Manufacturers face a widespread skilled labor shortage, but the problem can be alleviated through more intelligent automation, according to Watch Out. The company has developed highly automated work cells to make production more flexible and less labor intensive.
Nearly 2 million U.S. manufacturing jobs could go unfilled by 2033, according to a report from Deloitte and The Manufacturing Institute.
Watch Out offers processing cells that use patented sensors and machine learning for precision manufacturing in the aerospace, defense, automotive, medical and other industries. The Montreal-based company claimed it provides “level 5” autonomy for applications such as material handling, machining and inspection.
Watch Out begins in aerospace.
In 2012, Sébastian Laporte partnered with Frédéric Perret to create an aerospace precision manufacturer. He learned how to program some of France’s first CNC machines, said Bernard Mariette, president of Watch Out.
“Sébastian learned the limitations of these machines and recognized the challenges of retraining staff,” says Mariette. robot report. “He also created software to analyze the exact dimensions of small pieces of quartz watch submerged in oil, and Rolex later purchased the intellectual property from him.”
Laporte and Perret launched Watch Out in 2016, and Mariette joined in 2019. Mariette said the company designed high-speed connectivity and proprietary sensors into the system to start with data and deep learning rather than CNC machining.
“We designed the system from scratch to connect the sensors directly to FANUC’s CNC, which solved the first problem of frugal data collection,” he said. “Cameras on the machine monitor the position of the part and the tool itself. Because we have control, we work in nanoseconds and 2 microns for quality control rather than 6 seconds. “We can measure every piece, not just every 1,000 or 5,000 pieces, and analyze them under a microscope.”
Watch Out can also control the amount of aggregate data it collects for continuous learning without losing explainability. “All data related to a customer’s product stays with the customer,” he said.
Traceability is especially important in the mass production of medical items such as bone pins, aerospace parts and luxury goods, Mariette said. Additionally, a workcell can contain up to three stacks, each containing 25 tools.
The company has approximately 70 employees across its Precision Machining and Autonomous Solutions divisions. We have workshops in Bonneville, France and Dorval, Canada. Watch Out’s investors and customers include LISI Aerospace, a supplier to Airbus and Boeing.
“Startups need vision, resilience and the support of a large company,” Mariette said. “LISI believed in us and was very helpful in developing the system.”
AI allows machining to adjust itself
Watch Out said its artificial intelligence eliminates the need for human intervention, from CAD file management to part inspection. AI can also handle new work orders, calibration and optimization, and dynamic adjustments to serial production.
“Previously, if we wanted to change the parts we were producing, we needed an industry representative to analyze our plans,” Mariette said. “Then you have to have someone who knows the code of the machine. Then there is someone testing the code. Then you need to adjust your code. You can then move into production. For very difficult alloys, it can sometimes take half a day or two days.”
“For us, it takes up to 30 minutes because you put the CAD file into the machine and the machine designs its own process, selects its own tools and does the first run,” he explained. “If the first run of five pieces is incorrect, it will adjust itself and run five more, and so on.”
“This means we can change production routes, even on weekends or at night, without stopping the entire process,” says Mariette. “The system is designed to run completely autonomously for at least 48 hours.”
Adoption allows for reshoring of production.
Do factory workers see the “lights out” promise as a threat to their jobs?
“We are not taking away jobs,” Mariette responded. “We are doing the opposite by enabling reshoring. Even with full automation, today’s state-of-the-art factories still require higher levels of staff and logistics staff.”
“Today, 40 traditional machines require 40 people. “With our system, we need 10 pieces, but we don’t yet have the ability to automatically source parts from stock,” he added.
“In the Watch Out workcell, AI drives the process and makes decisions in real time,” said Mariette. “There may be multiple robotic arms and inspection modules. The entire product journey resides in the cell, making it a microfactory. Plus, whole cells can be placed in standard containers.”
RaaS can help with ROI, says Watch Out.
Standard practice in many manufacturing sectors is to purchase a machine and repay it over five years, Mariette said. Adaptive workcells eliminate obsolescence because parts know when to be replaced before they break, he said.
Watch Out offers its systems through a subscription or Robotics as a Service (RaaS) model.
“It’s no longer about capex,” Mariette said. “We have fewer machines, but it’s important to make the most of them.”
Watch Out workcells have been rolling out over the past year, and the company is looking to expand from France, Switzerland, and Canada to the U.S. and globally. Sales are expected to triple in 2022, reaching CAD 30 million (USD 20 million) in 2024.
Register now to save 40% on your conference pass!