Health Prediction for UAV Motors Based on Weak Degradation Characteristics

Abstract

For the multi-rotor unmanned aerial vehicles (UAVs), the power source is the brushless direct current (BLDC) motors whose working status directly affects the safety of the UAVs. Therefore, it is of great importance to accurately estimate and predict the healthy status of the BLDC motor. In this paper, to achieve such a purpose, a weak degradation characteristic extraction method is proposed based on the variational mode decomposition (VMD) and the Laplacian eigenmaps (LE). With the proposed method, the weak degradation characteristic of the BLDC motor can be extracted accurately and the loss of key information as well as interference of redundant information are avoided. By using the historical data memory and the relationship analysis ability of the long-term and short-term memory, the healthy status of the BLDC motor is well predicted.