Predictive maintenance technology is the health check-up of smart factory equipment. A smart factory is an intelligent factory based on the Internet of Things (IoT), artificial intelligence (AI), and big data. The adoption of smart factories has been accelerated since the onset of COVID-19, with automation and robotization driven by a sharp increase in labor costs being major trends. Equipment within smart factories is configured with optimized routes and lines, and any halt in one machine leads not only to production stoppage but also incurs losses such as raw material loss, semi-finished material loss, quality management costs, etc. Therefore, predictive maintenance technology, which diagnoses and monitors equipment, is a critical measure to maintain the productivity of smart factories.
[Image] Importance of predictive maintenance technology
Predictive maintenance is the technology of detecting and predicting abnormalities in equipment by inspecting and monitoring them. Predictive maintenance is categorized into four stages as technology advances. ① Reactive maintenance is the method of fixing equipment when a failure occurs. During the repair time, the equipment stops, worsening productivity until it is restarted. ② Planned maintenance is the execution of maintenance according to a pre-planned schedule. It involves directly performing scheduled maintenance based on each equipment's failure history and inspection cycle. However, this method wastes resources by performing predictive maintenance even on equipment that does not require maintenance. ③ Proactive maintenance is the maintenance method of removing future fault factors in advance to improve equipment performance. While this method minimizes downtime through proactive measures, it also suffers from similar resource waste issues as proactive inspection. ④ Predictive maintenance utilizes AI and big data technology to detect abnormal data from equipment and respond to equipment failures promptly. This method minimizes resource waste and is effective in maintaining productivity through timely responses. However, it requires sensors for anomaly detection and data analysis for predicting future anomalies. Research combining AI and big data to accurately analyze equipment abnormalities, which is the core of predictive maintenance technology, is actively ongoing.
Korean predictive maintenance company MOVIC Lab (CEO Lee Won-geun) has succeeded in raising investment (Pre-A, 1.5 billion won) with a predictive maintenance solution based on equipment vibration. MOVIC Lab's solution, Watch Bat, utilizes an AI Edge device that collects acoustic signals generated by equipment to measure the noise of the equipment up to the ultrasonic band. It then analyzes signal patterns through deep learning to predict the condition and risk of equipment failure. This solution allows real-time monitoring of equipment abnormalities based on sound signals and predicts anomalies using acoustic signals. MOVIC Lab's solution can be applied not only to production equipment but also to facilities (valves, pipes, etc.), making it highly versatile. MOVIC Lab plans to accelerate technology development based on this investment and focus on delivering to large companies next year. Also, it aims to expand into the global market by securing unrivaled ultrasonic diagnostic technology.
[Image] Overview of MOVIC Lab's predictive maintenance solution
Among Korean companies, Onepredict (CEO Yoon Byung-dong) is actively developing technology. Onepredict has predictive maintenance solutions for smart factories, including motor failure prediction diagnosis (Gardione Motor) based on current data, transformer failure prediction diagnosis (Gardione Substation) based on big data, and turbo equipment diagnosis and analysis solution (Gardione Turbo) based on vibration and operating factor data. Recognized for its technological capabilities, Onepredict has achieved large-scale investment (Series C, 30 billion won).
Recently, Onepredict has developed technology to predict future vibrations by analyzing past vibration data and other factors. This technology increases the accuracy of predicting abnormal conditions in rotating equipment, reducing management costs and complexity. In addition, Korean company PNG Tech has developed technology to more accurately predict equipment abnormalities using correlation analysis and CNN (Convolutional Neural Network-based analysis algorithms). Thus, domestic companies are actively developing predictive maintenance technology in line with the increasing adoption of smart factories.
[Image] Onepredict's predictive maintenance solution
Korean government support for the adoption of smart factories is active, especially to enhance the competitiveness of small and medium-sized enterprises (SMEs) through the manufacturing base of smart factories. The Ministry of SMEs and Startups provides active support for the introduction of smart factories through the 'Support Program for Smart Manufacturing Innovation of SMEs', which provides support for up to 50% of the total implementation cost, up to a maximum of 820 million won when introducing smart factories. It is expected that the scale of such support will expand further in line with the policy direction to enhance the competitiveness of SMEs. As the smart factory market grows, the demand for predictive maintenance solutions to manage and handle such equipment will increase significantly. Therefore, if companies seize this opportunity, they can lead the emerging predictive maintenance market.
'BLT insight' introduces a recently invested technology field every week.
If you have any questions about the Korean market or related to intellectual property rights, please ask your questions via the link below:
www.BLT.kr/contact
Or, you can inquire by emailing shawn@BLT.kr
Predictive maintenance technology is the health check-up of smart factory equipment. A smart factory is an intelligent factory based on the Internet of Things (IoT), artificial intelligence (AI), and big data. The adoption of smart factories has been accelerated since the onset of COVID-19, with automation and robotization driven by a sharp increase in labor costs being major trends. Equipment within smart factories is configured with optimized routes and lines, and any halt in one machine leads not only to production stoppage but also incurs losses such as raw material loss, semi-finished material loss, quality management costs, etc. Therefore, predictive maintenance technology, which diagnoses and monitors equipment, is a critical measure to maintain the productivity of smart factories.
[Image] Importance of predictive maintenance technology
Predictive maintenance is the technology of detecting and predicting abnormalities in equipment by inspecting and monitoring them. Predictive maintenance is categorized into four stages as technology advances. ① Reactive maintenance is the method of fixing equipment when a failure occurs. During the repair time, the equipment stops, worsening productivity until it is restarted. ② Planned maintenance is the execution of maintenance according to a pre-planned schedule. It involves directly performing scheduled maintenance based on each equipment's failure history and inspection cycle. However, this method wastes resources by performing predictive maintenance even on equipment that does not require maintenance. ③ Proactive maintenance is the maintenance method of removing future fault factors in advance to improve equipment performance. While this method minimizes downtime through proactive measures, it also suffers from similar resource waste issues as proactive inspection. ④ Predictive maintenance utilizes AI and big data technology to detect abnormal data from equipment and respond to equipment failures promptly. This method minimizes resource waste and is effective in maintaining productivity through timely responses. However, it requires sensors for anomaly detection and data analysis for predicting future anomalies. Research combining AI and big data to accurately analyze equipment abnormalities, which is the core of predictive maintenance technology, is actively ongoing.
Korean predictive maintenance company MOVIC Lab (CEO Lee Won-geun) has succeeded in raising investment (Pre-A, 1.5 billion won) with a predictive maintenance solution based on equipment vibration. MOVIC Lab's solution, Watch Bat, utilizes an AI Edge device that collects acoustic signals generated by equipment to measure the noise of the equipment up to the ultrasonic band. It then analyzes signal patterns through deep learning to predict the condition and risk of equipment failure. This solution allows real-time monitoring of equipment abnormalities based on sound signals and predicts anomalies using acoustic signals. MOVIC Lab's solution can be applied not only to production equipment but also to facilities (valves, pipes, etc.), making it highly versatile. MOVIC Lab plans to accelerate technology development based on this investment and focus on delivering to large companies next year. Also, it aims to expand into the global market by securing unrivaled ultrasonic diagnostic technology.
[Image] Overview of MOVIC Lab's predictive maintenance solution
Among Korean companies, Onepredict (CEO Yoon Byung-dong) is actively developing technology. Onepredict has predictive maintenance solutions for smart factories, including motor failure prediction diagnosis (Gardione Motor) based on current data, transformer failure prediction diagnosis (Gardione Substation) based on big data, and turbo equipment diagnosis and analysis solution (Gardione Turbo) based on vibration and operating factor data. Recognized for its technological capabilities, Onepredict has achieved large-scale investment (Series C, 30 billion won).
Recently, Onepredict has developed technology to predict future vibrations by analyzing past vibration data and other factors. This technology increases the accuracy of predicting abnormal conditions in rotating equipment, reducing management costs and complexity. In addition, Korean company PNG Tech has developed technology to more accurately predict equipment abnormalities using correlation analysis and CNN (Convolutional Neural Network-based analysis algorithms). Thus, domestic companies are actively developing predictive maintenance technology in line with the increasing adoption of smart factories.
[Image] Onepredict's predictive maintenance solution
Korean government support for the adoption of smart factories is active, especially to enhance the competitiveness of small and medium-sized enterprises (SMEs) through the manufacturing base of smart factories. The Ministry of SMEs and Startups provides active support for the introduction of smart factories through the 'Support Program for Smart Manufacturing Innovation of SMEs', which provides support for up to 50% of the total implementation cost, up to a maximum of 820 million won when introducing smart factories. It is expected that the scale of such support will expand further in line with the policy direction to enhance the competitiveness of SMEs. As the smart factory market grows, the demand for predictive maintenance solutions to manage and handle such equipment will increase significantly. Therefore, if companies seize this opportunity, they can lead the emerging predictive maintenance market.
'BLT insight' introduces a recently invested technology field every week.
If you have any questions about the Korean market or related to intellectual property rights, please ask your questions via the link below:
www.BLT.kr/contact
Or, you can inquire by emailing shawn@BLT.kr