NTT DATA, NTT COMWARE, ITOCHU Techno-Solutions, and Mitsubishi Chemical Group have successfully demonstrated a smart maintenance solution leveraging the IOWN All-Photonics Network (APN) and AI technologies.
The experiment utilized remote-controlled robots and AI-driven video analysis to inspect factory facilities, achieving real-time crack detection in pipes and precise vibration analysis. Conducted over a 120-kilometer APN between Odaiba and Gotanda in Japan, the system maintained high standards for latency and image quality, proving its practicality.
“Robotics and AI will greatly contribute to reducing human workload in all industries,” said Hidehiko Tanaka, Head of Technology and Innovation at NTT DATA. “We believe that this experiment shows the potential of robots’ detecting anomalies in the field with practical accuracy on behalf of human.”
Explore related questions
The project addressed challenges like high-risk inspections and time-consuming processes by enabling remote monitoring and multimodal AI analysis.
Wataru Imazato, Executive Vice President at NTT COMWARE, highlighted the milestone’s significance, saying, “We aim to further implement other technologies such as remote predictive detection for crack.”
The collaboration is part of the IOWN Global Forum’s vision for a sustainable society. Each company played a distinct role: NTT DATA developed systems for vibration analysis, NTT COMWARE managed the APN environment and digital twin implementation, ITOCHU Techno-Solutions verified high-speed video transmission, and Mitsubishi Chemical Group defined inspection requirements.
The companies plan to expand this technology for real-time, high-accuracy assessments of remote factory environments, enhancing safety and efficiency. Future trials will test the system at a Mitsubishi Chemical manufacturing site.
“Reducing the burden on on-site workers is a problem faced by all manufacturers,” noted Toshiya Katsuragi, CTO of Mitsubishi Chemical Group. “This result is the first step toward a new way of “monozukuri” based on the IOWN APN, including microfactories and others.”
What this means for ERP Insiders
Fault detection in manufacturing is gaining ground. AI-powered sensor data like vibration analysis is helping companies detect anomalies in functions like rotating machinery with accuracy rates that exceed 95%. Additionally, AI-based condition monitoring reduces the time spent diagnosing issues by 40-60% thereby improving operational efficiency.
AI is changing the way manufacturers look at plant maintenance. Predictive maintenance is becoming vital as companies look to reduce their costs, while bolstering efficiency and AI is helping them achieve this goal. For example, Siemens uses AI-powered predictive maintenance solutions to monitor the health of its wind turbines and optimize maintenance schedules to reduce downtime by 20-30%. Meanwhile, GE utilizes AI to predict equipment failures in power plants, minimizing disruptions to energy production. BP has also successfully used AI to monitor pipelines and detect leaks, reducing incident response times by 60%.
Enterprise providers are making clear strides in integrating business AI. SAPinsider research shows that ERP providers like SAP are focusing on AI adoption. For instance, SAP S/4HANA is perceived as a significant driver for AI adoption, with the potential to expand use cases, broaden functional applications, and accelerate implementation timelines. Organizations that effectively leverage this platform are likely to see enhanced AI capabilities and improved business outcomes.
