KPLS-Based Mach Number Prediction for Multi-Mode Wind Tunnel Flow System

In wind tunnels, the Mach number needs to be precisely monitored and controlled. It is difficult obtain directly online, especially when tunnel system operating in multiple modes. To deal with this problem, a prediction algorithm based on kernel partial least squares method proposed for multi-mode systems. First, order reflect real-time changes, time-slice regression adopted. Then, enable model represent information about whole working mode divided by key process variables, mean-value established compared model. considering that systems exhibit strong nonlinear characteristics, method, which suitable systems, used predict number. The results show better than model, models single modes abilities those modes, square more method.