Algoritma Hibrid Extended Kalman Filter dan Inferensi Fuzzy untuk Penjejakan Target Bermanuver

Ifan Wiranto, Wrastawa Ridwan, Yuliyanti Kadir

Abstract


Pada penelitian ini dikembangkan algoritma hibrid Extended Kalman Filter (EKF) dan Sistem Inferensi Fuzzy untuk mendapatkan hasil estimasi yang lebih akurat pada penjejakan target bermanuver. Logika Fuzzy telah digunakan untuk mengatur galat kovarian proses dan galat kovarian pengukuran dari proses EKF pada model sistem. Model state space yang digunakan untuk estimasi adalah model percepatan konstan, dan model pengukurannya adalah model radar. Hasil pengukuran sensor yang mengandung derau diestimasi menggunakan algoritma EKF. Kemudian galat kovarian yang dihasilkan dari proses EKF digunakan sebagai masukan pada Sistem Inferensi Fuzzy untuk koreksi berdasarkan ketidaksesuaian antara vektor inovasi dan kovarian inovasi. Hasil koreksi ini digunakan untuk mendapatkan gain Kalman yang optimal. Berdasarkan simulasi yang dilakukan menggunakan estimasi EKF dan Sistem Inferensi Fuzzy diperoleh peningkatan akurasi sebesar 59,97% dibandingkan dengan hasil pengukuran tanpa melakukan estimasi.

In this paper the Extended Kalman Filter and the Fuzzy Inference System hybrid algorithm has developed to get more accurate estimation result for maneuvering target tracking. Fuzzy Logic has used to adjust the process covariance error and measurement covariance error of the Extended Kalman Filter process in the system model. The state space model used for estimation is a constant acceleration motion model, and the measurement model is a radar model. The measurement result of the sensor containing noise estimated using the Extended Kalman Filter (EKF) algorithm. Then, the covariance error resulting from the EKF process is used as input to the Fuzzy Inference System (FIS) for correction based on the mismatch between innovation vector and innovation covariance. The result of this correction used to obtain the optimal Kalman gain. The proposed system model leads to improved accuracy of 59.97% compared to measurement results without estimation in the simulation case.

 


Keywords


Sistem Taklinier; Extended Kalman Filter; Inferensi Fuzzy

Full Text:

PDF

References


Wiranto, I., Bonok, Z., (2018), Application of Ant System and Nearest Neighbor Kalman Filter for Multi Target Tracking in Multi Sensor Radar System, ARPN Journal of Engineering and Applied Sciences, Vol. 13, No. 15, August 2018.

Liu, H., Xia, L., Wang, C.,(2019), Manuevering Target Tracking Using Simultaneous Optimization and Feedback Learning Algorithm Based on Elman Neural Network, Sensors, MPDI Open Access Journal

Li, X.L., Jilkov, V.P.,(2003), Survey of Maneuvering Target Tracking. Part I Dynamic Model. IEEE Trans. Aerosp. Electron. Syst., 2003, 39, 1333-1364

Yang S., Baum, M.,(2017), Extended Kalman Filter for Extended Object Tracking, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing.

Rao, S., Rajeswari, K., Lingamurty, K.,(2009), Unscented Kalman Filter with Application to Bearings- Only Target Tracking, IETE Journal of Research, vol. 55, no. 2

Sarkka, S., (2013), Bayesian Filtering and Smoothing, Cambridge University Press, Cambridge, UK

Stubberub, S.C., Member, S., Kramer, K.A., Geremia, J.A., (2007), Online Sensor Modeling Using a Neural Kalman Filter, IEEE Trans. Instrum. Meas. 2007, 56, 1451-1458

Duh, F.B., Lin, C.T., (2004): Tracking a Maneuvering Target Using Neural Fuzzy Network, IEEE Trans. Syst. Man Cybern. Part B Cybern., 2004, 34, 16-33.

Joelianto, E., Wiranto, I., (2011), An Application of Ant Colony Optimization, Kalman Filter and Artificial Neural Network for Multiple Target Tracking Problems. International Journal of Artificial Intelligence, Vol. 7, number A11.

Wiranto, I., Ridwan, W., (2021), Maneuvering Target Tracking With Constant Acceleration Motion Model Using Hybrid Mamdani Fuzzy-Kalman Filter Algorithm, ARPN Journal of Engineering and Applied Sciences. 16(2)

Torrubia, G.S., Blanc, C.T., (2010), A Mamdani-Type Fuzzy Inference System to Automatically Assess Dijkstra’s Algorithm Simulation. International Journal “information Theories and Applications”, Vol. 17, number 1.

Ridwan, W., Wiranto, I., & Dako, R.D.R., (2020), Ability estimation in computerized adaptive test using Mamdani Fuzzy Inference System, IOP Conf. Ser.: Mater. Sci. Eng. 850 012004

Ridwan, W., Wiranto, I., & Dako, R.D.R., (2021), Computerized Adaptive Test based on Sugeno Fuzzy Inference System, IOP Conf. Ser.: Mater. Sci. Eng. 1098 032077

Kusumadewi, S., & Purnomo, H.,(2013), Aplikasi Logika Fuzzy untuk Pendukung Keputusan, Penerbit Graha Ilmu, Yogyakarta

Escamilla-Ambrosio P.J., Mort N., (2001), Development a Fuzzy Logic-based Adaptive Kalman Filter, 2001 European Control Conference (ECC).

Wei Z., (2011), Fuzzy Logic and Neural Network-Aided Extended Kalman Filter for Mobile Robot Localization, The University of Guelph, Thesis




DOI: https://doi.org/10.37905/jjeee.v4i2.14121

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Published by:
Electrical Engineering Department
Faculty of Engineering
State University of Gorontalo
Jenderal Sudirman Street No.6, Gorontalo City, Gorontalo Province, Indonesia
Telp. 0435-821175; 081340032063
Email: redaksijjeee@ung.ac.id/redaksijjeee@gmail.com

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.