Goto

Collaborating Authors

Results


Machine-learning system accelerates discovery of new materials for 3D printing

#artificialintelligence

The growing popularity of 3D printing for manufacturing all sorts of items, from customized medical devices to affordable homes, has created more demand for new 3D printing materials designed for very specific uses. To cut down on the time it takes to discover these new materials, researchers at MIT have developed a data-driven process that uses machine learning to optimize new 3D printing materials with multiple characteristics, like toughness and compression strength. By streamlining materials development, the system lowers costs and lessens the environmental impact by reducing the amount of chemical waste. The machine learning algorithm could also spur innovation by suggesting unique chemical formulations that human intuition might miss. "Materials development is still very much a manual process. A chemist goes into a lab, mixes ingredients by hand, makes samples, tests them, and comes to a final formulation. But rather than having a chemist who can only do a couple of iterations over a span of days, our system can do hundreds of iterations over the same time span," says Mike Foshey, a mechanical engineer and project manager in the Computational Design and Fabrication Group (CDFG) of the Computer Science and Artificial Intelligence Laboratory (CSAIL), and co-lead author of the paper.


MIT Uses AI To Accelerate the Discovery of New Materials for 3D Printing

#artificialintelligence

Researchers at MIT and BASF have developed a data-driven system that accelerates the process of discovering new 3D printing materials that have multiple mechanical properties. A new machine-learning system costs less, generates less waste, and can be more innovative than manual discovery methods. The growing popularity of 3D printing for manufacturing all sorts of items, from customized medical devices to affordable homes, has created more demand for new 3D printing materials designed for very specific uses. To cut down on the time it takes to discover these new materials, researchers at MIT have developed a data-driven process that uses machine learning to optimize new 3D printing materials with multiple characteristics, like toughness and compression strength. By streamlining materials development, the system lowers costs and lessens the environmental impact by reducing the amount of chemical waste.


Accelerating the discovery of new materials for 3D printing

#artificialintelligence

The growing popularity of 3D printing for manufacturing all sorts of items, from customized medical devices to affordable homes, has created more demand for new 3D printing materials designed for very specific uses. To cut down on the time it takes to discover these new materials, researchers at MIT have developed a data-driven process that uses machine learning to optimize new 3D printing materials with multiple characteristics, like toughness and compression strength. By streamlining materials development, the system lowers costs and lessens the environmental impact by reducing the amount of chemical waste. The machine learning algorithm could also spur innovation by suggesting unique chemical formulations that human intuition might miss. "Materials development is still very much a manual process. A chemist goes into a lab, mixes ingredients by hand, makes samples, tests them, and comes to a final formulation. But rather than having a chemist who can only do a couple of iterations over a span of days, our system can do hundreds of iterations over the same time span," says Mike Foshey, a mechanical engineer and project manager in the Computational Design and Fabrication Group (CDFG) of the Computer Science and Artificial Intelligence Laboratory (CSAIL), and co-lead author of the paper.


BMW research explores value of AI for automated AM part identification in automotive - 3D Printing Industry

#artificialintelligence

With time-to-market in the automotive industry steadily decreasing, the demand for additive manufactured prototyping components is higher than ever. However, in order to make larger 3D printed volumes tangible, process chains still need to be optimized and further developed in regards to output quantity, production speed, and economic viability, according to a new study by German multinational automotive firm BMW. Having identified a need to further optimize and increase the efficiency of additive manufacturing technologies and their process chains, BMW has conducted research into the complexity and economical value of Artificial Intelligence (AI) for the automated identification of 3D printed parts. The paper outlines the state-of-play of current available additive manufacturing process chains, the complexities of using AI for part recognition, and the economic viability of using AI-based platforms such as AM-VISION, an automated machine learning part recognition system from Dutch 3D printing, post-processing and automation firm AM-Flow, to further industrialize overall 3D printing process chains. The research paper, which has been compiled by authors from BMW, AM-Flow and the University of Duisburg-Essen (UDE), highlights how additive manufacturing's technological progress is enabling higher production speeds, increased choice of materials, and adjustable robust mechanical properties within parts that resemble those of conventional products.


Amortized Synthesis of Constrained Configurations Using a Differentiable Surrogate

arXiv.org Artificial Intelligence

In design, fabrication, and control problems, we are often faced with the task of synthesis, in which we must generate an object or configuration that satisfies a set of constraints while maximizing one or more objective functions. The synthesis problem is typically characterized by a physical process in which many different realizations may achieve the goal. This many-to-one map presents challenges to the supervised learning of feed-forward synthesis, as the set of viable designs may have a complex structure. In addition, the non-differentiable nature of many physical simulations prevents direct optimization. We address both of these problems with a two-stage neural network architecture that we may consider to be an autoencoder. We first learn the decoder: a differentiable surrogate that approximates the many-to-one physical realization process. We then learn the encoder, which maps from goal to design, while using the fixed decoder to evaluate the quality of the realization. We evaluate the approach on two case studies: extruder path planning in additive manufacturing and constrained soft robot inverse kinematics. We compare our approach to direct optimization of design using the learned surrogate, and to supervised learning of the synthesis problem. We find that our approach produces higher quality solutions than supervised learning, while being competitive in quality with direct optimization, at a greatly reduced computational cost.


AI Weekly: AI helps companies design physical products

#artificialintelligence

This week in a paper published in the journal Nature, researchers at Google detailed how they used AI to design the next generation of tensor processing units (TPU), the company's application-specific integrated circuits optimized for AI workloads. While the work wasn't novel -- Google's been refining the technique for the better part of years -- it gave the clearest illustration yet of AI's potential in hardware design. But the Nature paper suggests AI can at the very least augment human designers to accelerate the brainstorming process. Beyond chips, companies like U.S.- and Belgium-based Oqton are applying AI to design domains including additive manufacturing. Oqton's platform automates CNC, metal, and polymer 3D printing and hybrid additive and subtractive workflows, like creating castable jewelry wax.


Machine Learning for Smarter 3D Printing

#artificialintelligence

However, one issue that still persists is how to avoid printing objects that don't meet expectations and thus can't be used, leading to a waste in materials and resources. Scientists at the University of Southern California's (USC's) Viterbi School of Engineering has come up with what they think is a solution to the problem with a new machine-learning-based way to ensure more accuracy when it comes to 3D-printing jobs. Researchers from the Daniel J. Epstein Department of Industrial and Systems Engineering developed a new set of algorithms and a software tool called PrintFixer that they said can improve 3D-printing accuracy by 50 percent or more. The team, led by Qiang Huang, associate professor of industrial and systems engineering and chemical engineering and materials science, hopes the technology can help make additive manufacturing processes more economical and sustainable by eliminating wasteful processes, he said. "It can actually take industry eight iterative builds to get one part correct, for various reasons," said Qiang, who led the research.


Region of Attraction for Power Systems using Gaussian Process and Converse Lyapunov Function -- Part I: Theoretical Framework and Off-line Study

arXiv.org Machine Learning

This paper introduces a novel framework to construct the region of attraction (ROA) of a power system centered around a stable equilibrium by using stable state trajectories of system dynamics. Most existing works on estimating ROA rely on analytical Lyapunov functions, which are subject to two limitations: the analytic Lyapunov functions may not be always readily available, and the resulting ROA may be overly conservative. This work overcomes these two limitations by leveraging the converse Lyapunov theorem in control theory to eliminate the need of an analytic Lyapunov function and learning the unknown Lyapunov function with the Gaussian Process (GP) approach. In addition, a Gaussian Process Upper Confidence Bound (GP-UCB) based sampling algorithm is designed to reconcile the trade-off between the exploitation for enlarging the ROA and the exploration for reducing the uncertainty of sampling region. Within the constructed ROA, it is guaranteed in probability that the system state will converge to the stable equilibrium with a confidence level. Numerical simulations are also conducted to validate the assessment approach for the ROA of the single machine infinite bus system and the New England $39$-bus system. Numerical results demonstrate that our approach can significantly enlarge the estimated ROA compared to that of the analytic Lyapunov counterpart.


Multi-agent Reinforcement Learning Embedded Game for the Optimization of Building Energy Control and Power System Planning

arXiv.org Machine Learning

Most of the current game-theoretic demand-side management methods focus primarily on the scheduling of home appliances, and the related numerical experiments are analyzed under various scenarios to achieve the corresponding Nash-equilibrium (NE) and optimal results. However, not much work is conducted for academic or commercial buildings. The methods for optimizing academic-buildings are distinct from the optimal methods for home appliances. In my study, we address a novel methodology to control the operation of heating, ventilation, and air conditioning system (HVAC). With the development of Artificial Intelligence and computer technologies, reinforcement learning (RL) can be implemented in multiple realistic scenarios and help people to solve thousands of real-world problems. Reinforcement Learning, which is considered as the art of future AI, builds the bridge between agents and environments through Markov Decision Chain or Neural Network and has seldom been used in power system. The art of RL is that once the simulator for a specific environment is built, the algorithm can keep learning from the environment. Therefore, RL is capable of dealing with constantly changing simulator inputs such as power demand, the condition of power system and outdoor temperature, etc. Compared with the existing distribution power system planning mechanisms and the related game theoretical methodologies, our proposed algorithm can plan and optimize the hourly energy usage, and have the ability to corporate with even shorter time window if needed.


Researchers Explore Machine Learning to Prevent Defects in Metal 3D-Printed Parts in Real Time

#artificialintelligence

For years, Lawrence Livermore National Laboratory engineers and scientists have used an array of sensors and imaging techniques to analyze the physics and processes behind metal 3-D printing in an ongoing effort to build higher quality metal parts the first time, every time. Now, researchers are exploring machine learning to process the data obtained during 3-D builds in real time, detecting within milliseconds whether a build will be of satisfactory quality. In a paper published online Sept. 5 by Advanced Materials Technologies, a team of Lab researchers report developing convolutional neural networks (CNNs), a popular type of algorithm primarily used to process images and videos, to predict whether a part will be good by looking at as little as 10 milliseconds of video. "This is a revolutionary way to look at the data that you can label video by video, or better yet, frame by frame," said principal investigator and LLNL researcher Brian Giera. "The advantage is that you can collect video while you're printing something and ultimately make conclusions as you're printing it.