Time-Series Device Diagnosis for Variable Torque and Speed States
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual division of machine operation patterns into uniform processes for analysis is time-consuming and inefficient, especially when torque, speed, or other parameters change, as existing techniques struggle to adapt to these changes effectively.
Innovation Solution
A device diagnosis system that uses time-series data to set threshold values, dividing data into ranges and calculating features and abnormality degrees to automate the process, reducing the time and effort required for analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual division of operation patterns is performed, then analysis accuracy is improved, but time and effort required are increased
Solution Approach 1:
The system performs self-service by automatically dividing operation patterns using threshold values derived from the data itself. The arithmetic operation unit calculates threshold values based on standard deviations of reference data, and the division unit automatically segments inspection data according to these thresholds, eliminating the need for manual operator intervention while maintaining analysis accuracy.
Solution Approach 2:
The patent replaces the mechanical manual division process with an automated computational system. Instead of operators manually analyzing and dividing operation patterns, the system uses arithmetic operations to calculate threshold values and automatically divides data based on these calculated thresholds, substituting human mechanical analysis with automated computational processing.
2Adaptability or versatility
If existing division techniques are used, then cyclic operation patterns can be divided, but they cannot adapt to changes in torque, speed, or other parameters
Solution Approach 1:
The system implements dynamics by making the division thresholds adaptive rather than fixed. The arithmetic operation unit dynamically calculates threshold values based on the standard deviation of reference data, allowing the division criteria to automatically adjust when torque, speed, or other parameters change. This enables the system to adapt to varying operation conditions without manual reconfiguration.
Solution Approach 2:
The patent applies parameter changes by using statistical parameters (mean and standard deviation) to dynamically determine division thresholds. When operation parameters such as torque or speed change, the system recalculates the threshold values based on the new reference data characteristics, automatically adapting the division criteria to match current operating conditions.
Data Source
AI summary
It is not possible to easily divide an analysis process according to a torque or a speed change. A device diagnosis system comprises a threshold value arithmetic operation unit that uses a portion of time-series data measured during an operation of a device as reference data, and sets a plurality of threshold values with respect to the reference data, a data division unit that divides the time-series data that match conditions based on the plurality of threshold values as statuses of respective ranges, a feature arithmetic operation unit that calculates a feature (a basic static quantity) thereof from the time-series data in each status, and an abnormality degree arithmetic operation unit that uses another portion of the time-series data measured during the operation of the device as inspection data, and that analyzes and calculates an abnormality degree which is a degree of an abnormality of the inspection data for each status by using the feature with respect to the inspection data.