Operating Plan Data Classification Using PCA and Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Process plants face challenges in efficiently generating and validating current operating and scheduling plans due to the variability in internal and external conditions, making it difficult to utilize historical operating plans effectively.
Innovation Solution
A computer-implemented method and system that classifies operating plan data using Principal Component Analysis (PCA) to reduce dimensionality and hierarchical clustering techniques to organize plans into clusters representing distinct operating and market conditions, facilitating the selection of relevant plans for current operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If historical operating plans are used to generate current plans, then the quality and efficiency of plan generation improves, but the complexity of classifying and matching historical cases increases
Solution Approach 1:
The patent transforms the classification problem by changing parameters from raw process variables to principal components through dimensionality reduction. This allows historical plans to be classified and matched efficiently without overwhelming complexity, resolving the contradiction between utilizing historical data for improved productivity and managing classification system complexity.
Solution Approach 2:
The patent extracts the essential variability information from numerous process variables by generating principal components that capture the dominant modes of variation. This extraction approach enables effective classification of historical operating plans without requiring complex processing of all original variables, thus improving plan generation efficiency while controlling system complexity.
2Measurement precision
If numerous process variables are used to represent operating plan data, then the classification accuracy improves, but the computational complexity and data processing time increase
Solution Approach 1:
The patent changes the parameter representation from numerous raw process variables to a reduced set of principal components that capture the essential variability. This transformation maintains classification accuracy by preserving the dominant modes of variation while dramatically reducing data processing time and computational complexity.
Solution Approach 2:
The patent extracts the most significant variability information from the full set of process variables through principal component analysis. By taking out only the essential variation patterns, the system achieves accurate classification without processing all original variables, thus reducing data processing time while maintaining measurement precision.
Data Source
AI summary
A computer system provides improved classification of operating and scheduling plan data of a process plant. The system finds patterns in cases of the plan data and, based on the patterns, organizes the cases into a hierarchical structure of clusters representing distinct conditions. The system receives a dataset of cases of operating plan data represented by process variables. The system reduces a number of process variables representing operating plan data in the dataset by generating principal component(s) from values of the process variables for each case. The principal component(s) are latent variables generated to capture variation in conditions across the cases. For each case, the system determines a value for each generated principal component in the dataset. Using automated clustering or machine learning techniques, the system iteratively clusters the cases into a hierarchical structure based on the respective determined value of each generated principal component. The hierarchical structure provides temporal and spatial classification indicating the distinct operating conditions across cases.