Search

The constantly increasing challenges of production technology for the economic and resource-saving production of metallic workpieces require, among other things, the optimisation of existing processes. Forming technology, which is confronted with new challenges regarding the quality of the workpieces, must also organise the individual processes more efficiently and at the same time more reliably in order to be able to guarantee good workpiece quality and at the same time to be able to produce economically. One way to meet these challenges is to carry out the forming processes in closed-loop control systems using softsensors. Despite the many potential applications of softsensors in the field of forming technology, there is still no definition of the term softsensor. This publication therefore proposes a definition of the softsensor based on the definition of a sensor and the distinction from the observer, which on the one hand is intended to stimulate scientific discourse and on the other hand is also intended to form the basis for further scientific work. Based on this definition, a wide variety of highly topical application examples of various softsensors in the field of forming technology are given. [ABSTRACT FROM AUTHOR]

Closed-loop control of product properties is becoming increasingly important in forming technology research and enables users to counteract unavoidable uncertainties in semi-finished product properties and process environments. Therefore, closed-loop controlled forming processes are considered to have the potential to reduce tolerances on desired product properties, resulting in consistent qualities. The achievement of associated increases in robustness and reliability is linked to enormous requirements, which in particular include the inline recording of the product properties to be controlled and the subsequent adaptation of the process control through the targeted derivation of manipulated variables. The present paper uses the example of an air bending process to show how the bending angle can be controlled camera-based and how springback can be compensated within a stroke by recording force signals and subsequently predicting the loaded bending angle using machine learning algorithms. The results show that the combined application of camera-based control and machine learning assisted springback compensation leads to highly accurate bending angles, whereby the results strongly depend on the machine learning algorithms and associated data transformation processes used. [ABSTRACT FROM AUTHOR]