Candy production processes involve many process variables. Operators often find it difficult to effectively monitor the process data, analyze current states, detect and diagnose process anomalies, and take appropriate actions to control the processes. The objective of this work is to develop an intelligent control system of candy production process to improve final candy quality and to increase production efficiency with good human-machine interfaces. The study is conducted by using virtual instrument, multi-sensor data fusion and fuzzy control technology to online detect and control typical parameters. Experiment results show that this system can reach requirements of processing accuracy and real-time property and is highly cost-efficient and practical.