Failure Pattern Ranking for Sensor-Based Technical System Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for monitoring technical systems, such as oil and gas production, struggle to reliably and efficiently detect subtle and rapid changes in machine behavior, often requiring extensive historical data and manual analysis, which can lead to missed anomalies and inefficient maintenance.
Innovation Solution
An assistance apparatus that analyzes multivariate time-dependent sensor data to identify failure types by determining specific temporal courses, assigning symbolic representations, calculating similarity measures, and ranking failure patterns, allowing for automatic detection and visualization of root causes without the need for machine learning training.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning approaches are used to identify failure types, then detection accuracy can be improved, but extensive historical data is required for training which increases system complexity and time requirements
Solution Approach 1:
The patent pre-defines failure patterns with expected temporal courses of sensor data before actual failure detection is needed. These patterns are established based on domain knowledge and physical laws, allowing immediate comparison with real-time sensor data without requiring historical training data collection.
Solution Approach 2:
Instead of using complex machine learning models that require extensive training, the patent employs simple pattern matching algorithms that can be quickly deployed and discarded or updated as needed. This approach uses lightweight computational methods rather than heavy machine learning infrastructure.
2Device complexity
If manual monitoring by operation staff is used, then system complexity is reduced, but subtle changes and rapid anomalies can be missed reducing reliability
Solution Approach 1:
The patent introduces an intermediate automated analysis layer that processes sensor data and compares it against predefined failure patterns. This intermediary system bridges the gap between simple manual monitoring and complex machine learning, providing automated detection while maintaining interpretability through pattern matching.
Solution Approach 2:
The monitoring approach is segmented into distinct failure patterns, each representing a specific failure type with characteristic sensor behavior. This segmentation allows the system to handle complexity in a structured way, breaking down overall system monitoring into manageable pattern-specific analyses.
3Ease of operation
If fixed threshold rules are used for monitoring, then ease of operation is improved, but ability to detect subtle changes over time deteriorates
Solution Approach 1:
The patent transitions from static fixed thresholds to dynamic temporal pattern matching. Instead of comparing sensor values against fixed thresholds, the system analyzes the temporal course and shape of sensor data, allowing detection of subtle changes that evolve over time while maintaining operational simplicity through pattern-based rules.
Solution Approach 2:
The monitoring approach changes from using fixed parameter thresholds to analyzing parameter evolution patterns over time. Each failure pattern defines expected temporal behavior of sensor parameters, enabling detection of subtle changes through pattern deviation rather than threshold crossing.
Data Source
AI summary
Assistance apparatus for automatically identifying failure types of a technical system is provided including at least one processor configured to determine for each sensor data a set of specific temporal courses of first time series of the sensor data of the sensor and assign a symbolic representation to each of the different specific temporal courses, provide at least one failure pattern, obtain more than one monitored time series of sensor data of the technical system, each of them divided into a sequence of time segments, and automatically assign to each time segment a symbolic representations according to the temporal course of the sensor data in the time segment, calculate a similarity measure for the set of symbolic representations of a selected time interval, determine a ranking of the failure pattern depending on decreasing values of the calculated similarity measure, and output the ranking.