Multi-Scale Process Data Mapping for Faster Plant Predictive Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing process of designing large-scale plants requires creating predictive models at each scale, which is time-consuming and costly, slowing down the development process.
Innovation Solution
An information processing device and method that acquires and extracts data sets from different scales to identify corresponding relationships, allowing for the automatic generation of predictive models for plant design and operation, reducing the need for manual tuning and accelerating the design process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If predictive models are created and tuned at each scale manually, then model accuracy is improved, but development time and cost increase significantly
Solution Approach 1:
The system performs preliminary actions by automatically generating predictive models for larger scales based on data from smaller scales before manual tuning is required. The extraction unit pre-identifies corresponding data pairs between different scales, and the generation unit creates initial model predictions that can be directly used or minimally adjusted, eliminating the need for time-consuming manual model creation at each scale.
2Reliability
If predictive models are created and tuned at each scale manually, then model reliability is improved, but development cost increases
Solution Approach 1:
The system applies universality by creating a multi-functional data processing framework that serves multiple scales simultaneously. The extraction unit and generation unit are designed to handle data from any scale and generate predictive models for any target scale, making the system universally applicable across different plant scales without requiring separate manual model development for each scale, thereby reducing overall development cost while maintaining reliability.
3Manufacturing precision
If data from multiple scales is collected and processed, then design accuracy is improved, but data processing complexity increases
Solution Approach 1:
The system applies segmentation by dividing the complex data processing task into distinct functional units: the extraction unit that identifies corresponding data pairs between scales, and the generation unit that creates predictive models. This segmentation allows the system to handle multi-scale data systematically by processing each scale's data through standardized extraction and generation steps, reducing overall processing complexity while maintaining design accuracy.
Data Source
AI summary
An information processing device, comprising: a first acquisition unit 127; a second acquisition unit 128; and an extraction unit 129, wherein the first acquisition unit 127 acquires a first data set including at least a first process data related to a first process and first system data related to a system where the first process is performed, the second acquisition unit 128 acquires a second data set including at least a second process data related to a second process and second system data related to a system where the second process is performed, and the extraction unit 129 extracts at least one of a pair of the first process data and the second process data whose contents are the same as or similar to each other and a pair of the first system data and the second system data whose contents are the same as or similar to each other from the first data set and the second data set, and stores at least one of the pairs extracted in a storage unit in a manner where their correspondence relationship is identifiable.