Kamakqua
Automated quality inspection of roof tiles using artificial intelligence
Initial situation
Quality assurance is a key part of production in industry and manufacturing. However, inspections are often based on visual checks and human decisions that can lead to inconsistent results due to fatigue, fluctuating concentration and subjective assessments. These variations reduce the reliability and reproducibility of inspection results and can cause quality fluctuations in delivered products.
Solution: inline inspection system with image and acoustic evaluation
Against this background, the INDAP network partners PA-ID Automation & Vermarktung GmbH and Datinf GmbH developed an innovative inline-capable inspection system that continuously captures and evaluates image and sound recordings of roof tiles as they pass through. Quality assessment is performed using artificial intelligence (AI). Tiles classified as defective are automatically rejected. In addition, the software provides recommendations for adjusting production parameters to minimize scrap and increase efficiency.
System setup
The system is designed for inline operation and is installed above a conveyor belt. Key components include:
- A high-resolution camera for image capture
- A sound module with striker for sound generation and a microphone for recording
- A compute unit for processing image and sound signals with an integrated AI system for quality assessment
- A recommendation algorithm to optimize production parameters
- A reject system with control unit and interface to the compute unit
Value
Using the automated inspection system enables 100% quality control, where every produced tile is inspected objectively and consistently. In addition, a reduced defect rate through early rejection helps save materials and resources, improving the sustainability of the production process.
Funding
The research and development project ran for two years and was funded by the Central Innovation Programme for SMEs (ZIM).