International Business Machines Corporation

Fateh A Tipu

Robert J Baseman

Sholom M Weiss

Ehud Aharoni

Oded Margalit

Noam Slonim

Tomasz J Nowicki

Adam D Ticknor

Raminderpal Singh

Hong Lin

Michal Rosen-Zvi

Ramona Kei

Timothy M McCormack

Kevin MacKey

Ramachandran Muralidhar

Amit Dhurandhar

Edwin Peter Dawson Pednault

Naoki Abe

Dzung Tien Phan

Nam H Nguyen

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

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

A system, method and/or computer program product for analyzing a functionality of at least two manufactured products obtain a first characteristic of a first manufactured product. The system acquires a second characteristic of a second manufactured product. The system identifies a common feature between the first characteristic and the second characteristic. The system identifies a distinguishable feature between the first characteristic and the second characteristic. The system determines a cause of a deviation of a functionality in the first manufactured product or the second manufactured product or both manufactured products based on the identified common feature or the identified distinguishable feature or both features.

Enhancing investigation of variability by inclusion of similar objects with known differences to the original ones

A system, a method and a computer program product for identifying incompatible manufacturing tools. The system receives measurements of products that were subject to a manufacturing process involving a plurality of manufacturing tools. The measurements pertain to a performance characteristic of each product. The system evaluates whether each manufacturing tool implemented in a sequential manufacturing process individually performs normally based on the received measurements. In response to evaluating each manufacturing tool implemented in said manufacturing process individually performs normally, the system evaluates whether a first combination of the manufacturing tools together in sequential manufacturing process perform normally based on the received measurements. The system further evaluates performance of products generated by all other combinations of tools in the sequential manufacturing process not including the first combination of tools, and, using objective measures, identifies a combination of tools that perform optimally.

Detecting combined tool incompatibilities and defects in semiconductor manufacturing

A method, a system and a computer program product suitable for use in a manufacturing environment comprising a multiplicity of nominally identical independent tools. A computing device generates a multi dimensional array of process trace data derived from at least one of the independent tools, wherein, the array includes data representing a first dimension comprising a list of steps in a manufacturing recipe and data representing a second dimension comprising a list of a set of sensors generating measurements from at least one of the independent tools. The computing device conducts an analysis on at least one preselected subset of the multi dimensional array for the purpose of evaluating at least one operating characteristic of at least one of the independent tools. The computing device presents results of the analysis via a set of hierarchically linked and browseable graphics.

Method and system for evaluating a machine tool operating characteristics

The present invention includes a computing system determining a best alias rule in a semiconductor manufacturing process. The computing system obtains an original rule and candidate alias rules based on sampled data from the semiconductor manufacturing process. The computing system compares the original rule to the candidate alias rules. The computing system ranks the candidate alias rules according to the comparison. The computing system filters the ranked candidate alias rules. A user selects one rule among the filtered candidate alias rules based on knowledge of the semiconductor manufacturing process.

Rule-based root cause and alias analysis for semiconductor manufacturing

A method and system for evaluating a performance of a semiconductor manufacturing tool while manufacturing microelectronic devices are disclosed. At least one report is generated based on executions of at least one statistical test. The report includes at least one heat map having rows that correspond to sensors, columns that correspond to trace data obtained during recipe steps, and cells at the intersection of the rows and the columns. At least one sensor in the tool obtains trace data of a recipe step while manufacturing at least one microelectronic device. A computing device analyzes the obtained trace data to determine a level of operational significance found in the data and assigns a score to the trace data that indicates a level of operational significance. Then, the computing device places the score in a corresponding cell of the heat map. A user uses the cell for evaluating the tool performance.

A fabrication history a group of wafers is provided, having a record for each wafer of the manufacturing events that did or did not occur in its fabrication, and having the measured value of a given target. A binary decision rule is formed based on the fabrication history, the rule being that if a wafer has a particular pattern of manufacturing events in its fabrication history then the statistic of the given fabrication target for that wafer is a first value; otherwise, the statistic is a second value having at least a given distance from the first value. The pattern of manufacturing events in the binary decision rule is identified in the generation of the binary decision rule. The identified pattern is significant with respect to the given target.

System and method for rule-based data mining and problem detection for semiconductor fabrication

Feature importance information available in a predictive model with correlation information among the variables is presented to facilitate more flexible choices of actions by business managers. The displayed feature importance information combines feature importance information available in a predictive model with correlational information among the variables. The displayed feature importance information may be presented as a network structure among the variables as a graph, and regression coefficients of the variables indicated on the corresponding nodes in the graph. To generate the display, a regression engine is called on a set of training data that outputs importance measures for the explanatory variables for predicting the target variable. A graphical model structural learning module is called that outputs a graph on the explanatory variables of the above regression problem representing the correlational structure among them. The feature importance measure, output by the regression engine, is displayed for each node in the graph, as an attribute, such as color, size, texture, etc, of that node in the graph output by the graphical model structural learning module.

Method and apparatus for presenting feature importance in predictive modeling

A fabrication history of a group of wafers is provided, having a record for each wafer of the manufacturing events that did or did not occur in its fabrication, and having the measured value of a given target. A binary decision rule is formed based on the fabrication history, the rule being that if a wafer has a particular pattern of manufacturing events in its fabrication history then the statistic of the given fabrication target for that wafer is a first value; otherwise, the statistic is a second value having at least a given distance from the first value. The pattern of manufacturing events in the binary decision rule is identified in the generation of the binary decision rule. The identified pattern is significant with respect to the given target.

Growing community of inventors

Wappingers Fall, NY, United States of America

Fateh A Tipu