CONTROL METHOD, CONTROL UNIT, LITHOGRAPHY DEVICE, AND ARTICLE PRODUCING METHOD

To provide an advantageous technology for improving control accuracy, when controlling a control target using a neural network.SOLUTION: A control method for controlling a control target using a first signal generated by a first compensator based on a control deviation of the control target and a se...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	ASAKURA YASUNOBU, KUSAYANAGI HIROKAZU, HATA TOMOYASU, HASHIMOTO TAKUMI
Format:	Patent
Sprache:	eng ; jpn
Schlagworte:	APPARATUS SPECIALLY ADAPTED THEREFOR CALCULATING CINEMATOGRAPHY COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING CONTROL OR REGULATING SYSTEMS IN GENERAL CONTROLLING COUNTING ELECTROGRAPHY FUNCTIONAL ELEMENTS OF SUCH SYSTEMS HOLOGRAPHY MATERIALS THEREFOR MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS ORIGINALS THEREFOR PHOTOGRAPHY PHOTOMECHANICAL PRODUCTION OF TEXTURED OR PATTERNED SURFACES,e.g. FOR PRINTING, FOR PROCESSING OF SEMICONDUCTORDEVICES PHYSICS REGULATING
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	To provide an advantageous technology for improving control accuracy, when controlling a control target using a neural network.SOLUTION: A control method for controlling a control target using a first signal generated by a first compensator based on a control deviation of the control target and a second signal generated by a second compensator by a neural network based on the control deviation comprises: a first control step of controlling the control target based on a target value of a first sequence; a second control step of controlling the control target based on a target value of a second sequence while applying a pseudo disturbance to the control target; and a determining step of determining parameter values of the neural network by learning based on the second index obtained in the second control step.SELECTED DRAWING: Figure 4 【課題】ニューラルネットワークを用いた制御対象の制御において、制御精度を向上させるために有利な技術を提供する。【解決手段】制御対象の制御偏差に基づいて第１補償器で発生された第１信号と、当該制御偏差に基づいてニューラルネットワークにより第２補償器で発生された第２信号とにより前記制御対象を制御する制御方法は、第１シーケンスの目標値に基づいて前記制御対象を制御する第１制御工程と、擬似的な外乱を前記制御対象に与えながら、第２シーケンスの目標値に基づいて前記制御対象を制御する第２制御工程と、前記第２制御工程で得られた第２指標に基づいて学習することにより前記ニューラルネットワークのパラメータ値を決定する決定工程と、を含む。【選択図】図４