Real-time part detection in a virtually machined sheet metal defined as a set of disjoint regions

Abstract

In sheet metal machining process, it is of extreme importance to be able to detect cut parts, differentiating the blank and processed elements. When the parts are cut from the rest of the sheet, such elements are prone to move freely and may jump or cause damage to the machine, or even affect workers’ safety. In this scenario, the simulation of sheet machining processes becomes important. This work presents a collection of algorithms to recover in real time the geometrical information of a machined sheet, taking into account that it is subdivided in an arbitrary number of disjoint regions. The proposed algorithms join all the subdivisions of the sheet in a common image-based representation, and then the existing cut parts are detected. Four variants of such algorithms are presented for different variations of the statement problem. Some tests are conducted to show the computational performance of the algorithms, including a discussion of the advantages of each of them regarding their inclusion in a real-time simulator.

Keywords:

• CNC machining
• part detection
• interactive simulation
• image-based algorithms
• sheet metal
• nesting planning

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

We thank the Basque Government Industry Department for the financial help received under the GAITEK research program.