AI-based Quality Control

AI-bases Quality Control (2 days)

AI-based quality control is a method of using artificial intelligence (AI) technologies to improve the accuracy and efficiency of quality assurance processes. The goal of AI-based quality control is to automate and optimize various quality control tasks by analyzing large amounts of data, that come directly from the manufacturing process, identifying patterns, and making predictions based on that data.

AI-based quality control can be applied in various industries, such as manufacturing, healthcare, and software development. In manufacturing, for example, AI-based quality control can be used to detect defects in products by analyzing images or sensor data. In healthcare, AI-based quality control can be used to identify potential errors in medical records or diagnostic imaging results. In software development, AI-based quality control can be used to identify bugs or errors in code by analyzing code changes and user behavior.

The key benefits of AI-based quality control include improved accuracy and consistency, faster and more efficient testing, and the ability to identify issues early on before they become more costly or time-consuming to fix. However, it is important to note that AI-based quality control does not replace existing routines, methods and expertise (e.g. Statistical Process Control), but rather augments, enhances and automates existing quality control processes. For example, one can very efficiently perform a 100% digital assessment of all components / processes, instead of the established sample-based assessments.

In this course you will learn the characteristics and benefits of a AI-based quality control. Special focus will be placed on the interplay between established methods (i.p. SPC, Six Sigma), Big Data and the opportunities offered by AI algorithms. You will understand a typical AI-workflow from acquiring and preprocessing data, feature engineering, model training, model evaluation, model deployment, and model management. Furthermore you will gain insights into root cause analysis of quality problems to identify which parts need rework or need to be rejected.

The theoretical topics of the training will be intensified by hands-on exercises, based on real-world IIoT datasets. By default, all exercises are performed with Python.

Course Outline

  • Introduction to AI-based quality control
  • Data sources and data acquisition
  • Process capability and process monitoring
  • Statistical Process Control (SPC) and its application on Big Data Streams
  • Data preprocessing for discrete and continuous processes
  • Feature engineering – how to create quality indicators
  • Supervised learning - application areas, algorithms and model training
  • Unsupervised learning - application areas, algorithms and model training
  • Supervised vs. Unsupervised Learning - when to choose which method?
  • Model evaluation and performance metrics
  • Model inference and special features when used in batch or real-time applications
  • Automated Model Training and Management - Best Practices

Who should attend

Managers of quality control & quality management, production plants, production planning, and production operations. Quality experts who want to learn about the new capabilities of AI in quality control. Data Scientists who want to apply their capabilities into practice in the field of AI-based quality control. Consultants whose objective is to put additional value on the latest innovative technology in the smart factory sector.

What you need to succeed

Basic programming skills in Python (e.g. our training courses Python for Smart Factory Analytics or Getting started with Python).

Did not find the training you are looking for? Please feel free to ask for any other Advanced Analytics training.

Contact us