Bringing Accuracy to the Calculation of Vehicle Fleet Fuel Consumption and Tailpipe Emissions with Predictive Analytics
LOVELAND, CO: To measure the fuel economy and tailpipe emissions of fleet vehicles accurately and efficiently, Lightning Systems are employing artificial neural networks form of artificial intelligence. The computing system of the neural network consists of a number of highly interconnected processing elements to process information as well as predicts future outcomes.
"Using artificial neural networks, we are able to accurately predict fuel consumption and emissions of commercial and government fleets," says Tyler Yadon, director of analytics for Lightning Systems. "Our computer modeling demonstrates the accuracy of predictive analytics to help fleets manage fuel consumption, decrease their fuel usage, and reduce emissions. The tools we are developing can take incredibly complex real-world problems and turn them into extremely accurate predictions about your fleet."
With high-frequency recordings of essential real-time parameters from vehicles, the system is trained to predict imminent maintenance repairs caused by fuel usage, driver behavior, drive cycles and routes. This is achieved through a high-frequency recording of many real-time parameters from the vehicle. The artificial neural network predictions on fuel consumption and emissions were created with the data obtained from the operation of hydraulic hybrid fleet vehicles in the UK and the US. The outcomes of the research on the artificial neural network, which was conducted by the engineering graduates of Colorado State University, will be presented at the SAE World Congress in Detroit in April.
Lightning Systems offers products such as the LightningHybrid, a hydraulic hybrid energy recovery system, which is installed onto trucks, buses and other large transit and delivery vehicles to add upgraded energy-management and power train-control systems to the conventional vehicles. Besides, Lightning Systems has just announced its new line of product—LightningElectric, a zero-emissions package for the heavy-duty Ford Transit. Against that background, Lightning Systems have embedded LightningAnalytics, a cloud-based analytic system within the aforementioned products to enhance the performance of the products.
"Artificial neural networks are not only less computationally costly than existing simulation standards, but they are easier and faster to re-train and apply to new vehicles and drive cycles offering the potential for high accuracy estimates with reduced infrastructure requirements," says Brian Johnston, director of emissions regulation and strategy for Lightning Systems and co-authors of a paper to be published by Colorado State University.
"Our research demonstrates significant benefit for designing improved vehicle-control strategies, such as eco-driving and optimal energy management. It also has the potential to reduce the need for physical vehicle testing, because this type of computer modeling accurately captures emissions results from slight drive-cycle variations and improves the understanding of real-world emissions and fuel impacts, enabling high-fidelity learning control in physical vehicles," says Will Briggs, lead test engineer for Lightning Systems and co-authors of the paper to be published by Colorado State University. "Our analysis predicted fuel consumption with a margin for error as low as 0.1 percent, and predicted CO2, CO and NOx emissions with 97 to 100 percent accuracy."
"Customer drive cycles are not always reproducible for fuel consumption and emissions research," says Yadon, “Our results indicate that artificial neural network models can be used for a variety of research applications due to their economic and computational benefits, such as improving vehicle-control strategies to reduce fuel consumption and emissions in modern vehicles.”