A method in which an acoustic sensor disposed in a polishing apparatus can be accurately calibrated is disclosed. In this method, polishing sounds of a substrate are acquired using an acoustic sensor; and then at least two distinctive sounds, having distinctive frequencies respectively, are selected from the acquired polishing sounds. Further, the at least two distinctive sounds are output from a sound source coupled to any of a polishing table, the acoustic sensor, and a substrate holder to cause the at least two distinctive sounds to be input to the acoustic sensor. Next, output values of the acoustic sensor are calibrated, such that the output values of the acoustic sensor relative to the at least two distinctive sounds come within an allowable range.

An apparatus for chemical mechanical polishing of a wafer includes a process chamber and a rotatable platen disposed inside the process chamber. A polishing pad is disposed on the platen and a wafer carrier is disposed on the platen. A slurry supply port is configured to supply slurry on the platen. A process controller is configured to control operation of the apparatus. A set of microphones is disposed inside the process chamber. The set of microphones is arranged to detect sound in the process chamber during operation of the apparatus and transmit an electrical signal corresponding to the detected sound. A signal processor is configured to receive the electrical signal from the set of microphones, process the electrical signal to enable detection of an event during operation of the apparatus, and in response to detecting the event, transmit a feedback signal to the process controller. The process controller is further configured to receive the feedback signal and initiate an action based on the received feedback signal.

The present application relates to systems and methods for obtaining real-time abrasion data. An example computer-implemented method could include receiving, at a computing device, sensor data from one or more sensors. The one or more sensors are disposed in proximity to an abrasive product or a workpiece associated with the abrasive product. The one or more sensors are configured to collect abrasion operational data associated with an abrasive operation involving the abrasive product or the workpiece. The computer-implemented method could further include training, based on the sensor data, a machine learning system to determine product specific information of the abrasive product and/or workpiece specific information. The computer-implemented method could also include providing the trained machine learning system using the computing device.

A method includes measuring a first thickness at a first location of the polishing pad and a second thickness at a second location of the polishing pad; obtaining a first reference thickness at the first location of the polishing pad, wherein the first reference thickness is an average thickness of multiple thicknesses at the first location; obtaining a second reference thickness at the second location of the polishing pad, wherein the second reference thickness is an average thickness of multiple thicknesses at the second location; calculating a first thickness difference; calculating a second thickness difference; modifying a conditioning parameter value at the first location of the polishing pad; and sweeping a conditioner across a surface of the polishing pad; and applying a downforce or a sweeping speed to the conditioner that urges the conditioner against the first location of the polishing pad according to the modified conditioning parameter value.

A semiconductor manufacturing apparatus includes a sound measuring unit that measures a first polishing sound of a film formed on a wafer, a sound pressure prediction regression model generation unit that generates a first regression model for obtaining a first sound pressure prediction value of the first polishing sound, a sound pressure prediction value calculation unit that performs a first calculation of the first sound pressure prediction value by using the first regression model, a residual difference calculation unit that performs a second calculation of a first residual difference, the first residual difference being a difference between a first sound pressure actual measurement value of the first polishing sound and the first sound pressure prediction value, and an end point determination unit that determines a polishing end point of the film by using the first residual difference.

A method determines state information relating to a belt grinder. The belt grinder has at least one abrasive belt for grinding a workpiece. The method includes providing measurement data relating to the belt grinder, and determining the state information from the measurement data using a machine learning system. The machine learning system is configured to determine the state information based on the provided measurement data.

There is provided a cutting machine for cutting a wafer using a cutting blade. The cutting machine includes a shape storage section, a shape measurement unit, a determination section, and an end face correction device. The shape storage section stores a cross-sectional shape of a support surface, which a mount of a cutting unit has, in an axial direction of a spindle. The shape measurement unit contactlessly measures the cross-sectional shape of the support surface in the axial direction of the spindle. Through a comparison between the cross-sectional shape stored in the shape storage section and the cross-sectional shape measured by the shape measurement unit, the determination section determines whether or not the support surface needs a correction. The end face correction device corrects a shape of the support surface.

A method for abrading a surface of a workpiece by means of an abrasion machine, including the following steps: (a) acquiring, with at least one sensor, on at least one portion of the surface of the workpiece, data in relation to at least one characteristic of the workpiece in at least two basic zones defined on the surface, processing, for each basic zone, the data in relation to the at least one characteristic in order to assign, to each basic zone and/or at least one group of basic zones, a value for this characteristic, determining and/or adjusting at least one abrasion parameter for the abrasion machine and/or an abrasion trajectory in accordance with the values attributed for the basic zones or group of basic zones, abrading at least a portion of the surface with the abrasion machine with the at least one abrasion parameter and the abrasion trajectory.

The present disclosure describes a method and apparatus to remove consumable (e.g., sacrificial) polishing pad layers from a multilayer polishing pad. For example, the method includes measuring a thickness profile of a top polishing pad layer of a multilayer polishing pad and comparing the thickness profile to a threshold. The method, in response to the thickness profile being above the threshold, rinses the top polishing pad layer of the multilayer polishing pad and removes, after the top polishing pad layer has been rinsed, the top polishing pad layer to expose an underlying polishing pad layer of the multilayer polishing pad.

Automated systems and methods of using a smart end-effector tool to prepare (e.g., scuffing, abrading, sanding, polishing, etc.) an object surface are provided. The smart tool can update its working state with a robot arm in real time, which in turn adjusts locomotion parameters to optimize the tool's working state on the object surface.