17455293. PERFORMANCE OPTIMIZATION OF COMPLEX INDUSTRIAL SYSTEMS AND PROCESSES simplified abstract (International Business Machines Corporation)
PERFORMANCE OPTIMIZATION OF COMPLEX INDUSTRIAL SYSTEMS AND PROCESSES
Organization Name
International Business Machines Corporation
Inventor(s)
Fabio Lorenzi of Tyrrelstown (IE)
Joern Ploennigs of Dublin (IE)
PERFORMANCE OPTIMIZATION OF COMPLEX INDUSTRIAL SYSTEMS AND PROCESSES - A simplified explanation of the abstract
This abstract first appeared for US patent application 17455293 titled 'PERFORMANCE OPTIMIZATION OF COMPLEX INDUSTRIAL SYSTEMS AND PROCESSES
Simplified Explanation
The patent application describes a method for improving the performance of industrial systems and processes using a computing system and a processor. Here are the key points:
- The method involves modeling the dependencies between various entities in a knowledge graph using a graph neural network (GNN).
- A reference graph model is created based on this modeling, which serves as a baseline for comparison.
- The system then monitors and detects anomalies in multiple processes by comparing them to the reference graph model.
- The anomalies can be identified and addressed promptly, leading to improved performance and efficiency in industrial systems.
Potential Applications
This technology has potential applications in various industries and sectors, including:
- Manufacturing: Optimizing production processes, identifying bottlenecks, and improving overall efficiency.
- Supply Chain Management: Tracking and managing inventory, identifying potential disruptions, and optimizing logistics.
- Energy and Utilities: Monitoring and optimizing power generation, distribution, and consumption.
- Healthcare: Improving patient care processes, detecting anomalies in medical devices, and enhancing operational efficiency.
Problems Solved
This technology addresses several challenges in industrial systems and processes, such as:
- Lack of visibility: By modeling dependencies and monitoring anomalies, the system provides a comprehensive view of the entire system, enabling better decision-making.
- Inefficiencies: By detecting anomalies and addressing them promptly, the system helps identify and resolve inefficiencies, leading to improved performance.
- Reactive approach: The system enables a proactive approach by continuously monitoring and detecting anomalies, allowing for timely interventions and preventing potential issues.
Benefits
The use of this technology offers several benefits, including:
- Improved performance: By monitoring and detecting anomalies, the system helps optimize processes, leading to increased efficiency and productivity.
- Cost savings: Identifying and addressing anomalies promptly can help reduce downtime, minimize waste, and optimize resource allocation, resulting in cost savings.
- Enhanced decision-making: The comprehensive view provided by the system enables better decision-making, allowing for proactive measures and improved outcomes.
Original Abstract Submitted
Embodiments are provided for providing increased performance of various industrial systems and processes in a computing system by a processor. Each of a plurality of dependencies of a plurality of entities in a knowledge graph are modeled as a graph neural network (“GNN”). A reference graph model is generated based on the modeling. One or more anomalies are monitored and detected for a plurality of process based on the reference graph model.
