Real-Time Temperature Drift Compensation Method of a MEMS Accelerometer Based on Deep GRU and Optimized Monarch Butterfly Algorithm

Abstract

In recent years, inertial sensors based on Micro-Electro-Mechanical Systems (MEMS) have become increasingly popular. They have been widely used in various fields due to their low cost, small size, and low power consumption. It seems that MEMS inertial sensors may eventually fully occupy the middle to lower end inertial navigation application market that traditional inertial sensors previously occupied. To realize the full potential of MEMS inertial sensors, one of the critical issues is their temperature drift. This paper first proposed a recursive model for real-time compensation. Then three algorithms were proposed, including a two-layer deep gated recurrent unit recurrent neural network (GRU-RNN, short GRU), deep GRU based on monarch butterfly algorithm (MBA), and deep GRU based on optimized monarch butterfly algorithm (OMBA). Each of these three algorithms is combined with the real-time compensation model to compensate for the temperature drift of a MEMS accelerometer. The experimental results proved the correctness of these three methods, and the MEMS accelerometer's temperature drift is compensated effectively. The results indicate that the deep GRU + OMBA shows the best performance for the temperature drift compensation combined with the real-time compensation model. After deep GRU + OMBA method compensation, the angle random walk, the bias instability, the rate random walk, and rate ramp of the MEMS accelerometer were improved from 4.97e −4 mg • s 1 2 , 4.90e −4 mg, 5.57e −5 mg/s 1 2 , 1.82e −6 mg /s to 3.90e −5 mg •s 1 2 , 1.07e −5 mg, 1.12e −6 mg/s 1 2 , 3.59e −8 mg /s, respectively. Their percentage of improvement reaches 96.50% on average. INDEX TERMSDeep GRU, MEMS accelerometer, real-time compensation, OMBA, temperature drift.

A Temperature Compensation Approach for Micro-Electro-Mechanical Systems Accelerometer Based on Gated Recurrent Unit–Attention and Robust Local Mean Decomposition–Sample Entropy–Time-Frequency Peak Filtering

“…Our algorithm achieved a greater reduction in random walking compared to Zhu et al [9] RBF NN + GA + KF method (96.11% reduction versus 95.53% reduction), as well as compared to Guo et al [37] DLSTM, RNN, and ISSA method (without denoising decomposition algorithm) (96.11% reduction versus 57.40% reduction), and Gang et al [38] GRU, RNN, short GRU, and optimized monarch butterfly method (96.11% reduction versus 92.15% reduction). This indicates that our method provides superior accuracy in reducing acceleration random walking.…”

A Multi-Objective Improved Hybrid Butterfly Artificial Gorilla Troop Optimizer for Node Localization in Wireless Sensor Groundwater Monitoring Networks

“…Figure 6 shows a comparison of various algorithms in terms of average error. At the beginning iterations (10)(11)(12)(13)(14)(15)(16)(17)(18)(19)(20), the ARO and HGS algorithms have higher average errors than the others, whereas the proposed iHBAGTO algorithm has the lowest average error. As the number of iterations increases, the average error decreases for all algorithms, but the iHBAGTO algorithm consistently outperforms the others with the lowest average error.…”

“…The minimum hop value between i and j is represented by hi, j. The hop size is the hop size from anchor node i to its neighbors, and it is broadcasted by node i using controlled flooding throughout the network [18]. The value of hu, i represents the number of hops between anchor node i and the unlocalized node u.…”