An Intelligent System-on-a-Chip for a Real-Time Assessment of Fuel Consumption to Promote Eco-Driving

Abstract

Pollution that originates from automobiles is a concern in the current world, not only because of global warming, but also due to the harmful effects on people’s health and lives. Despite regulations on exhaust gas emissions being applied, minimizing unsuitable driving habits that cause elevated fuel consumption and emissions would achieve further reductions. For that reason, this work proposes a self-organized map (SOM)-based intelligent system in order to provide drivers with eco-driving-intended driving style (DS) recommendations. The development of the DS advisor uses driving data from the Uyanik instrumented car. The system classifies drivers regarding the underlying causes of non-optimal DSs from the eco-driving viewpoint. When compared with other solutions, the main advantage of this approach is the personalization of the recommendations that are provided to motorists, comprising the handling of the pedals and the gearbox, with potential improvements in both fuel consumption and emissions ranging from the 9.5% to the 31.5%, or even higher for drivers that are strongly engaged with the system. It was successfully implemented using a field-programmable gate array (FPGA) device of the Xilinx ZynQ programmable system-on-a-chip (PSoC) family. This SOM-based system allows for real-time implementation, state-of-the-art timing performances, and low power consumption, which are suitable for developing advanced driving assistance systems (ADASs).

An eco‐driving approach for ride comfort improvement

“…To better analyse the aforementioned tradeoff, among many of the previously mentioned methods, SOMs have been successfully used to online cluster DS regarding meaningful features and to provide advice to modify the undesirable aspects of car handling [30].…”

“…To complete the dataset so as to be able to assess the fuel consumption and, consequently, the eco-driving characteristics, we added the fuel consumption data corresponding with each sample. This data, which the original dataset lacked, was obtained by introducing the real-world driving data into a realistic model of the instrumented car [30], developed with the GT-Suite simulator [69]. This model, as detailed in ref.…”

“…This model, as detailed in ref. [30], takes into account parameters of the car (e.g. car wheelbase, wheel radius, friction coefficients, aerodynamics, weight, inertia, and final transmission ratio), the individual ratios for each of the user-selectable gears, the engine parameters and, most importantly, the telemetry data related to the handling of the car, such as selected gear, accelerator pedal state, brake pedal state, clutch, and desired speed.…”

“…To perform those personalised recommendations, machine learning techniques, such as fuzzy logic and artificial neural networks have been used to give coaching feedback to the driver about his/her performance regarding the DS, such as ref. [30], where DS-associated fuel consumption was assessed to provide reduction recommendations, or ref. [31], where critical manoeuvres are analysed to identify eco-driving-compromising points.…”

Sustainable improvement and evaluation of the shifting smoothness of vehicle transmission

“…Poor vehicle transmission performance will reduce the driver's driving pleasure, make the driver feel tired, increase fuel consumption, and affect the driver's green driving. Especially in urban traffic conditions, the driver is very concerned about the comfort and smoothness of gear selection and shifting performance because the vehicle is always continuously engaged in gear selection and shifting action without interruption, and the performance index will directly affect the driver's efficiency assessment on a certain type of traffic vehicle 12 , 13 . It can be said that as an easy perception item for users, the shift performance of the vehicle transmission has a direct relationship with the degree of user complaints.…”