This model is simplified by considering the broad changes of energy leveland the cyclic variation associated with the strike pattern. We consider the effect of the centre of massto the overall energy balance along with force of resistance during initial motion of body. Results areobtained for t...

the morphological river evolution at long-time (centuries and even millennia) and large spatial scale (watersheds of several square kilometres) can be described by means of simplified 1d models, able to simulate the variation of bed elevation and grain size composition at non-detailed scales, involving a reduced computational effort. the erosion and deposition phenomena acting along rivers can ...

A hybrid neural network model based on-line re-optimization control strategy is developed for a batch polymerization reactor. To address the difficulties in batch polymerization reactor modeling, the hybrid neural network model contains a simplified mechanistic model covering material balance assuming perfect temperature control, and recurrent neural networks modeling the residuals of the simpl...

The on-line evaluation of the complete dynamic model in robot control is time-consuming and often dictates the use of simplified robot models in the controller. The impact of the simplifications on the controller performance cannot be easily quantified and experiments often contradict simulation results. The objective of this note is to demonstrate that numerically simplified models can violate...

Background: High-energy linear accelerator (linac) is a valuable tool and the most commonly device for external beam radiation treatments in cancer patients. In the linac head, high-energy photons with energies above the threshold of interaction produce photoneutrons. These photoneutrons deliver the extra dose to the patients in the planning treatment and increase the risk of secondary cancer.O...