The invention discloses a multi-target optimization and data driving control method in the sugar boiling crystallization process. The method comprises the following steps that the optimization ranges of sugar boiling parameters in the sugar boiling crystallization process are set; the sugar boiling parameters in certain sugar boiling crystallization process are obtained; the sugar boiling parameters are optimized to obtain the expected massecuite temperature, the expected sugar solution supersaturation, the expected sugar solution purity and the expected massecuite volume; the control parameter of a CFDL-MFAPC controller is set, and the expected massecuite temperature, the expected sugar solution supersaturation, the expected sugar solution purity and the expected massecuite volume are converted into expected output signal values of the CFDL-MFAPC controller; and the CFDL-MFAPC controller is executed, and according to the expected output signal values, control input signals of the CFDL-MFAPC controller are obtained to determine the opening degree of a feeding valve in the sugar boiling process. The method of the invention can overcome the problems that a traditional controller is low in robustness and reliability when the mechanism model is complex.