Feng Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Feng Liu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
Hua Wang
3 shared publicationsQingli Shi
2 shared publicationsFeng Cheng
1 shared publicationHailong Zhao
System Design Institute of Hubei Aerospace Technology Academy, Hubei, China
1 shared publication- Hao Cheng
Beihang University
1 shared publication Hengxian Wang
Department of School of Astronautics, Beihang University, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 5 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 5, 12951-12962
Comparison of an ANFIS and Fuzzy PID Control Model for Performance in a Two-Axis Inertial Stabilized Platform
An adaptive neuro-fuzzy inference system (ANFIS) of soft computing is an effective method for predicting performance. An statistical analysis and soft computing scheme based on the ANFIS neuro-fuzzy proportional-integral-differential (ANFP) control is proposed to predict the performance of a fuzzy PID controller for a two-axis inertially stabilized platform system. The data are extracted from an unconventional fuzzy PID stabilization controller output of the closed loop, and the model is trained using the Levenberg–Marquardt (LM) training algorithm and compared according to the experimental data from the output results of the ANFP controller. The comparative simulations are expatiated by the statistical values of the mean squared error (MSE) and the coefficient of determination (R) as performance indicators. The experimental results validate that the ANFP soft computing approach contributes to the indispensable improvement for predicting performance in accordance with the error analysis results.
- 5 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 5, 12951-12962
Open AccessComparison of an ANFIS and Fuzzy PID Control Model for Performance in a Two-Axis Inertial Stabilized Platform
An adaptive neuro-fuzzy inference system (ANFIS) of soft computing is an effective method for predicting performance. An statistical analysis and soft computing scheme based on the ANFIS neuro-fuzzy proportional-integral-differential (ANFP) control is proposed to predict the performance of a fuzzy PID controller for a two-axis inertially stabilized platform system. The data are extracted from an unconventional fuzzy PID stabilization controller output of the closed loop, and the model is trained using the Levenberg–Marquardt (LM) training algorithm and compared according to the experimental data from the output results of the ANFP controller. The comparative simulations are expatiated by the statistical values of the mean squared error (MSE) and the coefficient of determination (R) as performance indicators. The experimental results validate that the ANFP soft computing approach contributes to the indispensable improvement for predicting performance in accordance with the error analysis results.
- Open Access
- 25 July 2016
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2016, 1-9
The Effects of Matched Filter on Stable Performance of Semistrapdown Inertially Stabilized Platform
To enhance the optimization performance of matched filter and further improve line of sight (LOS) stability of platform in inertial space, the proposed matched filter algorithm is conducted by adjusting matched filter coefficients of first-order low pass filter utilizing the regional search method based on invariance principle. The coefficients of the fraction molecule and denominator of proposed regional search algorithm are altered instead of denominator coefficients only being modified. Simulations are performed to verify the validity of inside factors performed with stabilization control model and quartz rate sensor (QRS) mathematical model. The stable angular error is sharply alleviated, so the decoupling accuracy of airborne semistrapdown inertially stabilized platform is largely promoted. The optimization matched filter can effectively increase stability of LOS in inertial space.
- 25 July 2016
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2016, 1-9
Open AccessThe Effects of Matched Filter on Stable Performance of Semistrapdown Inertially Stabilized Platform
To enhance the optimization performance of matched filter and further improve line of sight (LOS) stability of platform in inertial space, the proposed matched filter algorithm is conducted by adjusting matched filter coefficients of first-order low pass filter utilizing the regional search method based on invariance principle. The coefficients of the fraction molecule and denominator of proposed regional search algorithm are altered instead of denominator coefficients only being modified. Simulations are performed to verify the validity of inside factors performed with stabilization control model and quartz rate sensor (QRS) mathematical model. The stable angular error is sharply alleviated, so the decoupling accuracy of airborne semistrapdown inertially stabilized platform is largely promoted. The optimization matched filter can effectively increase stability of LOS in inertial space.