Parametric and non-parametric models for lifespan modeling of insulation systems in electrical machines

Farah Salameh (1) , Antoine Picot (2) , Marie Chabert (3, 4) , Pascal Maussion (2)

1 LAPLACE - LAboratoire PLasma et Conversion d'Energie
2 LAPLACE-CODIASE - COmmande et DIAgnostic des Systèmes Electriques
3 IRIT-SC - Signal et Communications
4 Toulouse INP - Institut National Polytechnique (Toulouse)

This paper describes an original statistical approach for the lifespan modeling of electric machine insulation materials. The presented models aim to study the effect of three main stress factors (voltage, frequency and temperature) and their interactions on the insulation lifespan. The proposed methodology is applied to two different insulation materials tested in partial discharge regime. Accelerated ageing tests are organized according to experimental optimization methods in order to minimize the experimental cost while ensuring the best model accuracy. In addition to classical parametric models, the life-stress relationship is expressed through original non-parametric and hybrid models that have never been investigated in insulation aging studies before. These two models present the original contribution of this paper. For each material, models are computed from organized sets of experiments and applied on a randomly configured test set for validity checking. The different models are evaluated and compared in order to define their optimal use.

Mots clés: Accelerated aging; Design optimization; Electric machines; Lifetime estimation; Insulation; Model checking; Modeling; Partial discharges; Regression analysis; Stress

Domaines: Modélisation et simulation; Calcul formel [cs.SC]

Farah Salameh, Antoine Picot, Marie Chabert, Pascal Maussion. Parametric and non-parametric models for lifespan modeling of insulation systems in electrical machines. IEEE Transactions on Industry Applications, 2017, vol. 53 (n° 3), pp. 3119-3128. ⟨10.1109/TIA.2016.2635100⟩. ⟨hal-01611696⟩