Distributed Data Engines for Real-Time Process Analytics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current process control systems face limitations in real-time performance monitoring and analytics, as they rely on offline data analysis, are influenced by limited controller memory and bandwidth, and struggle with large data sets and streaming data, leading to inaccurate and delayed insights into process abnormalities and inefficiencies.
Innovation Solution
The implementation of distributed industrial process monitoring and analytics systems, which embed data monitoring and analytics engines within process control devices to stream and analyze real-time data, providing localized analytics while minimizing bandwidth usage and processing cycles, and enabling timely optimizations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If offline data analysis is used in traditional process control systems, then system complexity is reduced, but real-time performance monitoring capability deteriorates
Solution Approach 1:
The patent divides the data analysis function into distributed segments by embedding analytics engines within individual process control devices. Each device performs local real-time analytics on its own data, eliminating the need for centralized offline processing while maintaining system simplicity through modular, autonomous units.
Solution Approach 2:
The patent introduces analytics engines as intermediary components between process control devices and the central control system. These engines process data locally and transmit only relevant results or alerts, reducing communication bandwidth requirements and enabling real-time monitoring without overwhelming the central system.
2Device complexity
If controller memory and bandwidth are limited, then device complexity is reduced, but ability to handle large data sets deteriorates
Solution Approach 1:
The patent segments the data handling workload by distributing analytics processing to embedded engines at each device. Each engine processes only local data streams, eliminating the need for centralized storage and processing of all plant data, thus working within limited memory and bandwidth constraints.
Solution Approach 2:
The patent extracts the analytics processing function from the central controller and places it directly within process control devices. This extraction enables local data processing without requiring extensive controller memory or communication bandwidth, while still allowing the system to handle large volumes of process data through distributed computation.
3Ease of operation
If traditional process control systems are used, then ease of operation is maintained, but accuracy of fault detection deteriorates
Solution Approach 1:
The patent implements self-service analytics where embedded engines automatically monitor their own device's data streams and detect anomalies without requiring operator intervention. The system performs autonomous real-time analysis, maintaining ease of operation while significantly improving fault detection accuracy through continuous automated monitoring.
Solution Approach 2:
The patent establishes feedback loops where analytics engines continuously monitor process data, compare it against expected patterns, and immediately alert operators or trigger corrective actions when deviations are detected. This real-time feedback mechanism enhances fault detection accuracy while maintaining simple operation through automated monitoring and clear alerting.
4Productivity
If distributed analytics engines are embedded in process control devices, then real-time analytics capability is improved, but device complexity increases
Solution Approach 1:
The patent merges the analytics engine functionality directly into the process control device hardware and software. By combining data collection, processing, and analytics functions into a single integrated unit, the system achieves real-time analytics capability without requiring separate complex infrastructure, thus limiting the increase in overall device complexity.
Data Source
AI summary
Distributed industrial process monitoring and analytics systems and methods are provided for operation within a process plant. A plurality of distributed data engines (DDEs) may be embedded within the process plant to collect and store data generated by data sources, such as process controllers. Thus, the data may be stored in a distributed manner in the DDEs embedded throughout the process plant. The DDEs may be connected by a data analytics network to facilitate data transmission by subscription or query. The DDEs may be configured as a plurality of clusters, which may further include local and centralized clusters. The local clusters may obtain streaming data from data sources and stream selected data to a data consumer. The centralized cluster may register the local clusters, receive data therefrom, and perform data analytic functions on the received data. The analyzed data may be further sent to a data consumer.