Blast furnaces are still manually operated in the steel industry. To realize an efficient and stable operation, the authors developed an operation guidance system for controlling hot metal temperature and applied it to actual furnaces. The system features a newly developed 2D transient model that describes the sluggish and complicated process dynamics. Based on the transient model, nonlinear model predictive control (NMPC) and moving horizon estimation (MHE) were adopted to provide operators with appropriate control actions while minimizing the undesirable influence of disturbances. The online validation results demonstrated that the developed operation guidance system successfully reduced the variance of HMT by 1.9°C.