Robots Are Learning to Recycle for You

Date:

Visual Inspection

SSR/AMP DEMO LONG

From the Evansville Courier & Press:

The high-speed AMP Robotics Cortex uses artificial intelligence to identify and sort materials. In Evansville, it will primarily be used to capture #5 polypropylene, although it will also be used to sort #1 PETE and #2 HDPE bottles when it has extra capacity.

Since it was installed on May 8, the robot has already sorted out about 3,000 pounds of #5 plastic previously being sent to the landfill, Flores said.

Elsewhere in recycling AI, “GarbageNet has the potential to divert compost and recyclables from the landfill.” Learn more at IEEE Spectrum.

Acoustic Monitoring

Assembly Line

Why resources companies are looking to evented APIs

Date:

Author: Ryan Grondal

Topics: industrial control system

Vertical: Mining, Petroleum and Coal

Organizations: MuleSoft

Resources companies that want to get the most value from their data will process it the instant that it is created. The longer that data is left unprocessed, the more it diminishes in value. Operational excellence can be driven by evented APIs that can produce, detect, consume, and react to events occurring within the technology ecosystem.

Evented APIs can be applied to our example use case to deliver an autonomous feedback loop that incorporates smarter decision making in real-time.

Read more at MuleSoft Blog

Trash to Cash: Recyclers Tap Startup with World’s Largest Recycling Network to Freshen Up Business Prospects

Date:

Author: Scott Martin

Topics: AI, edge computing, computer vision, recycling

Vertical: Plastics and Rubber

Organizations: NVIDIA, AMP Robotics

People worldwide produce 2 billion tons of waste a year, with 37 percent going to landfill, according to the World Bank.

“Sorting by hand on conveyor belts is dirty and dangerous, and the whole place smells like rotting food. People in the recycling industry told me that robots were absolutely needed,” said Horowitz, the company’s CEO.

His startup, AMP Robotics, can double sorting output and increase purity for bales of materials. It can also sort municipal waste, electronic waste, and construction and demolition materials.

Read more at NVIDIA Blog

Machine Learning Keeps Rolling Bearings on the Move

Date:

Author: Rehana Begg

Topics: machine learning, vibration analysis, predictive maintenance, bearing

Organizations: Osaka University

Rolling bearings are essential components in automated machinery with rotating elements. They come in many shapes and sizes, but are essentially designed to carry a load while minimizing friction. In general, the design consists of two rings separated by rolling elements (balls or rollers). The rings can rotate can rotate relative to each other with very little friction.

The ability to accurately predict the remaining useful life of the bearings under defect progression could reduce unnecessary maintenance procedures and prematurely discarded parts without risking breakdown, reported scientists from the Institute of Scientific and Industrial Research and NTN Next Generation Research Alliance Laboratories at Osaka University.

The scientists have developed a machine learning method that combines convolutional neural networks and Bayesian hierarchical modeling to predict the remaining useful life of rolling bearings. Their approach is based on the measured vibration spectrum.

Read more at Machine Design

Evolution of Machine Autonomy in Factory Transactions

Date:

Author: Stephanie Neil

Topics: IIoT, blockchain

Organizations: Industrial Internet Consortium, IOTA Foundation, Siemens, IBM

So while we’ve not completely entered the age of the machine economy, defined as a network of smart, connected, and self-sufficient machines that are economically independent and can autonomously execute transactions within a market with little to no human intervention, we are getting close.

The building blocks to create the factory of the future are here, including the Internet of Things (IoT), artificial intelligence (AI), and blockchain. This trifecta of technology has the potential to disrupt the industrial space, but it needs to be connected with a few more things, such as digital twin technology, mobile robots, a standardized way for machines to communicate, and smart services, like sharing machine capacity in a distributed ecosystem.

“The biggest obstacle is culture,” said IIC’s Mellor. “The average age of the industrial plant is 19 years. These are huge investments that last for decades. The organizations that run these facilities are very cautious. Even a 0.5% chance of failure can cost millions of dollars.”

Read more at AutomationWorld

Nissan Accelerates Assembly Line with 3D Printing Solution

Date:

Topics: 3D printing, additive manufacturing

Vertical: Automotive

Organizations: Nissan, BCN3D

Previously Nissan outsourced all of its prototypes and jigs to mechanical suppliers who used traditional manufacturing methods, such as CNC and drilling. Although the quality of the finished product was good, the lead times were long and inflexible and the costs were high. Even simple tools could cost in the region of 400€ for machining. By printing some of these parts in-house with 3D printers, Nissan has cut the time of designing, refining and producing parts from one week to just one day and slashed costs by 95%.

Eric Pallarés, chief technical officer at BCN3D, adds: “The automotive industry is probably the best example of scaling up a complex product with the demands of meeting highest quality standards. It’s fascinating to see how the assembly process of a car – where many individual parts are put together in an assembly line – relies on FFF printed parts at virtually every stage. Having assembled thousands of cars, Nissan has found that using BCN3D 3D printing technology to make jigs and fixtures for complex assembly operations delivers consistently high quality components at a reduced time and lower cost”.

Read more at Manufacturing and Engineering Magazine

Scientists Set to Use Social Media AI Technology to Optimize Parts for 3D Printing

Date:

Author: Kubi Sertoglu

Topics: 3D Printing, additive manufacturing, AI, genetic algorithm

Organizations: Department of Energy, Argonne National Laboratory

“My idea was that a material’s structure is no different than a 3D image,” he explains. ​“It makes sense that the 3D version of this neural network will do a good job of recognizing the structure’s properties — just like a neural network learns that an image is a cat or something else.”

To see if his idea would work, Messner designed a defined 3D geometry and used conventional physics-based simulations to create a set of two million data points. Each of the data points linked his geometry to ‘desired’ values of density and stiffness. Then, he fed the data points into a neural network and trained it to look for the desired properties.

Finally, Messner used a genetic algorithm – an iterative, optimization-based class of AI – together with the trained neural network to determine the structure that would result in the properties he sought. Impressively, his AI approach found the correct structure 2,760x faster than the conventional physics simulation.

Read more at 3D Printing Industry

Surge Demand

COVID-19 exposed the just-in-time trade-offs we have made in our supply chains. Serial entrepreneur Nate Saal creates his own chocolate factory machinery. NVIDIA releases the Jetson AGX Xavier industrial module for harsh, safety-critical environments. Recycled plastic was used to 3D print the Tokyo 2020 Olympic podium.