講座內(nèi)容： Evolutionary Computing (EC), which is based on the principles of natural selection and genetic inheritance, is often considered a global optimization methodology with a metaheuristic or stochastic optimization character. It is distinguished by the use of a population of candidate solutions rather than traditional approach of iterating over a single point in the search space. EC is being increasingly applied to many problems, ranging from practical applications in industry to cutting-edge scientific research. The plenary will provide a brief overview of this exciting research field including opportunities and challenges faced in applying EC to a variety of real-world multi-objective problems, such as design automation, robust optimization and logistic application. In particular, a case study involving the estimation of remaining useful life (RUL) for turbofan engines in the area of robust prognostic will be studied. As one of the key enablers of condition-based maintenance, prognostic involves the core task of determining the RUL of the system. The plenary will also present an application of evolutionary deep learning ensembles to improve the prediction accuracy of RUL estimation for turbofan engines.