Showing papers by "Adrian Olaru published in 2011"
TL;DR: The paper open the way to the assisted choose of the optimal neural network by using the proper virtual LabVIEW instrumentation to establish some influences of the network parameters to the number of iterations till canceled the mean square error to the target.
Abstract: The paper open the way to the assisted choose of the optimal neural network. There are shown some important neurons type, transfer functions, weights and biases of neurons, and some complex layers with different type of neurons in a static and dynamic networks. By using the proper virtual LabVIEW instrumentation were established some influences of the network parameters to the number of iterations till canceled the mean square error to the target. Were presented the simulation of some different neural network types like linear, sigmoid, sigmoid bipolar and radial. For some of more important, were presented the complex mathematical models and numerical simulation using the proper teaching law.
14 citations
TL;DR: In this paper, assisted experimental research by data acquisition were established the influences of some different dampers to the dynamic behavior and was proposed one proper smart damper system with magnetorheological damper (MRD), proper neural network with some time delays and recurrent links and soft control with acquisition board.
Abstract: The paper showed the assisted research of some new dynamic behavior parameters and his influences to the dynamic behavior of the industrial robots. The research contents the mathematical model of these new dynamic parameters, assisted theoretical simulation of the new mathematical model after applies the rheological damper and the assisted establish of the influences of the model coefficients to the characteristics parameters. In the assisted experimental research by data acquisition were established the influences of some different dampers to the dynamic behavior and was proposed one proper smart damper system with magnetorheological damper (MRD), proper neural network with some time delays and recurrent links and soft control with acquisition board. By applying this new research was possible developing the new matrix -vector form of the torsor force- moment and the research of the global dynamic damper behavior and the global dynamic compliance of the industrial robot with proper smart damper system.
1 citations