Applied Materials, Inc.

Harikrishnan Rajagopal

Sima Didari

Tianqing Liao

John C Forster

Heng Hao

Arvind Shankar Raman

Methods and systems for rating a current substrate support assembly based on impedance circuit electron flow are provided. Data associated with an amount of radio frequency (RF) power flowed through an electrical component of a current substrate support assembly during a current testing process performed for the current substrate support assembly is provided as input to a trained machine learning model. One or more outputs of the trained machine learning model are obtained. A measurement value for an electron flow across an impedance circuit of the current substrate support assembly is extracted from the one or more outputs. In response to a determination that the extracted measurement value for the electron flow satisfies an electron flow criterion, a first quality rating is assigned to the current substrate support assembly.

Rating substrate support assemblies based on impedance circuit electron flow using machine learning

Methods, systems, and non-transitory computer readable medium are provided for long short-term memory (LSTM) anomaly detection for multi-sensor equipment monitoring. A method includes training a LSTM recurrent neural network (RNN) model for semiconductor processing fault detection. The training includes generating training data for the LSTM RNN model and providing the training data to train the LSTM RNN model on first training input and first target output to generate a trained LSTM RNN model for the semiconductor processing fault detection. The training data includes the first training input and the first target output based on normal runs of manufacturing processes of semiconductor processing equipment. Another method includes providing input based on runs of manufacturing processes of semiconductor processing equipment to a trained LSTM RNN model; obtaining one or more outputs from the trained LSTM RNN model; and using the one or more outputs for semiconductor processing fault detection.

Long short-term memory anomaly detection for multi-sensor equipment monitoring

A method includes determining, based on sensor data, that one or more components of substrate processing equipment are within a pre-failure window that is after a normal operation window. Corresponding data points in the normal operation window are substantially stable along a first health index value. The corresponding data points in the pre-failure window increase from the first health index value to a peak at a second health index value. Responsive to the determining that the one or more components are within the pre-failure window, the method further includes causing performance of a corrective action associated with the one or more components of the substrate processing equipment.

Correcting component failures in ion implant semiconductor manufacturing tool

Methods, systems, and non-transitory computer readable medium are provided for correcting component failures in ion implant semiconductor manufacturing tool. A method includes receiving, from sensors associated with an ion implant tool, current sensor data corresponding to features; performing feature analysis to generate additional features for the current sensor data; providing the additional features as input to a trained machine learning model; obtaining one or more outputs from the trained machine learning model, where the one or more outputs are indicative of a level of confidence of a predicted window; predicting, based on the level of confidence of the predicted window, whether one or more components of the ion implant tool are within a pre-failure window; and responsive to predicting that the one or more components are within the pre-failure window, performing a corrective action associated with the ion implant tool.

A server trains a neural network by feeding a first set of input time-series data of one or more sensors of a first processing chamber that is within specification to the neural network to produce a corresponding first set of output time-series data. The server calculates a first error. The server feeds a second set of input time-series data from corresponding one or more sensors associated with a second processing chamber under test to the trained neural network to produce a corresponding second set of output time-series data. The server calculates a second error. Responsive to the difference between a second error between the second set of input time-series data and the corresponding second set of output time-series data and a first error between the first set of input time-series data and the corresponding first set of output time-series data being equal to or exceeding a threshold amount, the server declares that the second processing chamber under test mismatches the first processing chamber that is within specifications.

Growing community of inventors

Santa Clara, CA, United States of America

Harikrishnan Rajagopal