Plant Trip Prevention Through Time-Frequency Deviation Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial plants face costly disruptions due to process perturbations and electrical trips, which can lead to equipment damage, injuries, and business losses, necessitating timely detection and mitigation of these events.
Innovation Solution
A method and system that analyze time-series data from both process and electrical domains using wavelet transformations to identify dominant frequency changes, detect deviations from predefined conditions, and generate actions to prevent or mitigate interruptions, such as alerts or recommendations for operators to take corrective actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional monitoring methods are used to detect process perturbations and electrical trips, then the system structure remains simple, but the detection precision and early warning capability are insufficient
Solution Approach 1:
The patent combines process domain data and electrical domain data into a unified analysis framework. Multiple data sources including SCADA, DCS, SIS, and electrical monitoring systems are merged to create a comprehensive view of plant operations, enabling more precise detection of perturbations and trips through multi-domain correlation analysis
Solution Approach 2:
The patent introduces time-frequency domain analysis as an additional dimension beyond traditional time-domain monitoring. By applying wavelet transformations and analyzing signals in both time and frequency domains simultaneously, the system achieves higher detection precision for transient events and early-stage perturbations that are invisible in conventional monitoring
2Reliability
If comprehensive data from multiple domains is analyzed to detect perturbations early, then the detection capability improves, but the data processing complexity increases
Solution Approach 1:
The patent segments the complex data processing task into distinct analytical components: wavelet transformation for time-frequency decomposition, dominant frequency identification for characteristic extraction, and deviation detection for anomaly recognition. This segmentation allows each component to be optimized independently while maintaining overall system reliability
Solution Approach 2:
The patent introduces intermediate processing layers including wavelet coefficients, dominant frequency spectra, and deviation metrics that mediate between raw multi-domain data and final detection results. These intermediaries simplify the complexity by transforming raw data into standardized features that can be systematically analyzed across different data sources
3Measurement precision
If wavelet transformation and frequency analysis are applied to time-series data, then the ability to identify dominant frequency changes improves, but the computational time and processing resources increase
Solution Approach 1:
The patent applies wavelet transformation and dominant frequency identification as preliminary processing steps before final deviation detection. By pre-computing time-frequency representations and characteristic frequencies during normal operations, the system prepares analysis results in advance, reducing the computational burden and processing time when actual perturbations or trips occur
Solution Approach 2:
The patent focuses computational resources on identifying dominant frequencies and significant deviations rather than analyzing all frequency components equally. By concentrating analysis on the most relevant frequency bands and deviation thresholds, the system achieves high identification accuracy while minimizing unnecessary computational expenditure on less significant data
4Reliability
If multiple data sources and domains are integrated for comprehensive analysis, then the detection coverage and reliability improve, but the ease of operation and implementation difficulty increase
Solution Approach 1:
The patent creates a universal analysis framework that handles multiple data sources (SCADA, DCS, SIS, electrical systems) and multiple analysis types (time-domain, frequency-domain, time-frequency-domain) through a single integrated platform. This multi-functional approach improves detection reliability across diverse data sources while providing a standardized interface that simplifies operation and implementation
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Systems and methods for simultaneously analyzing time-series and dominant frequency data from both a process domain and an electrical domain of a facility, such as an industrial plant, to detect instances of deviation from optimal, normal, or other predefined process conditions or electrical trips. Detecting when changes in frequencies occur in the time-series data creates a time-series of the changes in dominant frequencies. A data analysis server detects instances of deviation from the predefined process conditions or electrical trips by detecting one or more of correlations, patterns, clusters, and the like in the rates of change. The data analysis server employs one or more of statistical analyses, data mining, machine learning, deep neural networks, parallel coordinate analyses, etc. to identify the deviations and predict or detect onset of an undesired event such as a process perturbation or electrical trip.