Asset Fault Analysis Tool for Outlier Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for analyzing asset data tend to focus on individual assets rather than identifying asset attributes contributing to fault occurrences across multiple assets, making it challenging to analyze and present fault data effectively across a population of assets.
Innovation Solution
An asset data platform is configured to receive and process data from a population of assets, providing an interactive data analysis tool that allows users to analyze fault occurrences across different combinations of asset attributes and their values, identifying outliers and presenting data through various visualization views.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current systems analyze asset data on an asset-to-asset basis, then individual asset monitoring is achieved, but the ability to identify particular asset attributes leading to fault occurrences across a plurality of assets is lost
Solution Approach 1:
The system segments fault data from multiple assets by categorizing according to asset attributes (e.g., asset type, age, operating conditions). This allows precise analysis of fault patterns while maintaining the ability to compare across different asset segments, resolving the contradiction between individual asset precision and cross-asset versatility.
Solution Approach 2:
The invention adds a new dimension to fault analysis by introducing attribute-based grouping and comparison. Instead of only analyzing assets individually or as a single aggregate, the system creates multi-dimensional views of fault data organized by asset attributes, enabling simultaneous individual asset precision and cross-asset pattern recognition.
2Loss of information
If comprehensive asset attribute data is collected across a population of assets, then fault pattern analysis capability is improved, but data processing and presentation complexity increases
Solution Approach 1:
The system divides comprehensive asset attribute data into organized segments based on asset attributes. This segmentation structure allows complete fault data to be maintained while simplifying processing through systematic categorization, reducing the complexity burden of handling large volumes of diverse data.
Solution Approach 2:
The patent introduces an intermediary data processing layer that sits between raw asset data collection and final presentation. This intermediary layer performs automated attribute-based grouping, filtering, and organization, mediating between comprehensive data collection and manageable processing complexity.
3Ease of operation
If fault data is analyzed without considering asset attribute combinations, then analysis simplicity is maintained, but the ability to identify specific attribute combinations impacting fault rates is reduced
Solution Approach 1:
The system implements dynamic analysis capabilities that can adjust the level of detail based on user needs. Users can start with simple attribute-based groupings and progressively drill down into specific attribute combinations, maintaining ease of operation while enabling precise fault cause identification when required.
Solution Approach 2:
The patent performs preliminary organization of fault data by asset attributes before detailed analysis. This pre-grouping action simplifies subsequent analysis operations while preserving the ability to identify specific attribute combinations, as the data is already structured for both simple and detailed inquiry.
Data Source
AI summary
Disclosed herein are systems, devices, and methods related to analyzing faults across a population of assets. In particular, examples involve receiving a selection of variables each corresponding to an asset attribute type, accessing data associated with the selected variables, determining the number of fault occurrences across the population of assets for each combination of values of the selected variables, and facilitating the identification of outlier combination(s) that correspond to an abnormally large number of fault occurrences relative to other combination(s).