Industrial Automation Diagnostics Using Feature Selection and Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
As industrial automation processes become more complex, monitoring and diagnostics face challenges in efficiently analyzing large amounts of process data in real-time, leading to increased complexity and reduced analytical efficiency.
Innovation Solution
A control system that includes feature extraction and selection blocks to transform and reduce process data into a more manageable form, allowing for the determination of an expected operational state and facilitating diagnostics by selecting a subset of features indicative of the process's operation, and adjusting parameters for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If process data is analyzed in real-time for complex industrial automation processes, then monitoring and diagnostics capability is improved, but data processing complexity and computational load increase
Solution Approach 1:
The patent segments the complex process data into multiple feature sets, where each feature set contains a subset of features extracted from the process data. This segmentation allows the system to analyze different aspects of process operation separately, reducing the computational complexity of real-time analysis while maintaining comprehensive monitoring and diagnostics capability.
Solution Approach 2:
The patent extracts relevant features from the raw process data and organizes them into feature sets. By taking out only the most significant features needed for monitoring and diagnostics, the system reduces the volume of data that requires real-time processing, thereby lowering computational load while preserving the essential information needed for reliable process monitoring.
2Measurement precision
If all process data is processed for operational state determination, then analysis accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
The patent applies partial action by processing multiple feature sets in parallel, where each feature set contains a subset of features. Instead of processing all features sequentially, the system processes selected subsets simultaneously, reducing overall processing time while maintaining accurate operational state determination through the combined results of multiple partial analyses.
Solution Approach 2:
The patent transforms the analysis by organizing features into multiple sets and processing them in parallel dimensions. This dimensional approach allows the system to achieve comprehensive analysis accuracy without the sequential processing time penalty, as multiple feature sets are evaluated concurrently rather than one after another.
3Productivity
If feature extraction and selection is performed to reduce data complexity, then processing efficiency is improved, but information loss may occur
Solution Approach 1:
The patent segments the complete feature set into multiple overlapping or complementary feature sets. By distributing the information across multiple segments and processing them in parallel, the system maintains comprehensive information coverage while improving processing efficiency. Each feature set captures different aspects of the process, and their combined analysis preserves the full information content.
Solution Approach 2:
The patent changes the parameter organization by transforming process data into multiple feature sets with different compositions. This parameter reorganization allows the system to process data more efficiently through parallel computation while preserving the essential information content, as each feature set is designed to capture relevant process characteristics without redundant processing.
Data Source
AI summary
System and method for improving operation of an industrial automation system, which includes a control system that controls operation of an industrial automation process. The control system includes a feature extraction block that determines extracted features by transforming process data determined during operation of an industrial automation process based at least in part on feature extraction parameters; a feature selection block that determines selected features by selecting a subset of the extracted features based at least in part on feature selection parameters, in which the selected features are expected to be representative of the operation of the industrial automation process; and a clustering block that determines a first expected operational state of the industrial automation system by mapping the selected features into a feature space based at least in part on feature selection parameters.