In order to improve the performance of a micro-electro-mechanical system (MEMS) accelerometer, three algorithms for compensating its temperature drift are proposed in this paper, including deep long short-term memory recurrent neural network (DLSTM-RNN, short DLSTM), DLSTM based on sparrow search algorithm (SSA), and DLSTM based on improved SSA (ISSA). Moreover, the piecewise linear approximation (PLA) method is employed in this paper as a comparison to evaluate the impact of the proposed algorithm. First, a temperature experiment is performed to obtain the MEMS accelerometer’s temperature drift output (TDO). Then, we propose a real-time compensation model and a linear approximation model for neural network methods compensation and PLA method compensation, respectively. The real-time compensation model is a recursive method based on the TDO at the last moment. The linear approximation model considers the MEMS accelerometer’s temperature and TDO as input and output, respectively. Next, the TDO is analyzed and optimized by the real-time compensation model and the three algorithms mentioned before. Moreover, the TDO is also compensated by the linear approximation model and PLA method as a comparison. The compensation results show that the three neural network methods and the PLA method effectively compensate for the temperature drift of the MEMS accelerometer, and the DLSTM + ISSA method achieves the best compensation effect. After compensation by DLSTM + ISSA, the three Allen variance coefficients of the MEMS accelerometer that bias instability, rate random walk, and rate ramp are improved from 5.43×10−4mg, 4.33×10−5mg/s12, 1.18×10−6mg/s to 2.77×10−5mg, 1.14×10−6mg/s12, 2.63×10−8mg/s, respectively, with an increase of 96.68% on average.

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.