Sensor Value Screening for Reliable Turbine Condition Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Technical installations such as gas or wind turbines face reliability issues due to unreliable measurement values from sensors under extreme conditions, which can lead to incorrect assessments of the operating state and subsequent adjustments, affecting maintenance efficiency and costs.
Innovation Solution
A method that categorizes measured values as normal or anomalous using threshold value comparisons and statistical position parameters, identifying and filtering out unreliable values to improve data reliability, involving multiple stages of analysis including threshold comparisons, statistical calculations, and anomaly classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Temperature
If measurement sensors are used under extreme conditions (high temperatures, pressures, flow rates), then the technical installation can operate in extreme environments, but the error rates of the measurement sensors increase
Solution Approach 1:
The patent introduces an intermediary evaluation system that acts as a mediator between the measurement sensors and the control system. This evaluation system analyzes multiple measured values, detects anomalies using statistical methods (such as standard deviation analysis), and filters unreliable data before it reaches the control system. The intermediary layer compensates for the poor performance of individual sensors in extreme conditions by collectively evaluating multiple measurements and identifying outliers.
2Reliability
If multiple measured values are evaluated and anomalies are detected using statistical methods, then the reliability of measured values is improved, but the complexity of the evaluation system increases
Solution Approach 1:
The patent segments the evaluation process into distinct functional modules: data collection from multiple sensors, statistical analysis module that calculates mean and standard deviation, anomaly detection module that compares individual values against statistical thresholds, and filtering module that removes identified anomalies. This segmentation allows the complex evaluation system to be structured in manageable components, each performing a specific function, thereby reducing overall system complexity while maintaining high reliability.
Data Source
AI summary
Provided is a method for providing measured values of a technical installation in which measured values in at least one measurement series are captured, wherein a respective measured value is provided by a measurement sensor for a respective physical measurement variable in the technical installation for a respective measurement time. The measured values are categorized as normal measured values or anomalous measured values with the aid of a threshold value comparison and at least one further method stage. The further method stage comprises calculating one or more statistical position parameters for selected measured values from the same measurement series and/or different measurement series.The method makes it possible to increase the reliability of the measured values provided.A technical system comprising the technical installation, at least one measurement sensor and a program-controlled device, and a method for operating the technical system are also proposed.