During the manufacturing process of aircraft, quality deviation problems inevitably occur due to the high complexity of aircraft design, manufacturing errors, tooling mistakes, human factors, environmental influences, design defects, and other factors. The current quality deviation control system of civil aircraft suffers from two problems: (1) quality deviation control data are scattered in more than 100 management systems, and it is difficult to extract quality data-related information from the whole life cycle of the aircraft involving the main manufacturer and each supplier and (2) there is a lack of quality data analysis and a closed-loop information-physics fusion system for quality deviation control. Thus, it is difficult to locate the quality deviation problems and it takes a long time to deal with these problems as well. In this paper, a digital twin-based quality deviation control model is proposed. Through the digital twin modeling based on asset management shell technology, the multi-source and heterogeneous quality deviation data can be extracted and integrated. Furthermore, to deal with the second problem, a quality deviation system has been built based on digital twin. In this system, the aircraft quality deviation data can be analyzed by the FP-growth association rule algorithm and the results are provided through the system to guide the assembly site, improving the efficiency and accuracy of quality problem-solving in the physical world. In addition, a case study is stated, where the proposed approach is applied to deal with the aircraft quality deviation problems.