A new South Australian craft beer has been designed entirely by AI, thanks to a special project from the University of Adelaide’s Australian Institute for Machine Learning (AIML) working in partnership with Barossa Valley Brewing. Read more
When SafetyCulture first began, we started out on a mission to help teams do their best work everyday. As we continue to build out a world-class operations platform, we’re also on the lookout for other great innovations to help transform the experience of working teams. Read more
A leader in the salmon industry
Established in 1986, Huon Aquaculture has grown to become a salmon producer that is recognised around the world for the quality of its produce and the ingenuity of its operations. Read more
Dassault Systèmes is a French company that has a solid history in the aerospace and defence industries but now serves 11 industries including consumer packaged goods and retail. Dassault Systèmes’s 3DEXPERIENCE platform is fast becoming the catalyst and enabler of today’s global transformation in sustainable packaging.
The 3DEXPERIENCE platform is a platform for knowledge, a game-changing collaborative environment that empowers businesses and people to innovate in an entirely new way.
The platform powers various Dassault Systèmes brands across many industries. As a system of operations, it allows businesses to innovate with operational excellence from idea to modelling and simulation to market delivery and usage. For example, it empowers innovators to design and test packaging design in the virtual world, making traditional physical prototypes almost extinct.
Dassault Systèmes, Consumer Package Good & Retail (CPGR) industry solution director, Walid Darghouth, is a champion of the platform, and once you get into the nitty gritty of how it works, you can see why.
Italy-based Darghouth believes one of the key aspects of the platform that users will notice almost immediately is its collaborative nature.
“The value of the 3DEXPERIENCE platform is about the ability to empower collaboration. It allows everyone involved in a project – from the research lab to the factory to the consumer – to interact and work together,” he said. “Utilising the platform as business model, you’re able to coordinate collaboration and communication between stakeholders during the packaging development and production stages. As a result, it enables businesses to improve their processes, apply knowledge and know-how at a faster rate and become more competitive.”
So, how does it work? Being online, the platform provides a model-based system for better collaboration. All teams work together on the same data model, and are able to access the right type and level of information according to their function. Project managers use the same set of data that the packaging engineers are using, which is also connected to the data used by the simulation and manufacturing teams. The platform makes it easier to manage projects and keep data consistent. Everyone has the most up-to-date information at their fingertips and can see how one change impacts another team’s work.
“It is also key to note that the research and development made can be stored and searched for across multiple sites,” said Darghouth. “For example, if I am a designer based in Europe and I want to know if a sustainable bottle cap design exists or if there was a similar project started by colleagues in the USA or Australia, before I start, I can search on the system to access the latest project data. With that I am able to collaborate with the overseas colleague on new ideas or further develop that concept and bring it to fruition and not have to start from scratch.”
Another key feature is having full visibility project development data on one platform. Apart from the obvious time savings, it will also help with legacy of knowledge and know how.
“If you don’t have a platform where you manage everything in one place; how sure are you that you are able to connect the dots between people, idea and data?” said Darghouth.
“What the platform is capable of doing is to help our customers integrate everything we have all the information on one platform and ensure that ideas and development are shared across all users.”
In a world where getting products to market quickly has become crucial in the global market, turnaround times can also be a bugbear.
“What we are seeing today is pressure from the market for speed,” said Darghouth. “You have to innovate quickly. Often, when we do a physical test of a packaging design it can take up to six months and that doesn’t include the product inside. Add that and it can take a lot longer.
“When it comes to packaging design, it’s also about primary packaging, secondary packaging and tertiary packaging. When you experience a fail in one of those steps using a physical prototyping, you are forced to start from the beginning again, further delaying your product launch. Imagine how much time you will need each time you have to do it again and again?
“The virtual twin experience enables packaging specialists to create a 3D model of the packaging design in real world settings, and cut down on physical testing by using simulation to ensure that the packaging holds up throughout its entire lifecycle and evaluate the reliability and safety of packaging designs before committing to physical prototypes. It also allows designers to study and understand any mistakes in the virtual environment – something physical testing does not allow for – as well as test different material composition to determine the best option for sustainable packaging. With the processes being done virtually on the 3DEXPERIENCE platform, it also reduces the use of precious natural resources and costs, normally associated with development.”
Sustainable innovation lies at the heart of the industry and will be the primary driver of innovation across all sectors of the economy and progress. Darghouth said that it is important to bring sustainable products out, but why not start at the beginning when a designer first starts the project. A digital platform provides end-to-end visibility of the whole process, from material selection, material specification through to distribution.
A topic Darghouth is passionate about is Artificial Intelligence (AI)/machine learning, which the 3DEXPERIENCE platform utilises. He believes that it is the future, and the sooner manufactures get on board, the sooner they will begin to realise that the old way of doing things will become redundant.
“We have capability in this [AI] space already and industrial systems, especially in the space of Consumer Packaged Goods” he said. “Even with packaging, it’s often a consideration of the material needed and how we can align sustainability goals and deliver designs consumers will love, and now expect, from manufacturers.”
He gives an example of a designing a beer container made out of cardboard. Because of the effervescent nature of beer, you can use machine learning and AI to predict how to best construct the material for the packaging container to withstand pressure from the carbonated drink without compromising the integrity and taste of the beer. Using a complete modelling and simulation environment designed to allow research in materials science, you can study the packaging materials itself so you could augment the material and take into account the effect the gas would have on the final product.
“We have ready solutions for both the packaging supplier side as well as the food and beverage manufacturer. With increasing consumer demand for eco-friendly products. It’s about helping manufactures innovate and start with the idea of how are you going to improve the existing material properties and the characteristics of the design model. It allows us to rely on a flexible data-driven approach in packaging development and improve how it is designed, how the products can be transported via the various channels and what is possible for the post-consumption experience. This is important in the approach to sustainable packaging.”
Like any platform that is a game changer, one of the aspects that needs addressing is ease of use. Talk about AI, machine learning and Cloud solutions make it seem like there is a lot going on in terms of getting the platform up and running. Not so, said Darghouth.
“It’s easy to use. It has an interface which is intuitive where I can easily create my own collaborative space so I can share different ideas with my peers,” he said. “When I show a customer how to use it, they can immediately start playing with it and feel confident with it. On the Cloud we have dedicated applications that have been built in and is an ‘out-of-the-box’ solution. It already has the capabilities and best practices of the industry built inside. We are always fine-tuning our solution,” Darghouth added. “Updates, adding new features by listening to our customers and understanding their needs.”
The 3DEXPERIENCE platform has local support from Dassault Australia, and it is not lost on Asia Pacific South Marketing Manager Chad Lim that even before the pandemic and the lockdowns that have occurred in various states, the size of Australia meant that the platform is ideal for companies who have a footprint in the various states.
“We have received feedback from customers saying how simple it was for them to collaborate from their own homes using the 3DEXPERIENCE platform. The virtual world knows no silos. To ensure the best outcome, there must be a strong link from ideation all the way to production. Having a digital thread throughout the design and manufacturing process is essential for today’s CPG manufacturers.”
Darghouth thinks that the 3DEXPERIENCE platform is just the tip of the iceberg when it comes to packaging technology, and that Dassault Systèmes will provide companies with the advantage of bringing successful products to the market faster and with an end-to-end approach to sustainability. This supports a positive impact on consumers, the environment and to the business.
To find out more on what Dassault Systèmes can do for you, click here.
With an increasing global population, the urgency to find new and innovative ways to address food demand is felt around the world. Since 1970, fish farming has existed in the Nordics and developed into a major industry. Norway Royal Salmon (NRS) is a leading producer of sustainable salmon, selling about 70,000 tons of salmon every year. This equates to one million salmon meals per day, all year round.
In the harsh and sometimes dangerous environments of the most northern parts of Norway, NRS sought to increase the safety of its employees, reduce operational costs and prioritize sustainability of Nordic aquaculture.
Through an artificial intelligence (AI) for salmon analytics pilot, ABB and Microsoft co-created a solution with NRS to produce quality food in a safer and more environmentally responsible way. The pilot showed that NRS can increase the efficiency and safety of its workers, who now aren’t required to be at open sea as often as before. The new technology will have an impact on the CO2 footprint due to less operations and better fish welfare, resulting in cleaner seas and improved efficiencies.
“Norway Royal Salmon has always focused on extensive research, development, cooperation and innovation,” said Arve Olav Lervag, COO Farming, NRS. “To continuously improve sustainability and increase the safety of our individuals, we worked with ABB and Microsoft to co-create innovative ways that empower us to achieve more on every level.”
ABB and Microsoft implemented technology with remote visual object detection for biomass estimation and fish population counting. The technology will monitor the growth of the salmon and reduce the workload of NRS workers, while providing an edge in collecting critical data from the production of salmon.
Underwater cameras capture images of the salmon in their submerged fish pens, floating kilometers offshore at sea. A layer of AI on top of the video footage makes it possible to measure and count salmon automatically.
“ABB is fully committed to helping bring about a more sustainable future, and here we’re using AI to revolutionize aquaculture and deliver on that promise,” said ABB chief digital officer Guido Jouret. “By monitoring fish health and performance, to minimizing environmental impact and reducing operational costs, ABB Ability is enabling NRS to reach a new level of competitiveness.”
The solution is powered by Microsoft’s Azure cloud and ABB Ability, which delivers ABB’s deep domain expertise from device to edge to cloud to empower customers know more, do more, do better — together.
ICP Australia has introduced iEi’s new Mustang-MPCIE-MX2 computing accelerator miniPCIe card with two Intel Movidius Myriad X VPU, providing a flexible AI inference Solution, designed to execute two topologies simultaneously.
The Mustang-MPCIE-MX2 card includes two Intel Movidius Myriad X VPU, providing a flexible AI inference solution for space limited and embedded systems.
VPU is short for vision processing unit. It can run AI faster, and is well suited for low power consumption applications such as surveillance, retail and transportation, as its power consumption is 7.5W.
This highly flexible product supports Intel’s OpenVINO toolkit for the optimisation of pre-trained deep-learning models such as Caffe, MXNT, ONNX and Tensorflow.
With the advantage of power efficiency and high performance to dedicate DNN topologies, it is perfect to be implemented in AI Edge computing device to reduce total power usage, providing longer duty time for the rechargeable edge computing equipment.
- miniPCIe form factor (30 x 50 mm)
- 2 x Intel Movidius Myriad X VPU MA2485
- Power efficiency, approximate 7.5W
- Operating temperature 0°C-55°C (In TANK AIoT Dev. kit)
- Powered by Intel’s OpenVINO toolkit
OAL has announced the launch of the world’s first artificial intelligence-based vision system, April Eye, for date code verification. The system removes the operator from the date code verification process, achieving full automation to reduce the risk of product recalls and emergency product withdrawals (EPWs) caused by human error on packaging lines. Reaching speeds of over 300 packs a minute, April Eye can make a significant improvement to processes, safety, quality and efficiency and deliver cost savings to food and beverage manufacturers on their packaging lines.
By combining machine learning and artificial intelligence, April Eye transforms the traditional date code verification process, which relies on operators to check the date code is printed correctly. April Eye removes the human error inherent in these boring, repetitive tasks. By taking photos of each date code, the system can read them back using scanners to ensure they match the programmed date code for that product run, automating the verification process and allowing food and beverage manufacturers to achieve unmanned operations and full traceability. Running at speeds of over 300 packs a minute, it also allows them to increase throughput without compromising product safety. The production line comes to a complete stop if a date code doesn’t match, ensuring that no incorrect labels can be released into the supply chain, protecting consumers, margins and brands.
Traditional vision systems have relied on optical character recognition (OCR), designed to read specific characters. Due to the prevalence of inkjet printers in the food industry, which have a higher degree of variability, these vision systems have not been widely implemented. OAL therefore developed April Eye, which uses basic cameras backed up with an artificial brain to deliver a vision system that can deal with variations such as lighting, positioning, print quality and placement inherent in a food or beverage plant and read anything that is also legible to the naked eye. In this way, April Eye eliminates errors, offers full traceability and protects consumers and the brand while at the same time reducing labour costs and waste. The system also improves over time, further safeguarding manufacturers.
April Eye stemmed from an initiative led by a large retailer to eliminate food waste in the supply chain by preventing human error. Incorrect date codes and packaging was found to be one of the largest sources of food waste. OAL spearheaded the development as part of its Food Manufacturing Digitalisation Strategy, supported by the University of Lincoln and Innovate UK grant funding, designed to investigate how artificial intelligence could revolutionise this key area of the food manufacturing process. The University of Lincoln put together a team of global experts in AI, including Professor Stefanos Kollias, the founding professor of machine learning, to develop the April Eye solution. The system was first deployed with two leading global manufacturers and has since been rolled out across existing OAL Connected customers, with no EPWs related to date code errors to date.
Wayne Johnson, OAL connected director, comments, “Having experienced the pain of EPWs and product recalls first-hand, I was determined to develop a product that would offer food and beverage manufacturers a bullet-proof solution to avoid problems linked to label and date code verification. We’ve completely turned vision systems on their head, allowing manufacturers to move to unmanned production, improve traceability and reduce costs across the board. April Eye gives them the security they need to do this as it really is a fail-safe solution.”
A hand scanner solution and in-line scanning are already available, with a standalone audit solution coming later in the year.
The rapid uptake of Artificial Intelligence (AI) is dominating today’s business landscape, and its rising impact can’t be ignored.
A 2017 survey of large Australian businesses revealed that 89 per cent had already rolled out some form of AI, and that 70 per cent of senior Australian executives see their future business strategies hinging on this exciting new technology.
Why the sudden interest in AI? Because well-executed AI unlocks unprecedented opportunities for growth.
According to recent forecasting by Gartner, new business revenue created via AI will amount to $300 billion by 2020.
Clearly there is an opportunity for food and beverage companies to help themselves to a slice of this growing revenue pie. How? By effectively and flawlessly bridging the increasing disconnect between market volatility and revenue growth.
In today’s food and beverage industry, international competition is growing, margins are thinning and the price of commodities is constantly changing. Added to these pressures, are multitude of factors — from increased labour costs, seasonal trends and changes in consumer demand – that can create profitability obstacles.
In this tumultuous environment, manual pricing and quoting methods are no longer agile enough to deliver sufficient revenue. Without the ability to address market fluctuations as they occur, companies feel the effects of margin leaks. And this is where AI comes in.
AI can unlock big data and analytics to give food and beverage companies the insight to respond in real time to market instabilities, quote the right price at the right time, close more sales, and protect margins.
To maximise success, David Bray from PROS suggests that food and beverage companies prioritise the following three key capabilities when implementing AI-powered revenue management systems:
Get the picture: Analyse sales for a clearer understanding of which products drive overall profitability. When you know what your most profitable products are, you can prioritise these should you need to make a strategy pivot.
Find your price points: Map customers’ price sensitivities and reactions to pricing spikes. Find out the price points that cause buying behaviours to decline; and the price points at which buying behaviours increase.
Real-time response: Adjust prices dynamically to account for shifts in underlying commodity prices, changes in market conditions and up-to-date supply information. AI-enabled dynamic pricing technology takes all variables into account to formulate winning pricing strategies.
“AI-powered dynamic pricing technology delivers a number of tangible benefits,” Bray said. “It automates processes, so companies can streamline operations. The technology captures more sales with faster and more accurate quoting, and drives additional revenue from cross-sell opportunities,” he said.
According to Gartner Research, robust price optimisation strategies can increase margins by 50 basis points or more, and increase revenue by up to four per cent. Multinational dairy company, Fonterra, is one such example – after implementing a new dynamic pricing revenue realisation system, it achieved a 2-4 per cent margin uplift, equivalent to $20 million per quarter.
AI-based technologies are reshaping how companies around the world do business. A considered, strategic implementation of high-level AI-powered functions will ensure your business can override market instabilities to grow revenues and outpace the competition.
The Australian wine industry is turning to artificial intelligence to streamline its manufacturing.
South Australian tech firm Ailytic has developed an artificial intelligence (AI) program to significantly increase production efficiency by optimising machine use.
It uses an AI technique called ‘prescriptive analytics’ to account for all the variables that go into mass-producing wines such as grape variety, packaging and finished product inventory.
The program then creates the best possible operation schedule, allowing companies to save considerable time and money.
Ailytic’s list of clients includes world-renown wine companies such as Pernod Ricard, Accolade Wines and Treasury Wine Estates.
It has now included South Australian company Angove Family Winemakers as well.
Pernod Ricard Global Business Solutions Manager Pauline Paterson said AI was highly beneficial for the wine industry and helped to increase the bottom line.
“We use it mainly around production line and use it to derive the most efficient way to produce our product,” she said.
“It is definitely helpful with changeover, how many bottles we need, how much wine and what order to do everything in.”
Ailytic’s system is able to obtain essential information from wineries using remote sensors, which are placed on equipment and around winemaking facilities.
These sensors track a number of key metrics including throughput, machine uptime and changeover time from red to white when bottling.
This includes the sub-classification of each colour such as sweet red, dry red, aromatic white and fortified wines.
Ailytic’s program ensures that wine is changed quickly, without contamination, bottled using appropriate glassware, labelled and then packaged appropriately.
The sensors then transmit the data to a computer in real time using Wi-Fi.
A single production run for bottling can take anywhere between one hour to two days but Ailytic’s system reduces time spent changing the line setup by up to 30 per cent.
Pernod Ricard is the world’s second leading wine and spirits company, with a network of growers across six countries and €8.68 billion in sales in 2015.
Its brands include Jacobs Creek, Campo Viejo, Brancott Estate, Kenwood Vineyards and Wyndham Estate.
Ailytic co-founder and CEO James Balzary said the company’s AI program was perfect for the wine industry because it thrived in complex environments.
“Our algorithms work well for things like packaging, bottling and general manufacturing – the wine industry is where we are seeing a lot of appetite and the most uptake,” he said.
“People think of wine as a romantic artisan type of process, and it is, when you are producing small batches or super-premium wine, but the majority of wines we drink are mass manufactured in big complex tank operations. That’s where we come in – the more complex the business, the bigger the benefit.”
Ailytic’s involvement in wine manufacturing has seen it nominated at the 2017 Wine Industry IMPACT Awards in Adelaide.
Ailytic’s other clients are also based out of South Australia and include Australia’s lone sink manufacturer Tasman Sinkware.
However, it does plan to expand its clientele and has already garnered international interest in their product.
“Even though the bigger wineries would find this more useful, even smaller operations will benefit from this,” Balzary said.
“It’s an affordable solution that used to only be accessible to bigger companies but we try to focus on bringing advanced capabilities to Tier 2 and Tier 3 manufacturers and service providers.”