IEEE Sensors Journal · 2020 · 10 citations · 18 references
EngineeringMechatronics EngineeringElectromagnetismGeomagnetismSensor FusionAttitude ControlAttitude DeterminationMagnetic SensorsAdaptabilityAttitude CouplingAttitude Determination AlgorithmsInertial Attitude DeterminationInertial SensorsNeural Network ControlNeural Network Modeling
Due to use of low-cost inertial sensors, the attitude calculation results of guided projectiles are inaccurate. A coupling method of geomagnetic aided inertial attitude errors is proposed in this paper. The method combines principle of geomagnetic attitude measurement to couple inertial/geomagnetic attitude. The inertial attitude errors coupling model is constructed, and back propagation (BP) neural network is introduced to solve the model to compensate inertial attitude errors. The simulation results show that the proposed method can reduce inertial attitude maximum error angle (AMEA) by more than 45%, and attitude root mean square error (ARMSE) by more than 50% compared with inertial attitude results. The experiment results show that the proposed method can reduce AMEA and ARMSE by more than 25% compared with inertial attitude results. The proposed method has strong environmental adaptability and anti-noise ability, and is suitable for attitude calculation of guided projectiles.
18
Learning representations by back-propagating errors
David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams · Nature · 1986 · 30.9K citations
Fast Complementary Filter for Attitude Estimation Using Low-Cost MARG Sensors
Jin Wu, Zebo Zhou, Jingjun Chen et al. · IEEE Sensors Journal · 2016 · 222 citations