Das 2016 gegeründetet Start-up understand.ai mit seinen Würzeln am KIT, kombiniert Machine Learning mit menschlicher Sorgfalt. Gerade haben sie erst einen 2,8 Millionen Inevestment getätigt und blicken in eine schnell wachsende Zukunft ihres noch jungen Unternehmens. Wir haben die Gründer im Interview zu der Idee, der Gründungszeit und den Zukunftsaussichten befragt.
The spin-off Renumics GmbH uses machine learning methods to make Computer Aided Engineering more efficient and take the strain off computational engineers.
Crash tests are an expensive affair. In early development stages, collision experiments are therefore often replaced by computer simulations that can be performed thousands of times taking various influential factors into account. These simulations are usually based on computer-supported processes, on so-called Computer Aided Engineering (CAE). This concept centres on computational engineers who compile numerical models, thus assisting constructors in the analysis and optimisation of their designs. The crucial time and cost factors here are the many manual work steps involved. For example, computational engineers invest a considerable amount of time in routine activities such as pre-processing geometries and integrating data instead of being able to concentrate on modelling and analytical work, which is precisely where Renumics comes in. This KIT spin-off has developed a software with which CAE can be automated. In this context, machine learning methods help make simulations workflows considerably more efficient.
The KIT spinoff robodev GmbH has developed an intelligent module construction kit for a profitable production of small quantities in manufacturing enterprises.
Robot-supported automation is experiencing a boom. Nowadays, the automobile branch in particular would be quite inconceivable without modern industrial robots. From punching sheet metal components to the complete car body, whole automation lines are in operation partly without any human action. It is no coincidence that the automobile industry has become the paragon in this area. As a rule, unlike in many other branches, extremely large quantities are involved that all have to be produced according to exactly the same pattern. “The cost of a simple automation solution is at least 80,000 euro. If smaller quantities, below 10,000 items per month, are involved, this investment will usually not pay its way. Slightly below 75 per cent of processes in the German manufacturing industry are therefore manual or have only been automated to a small degree,” explains Dr Andreas Bihlmaier, co-founder of robodev GmbH.
Enough experimenting! The KIT spinoff GoSilico enables the biopharmaceuticals branch to introduce the computer-supported development of manufacturing processes for new agents.
The way from the discovery of a promising agent to its authorisation is tedious. It involves countless experiments that not only cause high costs but also require a considerable amount of perseverance. “It can take up to ten years for a drug to enter the market,” says Dr Thiemo Huuk. This is a shortcoming that he tends to address together with his co-founders Prof Dr Jürgen Hubbuch, Dr Teresa Beck and Dr Tobias Hahn.
With its high-tech 3D printers for high performance polymers, the KIT spin-off Indmatec GmbH is offering undreamt-off possibilities in prototyping and small series manufacturing.
Prof. Dr. Brando Okolo has been dealing with materials research for several years in the course of his academic career. He lectured at Karlsruhe Institute of Technology (KIT) in the field of micro-reforming of metals and plastics, with a focus on 3D printing technologies and Rapid Prototyping. He then took up a professorship at the German University of Cairo (GUC). “In my research, I also dealt with additive manufacturing – that is, on the basis of digital 3D construction data – using polymers as a material to work with. In this period, I already discovered the potential that 3D printing holds for high performance polymers, and I had my first thoughts about going into business,” Okolo recalls. The decision to end his lecturing activities after five years and realise his dream of an enterprise of his own brought Okolo back to Germany and his Karlsruhe environment.