-
1.发明公开
公开(公告)号：EP1190278A1
公开(公告)日：2002-03-27
申请号：EP00911256.6
申请日：2000-03-09
发明人： ULYANOV, Serguei , RIZZOTTO, Gianguido , KURAWAKI, Ichiro , PANFILOV, Serguei , GHISI, Fabio , AMATO, Paolo , PORTO, Massimo
CPC分类号： B82Y10/00 , G05B13/0285 , G06N99/002 , Y10S706/903 , Y10S706/906
摘要： A method of controlling a process (Plant) driven by a control signal (U*) for producing a corresponding output comprises producing an error signal (ε) as a function of a state of the process (X) and of a reference signal (Y), generating a control signal (U*) as a function of the error signal (ε) and of a parameter adjustment signal (CGS) and feeding it to the process (Plant), deriving a signal (S) representative of a quantity to be minimized calculated by processing paired values of the state (X) of the process and the control signal (U*), calculating a correction signal (K2) from a set of several different values of the control signal (U*), that minimize the derived signal (S) to be minimized, calculating the parameter adjustment signal (CGS) by a neural network and fuzzy logic processor from the error signal (ε) and correction signal (K2). The method of the invention is characterized in that the correction signal (K2) is periodically calculated by a Quantum Genetic Search Algorithm consisting in a merging of a genetic algorithm and a quantum search algorithm. A hardware embodiment of the method of the invention has been disclosed.
-
2.发明授权
公开(公告)号：EP1190278B1
公开(公告)日：2006-10-18
申请号：EP00911256.6
申请日：2000-03-09
发明人： ULYANOV, Serguei , RIZZOTTO, Gianguido , KURAWAKI, Ichiro , PANFILOV, Serguei , GHISI, Fabio , AMATO, Paolo , PORTO, Massimo
CPC分类号： B82Y10/00 , G05B13/0285 , G06N99/002 , Y10S706/903 , Y10S706/906
摘要： A method of controlling a process (Plant) driven by a control signal (U*) for producing a corresponding output comprises producing an error signal (ε) as a function of a state of the process (X) and of a reference signal (Y), generating a control signal (U*) as a function of the error signal (ε) and of a parameter adjustment signal (CGS) and feeding it to the process (Plant), deriving a signal (S) representative of a quantity to be minimized calculated by processing paired values of the state (X) of the process and the control signal (U*), calculating a correction signal (K2) from a set of several different values of the control signal (U*), that minimize the derived signal (S) to be minimized, calculating the parameter adjustment signal (CGS) by a neural network and fuzzy logic processor from the error signal (ε) and correction signal (K2). The method of the invention is characterized in that the correction signal (K2) is periodically calculated by a Quantum Genetic Search Algorithm consisting in a merging of a genetic algorithm and a quantum search algorithm. A hardware embodiment of the method of the invention has been disclosed.
-
搜索结果
2 条记录 (耗时 0.013 秒)
