Future Reliability Prediction Using Normalized Maintenance Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods struggle to accurately model and predict the future reliability of repairable systems based on maintenance spending, as excessive maintenance may not necessarily improve reliability and unplanned failures can be costly.
Innovation Solution
A system and method for modeling future reliability using operational and performance data, involving an input interface to receive maintenance expense, principle, and asset reliability data, applying comparative analysis models to categorize maintenance spending and estimate future reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If maintenance spending is increased, then system reliability may improve, but excessive maintenance spending may not necessarily improve reliability and can be wasteful
Solution Approach 1:
The patent transforms the continuous maintenance expense data into discrete category values through normalization and categorization. By changing the parameter representation from raw monetary values to standardized categories, the system enables more accurate modeling of the relationship between maintenance spending and reliability, allowing optimization of maintenance budgets to achieve desired reliability levels without excessive spending.
Solution Approach 2:
The patent replaces traditional mechanical judgment methods with data-driven computational modeling. Instead of relying on expert intuition or simple rules to determine appropriate maintenance spending, the system uses comparative analysis models that process operational and performance data to predict future reliability, substituting mechanical decision-making processes with automated analytical systems.
2Measurement precision
If traditional maintenance spending analysis is used, then simplicity is maintained, but accuracy in predicting future reliability is insufficient
Solution Approach 1:
The patent introduces category values as an intermediary layer between raw maintenance expense data and reliability prediction models. This intermediary categorization system simplifies the complexity by transforming continuous, varied expense data into standardized discrete categories that are easier to model and analyze, thereby improving prediction accuracy without requiring overly complex modeling approaches.
Solution Approach 2:
The patent segments maintenance expense data into distinct categories based on normalized values. By dividing the continuous range of maintenance spending into discrete segments or categories, the system makes the data more manageable for analysis and modeling, improving prediction accuracy while controlling complexity through structured segmentation.
3Reliability
If maintenance spending is not categorized, then data processing is simpler, but the ability to link maintenance expenses to asset reliability is reduced
Solution Approach 1:
The patent applies parameter transformation by converting maintenance expense values into normalized category values. This change in parameter representation enables meaningful comparison and linkage between maintenance spending patterns and asset reliability outcomes, as the standardized categories facilitate consistent analysis across different assets and time periods.
Solution Approach 2:
The patent creates a simplified categorical representation (copy) of the original maintenance expense data. Instead of directly using complex raw expense figures, the system generates category value copies that retain the essential information needed for reliability analysis while being simpler to process and analyze, thereby linking maintenance expenses to asset reliability more effectively.
Data Source
AI summary
Systems, methods, and apparatuses for improving future reliability prediction of a measurable system by receiving operational and performance data, such as maintenance expense data, first principle data, and asset reliability data via an input interface associated with the measurable system. A plurality of category values may be generated that categorizes the maintenance expense data by a designated interval using a maintenance standard that is generated from one or more comparative analysis models associated with the measurable system. The estimated future reliability of the measurable system is determined based on the asset reliability data and the plurality of category values and the results of the future reliability are displayed on an output interface.