Valve Condition Detection via Secure Time-Series Analytics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial process control systems face challenges in detecting conditions and modes of operation of valves in a secure and efficient manner, particularly in preventing cyber-intrusions and ensuring the integrity of process control systems.
Innovation Solution
The implementation of time-series analytics using computing devices that receive and analyze process parameter values from valves, applying rules and machine learning techniques to detect conditions and determine the mode of operation, while ensuring secure communication through mechanisms like data diodes and firewalls.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If time-series analytics and machine learning techniques are implemented to detect valve conditions, then measurement precision and reliability are improved, but device complexity increases
Solution Approach 1:
The system segments the complex analytics function into separate components: data collection modules at field devices, secure communication infrastructure (data diodes, firewalls), and analysis engines that can be distributed across edge devices and cloud platforms. This allows sophisticated machine learning algorithms to be implemented without requiring a single complex centralized system.
Solution Approach 2:
The patent introduces intermediary security components (data diodes, firewalls) that mediate between the process control system and external networks. These intermediaries enable secure data transmission for analytics while protecting the control system from cyber threats, thus allowing improved measurement precision without compromising system integrity.
2Reliability
If secure communication mechanisms like data diodes and firewalls are implemented, then reliability and security are improved, but loss of information and communication efficiency worsen
Solution Approach 1:
The communication architecture is segmented into multiple secure channels with different security levels. Data diodes provide unidirectional secure communication for critical data, while firewalls control bidirectional traffic. This segmentation allows information to flow efficiently through appropriate channels while maintaining security, reducing the loss of information compared to a single restrictive security barrier.
3Measurement precision
If centralized administrative computing devices are used for data analysis, then measurement precision is improved, but loss of time in data transmission increases
Solution Approach 1:
The system implements local quality by enabling data analysis capabilities at distributed locations including edge devices and local computing systems. This allows time-sensitive valve condition analysis to be performed locally without transmitting all raw data to centralized systems, reducing transmission time while maintaining analysis precision through localized intelligent processing.
Solution Approach 2:
The system performs preliminary data processing and filtering at the source and edge devices before transmitting data to centralized systems. This preliminary action reduces the volume of data requiring long-distance transmission while preserving the information needed for precise analysis, thus reducing transmission time without sacrificing measurement precision.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Securing communications from a process plant to a remote system includes a data diode disposed there between that allows data to egress from the plant but prevents ingress of data into the plant and its associated systems. Process plant data from the secure communications is then analyzed to detect conditions occurring at process plant entities in the process plant using various machine learning techniques. When the process plant entity is a valve, the mode of operation for the valve is determined and a different analysis is applied for each mode in which a valve operates. Additionally, the process plant data for each valve is compared to other valves in the same process plant, enterprise, industry, etc. Accordingly, the health of each of the valves is ranked relative to each other and the process plant data for each valve is displayed in a side-by-side comparison.