This study presents a novel data driven disturbance observer design method and its integration with a recursive controller developed for diesel engine airpath control problem. Mass Air Flow (MAF) and Manifold Absolute Pressure (MAP) are identified with Multi-Input Single-Output NFIR models using experimental data. Heavy-duty diesel engine airpath with variable geometry turbine (VGT) and exhaust gas recirculation (EGR) valve is the main focus of the paper. Presented data driven disturbance observer and controller are implemented to a serial production level engine embedded software. The proposed controllers are compared with the available commercial controllers in dynamometer test cycles. Better overall performance is achieved with respect to the commercial controllers using proposed easy-to-tune controllers.

中文翻译：

---

通过数据驱动扰动观测器的柴油机气路控制器

这项研究提出了一种新颖的数据驱动扰动观测器设计方法，并将其与针对柴油机气路控制问题开发的递归控制器集成在一起。使用实验数据，通过多输入单输出NFIR模型识别空气质量流量（MAF）和歧管绝对压力（MAP）。带有可变几何涡轮（VGT）和废气再循环（EGR）阀的重型柴油发动机气路是本文的重点。呈现的数据驱动的干扰观察器和控制器已实现为串行生产级引擎嵌入式软件。建议的控制器在测功机测试周期中与可用的商用控制器进行比较。使用建议的易于调节的控制器，相对于商用控制器，可以获得更好的整体性能。