"Pou\u017Eit\u00ED neuronov\u00FDch s\u00EDt\u00ED v adaptivn\u00EDm \u0159\u00EDzen\u00ED p\u0159i kr\u00E1tk\u00E9 period\u011B vzorkov\u00E1n\u00ED"@cs . "Pou\u017Eit\u00ED neuronov\u00FDch s\u00EDt\u00ED v adaptivn\u00EDm \u0159\u00EDzen\u00ED p\u0159i kr\u00E1tk\u00E9 period\u011B vzorkov\u00E1n\u00ED"@cs . . "WSEAS" . . "217-222" . "26220" . "O\u0161mera, Pavel" . "6"^^ . "\u0158ecko" . "2007-07-23+02:00"^^ . "Using of Neural Network Based Identification for Short Sampling Period in Adaptive Control" . "Using of Neural Network Based Identification for Short Sampling Period in Adaptive Control"@en . . "Using of Neural Network Based Identification for Short Sampling Period in Adaptive Control"@en . "Pivo\u0148ka, Petr" . "Veleba, V\u00E1clav" . "[F9DF93ADA84F]" . . . . "RIV/00216305:26220/07:PU69904" . "Using of Neural Network Based Identification for Short Sampling Period in Adaptive Control" . "Nov\u00FD p\u0159\u00EDstup pro identifikaci dynamick\u00FDch syst\u00E9m\u016F s neuronov\u00FDmi s\u00EDt\u011Bmi dovoluje pou\u017Eit\u00ED kr\u00E1tk\u00E9 periody vzorkov\u00E1n\u00ED."@cs . "P(GA102/06/1132), Z(MSM0021630503)" . . . . "457028" . "978-960-8457-90-4" . . . . . . "Systems Theory and Applications" . "Crete, Greece" . "3"^^ . . "The new approach to analysis of on-line identification methods based on one-step-ahead prediction clears up their sensitivity to disturbances in control loop and explain why should be neural network based identification better then classical by using of short sampling period. The use of short sampling period in adaptive control has not been described properly when controlling the real process by adaptive controller. On one hand faster disturbance rejection due to short sampling period can be an advantage but on the other hand it brings us some practical problems. Particularly, quantization error and finite numerical precision of industrial controller must be considered in the real process control. We concentrate our attention on dealing with adverse effects that work on real-time identification of process, especially quantization. It is shown; that a neural network applied to on-line identification process produces more stable solution in the rapid sampling." . . . . "The new approach to analysis of on-line identification methods based on one-step-ahead prediction clears up their sensitivity to disturbances in control loop and explain why should be neural network based identification better then classical by using of short sampling period. The use of short sampling period in adaptive control has not been described properly when controlling the real process by adaptive controller. On one hand faster disturbance rejection due to short sampling period can be an advantage but on the other hand it brings us some practical problems. Particularly, quantization error and finite numerical precision of industrial controller must be considered in the real process control. We concentrate our attention on dealing with adverse effects that work on real-time identification of process, especially quantization. It is shown; that a neural network applied to on-line identification process produces more stable solution in the rapid sampling."@en . . "3"^^ . "RIV/00216305:26220/07:PU69904!RIV08-GA0-26220___" . "Rapid sampling domain, Neural networks for identification, Comparison of identifications methods"@en . .