Dynamic Compensation of Tunable Filter Demodulation Error Based on Least Squares Support Vector Machine and Multi-Reference Gratings

Wenjuan Sheng; Haitao Lou; Gangding Peng

doi:10.3788/AOS221651

Acta Optica Sinica, Volume. 43, Issue 7, 0706003(2023)

Dynamic Compensation of Tunable Filter Demodulation Error Based on Least Squares Support Vector Machine and Multi-Reference Gratings

Wenjuan Sheng^1、*, Haitao Lou¹, and Gangding Peng²

Author Affiliations

¹College of Automation Engineering, Shanghai University of Electric Power, Shanghai 200090, China

²College of Electrical Engineering and Telecommunications, The University of New South Wales, Sydney 2052, New South Wales, Australia

show less

Abstract Get PDF(in Chinese)

Figures & Tables(15)

Fig. 1. Schematic diagram of dynamic modeling and compensation

Download full size

Fig. 2. Schematic diagram of FBG demodulation system

Download full size

Fig. 3. Principle of centroid detection algorithm

Download full size

Fig. 4. Temperature trend of reference grating in cooling mode

Download full size

Fig. 5. Compensation result of dynamic model in cooling mode. (a) Absolute wavelength drift; (b) prediction error

Download full size

Fig. 6. Temperature trend of reference grating in cooling-heating mode

Download full size

Fig. 7. Compensation result of dynamic model in cooling-heating mode. (a) Absolute wavelength drift; (b) prediction error

Download full size

Fig. 8. Compensation result of dynamic model in cooling mode (n=0, n=1). (a) Absolute wavelength drift; (b) prediction error

Download full size

Fig. 9. Compensation result of dynamic model in cooling mode (n=2, n=3). (a) Absolute wavelength drift; (b) prediction error

Download full size

Fig. 10. Compensation result of dynamic model in cooling-heating mode (n=0, n=1). (a) Absolute wavelength drift; (b) prediction error

Download full size

Fig. 11. Compensation result of dynamic model in cooling-heating mode (n=2, n=3). (a) Absolute wavelength drift; (b) prediction error

Download full size

Table 1. Characteristic wavelengths of FBG
View table
Table 1. Characteristic wavelengths of FBG
FBG No. 0 1 2 3
Wavelength /nm 1528.8393 1541.0621 1557.3460 1562.1832

Table 2. Influence of location of FBG3 on model performance

View table

Table 2. Influence of location of FBG3 on model performance

n	S	Cooling			Cooling-heating
n	S	MAXE /pm	RMSE /pm	CPU time /ms	MAXE /pm	RMSE /pm	CPU time /ms
0	0	39.12	14.94	181	77.02	58.17	179
1	FBG0	33.50	15.50	179	41.70	25.33	178
	FBG1	30.84	12.66		37.68	20.16
	FBG2	26.06	11.43		33.37	18.07
2	FBG0 and FBG1	8.02	4.99	181	29.07	12.96	180
	FBG0 and FBG2	5.01	2.66		27.42	12.04
	FBG1 and FBG2	3.79	2.01		22.88	11.83
3	FBG0，FBG1，and FBG2	2.53	1.30	182	8.78	5.24	182

Table 3. Influence of location of FBG2 on model performance

View table

Table 3. Influence of location of FBG2 on model performance

n	S	Cooling			Cooling-heating
n	S	MAXE /pm	RMSE /pm	CPU time /ms	MAXE /pm	RMSE /pm	CPU time /ms
0	0	33.65	13.75	180	69.25	49.51	181
1	FBG0	22.47	9.60	178	38.38	25.36	179
	FBG1	20.04	9.50		31.00	21.50
	FBG3	15.07	5.90		29.03	21.28
2	FBG0 and FBG1	12.71	3.77	179	18.68	9.14	180
	FBG0 and FBG3	11.56	3.14		15.28	8.89
	FBG1 and FBG3	7.71	2.72		13.97	8.21
3	FBG0，FBG1 and FBG3	3.63	1.06	181	7.84	3.33	179

Table 4. Model performance under different window lengths and number of reference gratings

View table

Table 4. Model performance under different window lengths and number of reference gratings

n	L_w	Cooling			Cooling-heating
n	L_w	MAXE /pm	RMSE /pm	CPU time /ms	MAXE /pm	RMSE /pm	CPU time /ms
0	50	62.10	32.75	181	106.27	73.22	181
	80	48.85	23.27		80.54	63.80
	100	33.65	13.75		69.25	49.51
1	50	50.58	29.05	178	92.75	60.57	180
	80	45.16	22.76		66.09	45.36
	100	22.47	9.60		38.38	25.36
2	50	42.66	21.69	183	84.09	55.89	181
	80	35.60	19.62		35.26	21.60
	100	12.71	3.77		18.68	9.14
3	50	37.35	14.19	182	76.78	50.29	182
	80	27.64	13.45		19.93	9.51
	100	3.63	1.06		7.84	3.33

Tools

Get Citation

Copy Citation Text

Wenjuan Sheng, Haitao Lou, Gangding Peng. Dynamic Compensation of Tunable Filter Demodulation Error Based on Least Squares Support Vector Machine and Multi-Reference Gratings[J]. Acta Optica Sinica, 2023, 43(7): 0706003

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites