Data is King: Why construction machine data is so valuable

We Predict is an industry-leading predictive analytics company. Since 2009, We Predict have been keeping pace with the increased thirst for data and are at the forefront of this digital technology.

Here, they share some of their insights on how to get more out of machine/component data and how it can be utilized to help reduce defects, minimise risk and boost profits.

How construction machine data benefits OEMs and end-users

Dr Stephen Norris, Technical Lead, explains, “With manufacturing relying heavily on digital technology, it’s vital you know the lifetime cost of every machine your company hires out or manufactures. We enable you to do exactly that.

“Based on millions of actual service records, unplanned repairs, recalls and warranty data, we measure service and warranty costs spent by manufacturers and owners and provide risk scores”.

It’s important to know how to spot potential problems so manufacturers and operators are able to cut warranty costs by as much as 25%.

Norris continues, “For example, we analysed data from 4,000 skid-steer loaders. The machines generated more than 8,000 warranty claims during the 24-month warranty period.

“A deeper look at the data revealed 1,300 machines – one third – had no warranty claims while 500 (12%) had more than five claims each. Those machines accounted for 43% of all claims. Identifying and solving problems with this targeted sub-set has a huge impact on reliability and costs.”

How to make the most of data in the supply chain

“Another example of how better use of data has brought improved efficiencies is with one of our Tier 1 supplier customers who needed to deliver monthly reports to an original equipment manufacturer (OEM) each month,” said Norris.

“The supplier had to collect, analyse and report on performance, warranty costs and other data. When we first began working with them, eight of their plants in various parts of the world were extracting and reporting on their own data. The reports were inconsistent, frequently late and contained errors. The OEM customer was not happy.

Norris said, “To make matters worse, collecting and reporting on the data diverted the supplier’s engineers from their core tasks. On average, each of the supplier’s eight plants had engineers logging the equivalent of 7 to 10 person-days per month to consolidate the data and generate the reports.

“That was equivalent to 56-to-80 days per month across the enterprise or 600-900 days per year. By outsourcing to us, the supplier gained the equivalent of 3 to 5 engineering employees, with an associated value of $300,000 to $500,000 per year.”

Norris concluded, “Once you know what questions to ask of your data, we can provide the answers you need. Frequently, we’ve seen companies under-utilise the data they’re generating meaning that opportunities are sometimes missed to reduce defects, improve overall quality and strengthen brand reputation.”