Manufacturing Data Transformation for Process Parameter Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manufacturing processes, particularly in glass manufacturing, face challenges in effectively optimizing process parameters due to the complexity of managing large volumes of real-time data from various sources, leading to inefficiencies in data processing and analysis, which results in defects, energy wastage, and material losses.
Innovation Solution
A computer-implemented method and system that transforms time-sequenced manufacturing data into a positionally-dimensioned data structure using a data matrix transformation, identifies and removes outliers, and imputes missing data, enabling the use of machine-learning algorithms to optimize process parameters and improve manufacturing efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If real-time data from multiple data sources is collected and processed, then manufacturing process optimization capability is improved, but data processing complexity and computational burden increase
Solution Approach 1:
The patent segments the manufacturing process into multiple discrete stages (e.g., melting, forming, annealing) and collects data from separate data sources for each stage. This segmentation allows the system to process and analyze data in manageable units rather than as one overwhelming dataset, reducing computational complexity while maintaining comprehensive optimization capability
Solution Approach 2:
The patent transforms time-sequenced data into a positionally-dimensioned data structure by mapping temporal data to spatial positions along the manufacturing line. This dimensional transformation organizes the data in a more manageable format that facilitates easier analysis and reduces the computational burden of processing large volumes of real-time data
2Manufacturing precision
If comprehensive manufacturing data is analyzed, then product quality is improved, but processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary data processing steps including outlier detection, removal, and imputation of missing data before the main analysis. By preparing and cleaning the data in advance, the system reduces the computational burden during real-time analysis, thereby maintaining high product quality standards while reducing overall processing time
Solution Approach 2:
The patent extracts and removes outlier data points from the manufacturing data before analysis. By eliminating these anomalous values that would require extensive processing and validation, the system achieves both high product quality through accurate data analysis and reduced processing time by removing computationally intensive outlier handling
3Measurement precision
If time-sequenced data is transformed to positionally-dimensioned data structure, then data analysis accuracy is improved, but processing complexity increases
Solution Approach 1:
The patent transforms time-sequenced data into a positionally-dimensioned data structure by mapping temporal measurements to spatial positions along the manufacturing line. This dimensional transformation improves data analysis accuracy by preserving the spatial relationships between measurements while organizing data in a more analyzable format, and the transformation algorithm is designed to be computationally efficient
4Productivity
If machine-learning algorithms are applied to optimize process parameters, then manufacturing efficiency is improved, but computational requirements and system complexity increase
Solution Approach 1:
The patent introduces an intermediary data processing layer that prepares and structures manufacturing data before feeding it to machine-learning algorithms. This intermediary layer includes steps for data cleaning, outlier removal, and transformation to positionally-dimensioned structures, which simplifies the input requirements for machine-learning algorithms and reduces overall system complexity while maintaining manufacturing efficiency improvements
Data Source
AI summary
Provided are a system, method, and computer program product for optimizing a manufacturing process. The method includes receiving manufacturing data associated with a manufacturing process for manufacturing a product. The manufacturing data may include data from a plurality of data sources associated with a plurality of stages of the manufacturing process, and the manufacturing data may include values for a plurality of parameters including at least one process parameter value and at least one quality parameter value. The method includes generating a time-sequenced data structure including the manufacturing data and transforming the time-sequenced data structure to a positionally-dimensioned data structure based on timing data associated with the plurality of stages. The method includes determining a new value for the at least one process parameter value based on the positionally-dimensioned data structure and at least one algorithm and optimizing the manufacturing process based on the new value.