Shared Material Data Mapping for Predictive Quality Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing production processes face challenges in ensuring product quality due to variations in raw material inputs and the limitations of the Six Sigma method, which does not effectively handle modern data-driven approaches or align different production processes, leading to potential defects and inefficiencies, especially in complex industries like chemical and pharmaceutical manufacturing.
Innovation Solution
A method that involves acquiring and mapping raw material and production data from multiple sources using AI algorithms to identify and validate quality characteristics, allowing for the selection of optimal raw material lots to improve product quality, leveraging data-driven automation and machine learning techniques to enhance production management systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If Six Sigma method with Statistical Process Control is used to monitor and control process parameters, then process quality can be maintained within control limits, but the method cannot effectively handle modern data-driven approaches and align different production processes
Solution Approach 1:
The patent introduces an intermediary layer between traditional SPC and modern data-driven approaches. This intermediary consists of standardized data interfaces and integration protocols that enable Six Sigma control charts to consume data from multiple modern production systems (ERP, MES, LIMS) while maintaining compatibility with contemporary data-driven methodologies. The intermediary translates various data formats into a unified structure that SPC can process, resolving the contradiction between maintaining traditional quality control reliability and adapting to modern systems.
Solution Approach 2:
The patent enhances the universality of Six Sigma by extending its applicability across different production processes and industries. The control chart system is designed to handle diverse data types (continuous, discrete, attribute data) from various sources simultaneously. This multi-functional capability allows the same SPC framework to serve traditional manufacturing, modern data-driven production, and cross-process alignment needs, eliminating the limitation of Six Sigma being confined to single-process applications.
2Measurement precision
If multiple data sources are integrated to improve quality prediction accuracy, then finished goods quality can be predicted based on raw material characteristics, but the complexity of data collection and mapping increases
Solution Approach 1:
The patent segments the complex data integration process into distinct, manageable modules: data collection from multiple sources (ERP, MES, LIMS), data mapping to standardized schemas, data validation, and quality prediction. Each module handles a specific aspect of the data flow, reducing overall system complexity. The segmentation allows independent optimization of each component while maintaining the ability to predict finished goods quality through integrated multi-source data.
Solution Approach 2:
The patent introduces intermediary data mapping layers and standardized interfaces between different data sources and the quality prediction system. These intermediaries translate heterogeneous data formats from ERP, MES, and LIMS into a unified structure that maintains measurement precision without requiring direct complex integration between all sources. The intermediary handles data transformation, validation, and harmonization, reducing the complexity burden on the overall system while preserving prediction accuracy.
3Ease of manufacture
If traditional quality control methods are used, then existing processes can be maintained, but they do not effectively identify root causes or provide corrective actions for modern production variations
Solution Approach 1:
The patent implements a closed-loop feedback system where control charts not only monitor process parameters but also automatically identify root causes and trigger corrective actions. When deviations are detected, the system provides feedback to production systems to adjust parameters and prevent defects. This feedback mechanism bridges traditional ease of manufacture with modern reliability needs by maintaining simple process operation while enabling sophisticated defect identification and correction through automated responses.
Solution Approach 2:
The patent applies preliminary action by using control charts to predict potential quality issues before they manifest as defects. The system analyzes trends and patterns in real-time data to identify root causes early in the production process, enabling preventive corrective actions. This approach maintains the simplicity of traditional quality control while significantly improving reliability by addressing issues before they result in defective products, rather than reacting after defects occur.
Data Source
AI summary
A method for developing or improving a process for producing a product from a material comprising steps of acquiring raw material data from at least two different sources for the production process and its relevant parameters by using a Data Collecting computer; using the acquired raw material data related to the production process to perform a Process Mapping step by using a Process Mapping computer; assigning the acquired raw material data related to the relevant parameters of the production process to its corresponding process parts by performing a Data Mapping step by using a Data Mapping computer; analyzing the therefore mapped process description with a specific software performed on an Analyzing computer thereby identifying and validating one or more existing characteristics related to the quality or performance of the production process; and using the identified and validated characteristics to develop the production process or improve its performance.