Business & Economy

Using artificial intelligence to control digital manufacturing

Researchers train a machine-learning model to monitor and adjust the 3D printing process to correct errors in real-time

Published

10 months ago

August 4, 2022

EP Staff

Written by Adam Zewe, MIT News Office

Scientists and engineers are constantly developing new materials with unique properties that can be used for 3D printing, but figuring out how to print with these materials can be a complex, costly conundrum.

Often, an expert operator must use manual trial-and-error — possibly making thousands of prints — to determine ideal parameters that consistently print a new material effectively. These parameters include printing speed and how much material the printer deposits.

MIT researchers have now used artificial intelligence to streamline this procedure. They developed a machine-learning system that uses computer vision to watch the manufacturing process and then correct errors in how it handles the material in real-time.

They used simulations to teach a neural network how to adjust printing parameters to minimize error, and then applied that controller to a real 3D printer. Their system printed objects more accurately than all the other 3D printing controllers they compared it to.

The work avoids the prohibitively expensive process of printing thousands or millions of real objects to train the neural network. And it could enable engineers to more easily incorporate novel materials into their prints, which could help them develop objects with special electrical or chemical properties. It could also help technicians make adjustments to the printing process on-the-fly if material or environmental conditions change unexpectedly.

“This project is really the first demonstration of building a manufacturing system that uses machine learning to learn a complex control policy,” says senior author Wojciech Matusik, professor of electrical engineering and computer science at MIT who leads the Computational Design and Fabrication Group (CDFG) within the Computer Science and Artificial Intelligence Laboratory (CSAIL). “If you have manufacturing machines that are more intelligent, they can adapt to the changing environment in the workplace in real-time, to improve the yields or the accuracy of the system. You can squeeze more out of the machine.”

The co-lead authors are Mike Foshey, a mechanical engineer and project manager in the CDFG, and Michal Piovarci, a postdoc at the Institute of Science and Technology in Austria. MIT co-authors include Jie Xu, a graduate student in electrical engineering and computer science, and Timothy Erps, a former technical associate with the CDFG. The research will be presented at the Association for Computing Machinery’s SIGGRAPH conference.

Picking parameters

Determining the ideal parameters of a digital manufacturing process can be one of the most expensive parts of the process because so much trial-and-error is required. And once a technician finds a combination that works well, those parameters are only ideal for one specific situation. She has little data on how the material will behave in other environments, on different hardware, or if a new batch exhibits different properties.

Using a machine-learning system is fraught with challenges, too. First, the researchers needed to measure what was happening on the printer in real-time.

To do this, they developed a machine-vision system using two cameras aimed at the nozzle of the 3D printer. The system shines light at material as it is deposited and, based on how much light passes through, calculates the material’s thickness.

“You can think of the vision system as a set of eyes watching the process in real-time,” Foshey says.

The controller would then process images it receives from the vision system and, based on any error it sees, adjust the feed rate and the direction of the printer.

But training a neural network-based controller to understand this manufacturing process is data-intensive, and would require making millions of prints. So, the researchers built a simulator instead.

Successful simulation

To train their controller, they used a process known as reinforcement learning in which the model learns through trial-and-error with a reward. The model was tasked with selecting printing parameters that would create a certain object in a simulated environment. After being shown the expected output, the model was rewarded when the parameters it chose minimized the error between its print and the expected outcome.

In this case, an “error” means the model either dispensed too much material, placing it in areas that should have been left open, or did not dispense enough, leaving open spots that should be filled in. As the model performed more simulated prints, it updated its control policy to maximize the reward, becoming more and more accurate.

However, the real world is messier than a simulation. In practice, conditions typically change due to slight variations or noise in the printing process. So the researchers created a numerical model that approximates noise from the 3D printer. They used this model to add noise to the simulation, which led to more realistic results.

“The interesting thing we found was that, by implementing this noise model, we were able to transfer the control policy that was purely trained in simulation onto hardware without training with any physical experimentation,” Foshey says. “We didn’t need to do any fine-tuning on the actual equipment afterwards.”

When they tested the controller, it printed objects more accurately than any other control method they evaluated. It performed especially well at infill printing, which is printing the interior of an object. Some other controllers deposited so much material that the printed object bulged up, but the researchers’ controller adjusted the printing path so the object stayed level.

Their control policy can even learn how materials spread after being deposited and adjust parameters accordingly.

“We were also able to design control policies that could control for different types of materials on-the-fly. So if you had a manufacturing process out in the field and you wanted to change the material, you wouldn’t have to revalidate the manufacturing process. You could just load the new material and the controller would automatically adjust,” Foshey says.

Now that they have shown the effectiveness of this technique for 3D printing, the researchers want to develop controllers for other manufacturing processes. They’d also like to see how the approach can be modified for scenarios where there are multiple layers of material, or multiple materials being printed at once. In addition, their approach assumed each material has a fixed viscosity (“syrupiness”), but a future iteration could use AI to recognize and adjust for viscosity in real-time.

Additional co-authors on this work include Vahid Babaei, who leads the Artificial Intelligence Aided Design and Manufacturing Group at the Max Planck Institute; Piotr Didyk, associate professor at the University of Lugano in Switzerland; Szymon Rusinkiewicz, the David M. Siegel ’83 Professor of computer science at Princeton University; and Bernd Bickel, professor at the Institute of Science and Technology in Austria.

The work was supported, in part, by the FWF Lise-Meitner program, a European Research Council starting grant, and the U.S. National Science Foundation.

Business & Economy

SVKM’s CNM School Organizes Mini Marathon, Raises ₹6 lakh to support cancer patients

The event was a phenomenal success, with parents and students running for a cause

Published

3 months ago

February 28, 2023

EP Staff

SVKM’s CNM School, as a part of their 25th-anniversary celebration, organised a Mini Marathon Run on the morning of February 26, 2023. The event was a phenomenal success, with parents and students running for a cause, and successfully raising Rs 6,00,000 for the Tata Memorial Center to support cancer patients.

With the theme “YES, WE CAN!” the event saw participation of 3,000 students, parents, and teachers of CNM School. The registration fee was Rs. 200 per participant, and all proceeds went towards the Tata Memorial Center.

“Our school has always believed in giving back to society, and this mini-marathon is a testament to that. With every step taken, we raise awareness and funds for a noble cause,” said Kavita Sanghvi, Principal of CNM School. She added: “The Management has organised this event to commemorate the 25th anniversary of SVKM’S CNM School and through this magnanimous gesture instilled lifelong values and learning within all.”

The event has raised Rs. 6,00,000 for the ImpaCCT Foundation, an acronym for “Improving Paediatric Cancer Care and Treatment.” It serves as the paediatric foundation of the Tata Memorial Hospital, which ensures that every child with cancer receives treatment and support regardless of their family background. It was established in October 2010 to ensure that every child with cancer coming to Tata Memorial Hospital, receives treatment and other support regardless of the family background.

The cheque for the raised funds was presented to the Tata Memorial Center on the day of the event.

“We invite all parents and students to join us in this selfless initiative of sharing and giving. Your participation is crucial in showing that you care,” added Principal Sanghvi.

It is said that charity begins at home. Running for a charity, whether the race is for one specific cause or the cause gets you into a specific race, gives an added purpose to the running. This event is in alignment with our credence as an institution, which has always believed in giving back to society. SVKM’s CNM School is committed to supporting young cancer patients.

Join the CNM School community and take a step towards making a difference in someone’s life.

Business & Economy

FoodTech Kerala to be held in Kochi from February 9^th to 11^th at Rena Event Centre

More than 60 exhibitors will showcase their products and services at this year’s FoodTech Kerala

Published

4 months ago

February 6, 2023

EP Staff

FoodTech Kerala, the state’s premier food processing and packaging expo, will be held for the fourteen edition at Rena Event Centre from February 9 to 11, 2023. FoodTech Kerala will be a 3-day exposition and will provide an interface for the manufacturers of food processing machinery, packaging equipment as well as suppliers of ingredients and flavours for the small and big food processing units in the state, the organizers told a media conference held at Press Club on Monday.

The organizers of the expo, said more than 60 exhibitors will showcase their products and services at this year’s FoodTech Kerala edition. “It is a ‘must not miss’ event for all organizations involved in the food processing and packaging sector to showcase their products and services.

The event is endorsed and supported by Kerala Bureau of Industrial Promotion (K-BIP), CIFT, BIS and FICCI-Kerala. The key highlight of this edition will be the Industrial Pavilion featuring 20 SME units from the state which is sponsored by the K-BIP, Govt of Kerala. The presence of food processing and packaging equipment suppliers, along with the buyers and food processors will give a new dimension to the expo bringing the local buyers and national suppliers together in a single platform.

The receding of pandemic has given a major push to the food industry especially to the small scale units and home bakers in Kerala. “Food Processing Industry has made a major headway all over Kerala, with the Ernakulam district only having many food based units, employing more than 50,000 people. The food processing industry in the district has various products including spices, fish and meat, oil and extracts and ready–to-eat products.

The show will be an ideal opportunity for NRI-Returnees to set up food and bakery units to target the growing Food & HORECA sector in Kerala. The state has a fairly strong base of food processing industries. This sector plays a major role in the economic development of this region and various studies reveal that its contribution to the total output, value additions and employment generation have been regularly increasing during the recent years.

FoodTech Kerala 2023 is organised by Kochi based Cruz Expos. The company has been regularly organising the FoodTech and HotelTech series of B2B trade expos in the state since the past 14 years. Cruz Expos, in a short span of 15 years, has become one of South India’s foremost professional exhibition organiser in the B2B segment.

Organised by:

CRUZ EXPOS

Chingam, K. P. Vallon Road, Kadavanthra, Kochi- 682 020. India

Mob: +91 8893304450

E-mail: joseph@cruzexpos.com

www.foodtechkerala.com

Business & Economy

The Workforce Institute at UKG Survey: More Than Half of Workers in India Wouldn’t Want Their Children to Have Their Job

The survey report titled ‘We can fix work’ entails a 10-country survey of employees, C-level leaders, and HR professionals which was done by The Workforce Institute at UKG

Published

6 months ago

December 12, 2022

EP Staff

The report launched on 9th December, 2022 at the UKG LIVE event happening in Sahara Star, Mumbai.
They survey found that 52% of people would tell their children to pursue jobs in which they find ‘meaning’ instead of being completely driven by the pay scale.
While money will continue to remain a driving factor when it comes to job choices, the coming generations definitely won’t regard it as the only factor.

Standing at the threshold of the future of work, The Workforce Institute at UKG, which provides research and education on critical workplace issues facing organizations around the world, surveyed employees and leaders across 10 countries to get a pulse of how they really feel about their jobs. According to the results, India ranked the highest with 66% of employees stating that they wouldn’t recommend their profession to their children or any young person that they care about, while 67% wouldn’t recommend their employers.

The full report, “We Can Fix Work,” provides insight into what parents, family members, and mentors are telling children about what they should value in their jobs and employers — urging future generations to let purpose, not money, guide career choices.

It found that on a global scale, nearly half (46%) of employees would not recommend their company nor their profession to their children or a young person they care about, and a startling 38% “wouldn’t wish my job on my worst enemy.”

“Employees and leaders alike, as has been found in this report, prioritise finding meaning in their work more than making money. We have to realise that with these shifting times, we are navigating towards a generation of workers who don’t necessarily rely on their job for survival: instead their work is more personal to them in terms of adding value to their lives, and fuelling their existing passions,” said Neil J Solomon, vice president, Asia Pacific and Latin America at UKG. “For a workforce such as this, we need to develop a workplace culture that nourishes and nurtures the overall development of its employees, takes care of their physical as well as mental wellbeing, appreciates their efforts, and maintains a mutual sense of respect with individuals at different levels of the organisation irrespective of hierarchies. This, right here, is the beginning of the future of work and employee centricity is at the heart of it.”

Workforce burnout: 45% of employees worldwide don’t want to work anymore, period

There has been a recent rise in the anti-work mindset, globally, owing to the pandemic as 77% of employees around the world want to spend less time working and more time doing things that matter to them. Amongst the C-suite leaders, it is the younger leaders that are ready to bow out of work completely, especially those belonging to the Gen Z (58%), who say they don’t want to work anymore. When compared to the C-suite leaders who are soon to be retiring from their jobs, 36% of the Millennial leaders and 33% of the Gen X leaders are ready to not work anymore. Therefore, a disinclination towards work is a phenomenon that is being observed across the ranks of employees and leaders alike.

Too much overtime affects the employee-employer relationship

If employees tend to work overtime more than twice per week, it strains their relationship with the employer and they’re even less likely to recommend their jobs or their companies to the next generation. This is evidenced by the more than half (58%) of employees, globally, who work overtime 3-4 times per week who wouldn’t recommend their profession to kids. 60% wouldn’t recommend the organisation. The report distinctly shows that more money does not equate to job satisfaction for individuals, as most people have a transactional relationship with work and only 23% of employees genuinely enjoy their work and are passionate about it. In fact, 64% of them would switch jobs right now if they could.

With purpose and trust, 88% of employees look forward to work

Now more than ever, companies must prioritise the wellbeing of their employees, not just for better outcomes in the present, but for their long-term sustainability in the future. Employees in India topped the global charts with a staggering 89% saying that they are committed in their pursuit of greater purpose at work — most of any country surveyed.

What does great look like?

Great Place To Work research finds people at the best workplaces around the world are living in a vastly different — and more fulfilling — reality than the typical employee, starting with the sense of purpose they find in their work. For those at the best workplaces:

90% feel like they can be themselves
88% look forward to going to work
85% believe their work has special meaning
85% enjoy psychologically healthy work environments

What’s more, rather than warn loved ones away, 89% of people at these best workplaces would “strongly endorse” their organizations to friends and family.

The full report, “We Need to Fix Work,” examines feedback from 2,200 employees surveyed in partnership with Workplace Intelligence across Australia, Canada, France, Germany, India, Mexico, New Zealand, the Netherlands, the U.K., and the U.S., as well as 600 C-suite leaders and 600 HR executives in the U.S.

Supporting Resources

Learn more about UKG and why our purpose is people.
View the latest UKG Environmental, Social, Governance (ESG) Report to learn more about how UKG is making a difference for its employees, customers, community, and environment.
Follow UKG on Facebook, Instagram, LinkedIn, Twitter, and YouTube.