On application of machine learning in fixture design and clamping optimization

In machining operations, frictional contact between workpiece and clamps makes clamping scheme a complex and non-linear problem with parameters such as contact area, state of contact, clamping force, wear and damage in the contact area and deformation of the component. One attribute of an efficient fixture plan is to know the optimum values of clamping forces. To solve this optimization problem, this study along investigating utilization of support vector machines (SVM) for fixture optimization, presents a hybrid method that uses finite element analysis (FEA) with a supportive combination of artificial neural network (ANN) and genetic algorithm (GA). A frictional model of workpiece-fixture system under cutting and clamping forces is solved through FEA. The results of this analysis are used for training and querying SVM and ANN where they are required to recognize a pattern between the clamping forces and state of contact in the workpiece-fixture system and workpiece maximum elastic deformation. Using the identified pattern a GA based program determines the optimum values for clamping forces that do not cause excessive deformation or stress in the component. The advantage of this work to similar studies is predicting the contact status between clamps and the workpiece. The results contribute to automation of fixture design task and computer aided process planning.