International Business Machines Corporation

Globalfoundries Inc.

Robert J Baseman

Fateh A Tipu

Yada Zhu

Sholom M Weiss

Jingrui He

Tomasz J Nowicki

Jian Wang

Jie Ma

Ramachandran Muralidhar

Young Min Lee

Jayant R Kalagnanam

Guan Zhang

Nam H Nguyen

Michal Rosen-Zvi

Christopher Vincent Jahnes

Ehud Aharoni

Oded Margalit

Emmanuel Yashchin

Noam Slonim

Dung Tien Phan

Amit Dhurandhar

Elham Khabiri

Adam D Ticknor

Raminderpal Singh

Hong Lin

Chandrasekhara K Reddy

William Grey

Ramona Kei

Timothy M McCormack

Kevin MacKey

Fateh Ali Tipu

Srideepika Jayaraman

Benjamin N Eldridge

Igor Y Khandros

Arthur R Zingher

Anuradha Bhamidipaty

Charles Allan Brown

Herman Russell Wendt

Thomas Robert Ervolina

Kaan Kudsi Katircioglu

Dzung Tien Phan

James T Yeh

William A Muth

Brian F White

Michael A Russak

Laura Beth Rothman

Joseph C Andreshak

Frederick A Scholl

Seyyed M Mirzamaani

Susan G Conti

A method for process control using predictive long short term memory includes obtaining historical post-process measurements taken on prior products of the manufacturing process; obtaining historical in-process measurements taken on prior workpieces during the manufacturing process; training a neural network to predict each of the historical post-process measurements, in response to the corresponding historical in-process measurements and preceding historical post-process measurements; obtaining present in-process measurements on a present workpiece during the manufacturing process; predicting a future post-process measurement for the present workpiece, by providing the present in-process measurements and the historical post-process measurements as inputs to the neural network; and adjusting at least one controllable variable of the manufacturing process in response to the prediction of the future post-process measurement.

Tool control using multistage LSTM for predicting on-wafer measurements

A computing device includes a processor and a storage device. A vehicle asset modeling module is stored in the storage device and is executed by the processor to configure the computing device to perform acts of identifying and clustering a plurality of assets based on static properties of a vehicle asset using a first module of the vehicle asset modeling module. The clustered plurality of assets is determined based on dynamic properties of the vehicle asset using a second module. Event prediction is performed by converting a numeric data of the clustered plurality of assets to a natural language processing (NLP) domain by a third module. One or more sequence-to-sequence methods are performed to predict a malfunction of a component of the vehicle asset and/or an event based on past patterns. Prediction information is stored in the storage device.

Vehicle asset modeling using language processing methods

A method of improving at least one of quality and yield of a physical process comprises: obtaining values, from respective performances of the physical process, for a plurality of variables associated with the physical process; determining at least one Gaussian mixture model (GMM) representing the values for the variables for the performances of the physical process; based at least in part on the at least one GMM, computing at least one anomaly score for at least one of the variables for at least one of the performances of the physical process; based on the at least one anomaly score, identifying the at least one of the performances of the physical process as an outlier; and, based at least in part on the outlier identification, modifying the at least one of the variables for one or more subsequent performances of the physical process.

Model management for non-stationary systems

A computing device includes a processor and a storage device. A wafer asset modeling module is stored in the storage device and is executed by the processor to configure the computing device to perform acts identifying and clustering a plurality of assets based on static properties of a wafer asset using a first module of the wafer asset modeling module. The clustered plurality of assets is determined based on dynamic properties of the wafer asset using a second module of the wafer asset modeling module. Event prediction is performed by converting a numeric data of the clustered plurality of assets to a natural language processing (NLP) domain by a third module of the wafer asset modeling module. One or more sequence-to-sequence methods are performed to predict a malfunction of a component of the wafer asset and/or an event based on past patterns. Prediction information is stored in the storage device.

Wafer asset modeling using language processing methods

Anomaly detection and remedial recommendation techniques for improving the quality and yield of microelectronic products are provided. In one aspect, a method for quality and yield improvement via anomaly detection includes: collecting time series sensor data during individual steps of a semiconductor manufacturing process; calculating anomaly scores for each of the individual steps using a predictive model; and implementing changes to the semiconductor manufacturing process based on the anomaly scores. A system for quality and yield improvement via anomaly detection is also provided.

Anomaly detection and remedial recommendation

Controlling product production in multi-stage manufacturing process automatically generates by machine learning causal relationships between the processing conditions and the product quality based on product genealogy data and product quality data. Real time sensor data from sensors coupled to processing units in a manufacturing facility implementing the multi-stage manufacturing process are received, and control rules are instantiated based on the real time sensor data. An instantiated control rule firing causes an actuator to automatically set a processing variable to a set point specified in the control rule.

Controlling multi-stage manufacturing process based on internet of things (IOT) sensors and cognitive rule induction

Controlling multi-stage manufacturing process based on internet of things (IoT) sensors and cognitive rule induction

A method, a computer program product, and a computer system for identifying significant and consumable-insensitive trace features. A computer computes a residual in a first regression of one or more secondary factors on a target. The computer computes residuals in a second regression of the one or more secondary factors on each of one or more trace features in one or more trace feature sets. The computer computes, for the one or more trace feature sets, coefficients of determination in a third regression of the residuals in the second regression on the residual in the first regression. The computer ranks the one or more trace feature sets by sorting the coefficient of determination. The computer determines, based on rankings of the one or more trace feature sets, significant trace feature sets.

System and method for identifying significant and consumable-insensitive trace features

The present invention generally relates to the monitoring and controlling of a semiconductor manufacturing environment and, more particularly, to methods and systems for virtual meteorology (VM) applications based on data from multiple tools having heterogeneous relatedness. The methods and systems leverage the natural relationship of the multiple tools and take advantage of the relationship embedded in process variables to improve the prediction performance of the VM predictive wafer quality modeling. The prediction results of the methods and systems can be used as a substitute for or in conjunction with actual metrology samples in order to monitor and control a semiconductor manufacturing environment, and thus reduce delays and costs associated with obtaining actual physical measurements.

System for wafer quality predictive modeling based on multi-source information with heterogeneous relatedness

An apparatus for performing run-to-run control and sampling optimization in a semiconductor manufacturing process includes at least one control module. The control module is operative: to determine a process output and corresponding metrology error associated with an actual metrology for a current processing run in the semiconductor manufacturing process; to determine a predicted process output and corresponding prediction error associated with a virtual metrology for the current processing run; and to control at least one parameter corresponding to a subsequent processing run as a function of the metrology error and the prediction error.

Run-to-run control utilizing virtual metrology in semiconductor manufacturing

A method for run-to-run control and sampling optimization in a semiconductor manufacturing process includes the steps of: determining a process output and corresponding metrology error associated with an actual metrology for a current processing run in the semiconductor manufacturing process; determining a predicted process output and corresponding prediction error associated with a virtual metrology for the current processing run; and controlling at least one parameter corresponding to a subsequent processing run as a function of the metrology error and the prediction error.

Method and system for wafer quality predictive modeling based on multi-source information with heterogeneous relatedness

A system, method and computer program product for predicting at least one feature of at least one product being manufactured. The system receives, from at least one sensor installed in equipment performing one or more manufacturing process steps, at least one measurement of the feature of the product being manufactured. The system selects one or more of the received measurement of the feature of the product. The system estimates additional measurements of the feature of the product at a current manufacturing process step. The system creates a computational model for predicting future measurements of the feature of the product, based on the selected measurement and the estimated additional measurements. The system predicts the future measurements of the feature of the product based on the created computational model. The system outputs the predicted future measurements of the feature of the product.

Continuous prediction of expected chip performance throughout the production lifecycle

A method for performing enhanced wafer quality prediction in a semiconductor manufacturing process includes the steps of: obtaining data including at least one of tensor format wafer processing conditions, historical wafer quality measurements and prior knowledge relating to at least one of the semiconductor manufacturing process and wafer quality; building a hierarchical prediction model including at least the tensor format wafer processing conditions; and predicting wafer quality for a newly fabricated wafer based at least on the hierarchical prediction model and corresponding tensor format wafer processing conditions.

Method and apparatus for hierarchical wafer quality predictive modeling

Growing community of inventors

Brewster, NY, United States of America

Robert J Baseman