Distributed Data Pipeline for Process Control Analytics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current process control systems face limitations in data archiving, analysis, and troubleshooting due to limited controller and device memory, communications bandwidth, and processor capability, leading to incomplete or inaccurate insights into abnormal conditions and faults in process plants.
Innovation Solution
Implementing a distributed data pipeline system within process control systems that automatically collects and processes data in real-time or stored data, using signal processing-based learning to determine fault sources and variations, integrating data processing modules across various devices for comprehensive analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If data is archived and stored in controllers and field devices, then complete data is available for analysis, but memory capacity is exceeded
Solution Approach 1:
The patent extracts data archiving functionality from controllers and field devices to dedicated data historians and external storage systems. This allows complete process data to be retained for analysis without consuming limited controller memory, as data is removed from the control system and stored in specialized external repositories designed for long-term data retention.
Solution Approach 2:
The patent introduces data historians as intermediary components between field devices and analysis systems. These historians act as mediators that collect, store, and manage process data, allowing complete data to be available for troubleshooting and analysis while preventing memory overflow in controllers and field devices by intercepting data before it consumes their limited storage capacity.
2Loss of information
If data is processed and analyzed in real-time, then complete insights are obtained, but processor capability is exceeded
Solution Approach 1:
The patent segments the data processing architecture into multiple independent components: data collection at field devices, data transmission through communication networks, data storage in historians, and data analysis in separate applications. This segmentation allows processing to be distributed across multiple devices with different processor capabilities, enabling complete real-time analysis without overwhelming any single controller's processor.
Solution Approach 2:
The patent introduces data historians and communication networks as intermediary layers between data sources and analysis applications. These intermediaries buffer and manage data flow, allowing comprehensive real-time data to be made available for analysis without requiring the controller processor to handle all processing tasks simultaneously, thus distributing the computational burden.
3Loss of information
If data is transmitted across the network, then data is accessible for analysis, but communications bandwidth is exceeded
Solution Approach 1:
The patent implements preliminary data collection and buffering actions at data historians before analysis is requested. Data is pre-transmitted from field devices to historians and stored in advance, so when analysis is needed, the data is already available locally without requiring additional network bandwidth. This preliminary action ensures data accessibility while managing network traffic during normal operation.
Solution Approach 2:
The patent extracts data from the real-time control network and stores it in separate data historian systems. This extraction removes the burden of continuous data transmission from the control network bandwidth, as data is captured once and stored for later analysis without requiring ongoing high-bandwidth communication between field devices and analysis applications.
Data Source
AI summary
A data pipeline is used as a fundamental processing element for implementing techniques that automatically or autonomously perform signal processing-based learning in a process plant or monitoring system. Each data pipeline includes a set of communicatively interconnected data processing blocks that perform processing on one or more sources of data in a predetermined order to, for example, clean the data, filter the data, select data for further processing, perform supervised or unsupervised learning on the data, etc. The individual processing blocks or modules within a data pipeline may be stored and executed at different devices in a plant network to perform distributed data processing. Moreover, each data pipeline can be integrated into one or more higher level analytic modules that perform higher level analytics, such as quality prediction, fault detection, etc. on the processed data. The use of data pipelines within a plant network enables data collected within a plant control or monitoring system to be processed automatically and used in various higher level analytic modules within the plant during ongoing operation of the plant.