Multi-Objective Approach to Automated Fixture Synthesis Incorporating Deep Neural Network for Deformation Evaluation

Authors：Alshameri, Taqiaden; Ding, Heng; Dong, Yude^*; Yiheng, Zhu; Hui, Jin; Maqram, Ahmed

Source：ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING, 2023, 84: 102579.

DOI：10.1016/j.rcim.2023.102579

• Fixture synthesis
• Robust
• Multi -objective optimization
• Simulated annealing
• Deep neural network
• Finite element analysis

In machining, the synthesis of a fixturing schema significantly impacts the accuracy of the final product. Moreover, A robust and automatic configuration of fixture elements can reduce production costs and eliminate the need for expert labor to perform the task. Given the multi-modal problem of fixture synthesis, this article presents a multi-objective approach to fixture synthesis in the discrete domain. The performance criteria are localization accuracy, detachment of locators, workpiece deformation, severity and dispersion of reaction loads, and the spacing between contact points. Optimization is performed via an improved Declining Neighborhood Simulated Annealing algorithm (DNSA). To achieve consistent performance over different inputs, the number of iterations follows a Shanon entropy index reflecting the recurrence of folds/corners. Except for deformation, all other objectives are derived from the kinematic analysis of the workpiece-fixtures system. In contrast, deformation is estimated via a Constitutive Deep Neural Network (CDNN). Both models incorporate the machining loads as quasi-static intervals. A new strategy is adopted for the trade-off based on the Z-score quantification of objectives through a pre-calibration run of DNSA. Numerical examples demonstrate the implementation flow of our generalized CAD-based tool developed for the purpose. The approach is verified and proved efficient in automating the robust selection of a fixture layout for a prismatic workpiece.