Hybrid semiparametric models integrate physics-based (“white-box”, parametric) and data-driven (“black-box”, non-parametric) submodels. Black-box models are often implemented using artificial neural ...networks (ANNs). In this work, we investigate the fitness of symbolic regression (SR) for black-box modelling. The main advantage of this approach is that a trained hybrid model can be expressed in closed form as an algebraic equation. We examine and test the idea on a simple example, namely the v-shape bending of a metal sheet, where an analytical solution for the stamping force is readily available. We explore unconstrained and hybrid symbolic regression modelling to show that hybrid SR models, where the regression tree is partly fixed according to a-priori knowledge, perform much better than purely data-driven SR models based on unconstrained regression trees. Furthermore, the generation of algebraic equations by this method is much more repeatable, which makes the approach applicable to process knowledge discovery.
The present investigation deals with an external-force laser assisted bending process of Grade 2 CP titanium and AA 7075 T6 aluminum sheets. High bending angles, sharp fillet radii and control of ...springback were achieved by tuning the contact pressure of a hydraulically driven tool with the local and selective heating of the bending zone by irradiation with a high power diode laser. First, the role of laser operational parameters, namely power, scanning speed and number of passes, in metal bending was investigated, allowing to identify the most suitable processing window. Second, a custom-built equipment to measure the bending angle during the forming process, together with the metal temperature, was implemented. Real-time monitoring of the bending angle and temperature allowed to evaluate the continuous evolution of the geometry of the metal substrates during the external force laser-assisted bending process. Experimental results showed both metal sheets could be bent to high angles with very low fillet radii by the appropriate combination of the tooling contact pressure and selective laser heating of the bending zone. Laser heating also reduces the risk of rupture in both metals during bending at high angles, limits the springback extent up to 10 times on titanium and 30 times on aluminum in comparison with conventional bending process and does not affect significantly the visual appearance of the bending zone.
Display omitted
•External-force laser assisted bending process of Grade 2 CP titanium and AA 7075 T6 sheets.•High bending angles, sharp fillet radii and control of springback in both the metal sheets.•Tuning the contact pressure of a tool with heating of the bending zone by laser irradiation.•Metal sheets could be bent to high angles, with very low fillet radii and limited springback.•Laser heating limits up to 30 times the springback extent in comparison with conventional bending.
Our planner allows the extraction of the metal sheets from a press-brake. Since the solution must respect safety standard, this operation can be very complex. For this reason it is useful to usean ...automatic system to plan these operations. Thus, we have developed a specific planning algorithm, called EFT (Exit from Tools), that utilizes a hybrid approach, combining a probabilistic roadmap with standard operations on the Cartesian configuration space. In addition, our algorithm has the important feature to be automatically reconfigurable. We performed several tests solving a set of critical real cases by WorkCellSimulator, an industrial software system for simulating manufacturing processing.
PDF
