Surface processing of semiconductor workpieces
An example method includes obtaining data indicative of a workpiece processing parameter. In some implementations, the example method includes determining a grinding depth for a semiconductor workpiece based at least in part on the data indicative of the workpiece processing parameter. In some implementations, the example method includes performing a grinding operation to remove material from the semiconductor workpiece to reduce a thickness of the semiconductor workpiece by the grinding depth.
1 . A method, comprising:
obtaining data indicative of a workpiece removal parameter, the workpiece removal parameter indicative of processing information used to separate semiconductor workpieces from a boule;
performing a grinding operation to remove material from a first semiconductor workpiece removed from the boule to reduce a thickness of the first semiconductor workpiece by a first grind depth;
obtaining an image of the first semiconductor workpiece after the grinding operation; and
determining, based on the image and the data indicative of the workpiece removal parameter, second grind depth for a second semiconductor workpiece, the second semiconductor workpiece removed from the boule after the first semiconductor workpiece;
wherein the second grind depth is different than the first grind depth.
2 . The method of claim 1 , wherein the semiconductor workpiece is a semiconductor wafer.
3 . The method of claim 1 , wherein the workpiece wafer removal parameter comprises at least one of a wafer separation type, a laser power, a position of the semiconductor wafer within a semiconductor boule, or a material type of the semiconductor wafer.
4 . The method of claim 3 , wherein the data indicative of the workpiece removal parameter further comprises a predetermined value.
5 . The method of claim 4 , wherein determining the grinding depth for the semiconductor workpiece comprises:
determining a first adjustment to the first grinding depth based at least in part on the predetermined value; and
determining a second adjustment to the first grinding depth based at least in part on a boule image.
6 . The method of claim 5 , wherein the first adjustment is greater than the second adjustment.
7 . The method of claim 1 , wherein the first grind depth is determined using a model, the model being a machine-learned model.
8 . The method of claim 7 , wherein the machine-learned model is trained to provide the output based at least in part on a boule image.
9 . The method of claim 1 , wherein the first grind depth is less than the second grind depth.
10 . A system for grinding semiconductor workpieces, the system comprising:
a grinding surface operable to remove semiconductor material from a surface of a semiconductor workpiece;
a translation stage operable to impart relative motion between the grinding surface and the semiconductor workpiece;
an image-capturing device; and
control circuitry configured to perform operations, the operations comprising:
determining a first grinding depth for a first semiconductor workpiece based at least in part on the data indicative of a workpiece removal parameter, the workpiece removal parameter indicative of processing information used to separate semiconductor workpieces from a boule;
controlling the grinding surface to remove the semiconductor material from the first semiconductor workpiece to reduce a thickness of the first semiconductor workpiece by the first grinding depth;
obtaining an image of the first semiconductor workpiece after the grinding operation; and
determining, based on the image and the data indicative of the workpiece removal parameter, a second grinding depth for a second semiconductor workpiece, the second semiconductor workpiece removed from the boule after the first semiconductor workpiece;
wherein the second grinding depth is different than the first grinding depth.