Abstract
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.
Highlights
Positioning, Navigation and Timing (PNT) information is essential for many applications, for example, smart mobile devices
This paper investigated a deep Simple Recurrent Unit Recurrent Neural Networks (SRU-RNN) based
There was a trade-off between the training data length and the de-noising performance, for the employed Inertial Measurement Unit, 500, 3000, and 3000 was sufficient for learning the model with set 100 training epoch; Among the major three Inertial Measurement Unit errors describing parameters, there was no regular pattern for the compensation degree of the parameters; The three-axis attitude had an improvement of 19.2%, 82.1%, and 69.4%, and which is consistent with the analysis from the three gyroscope signals
Summary
Positioning, Navigation and Timing (PNT) information is essential for many applications, for example, smart mobile devices. SVM and various Neural Networks are employed in MEMS IMU de-noising and they have been evaluated by many researchers [33,34,35,36] For both statistical or AI methods, gyroscope or accelerometer raw signals are treated as time series, and a model is described or learned to compensate the errors caused by the noises. Training data length is fixed and not long enough, it might be meaningful to explore the influence of the training data length on the deep RNN performance; and, Only Standard Deviation of the de-noised signals were presented and compared, but no detailed or further analysis of compensation, which could be a support of selecting proper neural networks for each MEMS IMU. Reminder of this paper is organized as: (1) the second section gives the basic mathematical equations and the information flow of the popular SRU-RNN; (2) the experiments results and comparisons are presented to support the conclusions; (3) final sections include the conclusion, discussion, and reference
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
