The uncertain optimization algorithm to suppress vibration of the crankshaft system with random-interval hybrid variables

Abstract

This study proposes a new uncertain optimization algorithm to suppress vibration of the crankshaft system. In this new algorithm, the interval expression with random-interval hybrid variables is obtained by the confidence level. In addition, the interval order relation, interval probability, radial basis function neural network technology, and multi-objective genetic algorithm are applied to construct uncertain optimization algorithm with random-interval hybrid variables. Moreover, typical examples are used to demonstrate the effectiveness of the proposed algorithm. To suppress vibration of the crankshaft system, the optimization–Latin hypercube sampling design is used to obtain the experimental scheme and the data sampling is performed by multi-body system simulation of the vibration performance. Then, the radial basis function neural network is built considering the torsional displacement and transient stress of the crankshaft. Finally, the uncertain optimization algorithm is operated on the crankshaft structure design of the high-power reciprocating compressor. The results demonstrate that the robustness of the vibration performance and strength property is improved through the uncertain optimization algorithm, compared with that through deterministic optimization. The uncertain optimization algorithm to suppress vibration of the crankshaft system with random-interval hybrid variables is an efficient and effective approach, which is finally proved by the prototype test.