SCADA-Based Subsystem Health Monitoring for Renewable Microgrids
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current condition monitoring systems in renewable generation plants and microgrids face challenges with accuracy due to missed and false alarms, high costs associated with additional sensors and data acquisition, and inability to account for nonlinear dynamics and subtle changes in individual components, leading to increased maintenance costs and downtime.
Innovation Solution
A method that automatically identifies subsystems and builds data-driven models using SCADA data to train models describing input-output relationships, setting alarm thresholds and providing a global health metric, which reduces the need for additional sensors and improves accuracy by considering the plant's structure and dynamics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If additional dedicated sensors, data acquisition, communication and analytics steps are employed to increase the accuracy of condition monitoring systems, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent applies universality by enabling SCADA systems to perform multiple functions - both their traditional supervisory control and data acquisition roles, and condition monitoring functions. The system reuses existing SCADA infrastructure (sensors, data acquisition, communication channels) to simultaneously support operational monitoring and condition-based maintenance, eliminating the need for separate dedicated condition monitoring hardware and reducing overall system complexity and cost.
Solution Approach 2:
The patent merges condition monitoring functionality with the existing SCADA system. By integrating condition monitoring algorithms and analytics into the SCADA platform, the system combines operational control and condition assessment into a unified system, sharing hardware resources, data processing capabilities, and communication infrastructure, thereby reducing device complexity while maintaining measurement precision.
2Device complexity
If standard Key Performance Indicators and simple alarm functionalities are used in SCADA systems, then device complexity is reduced, but measurement precision and ability to detect subtle changes deteriorate
Solution Approach 1:
The patent applies dynamics by implementing adaptive condition monitoring that evolves with the system. The monitoring approach dynamically adjusts alarm thresholds and detection sensitivity based on historical data, operational conditions, and learned patterns. This enables the system to detect subtle changes and degradation trends that static, simple alarm systems would miss, while maintaining computational efficiency suitable for SCADA environments.
Solution Approach 2:
The patent implements feedback mechanisms where the condition monitoring system continuously learns from operational data and alarm outcomes. By analyzing trends, comparing actual performance against predicted behavior, and adjusting detection parameters based on feedback from maintenance outcomes, the system improves its measurement precision over time without requiring increased device complexity, enabling detection of subtle degradation patterns.
3Measurement precision
If multivariate statistical approaches are applied to model correlations between measurements, then measurement precision is improved, but device complexity and difficulty of root-cause analysis increase
Solution Approach 1:
The patent applies segmentation by dividing the complex multivariate analysis into component-specific monitoring modules. Each subsystem (e.g., generators, transformers, motors) has its own dedicated analysis framework that models correlations specific to that equipment type. This segmentation maintains measurement precision through specialized multivariate modeling while reducing overall system complexity by localizing analytical complexity to individual components, thereby facilitating easier root-cause analysis.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The invention relates to a method and apparatus for monitoring the condition of subsystems within a renewable generation plant or microgrid which are using Supervisory Control and Data Acquisition (SCAD A) systems for allowing plant operators to monitor and interact with a plant via human machine interfaces.