Dynamic Process Simulation for Fault Detection in Plant APM
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial plants face a decrease in reliability over their operating period due to challenges in identifying effective limiting process parameters, which affects production rate, product quality, energy efficiency, and run length, making it difficult to timely recognize and address equipment failures.
Innovation Solution
The use of dynamic models for operator training simulations (OTS) as a digital twin, combining first principles models with data regressed models to monitor process performance and equipment health, enabling the identification of symptoms of failure and triggering alerts for timely maintenance actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If dynamic OTS models with first principles are used for APM, then measurement precision and reliability monitoring improve, but device complexity and computational requirements increase
Solution Approach 1:
The patent creates a digital twin (copy) of the physical industrial plant using dynamic OTS models. This virtual replica allows for complex first principles-based simulations and fault detection without adding physical complexity to the actual plant. The digital twin captures the essential behavior and dynamics of the physical system, enabling precise fault detection through model predictions compared against actual sensor data.
Solution Approach 2:
The patent introduces a workflow engine as an intermediary layer between the complex first principles models and the actual APM implementation. This intermediary manages the initialization, synchronization, and execution of the dynamic OTS models, handling the complexity of model management and coordinate transformations. It mediates between the detailed physical models and the practical APM requirements, making the complex system usable and manageable.
2Reliability
If real-time model synchronization is implemented, then reliability monitoring improves, but loss of time for model initialization and coordination increases
Solution Approach 1:
The patent performs preliminary initialization of the dynamic OTS models by pre-setting initial conditions and parameters based on historical data or steady-state operating conditions. This preliminary action prepares the models in advance for real-time synchronization, reducing the time required during actual operation. The workflow engine pre-configures model states and coordinates before real-time monitoring begins, enabling faster response when reliability issues arise.
3Reliability
If comprehensive process monitoring is implemented, then reliability and fault detection improve, but loss of energy for data processing increases
Solution Approach 1:
The patent extracts and focuses monitoring efforts on the most critical process variables and parameters that have the dominant impact on plant reliability and performance. Rather than comprehensively monitoring all possible variables, the system identifies and prioritizes key limiting parameters such as catalyst activity, fouling factors, and critical operating conditions. This selective extraction of essential monitoring targets reduces computational energy requirements while maintaining effective reliability monitoring.
Data Source
AI summary
An Asset Performance Monitoring (APM) based-system includes an APM workflow engine receiving measured data values for dependent process variables from a process. A process and control simulator includes a dynamic operator training simulations (OTS) model. The APM workflow engine initializes the OTS model at a defined operating point at values for independent process variables from the measured data values to synchronize to the OTS model. The OTS model simulates at the defined operating point to generate model predicted values for key dependent process variables used to generate a trained data model that generates trained model predicted values for the key dependent process variables. The trained model predicted values are compared to the measured data values to generate symptom inputs processed by fault models to identify a suspected fault with the processing equipment/process. The APM workflow engine triggers an alert relating to inspection or maintenance action regarding the processing equipment/process.