Coca-Cola has launched a new limited-edition Coca-Cola 3000 Zero Sugar within the Coca-Cola Creations platform, with the help of artificial intelligence (AI). The AI, in cooperation with humans, helped create both the taste and the design of the can, as Coca-Cola tries to identify what the year 3000 would look like for beverages. It is not just Coca-Cola using AI in the soft drinks category. Unilever, owner of PepsiCo, has developed AI tools to optimise various aspects of its business operations. Against this backdrop, the usage of AI in the soft drinks industry is set to grow for the discovery of new flavours and to enhance the efficiency of business operations, says GlobalData, a leading data and analytics company.

Coca-Cola started with a core question to its customers: What would the year 3000 look like? Consumers were asked how they saw Coca-Cola in the year 3000 via the Coca-Cola Creations platforms. The company then used AI to analyse all the responses to create the framework for the futuristic product based on how people see the future through emotions, ambitions, colours and flavours.

Dragos Dumitrachi, Analyst at GlobalData, comments: “Based on these inputs from consumers and its knowledge of beverage trends, the AI created a unique packaging and flavour profile for a carbonate in the year 3000. The packaging format is colourful, with a mix of spherical shapes blended in purple, pink, and blue colours with a pixelated logo, and the AI primarily perceived the future as being sugar-free. This is to be expected as low-calorie carbonates recorded a 39 % growth between 2015 and 2023 globally, with this growth set to continue over the next five years, as consumers increasingly focus on their health and wellness. According to the latest global survey^* by Global Data, 81 % of respondents consider that it is nice to have or essential for a product to be good for physical fitness/health.”

Global Data expects the AI market to grow from USD 81 billion in 2022 to USD 90 billion by 2030, with a 35 % compound annual growth rate (CAGR) during 2022-2030. Recent progress in machine learning (ML) on the back of improved algorithms (e.g., Google’s AlphaGo, OpenAI’s GPT-3/ChatGPT, Tesla’s AutoPilot) and increasing computing power have enabled AI to become more widely used in the soft drinks industry.

The AI-driven applications developed by Unilever leverage neural networks and the GPT API is aimed at enhancing the company’s ability to respond to the evolving needs of its consumer base and broader market dynamics. On top of that, Unilever is using AI to identify alternative ingredients that can reinforce the resilience of their supply chains, making their products more sustainable and cost-efficient, and streamlining the number of ingredients without impacting the effectiveness or quality of the products.

Dragos concludes: “The AI market in the soft drinks industry is still in its infancy; the rules and laws that will govern it are still under debate. Global Data is forecasting that the use of AI for supply chain, administrative issues, and the discovery of new flavours and packaging formats in the soft drinks industry will only grow.”

^*GlobalData 2023 Q2 Consumer Survey – Global, with 21,595 respondents, published November 2022

The challenges associated with manufacturing PET containers are varied and complex. Process windows are short, and even the daily changes in ambient temperature and humidity in the production hall require regular manual adjustments to various process parameters to ensure the required level of container quality. Added to this are the steadily increasing production speeds, where even the slightest deviations from ideal conditions can have a major impact on the production result. Meanwhile, demands on personnel are also evolving: Today, one operator is responsible for multiple machines and systems – and has less time for visual quality checks and manual process control on the stretch blow molder.

With Contiloop AI, Krones has developed an intelligent process control system for the Contiform stretch blow molder. The combination of AI-based software and newly developed hardware makes it possible to detect even the slightest variations in material distribution in the production of PET containers and to automatically adjust key stretch-blow-molding parameters in real time – and thus to ensure that bottle quality meets specifications.

Since its market launch, Contiloop AI has not only convinced customers around the world, but also this year’s jury of the AI Breakthrough Award, consisting of recognised experts from the fields of business, marketing, sales, analysis and science. The Krones solution received the MLOps Innovation Award, which recognises the most innovative AI product in the field of machine learning operations.

Training and optimising Contiloop AI

As part of an automated test run, various process settings are carried out and the resulting measurement results are forwarded to the Krones IIoT platform. There, the data flows into the Krones AI pipeline, which is used to train the future control algorithm, the AI agent. Once the training is complete, this AI agent is transferred to the machine’s Contiloop AI and is then available for production operation. The system thus learns to be able to adjust the stretch blow-moulding process precisely to the perfect bottle quality even under the new conditions.

About the AI Breakthrough Awards

Over 3,200 nominations from more than 20 countries – this year’s AI Breakthrough Awards once again showed that artificial intelligence is becoming increasingly important in industry. This year, AI companies and products with artificial intelligence were again honoured in 18 different categories such as AI platforms, robotics, business intelligence or AI hardware. When evaluating the submitted innovations, the AI Breakthrough jury focuses on innovation, performance, usability, functionality, value and impact.