Optimizing Fuel Consumption Prediction Model Without an On-Board Diagnostic System in Deep Learning Frameworks.

Real-time prediction of the instantaneous fuel consumption rate (FCR) of any vehicle is the key to improving energy efficiency and reducing emissions. The conventional prediction methods, which include an on-board diagnostic (OBD) system, require the specific vehicle parameters and environmental conditions such as air density. We propose a data-driven Bayesian optimization and Monte Carlo (MC) Dropout methods-based long short-term memory (BMC-LSTM) network FCR prediction model using only the vehicle's throttle position, velocity, and acceleration data. The cost-effective LSTM network-based solution enhances the high-resolution prediction accuracy within a deep learning framework. The network is integrated with the Bayesian optimization and MC-Dropout methods to ensure a probabilistically optimal hyperparameter set and robust networks. The proposed method presents an FCR model that provides calibrated predictions and reliability against distribution drift by probabilistically tuning hyperparameters with Bayesian optimization and quantifying epistemic uncertainty with the MC-Dropout. Our approach requires only vehicle speed, longitudinal acceleration, and throttle position at inference time. Note, however, that the reference FCR used to train and validate the models was obtained from OBD during data acquisition. The performance of the proposed method is compared with a conventional LSTM and Bidirectional LSTM-based multidimensional models, XGBoost and support vector regression-based models, and first- and fourth-order polynomials, which are derived using the least-squares method. The prediction performance of the method is evaluated using Mean Squared Error, Root Mean Squared Error, Mean Absolute, and R-squared statistical metrics. The proposed method achieves a superior R2 score and substantially reduces the conventional error metrics.