Batch-Run Quality Indicator Using Reference Time-Series Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In industrial production processes, determining the quality of batch runs is challenging due to varying time intervals and multi-variate data sources, which can lead to delayed classification and potential failures, as existing methods may ignore critical patterns or be too aggressive in data processing.
Innovation Solution
A two-phase approach is implemented, where quality categories are identified for subsequent phases of the production process by converting multi-variate time-series to uni-variate time-series, allowing for phase-specific analysis and communication of transition conditions to operators, enabling real-time adjustments and predictive outcomes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multi-variate time-series data is used for quality assessment, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent segments the complex multi-variate time-series data into multiple uni-variate time-series, each representing a specific parameter or feature. This segmentation simplifies the overall analysis by breaking down the complex data structure into manageable components that can be processed independently and then integrated for comprehensive quality assessment.
Solution Approach 2:
The patent introduces an intermediary processing layer that converts multi-variate time-series data into uni-variate representations. This intermediary step acts as a bridge between the complex raw data and the quality assessment system, transforming the data into a form that is easier to process while retaining essential quality indicators.
2Device complexity
If data processing is performed aggressively to simplify analysis, then device complexity is reduced, but loss of information increases
Solution Approach 1:
The patent applies local quality by processing different segments of the time-series data with different levels of detail. Critical patterns and features are preserved with high fidelity, while less important data is processed more simply. This allows the system to maintain information quality where it matters most while reducing overall processing complexity.
3Measurement precision
If quality categories are determined only after batch completion, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The patent performs preliminary quality assessment during the batch production process by continuously monitoring uni-variate time-series data and comparing it against reference patterns. This preliminary action allows for early detection of quality issues and enables corrective measures to be taken before the batch is completed, significantly reducing the time loss associated with quality determination.
Solution Approach 2:
The patent implements a feedback mechanism where quality assessments are continuously updated based on incoming data and reference comparisons. This feedback loop allows the system to provide real-time quality indicators during production, enabling dynamic adjustments and early warning of potential quality failures without waiting for batch completion.
4Manufacturing precision
If reference time-series are used for comparison, then manufacturing precision is improved, but adaptability decreases
Solution Approach 1:
The patent employs dynamic reference selection and adaptive comparison methods. Instead of using fixed reference time-series, the system dynamically selects appropriate references based on current production conditions and adjusts the comparison criteria accordingly. This allows the system to maintain manufacturing precision while adapting to varying production scenarios, equipment states, and material conditions.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
To control technical equipment (110) that performs a production batch-run (220) of a production process (200), a controller module performs a method (700) in that it accesses a reference time-series (*R*(1), *R*(2)) with data from a previously performed batch-run. The reference time-series (*R*, *R*(1), *R*(2)) is related to a parameter (660-1, 660-2) for the technical equipment (110). While the technical equipment performs the production batch-run (220), the module receives (720) a production time-series (*P*) with data, identifies (730) a sub-series (*R*(1)A, *R*(2)A) of the reference time-series (*R*, *R*(1), *R*(2)), and compares (740) the received time-series (*P*) and the sub-series (*R*(1)A, *R*(2)A) of the reference time-series. This results in an indication of similarity or non-similarity. In case of similarity, the module controls (750) the technical equipment during the continuation of the production batch-run, by using the parameter (660-1) as control parameter and/or by indicating a parameter from the reference time-series as a recommendation to the operator.