A New Algorithm for Optimal Parameter Settings of Light-Gauge Steel Wall Sound Isolation Systems

A new algorithm based on orthogonal arrays is developed to determine the optimal solution among the optional settings using the design of experiment approach for newly designed devices. The proposed algorithm begins with several successive orthogonal arrays and ends with a full factorial array. In the proposed algorithm, we suggest a mandatory verification of two additional settings at each orthogonal array to avoid errors in identifying the best level of the dominant factor, which often occur when a non-separable problem is solved. We initially verify the proposed algorithm by applying it to a well-known benchmark problem, the Rosenbrock function. The proposed procedure is described in detail in this paper. To distinguish the superior performance of the proposed algorithm relative to that of other design of experiment approaches, we study three types of problems with non-interactive or interactive variables. Finally, a light-gauge steel wall sound isolation system design is used to demonstrate the robust performance of the proposed algorithm. The results show that the proposed method not only provides a final solution that is identical to the problem’s exact solution but also requires much less computation time than a full factorial method.