International business machines corporation (20240103959). INTELLIGENT DYNAMIC CONDITION-BASED INFRASTRUCTURE MAINTENANCE SCHEDULING simplified abstract

INTELLIGENT DYNAMIC CONDITION-BASED INFRASTRUCTURE MAINTENANCE SCHEDULING

Organization Name

international business machines corporation

Inventor(s)

Pavankumar Murali of Ardsley NY (US)

Dzung Tien Phan of PLEASANTVILLE NY (US)

Nianjun Zhou of Chappaqua NY (US)

Lam Minh Nguyen of Ossining NY (US)

INTELLIGENT DYNAMIC CONDITION-BASED INFRASTRUCTURE MAINTENANCE SCHEDULING - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240103959 titled 'INTELLIGENT DYNAMIC CONDITION-BASED INFRASTRUCTURE MAINTENANCE SCHEDULING

Simplified Explanation

The abstract describes a method for generating a parametric model that expresses condition states for assets, predicting stochastic degradation of the assets, and creating a maintenance schedule based on these predictions and maintenance costs.

• Parametric model generation for assets condition states and transition probabilities
• Stochastic degradation predictions based on condition states and transition probabilities
• Maintenance schedule generation considering degradation predictions and maintenance costs

Potential Applications

This technology can be applied in various industries such as manufacturing, transportation, and infrastructure management to optimize maintenance schedules and reduce downtime.

Problems Solved

1. Predictive maintenance: Helps in predicting asset degradation and scheduling maintenance proactively. 2. Cost optimization: Enables efficient allocation of resources by considering maintenance costs and asset conditions.

Benefits

1. Increased asset reliability: By predicting degradation, maintenance can be performed before assets fail. 2. Cost savings: Optimized maintenance schedules can reduce overall maintenance costs. 3. Improved operational efficiency: Minimizing downtime by scheduling maintenance at optimal times.

Potential Commercial Applications

Optimized Maintenance Schedule Generation for Asset Management

Possible Prior Art

There are existing predictive maintenance systems that use data analytics and machine learning to predict asset failures and schedule maintenance. However, the specific method described in this patent application may have unique aspects that differentiate it from existing solutions.

How does this technology handle real-time data for asset condition monitoring?

The abstract does not mention how real-time data is incorporated into the parametric model and degradation predictions.

Are there any limitations to the scalability of this method for a large number of assets?

The abstract does not address how the method scales when dealing with a large number of assets and the computational resources required for generating maintenance schedules.

Original Abstract Submitted

in example aspects of this disclosure, a method includes generating, by one or more computing devices, a parametric model that expresses condition states for each of a plurality of assets, and the probability of the assets transitioning between the condition states; generating, by the one or more computing devices, stochastic degradation predictions of a group of the assets, based on the condition states and the probability of transitioning between the condition states for at least some of the assets; and generating, by the one or more computing devices, a maintenance schedule based on: the stochastic degradation predictions of the group of the assets, costs of corrective maintenance for assets in a failed state, and costs of scheduled maintenance for the assets.