Rotating Machine Defect Severity Diagnosis Using Weighted Vibration Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing rotating machine diagnosis systems fail to quantitatively evaluate the state of facilities, lacking a comprehensive method to integrate various diagnosis techniques for accurate defect assessment.
Innovation Solution
A method and system that determine a defect level in rotating machines by combining feature vectors, frequency analysis, total vibration values, and applying weights based on state history data and operation alarms, utilizing machine learning to quantify defect severity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple diagnosis techniques are used independently, then comprehensive defect detection capability is improved, but integration and quantitative evaluation capability deteriorate
Solution Approach 1:
The patent merges multiple independent diagnosis techniques (vibration analysis, operational data monitoring, historical defect data) into a unified diagnosis system. The system integrates these diverse data sources and techniques through a common processing framework that combines their results into a comprehensive defect assessment, resolving the contradiction by achieving both comprehensive detection and systematic integration.
Solution Approach 2:
The diagnosis system is designed with multi-functionality to handle various diagnosis techniques and data types uniformly. It processes vibration signals, operational parameters, and historical defect information through a universal processing framework that applies weighted evaluation across different data sources, enabling the system to perform multiple diagnosis functions while maintaining integrated quantitative evaluation.
2Ease of operation
If qualitative evaluation is used, then diagnosis simplicity is improved, but quantitative assessment capability deteriorates
Solution Approach 1:
The system transforms qualitative diagnosis results into quantitative assessments by introducing weighted evaluation parameters. Each diagnosis technique and data source is assigned a weight that reflects its importance and reliability. The system calculates a comprehensive defect severity score by combining individual assessment results with their respective weights, thereby achieving precise quantitative evaluation while maintaining operational simplicity through automated calculation.
3Measurement precision
If comprehensive data analysis is performed, then defect assessment accuracy is improved, but processing complexity deteriorates
Solution Approach 1:
The patent segments the comprehensive data analysis process into distinct modular components: vibration signal processing, operational data analysis, historical defect data retrieval, and weighted integration. Each module handles a specific aspect of data analysis independently, then their results are combined through a systematic weighting mechanism. This segmentation reduces processing complexity by organizing comprehensive analysis into manageable, standardized steps.
Solution Approach 2:
The system incorporates feedback mechanisms where the results from each diagnosis technique inform the overall defect assessment. The weighted evaluation framework provides feedback by adjusting the contribution of each data source based on its reliability and relevance. This feedback loop enables accurate defect assessment while managing processing complexity through iterative refinement of the evaluation weights based on accumulated diagnostic experience.
Data Source
AI summary
A method for diagnosing a defect in a rotating machine, according to the present disclosure, may comprise the steps of: determining a defect level on the basis of data obtained by diagnosing the state of the rotating machine, the data, obtained by diagnosing the state of the rotating machine, including at least one from among a feature vector related to a vibration signal of the rotating machine, a frequency linked to the defect in the rotating machine and the total vibration value of the rotating machine; applying a weight to the defect level on the basis of information related to a defect in state history data of the rotating machine and/or whether an alarm related to operating information about the rotating machine has occurred; and determining the defect severity of the rotating machine on the basis of the defect level to which the weight is applied.