3D vision systems help food manufacturers adapt to unpredictable markets

The food industry has faced huge challenges in the last year as COVID-19 has changed consumer demands, limited workers’ movements and put financial pressures on food supply chains. Food manufacturers must adapt to these changes in order to survive, but how? Here, Nigel Smith, CEO of TM Robotics, explains why 3D vision systems hold the key.

The food industry remains slow to embrace automation. In BCI’s Supply Chain Resilience Report 2021, 41.6 per cent of organisations answered “no” when asked if they have increased their use of technology to map supply chain disruption as a direct result of the COVID-19 pandemic. But, why the reluctance?

As Food Processing previously reported, some manufacturers are wary of change. There are cultural expenses, in terms of adapting your workers and management team to new Industry 4.0 systems. And there are opportunity costs, or the likelihood that new digitalised systems will slow things down before speeding things up and properly yielding a return on investment (ROI).

Aside from internal resistance, manufacturers also face external pressures. They include an increase in the cost of raw material and energy, and pressure from retailers for cheaper, faster production. There are also regulations.

“The food and beverage sector in general is well-known for having some of the most stringent manufacturing and control regulations in industry,” says Jonathan Wilkins, marketing director at industrial parts supplier EU Automation. “This is part of the reason why UK manufacturers have been relatively slow in the uptake in automation. However, this guarded attitude is slowly starting to change.”

Many food manufacturers understand that automation is the only way forward. According to research by Gartner, 79 per cent of supply chain leaders think that an internet- or platform-based approach is the most critical new business model to support post-pandemic recovery. But, for manufacturers to take the Industry 4.0 plunge, these systems must demonstrate ROI and compatibility with existing systems and processes.

Open the blinds

It should be noted that resistance to change among food manufacturers isn’t a weakness in relation to Industry 4.0. Actually, it’s a strength. For instance, when selecting the type of machine to introduce to your facility, considering the actual needs of your facility and processes will result in a more cost effective and appropriate machine being installed, boosting your potential ROI. It’s also crucial for manufacturers to consider what kind of objects the robot will be interacting with.

This is where machine vision systems can play a vital role alongside automation systems, cobots and other Industrial Internet of Things (IIoT) devices. Vision systems do more than just scan food. With tireless automatic monitoring, they can help ensure products meet the high standards of food associations.

Whereas blind industrial robots, or those without vision systems, can complete simple repetitive tasks, robots with machine vision can react to their surroundings intuitively. Indeed, traditional IIoT systems in general can suffer from blind spots when physically executing processes in a 3D plant environment, leaving human workers to diagnose process bottlenecks or malfunctions.  

2D or 3D vision systems can counter this blindness to better monitor production environments, in combination with artificial intelligence (AI) and machine learning. 2D vision is better suited for situations where colour or texture of the target object is important, like barcode detection.

Any task where shape or position are important, like bin picking, is better served by 3D machine vision that evolved from the idea of spatial computing first developed at Massachusetts Institute of Technology (MIT) in 2003. In 3D vision, multiple cameras are used to create a 3D model of the target object.  

Better quality

Shibaura Machine’s TSVision3D system operates in this way. As a result, it doesn’t require complex CAD data to recognise objects. Instead, two integrated and high-speed stereo cameras capture continuous, real-time 3D images.

The software can recognise any object that’s positioned in its field of vision, even for non-uniform products, like bananas or mangoes for instance. Not only can vision systems fit more flexibly into food manufacturers’ production lines, the technology is emerging as an effective and profitable way for manufacturers to their streamline production, improve quality checking and keep consumers safe from product contamination.

Such visibility would have greatly helped the industry in 2018, when the United States saw a massive recall of all romaine lettuce. Fortunately, should another incident occur, manufacturers can benefit from the visibility, planning and response advantages that vision systems provide. In doing so, they can adapt to changes in the supply chain in ways that will be essential for their survival.