基于支持向量机与模型预测控制的混合动力船舶能量管理策略

An Energy Management Strategy for Hybrid Ship Based on SVM and MPC

为了提高混合动力船舶能量利用效能,提升混合动力船舶燃油经济性,将在线工况识别与实时优化策略相结合,提出了基于支持向量机(support vector machine,SVM)与模型预测控制(model predictive control,MPC)的混合动力船舶能量管理策略。引入SVM理论,使用“美维凯越”号新能源游轮的实船数据,优化核函数类型及关键参数,构建船舶运行4个典型工况的在线识别模型;再通过对船舶当前时刻工况特征参数的分析与判断,确定船舶实时运行工况。以最小燃油消耗和保持储能单元荷电状态(state of charge,SOC)稳定为目标,以主机和复合储能单元之间的实时输出功率为优化变量,以功率需求预测模型为约束条件,构建模型预测控制MPC模型;为提高不同工况下功率需求预测的精度,提出基于多步马尔科夫模型的功率预测模型,并根据实时工况识别结果,更新MPC模型中的功率需求预测模型约束,实现船舶能量实时动态优化。最后,采用小波变换方法,将最优功率解分解成高频信号和低频信号;再根据复合储能单元中不同动力源工作特性的差异,将高频信号和低频信号分别分配给具有高功率密度的超级电容和具有高能量密度的蓄电池。为验证方法的有效性,开展了基于MATLAB的仿真实验,结果表明:在相同工况下,所提策略累计燃油消耗量为4 404.556 1 g,平均燃油消耗率为202.973 7 g/kWh;与基于单一模型预测控制的能量管理策略相比,所提方法可节省燃油消耗4.55%,验证了所提能量管理策略的有效性。

To improve the energy efficiency and fuel economy of hybrid ships,energy management strategy for hy-brid ships based on support vector machine(SVM)and model predictive control(MPC)is proposed,incorporating the working condition recognition into the strategy management.A working-condition recognition model is devel-oped based on the SVM theory,the kernel function type and key parameters are optimized by using the operation da-ta from the hybrid powered cruise ships called“MEIWEI KEYUE”,and the one of four working conditions is rec-ognized by feeding the real-time operation data.An energy management MPC model(EM-MPC)is proposed,allo-cating the output powers of main engine and composite ESUs for minimizing the consumption of fuel and maintain-ing the state of charge(SOC)stabilization of energy storage unit(ESU),which is constrained by the power demand prediction(PDP)model.Then,a prediction model based on the multi-step Markov model is proposed to improve the accuracy of PDP under different working conditions,and the PDP constraint in the EM-MPC model is updated based on the recognized working condition,which contributes to the real-time power allocation.The optimal solution is de-composed into high frequency signal and low frequency signal by wavelet transform method,and these signals are assigned to the super capacitor with high power density and the battery with high energy density,respectively.To validate the proposed strategy,a simulation via Matlab is introduced and the results show that:①the cumulative fuel consumption of the proposed method is 4404.5561 g and the average fuel consumption rate is 202.9737 g/kWh;②under the same working condition,the fuel consumption can be saved by 4.55%via the proposed EM-MPC,com-paring with the traditional method.