Engine knock is an undesirable combustion that could damage the engine mechanically. On the other hand, it is often desired to operate the engine close to its borderline knock limit to optimize combustion efficiency. Traditionally, borderline knock limit is detected by sweeping tests of related control parameters for the worst knock, which is expensive and time consuming, and also, the detected borderline knock limit is often used as a feedforward control without considering its stochastic characteristics without compensating current engine operational condition and type of fuel used. In this paper, stochastic Bayesian optimization method is used to obtain a tradeoff between stochastic knock intensity and fuel economy. The log-nominal distribution of knock intensity signal is converted to Gaussian one using a proposed map to satisfy the assumption for Kriging model development. Both deterministic and stochastic Kriging surrogate models are developed based on test data using the Bayesian iterative optimization process. This study focuses on optimizing two competing objectives, knock intensity and indicated specific fuel consumption using two control parameters: spark and intake valve timings. Test results at two different operation conditions show that the proposed learning algorithm not only reduces required time and cost for predicting knock borderline but also provides control parameters, based on trained surrogate models and the corresponding Pareto front, with the best fuel economy possible.
A surrogate-assisted optimization approach is an attractive way to reduce the total computational budget for obtaining optimal solutions. This makes it special for its application to practical optimization problems requiring a large number of expensive evaluations. Unfortunately, all practical applications are affected by measurement noises, and not much work has been done to address the issue of handling stochastic problems with multiple objectives and constraints. This work tries to bridge the gap by demonstrating three different frameworks for performing surrogate-assisted optimization on multi-objective constrained problems with stochastic measurements. To make the algorithms applicable to real-world problems, heteroscedastic (nonuniform) noise is considered for all frameworks. The proposed algorithms are first validated on several multi-objective numerical problems (unconstrained and constrained) to verify their effectiveness and then applied to the diesel engine calibration problem, which is expensive to perform and has measurement noises. A gt-suite model is used to perform the engine calibration study. Three control parameters, namely, variable geometry turbocharger (VGT) vane position, exhaust-gas-recirculating (EGR) valve position, and the start of injection (SOI), are calibrated to obtain the tradeoff between engine fuel efficiency performance (brake specific fuel consumption (BSFC)) and NOx emissions within the constrained design space. The results show that all three proposed extensions can handle the problems well with different measurement noise levels at a reduced evaluation budget. For the engine calibration problem, a good approximation of the optimal region is observed with more than 80% reduction in the evaluation budget for all the proposed methodologies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.