Heat transfer study on a stator-permanent magnet electric motor: A hybrid estimation model for real-time temperature monitoring and predictive maintenance

Abstract

When electrical machines operate without a specific cooling system, the surrounding environment plays a crucial role in the rise of temperature and the duty cycle of operation. More clearly, a natural convection cooling system with a low value of heat transfer coefficient carries the risk of thermal breakdown, insufficient safety, and reliability. This paper studies the heat transfer aspects of a low-power flux switching permanent magnet (FSPM) motor under natural convection cooling to implement a novel real-time sensor-less temperature monitoring system. Thermal and electromagnetic experiments are carried out to create foundations for transient and steady-state numerical models. A data-driven, deep learning algorithm estimates the core and permanent magnet (PM) eddy current losses in real-time, besides the already available copper and friction losses. Subsequently, a two-node thermal equivalent circuit in a hybrid model with a feed-forward neural network estimates the dynamic temperature profile of windings and PMs. It is indicated that the worst-case estimation error is below 7.5%, and the configuration is applicable under a wide range of operation states and environmental conditions. Lastly, the system, including the power source, FSPM motor, and hybrid temperature estimation unit, will be implemented in MATLAB/Simulink to investigate the fault prediction and operation management capabilities.