Jungheinrich Accelerates Battery Development with Monolith AI Models

[Cengiz Özemli]

## Jungheinrich Accelerates Battery Development with Monolith AI Models

Jungheinrich is reducing testing time and the need for physical tests in its battery development processes for electric industrial vehicles by using AI-powered models.

### AI-Powered Early Battery Performance Prediction

In collaboration with Monolith AI, Jungheinrich analyzes early-stage battery test data with the help of machine learning algorithms. This allows engineers to predict critical indicators related to battery performance before extensive physical validations.

This method provides a solution to the increasingly complex battery integration issues that arise with new battery chemistries and growing performance requirements.

### Technical Specifications

• Early performance prediction: Key parameters such as efficiency, durability, and behavior under load
• Accelerated technical validation: Early approval of design decisions through data-driven analyses
• Reduced test scope: Verified predictive models replace physical tests

### Efficiency in the Development Process with AI-Powered Engineering

Manufacturers aiming to adapt to rapid changes in battery technologies can shorten their R&D processes by 20% to 80% with AI applications. Predictive models enable prioritization of critical experiments and focus on high-impact design improvements.

### Central Engineering Data Platform

As part of the collaboration, a platform is being created for the centralized management of engineering data and analyses. On this platform:

• Historical test data sets
• Validated predictive models and performance analyses
• Future test and design recommendations

support decision-making processes by increasing project-based knowledge sharing and consistency among teams.

### Applications in Electric Industrial Vehicles

Battery performance directly affects the range, charging behavior, and efficiency of electric vehicles. With AI-powered evaluations, Jungheinrich aims to enhance the performance and sustainability of its electric product range.

Compared to traditional testing methods, AI-based approaches allow for the simultaneous evaluation of many design scenarios, thereby shortening time-to-market and utilizing engineering resources more effectively.

This collaboration reflects a general trend in the industry where data-driven tools are increasingly integrated into product development processes.