IN-PROCESS CONTROL OF TURNED THREADS

MACHINE CUTTING OF THREADS IS A KEY STEP IN RELIABLY MANUFACTURING MANY PRODUCTS. HOWEVER, LITTLE PROGRESS HAS BEEN MADE IN IMPROVING THIS PROCESS FOR DECADES DUE TO THE COMPLEXITY OF THE PROCESS AND THE DIFFICULTY IN PRECISELY CONTROLLING IT. NETROLOGIC PROPOSES USING NON-LINEAR PIEZOACTUATORS CONTROLLED BY NEURAL NETS TO OBTAIN 5 ARC MINUTES ACCURACY IN POSITIONING A CUTTING TOOL. IN PHASE I NEURAL NETWORKS WILL LEARN TO CONTROL A HIGHLY NON-LINEAR SET OF PIEZO ACTUATORS AS SIMULATED ON A COMPUTER. IN PHASE II A MACHINE TOOL WILL BE INSTRUMENTED TO DEMONSTRATE THE CONCEPT IN HARDWARE. TOOL POSITIONING INFORMATION WILL BE SUPPLIED BY A LASER MEASUREMENT DEVICE ALREADY FABRICATEDAND OPERABLE.