Off-highway Applications Research Articles

The influence of the fuel inlet temperature on diesel engine performance

The fuel inlet temperature has a significant influence on the performance levels of internal combustion engines, and this is particularly true for diesel engines. As a result, many passenger car manufacturers take this into account and incorporate a fuel temperature control system into their high-performance, latest-generation diesels. This paper describes a test project at Perkins for industrial diesel engines used in off-highway applications.

Neural Network Modelling of the Emissions and Performance of a Heavy-Duty Diesel Engine

Internal combustion engines are being required to comply with increasingly stringent government exhaust emissions regulations. Compression ignition (CI) piston engines will continue to be used in cost-sensitive fuel applications such as in heavy-duty buses and trucks, power generation, locomotives and off-highway applications, and will find application in hybrid electric vehicles. Close control of combustion in these engines will be essential to achieve ever-increasing efficiency improvements while meeting increasingly stringent emissions standards. The engines of the future will require significantly more complex control than existing map-based control strategies, having many more degrees of freedom than those of today. Neural network (NN)-based engine modelling offers the potential for a multidimensional, adaptive, learning control system that does not require knowledge of the governing equations for engine performance or the combustion kinetics of emissions formation that a conventional map-based engine model requires. The application of a neural network to model the output torque and exhaust emissions from a modern heavy-duty diesel engine (Navistar T444E) is shown to be able to predict the continuous torque and exhaust emissions from a heavy-duty diesel engine for the Federal heavy-duty engine transient test procedure (FTP) cycle and two random cycles to within 5 per cent of their measured values after only 100 min of transient dynamometer training. Applications of such a neural net model include emissions virtual sensing, on-board diagnostics (OBD) and engine control strategy optimization. (A)

Technical Note: Neural network modelling of the emissions and performance of a heavy-duty diesel engine

Internal combustion engines are being required to comply with increasingly stringent government exhaust emissions regulations. Compression ignition (CI) piston engines will continue to be used in cost-sensitive fuel applications such as in heavy-duty buses and trucks, power generation, locomotives and off-highway applications, and will find application in hybrid electric vehicles. Close control of combustion in these engines will be essential to achieve ever-increasing efficiency improvements while meeting increasingly stringent emissions standards. The engines of the future will require significantly more complex control than existing map-based control strategies, having many more degrees of freedom than those of today. Neural network (NN)-based engine modelling offers the potential for a multidimensional, adaptive, learning control system that does not require knowledge of the governing equations for engine performance or the combustion kinetics of emissions formation that a conventional map-based engine model requires. The application of a neural network to model the output torque and exhaust emissions from a modern heavy-duty diesel engine (Navistar T444E) is shown to be able to predict the continuous torque and exhaust emissions from a heavy-duty diesel engine for the Federal heavy-duty engine transient test procedure (FTP) cycle and two random cycles to within 5 per cent of their measured values after only 100 min of transient dynamometer training. Applications of such a neural net model include emissions virtual sensing, on-board diagnostics (OBD) and engine control strategy optimization.

Source contributions to atmospheric fine carbon particle concentrations

A Lagrangian particle-in-cell air quality model has been developed that facilitates the study of source contributions to atmospheric fine elemental carbon and fine primary total carbon particle concentrations. Model performance was tested using spatially and temporally resolved emissions and air quality data gathered for this purpose in the Los Angeles area for the year 1982. It was shown that black elemental carbon (EC) particle concentrations in that city were dominated by emissions from diesel engines including both on-highway and off-highway applications. Fine primary total carbon particle concentrations (TC=EC+organic carbon) resulted from the accumulation of small increments from a great variety of emission source types including both gasoline and diesel powered highway vehicles, stationary source fuel oil and gas combustion, industrial processes, paved road dust, fireplaces, cigarettes and food cooking (e.g. charbroilers). Strategies for black elemental carbon particle concentration control will of necessity need to focus on diesel engines, while controls directed at total carbon particle concentrations will have to be diversified over a great many source types.