Polymer Property Prediction Model for Reactor Control Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current polyolefin reactor systems face significant errors in real-time resin quality measurements due to sampling issues and equipment malfunctions, leading to inconsistent and inaccurate operator decisions for reactor control, necessitating a method to flag polymer property readings as acceptable or unacceptable before they are used to manipulate reactor variables.
Innovation Solution
A method and system that utilize a prediction model to define an average polymer property value, determine a feasible range, measure polymer properties, validate or invalidate them based on this range, and update the model iteratively to improve prediction accuracy, incorporating automated detection of erroneous measurements to prevent process disruptions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If real-time measurements of polyolefin resin quality are taken from resin samples, then reactor control can be maintained, but substantial errors occur due to sampling issues, laboratory procedure misapplications, and equipment malfunctions
Solution Approach 1:
The patent implements a feedback mechanism where measured resin properties are compared against predicted values from a computational model. The system automatically adjusts control decisions based on whether the measured values fall within an acceptable range of predicted values, thereby compensating for measurement errors and maintaining reliable reactor control.
Solution Approach 2:
The patent introduces a computational prediction model as an intermediary between the physical measurement system and the reactor control system. This intermediary compares measured values against predicted values and mediates the control decisions, filtering out erroneous measurements before they affect reactor operation.
2Reliability
If operator decisions are used to determine if laboratory readings are appropriate, then some level of judgment can be applied, but the complexity and uncertainty in the existing methodology results in decisions that are not sufficiently timely, consistent, or accurate
Solution Approach 1:
The patent implements self-service by enabling the system to automatically evaluate and accept or reject laboratory readings based on predefined criteria comparing measured values against predicted values. This eliminates the need for operator judgment, achieving timely and consistent decisions without human intervention.
Solution Approach 2:
The patent changes the decision-making parameter from subjective operator judgment to objective numerical comparison between measured and predicted values. By establishing clear numerical criteria (acceptable range around predicted values), the system achieves consistent and timely automated decisions.
3Ease of operation
If measured polymer properties are used to manipulate reactor variables, then reactor control can be adjusted, but erroneous measurements cause significant process disruption
Solution Approach 1:
The patent uses feedback to compare measured polymer properties against predicted values before implementing control adjustments. This feedback mechanism filters out erroneous measurements, allowing the system to maintain ease of operation while preventing process disruptions caused by bad data.
Solution Approach 2:
The patent applies preliminary action by validating measured values against predicted values before using them for reactor control manipulation. This preliminary validation step ensures that only reliable measurements are used for control adjustments, preventing harmful effects from erroneous data.
Data Source
AI summary
A method for improving the prediction of polymer properties and a system having improved polymer property prediction capabilities is provided. The method for improving the prediction of polymer properties comprises: (1) providing a polymer; (2) providing a prediction model; (3) utilizing said prediction model to define an average polymer property prediction value; (4) determining a feasible range; (5) measuring one or more properties of said polymer; (6) determining whether said one or measured polymer properties are within said feasible range: (7) validating said one or more measured polymer properties if said one or more measured polymer properties fall within the feasible range or invalidating said one or more measured polymer properties if said one or more measured polymer properties fall outside of the feasible range; (8) optionally updating said prediction model; (9) repeating said previous steps at least one or more times; and (10) thereby improving the prediction of polymer properties.