Field-test the Metaverse in 360° to Boost Productivity
Assembly Line
This week's most influential Industry 4.0 media.
Toyota Improves Engine Assembly
As examples of how the plant is contributing to the company’s goal of carbon neutrality, Matsuoka points to a manual assembly line that uses karakuri—material handling mechanisms that do not rely on electricity—and a casting line that has eliminated the need for large-scale equipment. By using karakuri mechanisms, engineers have been able to improve lifting operations so that they can be done with a single touch. Since parts can be moved without applying a large amount of force, safety issues are also solved, meaning that covers are no longer needed.
Although casting requires a large amount of energy, improvements have reduced annual CO2 emissions by approximately 1,800 tons, or the equivalent of annual emissions of 600 households. These changes were brought about when Toyota introduced its next-generation engine design. To realize both high fuel efficiency and high power output, engineers concentrated on improving the engine’s thermal efficiency. This required improvements in the cylinder head cooling functions. Specifically, this means that the water jacket, through which coolant passes, must pass extremely close to the combustion chamber and exhaust port, where temperatures are highest.
Warping in the real world: Remote factory meetings in 360°
In a research project with SB&D, ETH students Michael Stegmaier and Cesare Primultini led our field test of interactive mixed reality live streaming technology in manufacturing. Michael and Cesare conceptualized two ways to transmit live-streaming 360° video from the shop floor of SB&D: A first-person view where a camera was mounted to a hard hat and a fixed-position view where the camera could be mounted inside a machine during a changeover. Live-streamed 360° video would be transmitted to a cloud, where participants would meet virtually from anywhere (see figure below). Back in 2021, we identified Avatour, a startup from California, as our project’s only viable software provider.
Where can this technology find good use? High-potential use cases are safety audits, training programs, and tasks that require the presence of an expert or coach. Other use cases are factory tours, external or internal audits, technology transfer projects, inspections, and on-the-job coaching of individuals.
Hitachi's metaverse tech helps keep Japanese craftsmanship alive
Hitachi has developed a metaverse-based system that lets skilled workers run remote demonstrations using real-world factory equipment, with an eye toward industries where know-how is concentrated among aging veterans. This reporter experienced it firsthand with demonstration equipment. Through a virtual reality headset, an image of an instructor’s hands was superimposed on a drum-shaped machine.
Improving Quality and Consistency with Robotic Sanding
Hierarchical ensemble deep learning for data-driven lead time prediction
This paper focuses on data-driven prediction of lead times for product orders based on the real-time production state captured at the arrival instants of orders in make-to-order production environments. In particular, we consider a sophisticated manufacturing system where a large number of measurements about the production state are available (e.g. sensor data). In response to this complex prediction challenge, we present a novel ensemble hierarchical deep learning algorithm comprised of three deep neural networks. One of these networks acts as a generalist, while the other two function as specialists for different products. Hierarchical ensemble methods have previously been successfully utilised in addressing various multi-class classification problems. In this paper, we extend this approach to encompass the regression task of lead time prediction. We demonstrate the suitability of our algorithm in two separate case studies. The first case study uses one of the largest manufacturing datasets available, the Bosch production line dataset. The second case study uses synthetic datasets generated from a reliability-based model of a multi-product, make-to-order production system, inspired by the Bosch production line. In both case studies, we demonstrate that our algorithm provides high-accuracy predictions and significantly outperforms selected benchmarks including the single deep neural network. Moreover, we find that prediction accuracy is significantly higher in the synthetic dataset, which suggests that there is complexity (i.e. subtle interactions) in industrial manufacturing processes that are not easily reproduced in artificial models.
Business Transactions
This week's top funding events, acquisitions, and partnerships across industrial value chains
Sierra Space Increases Total Investment to a Record $1.7 Billion with $290M Series B Funding, Bringing Valuation to $5.3 Billion
Sierra Space, a leading pureplay commercial space company building the first end-to-end business and technology platform in space with $3.4 billion in customer contracts, announced today it has closed a $290 million Series B funding round.
With this latest private capital infusion, Sierra Space expects to forge critical global partnerships and accelerate plans to build a transformational space tech ecosystem that will revolutionize the space economy of tomorrow. The company is currently transitioning the Dream Chaser spaceplane from years of development to recurring mission operations for NASA cargo resupply flights to the International Space Station (ISS). The company has been in development of the first commercial space station for five years, successfully achieving several hardware design and testing milestones; full-scale testing is due by the end of this year. The program maturity cements Sierra Space’s position as the industry leader in business-ready commercial space station development for use in Low Earth Orbit (LEO) and in deep space.
Electrifying success: H55 the leading provider of certified electric propulsion technologies raises CHF 45 million in its Series C financing round
The secured funds will be deployed to finance H55’s ongoing infrastructure investments including building a factory in its recently established Montreal, Quebec facility, moving to semi and automated production in the company’s production facilities in Switzerland and Canada and opening a subsidiary in Toulouse, France. These financial resources will also expedite the development and commercialization of H55’s electric aviation technologies, encompassing advanced propulsion systems and state-of-the-art battery technologies.
GeologicAI Announces $10M in Additional Funding
GeologicAI, a global leader in digital rock analysis, announced the closing of an additional US$10 million in funding from Export Development Canada (“EDC”) as an extension to its Series A financing round led by Breakthrough Energy Ventures, bringing the total round of funding to US$30 million. This investment will accelerate global deployment of GeologicAI’s fleet of AI-powered robot geologists to support the exploration and extraction of the critical minerals required for the energy transition.
Traceless Materials raises €36.6M for eco-friendly plastic alternative
Hamburg-based biomaterials startup traceless materials has raised €36.6 million in a Series A funding round. The startup intends to use the investment to scale the production capabilities of its plastic alternative beginning with the construction of a demonstration plant.
UnitX Raises $5M from SE Ventures to Elevate Manufacturing Quality with AI-powered Defect Detection
UnitX, a robotics company building next-generation AI vision systems at the forefront of quality and yield management in manufacturing, is proud to announce a $5 million investment from SE Ventures, a Silicon Valley-based venture fund backed by global energy and automation giant Schneider Electric.
UnitX, through its software-defined vision system (“OptiX”) and its edge AI compute platform (“CorteX”), delivers unparalleled inspection and defect detection capabilities to manufacturing customers. This technology can drive step-change improvements in the detection of visual defects that often escape error-prone and overworked human inspectors or legacy machine vision systems. By partnering with UnitX, customers can significantly reduce scrap, improve yield, and maintain the highest quality standards.
Emerson Ventures Invests in First Resonance
Emerson (NYSE EMR) today announced it has made a strategic investment through Emerson Ventures, its corporate venture capital arm, in First Resonance, a Los Angeles-based start-up transforming manufacturing with its ION Factory Operating System (OS).
John Deere and Yara partner to increase fertilization efficiency
John Deere and Yara have joined forces to launch a partnership that will combine Yara’s agronomic expertise with John Deere’s precision technology and advanced machinery. The partnership will enable farmers to increase yields and optimize fertilizer use, helping them contribute to the ambition of the European Union’s Farm to Fork Strategy.