IoT Anomaly Detection via Inter-Feature Correlation Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In manufacturing environments, the vast amounts of data generated from IoT devices are underutilized due to the impracticality of manual analysis, leading to a 'rich data but poor information' problem, particularly in predictive maintenance where rare events like equipment failures are difficult to detect accurately.
Innovation Solution
The method involves performing correlation analysis on normal data records to identify clusters of correlated features, building models to estimate feature values, and comparing observed values with estimated values to detect anomalies, thereby improving prediction accuracy and identifying rare events.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis methods are used to analyze manufacturing data, then analysis accuracy can be maintained, but the analysis becomes impractical due to the huge volume of data
Solution Approach 1:
The patent replaces manual mechanical analysis with automated computational systems. The system automatically performs data preprocessing, feature extraction, correlation analysis, and anomaly detection using computer algorithms, eliminating the need for manual analysis while maintaining accuracy and enabling processing of large-scale manufacturing data.
Solution Approach 2:
The patent introduces an intermediate automated analysis system that acts as a mediator between raw manufacturing data and actionable insights. This system includes components for data preprocessing, feature extraction, correlation computation, and anomaly detection that bridge the gap between data collection and decision-making.
2Reliability
If all data records are analyzed to detect rare anomalies, then detection completeness improves, but computation time increases significantly
Solution Approach 1:
The patent extracts and focuses on the most relevant features and patterns from the dataset. By identifying key correlations and anomalies through automated analysis, the system extracts critical information without needing to process every single data record in detail, thus reducing computation time while maintaining detection completeness.
Solution Approach 2:
The patent performs preliminary data preprocessing and feature extraction before anomaly detection. This preliminary action includes cleaning data, extracting relevant features, and computing correlations in advance, which reduces the computational burden during the actual anomaly detection phase and enables faster processing.
3Loss of information
If complex analysis methodologies are used to discover useful information, then information quality improves, but system complexity increases
Solution Approach 1:
The patent segments the complex analysis process into distinct modular components: data preprocessing, feature extraction, correlation analysis, and anomaly detection. Each component handles a specific aspect of the analysis, making the overall system more manageable and easier to implement while maintaining high information quality through systematic processing.
Data Source
AI summary
The present disclosure describes methods, systems, and computer program products for detecting anomalies in an Internet-of-Things (IoT) network. One computer-implemented method includes receiving, by operation of a computer system, a dataset of a plurality of data records, each of the plurality of data records comprising a plurality of features and a target variable, the plurality of features and target variable including information of a manufacturing environment; identifying a set of normal data records from the dataset based on the target variable; identifying inter-feature correlations by performing correlation analysis on the set of normal data records; and detecting anomaly based on the inter-feature correlations for predictive maintenance.