Graphical Data Modeling Studio for Big-Data Process Plant Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current process control systems face limitations in data archiving, memory management, and communication efficiency, leading to inaccurate, incomplete, and unusable data for complex process modeling due to memory and bandwidth constraints, and lack the ability to effectively analyze big data for predictive analysis and trend detection in process plants.
Innovation Solution
A data modeling studio provides a graphical environment for creating and executing data models using big data machines, allowing for comprehensive diagnosis, prognosis, and analysis by configuring user interface elements, model templates, and a runtime engine to retrieve and execute data models, enabling efficient data analysis and model iteration without reconfiguring the plant.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data is archived in traditional controllers with limited memory, then memory usage is minimized, but data completeness and accuracy deteriorate due to compression and sampling limits
Solution Approach 1:
The system divides data archiving functionality between two segments: traditional controllers handle real-time control with minimal archiving, while a separate big data machine handles comprehensive data storage and analysis. This segmentation allows each component to operate within its optimal capabilities without the memory constraints limiting overall data quality.
Solution Approach 2:
A data highway acts as an intermediary communication channel between controllers and the big data machine. This intermediary enables high-bandwidth data transfer, allowing controllers to offload comprehensive data archiving to the big data machine without impacting real-time control performance or data accuracy.
2Device complexity
If traditional control systems are used, then system simplicity is maintained, but data analysis capability deteriorates due to inability to handle big data
Solution Approach 1:
The big data machine serves multiple functions: it archives historical data, performs real-time data analysis, supports predictive maintenance, enables process optimization, and provides a graphical user interface for user interaction. This multi-functionality allows the system to handle diverse data analysis tasks without requiring multiple separate systems.
Solution Approach 2:
The system adds a new dimensional layer by introducing a graphical user interface that operates above the traditional control architecture. This interface dimension enables users to interact with and analyze big data without modifying the underlying control system, thereby enhancing adaptability while maintaining operational simplicity.
3Quantity of substance
If data is reported to centralized historians, then controller memory is reduced, but communication efficiency deteriorates due to excessive loading
Solution Approach 1:
The system implements dynamic data routing where the big data machine actively subscribes to and receives data streams directly from controllers through the data highway. This dynamic approach allows controllers to maintain minimal local memory while the big data machine flexibly manages comprehensive data collection, balancing memory usage with communication efficiency.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A data modeling studio provides a structured environment for graphically creating and executing models which may be configured for diagnosis, prognosis, analysis, identifying relationships, etc., within a process plant. The data modeling studio includes a configuration engine for generating user interface elements to facilitate graphical construction of a model and a runtime engine for executing data models in, for example, an offline or an on-line environment. The configuration engine includes an interface routine that generates user interface elements, a plurality of templates stored in memory that serve as the building blocks of the model and a model compiler that converts the graphical model into a data format executable by the run-time engine. The run time engine executes the model to produce the desired output and may include a retrieval routine for retrieving data corresponding to the templates from memory and a modeling routine for executing the executable model.