Improved ABC algorithm for optimizing BP neural network in short-term clock bias prediction and application

doi:10.11947/j.AGCS.2025.20240318

Abstract

Abstract:

In order to solve the problem that BP neural network is easy to fall into the local optimal solution and the convergence speed is slow when dealing with nonlinear and complex environments, an improved artificial bee colony algorithm is proposed to optimize BP neural network and apply it to short-term prediction of clock deviation. Firstly, from the perspective of enhancing the randomness of the step size, improving the search efficiency and maintaining the diversity of the population, the Lévy flight strategy, the teaching and learning optimization algorithm and the fitness-distance balance mechanism were introduced to improve the artificial bee colony algorithm, which effectively improved the global search ability of the algorithm and avoided falling into the local optimal solution. Secondly, the improved artificial bee colony algorithm is combined with BP neural network to be applied to the short-term prediction of satellite clock deviation, and the corresponding calculation steps are given. Then, the high-precision satellite clock products provided by GFZ are selected to compare and analyze the single-day and multi-day forecasts from the aspects of algorithm efficiency, stability and accuracy, so as to verify the applicability of the model. Finally, the prediction results of the optimization model are verified to be applied in PPP. Compared with the QP, BP and ABC-BP models, the average accuracy is increased by 56.55%, 25.11% and 7.07%, respectively, and the improvement effect of MEO-PHM clock is better than that of MEO-Rb clock. The improved artificial bee colony algorithm and the BP combined model have a more concentrated residual distribution, a median closer to zero, and a smaller extreme value, which has high accuracy and stability in the 6 and 12 h prediction. The accuracy of the combined model in the E, N and U directions was improved by using the forecast clock error sequence to improve the accuracy of the results in the E, N and U directions, which were improved by 42.07%, 31.07%, 41.79% and 45.42%, 50.16%, 46.18% compared with the ABC-BP model and the BP model, respectively.

Key words: fitness-distance balance, teaching-learning-based optimization, short-term prediction, precision point positioning

CLC Number:

P228

Xiong PAN, Longjie ZHANG, Qingsong AI, Lihong JIN, Mao CAI. Improved ABC algorithm for optimizing BP neural network in short-term clock bias prediction and application[J]. Acta Geodaetica et Cartographica Sinica, 2025, 54(8): 1404-1415.

Figures/Tables 14

Fig. 1

Tab. 1

Fig. 2

Fig. 3

Fig. 4

Tab. 2

Fig. 5

Tab. 3

Tab. 4

Tab. 5

Tab. 6

Fig. 6

Tab. 7

Tab. 8

References 26

[1]	杨元喜. 北斗卫星导航系统的进展、贡献与挑战[J]. 测绘学报, 2010, 39(1): 1-6.
	YANG Yuanxi. Progress, contribution and challenges of Compass/BeiDou satellite navigation system[J]. Acta Geodaetica et Cartographica Sinica, 2010, 39(1): 1-6.
[2]	YANG Yuanxi. Resilient PNT concept frame[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(3): 1-7.
[3]	YAO Yibin, YANG Yuanxi, SUN Heping, et al. Geodesy discipline: progress and perspective[J]. Journal of Geodesy and Geoinformation Science, 2021, 4(4): 1-10.
[4]	CHEN Jun, LI Zhilin, LI Songnian, et al. From digitalized to intelligentized surveying and mapping: fundamental issues and research agenda[J]. Journal of Geodesy and Geoinformation Science, 2022, 5(2): 148-160.
[5]	毛亚, 王潜心, 胡超, 等. BDS-3卫星钟差特性分析[J]. 武汉大学学报(信息科学版), 2020, 45(1): 53-61.
	MAO Ya, WANG Qianxin, HU Chao, et al. Analysis of the characterization for BDS-3 satellite clock error[J]. Geomatics and Information Science of Wuhan University, 2020, 45(1): 53-61.
[6]	潘雄, 赵万卓, 黄伟凯, 等. 基于优化自注意力神经网络的卫星钟差短期预报[J]. 中国惯性技术学报, 2023, 31(11): 1092-1101.
	PAN Xiong, ZHAO Wanzhuo, HUANG Weikai, et al. Short-term prediction of satellite clock bias based on improved self-attention model[J]. Journal of Chinese Inertial Technology, 2023, 31(11): 1092-1101.
[7]	XI Chao, CAI Chenglin, LI Simin, et al. Long-term clock bias prediction based on an ARIMA model[J]. Chinese Astronomy and Astrophysics, 2014, 38(3): 342-354.
[8]	YAN Xiong, LI Wentao, YANG Yufeng, et al. BDS satellite clock offset prediction based on a semiparametric adjustment model considering model errors[J]. Satellite Navigation, 2020, 1(1): 11.
[9]	潘雄, 杨玉锋, 欧吉坤, 等. BDS-2卫星钟设计年限末期阶段性能评估与分析[J]. 大地测量与地球动力学, 2020, 40(10): 991-999, 1033.
	PAN Xiong, YANG Yufeng, OU Jikun, et al. Performance evaluation and analysis of the final stage of BDS-2 satellite clock design period[J]. Journal of Geodesy and Geodynamics, 2020, 40(10): 991-999, 1033.
[10]	潘雄, 黄伟凯, 赵万卓, 等. 基于BiLSTM模型的BDS-3短期钟差预报精度研究[J]. 测绘学报, 2024, 53(1): 65-78. DOI: . doi: 10.11947/j.AGCS.2024.20230082
	PAN Xiong, HUANG Weikai, ZHAO Wanzhuo, et al. Research on short-term prediction accuracy of BDS-3 clock bias based on BiLSTM model[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(1): 65-78. DOI: . doi: 10.11947/j.AGCS.2024.20230082
[11]	李方能, 梁益丰, 许江宁, 等. 基于鲁棒双参数指数平滑法的BDS卫星钟差预报[J]. 中国惯性技术学报, 2024, 32(7): 645-653.
	LI Fangneng, LIANG Yifeng, XU Jiangning, et al. Prediction of BDS satellite clock bias based on robust two-parameter exponential smoothing method[J]. Journal of Chinese Inertial Technology, 2024, 32(7): 645-653.
[12]	李文涛, 颜雄, 夏磊, 等. BDS卫星钟差半参数平差模型异常数据探测与处理[J]. 测绘学报, 2020, 49(1): 55-64. DOI: . doi: 10.11947/j.AGCS.2020.20180384
	LI Wentao, YAN Xiong, XIA Lei, et al. Abnormal data detection and process by using BDS satellite offset semiparametric adjustment model[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(1): 55-64. DOI: . doi: 10.11947/j.AGCS.2020.20180384
[13]	HE Shaofeng, LIU Jiulong, ZHU Xiangwei, et al. Research on modeling and predicting of BDS-3 satellite clock bias using the LSTM neural network model[J]. GPS Solutions, 2023, 27(3): 108.
[14]	黄观文, 崔博斌, 张勤, 等. 附加周期和神经网络补偿的实时钟差预报模型[J]. 宇航学报, 2018, 39(1): 83-88.
	HUANG Guanwen, CUI Bobin, ZHANG Qin, et al. Real-time clock offset prediction model with periodic and neural network corrections[J]. Journal of Astronautics, 2018, 39(1): 83-88.
[15]	YANG Yuanxi, MAO Yue, SUN Bijiao. Basic performance and future developments of BeiDou global navigation satellite system[J]. Satellite Navigation, 2020, 1(1): 1.
[16]	ZHU Jiangmiao, SUN Panpan, GAO Yuan, et al. Clock differences prediction algorithm based on EMD-SVM[J]. Chinese Journal of Electronics, 2018, 27(1): 128-132.
[17]	LÜ Dong, LIU Genyou, OU Jikun, et al. Prediction of GPS satellite clock offset based on an improved particle Swarm algorithm optimized BP neural network[J]. Remote Sensing, 2022, 14(10): 2407.
[18]	WANG Xu, CHAI Hongzhou. Developing an innovative high-precision approach to predict medium-term and long-term satellite clock bias[J]. Journal of Geodesy and Geoinformation Science, 2023, 6(1): 47-58.
[19]	黄博华, 杨勃航, 李锡瑞, 等. 顾及一次差分数据结构特征的钟差预报模型[J]. 武汉大学学报(信息科学版), 2021, 46(8): 1161-1169.
	HUANG Bohua, YANG Bohang, LI Xirui, et al. Prediction of navigation satellite clock bias considering structure characteristics of single difference data[J]. Geomatics and Information Science of Wuhan University, 2021, 46(8): 1161-1169.
[20]	吕栋, 欧吉坤, 于胜文. 基于MEA-BP神经网络的卫星钟差预报[J]. 测绘学报, 2020, 49(8): 993-1003. DOI: . doi: 10.11947/j.AGCS.2020.20200002
	LÜ Dong, OU Jikun, YU Shengwen. Prediction of the satellite clock bias based on MEA-BP neural network[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(8): 993-1003. DOI: . doi: 10.11947/j.AGCS.2020.20200002
[21]	ZHU Chonghao, ZHANG Jianjing, LIU Yang, et al. Comparison of GA-BP and PSO-BP neural network models with initial BP model for rainfall-induced landslides risk assessment in regional scale: a case study in Sichuan, China[J]. Natural Hazards, 2020, 100(1): 173-204.
[22]	周凯红, 叶高威, 蒋青谷. 基于SSA-GA-BP神经网络的数显千分表非线性误差补偿[J]. 河南科技大学学报(自然科学版), 2024, 45(3): 1-8, 115.
	ZHOU Kaihong, YE Gaowei, JIANG Qinggu. Nonlinear error compensation of digital dial indicator based on SSA-GA-BP neural network[J]. Journal of Henan University of Science and Technology (Natural Science), 2024, 45(3): 1-8, 115.
[23]	MENG Caixia, WU Di, LEI Yu. Neural network satellite clock bias prediction based on the whale optimization algorithm[C]//Proceedings of 2022 Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery. Cham: Springer, 2022: 1152-1160.
[24]	RAO R V, SAVSANI V J, VAKHARIA D P. Teaching-learning-based optimization: an optimization method for continuous non-linear large scale problems[J]. Information Sciences, 2012, 183(1): 1-15.
[25]	CHEN Xu, XU Bin. Teaching-learning-based artificial bee colony[C]//Proceedings of 2018 Advances in Swarm Intelligence. Cham: Springer, 2018: 166-178.
[26]	KAHRAMAN H T, BAKIR H, DUMAN S, et al. Dynamic FDB selection method and its application: modeling and optimizing of directional overcurrent relays coordination[J]. Applied Intelligence, 2022, 52(5): 4873-4908.

类型	PRN
MEO-Rb	C19、C20、C21、C22、C23、C24、C32、C33、C36、C37、C41、C42
MEO-PHM	C25、C26、C27、C28、C29、C30、C34、C35、C43、C44、C45、C46
IGSO-PHM	C38、C39、C40
GEO-PHM	C59、C60

预报时间/h	QP/ns	BP/ns	ABC-BP/ns	I-ABC-BP/ns	相对于基准策略/(%)
1	0.24	0.11	0.08	0.07	12.50
3	0.37	0.23	0.17	0.16	5.88
6	0.63	0.43	0.35	0.33	5.71
12	1.41	0.77	0.72	0.69	4.17

钟类型	QP			BP			ABC-BP			I-ABC-BP
钟类型	RMSE	Range	Mean	RMSE	Range	Mean	RMSE	Range	Mean	RMSE	Range	Mean
MEO-Rb	0.199	0.124	0.193	0.139	0.189	0.123	0.092	0.150	0.078	0.072	0.129	0.058
MEO-PHM	0.271	0.170	0.265	0.100	0.151	0.084	0.073	0.123	0.060	0.070	0.119	0.056
IGSO-PHM	0.107	0.076	0.104	0.079	0.112	0.073	0.071	0.089	0.065	0.071	0.087	0.065
GEO-PHM	0.462	0.284	0.454	0.076	0.133	0.062	0.035	0.097	0.011	0.071	0.154	0.048

钟类型	QP			BP			ABC-BP			I-ABC-BP
钟类型	RMSE	Range	Mean	RMSE	Range	Mean	RMSE	Range	Mean	RMSE	Range	Mean
MEO-Rb	0.276	0.336	0.251	0.292	0.469	0.255	0.205	0.377	0.163	0.200	0.398	0.153
MEO-PHM	0.412	0.529	0.362	0.195	0.352	0.153	0.141	0.364	0.078	0.118	0.319	0.060
IGSO-PHM	0.180	0.268	0.149	0.175	0.286	0.150	0.125	0.201	0.112	0.103	0.161	0.091
GEO-PHM	0.909	1.173	0.837	0.199	0.345	0.175	0.162	0.358	0.116	0.213	0.437	0.144

钟类型	QP			BP			ABC-BP			I-ABC-BP
钟类型	RMSE	Range	Mean	RMSE	Range	Mean	RMSE	Range	Mean	RMSE	Range	Mean
MEO-Rb	0.493	0.812	0.399	0.569	1.070	0.459	0.448	0.903	0.352	0.443	0.880	0.351
MEO-PHM	0.683	1.035	0.593	0.299	0.537	0.246	0.256	0.538	0.173	0.218	0.498	0.134
IGSO-PHM	0.276	0.453	0.238	0.268	0.440	0.239	0.202	0.391	0.147	0.151	0.296	0.118
GEO-PHM	1.628	2.257	1.456	0.555	1.203	0.440	0.538	1.226	0.389	0.557	1.351	0.396