Batch-Run Quality Control Using Time-Series Similarity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining similarity between batch runs in production processes face challenges due to varying time intervals and multi-variate data, leading to potential delays in classifying production quality, as they may ignore critical patterns and be overly aggressive in data processing.
Innovation Solution
A computer-implemented method that accesses a reference time-series from a previous batch run and compares it with real-time production data, converting multi-variate time-series to uni-variate time-series using source-specific factors to identify similarity and non-similarity, allowing for real-time control adjustments during the production process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multi-variate time-series data is processed using conventional similarity detection methods, then comprehensive quality assessment is achieved, but processing time increases and critical patterns may be lost due to overly aggressive data processing
Solution Approach 1:
The patent segments multi-variate time-series data into multiple uni-variate time-series, each representing a specific data source or parameter. This segmentation allows independent processing of each uni-variate series, reducing computational complexity while preserving essential characteristics of the original multi-variate data for accurate quality assessment
Solution Approach 2:
The patent extracts essential characteristics from multi-variate time-series data by converting them into uni-variate representations. This extraction process removes redundant information and focuses on critical patterns, enabling faster processing without sacrificing quality assessment accuracy
2Measurement precision
If time-series data from batch runs with varying durations is compared using conventional methods, then similarity detection is performed, but the varying time intervals cause misalignment and reduce detection accuracy
Solution Approach 1:
The patent applies dynamic time warping techniques to align time-series data with varying durations and intervals. This dynamic approach allows flexible matching of corresponding points across different batch runs, accommodating variations in processing speeds and durations while maintaining accurate similarity detection
Solution Approach 2:
The patent transforms time-series data by changing temporal parameters, including resampling and time normalization. These parameter changes enable consistent comparison across batch runs with different durations by standardizing the time intervals while preserving the essential temporal patterns
Data Source
AI summary
A computer-implemented method to control technical equipment that performs a production batch-run of a production process, the technical equipment providing data in a form of time-series from a set of data sources, the data sources being related to the technical equipment, includes: accessing a reference time-series with data from a previously performed batch-run of the production process, the reference time-series being related to a parameter for the technical equipment; and while the technical equipment performs the production batch-run: receiving a production time-series with data, identifying a sub-series of the reference time-series, and comparing the received time-series and the sub-series of the reference time-series, to provide an indication of similarity or non-similarity, in case of similarity, controlling the technical equipment during a continuation of the production batch-run, by using the parameter as control parameter.