Time-Series Display Layout for Machine Failure Pattern Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting machine apparatus failures are inefficient due to the high volume of time-series data collected at high sampling rates, leading to increased workload and decreased accuracy in data analysis, as existing data display methods often scatter failure-related data irregularly along a long time axis, deforming waveforms and making detailed comparison difficult.
Innovation Solution
An information processing method and apparatus that extracts and displays partial time-series data related to machine apparatus states by aligning them closer together on a horizontal axis, reducing the distance between data points to facilitate easier comparison and analysis, thereby enhancing data extraction and waveform inspection for failure prediction modeling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Duration of action of stationary object
If time-series data is displayed along a long time axis to show the temporal distribution of data points, then the temporal sequence is preserved, but the waveform is deformed and detailed comparison becomes difficult
Solution Approach 1:
The patent transitions from a one-dimensional time-axis display to a two-dimensional display space where the horizontal axis represents time and the vertical axis represents the magnitude of physical quantities. This dimensional change allows simultaneous preservation of temporal sequence and waveform shape, enabling both long-time-span visualization and detailed comparison without distortion.
2Measurement precision
If high sampling rate is used to collect time-series data, then data resolution is improved, but data volume increases leading to increased workload in analysis
Solution Approach 1:
The patent extracts and highlights only the portions of time-series data that are relevant to failure prediction, separating them from the bulk of normal operation data. This extraction approach maintains high resolution for critical data points while reducing the overall data volume that requires detailed analysis, thereby lowering workload without sacrificing measurement precision.
3Measurement precision
If detailed data analysis is performed to ensure accurate failure prediction, then prediction accuracy is improved, but analysis time and workload increase
Solution Approach 1:
The patent performs preliminary organization and visualization of time-series data before detailed analysis, arranging data points in a manner that facilitates quick identification of failure patterns. This preliminary action reduces the subsequent analysis time and workload by pre-processing the data into a more analyzable format, while maintaining the capability for accurate failure prediction through preserved data integrity.
Data Source
AI summary
A display apparatus for displaying physical quantity related to a state of a machine apparatus includes a processing portion. The processing portion is configured to display an image such that a distance between one piece of a plurality of extracted pieces of partial time-series data extracted from a time-series data of the physical quantity and another piece of the plurality of extracted pieces of partial time-series data is smaller than a distance between the one piece of the plurality of pieces of partial time-series data before extracted and the other piece of the plurality of pieces of partial time-series data before extracted.