​
Automated Infrastructure: Integration of Diverse Data
Invention Summary:
The degradation monitoring of transportation infrastructure such as roads and railways, in the US faces challenges due to the vastness of the network and limited resources for continuous inspection. There is a need for predictive maintenance and life-cycle management of infrastructure, that does not require direct monitoring and assessments that focuses on modeling the degradation of critical assets, such as railways and other transportation structures, which are subject to wear and deterioration over time.
Rutgers researcher, Dr. Xiang Lu has developed system that uses data-driven modeling and artificial intelligence (AI) techniques to analyze and predict asset degradation. It leverages datasets with features like asset age, usage, environmental conditions, and historical failure types to estimate future degradation and risk levels. Key to this model is an AI framework that dynamically adapts predictions based on evolving asset conditions. This approach aids in predicting failure and also supports decision-making for timely interventions, potentially extending asset life and reducing unplanned downtimes.
Market Applications:
- Railway Systems: Predictive maintenance for tracks and components.
- Highway and Bridge Maintenance: For life-cycle maintenance to prevent failures in critical structures.
- Public Utilities: to predict asset degradation for pipelines and power lines for maintenance and uninterrupted service.
Advantages:
- Allows for proactive rather than reactive maintenance.
- Optimizes repair schedules and reduces the frequency of failures.
- Applicable across different types of infrastructure, from transportation networks to utilities
Intellectual Property & Development Status: Patent Issued: WO 2022/159565 A1. Available for licensing and/or research collaboration. For any business development and other collaborative partnerships contact marketingbd@research.rutgers.edu
