Phase-Specific Batch Monitoring for Accurate Quality Indicators
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In industrial production processes, especially in batch operations, determining quality indicators in real-time is challenging due to the complexity of data from multiple sources and the need for expert intervention, which can lead to delayed or inaccurate assessments, affecting the efficiency and accuracy of quality control.
Innovation Solution
A control module processes batch-run data from technical equipment using parameters obtained by a parameter module that splits time-series data into phase-specific partial series, differentiates relevant from non-relevant data, and stores this information in a parameter matrix to filter and aggregate data effectively, enabling timely and accurate quality indicator determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data from multiple sources is collected and evaluated in combination, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent segments the batch process into multiple phases based on manufacturing operations, and divides time-series data into phase-specific partial series. This segmentation allows the system to evaluate data in smaller, manageable units rather than processing all multi-source data simultaneously, thereby maintaining measurement precision while reducing the apparent complexity of data processing.
Solution Approach 2:
The system performs preliminary actions by pre-defining phases and storing phase-specific parameters in advance. The parameter module pre-processes reference data and stores it in a parameter matrix, so that during actual batch monitoring, the system can directly compare current data against pre-established phase-specific criteria, improving accuracy without requiring complex real-time processing of all data sources.
2Measurement precision
If expert intervention is used to determine quality indicators, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The system implements self-service by automatically determining quality indicators through computer-based processing of batch data against stored phase-specific parameters. The control module autonomously compares current batch data with reference data and generates quality assessments without requiring expert intervention, thereby maintaining precision through structured algorithms while eliminating time delays associated with human expert analysis.
Solution Approach 2:
The patent replaces the mechanical system of expert human analysis with an automated computer-based information processing system. The control module and parameter module use algorithmic comparisons and pre-defined criteria to determine quality indicators, substituting human expertise with automated computational methods that provide both accuracy and speed.
3Measurement precision
If all batch-run data is processed, then measurement precision is improved, but productivity decreases
Solution Approach 1:
The system extracts only the relevant portions of batch-run data by dividing time-series into phase-specific partial series and using phase-specific parameters to identify important data points. The parameter matrix stores only the essential parameters needed for quality assessment, allowing the system to achieve high measurement precision by processing a subset of critical data rather than all available data, thereby improving productivity.
Data Source
Figure 1
Figure 2(A)~3
Figure 4
AI summary
A control module (604) is adapted to control technical equipment (110) by processing batch-run data (504) from the technical equipment (110). The control module operates according to parameters (550) that are obtained by a parameter module (602). The module (602) receives a reference plurality (502) of multi-variate reference time-series with data values from sources that are related to the equipment (110). There are time-series with measurement values and time-series with data that describes particular manufacturing operations during a batch-run time interval. The module (602) splits the time interval into phases by determining transitions between the particular manufacturing operations, and divides the time-series into particular phase-specific partial series. For each phase separately, and for the phase-specific partial series in combination, the module differentiates phase-specific time-series into relevant partial time-series or non-relevant partial time-series and set the parameters (550) accordingly.