Development of a Magnetic Absolute Encoder Using Eccentric Structure and Long Short-Term Memory

Takeyama, Akishi; Komatsuzaki, Shota; Sado, Keita; Nagastu, Yuki; Hashimoto, Hideki

doi:10.1109/iecon48115.2021.9589568

Cited by 2 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Technologies Merits [11] Long Short-Term Memory (LSTM) Decreasing angle error via fewer sensors [15] Self-referencing lookup table (LUT) Eliminating the external disturbance effects [16] Type-2 phase-locked loop (PLL) Using little memory, with total position error of ±0.2 • [17] Adaptive Linear-Neuron and a third-order phase-locked loop (ALN-PLL)…”

Section: Referencementioning

confidence: 99%

“…The population is initialized with the number of iterations of the swarm set as 100 and the number of particles in the swarm set as 30. The individual fitness and population fitness are updated as iterations increase, and the speed and position are updated according to Equations (10) and (11). The specific process is shown in Figure 7.…”

Section: The Filtering Window Width Prediction Algorithm Based On Ipsomentioning

confidence: 99%

“…Considering its structure, these issues can be alleviated by improving the installation accuracy of the Hall elements, the direction and accuracy of magnetization of the magnetic steel, and the number of poles contained in the magnetic steel. An eccentric rotation structure is employed to obtain high resolution without reducing absolute angle precision in [10][11][12]. However, the method of handling multi-poles is not related to the number of Hall ICs that fail, as pointed out in [10], and long short-term memory (LSTM) has been proposed in [11] to decrease the huge angular position error when the number of sensors is cut down.…”

Section: Introductionmentioning

confidence: 99%

“…An eccentric rotation structure is employed to obtain high resolution without reducing absolute angle precision in [10][11][12]. However, the method of handling multi-poles is not related to the number of Hall ICs that fail, as pointed out in [10], and long short-term memory (LSTM) has been proposed in [11] to decrease the huge angular position error when the number of sensors is cut down. An absolute multi-pole structure including an index track and sub-division track has been proposed to enhance the resolution of the encoder [13].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Novel Angle Segmentation Method for Magnetic Encoders Based on Filtering Window Adaptive Adjustment Using Improved Particle Swarm Optimization

Wang,

Wei,

Liang

et al. 2023

Sensors

View full text Add to dashboard Cite

In this paper we outline newly-developed control algorithms, designed to achieve high-precision feedback for a motor control system using a magnetic encoder. The magnetic encoder, combing single-pole and multi-pole magnetic steels, was adopted to extend the resolution of the magnetic encoder. First, with a view to settling the issue of the jump points of the multi-pole angle value at the convergence of two adjacent magnetic poles, the angle segmentation method, which uses the window filter discrimination method, is employed to determine the actual angle value. The appropriate filter window width is selected via the improved particle swarm optimization (IPSO) algorithm, and an expanded resolution is achieved. Second, a compensation table is completed via a linear compensation algorithm based on virtual cutting to enhance the accuracy of the combined magnetic encoder. On this basis, a linear difference algorithm is used to achieve deviation correction of the angle. Finally, the jump points can be restrained effectively via the angle segmentation method. The resolution reaches 0.05°, and the accuracy is 0.045°.

show abstract