Intelligent Control of Connected and Automated Vehicles and Powertrains for Cold Climates

适用于寒冷气候的互联自动化车辆和动力系统的智能控制

• 批准号: RGPIN-2020-04403
• 负责人: Shahbakhti, Mahdi
• 金额: $ 2.84万
• 依托单位: University of Alberta
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2020
• 资助国家: 加拿大
• 起止时间: 2020-01-01 至 2021-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=716880
• 关键词: Intelligent; Control; Connected; Automated; Vehicles

Connected and automated vehicles (CAVs) will become major parts of the Canadian transportation industry. By 2022, the majority of vehicles sold in the US and Canada will have embedded connectivity. In addition, major automotive companies have launched large-scale programs for deploying CAVs on the road over the next 10 years. CAVs reduce traffic congestion, improve mobility, and decrease vehicular energy consumption and greenhouse gas emissions. Currently in Canada, end users of the transportation industry consume about 30% of Canada's total energy, causing 24% of Canada's greenhouse gas emissions. The availability of V2X (vehicle to vehicle, infrastructure) data, along with vehicle automation, provides a great opportunity for Canadians to save energy and reduce their GHG emissions. The long-term vision of the proposed research is to enable energy-optimal CAVs for cold climate operations via advanced control methods and understanding major dynamics that affect vehicle energy consumption and emissions. The short-term objectives of this program include utilizing V2X data to design optimal and integrated control strategies that includes vehicle powertrain, heating, ventilation, air conditioning (HVAC), vehicle dynamics, and powertrain thermal management. The goal of the proposed research is to provide fundamental contributions towards reducing vehicle fuel consumption up to 34% and substantially reducing greenhouse gas emissions for operation in cold climates. This program centers on CAVs ranging from partial automation (L2) to high automation (L4). The long-term objectives include i) developing cold climate CAV control strategies by leveraging vehicle full autonomy and complete penetration of connectivity data, and ii) developing Artificial Intelligence methods based on peer-learning for integrated powertrain and thermal energy management. Despite the fact that over 85% of Canada's population live in regions with long cold winters, and energy consumption and emissions from vehicles increase drastically in cold climates, very little research has been done in the area of vehicle powertrain and HVAC controls for CAV operation in cold climates. This Discovery program will address the challenges of CAV powertrain and HVAC control, with both conventional and electrified powertrains. The research methodology will include experimental powertrain and vehicle studies, dynamical analysis, advanced predictive control techniques, and methods of machine learning for robust vehicle controls. The program will provide training to 14 highly qualified personnel and include outreach to high school students. The experimental work will be conducted in Edmonton (>1.3M metropolitan population) with average 180 days with the minimum temperature of the day 0oC. The results will lead to a unique data bank of powertrain, HVAC, and emissions information for CAVs operating in cold climates. This unique data bank will be shared with the public and the research community.

联网和自动驾驶汽车（CAV）将成为加拿大交通运输业的主要组成部分。到2022年，在美国和加拿大销售的大多数汽车将具有嵌入式连接。此外，主要汽车公司已经启动了大规模的计划，在未来10年内在道路上部署CAV。CAV减少了交通拥堵，提高了机动性，降低了车辆能耗和温室气体排放。目前在加拿大，运输行业的终端用户消耗了加拿大总能源的30%左右，造成了加拿大24%的温室气体排放。V2X（车对车，基础设施）数据的可用性沿着车辆自动化为加拿大人节省能源和减少温室气体排放提供了一个很好的机会。 拟议研究的长期愿景是通过先进的控制方法和了解影响车辆能耗和排放的主要动力学，使能源最佳的CAV能够在寒冷气候下运行。该计划的短期目标包括利用V2X数据设计最佳和集成的控制策略，包括车辆动力系统，加热，通风，空调（HVAC），车辆动力学和动力系统热管理。拟议研究的目标是为减少车辆燃料消耗高达34%，并大幅减少寒冷气候下运行的温室气体排放量提供基础性贡献。该计划以CAV为中心，范围从部分自动化（L2）到高度自动化（L4）。长期目标包括：i）通过利用车辆完全自主和完全渗透连接数据来开发寒冷气候CAV控制策略，以及ii）开发基于同行学习的人工智能方法，用于集成动力系统和热能管理。 尽管超过85%的加拿大人口生活在冬季寒冷的地区，并且车辆的能耗和排放在寒冷气候下急剧增加，但在寒冷气候下CAV运行的车辆动力系统和HVAC控制方面的研究很少。这个发现计划将解决CAV动力系统和HVAC控制的挑战，包括传统和电气化动力系统。研究方法将包括实验动力系统和车辆研究，动力学分析，先进的预测控制技术，以及机器学习方法，用于鲁棒的车辆控制。 该方案将为14名高素质人员提供培训，并包括向高中生提供培训。实验工作将在埃德蒙顿（> 130万大城市人口）进行，平均180天，每天最低气温为0 ℃。结果将导致一个独特的数据库的动力系统，暖通空调和排放信息的CAV在寒冷的气候中运行。这一独特的数据库将与公众和研究界共享。