Abstract
Nonlinear errors of sensor output signals are common in the field of inertial measurement and can be compensated with statistical models or machine learning models. Machine learning solutions with large computational complexity are generally offline or implemented on additional hardware platforms, which are difficult to meet the high integration requirements of microelectromechanical system inertial sensors. This paper explored the feasibility of an online compensation scheme based on neural networks. In the designed solution, a simplified small-scale network is used for modeling, and the peak-to-peak value and standard deviation of the error after compensation are reduced to 17.00% and 16.95%, respectively. Additionally, a compensation circuit is designed based on the simplified modeling scheme. The results show that the circuit compensation effect is consistent with the results of the algorithm experiment. Under SMIC 180 nm complementary metal-oxide semiconductor (CMOS) technology, the circuit has a maximum operating frequency of 96 MHz and an area of 0.19 mm2. When the sampling signal frequency is 800 kHz, the power consumption is only 1.12 mW. This circuit can be used as a component of the measurement and control system on chip (SoC), which meets real-time application scenarios with low power consumption requirements.
Highlights
Microelectromechanical system (MEMS) inertial sensors, such as gyroscopes, acceleration meters, angular position sensors (APS), are manufactured by the MEMS process.MEMS inertial sensors have the characteristics of small size, low cost, and low power consumption, and are widely used in the fields of aerospace, intelligent robots, vehicles, mobile equipment, etc. [1,2]
The computational complexity of the error compensation scheme based on neural networks is large, which is a challenge for real-time online applications
17.00% and static timing analysis in Primetime were performed at three process corners—slow process designed circuit implemented under the SMIC 180 nm com(SS),The typical process (TT), isand fast processand (FF).analyzed
Summary
Microelectromechanical system (MEMS) inertial sensors, such as gyroscopes, acceleration meters, angular position sensors (APS), are manufactured by the MEMS process. The accuracy improvement of statistical methods requires accurate analysis and modeling of error components, while another research idea is to obtain model structure and model parameters with machine learning schemes. By training the collected data, the model parameters are calculated, and the error compensation results on the test dataset can have better accuracy improvement than statistical models These methods obtain the network structure through the learned parameter values, reducing the requirements for accurate modeling. One solution is to analyze and design a simplified network model through model complexity analysis and optimization [24] Another solution is to refer to artificial intelligence chips [27] widely used in neural network acceleration, performing circuit-level parallel processing solutions to solve real-time problems.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
