Researchers go nuts with new automated almond grader

'Nutty' professors develop world first almond grading machine

Machinery
THE A(lmond) TEAM: University of South Australia researchers Brajesh Panda, Gayatri Mishra and Wilmer Ariza with their prototype almond grading and contaminant detection machine.

THE A(lmond) TEAM: University of South Australia researchers Brajesh Panda, Gayatri Mishra and Wilmer Ariza with their prototype almond grading and contaminant detection machine.

Aa

A research team at the University of South Australia have developed a prototype machine that can grade almonds and detect potentially dangerous contaminants in kernels.

Aa

University of South Australia researchers say they have developed a world-first automated machine that can simultaneously grade almonds and detect potentially serious contaminants in kernels.

Australia's almond crop is now was worth around $1 billion and is tipped to grow to $1.5 billion in coming years.

The local industry is exporting to more than 50 nations which has increased the need for accurate and consistent grading of almonds to protect markets.

Almonds have traditionally been graded manually with samples taken hourly from production lines to check for consistency of appearance, chips and scratches, double kernels, insect and mould damage and other defects.

This process is labour intensive, slow and subjective, all of which can lead to inaccurate and inconsistent grading, particularly from season to season due to staff turnover.

In conjunction with industry partner SureNut, researchers at the University of South Australia have developed a machine that significantly improves the accuracy of almond grading as well detecting potentially fatal contaminants common in almond kernels.

Funded through the Co-operative Research Centres Projects program, a research team led by Associate Professor Sang-Heon Lee combined two high-definition cameras, a hyperspectral camera and purpose developed AI algorithms to create a system that can examine almond quality in far greater detail than the human eye.

Uni researchers develop robotic apple picker

The system can accurately assess physical defects such as chips and scratches and detect harmful contaminants including the presence of aflatoxin B1, a potent carcinogen that may be implicated in more than 20 per cent of global liver cancer cases.

"Our goal with this innovation was not to simply replicate what a human being could do but go far beyond that," Assoc Prof Lee said.

"So, in respect to physical appearance, this machine can detect defects more quickly and more accurately than manual grading and by using two high-definition cameras and a transparent viewing surface, it can also view both sides of the nut simultaneously."

SURE THING: A SureNut machine running the UniSA-developed grading system has recently been field tested at Riverland Almonds, one of South Australia's leading almond producers.

SURE THING: A SureNut machine running the UniSA-developed grading system has recently been field tested at Riverland Almonds, one of South Australia's leading almond producers.

The addition of the hyperspectral camera for contamination detection was a ground-breaking world first, he said.

UniSA engineering researchers Dr Wilmer Ariza and Dr Gayatri Mishra developed the hyperspectral system used on the SureNut machine.

Dr Ariza said almonds presented a unique challenge for the technology.

"We are the first team to successfully use hyperspectral imaging this way with almonds even though other researchers have tried," he said.

"Certain characteristics of the nut kernels - which we are keeping a secret - made the process extremely difficult but we overcame that and now we can deliver highly accurate analysis using hyperspectral imaging.

"Through the process we also discovered some new information about hyperspectral imaging in general which we will share with the wider research community in time."

The SureNut system can monitor key indicators in almonds - moisture content, free fatty acid content (FFA) and peroxide value (PV) - which are associated with rancidity and aflatoxin B1 content.

"Moisture, FFA, PV and aflatoxin B1 content were all correctly predicted by the developed model with accuracy of 95pc, 93pc, 91pc and 94pc respectively," Assoc Prof Lee said.

"Previously the only way to detect these contaminants was through laboratory methods that require the sample to be ground up and chemically treated, making validation difficult.

"So our technique is a major safety improvement for the industry given rancidity and aflatoxin have significant effect on consumer health."

While the hyperspectral analysis has only been tested on a lab prototype device at this stage, a SureNut machine running the UniSA-developed grading system has recently been field tested at Riverland Almonds, one of South Australia's leading almond producers.

Quality assurance supervisor at Riverland Almonds Deanne Crawford said the trials during this season's harvest showed the huge potential for the SureNut system.

"Riverland Almonds have continued to work closely with SureNut and have been trialling a unit during the 2021 production season," she said.

"While the unit is a prototype and still under development, we are encouraged by the progress made and optimistic that the results achieved over the course of this season will demonstrate that the technology has a commercial application within the industry."

Aa

From the front page

Sponsored by