Bridge the gap: Enabling ML for safety-critical industrial applications

Do you want to use machine learning (ML) in safety-critical industrial applications to automate your production or make it more efficient? You are not sure how to bridge the gap between the core safety principles? Then book our in-house training “Enabling ML for safety-critical industrial applications” for your company.

Considering existing and future ISO standards for AI, safety, and automation, we guide you through an appropriate selection of methods and tools for integrating machine learning into your project without risking the reliability and safety of the application. With the acquired knowledge you will be able to shape the development and assessment of ML-based safety-related functions to understand where to apply advanced ML techniques without undermining safety.

Learning objectives

By successfully completing this course, you will be able to:

• Recognize the impact of machine learning (ML) on functional safety and the safety of the intended functionality (e.g. IEC 62061, ICE TS 62998).
• Utilize ML key concepts and terminology relevant to the formulation of a safety assurance argument (e.g., robustness, bias, prediction certainty).
• Develop a project-specific safety-lifecycle that integrates ML-specific safety activities and artefacts into an overall system-level development process.
• Derive specific safety requirements for an ML-based function from a system level context.
• Evaluate a given ML-based function with respect to its safety-related properties and identify insufficiencies affecting the functions safety.
• Implement proven methods to correct common ML insufficiencies during design and operation time.
• Assess new ML strategies and countermeasures for insufficiencies toward ensuring the safety of an ML-based function.

Target audience

The course is designed for engineers who want to integrate AI into their production processes and must provide the corresponding safety verification by assessing and ensuring the safety of functions and systems based on components using some form of ML. The curriculum offers a structured framework and a comprehensive toolkit for safely employing ML in increasingly changing and complex scenarios.

Prerequisites

Participants should have experience with applying industry standards and a basic understanding of ML techniques. Prior safety knowledge is beneficial but not mandatory.