Linear multiple regression (LMR) and nonlinear polynomial network (NPN) models were developed from data collected from ISO 8178-4 (1996) test cycle B-type tests (ISO) and an expanded set of tests (EXP) to predict hydrocarbon (HC) emissions from a diesel engine. LMR using the ISO training data (R 2 = 0.94) resulted in overfitting of the model as applied to the evaluation data (R 2 = 0.49). LMR based on the expanded data (R 2 = 0.68) was a better LMR model when applied to the evaluation data (R 2

more »

... = 0.64). NPN using the expanded training data (R 2 = 0.99) resulted in the best model when applied to the evaluation data (R 2 = 0.98) and is preferred for predicting HC when the larger set of test mode data are available. NPN using the ISO training data (R 2 = 0.99) resulted in a satisfactory fit for the evaluation data (R 2 = 0.91), although with a higher average absolute error (0.52 vs. 0.42 g/kWh) than NPN using the EXP training data. This model was also considered suitable for predicting HC. Results of this initial study suggest that data could be collected during ISO 8178-4 emission tests and modeled with NPN to predict HC emissions for a diesel engine operating at various constant speeds and loads. ven with increased emissions regulations, the availability and flexibility of fossil-fueled, internal combustion engines results in new applications on a regular basis. This is especially true in agriculture, where remote power requirements are common. In the past, emissions regulations were only for on-road engines, but by 2001, emissions of non-road power units were being regulated (CCR, 1999) . Engine manufacturers are required to have engine emissions certified per acceptable standards, such as ISO 8178-4 (ISO, 1996). The ISO 8178-4 standard for emissions measurement (ISO, 1996) includes universal test cycle B, which includes the engine speed and load combinations of the other test cycles. Test cycle B specifies 11 test modes of engine load and speed combinations for emissions measurement, specifically 10%, 25%, 50%, 75%, and 100% torque at rated speed and an intermediate speed and no load at low idle. Overall emission values are determined by averaging (other test cycles require weighting) the emissions of the test modes. The goal of the ISO standard was to minimize test modes while ensuring that test cycles were representative of actual engine operation (ISO, 1996) . Hansson et al. (2001) found hydrocarbon (HC) emissions of representative average trac-