PCC Energy-saving Optimization Based on Historical Driving Data Identification of Energy Consumption Model

The automotive industry is currently emphasizing the pursuit of low-carbon and environmentally friendly development, with a specific focus on addressing the high fuel consumption observed in commercial vehicles. To this end, various energy-saving assisted driving solutions, including Predictive Cruise Control (PCC), have proven to be effective. However, the implementation of these solutions often necessitates access to engine-related data, such as energy consumption maps and external characteristic curves, which can be challenging for nonautomotive manufacturers to acquire. This article introduces a solution to this challenge by developing a method for fitting energy consumption and universal characteristics specific to commercial vehicles based on multi-operating condition data. The resulting dataset can then be leveraged to design and implement the Predictive Cruise Control (PCC) control system. Test results demonstrate that this method enhances the algorithm’s applicability by effectively addressing the difficulties associated with obtaining the requisite data for the real-world application of the PCC algorithm in vehicles.