DEVELOPMENT OF AN AUTOMATED ASSEMBLY PROCESS SUPPORTED WITH AN ARTIFICIAL NEURAL NETWORK
Journal Title: Journal of Machine Engineering - Year 2018, Vol 18, Issue 3
Abstract
A central problem in automated assembly is the ramp-up phase. In order to achieve the required tolerances and cycle times, assembly parameters must be determined by extensive manual parameter variations. Therefore, the duration of the ramp-up phase represents a planning uncertainty and a financial risk, especially when high demands are placed on dynamics and precision. To complete this phase as efficiently as possible, comprehensive planning and experienced personnel are necessary. In this paper, we examine the use of machine learning techniques for the ramp-up of an automated assembly process. Specifically we use a deep artificial neural network to learn process parameters for pick-and-place operations of planar objects. We describe how the handling parameters of an industrial robot can be adjusted and optimized automatically by artificial neural networks and examine this approach in laboratory experiments. Furthermore, we test whether an artificial neural network can be used to optimize assembly parameters in process as an adaptive process controller. Finally, we discuss the advantages and disadvantages of the described approach for the determination of optimal assembly parameters in the ramp-up phase and during the utilization phase.<br/><br/>
Authors and Affiliations
Paul BOBKA, Jakob HEYN, Jann-Ole HENNINGSON, Martin RÖMER, Thomas ENGBERS, Franz DIETRICH, Klaus DRÖDER
Keywords
Related Articles
- EP ID EP376428
- DOI 10.5604/01.3001.0012.4605
- Views 77
- Downloads 0
Evaluation of different approaches to 3d numerical model development of the contact zone between elementary asperities and flat surface
This paper presents two triaxial finite element (FE) models: a “full model” and a “quarter model”, representing the contact between the specimen’s rough surface and the ideally smooth and flat surface of the punch. Model...
THE EFFECT OF ALTERNATIVE CUTTER PATHS ON FLATNESS DEVIATIONS IN THE FACE MILLING OF ALUMINUM PLATE PARTS
In this paper the relationships between the alternative machining paths and flatness deviations of the aluminum plate part, were presented. The flatness tolerance of the main surface of the plate part has crucial meaning...
DIGITAL TWIN BASED SYNCHRONISED CONTROL AND SIMULATION OF THE INDUSTRIAL ROBOTIC CELL USING VIRTUAL REALITY
During the years common understanding of the possibilities and perspectives of Virtual Reality (VR) usage has been changed. It is thought that VR is mainly used in entertainment purposes, but it is being used already for...
DESIGN APPROACH FOR HIGH-DYNAMIC PLANAR MOTION SYSTEMS BASED ON THE PRINCIPLE OF KINEMATICALLY COUPLED FORCE COMPENSATION
Machine tools’ feed dynamics are usually limited in order to reduce excitation of machine structure oscillations. Consequently, the potential increase in productivity provided by direct drives, e.g. linear motors, cannot...
INVESTIGATION OF A HIGH-FORCED COOLING SYSTEM FOR THE ELEMENTS OF HEAT POWER INSTALLATIONS
The studies of the ultimate thermal flows have been carried out in metallic and poorly heat-conducting porous structures, which operate when gravitational and capillary forces act jointly and cool various devices of ther...