Asset-Specific Leading Indicators for Event Prediction Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manufacturer-defined leading indicators for physical assets are generic and fail to account for specific environmental and operational conditions of individual assets, leading to inaccurate predictions of maintenance needs.
Innovation Solution
An automated machine learning system that identifies significant leading indicators specific to each asset by analyzing sensor data and historical event data, including operating conditions and attributes, to predict future events with high accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manufacturer-defined generic leading indicators are used, then the system is simple to implement and operate, but the prediction accuracy for specific assets deteriorates
Solution Approach 1:
The patent segments the generic leading indicators into asset-specific components by using machine learning to identify which indicators are most relevant to each individual asset's operating conditions, environment, and historical performance. This divides the general indicator set into customized subsets for each asset.
Solution Approach 2:
The system dynamically adjusts the parameters of leading indicators based on asset-specific data. The machine learning model changes the weight, threshold, and relevance of each indicator parameter according to the specific asset's characteristics, transforming static manufacturer-defined indicators into dynamic asset-specific indicators.
2Measurement precision
If asset-specific leading indicators are identified through data analysis, then the prediction accuracy improves, but the system complexity increases
Solution Approach 1:
The system performs self-service by automatically identifying and selecting asset-specific leading indicators through machine learning algorithms. The system autonomously analyzes asset data, determines relevant indicators, and updates predictions without requiring manual configuration or expert intervention, thereby managing complexity internally while maintaining simplicity for the user.
Solution Approach 2:
The machine learning model performs preliminary analysis of asset data to pre-identify relevant leading indicators before actual prediction is needed. This preliminary action prepares the system in advance, so when prediction is required, the complex analysis has already been completed and the system can operate efficiently with pre-determined asset-specific indicators.
3Ease of manufacture
If generic leading indicators are used, then the implementation cost is low, but the maintenance effectiveness deteriorates
Solution Approach 1:
The system transitions from static generic indicators to dynamic asset-specific indicators. The machine learning model continuously adapts the leading indicators based on changing asset conditions, operating environments, and historical performance data, making the maintenance system dynamically responsive to each asset's actual state rather than relying on fixed manufacturer recommendations.
Solution Approach 2:
The system implements feedback loops where prediction outcomes and actual asset performance are continuously monitored. This feedback informs the machine learning model to refine and adjust the asset-specific leading indicators over time, improving maintenance effectiveness while maintaining cost-efficiency through automated learning rather than manual optimization.
Data Source
AI summary
Provided is a system and method for predicting leading indicators for predicting occurrence of an event at a target asset. Rather than rely on traditional manufacturer-defined leading indicators for an asset, the examples herein predict leading indicators for a target asset based on actual operating conditions at the target asset. Accordingly, unanticipated operating conditions can be considered. In one example, the method may include receiving operating data of a target resource, the operating data being associated with previous occurrences of an event at the target resource, predicting one or more leading indicators of the event at the target resource based on the received operating data, each leading indicator comprising a variable and a threshold value for the variable, and outputting information about the one or more predicted leading indicators of the target resource for display via a user interface.