全电力推进船舶的复杂工况使其负荷情况难以预测，无法确立精确的数学模型刻画，而应用RBF神经网络建立船舶电力系统负荷预测模型具有可靠性和准确性。通过对全电力推进船舶负荷特点的分析和对RBF神经网络负荷预测的基本原理研究，提出一种基于RBF神经网络的全电力推进船舶的负荷预测方法，选取合理的历史负荷数据，将其归一化处理后输入至RBF神经网络预测模型，再将模型输出反归一化后得到负荷预测结果。在Matlab/Simulink中对某全电力推进船舶在恶劣复杂工况下实际短期运行的负荷情况进行预测，预测准确率高达96.4%。预测结果表明，该方法实现了对复杂工况下全电力推进船舶短期负荷的精准预测，模型拟合程度很高。
It is difficult to predict the load of all-electric propulsion ship because of its complex working conditions, and it is difficult to establish an accurate mathematical model. Based on the analysis of the characteristics of the load of the all-electric propulsion ship and the study of the basic principle of the load forecasting by RBF neural network, a load forecasting method of the all-electric propulsion ship based on RBF neural network is proposed, the reasonable historical load data are selected and input into RBF neural network forecasting model after normalization, and then the output of the model is normalized to get the load forecasting result. In Matlab/Simulink, the short-term load of an all-electric propulsion ship under severe and complex conditions is predicted, and the accuracy of the prediction is as high as 96.4% . The prediction results show that the method can accurately predict the short-term load of full-electric propulsion ship, and the fitting degree of the model is very high.
2023,45(17): 97-101 收稿日期：2022-09-02
DOI：10.3404/j.issn.1672-7649.2023.17.020
分类号：U661
基金项目：国网江苏省电力有限公司研发服务资助项目（6410402000N6）；国家自然科学基金资助项目（52177221）
作者简介：钱宇轩(1991-),男,工程师,从事电力系统及自动化方面的研究
参考文献：
[1] 张宇涵, 高海波, 商蕾, 等. 基于神经网络模型的船舶电网短期电力负荷预测[J]. 应用科技, 2021, 48(5): 12–15+22 ZHANG Yuhan, GAO Haibo, SHANG Lei, et al. Short-term load forecasting for marine electric network based on neural network models[J]. Applied Science and Technology, 2021, 48(5): 12–15+22
[2] 刘银波, 吕越. RBF神经网络在船舶电力负荷预测中的应用[J]. 舰船科学技术, 2021, 43(18): 121–123 LIU Yin-Bo, LV Yue. Application of RBF neural network in ship power load forecasting[J]. Ship Science And Techology, 2021, 43(18): 121–123
[3] 周旭, 来庭煜, 饶佳黎. 基于RBF神经网络模型的电力系统短期负荷预测[J]. 通信电源技术, 2018, 35(11): 152–154 ZHOU Xu, LAI Ting-yu, RAO Jia-li. Short term load forecasting of power system based on RBF neural network model[J]. Telecom Power Technology, 2018, 35(11): 152–154
[4] 宋明达. 基于改进遗传算法优化Elman神经网络的短期负荷预测[D]. 衡阳: 南华大学, 2020.
[5] 侯文君, 汪英英, 姚艺新, 等. 支持向量机的船舶短期电力负荷预测方法[J]. 舰船科学技术, 2018, 40(18): 79–81 HOU Wen-jun, WANG Ying-ying, YAO Yi-xin, et al. Short term load forecasting method based on support vector machine[J]. Ship Science and Techology, 2018, 40(18): 79–81
[6] 赵登福, 王蒙, 张讲社, 等. 基于支撑向量机方法的短期负荷预测[J]. 中国电机工程学报, 2002(4): 27–31 ZHAO Deng-fu, WANG Meng, ZHANG Jiang-she, et al. A support vector machine approach for short term load forecasting[J]. Proceedings of the CSEE, 2002(4): 27–31
[7] 王嘉钰. 全电力推进船舶短期电力负荷预测研究[D]. 哈尔滨: 哈尔滨工程大学, 2010.
[8] 刘静. 最小二乘SVM在电力推进船舶电力负荷短期预测的应用[J]. 舰船科学技术, 2021, 43(24): 61–63 LIU Jing. Application of least square SVM in short-term forecasting of electric load of electric propulsion ship[J]. Ship Science and Technology, 2021, 43(24): 61–63
[9] 朱诗卉, 代焕利, 王飒, 等. RBF神经网络电力负荷预测模型研究[J]. 三峡大学学报(自然科学版), 2013, 35(5): 46–49 Zhu Shihui, Dai Huanli, Wang Sa, et al. Research on RBF neural network models of power load forecasting[J]. Journal of China Three Gorges Univercity (Natural Sciences), 2013, 35(5): 46–49
[10] 王成, 代祥, 刘飞, 等. 基于RBF神经网络的电力系统负荷预测[J]. 电力学报, 2018, 33(5): 399–407 WANG Cheng, DAI Xiang, LIU Fei, et al. Power system load forecasting based on RBF neural network[J]. Journal of Electric Power, 2018, 33(5): 399–407
