Most children break their toys. Four-year-old Ajit Srikanth wanted to cure his body quirks.
When Srikanth broke a small toy bicycle he had been given, he got nervous and informed his parents. Worried he wouldn't be able to get another one, he decided to repair it. He used a little glue to get the broken wheel and handlebar back in place. He got his toy back and learned a valuable lesson.
“My mother encouraged me to think: If something breaks, let's fix it,” said Srikanth, currently a master's engineering student at Northeastern University who works in advanced and intelligent manufacturing. “Then at least you see the value of the effort you put in and learn something in the process of fixing it. … After I fail, it's not really a failure to me. I try to think of that failure as a lesson for my next goal or ambition.”
Srikanth now repairs things far more complex than toy bikes and uses tools far more advanced than glue. He is using AI to revolutionize an industry that is fundamental to almost every area of life: manufacturing. As a co-op with Van Dyk Recycling Solutions, a leading provider of recycling facility design, consulting, and equipment, Srikanth is pushing AI and himself to new frontiers.
“I've been on a lot of ships, but the learning and exposure I get from doing something like this is just phenomenal for me,” Srikanth said. “I used to see manufacturing as just one thing. Now I see manufacturing as part of a bigger picture with AI, recycling, and sustainability.”
At Northeastern, Srikanth was designing chatbots to troubleshoot solutions that engineers encountered on the manufacturing floor, such as broken sensors, conveyor belts, and laser marking machines. This project earned him a collaboration at Van Dyk. Van Dyk wanted a similar chatbot for its engineers.
“This helps people, especially service engineers, collect information that is found in hundreds of manuals,” says Srikanth.
Srikanth completed the project in just two months and immediately began finding ways to integrate AI into nearly every part of Van Dyk's operations.
As part of the chatbot, Srikanth also built backend software that allows engineers who solve hardware problems themselves to submit a form with details about their solution. The idea is to create a more robust knowledge dataset that chatbots can extract from when helping people troubleshoot issues. Humans are still in the loop and are actually essential to allowing chatbots to operate effectively.
He developed a model that uses cameras to help Van Dyk's recycling machines better differentiate and separate different types of waste, such as plastic, cardboard, and glass. He also built a model that extracted from a database of more than 1 million Van Dyk engineering documents to quickly identify specific machines and their parts.
That may sound simple, but for Van Dyk, who has been around for 48 years and has a machine that's just as old, it's a big deal. Srikanth continues to solve things the same way he always has.
“That way, we can repair the machine without scrapping it, which saves time,” Srikanth says. “Right now they are refurbishing the machines, which saves the company money and also saves the environment.”
Ultimately, Srikanth designed 13 different AI-based models and systems for Van Dyk.
“Thanks to AI, we have moved from reactive, manual operations to proactive, automated operations,” said Faizan Jamal, an engineer at Van Dyk. “We are now extracting, classifying, and validating data at scale, accelerating tasks such as file matching, equipment tracking, and document review. We are changing the way we design processes and thinking in terms of automation, quality, and scalability rather than manual and traditional workflows.”
Srikanth still believes that AI is the future of manufacturing and a revolutionary force in our lives. But his time at Van Dyk convinced him that knowing when to stop using AI is just as important as knowing when to use it.
“AI can only be used to help people, not to build things. Whether it builds things depends on your brain and how you calculate it,” Srikanth says. “For me and for my company, AI is not going to take your job away. AI is going to help you do your job better. You need to know how to leverage AI to your advantage, not one, none, or two. You don't want to overuse it to the point where it becomes a burden on your job.”
