A hybrid optimization method combining an improved bioinspired algorithm based on membrane computing (IBIAMC) with a sequential quadratic programming (SQP) algorithm (HBS) is proposed to overcome difficulties in solving complex constrained problems. The netted membrane structure of FIBS is based on the distributed parallel computational mode of membrane computing (MC) and inspired by the shape, structure, and function of the Golgi apparatus of eukaryotic cells. The different localized subalgorithms in the proposed hybrid method are translated from the different local rules used in different membranes. When this hybrid method is applied to solve optimization problems, these subalgorithms operate in an orderly fashion on the objects containing a tentative solution in accordance with their probabilities; simultaneously, the communication object comprising best objects is transferred between different membranes according to the communication rule. The search capacity of the proposed method is ensured by both the global search subalgorithm of the improved BIAMC and the local search subalgorithm of SQP. Eight benchmark constrained problems are used to test the performance of the hybrid method, and then two simulation examples of the gasoline blending scheduling problem and the process design of the Williams-Otto flow sheet are applied to validate the proposed algorithms.