Accelerating India’s EV ambitions with deep learning and 3D inspection tools

With the global demand for electric vehicles (EVs) on the rise, spurred by sustainability commitments such as India’s 2070 net-zero target, the importance of efficient and reliable battery manufacturing has become crucial. 

Based on industry forecasts, the demand for EV lithium batteries in India is expected to surge from 4 gigawatt hours (GWh) in 2023 to nearly 139 GWh by 2035. To support this growing demand, large-scale production of high-quality lithium-ion batteries will be required. 

To ensure consistent quality and efficiency, carmakers and battery manufacturers are leveraging advanced technologies such as deep learning, machine vision, and 3D inspection systems. These tools enable precise inspection of surface coatings, defect detection in cells, barcode and serial number reading, and the consistent application of adhesives and thermal beads. 

Vision-guided robotics also guide the assembly of battery packs. Together, these technologies support high standards across production, ensuring reliable batteries that meet the demands of the growing EV market.

Use and procurement today
Deep learning machine vision software, 3D technology, and vision-guided robotics are unlocking new levels of visual inspection for quality, safety, and compliance across the electric battery manufacturing process. 

There is a range of ways manufacturers procure machine vision solutions for existing and new factories – selection made at the site level with sign-off at the corporate level, and selection and sign-off both at the site level being two main approaches. This site level focus has its benefits but can leave room for less desirable variation where different sites are using different machine vision solutions for similar workflows, with expertise and data not shared across sites. 

Today’s machine vision software comes with deep learning tools which are needed for higher levels of inspection and are better at handling more complex use cases. Deep learning neural networks (specifically convolutional neural networks) are powerful, advanced artificial intelligence (AI) tools that mimic the human brain. 

Uses and benefits of 3D 
3D vision systems can reconstruct the spatial layout of objects within an electric battery, including the object’s shape, size, position, and orientation in a three-dimensional space. It can provide accurate, detailed data that 3D inspection processes can use to perform comprehensive and precise inspections of cells, solder beads used for cell assembly, tabs and connectors, and adhesive beads for cell stack assembly. 

Furthermore, 3D scanning can be done using one of several techniques, such as laser scanning, structured light scanning, Time of Flight (ToF) scanning, photogrammetry, or contact scanning. 

3D tools for machine vision 
3D profile sensors are important for machine vision tasks like quality control and inspection. 3D profile sensors also extend the capabilities of machine vision systems. They enhance depth perception and improve quality control with a rich 3D dataset for modern machine vision software equipped with 3D tools to process and analyze the 3D point cloud data. 

Tools include a 3D surface matcher to find and estimate pose of surface model occurrences in a point cloud, and 3D shape finders to find and characterize cylinders, (hemi)spheres, rectangular planes, and boxes in a point cloud.

Other tools could include 3D blob analysis to segment a point cloud into blobs and calculate their characteristics, and 3D measurement to find transitions in extracted profiles from depth maps and compute metrics on and from these. 

3D and vision-guided robots
Robotic arms are used in electric battery and automotive manufacturing for picking, sorting, and assembly at factory sites and assembly lines. Picking and sorting applications are useful when detecting and removing defective items from the production line. Robotics also helps in heavy lifting, repetitive, and high accuracy assembly use cases.  

Additionally, vision-guided robots can be programmed to pick-and-place cells for cell stack and battery module assembly with high levels of accuracy and control, for example.   

Conclusion 
As new electric battery and vehicle technologies continue to emerge, an increasing number of companies will likely reassess their operational processes and supply chains. This re-evaluation aims to minimize waste, lower costs, and enhance production efficiency and profitability. To successfully navigate this transformation, businesses will require advanced tools and technologies. 

Deep learning machine vision, as well as 3D data capture and analysis tools, are already empowering manufacturers with a competitive advantage in electric battery production. These innovative technologies enable real-time monitoring and optimization of manufacturing processes, allowing for precise quality control and improved yield rates. 

By leveraging such advanced solutions, companies can streamline operations, make data-driven decisions, and ultimately position themselves for success in an increasingly competitive market.

-- Subramaniam Thiruppathi, Director Sales, India sub-continent business, Zebra Technologies.