Producing large workpieces from lead-bronze alloys by centrifugal casting is an energy- and time-intensive process. In order to avoid manufacturing errors and thus expensive rejects, the TH Köln, together with the Martin Luck Metallgiesserei GmbH in Saarland, has digitised the casting process and optimised the process parameters using artificial intelligence (AI).
“Among other things, our project partner manufactures plain bearings for machines in the mining industry. The components, which weigh up to 1.5 tonnes, are produced in very small batches. Accordingly, the machine parameters have to be readjusted for almost every part,” explains Prof. Dr Danka Katrakova-Krüger from the Institute for General Mechanical Engineering at TH Köln.
Up to now, both the settings and the documentation have been done manually, which is prone to errors and makes a targeted evaluation with high reproducibility impossible. According to the project partners, centrifugal casting could benefit greatly from digitalised and (partially) automated production. In the manufacturing process for rings, discs and pipes, liquid metal – in this specific case an alloy of copper, tin and lead – is filled into a mould rotating around the central axis, the so-called ingot mould. The molten metal is pressed against the mould wall by rotation and hardens there.
“Sometimes it takes three attempts until a product is perfect – the failed attempts have to be melted down again. The associated expenditure of energy and resources, the tying up of capacities and the long delivery times are a burden on the company. AI-supported production systems can help solve these problems,” says Prof. Dr. Christian Wolf from the :metabolon Institute at the university.
Defining process parameters and training AI
First, the project partners investigated which process parameters have a particularly large influence on the quality and, above all, on the distribution of the lead in the finished workpiece.
“Since lead has a much lower melting point than bronze and is also significantly heavier, inhomogeneous lead distribution can occur during the cooling process, making the product unfit for use,” Katrakova-Krüger explains.
Relevant parameters include casting temperature, cooling conditions, rotation speed of the mould or quantity and temperature of the cooling water used. The project team also digitised the existing machinery so that the selected process parameters and machine settings can be automatically recorded and correlated with successful or unsuccessful casting results. An artificial intelligence was then trained with this data.
“We can enter the geometry of the desired component into the resulting system. The AI then suggests relatively reliable parameters that have led to success with the same or similar components in the past,” says Wolf.
In addition, the system can evaluate whether a finished component meets the quality requirements. The project partners want to build on the results and develop them further in order to predict component quality even better.
The research project by the Faculty of Computer Science and Engineering at TH Köln and Martin Luck Metallgießerei was funded under the Central Innovation Programme for SMEs (ZIM) of the German Federal Ministry of Economics and Climate Protection from September 2020 to June 2023. TH Köln is one of the most innovative universities of applied sciences. Currently, around 25,000 students are enrolled in about 100 Bachelor’s and Master’s degree programmes.