TY - GEN
T1 - RSM-DE-ANN method for sensitivity analysis of active material cost in PM motors
AU - Fatemi, Alireza
AU - Ionel, Dan M.
AU - Demerdash, Nabeel A.O.
AU - Stretz, Steven J.
AU - Jahns, Thomas M.
PY - 2016
Y1 - 2016
N2 - In this paper, a numerical technique is developed for sensitivity analysis of active material cost (AMC) in PM motors with distributed and fractional slot concentrated windings. A comprehensive analysis is carried out to identify how the optimal design rules and proportions of IPM motors with sintered NdFeB magnets vary with respect to the changes in the commodity prices of permanent magnet material, copper, and steel. The sensitivities of the correlations between the design parameters and the AMC with respect to the commodity price ranges are investigated based on response surface methodology (RSM) and large-scale design optimization practice using differential evolution (DE) optimizer. An innovative application of artificial neural network (ANN)-based design optimization is introduced. Multi-objective minimization of cost and losses is pursued for an overall of 200,000 design candidates in 30 different optimization instances subjected to different cost scenarios according to a systematic design of experiments (DOE) procedure. An interesting finding is that, despite common expectations, the average mass of steel in the optimized designs is more sensitive to changes in the commodity prices than the masses of copper and rotor PMs.
AB - In this paper, a numerical technique is developed for sensitivity analysis of active material cost (AMC) in PM motors with distributed and fractional slot concentrated windings. A comprehensive analysis is carried out to identify how the optimal design rules and proportions of IPM motors with sintered NdFeB magnets vary with respect to the changes in the commodity prices of permanent magnet material, copper, and steel. The sensitivities of the correlations between the design parameters and the AMC with respect to the commodity price ranges are investigated based on response surface methodology (RSM) and large-scale design optimization practice using differential evolution (DE) optimizer. An innovative application of artificial neural network (ANN)-based design optimization is introduced. Multi-objective minimization of cost and losses is pursued for an overall of 200,000 design candidates in 30 different optimization instances subjected to different cost scenarios according to a systematic design of experiments (DOE) procedure. An interesting finding is that, despite common expectations, the average mass of steel in the optimized designs is more sensitive to changes in the commodity prices than the masses of copper and rotor PMs.
KW - Active material cost (AMC)
KW - artificial neural network (ANN)
KW - design optimization
KW - permanent magnet (PM) motors
KW - response surface methodology (RSM)
KW - sensitivity analysis
UR - http://www.scopus.com/inward/record.url?scp=85015456408&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85015456408&partnerID=8YFLogxK
U2 - 10.1109/ECCE.2016.7855414
DO - 10.1109/ECCE.2016.7855414
M3 - Conference contribution
AN - SCOPUS:85015456408
T3 - ECCE 2016 - IEEE Energy Conversion Congress and Exposition, Proceedings
BT - ECCE 2016 - IEEE Energy Conversion Congress and Exposition, Proceedings
T2 - 2016 IEEE Energy Conversion Congress and Exposition, ECCE 2016
Y2 - 18 September 2016 through 22 September 2016
ER -