Transient Detection Data Acquisition for Industrial Assets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional methods for collecting and processing industrial asset data are inadequate for monitoring fast-developing transients due to low acquisition frequency, leading to excessive network traffic, computational resource issues, and potential loss of transient data, especially when dealing with a large number of assets.
Innovation Solution
The system dynamically adjusts data collection by determining the minimum number of sensor tags needed to detect valid operating state transitions, reading full or minimal subsets of sensor values based on transient periods, and implementing a catch-up mechanism to ensure data availability, thereby reducing network traffic and improving server performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is collected at low acquisition frequency from snapshot buffers, then network traffic is reduced and storage requirements are lowered, but transient signals cannot be detected reliably
Solution Approach 1:
The system dynamically adjusts data collection frequency based on detected transient conditions. During normal operation, data is collected at low frequency to reduce network traffic and storage requirements. When a transient condition is detected, the system automatically increases acquisition frequency to capture the transient signal reliably, then returns to low-frequency collection after the transient ends.
Solution Approach 2:
The system changes the acquisition frequency parameter from a fixed low value to a variable value that adapts based on transient detection needs. This allows the system to maintain high reliability for transient detection only when necessary, rather than continuously operating at high frequency which would generate excessive data volume.
2Reliability
If data is collected at high acquisition frequency for all sensors, then transient signals are captured reliably, but network traffic increases substantially and server resources are overwhelmed
Solution Approach 1:
The system extracts and processes only the minimal subset of sensor data necessary for transient detection. Rather than collecting high-frequency data from all sensors continuously, the system identifies and collects data only from sensors relevant to transient conditions, removing unnecessary data collection overhead and improving system efficiency.
Solution Approach 2:
The system applies partial action by collecting high-frequency data only when and where necessary for transient detection, rather than applying full data collection across all sensors at all times. This selective approach maintains transient detection reliability while avoiding the inefficiency of universal high-frequency collection.
3Loss of information
If full sensor data sets are collected continuously, then complete information is available for analysis, but storage requirements and computational resources increase significantly
Solution Approach 1:
The system applies different data collection strategies to different sensors based on their relevance to transient detection. Critical sensors maintain high-frequency collection to preserve information completeness, while non-critical sensors operate at lower frequencies or are sampled selectively, reducing overall storage requirements while maintaining necessary information quality.
Solution Approach 2:
The system segments the sensor data collection process into critical and non-critical components. By dividing the data collection strategy, the system preserves complete information for transient-relevant sensors while reducing data volume from other sensors, thereby balancing information completeness with storage efficiency.
4Speed
If data collection frequency is increased to capture fast-developing transients, then transient detection capability improves, but network traffic and computational time increase
Solution Approach 1:
The system uses periodic low-frequency data collection during normal operation and switches to high-frequency periodic collection only when transient conditions are detected. This periodic adjustment of acquisition frequency maintains fast transient response capability when needed while minimizing network traffic and computational resource consumption during stable operation.
Data Source
Figure 1
Figure 2
AI summary
Approaches are provided where a group of historical data relating to the operation of an industrial asset are collected on a time interval. It is determined whether the collected group of historical data corresponds to a transitory period of the industrial asset. When the collected group of historical data corresponds to the transitory period a full set of sensor values is read and made available to an analytics engine. When the collected group of historical data does not correspond to the transitory period, a minimal subset of sensor values necessary to detect a start or an end of the transitory period is read and stored.