Sensor Data Plot Matching for Machinery Malfunction Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying malfunctions in machinery from sensor data can be challenging, especially for those unfamiliar with diagnostic analysis, as the data requires interpretation of plots which may not be intuitive.
Innovation Solution
A method and system that store reference data sets associated with machine malfunctions, allowing for the display of measurement data plots in matching plot types, enabling direct comparison and identification of malfunctions by correlating sensor data with pre-defined reference data sets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If measurement data is displayed in standard plot formats, then the data can be viewed and stored, but it becomes difficult for users unfamiliar with diagnostic analysis to identify malfunctions
Solution Approach 1:
The system creates visual copies of reference plots that represent known malfunction patterns. These reference plots are stored in a database and retrieved to compare against current measurement data. By copying and displaying established malfunction patterns, the system enables users to identify issues through visual matching without requiring deep diagnostic expertise.
Solution Approach 2:
The system performs preliminary actions by pre-collecting, storing, and organizing reference plots that represent various malfunction conditions before they are needed for diagnosis. These reference plots are prepared in advance with associated metadata about the malfunction type, allowing for rapid comparison and identification when actual measurement data is analyzed.
2Loss of information
If multiple plot types are used to represent different reference data sets, then more information can be conveyed, but the display complexity increases
Solution Approach 1:
The system implements a universal plot display interface that can accommodate multiple plot types (time-series, frequency spectrum, phase orbit, etc.) through a single standardized display mechanism. The plot rendering engine automatically adapts to different data types and reference patterns, allowing the same display infrastructure to handle diverse diagnostic visualizations without requiring separate specialized displays for each plot type.
3Reliability
If reference data sets are stored and compared with measurement data, then malfunction identification improves, but the system complexity increases
Solution Approach 1:
The system implements self-service through automated plot matching and comparison algorithms. When measurement data is received, the system automatically retrieves relevant reference plots from the database, performs visual and numerical comparisons, and identifies matching patterns without requiring manual intervention. The system also automatically generates explanations of why certain patterns match, reducing the need for expert diagnostician input.
Data Source
AI summary
A method for correlating data collected from at least one sensor of machinery with a malfunction of the machinery includes storing, in a memory, one or more reference data sets where each reference data set is associated with a malfunction of the machinery. The method also includes receiving measurement data based on measurement information from the at least one sensor and displaying, with a display device, a first plot representing a reference data set of the one or more reference data sets where the first plot has a plot type associated with the reference data set. The method also includes displaying, with the display device, a second plot representing the measurement data where the second plot is plotted using the first plot based at least in part with the association of the plot type with the reference data set. Furthermore, the method includes displaying, with the display device, an explanation of an appearance of the second plot.