Research, work on the future!

AI-SLAM

In the field of additive manufacturing (AM), far-reaching progress has been made in recent years. With regard to economic, ecological and functional aspects, AM processes are increasingly competitive or even exceed conventional manufacturing processes. Nevertheless, nowadays, most industrial applications of DED are in wear protection and repair in a variety of industries such as aerospace, automotive, tooling, offshore, power generation, and mining industry. One important cost driver and obstacle for broad industrial application of DED is the effort for process development including process parameter optimization and toolpath planning, especially for small badge sizes. The use of artificial intelligence (AI), in particular machine learning (ML), is a key element of the AI-SLAM solution to advance DED by decreasing process development iterations. The solution involves using ML and adaptation algorithms to enable quality prediction and parametric optimization instead of elaborating suitable parameter sets by cost and time-intensive tests.

In addition, the AI should help to improve the quality of the welding results by a layer-by-layer, local adjustment of the process parameters. The input data for ML are delivered by sensors which:
a.) are monitoring the build process (pyrometer, high-speed thermal camera, CCD camera),
b.) capture data layer-wise intermittent (laser triangulation scanner, laser ultra-sound)

The process chain consists of the following steps:
1) Build-up of a predefined number of deposited layers of consecutive layers,
2) online and layer-wise intermittent in-machine inspection of built-up layers
3) evaluation of acquired data using ML models
4) adaption of toolpath planning and local process parameters for the next layers

The Canadian-German consortium – consisting of SMEs and R&D institutes – has the necessary expertise in the field of industrial applications, process development, software and sensor technology and AI to successfully meet the technological challenges of the AI-SLAM project.

Press release “LMD processdevelopment supported by KI methods.”

ProLMD

The aim of this project is to develop an efficient process chain including machining equipment and laser based processes. For validation demonstrator parts introduced by the industrial partners, are used. In ProLMD robots are used to reduce Costs and increas the System flexibility. In Addition to this flixible shielding units will help to reduce the amount of shielding gas, significantly. New processing heads, capable working with wire and powder and a hybrid-Ready CAM system are also included in the developments.

HyProCell

The objective of this EU funded research project is to develop and demonstrate a new concept of multi-process production cell, featuring both, additive and subtractive manufacturing connected over ICT platforms

The developed concept will be implemented at industrial (pilot facility) level to validate it in real settings, manufacturing real parts and measure the benefits (TRL5 -> TRL7).

BCT contributes to this project supporting the DED machine with measuring devices for capturing the real part geometry and with corresponding adjustment methods to align the parts or to adapt the NC programs to the individual needs.

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 723538.

OpenHybrid

The focus of this project is on the development of manufacturing solutions that use both additive and subtractive manufacturing methods within one machine. For this purpose, a broad range of machines – ranging from classic machine tools to gantry machines – are supported. The objective is to realize a continuous, uninterrupted process chain on one machine. Both powder-based and wire-based methods are employed.

The methods investigated are suitable for the creation of new parts and, in particular, for the repair of high-value components made of metallic materials.

BCT is involved, within the framework of this project, in the development of special software solutions giving the operator simplified access to complex technologies. Adaptation is used to adapt both additive and subtractive methods to the particular parts.

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 723917.

AMAZE

Within the framework of AMAZE, the largest European research project in the sector of additive manufacturing, various AM methods have been investigated and improved in order to increase the performance capability of the systems and the quality of the parts. This work is supported by newly developed simulations and non-destructive testing methods. Following the incorporation of adaptive approaches into the LMD method, BCT has played an active role in the remachining of parts produced by additive manufacturing.

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 313781.

MBFast18

To be in a position to master the challenges posed by the series manufacture of large parts in the future as well, we have to depart from classic work flows in which parts are usually transported from one process to the next. Within the scope of the project MBFast18, we have explored the question of how production volumes can be increased by bringing the process to the part.

BCT was involved in the referencing of a local work unit based on tracking data. With this method a machine center with a limited work space can be securely placed on a large part. –> Video