|
|
|
A
Paperitalo
Publication
|
|
Welcome to Industree 4.0 for March 2022, exclusively sponsored by SAP. |
|
|
By Susan Galer and
Kai Aldinger, SAP
|
|
Sustainable AI Turns Small Data Into Huge Results |
Sparse modeling AI is edging out traditional deep learning to become the technology of choice for product manufacturers like paper producers because it ticks off all the boxes for modern quality control: explainability, energy efficiency, and speed. Just ask some of the customers from Hacarus, a Japan-based startup that’s developed a standout AI-fueled visual inspection solution.
“Sparse modeling AI is a surprising revelation for our clients that need to innovate faster while meeting high-quality standards, whether it’s electric vehicles, luxury watches, or drug discovery,” said Kenshin Fujiwara, CEO and founder of Hacarus. “They’re amazed at how we’re tackling traditional AI’s dirty secret, reducing the high energy costs of data collection and training, which saves time and our planet’s resources.”
A green, explainable AI alternative
According to some studies, training a single AI model using traditional machine learning (ML) can equal the carbon emissions of five cars across their entire lifecycles. That’s because ML algorithms attempt to “understand” every detail gleaned from huge amounts of data from scratch. In contrast, sparse modeling doesn’t require training from tens of thousands of images to yield a strong model for prediction. Because it starts with built-in assumptions, restrictions, and hypotheses, sparse modeling saves time by ignoring what’s already known. This reduces computational time and energy consumption.
On the factory floor, manufacturers need far fewer samples of both good and bad product parts to train the AI model, speeding up visual product inspections to detect defects and anomalies without sacrificing sustainability. Inside research labs, sparse modeling yields more explainable AI. For example, scientists exploring new drug treatments can more easily distinguish chemical compound reactions. In one pilot project with a pharmaceutical company in Japan, Hacarus’ solution performed 56 times faster than a deep learning algorithm.
“Sparse modeling is ideal for any precision engineering equipment or research company developing advanced products with less data,” Fujiwara. “Electric vehicle parts are a great example because it’s a brand new sector. Automakers and suppliers can create a reliable, AI-based model with as little as 20 images. It delivers the equivalent results of deep learning in a fraction of the time and energy.”
In addition to electric and combustion-fueled vehicle manufacturers, Hacarus’ customers in Japan and Europe span numerous industries, including luxury goods, chemicals, and life sciences. A global pharmaceutical company shortened drug discovery computational times by 99%, while gaining insights into correlational changes, bringing crucial explainability into the field. One chemicals and life science products manufacturer combined Hacarus AI technology with sensors to speed up carboxymethyl cellulose sodium (CMC) quality inspections by 600%. CMC is an environmentally friendly plant-derived material used in many products such as lithium-ion batteries and high-grade fish feed. The company expected to reduce inspection labor and training costs by about 50% over the next two to three years.
Applications in the paper industry include optimizing quality and energy consumption. Operational data such as speed or temperature from machine sensors, quality characteristics such as water content or fiber length of the raw materials, or the measured energy consumption from intelligent electricity meters can be combined to gain insights and achieve optimizations that would not be apparent without the use of AI. In an application in the paper industry, for example, it was found that the conveyor belts for the paper fabric from different suppliers- though they should be identical according to the specification - lead to different energy consumption.
Using AI for sustainable business innovation
Hacarus is Fujiwara’s fourth startup, and the company’s history reflects the entrepreneur’s gold standard of fast fail until you make it with phenomenal success. The startup began as an IoT-based kitchen scale, followed by a fitness app ─ all the while focusing on small data analysis ─ before arriving at sparse modeling to help industrial and researchers achieve more with less.
“Hacarus means ‘to measure’ in Japanese, and I’ve always been focused on getting results from small data” he said. “We realized that sparse modeling would help companies gain the benefits of AI where gathering large data sets was not possible or economical.”
Partnership with SAP.iO for shared sustainable vision
“SAP is a global leader in our mutual priority industries, and they helped us understand what customers were looking for,” said Fujiwara. “Integrating inspection data from our sparse modeling AI capabilities with SAP solutions helps organizations continue digitalization for Industry 4.0. This reflects SAP’s vision for companies to become intelligent, sustainable, networked enterprises.”
While most of Hacarus’ customers are currently in Japan, international expansion plans are underway with projects in Europe and growing opportunities in North America. Widely used in academia — it was the technology used to create the first ever image of a black hole — sparse modeling is now lighting the way to more sustainable AI.
|
|
|
|
By Pat Dixon, PE, PMP
Vice President of Automation, Pulmac Systems International (pulmac.com)
|
|
The first mention of the term Industry 4.0 that most of us are aware of came from the 2011 Hannover Fair in Germany. Here we are 11 years later and there is wide disparity and disagreement on what Industry 4.0 means.
An example is a recent interview between Walker Reynolds and Alasdair Gilchrist. Walker is founder of Intellic Integration, one of the leading Industry 4.0 system integration firms. Alasdair is author of the book “Industry 4.0: The Industrial Internet of Things”. These well credentialed speakers argued for over an hour on the definition of Industry 4.0. This is one example among many demonstrating confusion in the marketplace.
This is why I will be speaking at TappiCon and the IEEE Pulp and Paper conference about the “Industry 4.0 Lexicon”. This is the result of a project to create definitions of terms pertinent to Industry 4.0. If industry is going to be transformed into a new era, there should at least be common understanding of the goal.
|
|
|
|
|
|
We tend to accept and believe what we can see and that which is in our immediate surroundings. As our world has expanded to encompass the whole world, indeed the universe to some extent, this visual verification of reality sometimes fails us.
I have manage to experience three eras of reality thus far. When a boy, my father was heavily involved in the era of replacing steel and other materials with plastic, especially fiberglass reinforced plastic. I didn't realize, and I don't think the adults of the day realized, what ramifications the explosion in plastics goods would create.
In my early career years, as an engineer at one of the largest consumer goods companies in the world, we experienced the throwaway era. Use a product, throw away the packaging. We designed them all this way.
For the last thirty years, I have been, to a large extent, involved in recycling in the pulp and paper industry.
All three of these eras were visual. We trusted what we could see.
As Galer and Aldinger note in their article above, in today's world we must look beyond the visual. To quote them again, "According to some studies, training a single AI model using traditional machine learning (ML) can equal the carbon emissions of five cars across their entire lifecycles."
I bought the first computer for one of my businesses in 1979. At the time, we did not think about the energy a computer would use, it was perceived to be trivial, especially as they moved from climate controlled rooms to the desktop. In the ensuing 43 years, computers, computing power and computational energy requirements have exploded, much like plastics explosion I witnessed in the fifties and sixties. It is being recognized that even the latest craze (my assigned moniker, perhaps not yours), cryptocurrency, is consuming prodigious amounts of energy.
If we want a sustainable world going forward, we will have to learn to look beyond the visual. Thanks to computational power requirements, all is not as it seems any longer.
An example is our own home. My wife and I both work in our house. In most cases, we have the latest energy savings appliances. We have extra insulation and mostly new double pane windows. We have roof mounted solar capacity that can provide up to 30% of our electrical needs in the summer. But...we have at least three, often four, computers running at a time, one of them a large server. Our power company sends us an analysis of our purchased usage each month. Consistently, we run about 15 - 20% higher than comparably sized homes in our area. Oh, did I mention our robotic lawn mower, which according to its readout, travels about 700 MILES per year across our small lawn?
It all adds up.
|
|
|
|
Digital Twins for Discrete Manufacturing Applications |
|
|
|
An integral component of a digital twin of a production system is the virtual model of the real-world products, assets, and processes. Virtual modeling provides manufacturing engineers with the ability to simulate and model the virtual and the physical, simultaneously or separately. |
|
|
|
Your Guide to Remote IoT Device Management |
|
|
|
Learning about remote IoT device management is an important step to keeping your business secure and helping it grow. IoT consulting services can also be helpful for security and improving efficiency. Being aware of the challenges, tips, and new standards in the IoT market will make your remote IoT device management both effective and tailored to the needs of your business. |
|
|
|
How Industry 4.0 is Changing the Employment Market |
|
|
|
The employment market has been adopting new technologies, including Industry 4.0. With smart technologies becoming more mainstream, it’s worth considering the impact of these technologies on society and the workforce. |
|
|
|
Automation Won’t Fix a False Sense of Lean Maturity |
|
|
|
There is a myth in the world, even within manufacturing itself, that factories are filled with assembly lines with full automation and robots. While there are increases in the amount of automation deployed generally, fully automated “lights-out” factories couldn’t be further from the truth. In fact, manufacturing is a $15 trillion industry, making up nearly 13% of the world GDP, with 70% of assembly tasks still performed by people. |
|
|
|
Industree 4.0 is exclusively sponsored by SAP |
|
|
|
|
|
|
