FGD Process Monitoring with Soft Sensors for Slurry Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current FGD systems lack real-time measurement capabilities for crucial parameters like limestone slurry concentration and gypsum slurry conversion, and they inadequately monitor and control various sub-systems, leading to inefficiencies and frequent equipment failures that can cause plant shutdowns.
Innovation Solution
A system comprising hardware processors, communication interfaces, and databases that collect and process real-time data to build predictive models, using sensors and machine learning techniques to optimize FGD process parameters, including limestone slurry concentration and gypsum conversion, and monitor equipment health to prevent failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If real-time measurement of key parameters like limestone slurry concentration and gypsum slurry conversion is implemented, then process control precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent introduces soft sensors as intermediary computational models that estimate unmeasurable parameters (limestone slurry concentration, gypsum slurry conversion) based on readily available process data. These soft sensors act as mediators between existing measurements and the required process parameters, avoiding direct installation of complex physical measurement devices while achieving precise parameter estimation through machine learning algorithms.
Solution Approach 2:
The patent replaces physical measurement instruments (mechanical/chemical sensors) with computational models (soft sensors based on machine learning). Instead of using complex physical devices to directly measure slurry concentration and conversion, the system uses algorithms that process existing process data to infer these parameters, substituting mechanical measurement systems with information processing systems.
2Reliability
If comprehensive monitoring of all FGD sub-systems is implemented, then reliability is improved, but device complexity and operational cost increase
Solution Approach 1:
The patent applies local quality by focusing monitoring efforts on critical equipment and parameters that have the greatest impact on FGD reliability. Rather than uniformly monitoring all components, the system identifies key sub-systems (absorber, pumps, spray nozzles) and parameters (slurry concentration, pH, equipment vibration) that require enhanced monitoring, allocating resources locally where they provide maximum reliability improvement.
Solution Approach 2:
The patent implements preliminary action through predictive maintenance capabilities. The system continuously analyzes equipment data to predict potential failures before they occur, allowing maintenance to be scheduled in advance. This prevents unexpected equipment failures and shutdowns by taking proactive measures based on early detection of degradation trends, rather than waiting for actual failures.
3Manufacturing precision
If multiple predictive models are built and continuously updated, then manufacturing precision of process parameters is improved, but loss of time for model training and computation increases
Solution Approach 1:
The patent applies partial action by implementing a hierarchical modeling approach where simple, fast models provide baseline predictions and more complex models are only trained and updated when needed. The system uses online learning techniques that update models incrementally with new data rather than requiring complete retraining, performing partial updates that maintain precision while minimizing computational time and resource usage.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
State of the art techniques used for Flue Gas Desulpharization (FGD) process monitoring fail to comprehend the relationship between various process parameters, which is crucial in determining the performance of a FGD process being monitored. The disclosure herein generally relates to industrial process monitoring, and, more particularly, to a method and system for performance optimization of Flue Gas Desulphurization (FGD) Unit. The system identifies Key Performance Indicators (KPIs) associated with the process being monitored, and identifies parameters associated with each KPI. This information is used to generate several predictive models, from which a predictive model having the highest value of composite model score amongst the predictive models is selected as the predictive model for processing the input data, which is then used to perform optimization of the FGD process.