Synchronized Reference Vibration Data for Machine State Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vibration prediction methods for production machines lack accuracy due to inadequate methods for creating reference vibration patterns, leading to unreliable failure predictions.
Innovation Solution
A diagnostic method and device that acquire and process time-series data from physical quantity sensors to generate reference data by synchronizing and calculating representative values from measurement data during a baseline operation period, allowing for accurate comparison with data from a subsequent operation period to diagnose the state of an object.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a simple reference vibration pattern is created without synchronization processing, then the device complexity is reduced, but the measurement precision and reliability of failure prediction decrease
Solution Approach 1:
The patent applies preliminary action by performing synchronization processing on vibration data during the reference period before creating the reference vibration pattern. This advance processing ensures that the reference pattern accurately reflects the normal vibration characteristics, thereby improving measurement precision without adding complexity during the actual failure detection phase.
Solution Approach 2:
The patent creates a copied and synchronized version of the vibration data from the reference period to generate the reference vibration pattern. By copying and synchronizing multiple periods of vibration data, the system produces a more accurate reference pattern that can be reliably compared against future vibration data for failure detection.
2Reliability
If synchronization processing is performed on multiple periods of vibration data, then the reliability of state diagnosis is improved, but the loss of time for data processing increases
Solution Approach 1:
The patent performs synchronization processing during the reference period in advance, before actual failure detection begins. This preliminary action allows the system to invest time in creating an accurate reference vibration pattern once, which then can be reused for multiple failure detection operations, reducing the time loss in ongoing monitoring.
Solution Approach 2:
The patent utilizes periodic vibration data from multiple complete operation cycles to build the reference pattern. By collecting data over several periodic cycles and synchronizing them, the system achieves high reliability while the processing is confined to the reference period, after which the reference pattern can be used efficiently for extended periods.
3Productivity
If reference data is generated from a single period of vibration data, then the productivity of data processing is improved, but the manufacturing precision of the reference vibration pattern decreases
Solution Approach 1:
The patent performs synchronization processing during the reference period in advance, before actual failure detection begins. This preliminary action allows the system to invest time in creating an accurate reference vibration pattern once, which then can be reused for multiple failure detection operations, reducing the time loss in ongoing monitoring.
Solution Approach 2:
The patent creates a copied and synchronized version of the vibration data from the reference period to generate the reference vibration pattern. By copying and synchronizing multiple periods of vibration data, the system produces a more accurate reference pattern that can be reliably compared against future vibration data for failure detection.
Data Source
AI summary
A diagnostic method includes: acquiring first measurement data based on a physical quantity generated by an object repeating a predetermined operation pattern in a first period; a reference data generation step of generating reference data based on the first measurement data; acquiring second measurement data based on a physical quantity generated by the object repeating the predetermined operation pattern in a second period; and a diagnosis step of diagnosing a state of the object based on the reference data and the second measurement data, in which the reference data generation step includes extracting, from the first measurement data, a plurality of pieces of first period unit data corresponding to at least a part of the predetermined operation pattern, and generating the reference data by calculating a representative value of the plurality of pieces of first period unit data subjected to synchronization processing.


