A growing number of companies are realising the ever-growing volume of data they generate has the potential to transform their businesses. Pirelli is one of them. Its production line machines measure hundreds of parameters in the tyre-making process every second. More than 4,000 Cyber Fleet sensors send back data from the field with every turn of the wheel. And all of this information can deliver new insights and act as a catalyst for fresh innovation.
Add to that the mountain of data coming in from the company’s research labs, test tracks, suppliers, customers, weblogs and social media, and you can see that Pirelli's first Head of Data Science and Analytics, Carlo Torniai, and his team have plenty to explore.
There’s a lot of untapped potential in the data we have in the company and my goal is to use it to build smarter solutions
“I’m impressed by the amount of data about production and process we have and the variety and complexity of our in-house data ecosystem” says Torniai. “There’s a lot of untapped potential in the data we have in the company and my goal is to use it to build smarter solutions.”
To start with, Torniai’s team is concentrating on three main areas at Pirelli: smart manufacturing, Cyber Technologies development, and the extended value chain, from the supply of raw materials to the final point of sale. The team’s brief is to measure and manage the data more precisely than ever before, and use real-time information to come up with more efficient solutions.
The benefits of effective data analytics
Evidence suggests that data-driven companies perform better in financial and operational measures. Companies leading the way in data-driven decision making are 5 per cent more productive and 6 per cent more profitable than their competitors, according to research by the MIT Center for Digital Business, working in partnership with McKinsey’s business technology office.
Companies like General Electric – an early believer in big data to both improve its own business and develop software products to sell to customers – see room for improvement everywhere. GE’s analysis of the aviation industry, for example, finds that $22 billion is wasted every year on inefficiencies around unplanned downtime, poor processes and avoidable incidents; money which could be saved through better use of big data.
Developing smarter manufacturing
For Pirelli, the biggest source of data is the production line machines. They measure the operational parameters for tyre-making along with the quality of the product throughout the cycle. So for any tyre you can monitor the raw materials that went into it and the different settings and readings on the machines that produced it. Armed with this information you can build predictive models that can tell you in real time the expected quality of a tyre, based on how it is made.
The next step is to move from predictive to prescriptive models and actually suggest corrections in the parameters of the machines during the production process, as well as in the deployment of individual machines, to create the best quality and efficiency. The system will “learn” each time it makes a change and as a result the process will be continually improved.
“In the not so distant future we envision a virtual factory where at any given time the allocation of resources and expected outcome is known, and where machines can automatically regulate processes and material flow and suggest skills required on the floor,” says Torniai.
Realising the potential of Cyber Technologies
Another rich area for data analytics is the reams of information coming from Pirelli’s Cyber Technologies. These are already in action for customers of the company’s Cyber Fleet system, giving trucking companies real-time information on their vehicles’ tyre pressure and temperature along with their GPS location with more than 300 Million kilometers monitored.
Over the past two years Pirelli has been collecting data from its Cyber Technologies sensor research fleet out in the field. Within the daily measurements of tyre temperature, pressure and wear, data scientists are looking for patterns that could help improve the safety of the vehicles we drive and prompt more efficient fuel use.
Pirelli’s data team will be looking to add more benefits for customers from the new technology, in things like predicting when tyre maintenance is needed, letting drivers know when their tyres should be inflated, repaired or changed, thus allowing fleets to keep downtime to a minimum.
Then there is the possibility for Cyber Technologies sensors to interact with external data, likely from service stations or navigation equipment companies, which could help drivers to plot their routes better, avoiding dangerous or difficult roads or even traffic congestion.
Cyber Technologies products for the consumer market are still in development, with all these possibilities and more in the pipeline.
Improving the use of resources
The third focus for Pirelli’s data scientists is the company’s extended value chain – covering everything from the supply of raw materials to the distribution of the product. Forecasting resource flows and reacting faster to make changes when needed can save on materials and create the most efficient processes.
Beyond these three initial clusters of activity lies a wealth of other data including competitive analysis, HR analytics, and analytics from Pirelli’s website and social media, all with potential to bring improvements to the company. The goal is to have a single intelligent information framework, which the whole company can access.
A good part of the job is the ability to tell stories with data to people who are not necessarily technical folks
As many companies are discovering, putting data analytics at the core of a business involves a new way of thinking and a new process of decision-making. And even for a company as rooted in numbers and data as Pirelli, that can be a big step.
Torniai feels that part of his work is to explain this new approach while proving the business case.
“It doesn’t just require technical skills but communication skills and the ability to tell stories with data to people who are not necessarily technical folks,” he says. “Then it’s about explaining that often you don’t get a black and white solution but a range of possibilities. So you need to explain the “fuzziness” in results to people who are used to dealing with straight numbers, then use this as the basis to make decisions.”