Chemical Production Control Settings Using Historical Process Identifiers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In industrial chemical production, maintaining consistent and predictable quality of chemical products is challenging due to complex dependencies on production parameters, especially in multi-stage processes, leading to increased costs and complexity in quality control, particularly in continuous or batch processes that generate vast amounts of time series data difficult to integrate effectively.
Innovation Solution
A method using computing units to determine control settings for manufacturing chemical products by leveraging historical data from object identifiers, which include relevant process parameters and operational settings, through a scorer module that selects optimal settings based on desired performance parameters, and appending real-time process data to these identifiers for improved traceability and machine learning applications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If quality control is performed by collecting and analyzing samples regularly, then product quality consistency is improved, but production time and costs increase
Solution Approach 1:
The system performs preliminary actions by continuously collecting and storing process parameter data during production, pre-processing and organizing this data in advance. When quality control is needed, the pre-organized data can be quickly retrieved and analyzed without interrupting the production flow, thus maintaining quality consistency while reducing the time loss associated with traditional sampling and testing
Solution Approach 2:
The patent replaces the traditional mechanical quality control system (physical sampling, manual testing, and analysis) with an information-based system that uses computational methods to analyze process parameter data. This substitution eliminates the need to physically stop production for quality testing, thereby maintaining reliability while significantly reducing time loss
2Reliability
If quality control samples are collected frequently to match production variations, then product quality consistency is improved, but production costs increase
Solution Approach 1:
The system replaces expensive physical quality control operations (sampling, testing, analysis) with a computational information system that continuously monitors and analyzes process parameter data. This information-based approach provides equivalent or superior quality assurance at lower cost by eliminating the need for frequent physical interventions and reducing waste of materials and energy
Solution Approach 2:
The system enables self-service quality control by automatically collecting, storing, and analyzing process data without requiring external quality control operations. The production process itself generates the data needed for quality assessment, and the system autonomously identifies quality issues and triggers appropriate responses, eliminating the need for separate quality control resources and reducing overall production costs
3Loss of information
If vast amounts of time series data are collected from continuous processing, then production monitoring capability is improved, but data integration difficulty increases
Solution Approach 1:
The patent applies segmentation by organizing the vast time series data into discrete, manageable units associated with specific production objects (batches, orders, products). Each object identifier serves as a container for relevant process parameters, quality data, and metadata. This segmentation transforms the overwhelming continuous data stream into structured, queryable units that can be easily integrated and analyzed without requiring complex data handling infrastructure
Solution Approach 2:
The system introduces object identifiers as intermediary elements that mediate between the raw time series data and the production monitoring system. These identifiers act as keys that link process parameters, quality data, and product information together, enabling efficient data integration and retrieval. The intermediary layer simplifies the complexity of data integration by providing a standardized interface for accessing and correlating diverse data sources
Data Source
AI summary
The present teachings relate to a method for improving a production process for manufacturing a chemical product at an industrial plant comprising at least one equipment and one or more computing units, and the product being manufactured by processing at least one input material, which method comprises: providing at least one desired performance parameter related to the chemical product, determining a set of control settings for controlling the production of the chemical product: wherein the control settings are determined using a scorer module configured to select at least one historical object identifier from a memory storage, wherein the historical object identifier has appended to it historical process parameters and/or operational settings that were used for manufacturing past one or more chemical products. The present teachings also relate to a system for improving the production process, a use and a software program.