Tell the Story of Manufacturing Technology

Exponential Industry begins year two. Autonomous mobile robots rove around industrial sites. Automotive semiconductors remain a problem.

Jan 02, 2022

Exponential Industry started at the beginning of 2021 with a single goal: aggregate the highest quality media and research on Industry 4.0 technologies. Preferably direct from the source of action. To that end, over a thousand periodicals, blogs, YouTube channels, and podcasts are sifted through on a weekly basis. The best 5 to 10 are brought to you each week.

But, that’s not all.

More than being a just a newsletter, Exponential Industry seeks to smartly archive this information to recall the adoption journey going on in each vertical, organization, and topic. To my surprise, when I launched there were no blog templates to do this. So I built one. In 2022, there is plenty more to come on using this archive to tell the stories of the transformation occurring. If you would like to tell your story, reach out to me on Twitter or reply to this email.

Lastly, Exponential Industry seeks to build community across engineers, managers, and observers innovating within industry. To date, we have organically attracted leading venture capitalists, founding CEOs, enterprise sales executives, and many engineers to the community. I have yet to build out the tools to enable engagement across community members, but I hope to soon. If you’ve been enjoying this newsletter, please share with colleagues and friends!

Assembly Line

Sensor fusion gets robots roving around factories

Date: December 21, 2021

Tweet | Pocket | Instapaper

Adam explained that most manufacturing processes are organized around fixed conveyors and robotic systems. To vary the specifications of the end product, human operators are typically needed to move product pieces from one assembly process to another. ‘Increasing flexibility requires more people to handle the work pieces and push them around, but this human intervention does not add much value,’ he said.

For that reason large manufacturing companies are keen to deploy mobile robots to transport inventory and product pieces around the factory floor. These autonomous mobile robots (AMRs) are designed to move and operate by themselves, which means that they must be able to perceive their surroundings and react to them. Visual information is crucial to aid navigation and avoid collisions, as well as to enable the robot to perform simple functions such as selecting and picking up the objects that need to be moved.

Read more at Imaging & Machine Vision Europe

The Role Of Blockchain In The Development Of The EV Industry

Date: December 21, 2021
Author: Naveen Joshi
Vertical: Automotive

Tweet | Pocket | Instapaper

Blockchain-based applications come with a track-and-trace feature. This feature allows EV manufacturers to keep tabs on the materials as they are brought for production. Certain types of materials, such as wolframite and cobalt, are sourced from hard-to-trace developed countries. Such materials change hands several times before they’re brought to factories for processing and production. Therefore, blockchain is useful to accurately store the provenance-related details of raw materials so that the manipulation of such materials coming from such sources can be prevented. Using blockchain for EV production also enables manufacturers to monitor any diversions while materials are being brought into factories for EV production. Blockchain-enabled tracking allows EV manufacturers to react to vehicle recalls in a cost-effective way. If there are any material issues that require vehicles to be recalled, the manufacturers can call back only those EVs that were built using parts or materials from the partner who supplied them. This makes your supply chain much leaner and cost-effective. A leaner supply chain results in lower production costs for EV makers.

How Elon Musk’s Software Focus Helped Tesla Navigate Chip Shortage

Date: December 30, 2021
Author: Rebecca Elliott
Vertical: Automotive

Tweet | Pocket | Instapaper

Tesla has been able to keep production lines running in part by leaning on in-house software engineering expertise that has made it more adept than many rival auto makers at adjusting to a global shortfall of semiconductors, industry executives and consultants said. Chips are used in everything from controlling an electric motor to charging a phone.

Read more at Wall Street Journal (Paid)

How a startup uses AI to put worker safety first

Date: December 21, 2021
Author: @LouisColumbus

Tweet | Pocket | Instapaper

Everguard.ai, a startup based in Irvine, California, combines AI, computer vision, and sensor fusion to reduce the risk of injuries and accidents by preventing them before they happen. The company’s SENTRI360 platform proves effective in preventing workplace injuries and operational downtimes at several steel-heavy manufacturing companies, including Zekelman Industries and SeAH Besteel.

Everguard’s CEO, Sandeep Pandya shared details about workers’ privacy, given the massive amount of data it captures and analyzes at client sites. “The most important thing is to give shop floor workers and their leaders the complete visibility into how the data collected is used. Our implementation teams work with them and provide complete access to our systems, how data is anonymized for specific tasks, and how we are careful to protect each workers’ identity,” Sandeep said.

A deep transfer learning method for monitoring the wear of abrasive belts with a small sample dataset

Date: December 13, 2021
Authors: Zhihang Li, Qian Tang, Sibao Wang, Penghui Zhang

Tweet | Pocket | Instapaper

According to the analysis of displacement data, a new method for the prediction of abrasive belt wear states using a multiscale convolutional neural network based on transfer learning is proposed. Initially, first-order difference preprocessing is ingeniously performed on displacement data. Then, the network parameters of the model are obtained by pretraining the fault dataset and are directly transferred or fine-tuned according to the preprocessed displacement data. Finally, the preprocessed displacement data corresponding to different abrasive belt wear states are accurately classified. This method verifies the application of transfer learning between cross-domain data in industry and resolves the contradiction between the large sample size required for deep learning and the difficulty of obtaining a large amount of sample data in actual production. The experimental results show that this method can accurately predict the wear status of abrasive belts, with an average prediction accuracy of 93.1%. This method has the advantages of low cost and easy operation, and can be applied to guide the replacement time of abrasive belts in production.

Surge Demand

A recap of Asian stocks performance in 2021, with lesser known manufacturers leading the way. Samsung beat out Intel to take the top spot for semiconductor sales in 2021. Autonomous trucking software remains competitive. Molex released a report on the State of Industry 4.0. The Log4J threat persists in SCADA systems and raises questions about open source development.