Performance Analysis of a Deep Simple Recurrent Unit Recurrent Neural Network (SRU-RNN) in MEMS Gyroscope De-Noising
Microelectromechanical System (MEMS) Inertial Measurement Unit (IMU) is popular in the community for constructing a navigation system, due to its small size and low power consumption. However, limited by the manufacturing technology, MEMS IMU experiences more complicated noises and errors. Thus, noi...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/18/12/4471 |
| _version_ | 1798006674342019072 |
|---|---|
| author | Changhui Jiang Shuai Chen Yuwei Chen Yuming Bo Lin Han Jun Guo Ziyi Feng Hui Zhou |
| author_facet | Changhui Jiang Shuai Chen Yuwei Chen Yuming Bo Lin Han Jun Guo Ziyi Feng Hui Zhou |
| author_sort | Changhui Jiang |
| collection | DOAJ |
| description | Microelectromechanical System (MEMS) Inertial Measurement Unit (IMU) is popular in the community for constructing a navigation system, due to its small size and low power consumption. However, limited by the manufacturing technology, MEMS IMU experiences more complicated noises and errors. Thus, noise modeling and suppression is important for improving accuracy of the navigation system based on MEMS IMU. Motivated by this problem, in this paper, a deep learning method was introduced to MEMS gyroscope de-noising. Specifically, a recently popular Recurrent Neural Networks (RNN) variant Simple Recurrent Unit (SRU-RNN) was employed in MEMS gyroscope raw signals de-noising. A MEMS IMU MSI3200 from MT Microsystem Company was employed in the experiments for evaluating the proposed method. Following two problems were furtherly discussed and investigated: (1) the employed SRU with different training data length were compared to explore whether there was trade-off between the training data length and prediction performance; (2) Allan Variance was the most popular MEMS gyroscope analyzing method, and five basic parameters were employed to describe the performance of different grade MEMS gyroscope; among them, quantization noise, angle random walk, and bias instability were the major factors influencing the MEMS gyroscope accuracy, the compensation results of the three parameters for gyroscope were presented and compared. The results supported the following conclusions: (1) considering the computation brought from training dataset, the values of 500, 3000, and 3000 were individually sufficient for the three-axis gyroscopes to obtain a reliable and stable prediction performance; (2) among the parameters, the quantization noise, angle random walk, and bias instability performed 0.6%, 6.8%, and 12.5% improvement for X-axis gyroscope, 60.5%, 17.3%, and 34.1% improvement for Y-axis gyroscope, 11.3%, 22.7%, and 35.7% improvement for Z-axis gyroscope, and the corresponding attitude errors decreased by 19.2%, 82.1%, and 69.4%. The results surely demonstrated the effectiveness of the employed SRU in this application. |
| first_indexed | 2024-04-11T12:58:10Z |
| format | Article |
| id | doaj.art-5ec61e882e18411c8db8a5c481de16d1 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T12:58:10Z |
| publishDate | 2018-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-5ec61e882e18411c8db8a5c481de16d12022-12-22T04:23:01ZengMDPI AGSensors1424-82202018-12-011812447110.3390/s18124471s18124471Performance Analysis of a Deep Simple Recurrent Unit Recurrent Neural Network (SRU-RNN) in MEMS Gyroscope De-NoisingChanghui Jiang0Shuai Chen1Yuwei Chen2Yuming Bo3Lin Han4Jun Guo5Ziyi Feng6Hui Zhou7School of Automation, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Automation, Nanjing University of Science and Technology, Nanjing 210094, ChinaCentre of Excellence in Laser Scanning Research, Finnish Geospatial Research Institute (FGI), Geodeetinrinne 2, FI-02431 Kirkkonummi, FinlandSchool of Automation, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Automation, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Automation, Nanjing University of Science and Technology, Nanjing 210094, ChinaCentre of Excellence in Laser Scanning Research, Finnish Geospatial Research Institute (FGI), Geodeetinrinne 2, FI-02431 Kirkkonummi, FinlandElectronic Information School, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaMicroelectromechanical System (MEMS) Inertial Measurement Unit (IMU) is popular in the community for constructing a navigation system, due to its small size and low power consumption. However, limited by the manufacturing technology, MEMS IMU experiences more complicated noises and errors. Thus, noise modeling and suppression is important for improving accuracy of the navigation system based on MEMS IMU. Motivated by this problem, in this paper, a deep learning method was introduced to MEMS gyroscope de-noising. Specifically, a recently popular Recurrent Neural Networks (RNN) variant Simple Recurrent Unit (SRU-RNN) was employed in MEMS gyroscope raw signals de-noising. A MEMS IMU MSI3200 from MT Microsystem Company was employed in the experiments for evaluating the proposed method. Following two problems were furtherly discussed and investigated: (1) the employed SRU with different training data length were compared to explore whether there was trade-off between the training data length and prediction performance; (2) Allan Variance was the most popular MEMS gyroscope analyzing method, and five basic parameters were employed to describe the performance of different grade MEMS gyroscope; among them, quantization noise, angle random walk, and bias instability were the major factors influencing the MEMS gyroscope accuracy, the compensation results of the three parameters for gyroscope were presented and compared. The results supported the following conclusions: (1) considering the computation brought from training dataset, the values of 500, 3000, and 3000 were individually sufficient for the three-axis gyroscopes to obtain a reliable and stable prediction performance; (2) among the parameters, the quantization noise, angle random walk, and bias instability performed 0.6%, 6.8%, and 12.5% improvement for X-axis gyroscope, 60.5%, 17.3%, and 34.1% improvement for Y-axis gyroscope, 11.3%, 22.7%, and 35.7% improvement for Z-axis gyroscope, and the corresponding attitude errors decreased by 19.2%, 82.1%, and 69.4%. The results surely demonstrated the effectiveness of the employed SRU in this application.https://www.mdpi.com/1424-8220/18/12/4471microelectromechanical systemsinertial measurement unitsimple recurrent unitdeep learning |
| spellingShingle | Changhui Jiang Shuai Chen Yuwei Chen Yuming Bo Lin Han Jun Guo Ziyi Feng Hui Zhou Performance Analysis of a Deep Simple Recurrent Unit Recurrent Neural Network (SRU-RNN) in MEMS Gyroscope De-Noising Sensors microelectromechanical systems inertial measurement unit simple recurrent unit deep learning |
| title | Performance Analysis of a Deep Simple Recurrent Unit Recurrent Neural Network (SRU-RNN) in MEMS Gyroscope De-Noising |
| title_full | Performance Analysis of a Deep Simple Recurrent Unit Recurrent Neural Network (SRU-RNN) in MEMS Gyroscope De-Noising |
| title_fullStr | Performance Analysis of a Deep Simple Recurrent Unit Recurrent Neural Network (SRU-RNN) in MEMS Gyroscope De-Noising |
| title_full_unstemmed | Performance Analysis of a Deep Simple Recurrent Unit Recurrent Neural Network (SRU-RNN) in MEMS Gyroscope De-Noising |
| title_short | Performance Analysis of a Deep Simple Recurrent Unit Recurrent Neural Network (SRU-RNN) in MEMS Gyroscope De-Noising |
| title_sort | performance analysis of a deep simple recurrent unit recurrent neural network sru rnn in mems gyroscope de noising |
| topic | microelectromechanical systems inertial measurement unit simple recurrent unit deep learning |
| url | https://www.mdpi.com/1424-8220/18/12/4471 |
| work_keys_str_mv | AT changhuijiang performanceanalysisofadeepsimplerecurrentunitrecurrentneuralnetworksrurnninmemsgyroscopedenoising AT shuaichen performanceanalysisofadeepsimplerecurrentunitrecurrentneuralnetworksrurnninmemsgyroscopedenoising AT yuweichen performanceanalysisofadeepsimplerecurrentunitrecurrentneuralnetworksrurnninmemsgyroscopedenoising AT yumingbo performanceanalysisofadeepsimplerecurrentunitrecurrentneuralnetworksrurnninmemsgyroscopedenoising AT linhan performanceanalysisofadeepsimplerecurrentunitrecurrentneuralnetworksrurnninmemsgyroscopedenoising AT junguo performanceanalysisofadeepsimplerecurrentunitrecurrentneuralnetworksrurnninmemsgyroscopedenoising AT ziyifeng performanceanalysisofadeepsimplerecurrentunitrecurrentneuralnetworksrurnninmemsgyroscopedenoising AT huizhou performanceanalysisofadeepsimplerecurrentunitrecurrentneuralnetworksrurnninmemsgyroscopedenoising |