CCGT Optimization via Soft Sensors and Anomaly Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Combined cycle gas turbine (CCGT) power plants face inefficiencies due to fluctuating load demands and equipment anomalies, which existing control systems struggle to address effectively, often leading to sub-optimal or erroneous settings of manipulated variables, and the inability to measure key performance parameters like turbine inlet temperature.

Innovation Solution

A system that integrates real-time and non-real-time data from CCGT databases to estimate soft sensor parameters, detect anomalies, determine operational states, and optimize manipulated variables using predictive models, anomaly detection, and optimization algorithms, ensuring optimal settings and improved performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If process optimization is applied without identifying the state of operation, then manipulated variables can be adjusted, but sub-optimal or erroneous settings occur leading to reduced reliability

Engineering Contradiction:

Improvepower generation efficiencyVSAvoidoperational reliability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system dynamically adapts the optimization process based on the detected state of operation. It transitions between steady-state optimization and transient-state monitoring, adjusting the control strategy in real-time to match current operational conditions, thereby avoiding erroneous manipulations during critical transitions

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system implements feedback through continuous anomaly detection and state identification. By monitoring operational parameters and comparing them against expected behavior patterns, the system provides feedback signals that prevent optimization actions when anomalies are detected, ensuring reliability while maintaining efficiency

Inventive Principle:

Principle #23Feedback

2Productivity

If optimal settings from process optimization are implemented without reconciling with control system settings, then efficiency may improve, but system stability deteriorates due to complex CCGT dynamics

Engineering Contradiction:

Improvethermal efficiencyVSAvoidprocess stability

Core Design Contradiction:

ProductivityVSStability of the object's composition

Solution Approach 1:

The system introduces an intermediary reconciliation layer between process optimization recommendations and control system implementation. This intermediary compares optimal settings with current control settings, evaluates the magnitude of changes required, and determines whether implementation is safe based on current operational stability, thus mediating between efficiency goals and stability constraints

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system carefully manages parameter changes by evaluating the magnitude and rate of proposed manipulations. It adjusts optimization aggressiveness based on operational conditions, allowing larger changes when stable and preventing rapid changes during transient states, thereby maintaining process stability while achieving efficiency improvements

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If key performance parameters like turbine inlet temperature are measured directly, then measurement accuracy improves, but equipment complexity and cost increase

Engineering Contradiction:

Improveturbine inlet temperature measurement accuracyVSAvoidsensor and measurement system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system creates virtual copies of physical measurements through soft sensors. These software-based measurement models replicate the function of physical sensors by calculating difficult-to-measure parameters from easily measurable ones, providing accurate estimates of turbine inlet temperature and other critical parameters without requiring complex or expensive physical measurement devices

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system replaces mechanical/physical measurement systems with computational models. Instead of using complex physical sensors to directly measure difficult parameters, the system uses mathematical models and data processing to compute these parameters from available sensor data, substituting mechanical measurement complexity with computational simplicity

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12173625B2Method and system for optimization of combination cycle gas turbine operation

Publication Date: 2024.12.24 TATA CONSULTANCY SERVICES LTD

AI summary

Combined cycle gas turbine (CCGT) power plants have become common for generation of electric power due to their high efficiencies. There are various problem related with improving the efficiency of CCGT plants by optimizing the manipulated variables. The method and system for optimizing the operation of a combined cycle gas turbine has been provided. The system is configured to calculate an optimal value of manipulated variables (MV) with efficiency as one of the key performance parameters. The MVs from the existing CCGT automation system, i.e. a first set of manipulated variables and the manipulated variables from the optimization approach, i.e. a second set of manipulated variables are combined to determine an optimal set of manipulated variables. The method further checks for the anomalous behavior of the system and define the root cause of the identified anomaly and the operational state of the CCGT plant.