Using the AMCE Algorithm to High-Efficiently Develop Vehicle Driving Cycles With Road Grade

Abstract

Road grade greatly affects energy consumption and pollutant emission of heavy-duty vehicles. It is therefore necessary to develop representative three-parameter driving cycles while taking road grade into account. However, the low running efficiency of existing methods for developing driving cycles is a serious problem. To improve efficiency, inspired by the idea that intelligent algorithms with self-adaptivity can accelerate convergence, an adaptive Markov chain evolution (AMCE) method is proposed in this study. Based on the characteristics of the evolution strategies of a Markov chain evolution (MCE) satisfying the Markov property, a strategy boundary variable is defined to classify the MCE evolution strategies into two categories, one with the global and one with local search capability. Then, an adaptive probability equation is used to adjust the proportion of the evolution strategies, thus the evolution strategies can satisfy not only the Markov property of driving cycle but is also self-adaptive. By collecting driving data including the elevation information from heavy-duty vehicles driving on a highway, a three-parameter driving cycle with road grade was generated using the proposed method. In comparison with the MCE method, the proposed method can obtain the three-parameter representative driving cycles on the highway, and running efficiency was increased by 43.08% under the given conditions. Additionally, the rationality and necessity of the proposed method are fully verified.INDEX TERMS Vehicle driving cycle, road grade, self-adaptivity, Markov chain evolution, running efficiency.

Simulation Study of The Dump Trucks' Speed Profile Impact on Open Pit Efficiency

“…For example, in studies [11][12][13], the effect on the dynamics of a car of its mass and longitudinal road grade, as well as speed, is shown [14]. This, in turn, reduces the driving time [15] or travel time along the route [16], increases the number of trips during the operation of the mining dump truck.…”

“…Research in the field of intellectualization of vehicles and improvement of autonomous driving systems, at present, is aimed at considering various factors that affect the speed of both an individual car and the efficiency of vehicle fleet operation. The main factors include: the value of the longitudinal slope of both individual sections of the road [21][22][23] and several sections along the entire length of the highway route [15,16], inertia forces [24], the interaction of vehicles in the traffic flow [25].…”

“…Regression models, Bayesian approach [20], nonlinear mathematical models [26], dynamic programming methods [16], Markov chains [15] are most widely used as research methods and models of vehicle speed characteristics.…”

Development of Driver-Behavior Model Based onWOA-RBM Deep Learning Network

“…Driver models can be applied to (1) vehicle dynamics [1] including vehicle component design, vehicle dynamics analysis, overall vehicle stability analysis, and design of onboard controls; (2) intelligent transport systems (ITS) [2,3] including simulation of traffic flow based on the control theory models of driver behavior and modeling drivers' risk taking behavior; (3) driverless vehicle systems [4]; and (4) traffic energy consumption systems [5]. Traffic energy consumption systems are different from the vehicle dynamics simulation.…”