Application of a novel machine learning based optimization algorithm (ActivO) for accelerating simulation-driven engine design
share
A novel design optimization approach (ActivO) that employs an ensemble of machine learning algorithms is presented. The proposed approach is a surrogate-based scheme, where the predictions of a weak leaner and a strong learner are utilized within an active learning loop. The weak learner is used to identify promising regions within the design space to explore, while the strong learner is used to determine the exact location of the optimum within promising regions. For each design iteration, exploration is done by randomly selecting evaluation points within regions where the weak learner-predicted fitness is high. The global optimum obtained by using the strong learner as a surrogate is also evaluated to enable rapid convergence once the most promising region has been identified. The proposed approach is tested on two optimization problems. The first is a cosine mixture test problem with 25 local optima and one global optimum. In the second problem, the objective is to minimize indicated specific fuel consumption of a compression-ignition internal combustion (IC) engine while adhering to desired constraints associated with in-cylinder pressure and emissions, by finding the optimal combination of nine design parameters relating to fuel injection, thermodynamic conditions, and in-cylinder flow. The efficacy of the proposed approach is compared to that of a genetic algorithm, which is widely used within the IC engine community for engine optimization, showing that ActivO reduces the number of function evaluations needed to reach the global optimum, and thereby time-to-design by 80
READ FULL TEXT