In this work, an energy management system to address the optimal power-split problem in hybrid ship propulsion is developed. The torque of the diesel engine and the electric machine is regulated based on a predictive strategy with a weighting factor which determines the trade-off between fuel consumption and NOx emissions minimization. The modeling for the controller design is based on first principles and data gathered from the hybrid plant. In addition a disturbance observer is designed to estimate the propeller load characteristics. A neural network model that predicts rotational speed reference within the prediction horizon complements the control system design. It is used along with the observer to calculate the future load demand. A parametric simulation study is performed for the trade-off evaluation between fuel consumption and NOx emissions reduction of the control scheme. The control scheme is experimentally implemented and tested in real-time operation, where it has to cope with environmental disturbance rejection and follow the desired rotational speed reference, while performing the power-split in respect to the fuel to NOx weighting parameter and operate the plant within the desirable constraints.

在这项工作中，开发了一种能源管理系统来解决混合动力船舶推进中的最佳功率分配问题。柴油机和电机的扭矩基于具有权重因子的预测策略进行调节，该权重因子确定了燃料消耗与NOx排放量最小化之间的权衡。控制器设计的建模基于第一原理和从混合电站收集的数据。此外，还设计了一个扰动观测器来估算螺旋桨的负载特性。在预测范围内预测转速参考值的神经网络模型对控制系统设计起到了补充作用。它与观察者一起用于计算未来的负载需求。为控制方案的燃料消耗和NOx排放量之间的折衷评估进行了参数模拟研究。该控制方案是通过实验实现的，并在实时操作中进行了测试，该方案必须应对环境干扰抑制并遵循所需的转速参考，同时对燃料到NOx的加权参数执行功率分配，并运行工厂在理想的约束范围内。