This website uses cookies primarily for visitor analytics. Certain pages will ask you to fill in contact details to receive additional information. On these pages you have the option of having the site log your details for future visits. Indicating you want the site to remember your details will place a cookie on your device. To view our full cookie policy, please click here. You can also view it at any time by going to our Contact Us page.

Taking maintenance to the next level with AI

11 January 2021

Marcel Koks looks at how food companies can take maintenance to the next level. 

Continue reading this article

Register now for free and access every article and to register for the print edition.

Industry 4.0 – in conjunction with digitalisation – is starting to transform the way we all work, collaborate, create products, and go-to-market. Data is now the driving force behind success, helping to track everything from the identification of plant assets and associated maintenance requirements to traceability and customer buying trends. But, as more and more organisations roll out their own digital initiatives, there are some common stumbling points.
In the same way that food and drink has a shelf life, data must be consumed quickly to be relevant and useful. However, food and beverage manufacturers often struggle to process and apply data insights with appropriate urgency. Multiple factors get in the way, with data overload often being the most debilitating issue.

Data volume is a key IIoT challenge. It is easy to become bogged down in the never-ceasing flow of data points.  Organisations are often ill-equipped to aggregate, prioritise, and draw conclusions from the data. Storage of huge volumes of data can also be a challenge, forcing companies to turn to cloud computing with elastic flexibility. Problems often occur dur to a lack of experience. For example, AI-driven analytics that can forecast likely outcomes and prescribe responses are technologies available typically require IT professionals with data science skills. Companies have often been forced to turn to third-parties which can become costly.
In turn this makes it challenging to scale true Industry 4.0 initiatives as AI-powered analytics can take years to build and deploy. While massive projects offer promising opportunities, they tend to require advanced data science principles and specialised skills, including report-writing expertise. A more practical approach is needed for the every-day decisions that keep operations running effectively.
A better approach
A new breed of AI tools puts powerful predictive analytics in the hands of front-line users, helping them address day-to-day needs with greater insight. It is no longer necessary to turn to code-writing developers to create use-case-specific applications. With functionality assured through solid back-end code and application programming interfaces (APIs), users can delve into the data they care about with a variety of automated analytic tools. 
AI can be used for more than automating some simple processes. Its true potential comes from applying machine leaning and predictive analytics to a variety of practical and personalised use cases – whether it is a farm that wants to project optimal field yield or a brewery that needs to estimate the amount of barley and hops to procure each month. AI has the potential to offer advice, discover performance patterns, analyse multiple influencing factors, and draw complex conclusions about a specific question — including questions that require a window into the future.
The maximum potential is reached when AI can emulate and enhance human performance, offering advice that is reliable and intelligent. This predictive insight helps organisations anticipate, understand and prepare for future trends and outcomes. This is especially important in the food sector, as manufacturers race to develop new products based on changing customer preferences. As buying habits change companies can turn to AI-driven analytics to monitor costs, optimise margins, and refine supply chain decisions.
For line-of-business managers and plant operational teams to make good use of AI, the technology has to have been an intuitive interface automating decisions about what algorithms to apply and how to incorporate relevant contextual information, like weather variables, crew shifts or time of day. The system should automate the machine-learning process, continually refining the 20 or 30 different factors that might go into the algorithm.
Behind the curtain, an AI solution can autonomously analyse data, generating reports that that the business user will be able to apply in daily tasks. The data patterns can be used to spot issues, opportunities or unknowns that simply would never be visible through traditional spreadsheets and reports.  
Rather than being overwhelmed by mass amount of data, forward-thinking food manufacturers need to invest in tools to help them turn numbers into insights. New AI-driven analytics allow users to consume the data and formulate meaningful, practical applications. This helps business users at all levels of an organisation to gain the benefits of data science—without requiring customer report-writing or help of code-writing IT experts. Democratising data analysis empowers individuals. It leads to a well-thought-out AI strategy that can accelerate the flow of information across the enterprise. To succeed in the modern world, food manufacturers need smart tools to help them make fact-based decisions and unleash the true potential of Industry 4.0.

Marcel Koks is director of industry and solution strategy  at Infor. 

Contact Details and Archive...

Print this page | E-mail this page