Semiconductor run-to-run control system with missing and out-of-order measurement handling

A method for controlling a manufacturing process, includes:

• processing using a process input and producing a process output;
• storing the process input in a database;
• storing at least one measurement of the process output in the database associated with each process input;
• iterating over data from the database to estimate a process state;
• if one or more measurements is missing from the database, replacing the missing measurements for the database based on a prediction from a model;
• and
• updating said model with said processing state estimate, wherein if actual measurements become available a time period after process state estimation, for said one or more measurements which was missing, replacing the predicted measurements with said actual measurements, storing said actual measurements in said database, and utilizing said actual measurements in subsequent process state estimation.

A control system includes:

• a controller capable of providing a process input;
• a process coupled to the controller to receive the process input and provide a process output;
• a database configured to receive the process input and a measurement of the process output, the database capable of associating each process input and each process output;
• a model capable of providing a model output;
• and
• a state estimator coupled to receive the database output and the model output, the state estimator coupled to the controller and capable of generating process state estimates, and configured to provide an updated model to said controller based on said process state estimates.

An apparatus includes:

• means for processing using a process input and producing a process output;
• means for storing the process input in a database, the means for storing including providing a timestamp;
• means for storing at least one measurement of the process output in the database aligned with each process input using the timestamp;
• means for iterating over the data from the database to estimate a process state;
• means for replacing measurements missing from the database based on a prediction from a model;
• and
• means for updating said model with said process state estimate.

A method for controlling a manufacturing process, includes:

• processing using a process input and producing a process output;
• storing the process input in a database;
• storing at least one measurement of the process output in the database associated with each process input;
• iterating over data from the database to estimate a process state, wherein a constrained quadratic optimization is solved at each iteration of data;
• if one or more measurements is missing from the database, replacing the missing measurements for the database based on a prediction from a model;
• and
• updating said model with said process state estimate.

A method for controlling a manufacturing process, includes:

• processing using a process input and producing a process output;
• storing the process input in a database;
• storing at least one measurement of the process output in the database associated with each process input;
• iterating over data from the database to estimate a process state, wherein a constrained quadratic optimization is solved at each iteration of data;
• if one or more measurements is missing from the database, replacing the missing measurements for the database based on a prediction from a model;
• and
• updating said model with said process state estimate wherein if actual measurements become available a time period after process state estimation, for said one or more measurements which was missing, replacing the predicted measurements with said actual measurements, storing said actual measurements in said database, and utilizing said actual measurements in subsequent process state estimation.

A method for controlling a manufacturing process, includes:

• providing a database with process input data and associated process output data;
• iterating over data from the database to estimate a process state;
• if one or more measurements is missing from the database, replacing the missing measurements for the database based on a prediction from a model;
• and
• updating said model with said process state estimate.

A method for controlling a manufacturing process, includes:

• providing a database with process input data and associated process output data;
• iterating over data from the database to estimate a process state;
• if one or more measurements is missing from the database, replacing the missing measurements for the database based on a prediction from a model;
• and
• updating said model with said process state estimate, wherein if actual measurements become available a time period after process state estimation, for said one or more measurements which was missing, replacing the predicted measurements with said actual measurements, storing said actual measurements in said database, and utilizing said actual measurements in subsequent process state estimation.