Identification Method of SINS Error Parameters Utilizing Artificial Neural Network for Hypersonic Vehicle

Guo, Weilin; Yu, Xiaoquan; Zhang, Daqiao; Wang, Zhaoqiang

doi:10.1109/access.2019.2953175

Cited by 3 publications

(3 citation statements)

References 12 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in equations ( 8) to (10), the relationship between the angular increments ∆θ xb , ∆θ yb , and ∆θ zb and the attitudes φ, ψ, and γ is nonlinear [27]. Therefore, the activation function f b2 of the output layer is also a nonlinear function.…”

Section: Qnswnn Error Signal Back Propagationmentioning

confidence: 99%

“…The main research content of these ANN methods is to predict the navigation parameters without estimating the inertial measurement unit (IMU) error parameters. However, the estimation of IMU error parameters has significance for improving the independent flight capability of the hypersonic vehicle and the ability to adapt to a complex battlefield environment [27]. The ANN method is used to identify the SINS error parameters of the hypersonic vehicle, which is an offline training and online prediction neural network method [27].…”

Section: Introductionmentioning

confidence: 99%

“…However, the estimation of IMU error parameters has significance for improving the independent flight capability of the hypersonic vehicle and the ability to adapt to a complex battlefield environment [27]. The ANN method is used to identify the SINS error parameters of the hypersonic vehicle, which is an offline training and online prediction neural network method [27]. However, the parameter estimation accuracy needs to be further improved.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A new IMU error parameter estimation method for hypersonic vehicle based on hybrid neural network

Guo¹,

Yu²,

Chang³

et al. 2020

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

To realize the effective estimation of the inertial measurement unit (IMU) error parameters of a hypersonic vehicle and satisfy the high-precision navigation requirements, a hybrid neural network (HYNN) method that consists of a quasi-Newton semi-determined weight neural network (QNSWNN) and a semi-determined weight recurrent neural network (SWRNN) is proposed. In contrast to conventional neural networks, the weights of the HYNN model, which are determined by the IMU error parameters, have physical meanings. First, the IMU error model and strap-down inertial navigation system (SINS) navigation model are established. Second, the QNSWNN model is constructed based on the SINS/celestial navigation system (CNS) integrated navigation system information. The quasi-Newton is used to adjust the weights, which include the gyroscope error. The rest weights of QNSWNN are fixed based on a SINS attitude calculation model. The gyroscope error parameters can be estimated during the QNSWNN training process. Lastly, the SWRNN model is constructed based on the SINS/GPS integrated navigation system information. The BP algorithm is used to adjust the weights, which include the accelerometer error. The rest weights of SWRNN are fixed based on the SINS navigation calculation model. The accelerometer error parameters can be estimated during the SWRNN training process. The simulation results show that the IMU error parameter can be effectively estimated by the HYNN, and the relative errors are below 25%. Moreover, when the signal of the auxiliary navigation system is interrupted, the HYNN method still has high prediction accuracy for the SINS navigation parameters.

show abstract

Section: Qnswnn Error Signal Back Propagationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A new IMU error parameter estimation method for hypersonic vehicle based on hybrid neural network

Guo¹,

Yu²,

Chang³

et al. 2020

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

Research on dual-threshold detection based adaptive fault-tolerant kalman filtering algorithm for dynamic 6-DOF measurement

Xin,

Lin,

Shi

et al. 2024

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

Flexible joint parameters identification method based on improved tracking differentiator and adaptive differential evolution

Song

Yang

et al. 2022

Review of Scientific Instruments

View full text Add to dashboard Cite

The assembly error of flexible joints and the change in joint stiffness during movement make the actual value of joint parameters inconsistent with the given value, which affects the joint control accuracy. In order to suppress the influence of parameters error, a parameters identification method for flexible joint combined offline identification and online compensation is proposed. First, the offline identification model of inertia, mass, and damping and the online identification model of joint stiffness are established, respectively. Then, a hybrid tracking differentiator based on an improved Sigmoid function is designed to track the differential signals of joint motion parameters, and the Lyapunov function is designed to prove its convergence. The adaptive differential evolution is used as the identification algorithm, and the improved adaptive crossover, mutation factor, and Metropolis acceptance criterion are designed to improve the convergence speed. Finally, a feedforward control structure based on identification is designed to compensate for the model deviation. Simulation and experimental results show that the improved differentiator can effectively improve the tracking speed and derivation accuracy of the signals. Compared with other algorithms, the proposed identification method has a faster convergence speed and higher identification accuracy, and feedforward compensation control can effectively correct model parameters and improve control accuracy.

show abstract

Identification Method of SINS Error Parameters Utilizing Artificial Neural Network for Hypersonic Vehicle

Cited by 3 publications

References 12 publications

A new IMU error parameter estimation method for hypersonic vehicle based on hybrid neural network

A new IMU error parameter estimation method for hypersonic vehicle based on hybrid neural network

Research on dual-threshold detection based adaptive fault-tolerant kalman filtering algorithm for dynamic 6-DOF measurement

Flexible joint parameters identification method based on improved tracking differentiator and adaptive differential evolution

Contact Info

Product

Resources

About