Fixtures are widely used in almost any modern manufacturing. They add directly to the cost base, impact manufacturing firms' responsiveness and contribute to the overall product quality. Computer-aided intelligent fixture design was developed over the years to give a competitive edge to the manufacturing firms who are facing unprecedented competition and challenges. Among the techniques, case-based reasoning (CBR) method leverages previous design experience and emerged as one of the most popular methods. However, existing CBR methods are more focused on frame work building and less on detailed techniques on case retrieving, which is the central part of any CBR methods. This would inevitably impose negative impact on the overall efficiency of any CBR-based methods. In light of this, this paper presents a new case retrieving method based on a constrained common subgraph technique. This technique tracks down similar cases from a case library through comparing the maximal common subgraphs constrained by meeting fixturing functional requirement. Efficient and robust algorithms have been developed subsequently to implement this technique. The developed method can be highly effective for retrieving cases related to some manufacturing parts with complex geometry. An illustrative example, combined with other key fixture design factors, demonstrates the effectiveness of the proposed method. The presented method is intuitive and can be used in combination with existing CBR methods and well positioned for the upcoming "big data" manufacturing. Note to Practitioners-Providing capability for rapid responsiveness, enhancement of product quality, and production at low cost are the three main objectives for the wide manufacturing firms. Fixtures are widely used across manufacturing and assembly processes, and they are closely linked to all these three objectives. Today's manufacturing enterprises face unprecedented challenges to control costs and to deal with an ever increasing number of product variants and smaller lot sizes. All these facts raise high demands on computer-aided intelligent fixture design. Case-based reasoning (CBR) method, tackling new problem by using the solution of similar past problems or through revising the previous solution, gains popularity among researchers and practitioners. However, existing CBR methods put more focus on CBR framework design while the case retrieving, the key process of any CBR methods, still relies on some basic feature attributes comparison. This would inevitably reduce the overall effectiveness of the CBR method. In view of that, this paper proposed a graph method for case retrieval based on comparing maximal common subgraphs (MCSs). Dictated by fixture functional requirement, a constraint (to match machining features and/or other user defined requirement) has been imposed during the MCS search process. This constraint turns out to be quite useful in term of reducing search space and increasing computation efficiency. Robust algorithms have been subsequently developed to implement this technique. Graph is a powerful tool to analyze structured object, the proposed method can handle some bespoke and complex fixture design cases. The presented method is intuitive and flexible and can be integrated into existing CBR frameworks to improve the allover effectiveness of current intelligent fixture design.
