Abstract: A method for plasma processing includes providing a tailored hybrid waveform as a bias voltage to a bottom electrode of a plasma processing chamber, measuring a control variable of a plasma with a sensor of the plasma processing chamber, and adjusting the tailored hybrid waveform based on the control variable.

Abstract: A method of endpoint detection includes receiving a wafer classification model that includes wafer types, product types and end-point detection (EPD) algorithms. Each EPD algorithm corresponds to a respective wafer type and a respective product type. Initial data of a wafer measured by an optical instrument are received. The wafer classification model is executed based on the initial data to determine a wafer type, a product type and an EPD algorithm for the wafer or to determine whether the wafer or the optical instrument is faulty. An etching process is executed on the wafer to obtain a product. The EPD algorithm is run to obtain an etching depth using data associated with the etching process so that an endpoint time of the etching process is determined by the etching depth or a maximum endpoint time. A post-etching outlier model is executed to determine whether the product is faulty.

Abstract: The profile detecting method includes: detecting a specific shape included in a detection target image from the detection target image including the specific shape using a model that has learned a learning image including the specific shape and information regarding the specific shape included in the learning image; and outputting shape information of the detected specific shape.

Abstract: Aspects of the disclosure provide a method for wafer result prediction. The method includes determining predictor parameters of a semiconductor process using domain knowledge that includes knowledge of the semiconductor process, a processing tool associated with the semiconductor process, a metrology tool, and/or the wafer. The method also includes removing collinearity among the predictor parameters to obtain key predictor parameters, and selecting a subset of the key predictor parameters based on metrology data of the wafer obtained from the metrology tool. The method further includes building a virtual metrology (VM) model on the subset of the key predictor parameters and may include predicting wafer results using the VM model.

Abstract: A method for detecting an endpoint of a seasoning process for a plasma tool includes (a) operating the plasma tool to run a seasoning recipe on at least one seasoning wafer before running a monitoring recipe on at least one monitoring wafer; (b) collecting, while running the monitoring recipe on the monitoring wafer, monitoring data associated with the running the monitoring recipe; and (c) generating an estimated product parameter using a virtual metrology (VM) model that is configured to estimate a product parameter using the monitoring data. The VM model is based on production data associated with running a production recipe on production wafers and product parameters of the production wafers measured after the running the production recipe. The endpoint of the seasoning process is obtained by repeating (a), (b) and (c), and the endpoint is obtained when the estimated product parameter stabilizes.

Abstract: A method for processing a substrate that includes: processing a series of substrates using a plasma processing system having a plasma processing chamber by reactive ion etching (RIE) according to a RIE process condition; and after the processing, performing an in-situ diagnosis of the plasma processing system, the in-situ diagnosis including loading a substrate in the plasma processing chamber, depositing a film over the substrate, purging the plasma processing chamber with an inert gas, generating a RF plasma in the plasma processing chamber from the inert gas, sputtering the film to generate an etch product, the sputtering including exposing the substrate to the RF plasma, determining a rate of the sputtering of the film, and based on the rate of the sputtering of the film, determining a usability condition of the plasma processing system for processing another substrate.

Abstract: A method of optimizing a recipe for a plasma process includes (a) building a virtual metrology (VM) model that predicts a wafer characteristic resulting from the plasma process based on a plasma parameter and (b) building a control model that describes a relationship between the plasma parameter and a recipe parameter. (c) The wafer characteristic is measured after performing the plasma process according to the recipe. (d) Whether the wafer characteristic is within a predetermined range is determined. (e) The VM model and the control model are calibrated based on the wafer characteristic. (f) The recipe is optimized by updating the plasma parameter based on the wafer characteristic using the VM model and updating the recipe parameter based on the plasma parameter using the control model. (c), (d), (e) and (f) are repeated until the wafer characteristic is within the predetermined range.

Abstract: A method of operating a plasma tool includes executing a plasma process on a wafer. Data associated with the plasma process are measured using a plurality of sensors while the plasma process is executed on the wafer. The plasma process is terminated at an endpoint time. A post-process fault detection is executed by determining whether a post-process wafer state is within a target range. When the post-process wafer state is outside the target range so that a fault is detected, the fault is corrected using the data associated with the plasma process.

Abstract: A method for detecting an endpoint of a seasoning process for a plasma tool includes (a) operating the plasma tool to run a seasoning recipe on at least one seasoning wafer before running a monitoring recipe on at least one monitoring wafer; (b) collecting, while running the monitoring recipe on the monitoring wafer, monitoring data associated with the running the monitoring recipe; and (c) generating an estimated product parameter using a virtual metrology (VM) model that is configured to estimate a product parameter using the monitoring data. The VM model is based on production data associated with running a production recipe on production wafers and product parameters of the production wafers measured after the running the production recipe. The endpoint of the seasoning process is obtained by repeating (a), (b) and (c), and the endpoint is obtained when the estimated product parameter stabilizes.

Abstract: Provided is a method for monitoring a plasma-related process in a plasma tool. The method includes measuring data associated with the plasma-related process using a plurality of sensors while executing the plasma-related process on a wafer. Respective data measured by each sensor of the plurality of sensors are input into a respective individual estimation method to output a respective individual wafer state of the wafer, which results in a plurality of individual wafer states. The respective individual estimation method is configured to estimate the respective individual wafer state using at least the respective data. The plurality of individual wafer states is input into an integrated estimation method to output an integrated wafer state of the wafer. The integrated estimation method is configured to estimate the integrated wafer state using at least the plurality of individual wafer states.

Abstract: A method of evaluating tool health of a plasma tool is provided. The method includes providing a virtual metrology (VM) model that predicts a wafer characteristic based on parameters measured by module sensors and in-situ sensors of the plasma tool. A classification model is provided that identifies a plurality of failure modes of the plasma tool. An initial test is performed on an incoming wafer to determine whether the incoming wafer meets a preset requirement. The wafer characteristic is predicted using the VM model when the incoming wafer meets the preset requirement. A current failure mode is identified using the classification model when the wafer characteristic predicted by using the VM model is outside a pre-determined range.

Abstract: A method of evaluating tool health of a plasma tool is provided. The method includes providing a virtual metrology (VM) model that predicts a wafer characteristic based on parameters measured by module sensors and in-situ sensors of the plasma tool. A classification model is provided that identifies a plurality of failure modes of the plasma tool. An initial test is performed on an incoming wafer to determine whether the incoming wafer meets a preset requirement. The wafer characteristic is predicted using the VM model when the incoming wafer meets the preset requirement. A current failure mode is identified using the classification model when the wafer characteristic predicted by using the VM model is outside a pre-determined range.

Abstract: A method of optimizing a recipe for a plasma process includes (a) building a virtual metrology (VM) model that predicts a wafer characteristic resulting from the plasma process based on a plasma parameter and (b) building a control model that describes a relationship between the plasma parameter and a recipe parameter. (c) The wafer characteristic is measured after performing the plasma process according to the recipe. (d) Whether the wafer characteristic is within a predetermined range is determined. (e) The VM model and the control model are calibrated based on the wafer characteristic. (f) The recipe is optimized by updating the plasma parameter based on the wafer characteristic using the VM model and updating the recipe parameter based on the plasma parameter using the control model. (c), (d), (e) and (f) are repeated until the wafer characteristic is within the predetermined range.

Abstract: Aspects of the disclosure provide a method for wafer result prediction. The method includes determining predictor parameters of a semiconductor process using domain knowledge that includes knowledge of the semiconductor process, a processing tool associated with the semiconductor process, a metrology tool, and/or the wafer. The method also includes removing collinearity among the predictor parameters to obtain key predictor parameters, and selecting a subset of the key predictor parameters based on metrology data of the wafer obtained from the metrology tool. The method further includes building a virtual metrology (VM) model on the subset of the key predictor parameters and may include predicting wafer results using the VM model.

Abstract: Embodiments are described herein for systems and methods for plasma processing tool matching after preventative maintenance (PM). Before the PM, the plasma processing tool is operated to run a process on a test wafer, and measurements are taken for pre-PM operational data associated with the process during the operating. After the PM, the plasma processing tool is again operated to run the process on a test wafer, and measurements are taken for post-PM operational data associated with the process during the operating. A prediction model is then applied to the pre-PM operational data and the post-PM operational data to generate an estimated difference in a product parameter, and the prediction model is configured to provide an estimate for the product parameter based upon operational data. One or more control settings for the plasma processing tool are then adjusted to compensate for the estimated difference in the product parameter.

Abstract: Embodiments are described herein for sensor-to-sensor matching methods for chamber matching across multiple plasma processing chambers. For disclosed embodiments, a baseline signature in a first processing chamber is compared to a signature generated in a second processing chamber in order to adjust and match sensor display values for the second processing chamber. The baseline signature is determined using a golden reference sensor disposed within the first processing chamber and plasma sensors monitoring a baseline plasma. The signature of the plasma is determined using the golden reference sensor disposed within the second processing chamber and plasma sensors monitoring the plasma. Differences are determined between the baseline signature and the signature, and a display value for the plasma sensors for the second processing chamber is adjusted based on the differences to provide chamber matching with the first processing chamber. The golden reference sensor can be a wafer with embedded sensors.

Abstract: A method and a system for monitoring a plasma chamber are provided. The method includes receiving process chamber characteristics from the plasma chamber; determining whether one or more variables associated with the process chamber characteristics are within predetermined specification. The method further includes updating a status of the plasma chamber to failure when the chamber characteristics are not within the predetermined specification. The method generates a warning notification when the chamber characteristics are within predetermined specification and when an operation status of the plasma chamber received from a fault detection system indicates a failure.

Abstract: Embodiments are described herein for sensor-to-sensor matching methods for chamber matching across multiple plasma processing chambers. For disclosed embodiments, a baseline signature in a first processing chamber is compared to a signature generated in a second processing chamber in order to adjust and match sensor display values for the second processing chamber. The baseline signature is determined using a golden reference sensor disposed within the first processing chamber and plasma sensors monitoring a baseline plasma. The signature of the plasma is determined using the golden reference sensor disposed within the second processing chamber and plasma sensors monitoring the plasma. Differences are determined between the baseline signature and the signature, and a display value for the plasma sensors for the second processing chamber is adjusted based on the differences to provide chamber matching with the first processing chamber. The golden reference sensor can be a wafer with embedded sensors.

Abstract: A method and a system for plasma etching are provided. The method includes measuring a first set of plasma etch processing parameters; determining an etch rate; altering the plasma etch processing chamber hardware configuration if the determined etch rate differs from a standard etch rate by more than a predetermined etch rate difference threshold, thereafter repeating the determining and altering until the determined etch rate differs from the standard etch rate by less than the predetermined etch rate difference threshold. The method further includes measuring a critical dimension of an etched feature and altering the etch processing parameters if the measured critical dimension differs from a standard critical dimension by more than a predetermined critical dimension difference threshold, thereafter repeating the determining and altering until the measured critical dimension differs from the standard critical dimension by less than the predetermined critical dimension difference threshold.

Abstract: A method and a system for plasma etching are provided. The method includes measuring a first set of plasma etch processing parameters; determining an etch rate; altering the plasma etch processing chamber hardware configuration if the determined etch rate differs from a standard etch rate by more than a predetermined etch rate difference threshold, thereafter repeating the determining and altering until the determined etch rate differs from the standard etch rate by less than the predetermined etch rate difference threshold. The method further includes measuring a critical dimension of an etched feature and altering the etch processing parameters if the measured critical dimension differs from a standard critical dimension by more than a predetermined critical dimension difference threshold, thereafter repeating the determining and altering until the measured critical dimension differs from the standard critical dimension by less than the predetermined critical dimension difference threshold.