İnci Akü & İnci Radar Open Innovation Call
AI-Powered Quality and Traceability in Battery Manufacturing
As İnci Akü and İnci Radar, we seek to collaborate with technology developers and startups to enhance quality in our battery production processes, reduce scrap rates, and strengthen our data-driven decision-making capabilities.
Within the scope of this call, we are looking for AI-supported, applicable, and scalable solutions for critical problems encountered on our production lines.
🚀 Challenge Areas
1. AI-Powered Process Optimization (Sealing & Bonding Processes)
The lid-to-case bonding process at the sealing station of the battery production line is a critical process step for manufacturing quality. If the bonding is not completed with sufficient quality, the products are rejected at the subsequent leak test station, resulting in scrap.
This scrap category is one of the top three waste sources in the factory and is observed across three different battery types: HD, AGM, and Flooded. Deviations in machine parameters at the sealing station—such as temperature, pressure, duration, and adhesive amount—from their optimum values lead to inconsistent bonding quality and high scrap rates.
Currently, parameter settings rely heavily on operator experience; there is no dynamic optimization mechanism in place that accounts for battery type, environmental conditions, or material variations.
🎯 Our Expectation:
- AI-powered systems that analyze process data
- Systems that determine optimum parameter sets
- Capabilities to apply these parameters to machines automatically or semi-automatically
- Continuous learning systems
2. Component-Based Product Traceability & End-to-End Traceability in Battery Manufacturing
Although test data is collected at the plate group evel during battery production, it is currently not possible to track which final battery these sets are used in. This disconnect makes it difficult to link quality problems occurring on the production line with specific components and limits root cause analysis.
Furthermore, production parameters are mostly optimized manually or based on experience, leading to high scrap rates, efficiency losses, and quality fluctuations.
At the core of the problem lies the lack of traceability between plate group production and battery assembly. Since it is unknown which battery an plate group goes into, faulty production batches cannot be tracked retrospectively, and quality issues usually only become visible at the final testing stage.
🎯 Our Expectation:
- Systems providing end-to-end traceability starting from the plate group level to the final product
- Integration of production and test data
- AI-powered analysis to predict quality problems
- Matching quality issues with the correct components and process parameters
- Systems providing actionable insights
💡 Sought-After Solution Areas
- Artificial intelligence and machine learning
- Industrial data analytics
- Image processing and sensor technologies
- IoT and edge solutions
- Manufacturing traceability systems
🎯 Targeted Impact
- Reduction in scrap rates
- Increase in production efficiency
- More stable and sustainable quality
- Fast and accurate root cause analysis
- Data-driven production management
🤝 Who Should Apply?
- Startups
- Technology providers
- R&D teams and academic spin-offs
Call Timeline
- 📅 Call Announcement: April 27, 2026
- 📅 Application Deadline: May 30, 2026
- 📅 Pre-Evaluation: June 2, 2026
- 📅 Introduction & Q&A Session: June 8, 2026
- 📅 PoC & Pilot Process: June – August 2026
