The Silicon Review
“The Black-Box, based on machine language processing, enables us to reproduce, see, understand, interpret, analyze, learn, and predict machine control operations and health conditions.”
The latest technological improvements and developments in the manufacturing industry, also known as industry 4.0, have changed how the manufacturing industry works entirely. Industry 4.0 is paving the path for digitization of the manufacturing sector, where artificial intelligence (AI) and machine learning (ML) based systems are not only changing the ways we interact with information and computers but also revolutionizing it. It has brought about a change in the pattern of the operation of industry, driven by a new form of interaction between man and machine.
UDMTEK CO., LTD is one such leader in AI and ML technologies, primarily focusing on research and development of next-generation simulation areas. The company develops and delivers Unified Digital Manufacturing (UDM) technology with robust digital transformation trends. UDMTEK, with its research groups including academic and industry members, have worked for developing UDM solutions applying automobile, display, electronics, chemical process, and PLC controlled machinery.
UDMTEK was founded in 2007 and is headquartered in Gyeonggi-do, Korea.
GI NAM Wang, CEO of UDMTEK CO., LTD spoke exclusively to The Silicon Review on how his company is revolutionizing digital transformation.
Q. What was the motivation behind starting UDMTEK CO., LTD?
UDMTEK was established in the UDM LAB laboratory of Ajou University in Korea while carrying out the virtual commissioning project, an industry-academic project of Hyundai Motor Company. It started competitively with global companies, and many master’s and doctoral researchers graduated without finishing a project. UDMTEK was established to continuously conduct Hyundai projects and international practical research without interruption.
Q. Can you explain about your services in brief?
UDMTEK tries to provide next-generation new value in the fields of the industry 4.0 manufacturing AI, AI edge-based automation, analytic AI platform, digital twin, and intelligent factory through the development of MLP (machine language processing) technology which is different from the existing natural language processing.
Q. How do you conceive, create, and introduce unique products and solutions to the world? Tell us in brief about the processes involved.
Machine language processing is a technology developed by UDMTEK for the first time. UDMTEK defines machine language processing as understanding static and dynamically executed control programs. To understand the program being executed, it is necessary to first express different low-level languages for various controllers in a common high-level language. The next step is grasping the relationship between static and dynamic information flows in the process of executing the control software. Dynamic information is the process of communicating with various sensors or control H/Ws related to the input and output of the control S/W.
The Black-Box, based on machine language processing, enables us to reproduce, see, understand, interpret, analyze, learn, and predict machine control operations and health conditions. It could reproduce and analyze possible issues while executing control logic for the complex process in the past, evaluating predictable AI methods.
Q. How do you maintain exclusivity in the marketplace?
MLP (Machine Language Processing) will give life to the machine and make it intelligent by linking and interpreting all data generated inside the machine and data observed outside the machine. Customers and users could create additional values, new technologies, and new industries with MLP.
MLP is different from human language processing, and S/W or service development using MLP requires a deep understanding of the controlling machine or various manufacturing processes and a deep understanding of the control. In addition, MLP also requires deep S/W development technology, and the entry barrier for related technology development is very high. We continuously develop new products while continuously patenting related product technologies.
Q. Tell us about the support services offered by you to improve customer experience.
The Black-Box collects and interprets large-scale manufacturing data from major LG groups at high speed and uses it to analyze precise control operations. It is utilized to track delay factors and optimize process operations.
In Hyundai, Kia, MOBIS, LG Energy Solutions, the Black-Box was applied to equipment abnormality identification and health trend analysis interpreting control program execution and explainable the machine cycle time chart and graph AI of data expression. It could create a robust anomaly analysis and prediction system using the reproduction of the failure occurrence and the corresponding pattern analysis.
Q. Compliance is important for any organization. What are the measures you adopt to comply with regulations?
We are currently in the stage of expanding our organization. We are trying to find a way to give responsibility and authority to individuals as much as possible. We give each team leader as much authority as possible to manage the regulations.
Q. Experts predict that failure of trusted algorithms is bound to happen. How can you make your solution foolproof?
Our solutions are tested in many operations at various sites. And while complementing each other, we are continuously building possible different test scenarios.
Q. How do you market your services?
So far, customers have visited us, such as Hyundai KIA Motors, Hyundai MOBIS, LG Energy Solution, LG Display, LG Electronics, etc. In the future, we are planning to expand domestically, focusing on retaining current customers, and expand overseas to the European market like EPLAN S&S. We are also looking for resellers for The US and Japanese markets.
Q. Do you have any new services ready to be launched?
We are planning to release a new product. It is a product that allows engineers to continuously improve their knowledge while evaluating the AI predictive model they have created while improving AI’s model accuracy complementarily.
Q. What does the future hold for your company and its customers? Are exciting things on the way?
Unlike the name, the Black-Box enables an understanding of all anonymous data flow in the manufacturing process or machine, making an understandable white box. Engineers and AI models based on Black-Box will be continuously intelligent, complementarily working with each other.