Collaboration develops AI-powered line clearance for pharma

Together, they have developed a lower cost, flexible, and scalable alternative to existing AI-powered automated technologies. 

According to 42 Technology (42T), most dedicated systems designed to automate line clearance processes are too expensive for widespread use because of their high hardware costs, complex integration, and the need for extensive training on production lines.

The new approach is said to address these challenges by using a fully autonomous, deep-learning AI platform. Unlike conventional systems, the inspection system is designed to enable in-process learning without the need for lengthy setup and training routines on live production lines.

Line clearance checks are critical in pharmaceutical manufacturing to ensure that all materials, products, labels and records from a previous batch have been completely removed before starting the next one. The process involves manual inspections, often taking up to one hour between batches.

MORE FROM AI

The new AI-powered approach combines Balluff’s high-performance image acquisition system with Arcturus’s deep-learning models and the Synaptics Astra SL1680 edge AI processor. 

A limitation of existing automated solutions is the need for extensive on-site training of their machine learning models at multiple points on live production lines.

This new AI-powered platform eliminates that requirement by using deep learning as a stand-alone method for continuous model improvement.  This creates a fully automatic process where datasets are continuously developed in real time.

42T said the system’s embedded intelligence compensates for variables such as shadows and changing light conditions, while its self-learning capability continuously improves accuracy and reliability during real-time operation to further boost production efficiencies for pharmaceutical manufacturers.

In a statement, David Sandner, product marketing manager for machine vision at Balluff said: “With some pharmaceutical manufacturers operating up to 100 production lines with 20 or more cameras on each, cost and complexity have been major barriers to automating line clearance.  Balluff is developing image acquisition and processing platforms to help customers and partners address these challenges in more cost-efficient ways.  These solutions promise a real breakthrough in helping manufacturers to boost production efficiencies, save costs and increase security.”

The solution could also be used in other regulated industries such as medical devices, and food and beverage.  The system uses fixed position cameras at key locations for monitoring, and is flexible enough to accommodate ‘pan and tilt’ cameras to scan different production areas depending on the application.