Food sorting machines with the ability to think like humans could solve the greatest challenges facing the industry today.
Food security and reducing waste are both high on the international agenda. The Food and Agriculture Organization of the United Nations has estimated for years that in the next few decades, feeding the growing global population will require a significant increase in food production. In addition, a report by the UK’s Institute of Mechanical Engineers suggested that as much as half of all the food produced in the world—equivalent to 2 billion metric tons—ends up as waste each year.
Pieter Willems, technical director at Tomra Sorting Food, which manufactures food sorting machines and processing technology for the fresh and processed food industries, says that consumer tolerance toward natural variations in foods should be fed back into the manufacturing process to make it more efficient, optimize scarce resources and cut waste.
“Research is being carried out with consumers to discover what they perceive as good or poor quality product,” says Willems. “Consumers do have a tolerance to this with processed fresh produce, but it is about getting the balance right.”
Machines manufacturing french fries can struggle to deliver a consistent product because of the natural variation that potatoes have in size and shape. A machine will always try to make the same product regardless of the shape and size of the potato that went into the processing line. This uniform approach to food processing can create a great deal of unnecessary waste, as fries are left that are too short or too thin.
“However,” says Willems, “if a machine is capable of identifying and then separating potatoes that are most suitable for french fries from those more suited to potato wedges or crisps, for instance, you have a much more efficient production line and a happier, more satisfied consumer.”
This line of thinking is all about capturing the essence of consumer thought and putting that intelligence into a machine. The ultimate goal for food sorting and processing is for a machine to view food in the same way consumers do. The ability to control a natural variable and apply a degree of intelligence to the process could be hugely powerful tools to the food industry in general. By removing the “good/bad, yes/no” element to food processing, the amount of food that could be saved and processed rather than being filtered out as waste would be huge. “We are talking millions and millions of tons of product being saved, optimum use of food, and maximum yield from farm to fork,” says Willems.
“Demand for high quality food has increased significantly over the past 30 to 40 years,” says Lorraine Dundon, vice president and head of group brand at Tomra. “For many years, our focus was about designing machines capable of eliminating foreign material and poor quality produce from production lines. In the beginning that was a challenge, but technology has come so far.”
Tomra’s sorting machines use a variety of sensors that go beyond the common use of color cameras. Near-infrared (NIR) spectroscopy enables an analysis of the molecular structure of a product while X-rays, fluorescent lighting and lasers measure the elemental composition of objects. The internal composition and surface structure of objects can also be analyzed to determine good or bad produce.
“We have changed our focus in recent years to looking at how we can optimize product,” says Dundon. “It is a given that bad produce can be removed, but what happens to product that is of a good enough standard to be processed is now key to the resource revolution. Optimizing produce, getting more out of what comes onto the production line from field to fork, is now at the heart of out ethos.”
In practice, this shift in approach to resource management is evident in where sorting takes place. In the past it has been about providing machines that allow farmers to sort product in the field—harvesters that can identify and remove bad product at the first stage of the processing chain so that money and energy is not spent taking poor quality produce away from the field.
Tomra’s sorting and peeling solutions typically recover 5 to 10 percent of produce through higher yields and better utilization, reducing pressure on the food chain and cutting food waste. That is equivalent to about 25,000 truckloads of potatoes per year.
“Today, the entire food processing sector is far more efficient in terms of energy and waste,” says Willems. “A tomato that may not be aesthetically pleasing may still be fine in terms of food quality and safety. It may not cut it as a tomato for a salad but for tomato sauce or puree, it is absolutely acceptable. In the past that tomato may have gone to waste when sorted in the field, but thanks to innovations in technology it can now be processed and used for food.
This is the beginning of the “intelligent machines” concept—sorters that go beyond good and bad sorting to optimizing product. Integrating that human control and human intellect into machines is how the next resource revolution begins.