Nearly 30,000 connected units of equipment across the world. Digital records of over 600,000 customer assets. Seamless data flow creating predictions of the future. At Konecranes, we firmly believe that data is the fuel of tomorrow. But what is needed to predict the future? And how does data generate value to our customers?
Artificial intelligence (AI) has emerged as a transformative force in various industries, and the manufacturing sector is no exception. This cutting-edge technology leverages machine learning and neural networks to create, design, and optimize products and processes. Its benefits in the manufacturing industry are profound, offering increased efficiency, cost savings, and enhanced innovation.
However, turning data into actionable insights requires data scientists who understand both the theory behind data science and the practicalities of manufacturing industry. To support this and tap into the benefits of the industrial internet for our products, services, and operations, Konecranes established its Data Science Laboratory in Lyon, France in 2019.
The purpose of the team is to fuel business growth and profitability with data driven solutions, which are based on statistics and advanced mathematics, computer science and business understanding. But what kind of solutions have been developed in the Laboratory to help Konecranes’ customers increase their operational efficiency?
“Fuel consumption prediction for reach stackers, prediction of part failure and the predictive maintenance engine to identify crane service needs, to mention a few. Our ability to mine data from our digitalized processes and connected products allow us to produce greater value for our customers and create new business models”, says Julien Chambrillon, Director for Konecranes’ Data Science Laboratory.
Helping customers to maintain operational efficiency
The predictive maintenance engine was developed in 2022 and launched last spring by Konecranes to help our customers keep their equipment reliable and compliant with original equipment manufacturer recommendations.
“The predictive maintenance engine is a system that predicts service needs of an asset based on the asset information, condition data and historical maintenance data. With the prediction rules and thresholds, the engine provides us an estimate of the equipment’s service needs. It also forwards the information automatically to our service sales, who review the service leads and contact our customers in a proactive way with a suitable solution for tackling the service need“, says Erwan Le Covec, Konecranes’ Lead Data Scientist.
“Our predictive engine monitors the customer asset data flow actively. When a customer has a crane under our maintenance agreement, Konecranes’ service will proactively inform the customer of needed service actions triggered by the predictive engine.”
Moving from preventive maintenance to predictive maintenance helps customers to better understand their assets’ upcoming and overdue maintenance needs, keep their equipment compliant with recommendations and design limits of the components, and reduce risks of unexpected failures which would lead to costly downtime and urgent on-call repairs.
Predictive solutions do not benefit only our customers, but also have a positive impact on Konecranes’ carbon footprint. “Predictive maintenance enables us to plan our service visits and actions so that we have the needed parts and tools already available when we go to the customer site. It also helps us to estimate needed spare part stock for coming months so that we operate efficiently”, says Le Covec.
Part of everyday life, not science fiction
But the predictive maintenance engine is only one example of our data science capabilities and the data-driven solutions we provide to our customers. “Our data scientists are always involved when we try to find answers to concrete business problems and questions such as why did it happen, what will happen next and what is the best that could happen,“ says Chambrillon.
Another example of Konecranes’ data-driven solutions is the Konecranes Predict & Plan for mobile harbour cranes. “After analyzing material and parts failure data spanning decades, across hundreds of port cranes and using a combination of different algorithms and predictive models, our data scientists built us a tool which can pin-point when material failure, per part, is likely to occur”, says Chambrillon.
Data Science is not science fiction, but something that is already everywhere in our daily lives, such as in web searches, insurances, entertainment or social media. ”In the same way that an entertainment streaming service recommends new series for you to watch, we can recommend specific spare parts or service to our customers, so that they can better focus on their core business”, Chambrillon concludes.
Data Science permits us to solve business problems by exploiting data. However, to be successful it’s crucial to understand the business challenge and start from a question first, instead of only exploiting the data. At Konecranes Data Science Lab, we have a diverse team of 15 data scientists, machine learning engineers and AI product owners who represent 8 different nationalities. They continuously develop their data science knowledge to better serve customers and to permit Konecranes to become a data-driven company over time.
Read more about Konecranes' predictive maintenance. Solution currently available in all regions for selected components.
