Blog
Data Curation Checklist for Condition Monitoring (Part 1)
Data collection for condition monitoring has several pitfalls, potentially leading to data that is not suitable for training robust machine learning models. The data problems resulting from the data collection include but are not limited to the presence of failures in the recording equipment, the dominance of specific operating conditions, or mislabeled audio samples. In this article, we will thus help you to ask the right questions and equip you with a checklist you can use when collecting and preparing data for your condition monitoring use case.
Daniel Klitzke
May 24 • 6 min
Improving Sample Selection in Surrogate Modeling
Selecting samples for training robust surrogate models in simulation can be a real challenge. Active learning-like approaches where samples are selected iteratively can help overcome this challenge. We show how to apply such a procedure to save time and computational resources while making your surrogate model even more robust.
Daniel Klitzke
Mar 24 • 4 min
Building Robust Visual Inspection Models Using Amazon Lookout for Vision
Building robust models for Visual Inspection in production settings can be a real challenge. Here, cloud services like Amazon Lookout for Vision promise relief for model training but have limitations regarding data curation. This article explores those potential shortcomings and shows how to improve over them to leverage these services to the fullest.
Daniel Klitzke
Mar 15 • 8 min
Removing Unwanted Bias
Making your data match the real-world data of your use-case is crucial for training a robust machine learning model. This post shows you how to interactively curate your data to adapt your data in an informed manner.
Daniel Klitzke
Feb 16 • 3 min
Matching Vibroacoustic Test and Simulation Data With Machine Learning
The acoustic and vibrational behavior of a product is a cornerstone of the user experience. This is true for product categories from vacuum…
Stefan Suwelack
Feb 15 • 5 min
How to Quickly Find and Correct Label Errors
Ensuring label consistency is critical for building robust machine learning models. This post shows you how to achieve label consistency in a data centric way.
Daniel Klitzke
Feb 3 • 2 min
Training an Acoustic Event Detection System Using Renumics Spotlight
Machine Learning based systems for acoustic event detection typically require a vast amount of training data. Intelligent labeling techniques open up new possibilities for small data scenarios.
Daniel Klitzke
Dec 22 • 5 min
How Data-Centric ML Helps to Build Reliable Models Fast
ML researchers typically iterate different model architectures on a fixed dataset that they often know very little about. In real use cases, it is often a good idea to focus most efforts on the data and not on the model.
Stefan Suwelack
Dec 9 • 8 min
Data-Centric AI for Engineering and Manufacturing
Data-centric machine learning is an emerging paradigm. Is this a game-changer for ML in engineering and manufacturing?
Stefan Suwelack
Nov 22 • 4 min
The AI-Assisted Engineering Canvas
Data-driven methods have arrived and promise to speed up product development. The AI-assisted Engineering Canvas helps to get started.
Stefan Suwelack
Aug 30 • 8 min
What Is AI-Assisted Design?
Generative ML methods have achieved tremendous success in image and audio processing. Can mechanical engineers benefit from this technology?
Stefan Suwelack
Sep 16 • 6 min
Use Cases for AI-Assisted Engineering
Machine learning will transform engineering work. But how does this process look like and where will it start?
Stefan Suwelack
Feb 24 • 6 min
What Is AI-Assisted Engineering ?
Engineers spend a lot of time on manual routine tasks. Novel machine learning techniques promise to change that.
Stefan Suwelack
Jan 30 • 5 min
