Data Science in Manufacturing2020-05-29T14:13:04+02:00

Data Science in Manufacturing

Artificial Intelligence increases adherence to schedules

The manufacturing industry has the advantage of a lot of data available in many systems. The disadvantage, however, is that the collected data is usually far from practical. The consequence is very inaccurate planning, which makes it difficult to give customers exact delivery dates.


98% Operational Excellence
42% Better data
90% More precise planning

Machine learning improves planning values in machine and systems engineering

Machine and systems engineers are familiar with this problem. The very complex production planning of purchased parts and in-house production with many variants is a difficult challenge even without inaccurate planning values. The use of machine learning helps

achieve strong improvements, for example to determine replacement times more reliably and precisely. This is because the data often does not correspond to reality; production planning, for example, is then calculated to be 10 instead of 20 days. The result is very imprecise delivery dates and frequent delays. These errors can be eliminated by data cleansing using machine learning and the quality of master data therefore improved in the long term. Historical SAP data on suppliers, materials or orders, among other things, help to improve replenishment times by up to 42 percent.

The precise planning values can then be integrated into a mobile, dynamic shop floor management system where productivity key figures can be viewed directly in production at each machine via a dashboard. In this way, production can also be made digital and paperless.

0% faster response time
0monitored sensors
0years of training data

Data Cleaning: Pitfalls and Solutions

As the interest in machine learning and artificial intelligence grows, companies regularly find themselves confronted with the dissatisfying quality of their data. This discovery is either made early-on with a structured approach, or a lot later, when poor data quality is identified as the root-cause of poorly performing models. In either case, the next step should be a methodical exploration of the available data, followed by a series of steps to remedy the identified issues. In this article, I will [...]

Load More Posts

Would you like to learn more about data analytics and data science for the manufacturing industry as well as other successful projects?

Request now

Latest Blog


Im 2. Teil des Interviews mit Dr. Roos von der Neuropädiatrie des Universitätsklinikum Essen erfahren Sie, wie ein Verfahren auf Basis von #ArtificialIntelligence die Diagnose & Behandlung neuromuskulärer Erkrankungen optimieren soll >>


Great #QlikWorld conference this year with very interesting sessions! Also online the place to be for all #qlik enthusiasts! Thanks @qlik team! 🎉👍

Load More...


Recent Posts