Applied Materials, Inc.

Roger Alan Lindley

Keiji Horioka

Bryan Y Pu

Vijay D Parkhe

Daniel John Hoffman

Jingbao Liu

Kenneth S Collins

Andrew Nguyen

Chun Yan

Upendra V Ummethala

Hongching Shan

Michael C Kutney

Steven E Babayan

Sidharth Bhatia

Evans Yip Lee

Lawrence Wong

Douglas H Burns

Thomas Li

Michael Howells

Taeho Shin

Kuang-Han Ke

Scott A Hogenson

Panyin Hughes

Qi Li

Mimi-Diemmy Dao

Kartik Ramaswamy

Yang Yang

Philip Allan Kraus

Hiroji Hanawa

Shahid Rauf

Douglas A Buchberger, Jr

Kallol Bera

Thai Cheng Chua

Yunsang Kim

Steven C Shannon

Michael D Welch

Martin Jeffrey Salinas

Hamid Tavassoli

Imad Yousif

Steven Lane

Claes H Bjorkman

Hong Sheng Yang

Hongqing Shan

Ajey M Joshi

Richard W Plavidal

Richard Raymond Mett

Ying Rui

Martin Jeff Salinas

Charles Hardy

Mahmoud Dahimene

Ji Ding

Zongyu Li

Henry Fong

Masao Drexel

James A Stinnett

Ying Xiao

Xue Yu Qian

Takehito Komatsu

Joanna Kejun Loh

Li Ming Tan

Zhiqiang Huang

Olivia Fatma Koentjoro

A method includes providing, as input to a first trained machine learning model, trace data associated with one or more substrate processing procedures. The input further includes equipment constants associated with the one or more substrate processing procedures. The input further includes trace data of a first processing chamber. The input further includes equipment constants of the first processing chamber. The method further includes obtaining, as output from the first trained machine learning model, a recommended update to a first equipment constant of the first processing chamber. The method further includes updated the first equipment constant of the first processing chamber responsive to obtaining the output from the first trained machine learning model.

Determining equipment constant updates by machine learning

A method includes receiving, by a processing device, data indicative of performance of a plurality of process chambers. The method further includes providing the data indicative of performance of the plurality of process chambers to a model. The method further includes receiving as output from the model a first recommended equipment constant update associated with a first process chamber of the plurality of process chambers and a second recommended equipment constant update associated with a second process chamber of the plurality of process chambers. The method further includes updating a first equipment constant of the first process chamber and a second equipment constant of the second process chamber in view of the first recommended equipment constant update and the second recommended equipment constant update.

Chamber matching by equipment constant updates

The disclosure describes methods and systems for training and deploying a machine learning predictive model for use in a semiconductor manufacturing process. Specifically, the present disclosure provides for training machine learning predictive models for manufacturing components using design data, process parameters, gas flow configurations from a pixelated showerhead, temperature profile across an electrostatic chuck, and measured uniformity profiles of processed wafers. The present disclosure also provides for deploying the machine learning predictive model to effectuate real-time adjustments to a manufacturing process.

Machine learning model for semiconductor manufacturing processes

The present disclosure is a method of bonding an electrostatic chuck to a temperature control base. According to the embodiments, a bonding layer is formed between a dielectric body comprising the electrostatic chuck and a temperature control base. A flow aperture extends through the dielectric body and is aligned with a flow aperture in the temperature control base. The bonding layer is also configured with an opening that aligns with apertures in the dielectric body and the temperature control base. In one aspect, a porous plug may be disposed within the flow aperture to protect the bonding layer. In another aspect, a seal is disposed within the flow aperture to seal off the boding layer from gases in the flow aperture.

Bonding structure of e chuck to aluminum base configuration

The present disclosure generally relates to plasma assisted or plasma enhanced processing chambers. More specifically, embodiments herein relate to electrostatic chucking (ESC) substrate supports configured to provide independent pulses of direct-current ('DC') voltage through a switching system to electrodes disposed in the ESC substrate support. In some embodiments, the switching system can independently alter the frequency and duty cycle of the pulsed DC voltage that is coupled to each electrode. In some embodiments, during processing of the substrate, the process rate, such as etch rate or deposition rate, can be controlled independently in regions of the substrate because the process rate is a function of the frequency and duty cycle of the pulsed DC voltage. The processing uniformity of the process performed on the substrate is improved.

System for coupling a voltage to spatially segmented portions of the wafer with variable voltage

Bonding structure of E chuck to aluminum base configuration

Implementations described herein provide a substrate support assembly which enables tuning of a plasma within a plasma chamber. In one embodiment, a method for tuning a plasma in a chamber is provided. The method includes providing a first radio frequency power and a direct current power to a first electrode in a substrate support assembly, providing a second radio frequency power to a second electrode in the substrate support assembly at a different location than the first electrode, monitoring parameters of the first and second radio frequency power, and adjusting one or both of the first and second radio frequency power based on the monitored parameters.

Multiple electrode substrate support assembly and phase control system

A magnetic field generator which provides greater control over the magnetic field is provided. The magnetic field generator has a plurality of overlapping main magnetic coil sections for forming a magnetic field generally parallel to the top surface of the supporting member. In other embodiments, sub-magnetic coil sections are placed symmetrically around the main magnetic coil sections.

Method and apparatus for shaping a magnetic field in a magnetic field-enhanced plasma reactor

A plasma reactor for processing a workpiece, includes a vacuum chamber defined by a sidewall and ceiling, and a workpiece support pedestal having a workpiece support surface in the chamber and facing the ceiling and including a cathode electrode. An RF power generator is coupled to the cathode electrode. Plasma distribution is controlled by an external annular inner electromagnet in a first plane overlying the workpiece support surface, an external annular outer electromagnet in a second plane overlying the workpiece support surface and having a greater diameter than the inner electromagnet, and an external annular bottom electromagnet in a third plane underlying the workpiece support surface. D.C. current supplies are connected to respective ones of the inner, outer and bottom electromagnets.

Plasma reactor with minimal D.C. coils for cusp, solenoid and mirror fields for plasma uniformity and device damage reduction

Methods and apparatus for automated validation of semiconductor process steps are provided herein. In some examples, a method for validating a semiconductor process recipe includes: selecting a rule set describing an operating window for a semiconductor process tool; checking parameter values defined by steps in the semiconductor process recipe against limit-checking rules of the rule set to produce first results; determining step types from the steps in the semiconductor process recipe using step definition rules of the rule set to produce second results; checking transitions between the step types against step transition rules of the rule set to produce third results; and generating, using the computer, validation data for use of the semiconductor process recipe with the semiconductor process tool based on the first, the second, and the third results.

Method and apparatus for automated validation of semiconductor process recipes

A method and apparatus for providing flow into a processing chamber are provided. In one embodiment, a vacuum processing chamber is provided that includes a substrate support pedestal disposed in an interior volume of a chamber body, a lid enclosing the interior volume, a gas distribution plate positioned below the lid and above the substrate support pedestal, and a vortex inducing gas inlet oriented to induce a vortex of gas circulating in a plenum around a center line of the chamber body prior to the gas passing through the gas distribution plate.

Plasma processing chamber with enhanced gas delivery

A method and apparatus for confining a plasma are provided herein. In one embodiment, an apparatus for confining a plasma includes a substrate support and a magnetic field forming device for forming a magnetic field proximate a boundary between a first region disposed at least above the substrate support, where a plasma is to be formed, and a second region, where the plasma is to be selectively restricted. The magnetic field has b-field components perpendicular to a direction of desired plasma confinement that selectively restrict movement of charged species of the plasma from the first region to the second region dependent upon the process conditions used to form the plasma.

Magnetic confinement of a plasma

Methods for rotating a magnetic field in a process chamber is provided herein. In one embodiment, a method for rotating a magnetic field in a process chamber includes forming a magnetic field having a primary shape; changing the primary shape to at least two sequential transitional shapes; and changing the transitional shape to a rotated primary shape. Optionally, the magnetic field may be maintained at an approximately constant magnitude throughout each step. Optionally, a maximum of one current applied to one or more magnetic field producing coils is equal to zero or has its polarity reversed between any two adjacent steps.

Method for shaping a magnetic field in a magnetic field-enhanced plasma reactor

Embodiments of the present invention relate to plasma processing apparatus and methods of use thereof. In some embodiments, a plasma control magnet assembly includes a plurality of magnets arranged in a predetermined pattern that generate a magnetic field having a strength greater than 10 Gauss in a region proximate the assembly and less than 10 Gauss in a region remote from the assembly.

Plasma processing apparatus

Growing community of inventors

Santa Clara, CA, United States of America

Roger Alan Lindley