FCC Pre-Treatment Predictive Control for Gasoline Sulfur

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current industrial process control systems for fluidized catalytic cracking (FCC) pre-treatment units lack real-time adjustments based on downstream gasoline product sulfur levels, hindering effective desulphurization and meeting stringent diesel and gasoline specifications.

Innovation Solution

Implementing a real-time predictive model using machine learning and data analytics to adjust the pre-treatment reactor temperature in the FCC unit, based on real-time operating data and product sulfur levels, to control sulfur levels in the gasoline product.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional model-based control systems are used for FCC pre-treatment units, then the control system structure is simple and easy to implement, but the system cannot perform real-time adjustments based on downstream gasoline product sulfur levels, resulting in poor desulphurization control

Engineering Contradiction:

Improvedesulphurization control effectivenessVSAvoidcontrol system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent implements a real-time feedback mechanism where the predictive model continuously receives downstream gasoline product sulfur level measurements and adjusts pre-treatment reactor temperature accordingly. This closed-loop feedback enables the system to respond dynamically to actual sulfur levels, resolving the contradiction by making the control effective while managing complexity through targeted real-time adjustment rather than complete system redesign

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The predictive model performs preliminary calculations to determine optimal pre-treatment reactor temperature settings before actual processing occurs. By pre-calculating the required temperature adjustments based on predicted sulfur levels and processing conditions, the system prepares control actions in advance, improving desulphurization effectiveness while maintaining manageable system complexity through proactive rather than reactive control

Inventive Principle:

Principle #10Preliminary action

2Manufacturing precision

If real-time predictive modeling with machine learning is implemented, then precise control of sulfur levels and desulphurization efficiency is achieved, but the device complexity and computational requirements increase significantly

Engineering Contradiction:

Improvesulfur level control precisionVSAvoidpredictive model complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent focuses on optimizing a specific set of critical parameters (pre-treatment reactor temperature, feed rate, catalyst circulation rate) rather than attempting to control all process variables. By concentrating computational resources on the most influential parameters that directly affect sulfur levels, the system achieves precise sulfur control while keeping the predictive model complexity manageable through parameter prioritization

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The control system is segmented into distinct functional modules: data collection from multiple sources, predictive modeling for sulfur level estimation, optimization calculation for temperature adjustment, and execution of control actions. This modular segmentation allows each component to be developed and validated independently, reducing overall system complexity while enabling precise sulfur level control through coordinated module interactions

Inventive Principle:

Principle #1Segmentation

3Adaptability or versatility

If continuous real-time data collection and model updates are performed, then the control system adapts to changing process conditions effectively, but the computational load and processing time increase

Engineering Contradiction:

Improveadaptability to process condition changesVSAvoidcomputational processing time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The predictive model performs real-time calculations at strategically determined intervals rather than continuously, balancing adaptability with processing time requirements. By updating sulfur level predictions and adjusting temperature recommendations periodically based on significant process condition changes or elapsed time thresholds, the system maintains effectiveness while reducing unnecessary computational overhead

Inventive Principle:

Principle #19Periodic action

Solution Approach 2:

The system performs full real-time predictive modeling and optimization only when process conditions change significantly or when approaching critical sulfur level thresholds. During stable operating conditions, the system uses simplified models or maintains previous control settings, reducing computational load and processing time while still achieving effective adaptability when it matters most for sulfur control

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS11676061B2Harnessing machine learning and data analytics for a real time predictive model for a FCC pre-treatment unit

Publication Date: 2023.06.13 HONEYWELL INTERNATIONAL INC

AI summary

This disclosure provides an apparatus and method for harnessing machine learning and data analytics for a real-time predictive model for a FCC pre-treatment unit. The method includes collecting operating parameters of a pre-treatment unit and fluid catalytic cracking (FCC) unit; evaluating an independent variable of the operating parameters; and adjusting an input to the pre-treatment unit to control the independent variable within specifications in an output of the FCC unit.