Industrial Machine Fault Diagnosis Using Time-Series Segment Replacement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to accurately identify the root cause of abnormal operations in industrial machines, leading to potential downtime and inefficiencies, as they often only detect deviations without pinpointing the critical parameters responsible for the abnormality.
Innovation Solution
A computer-implemented method that processes multi-variate time-series data to identify critical parameters causing abnormal operations by replacing deviating segments with corresponding segments from a reference time-series, calculating error values, and determining the parameter with the lowest error as the critical parameter.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional sensor monitoring is used to detect abnormal operation, then the operator can identify broken components, but the system cannot detect the root cause of abnormal operation or provide recommendations for modification
Solution Approach 1:
The patent segments the time-series data into multiple segments and applies different processing strategies to each segment. By dividing the data analysis into discrete segments, the system can identify which specific segments contain abnormal patterns and focus computational resources on those segments, thereby improving detection accuracy while preserving root cause information.
Solution Approach 2:
The patent transforms the problem from detecting abnormal operation to identifying the specific time segments that cause abnormality. By adding the temporal dimension of segment identification, the system not only detects that abnormal operation occurs but also pinpoints exactly when and what causes it, thus recovering the lost root cause information.
2Quantity of substance
If all parameters are monitored continuously, then comprehensive data is collected, but the critical parameters causing abnormal operation remain undetected due to data complexity
Solution Approach 1:
The patent extracts critical information from the large volume of monitored parameters by identifying and isolating the specific time segments that contain abnormal patterns. Instead of analyzing all parameters continuously, the system extracts only the relevant segments that contribute to abnormal operation, thereby improving critical parameter detection despite the complexity of comprehensive data collection.
Solution Approach 2:
The patent applies different analysis quality levels to different time segments. Rather than uniformly analyzing all data with the same depth, the system applies intensive analysis only to segments identified as containing abnormal patterns, while using lighter analysis for normal segments. This local differentiation of analysis quality improves detection precision without requiring exhaustive processing of all data.
3Measurement precision
If deviating segments are replaced with reference segments to calculate error values, then the critical parameter can be identified, but the process requires multiple calculations and comparisons
Solution Approach 1:
The patent performs preliminary identification of deviating segments before conducting the full error calculation process. By pre-identifying which segments contain abnormalities, the system can focus subsequent calculations only on those specific segments rather than processing the entire time-series data. This preliminary action reduces the overall calculation complexity while maintaining precise critical parameter identification.
Data Source
AI summary
A computer differentiates parameters to find critical parameters that cause abnormal operation of an industrial machine, where the computer receives and obtains multi-variate time-series that represents the operation of the machine or that serve as reference, the computer identifies a time-series that deviate from the reference at least in a segment, and for activity-specific replacement variations, the computer selects deviating segments within the series according to a particular replacement variation, replaces the deviating segments, and determines an error value, the computer then determines the variation for that the error value has its lowest value and provides the determination as an identification of the critical parameter to the operator of the machine.