US 12,265,382 B2
B vs W two pack confirmation test
Matthew Peterson, Easley, SC (US); and Craig Hysong, Saline, MI (US)
Assigned to SHAININ II LLC, Northville, MI (US)
Filed by Shainin II LLC, Northville, MI (US)
Filed on Aug. 18, 2022, as Appl. No. 17/820,622.
Prior Publication US 2024/0061414 A1, Feb. 22, 2024
Int. Cl. G05B 23/02 (2006.01); G06F 3/0484 (2022.01)
CPC G05B 23/0251 (2013.01) [G05B 2223/02 (2018.08); G06F 3/0484 (2013.01)] 9 Claims
OG exemplary drawing
 
1. A method of improving a manufacturing process via a parametric B vs W two pack confirmation test for analyzing whether a testable parameter of a manufacturing process operation or a workpiece is a cause of an observable problem, the method comprising:
receiving, via a GUI, an indication of a desired alpha risk and a set of output sample data corresponding to a population of workpieces or manufacturing process operations associated with the observable problem, and each output sample in the output sample data having an associated measured value of an output variable that is representative of the observable problem;
processing, via a computer processor, the output sample data to generate an estimated distribution of the output variable for the population of workpieces or manufacturing process operations;
determining, via the computer processor, bins of equal probability in the estimated distribution to define best-of-best (BOB) and worst-of-worst (WOW) regions based on the desired alpha risk;
receiving, via the GUI, a first measured value of the output variable of a B sample of the workpiece or manufacturing process having the parameter at a first parameter value that is predicted to result in the output variable falling within the BOB region, and a second measured value of the output variable of a W sample of the workpiece or manufacturing process having the parameter at a second parameter value that is predicted to result in the output variable falling within the WOW region; and
determining whether the first measured value of the output variable of the B sample falls in the BOB region and the second measured value of the output variable of the W sample falls within the WOW region to indicate on the GUI that the parametric B vs W two pack confirmation test passed with the desired alpha risk, thereby identifying the parameter as a cause of the observable problem;
controlling the parameter to reduce the incidence of the observable problem caused by the workpiece or manufacturing process.