Axion Ray brings intelligence to production to find problems before they cause trouble • TechCrunch

Manufacturers face a multitude of potential problems around the machines they manufacture, and it can be difficult to track down the problems. This is not only good to know. It’s important information, which is often manually tracked these days by human auditors in spreadsheets. In some cases, not understanding when a defective part is present can lead to costly recalls and in the most extreme cases death and lawsuits.

Enter axis ray, an early-stage startup is using machine learning to track these issues in unstructured data to build a big picture of potential problems before they get out of hand. control. Today, the company announced a $7.5 million healthy seed round.

“What we did was build a new artificial intelligence platform that helps manufacturers overcome their major risks like recalls by mining and aggregating unstructured data in new ways. which up to this point has not really been touched,” co-founder and CEO Daniel First told TechCrunch.

He says that unstructured data comes from users and separates his company from those that came before him.

“In traditional machine learning and many of the companies that have come before us, much of the focus in manufacturing is on highly structured data sets like installing cameras on a production line or looking at sensor data for dynamic failure prediction. muscle.”

“But the cool thing about Axion is that we can leverage a huge amount of unstructured data, things like [chatter] comes from service or dealer networks, where most of the data is technician observations and is found in comments and issues and troubleshooting data comes from humans.”

First worked as a McKinsey consultant for several years prior to founding the company and witnessed first-hand how manufacturers struggled to recognize potential problems before they could. really start to deal with them. He also observed that the technicians working on these machines had problems for months before the companies realized there was a bigger problem and the idea of ​​the Axion Ray began to take shape.

“Clearly there is a huge opportunity to enable early warning indicators to be detected and flagged, and that could help people detect that there are risks months earlier.”

The company was founded in 2021 and has worked with clients such as Boeing, Penn Engineering and Cummins. First doesn’t want to share customer numbers yet, but it’s clear that some of the big players are interested in what his company is doing.

With nearly 20 employees, the startup is hiring, especially engineers and staff with machine learning expertise. First said building a diverse workforce was a priority from the start.

“Although we are a small team, we have dedicated full-time colleagues who are responsible for ensuring that we are building diverse candidate sources and recruiting methods right from the start. the first day. We are also delighted to be able to partner with Inspired Capital as our co-lead investor, which is one of the largest female-led venture capital funds in the country,” he said. speak.

Today’s $7.5 million investment is co-led by Inspired and Amplo along with Boeing, Tinicum Venture Partners and industry angels.