Smart Factory Data Mapping for Continuous Process Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional factory data processing systems, such as those in the steel industry, are unable to process large amounts of data in real time and analyze correlations between data generated in continuous processes due to high data velocity and noise in factory environments.
Innovation Solution
A smart factory platform with a distributed parallel processing system that maps and sorts data using process IDs, and a big data analysis system for storing and analyzing data, enabling real-time processing and correlation analysis across multiple processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a conventional factory data processing system processes data from a single process, then the processing system is simple and easy to implement, but it cannot process large amounts of data generated in continuous processes in real time and cannot analyze correlations between data from different processes
Solution Approach 1:
The system divides the continuous process into multiple discrete process segments (first process, second process, etc.), each with its own data collection and processing pipeline. This segmentation allows the system to handle large volumes of data from different processes simultaneously while maintaining manageable complexity through modular architecture.
Solution Approach 2:
The patent introduces an intermediary data processing layer that collects data from multiple processes, performs correlation analysis, and generates integrated results. This intermediary layer acts as a mediator between individual process data sources and the final analysis output, enabling real-time processing of multi-process data without overwhelming the system.
2Quantity of substance
If data is collected continuously from multiple processes, then the amount of data available for analysis increases, but the data velocity increases and measurement errors occur more frequently due to noise and environmental factors
Solution Approach 1:
The system implements feedback mechanisms that continuously monitor data quality and system performance. By analyzing measurement errors and noise patterns in real-time, the system adjusts processing parameters and filters to maintain data accuracy despite high data velocity and environmental interference.
Solution Approach 2:
The patent dynamically changes processing parameters such as sampling rates, filtering thresholds, and analysis windows based on current data conditions. When noise levels increase or data velocity changes, the system adjusts these parameters to optimize both the quantity and precision of processed data.
3Loss of time
If data processing is performed in real time, then the responsiveness of the system improves, but the computational load increases and requires more processing power
Solution Approach 1:
The system performs preliminary data processing, filtering, and preprocessing operations as data is collected from each process. By preparing data in advance before comprehensive analysis is required, the system reduces the computational load during real-time decision-making while maintaining fast response times.
Solution Approach 2:
The patent implements a multi-level processing approach where critical data receives full real-time processing while less critical data undergoes partial processing or batch analysis. This selective processing strategy maintains system responsiveness for important operations while reducing overall computational energy consumption.
Data Source
AI summary
Disclosed is a smart factory platform for processing data obtained in a continuous process including a first process and a second process following the first process. The smart factory platform includes a distributed parallel processing system including at least one processing unit that generates mapping data by mapping a process identification (ID) to collection data collected from the continuous process and sorts the mapping data to generate sorting data, the process ID defining a process where the collection data occurs and the sorting data being generated for association processing between pieces of collection data collected from different processes; and a big data analysis system storing the sorting data with respect to the process ID.