6160sigma160bb黑带培训资料-160160trw_booster_wk2_06_doe4(编辑修改稿)

6160sigma160bb黑带培训资料-160160trw_booster_wk2_06_doe4(编辑修改稿)内容摘要：

ne time • Days • Shifts • Location  Can’t make all parts from similar raw material • Lots • Batches • Regions  Can’t make tests under similar conditions • Machines • Workers • Customers • Environment 134 Using Minitab to Design a Blocked Experiment Example: in 8 blocks of Size 2 Stat DOE Create Factorial Design Factors “6” Design 262IIIAltho ug h t he unb lockedde sig n ( ) isRe sol uti on IV , thebl ocked desi gn hasbl ocks con foun de d wi thtwofact or i ntera ct ion sresu ltin g i n a Reso luti onIII desi gn .262 I I I135 Using Minitab to Design a Blocked Experiment, cont. Design in randomized order StdOrder RunOrder Blocks A B C D E F 16 1 8 + + + + + + 15 2 8 13 3 7 + + 14 4 7 + + + + 2 5 1 + + + 1 6 1 + + + 7 7 4 + + + + 8 8 4 + + 5 9 3 + + 6 10 3 + + + + 3 11 2 + + + 4 12 2 + + + 11 13 6 + + + 12 14 6 + + + 10 15 5 + + + 9 16 5 + + + The blocks are in random order and the runs within the blocks have been randomized, too 136 Using Minitab to Design a Blocked Experiment, cont. Session window output Factorial Design Fractional Factorial Design Factors: 6 Base Design: 6, 16 Resolution with blocks: III Runs: 16 Replicates: 1 Fraction: 1/4 Blocks: 8 Center pts (total): 0 *** NOTE *** Blocks are confounded with twoway interactions Design Generators: E = ABC F = BCD Block Generators: AB BC BF Alias Structure I + ABCE + ADEF + BCDF Blk1 = AB + CE + ACDF + BDEF Blk2 = AE + BC + DF + ABCDEF Blk3 = BF + CD + ABDE + ACEF Blk4 = AC + BE + ABDF + CDEF Blk5 = AF + DE + ABCD + BCEF Blk6 = BD + CF + ABEF + ACDE Blk7 = AD + EF + ABCF + BCDE A + BCE + DEF + ABCDF B + ACE + CDF + ABDEF C + ABE + BDF + ACDEF D + AEF + BCF + ABCDE E + ABC + ADF + BCDEF F + ADE + BCD + ABCEF ABD + ACF + BEF + CDE ABF + ACD + BDE + CEF Notice that in this design, the Block effects are confounded with 2way interactions and higher 137 Interpreting Block Effects 4 3 2 1 1 2 3 4 5 6 7 8 Block Response Average  If any of the block effects are judged to be important, we know the blocks differ from each other.  This is not a surprise since the design was blocked to control known sources of variation.  To find how the blocks differ from each other, you must find the averages of。