Dynamic System Model Using Functional Nests for Evolving Process Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for monitoring evolving systems, such as 'a-priori' and statistical-based approaches, face limitations in understanding underlying processes and maintaining accuracy over time, necessitating a more effective approach for diagnosis and prognosis.
Innovation Solution
A method involving the iterative construction and selection of functional nests from a basic set of functionals, using sensor data streams to model system evolution, combining process knowledge with sensor-driven selection for optimal representation of system responses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If an 'a-priori' based process model is used to monitor an evolving system, then the model can be run to show system evolution from initial conditions, but the underlying processes are not always known or well characterised and may change over time
Solution Approach 1:
The patent applies dynamics by making the system model adaptive and evolving over time. Instead of using a static a-priori model, the system continuously updates the process model by integrating sensor data with the existing model, allowing the model to adapt to changing underlying processes and conditions in the monitored system.
Solution Approach 2:
The patent implements feedback by using sensor data to continuously validate and update the process model. The sensor measurements are compared against model predictions, and the model is refined based on the differences, creating a closed-loop system that improves accuracy over time while adapting to actual system behavior.
2Ease of manufacture
If a statistical-based approach is used to analyze time-dependent data, then understanding of underlying system mechanisms is not required, but the results are often only valid under limited conditions
Solution Approach 1:
The patent merges statistical-based data analysis with process knowledge and mechanistic understanding. By combining sensor data processing with domain-specific process models, the system achieves both the ease of statistical methods and the broader applicability of mechanistic models across different operating conditions.
Solution Approach 2:
The patent creates a universal monitoring framework that can handle multiple types of data and apply to various systems. The integrated approach using sensor data, process models, and adaptive updating mechanisms makes the system applicable across different industrial processes and conditions, beyond limited statistical validity ranges.
3Loss of information
If multiple sensors monitoring causal agents and conditions are deployed, then comprehensive system monitoring is achieved, but data processing complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the complex data processing task into distinct functional components: sensor data acquisition, causal agent analysis, condition monitoring, and model updating. This modular approach processes information from multiple sensors in an organized manner, maintaining information completeness while reducing overall processing complexity.
Data Source
AI summary
A method of monitoring an evolving system, the method including the steps of: obtaining a plurality of sensor data streams relating to outputs from sensors monitoring said system, wherein at least one of said sensors monitors a condition of said system, and wherein at least one of said sensors monitors a causal agent for said condition; iteratively constructing a plurality of functional nests, each functional nest being a functional formed from a combination of selected functionals from a basic set of functionals; determining an output data stream for each functional nest by inputting said sensor data streams into said functional nests; selecting a functional nest from said plurality of functional nests based on said output data streams; and using said selected functional nest to monitor said system.