Predictive Quality Analytics
Quality 4.0: Leveraging on your data to achieve best in class output!
What we do
We understand the high-quality standards of the industrial sector and its need for continuous innovation and output optimization. By combining our client’s quality management expertise and production data with our predictive analytics know-how, we can identify root causes and early recognize or even prevent quality issues. This is an iterative process . We use various data analysis techniques and state of the art machine learning algorithms to develop robust models for our customers.
These models help to improve the quality of products and simultaneously result in decrease of scrap, warranty claims, rework cost as well as quality-related machine downtimes.
Are you interested? Talk to us about the Predictive Quality solution you need!
Case Study
Reducing scrap and increasing efficiency
Similar to predictive quality use cases in the automotive, pulp and paper, steel and wood industry, we also worked on a solution for an international leader in brick production. The production line of bricks starts with the preparation of the material, through grinding and milling. Then the bricks are being shaped and dried. Our client was interested in reducing the rate of scrap output in one of its production facilities.
Challenge
Quality management in this facility was only done at the end of the production process. This makes it hard to link scrap output to its root causes and understand when and why faulty bricks are being produced. This makes the process not only unpredictable but also inefficient.
Solution
By combining the quality data with the machine and sensor data from various production steps, we detected patterns in the data that made us understand where quality issues occur and what causes them. Building on that, our quality control AI predicts potential problems in the production line early on.
Result
Based on our recommendations for more accurate settings based on real-time data- insights, production failures could be significantly reduced. The process became more efficient and the scrap rate significantly reduced.
The Process
Together with an interdisciplinary team from both the client's side and craftworks, the concrete questions that should be answered were evaluated.
Using the gathered data from different production steps, we develop a machine learning algorithm that detects quality problems and its root causes. The results are being visualized in a way that makes it easy for the client’s operators to read and understand how the system and its recommendations work. After a successful proof of concept, the algorithm can be transformed and applied to other production machines step by step.
In a next phase, instead of acting upon recommendations from the system, the settings of parameters can be automated. The result: an even more efficient process and better quality assurance.
How you can work with us
Consultancy
You would like to be advised on the basic setup of an industrial AI approach in your company? You need guidance in how machine learning can help you make your processes more efficient and cost effective? Through tailor made workshops we will help you find the right approach for your company.
Co-Development
You already have a functional team in place, but you are short on manpower or specific experience? Our team is used to working closely with our customers on new solutions and facilitates through knowledge sharing.
Full Service
You are looking for a trusted partner to develop a robust customised solution to your specific needs and requirements? Well, you found us!
A selection of our Industrial AI clients
With craftworks it was simple and uncomplicated. After an initial conversation, we could start a project within a short amount of time. While the data scientists at craftworks supported us in drawing valuable conclusions from our data, the close collaboration together with their domain experts made it possible to have fast results within a month.
Stefan Kermer
Wien Energie, Head of Innovation and Strategic Projects
“
Industrial AI -
10 Steps to Success
Learn more about the successful way of
implementing Industrial AI in practice.
