Predictive apparatus in a gas discharge light source
AssigneeCymer, Inc.
InventorMatthew Minakais
Life of this patent
Estimating the term…
Abstract
An apparatus includes a decision module that is configured to: receive a performance metric relating to performance conditions of an optical system emitting a light beam; estimate, based on the performance metric and a predetermined learning model, an effectiveness of a proposed change to the optical system; and output a change command to the optical system if it is estimated that the proposed change to the optical system would be effective.
Claims32
An apparatus comprising:
- a decision module in communication with an optical system and an interface module, comprising a predetermined learning model, and being configured to:
- receive, from the interface module, a performance metric relating to performance conditions of an optical system emitting a light beam;
- estimate, based on the performance metric and the predetermined learning model, an effectiveness of a proposed change to the optical system;
- and
- output a change command to the optical system if it is estimated that the proposed change to the optical system would be effective;
- wherein the predetermined learning model receives as an input the performance metric and outputs the estimate.
A method comprising:
- receiving a training dataset based on a plurality of test optical systems, the training dataset includes, for each of a plurality of changes of each test optical system:
- a plurality of values of performance conditions relating to the test optical system prior to the change;
- and
- a plurality of values of the performance conditions relating to the test optical system after the change;
- and
- generating, based on the training dataset, a prediction model that estimates an effectiveness of a proposed change in an optical system based on a performance metric relating to performance conditions of the optical system.
A method comprising:
- receiving a performance metric relating to performance conditions of an optical system emitting a light beam;
- estimating, based on the performance metric and a predetermined learning model, an effectiveness of a proposed change to the optical system, the estimating including determining whether the performance conditions of the light beam would be improved;
- and
- instructing a change to the optical system if it is estimated that the proposed change would be effective.
A non-transitory computer-readable medium storing instructions that, when executed by a computer, cause it to perform the following method comprising:
- receiving a training dataset based on a plurality of test optical systems, the training dataset includes, for each of a plurality of changes of each test optical system:
- a plurality of values of performance conditions relating to the test optical system prior to the change;
- and
- a plurality of values of the performance conditions relating to the test optical system after the change;
- and
- generating, based on the training dataset, a prediction model that estimates an effectiveness of a proposed change in an optical system based on a performance metric relating to performance conditions of the optical system.
A non-transitory computer-readable medium storing instructions that, when executed by a computer, cause it to perform the following method comprising:
- receiving a performance metric relating to performance conditions of an optical system emitting a light beam;
- estimating, based on the performance metric and a predetermined learning model, an effectiveness of a proposed change to the optical system;
- and
- instructing a change to the optical system if it is estimated that the proposed change would be effective;
- wherein the predetermined learning model receives as an input the performance metric and outputs the estimate.
An apparatus comprising:
- a decision module in communication with an optical system and an interface module, the decision module configured to:
- receive, from the interface module, a performance metric relating to performance conditions of an optical system emitting a light beam;
- estimate, based on the performance metric and a predetermined learning model, an effectiveness of a proposed refill of a gas mixture of the optical system;
- and
- output a refill command to the optical system if it is estimated that the proposed refill of the gas mixture of the optical system would be effective.
A method comprising:
- receiving a performance metric relating to performance conditions of an optical system emitting a light beam;
- estimating, based on the performance metric and a predetermined learning model, an effectiveness of a proposed gas refill of a gas mixture of the optical system;
- and
- instructing a gas refill to the optical system if it is estimated that the proposed gas refill would be effective.
An apparatus comprising:
- a decision module in communication with an optical system and an interface module, and being configured to:
- receive, from the interface module, a performance metric relating to performance conditions of an optical system emitting a light beam;
- estimate, based on the performance metric and a predetermined learning model, an effectiveness of a proposed change to the optical system indicating whether performance conditions of the optical system after the proposed change improve relative to the conditions of the optical system prior to the proposed change;
- and
- output a change command to the optical system if it is estimated that the proposed change to the optical system would be effective.
Dependencies are inferred from the claim text.