Temperature error compensation method for fiber optic gyroscope based on a composite model of k-means, support vector regression and particle swarm optimization

doi:10.23919/JSEE.2025.000023

Journal of Systems Engineering and Electronics ›› 2025, Vol. 36 ›› Issue (2): 510-522.doi: 10.23919/JSEE.2025.000023

• CONTROL THEORY AND APPLICATION • Previous Articles

Temperature error compensation method for fiber optic gyroscope based on a composite model of k-means, support vector regression and particle swarm optimization

Yin CAO¹^,*(), Lijing LI¹(), Sheng LIANG²()

¹ School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing 100191, China
² Key Laboratory of Education Ministry on Luminescence and Optical Information Technology, National Physical Experiment Teaching Demonstration Center, School of Physical Science and Engineering, Beijing Jiaotong University, Beijing 100044, China

Received:2024-02-26 Accepted:2025-02-21 Online:2025-04-18 Published:2025-05-20
Contact: Yin CAO E-mail:yinc0901@buaa.edu.cn;lilijing@buaa.edu.cn;shliang@bjtu.edu.cn
About author:
CAO Yin was born in 1998. She received her M.S. degree in optical engineering from the School of Physical Science and Engineering, Beijing Jiaotong University, Beijing, China, in 2023. She is pursuing her Ph.D. degree in optical engineering at Beihang University, Beijing, China. Her research interests mainly focuses on artificial-intelligence based photoelectric detection. E-mail: yinc0901@buaa.edu.cn

LI Lijing was born in 1974. He received his Ph.D. degree from Tianjin University, Tianjin, China, in 2002. He is currently a professor with the School of Instrumentation and Opto-electronic Engineering, Beihang University, Beijing, China. His research interests include missile guidance and control, photoelectric detection imaging, and fiber sensing. E-mail: lilijing@buaa.edu.cn

LIANG Sheng was born in 1981. He received his Ph.D. degree in precision instrument and machinery from Beihang University, Beijing, China, in 2011. He is a professor with the Department of Physics, School of Science, Beijing Jiaotong University, Beijing, China. His research interest are intelligent photonics including artificial intelligence based fiber-optic sensors, and micro-struct. E-mail: shliang@bjtu.edu.cn
Supported by:
This work was supported by the National Natural Science Foundation of China (62375013).

Abstract

Abstract:

As the core component of inertial navigation systems, fiber optic gyroscope (FOG), with technical advantages such as low power consumption, long lifespan, fast startup speed, and flexible structural design, are widely used in aerospace, unmanned driving, and other fields. However, due to the temperature sensitivity of optical devices, the influence of environmental temperature causes errors in FOG, thereby greatly limiting their output accuracy. This work researches on machine-learning based temperature error compensation techniques for FOG. Specifically, it focuses on compensating for the bias errors generated in the fiber ring due to the Shupe effect. This work proposes a composite model based on k-means clustering, support vector regression, and particle swarm optimization algorithms. And it significantly reduced redundancy within the samples by adopting the interval sequence sample. Moreover, metrics such as root mean square error (RMSE), mean absolute error (MAE), bias stability, and Allan variance, are selected to evaluate the model’s performance and compensation effectiveness. This work effectively enhances the consistency between data and models across different temperature ranges and temperature gradients, improving the bias stability of the FOG from 0.022 °/h to 0.006 °/h. Compared to the existing methods utilizing a single machine learning model, the proposed method increases the bias stability of the compensated FOG from 57.11% to 71.98%, and enhances the suppression of rate ramp noise coefficient from 2.29% to 14.83%. This work improves the accuracy of FOG after compensation, providing theoretical guidance and technical references for sensors error compensation work in other fields.

Key words: fiber optic gyroscope (FOG), temperature error compensation, composite model, machine learning, clustering, regression

Yin CAO, Lijing LI, Sheng LIANG. Temperature error compensation method for fiber optic gyroscope based on a composite model of k-means, support vector regression and particle swarm optimization[J]. Journal of Systems Engineering and Electronics, 2025, 36(2): 510-522.

Figures/Tables 17

Fig 1

Fig 2

Table 1

Fig 3

Fig 4

Fig 5

Fig 6

Fig 7

Table 2

Table 3

Fig 8

Table 4

Table 5

Table 6

Fig 9

Table 7

Fig 10

References 35

1	PATUREL Y, HONTHAAS J, LEFÈVRE H. One nautical mile per month FOG based strapdown inertial navigation system: a dream already within reach? Gyroscopy and Navigation, 2014, 5(1): 1–8.
2	LIU H Q, LUO W, LU J Z High precision fiber-optic gyroscope resolution test method based on low precision turntable. IEEE Sensors Journal, 2020, 20 (15): 8656- 8662. doi: 10.1109/JSEN.2020.2982982
3	PAVLATH G A. Fiber optic gyros: the vision realized. Proceedings of the SPIE, 2006. DOI: 10.1117/12.683457.
4	LOFTS C M, RUFFIN P B, PARKER M D Investigation of the effects of temporal thermal gradients in fiber optic gyroscope sensing coils. Optical Engineering, 1995, 34 (10): 2856- 2863. doi: 10.1117/12.210771
5	FENG T X, ZHANG S Y, WU T, et al Entangled photon-pair source using a wedge-shaped nonlinear crystal. Optical Materials, 2023, 145, 114441. doi: 10.1016/j.optmat.2023.114441
6	CHANG K F, LI Y, WANG W. Numerical study of two-stage temperature control strategy for high temperature stability of satellite-borne fiber optic gyroscope. Journal of Electronic Packaging, 2023, 145(3): 031011.
7	BLIN S, KIM H K, DIGONNET M J F Reduced thermal sensitivity of a fiber-optic gyroscope using an air-core photonic-bandgap fiber. Journal of Lightwave Technology, 2007, 25 (3): 861- 865. doi: 10.1109/JLT.2006.889658
8	BLIN S, DIGONNET M J F, KINO G S Noise analysis of an air-core fiber optic gyroscope. IEEE Photonics Technology Letters, 2007, 19 (19): 1520- 1522. doi: 10.1109/LPT.2007.903878
9	HUANG C F, LI A, QIN F J, et al. Temperature error compensation method for fiber optic gyroscope considering heat transfer delay. Proc. of the 3rd International Conference on Electronic Information Technology and Computer Engineering, 2019: 1061−1067.
10	WANG X W, CUI Y, CAO H L Temperature drift compensation of fiber optic gyroscopes based on an improved method. Micromachines, 2023, 14 (9): 1712- 1730. doi: 10.3390/mi14091712
11	TIAN L L, NIU Y X, HUANG C W, et al A novel temperature-compensation method based oncorrelation analysis for multi-FOG INS. Chinese Journal of Aeronautics, 2023, 36 (6): 279- 287. doi: 10.1016/j.cja.2023.02.009
12	GONTAR D A, DRANITSYNA E V. Improving the efficiency of fiber-optic gyrotemperature sensitivity compensation. Proc. of the 29th Saint Petersburg International Conference on Integrated Navigation Systems, 2022. DOI: 10.23919/ICINS51784.2022.9815434.
13	CAI W, WANG J Y, HAO W H, et al. RBF neural network-based temperature error compensation for fiber optic gyroscopes. Proc. of the International Conference in Communications, Signal Processing, and Systems, 2020: 1627−1635.
14	XU J T, TIAN A L, LIU H, et al Modeling and prediction of thermal deformation errors in fiber optic gyroscopes based on the TD-model. Sensors, 2023, 23 (23): 9450- 9464. doi: 10.3390/s23239450
15	WANG W, CHEN X Y. Temperature drift modeling and compensation of fiber optical gyroscope based on improved support vector machine and particle swarm optimization algorithms. Applied Optics, 2016, 55(23): 6243−6250.
16	LIU J G, CHEN X Y Temperature drift compensation of a FOG based on an HKSVM optimized by an improved hybrid BAS-GSA algorithm. Applied Optics, 2021, 60 (34): 10539- 10547. doi: 10.1364/AO.440887
17	MAO N, XU J N, LI J S, et al. A LSTM-RNN-based fiber optic gyroscope drift compensation. Mathematical Problems in Engineering, 2021, 32: 1636001.
18	ZHAO X X, CHEN G, LIU H, et al A multivariate temperature drift modeling and compensation method for large-diameter high-precision fiber optic gyroscopes. IEEE Trans. on Instrumentation and Measurement, 2022, 71, 8502912.
19	WANG G C, WANG Q Y, ZHAO B, et al Compensation method for temperature error of fiber optical gyroscope based on relevance vector machine. Applied Optics, 2016, 55 (5): 1061- 1066. doi: 10.1364/AO.55.001061
20	ZHENG B D, LIU W, LV M, et al. Segmental compensation of FOG temperature error based on ELM prediction model. Proc. of the 33rd Chinese Control and Decision Conference, 2021: 6286−6290.
21	FU J, JIANG S, QIN F J, et al. Novel piecewise compensation method for FOG temperature error. Journal of Chinese Inertial Technology, 2016, 24(2): 242−244.
22	CAO Y, XU W Y, LIN B, et al A method for temperature error compensation in fiber-optic gyroscope based on machine learning. Optik, 2022, 256, 168765. doi: 10.1016/j.ijleo.2022.168765
23	CAO Y, XU W Y, LIN B, et al Long short-term memory network of machine learning for compensating temperature error of a fiber optic gyroscope independent of the temperature sensor. Applied Optics, 2022, 61 (28): 8212- 8222. doi: 10.1364/AO.471762
24	POST E J Sagnac effect. Reviews of Modern Physics, 1967, 39 (2): 475- 494. doi: 10.1103/RevModPhys.39.475
25	SHUPE D M Thermally induced nonreciprocity in the fiber optic interferometers. Applied Optics, 1980, 19 (5): 654- 655. doi: 10.1364/AO.19.000654
26	HARTIGAN J A, WONG M A Algorithm AS 136: a k-means clustering algorithm. Journal of the royal statistical society, Series C (applied statistics), 1979, 28 (1): 100- 108.
27	SINAGA K P, YANG M S Unsupervised K-means clustering algorithm. IEEE Access, 2020, 8, 80716- 80727. doi: 10.1109/ACCESS.2020.2988796
28	ZHANG L Research on K-means clustering algorithm based on MapReduce distributed programming framework. Procedia Computer Science, 2023, 228, 262- 270. doi: 10.1016/j.procs.2023.11.030
29	KE T, LIAO Y Y, WU M Y, et al Maximal margin hyper-sphere SVM for binary pattern classification. Engineering Applications of Artificial Intelligence, 2023, 117, 105615. doi: 10.1016/j.engappai.2022.105615
30	TRAN T N A new grid search algorithm based on median values for SVR model in case of load forecasting. Periodica Polytechnica Electrical Engineering and Computer Science, 2023, 67 (1): 51- 60. doi: 10.3311/PPee.20887
31	KENNEDY J, EBERHART R. Particle swarm optimization. Proc. of the IEEE International Conference on Neural Networks, 1995: 1942−1948.
32	PARSOPOULOS K E, VRAHATIS M N Unified particle swarm optimization for solving constrained engineering optimization problems. Lecture Notes in Computer Science, 2005, 3612, 582.
33	IEEE B E. IEEE draft standard specification format guide and test procedure for single-axis interferometric fiber optic gyros. IEEE P952/D07, New York, USA: 1998.
34	WANG L, ZHANG C X, LIN T, et al Characterization of a fiber optic gyroscope in a measurement while drilling system with the dynamic Allan variance. Measurement, 2015, 75, 263- 272. doi: 10.1016/j.measurement.2015.05.001
35	SONG R, CHEN X Y, HUANG H Q Nonstationary dynamic stochastic error analysis of fiber optic gyroscope based on optimized Allan variance. Sensors and Actuators A: Physical, 2018, 276, 26- 33. doi: 10.1016/j.sna.2018.04.002

Stage number	Experiment 1		Experiment 2		Experiment 3
Stage number	Variation rate/(℃/h)	Time/ h	Variation rate/(℃/h)	Time/ h	Variation rate/(℃/h)	Time/ h
0	Room T to −40 ℃	1	Room T to −40 ℃	1	Room T to −40 ℃	1
1	+50	1	+50	1	50	1
2	+25	2	−35	1	35	1
3	−25	2	+40	1	15	1
4	−50	1	−15	1	50	1
5	Powered off and return to room T	−	+35	1	35	1
6	−		−10	1	15	1
7	−	−	+35	1	Powered off and return to room T	−
8	−	−	Powered off and return to room T	−	−	−

k	SC	CH
k=2	0.3594	13581
k=3	0.4851	29017
k=4	0.4590	26546

Parameter	Value
Particle number	20
Iteration number	30
Dim	2
Position upper limit	(0.001, 2.0)
Position lower limit	(0.0001, 0.5)
Velocity upper limit	(0.00002, 0.01)
Velocity lower limit	(−0.00002, −0.01)
pBest learning factor	1.5
gBest learning factor	1.5

Model	Gamma	C
Model 1	0.00096414	0.80758310
Model 2	0.00054646	1.07708036
Model 3	0.00033551	1.57668264

Method	RMSE	MAE
OS+SVR	1.0662	0.8643
OS+ k-means-SVR-PSO	0.8758	0.6794
IS+SVR	0.7795	0.6087
IS+ k-means-SVR-PSO	0.6490	0.5173

Temperature error compensation method for fiber optic gyroscope based on a composite model of k-means, support vector regression and particle swarm optimization

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 17

References 35

Related Articles 15

Recommended Articles

Metrics

Comments

Method	B_s/((°)/h)	I_B/%
Before compensation	0.022168	−
OS+SVR	0.009508	57.11
OS+ k-means-SVR-PSO	0.008749	60.53
IS+SVR	0.007664	65.43
IS+ k-means-SVR-PSO	0.006212	71.98

Noise source	Before compensation	OS+SVR		IS+ k-means-SVR-PSO
Noise source	Before compensation	After compensation	Noise suppression/%	After compensation	Noise suppression/%
Q/(°)	4.4527×10⁻⁶	3.3603×10⁻⁶	24.53	2.8883×10⁻⁶	35.13
N_A/((°)/h^1/2)	1.6570×10⁻³	1.4936×10⁻³	9.86	1.3726×10⁻³	17.16
B/((°)/h)	2.1041×10⁻²	1.5849×10⁻²	24.68	1.2701×10⁻²	39.64
K_R/((°)/h^3/2)	5.1614×10⁻²	3.7022×10⁻²	28.27	2.8217×10⁻²	45.33
R/((°)/h²)	3.0961×10⁻²	3.0248×10⁻²	2.29	2.6378×10⁻²	14.83

[1]	Yu JIN, Xucheng WANG, Yunlang XU, Jianbo YU, Qiaodan LU, Xiaofeng YANG. Hysteresis modeling and compensation of piezo actuator with sparse regression [J]. Journal of Systems Engineering and Electronics, 2025, 36(1): 48-61.
[2]	Heyu CHEN, Xuexin QIN, Huan XIE, Linghai KONG, Yue ZHENG. Vibration-induced bias error reduction using loop gain compensation for high-precision fiber optic gyroscopes [J]. Journal of Systems Engineering and Electronics, 2025, 36(1): 224-232.
[3]	Jian WANG, Jingyi ZHU, Hua SHI, Huchen LIU. New density clustering-based approach for failure mode and effect analysis considering opinion evolution and bounded confidence [J]. Journal of Systems Engineering and Electronics, 2024, 35(6): 1491-1506.
[4]	Yu LU, Jiongqi WANG, Zhangming HE, Haiyin ZHOU, Yao XING, Xuanying ZHOU. System error iterative identification for underwater positioning based on spectral clustering [J]. Journal of Systems Engineering and Electronics, 2024, 35(4): 1028-1041.
[5]	Youliang LIN, Wu LI, Gang LIU, Dong HUANG. Method for triangular fuzzy multiple attribute decision making based on two-dimensional density operator method [J]. Journal of Systems Engineering and Electronics, 2024, 35(1): 178-185.
[6]	Sheng TONG, Hong QU, Junjie XUE. K-DSA for the multiple traveling salesman problem [J]. Journal of Systems Engineering and Electronics, 2023, 34(6): 1614-1625.
[7]	Chi HAN, Wei XIONG, Minghui XIONG, Zhen LIU. Support vector regression-based operational effectiveness evaluation approach to reconnaissance satellite system [J]. Journal of Systems Engineering and Electronics, 2023, 34(6): 1626-1644.
[8]	Lei XIE, Shangqin TANG, Zhenglei WEI, Yongbo XUAN, Xiaofei WANG. UCAV situation assessment method based on C-LSHADE-Means and SAE-LVQ [J]. Journal of Systems Engineering and Electronics, 2023, 34(5): 1235-1251.
[9]	Fuyunxiang YANG, Leping YANG, Yanwei ZHU. An AutoML based trajectory optimization method for long-distance spacecraft pursuit-evasion game [J]. Journal of Systems Engineering and Electronics, 2023, 34(3): 754-765.
[10]	Fengfei WANG, Shengjin TANG, Liang LI, Xiaoyan SUN, Chuanqiang YU, Xiaosheng SI. Remaining useful life prediction of aero-engines based on random-coefficient regression model considering random failure threshold [J]. Journal of Systems Engineering and Electronics, 2023, 34(2): 530-542.
[11]	Fengfei WANG, Shengjin TANG, Xiaoyan SUN, Liang LI, Chuanqiang YU, Xiaosheng SI. Remaining useful life prediction based on nonlinear random coefficient regression model with fusing failure time data [J]. Journal of Systems Engineering and Electronics, 2023, 34(1): 247-258.
[12]	Xu LYU, Baiqing HU, Yongbin DAI, Mingfang SUN, Yi LIU, Duanyang GAO. Gaussian process regression-based quaternion unscented Kalman robust filter for integrated SINS/GNSS [J]. Journal of Systems Engineering and Electronics, 2022, 33(5): 1079-1088.
[13]	Yuan ZENG, Wenbin LU, Bo YU, Shifei TAO, Haosu ZHOU, Yu CHEN. Improved IMM algorithm based on support vector regression for UAV tracking [J]. Journal of Systems Engineering and Electronics, 2022, 33(4): 867-876.
[14]	Hao FENG, Jianzhong WU, Lu ZHANG, Mingsheng LIAO. Unsupervised change detection of man-made objects using coherent and incoherent features of multi-temporal SAR images [J]. Journal of Systems Engineering and Electronics, 2022, 33(4): 896-906.
[15]	Jinfeng LYU, Fucai LIU, Yaxue REN. Fuzzy identification of nonlinear dynamic system based on selection of important input variables [J]. Journal of Systems Engineering and Electronics, 2022, 33(3): 737-747.