Folie 1Folie 2Folie 3Folie 4Folie 5Folie 6Folie 7Estimation of car gas consumption in city cycle with ANNIntroduction An ANN based approach to estimation of car fuel consumption Multi Layer Perceptron as a choice of the art Different discrete and continuous features Prediction without extensive trials on the road Could be used as first guessEstimation of car gas consumption in city cycle with ANNData Description Seven features used: Horsepower, Weight, Number of Cylinders etc. Some data with unknown values Wide variation of cars, 398 samples available Equally distributed from different manufacturers Quite old, from early ‘80sEstimation of car gas consumption in city cycle with ANNData Preprocessing Feature dimension statistical values differ very much Removing name of car and values with unknown parameters Normalization of each feature dimension Create data sets for training and final testingEstimation of car gas consumption in city cycle with ANNMLP Development I Estimation of underlying physical model difficult How complex and how “much” nonlinear? One hidden layer versus several hidden layers Cross-validation as best way to find optimal configurations Five parameters for variationEstimation of car gas consumption in city cycle with ANNMLP Development II Each cross validation performed several times with same parameters to get a meaningful average Learning rate and epoch size most important Tables to evaluate best settings No complete automation, two-step evaluation Several comparable best configurationsEstimation of car gas consumption in city cycle with ANNComparison to Base Case Best result from final training still 30-40% worse than base case No improvement achieved with two hidden layers Results still good for first estimation Understanding of model not sufficient enoughEstimation of car gas consumption in city cycle with ANNConclusion Use of MLP delivered satisfactory results, but not better than base case Using different activation function could bring improvement Without some prior knowledge of physical model hard to see what features are more important than others Other ANN like radial basis functions
View Full Document