Symbolic Sensor Pattern Matching for Early Failure Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for monitoring technical systems, such as electrical submersible pumps, struggle to reliably detect subtle and rapid changes in behavior due to the need for extensive historical data and manual analysis, often missing early signs of failures and requiring cumbersome rule-based comparisons.
Innovation Solution
An assistance apparatus that analyzes multivariate time-dependent sensor data to identify specific temporal courses, assigns symbolic representations to these courses, calculates similarity measures, and ranks failure patterns using a graphical user interface to visualize probable root causes, enabling early and reliable detection of failures without machine learning training.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning approaches are used to identify failures, 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 and temporal courses based on domain knowledge and physical laws before actual failure detection. These patterns include expected sensor behavior during normal operation and various failure modes, allowing immediate comparison with real-time data without requiring historical training data collection
Solution Approach 2:
The patent introduces symbolic representations as an intermediary layer between raw sensor data and failure detection. Temporal courses of sensor data are converted into symbolic sequences that can be directly compared with pre-defined failure patterns, eliminating the need for machine learning training while maintaining high detection accuracy
2Device complexity
If manual monitoring by operation staff is used, then system complexity is reduced, but subtle and rapid changes in technical system behavior are missed reducing reliability
Solution Approach 1:
The system automatically compares real-time sensor data against pre-defined failure patterns and temporal courses, enabling self-diagnosis without requiring manual expert analysis. The apparatus independently identifies failures by matching observed temporal courses with stored failure patterns, ensuring consistent and reliable detection
Solution Approach 2:
The patent divides the monitoring task into discrete temporal courses and failure patterns, each representing specific behavioral characteristics. This segmentation allows the system to methodically compare different aspects of sensor behavior against known failure modes, improving detection reliability while maintaining manageable system complexity
3Ease of operation
If rule-based monitoring with fixed thresholds is used, then ease of operation is improved, but the ability to detect subtle changes over time deteriorates
Solution Approach 1:
The patent replaces static threshold rules with dynamic temporal course analysis. Instead of comparing sensor values against fixed thresholds, the system evaluates the time-dependent behavior patterns of sensors, allowing detection of subtle changes that evolve over time while maintaining straightforward operation through pattern matching
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Assistance apparatus for automatically identifying failure types of a technical system by analysing monitored time series of more than one different sensor data, each sensor data representing a different parameter of the technical system, comprising at least one processor configured to determine for each sensor data a set of specific temporal courses of first time series of said sensor data of said sensor and assign a symbolic representation to each of the different specific temporal courses, - provide at least one failure pattern, each failure pattern representing one failure type out of several failure types of the technical system and each failure pattern consisting of a failure-type-specific combination of specific temporal courses of the first time series of at least a subset of sensor data in the same segment of time, wherein each specific temporal course is represented by the respective symbolic representation, - 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 (20, 27) 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 of the obtained more than one monitored time series of sensor data and all failure patterns, - determine a ranking of the failure pattern depending on decreasing values of the calculated similarity measure, and - output the ranking via a user interface.