Northwestern University’s Ping Guo is at the forefront of advanced manufacturing research, exploring innovative technologies that are shaping the future of additive manufacturing (AM) and beyond. From intelligent metrology and solid-state powder production to groundbreaking robotics for large-scale surface patterning, Guo’s Advanced Intelligent Manufacturing Laboratory is tackling industry challenges with multidisciplinary approaches that promise scalability, affordability, and precision. 3DPrint.com visited Guo at Northwestern, where we were able to get an in-depth look at the work being performed and learn about its implications for the broader manufacturing landscape. Intelligent Metrology for Precision Manufacturing At the heart of many AM challenges is quality control, a domain where Guo’s team has developed game-changing solutions. Leveraging photometric stereo and deep learning algorithms, the lab has created a metrology system capable of detecting surfaces defects additively manufactured parts. This system uses multi-modal imaging and computer vision to provide real-time 3D geometry and surface texture analysis, all within a scalable framework. A research setup for studying multi-modal sensing for directed energy deposition at Prof. Guo’s lab. “What we envision is a future where computer vision is all you need for measurement and understanding,” Guo explained during the lab visit. “These systems can do what human eyes can’t—capture minute details while providing actionable insights.” Iterations of a setup for studying the combination of neural network deep learning and photometric stereo measurement of surface details of an object for in-process metrology. Photometric stereo is a particularly innovative approach, as it uses varying light angles to capture detailed surface reflectance data, which is then analyzed using deep learning. This allows the system to detect not only geometric irregularities but also subtle texture inconsistencies that might otherwise go unnoticed. Unlike fringe projection, which often struggles with resolution and scalability, or contact-based systems that risk damaging parts, Guo’s non-contact solution is both precise and adaptable. The ability to scale these metrology systems is a standout feature. “Our setup can go from a desktop-sized configuration to a room-wide implementation, enabling precise inspection for massive workpieces like ship hulls or aircraft wings,” Guo pointed out. The implications for industries such as aerospace, automotive, and energy are enormous. For example, manufacturers could use these systems to perform in-situ inspections of turbine blades or automotive panels, reducing the risk of failure and increasing operational efficiency. A scaled version of Guo’s deep learning enabled photometric stereo metrology system. By integrating hyperspectral imaging and computer vision, Guo’s lab is paving the way for smarter quality control systems that reduce waste, improve throughput, and enhance product reliability. Sustainable Metal Powder Production Another groundbreaking area of research in Guo’s lab is the production of high-quality metal powders for AM. By employing ultrasonic vibration machining, the team has demonstrated a novel method for generating uniform, micron-sized powders with tight dimensional tolerances. This solid-state process avoids the traditional atomization methods that require high energy inputs and often result in material waste. “These powders are not just more sustainable to produce—they’re better in different perspectives,” Guo explained. “We’ve shown that our produced aluminum powders show extreme particle size uniformity without the need of sifting to have a large yield rate.” The ultrasonic vibration technique operates by applying high-frequency vibrations to a machining tool, which breaks the material into uniform particles. This process ensures consistency across batches, a critical factor for AM applications that require precise material properties. Traditional atomization processes, by contrast, often produce powders with wide size distributions, which can compromise the quality of printed parts. Scalability is also a key advantage of this approach. The lab has developed models to predict particle sizes under various machining parameters, allowing for precise control of the production process. “We’ve designed parallel production setups and high-efficiency collection systems to make this method viable for industrial-scale applications,” Guo explained. The reduced energy consumption and material waste associated with this process align perfectly with the growing emphasis on sustainability in manufacturing. With sectors like aerospace and automotive increasingly adopting AM for lightweight, high-performance components, Guo’s work could play a pivotal role in meeting the demand for reliable and eco-friendly metal powders. Structural Coloration and Surface Functionalization Guo’s work on structural coloration uses vibration-assisted machining to create micro/nano-gratings on surfaces, enabling iridescent colors without the use of dyes or pigments. These patterns are angle-independent, offering applications ranging from anti-counterfeiting measures to decorative and functional coatings. “This technology is more than just aesthetics,” Guo remarked. “By controlling surface reflectivity and light absorption, we can unlock applications in solar energy and beyond.” The lab’s ability to produce high-resolution patterns is a testament to the precision of their vibration-assisted techniques. The gratings are capable of manipulating light at the nanometer scale, which opens up possibilities for advanced optics, energy harvesting, and even biomedical devices. For example, these surfaces could be used to enhance the efficiency of solar panels by optimizing light absorption across varying wavelengths. In collaboration with Prof. Todd Murphey at Northwestern, Guo’s innovations extend to large-scale surface functionalization through compact, autonomous robots. These robots are designed to apply micro-structured patterns to enhance properties like friction, wear resistance, and hydrophobicity. Unlike traditional methods that focus on precise feature placement, Guo’s robots prioritize feature density, which reduces costs while maintaining high fidelity. “Imagine a fleet of tiny, intelligent robots transforming an entire airplane wing into a highly efficient aerodynamic surface,” Guo said. “Our robots demonstrate a shift from machines larger than the workpiece to a paradigm where tiny, intelligent systems handle massive structures.” Beyond manufacturing, these robots have potential applications in agriculture—such as modifying terrains for optimized irrigation—and in environmental conservation, where they could be deployed for large-scale surface cleaning or restoration. This versatility underscores the transformative potential of Guo’s approach to robotics. Human-Centric Manufacturing: Wearable Sensors and Worker Safety In collaboration with Prof. John Rogers and other Northwestern researchers, Guo’s team has also developed wearable sensors for real-time fatigue monitoring in manufacturing environments. These sensors use physiological data to predict fatigue and recommend rest intervals, improving worker safety and productivity. “There are a lot of questions from reviewers and the media expressing concerns for privacy and monitoring worker performance,” Guo explained. “But the idea is that the data is for the workers themselves—not for management—to help them maintain their health and safety.” Image courtesy of Payal Mohapatra and Vasudev Aravind. The sensors rely on lightweight machine learning algorithms that analyze data from multiple physiological markers, including body movement, heart rate, and skin temperature. In trials conducted at factories such as Boeing’s assembly lines, workers often forgot they were even wearing the sensors, a testament to their unobtrusive design. The potential applications for these sensors extend beyond manufacturing. They could be used in healthcare to monitor patient recovery or in ergonomics to optimize workplace environments. “By understanding how tasks impact worker fatigue, we can create environments that are not only safer but also more efficient,” Guo noted. Partnerships with industry leaders such as John Deere, Boeing, GM, Intel, and John Deere underscore the practical implications of Guo’s research. These collaborations enable rapid prototyping, testing, and iteration, ensuring that the technologies developed in his lab are both innovative and market-ready. “Our vision is to create a smarter, more adaptive system that improves efficiency across industries, from manufacturing to intelligence,” Guo said. {Categories} _Category: Takes{/Categories} {URL}https://3dprint.com/315009/the-future-of-manufacturing-is-on-display-at-prof-ping-guos-northwestern-lab/{/URL} {Author}Michael Molitch-Hou{/Author} {Image}https://3dprint.com/wp-content/uploads/2024/12/structural-coloration-ping-guo-northwestern.jpeg{/Image} {Keywords}3D Printing,3D Printing Materials,3D Printing Research,Automation,Exclusive Interviews,Featured Stories,Metal 3D Printing,North America,Quality Control,autonomous robotics,computer vision,energy efficiency,ergonomic optimization,fatigue monitoring,intelligent metrology,Northwestern University,photometric stereo,physiological data sensors,Ping Guo,solid-state powder production,structural coloration,surface defect detection,surface functionalization,surface patterning robots,ultrasonic vibration machining,vibration-assisted machining,wearable sensors,worker safety{/Keywords} {Source}POV{/Source} {Thumb}{/Thumb}