Search Results

A frequency-domain approach to balancing of air-fuel ratio (A/F) in a multi-cylinder engine is described. The technique utilizes information from a single Wide-Range Air-Fuel ratio (WRAF) or a single switching (production) O₂ sensor installed in the exhaust manifold of an internal combustion engine to eliminate the imbalances. At the core of the proposed approach is the development of a simple novel method for the characterization of A/F imbalances among the cylinders. The proposed approach provides a direct objective metric for the characterization of the degree of A/F imbalances for diagnostic purposes as well as a methodology for the control of A/F imbalances among various cylinders. The fundamental computational requirement is based on the calculation of a Discrete Fourier Transform (DFT) of the A/F signal as measured by a WRAF or a switching O₂ sensor.

For engine diagnostics and fault-tolerant control system design provision of analytical models, in the form of virtual sensors, will enable more reliable system design and operation. This paper presents applications of recurrent neural network (RNN)-based architectures for the development of virtual sensors for salient SI engine variables such as manifold absolute pressure, mass airflow rate, air-fuel ratio and engine torque. The RNN architectures developed allow effective sensing of these crucial engine variables while, for computational efficiency, keeping a compact size for the network topology. A nonlinear state-space model strategy is proposed for architecting the stated recurrent neural network and is trained using variants of the real-time recurrent learning (RTRL) algorithm. Representative experimental results obtained for a 5.7 L V8 engine are listed and discussed. The application, dependency and limitations of the proposed approaches are also pointed out.