By clicking “Accept”, you agree to the storing of cookies on your device to enhance site navigation, analyze site usage, and assist in our marketing efforts. View our Cookie Policy and Privacy Policy for more information.
Article
0
min reading time

Microsoft, Carnival Maritime, and Arundo team up to test the waters with machine learning in the Cortana Intelligence Suite

Arundo leverages the Microsoft Cortana Intelligence Suite to understand Carnival Maritime's water challenges.

Keeping a cruise ship afloat is not only a jaw-dropping example of the principles of physics, it also is a massive mechanical operation requiring complex industrial equipment that works around the clock keeping engines, boilers, and fans running smoothly below deck. On the ships of the Costa Group, a fleet of 26 cruise ships that sail all over the world, the industrial equipment is arrayed with thousands of sensors that collect data in real time. As part of its enterprisewide digital transformation, the company’s marine service unit, Carnival Maritime, wanted to explore how it might take advantage of this data to find opportunities for operational improvement.

Like many businesses in asset-intensive industries, Carnival Maritime has more data than it can make use of. “To build a big data and analytics strategy, our company needs to better understand what kind of data we can collect on the ships and what kind of data we need to have in the future,” says Alexander Klingelhoefer, Director of Continuous Improvement at Carnival Maritime. “We want to use the data to get a better understanding of our operations and to help our ships be more efficient and sustainable.”

In search of a forward-thinking partner with sophisticated tech capability, Carnival Maritime found Arundo Analytics, a global provider of analytical and predictive solutions that is known for its work in the oil and gas industry. “We understand the value that big data analysis brings to a company like ours,” says Klingelhoefer. “And we needed someone who has the expertise to experiment with a test case. Arundo not only has that expertise, it also uses the Microsoft Azure cloud, a platform we are building on in other places across our company.”

Arundo’s approach was to avoid re-instrumenting the company’s architecture and, instead, configure a system that capitalizes on the industrial hardware Costa Group had already invested in by using software to study the data being collected from thousands of on-board sensors. To make that data queryable, Arundo uses Azure SQL Data Warehouse. “Arundo has built a large big-data platform that runs on Microsoft Azure, and it was an exciting challenge figuring out what we can do with it for Carnival Maritime,” says Tor Jakob Ramsoy, Arundo’s CEO. “We can very quickly prove a use case or a business case to show the business value that applying advanced analytics and big data can bring—and how it can bring that value in a very short time and make a big impact on operations.”

To read the rest of the Customer Story, please click the link to open Microsoft's website.

Let’s connect the dots!

Join other leading industrial companies and discover how Arundo’s AI Foundation adds insight and intelligence to your operations

More articles

All articles
Article
What a Cup of Coffee Can Teach Us About AI-Driven Manufacturing
Article
Using Large Language Models and AI Agent Systems to Provide AI Assistants for Improved Industrial Operations
Article
While large language models (LLMs) may struggle to generate insights directly from time-series data, their strong pattern-recognition capabilities make them well-suited for identifying and synthesizing already existing insights. We therefore argue that an architecture featuring a separate graph-based domain model and time-series data storage is the ideal architecture for a generalized AI companion serving the heavy asset industry: An agentic AI can first identify relevant nodes (assets, sensors, and a large variety of pre-computed models) for answering a user prompt using a mixture of APIs, query language generation, semantic search, and graph traversal. Only after this filtering step is time-series data accessed and retrieved to synthesize an answer.