A novel real-coded quantum-inspired genetic algorithm and its application in data reconciliation

Data reconciliation techniques play a significant role in the industrial manufacture process, especially in the petrochemical industry. Different heuristic optimization methods have been proposed to solve this problem in previous study. In this paper, a novel real-coded quantum-inspired genetic algorithm (RLCQGA) is proposed, which has stronger search ability and quicker convergence speed, not only because of the introduction of real number coding method, but also due to interval division technique. The proposed approach is tested with five standard benchmark functions and two industrial process cases. Detailed comparisons with similar approaches are given and discussed. The promising results illustrate the efficiency of the proposed method and show that it could be used as a reliable tool for solving nonlinear data reconciliation problems.