Virtual Sensor Fault Isolation With Fewer Physical Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing apparatuses face challenges in efficiently detecting and isolating fault conditions with a minimal number of sensors, leading to increased costs and potential weight issues, while using fewer sensors results in inadequate fault analysis.
Innovation Solution
A control circuit processes sensor information from a plurality of sensors to output virtual parameters, enabling fault class determination and targeted maintenance tasks, even with insufficient sensor data, using a neural network trained on data from similar or different apparatuses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a large number of sensors are employed to monitor different sections and operating states of the apparatus, then fault detection capability and fault isolation precision are improved, but device complexity, cost, and weight increase
Solution Approach 1:
The patent introduces virtual sensors as intermediary elements that compute virtual parameters from actual sensor readings. These virtual sensors act as mediators between the physical sensor array and the fault diagnosis system, enabling sophisticated fault isolation without requiring additional physical sensors. The virtual sensors process and transform raw sensor data into meaningful diagnostic parameters through computational models.
Solution Approach 2:
The patent replaces the mechanical/physical sensor system with a computational/virtual sensor system. Instead of adding more physical sensors to improve fault isolation precision, the system substitutes computational processing of existing sensor data with virtual sensors that simulate additional measurement capabilities. This substitution eliminates the need for additional physical hardware while achieving enhanced diagnostic precision.
2Reliability
If a large number of sensors are employed to monitor different sections and operating states of the apparatus, then fault detection capability is improved, but weight increases
Solution Approach 1:
The patent replaces physical sensors with virtual sensors that compute measurement values through computational models. This substitution eliminates the weight of additional physical sensor hardware while maintaining fault detection capability. The virtual sensors run software-based algorithms that process data from existing sensors to generate additional diagnostic information without adding physical mass to the system.
Solution Approach 2:
The patent creates virtual copies of sensor measurements through computational modeling. Instead of installing additional physical sensors, the system creates virtual replicas of sensor functionality through software algorithms that simulate sensor behavior and generate virtual measurement data. These copied measurement capabilities provide enhanced fault detection without the weight penalty of physical sensor duplication.
3Device complexity
If fewer sensors are employed to monitor the apparatus, then device complexity and cost are reduced, but fault analysis capability becomes inadequate
Solution Approach 1:
The patent substitutes computational processing with physical measurement limitations. Instead of being constrained by the number of physical sensors, the system uses virtual sensors to computationally generate additional measurement information. This substitution transforms the limitation of fewer physical sensors into an advantage by enabling sophisticated data processing and virtual measurement synthesis that compensates for the reduced physical sensor array.
Solution Approach 2:
The patent changes the parameters of measurement from direct physical measurements to computed virtual parameters. The system transforms the nature of measurement data by calculating derived parameters from basic sensor readings, enabling comprehensive fault analysis with fewer physical sensors. This parameter transformation allows the system to extract more information from the same physical sensor inputs through computational derivation.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
Sensor information from a plurality of sensors (105) that monitor an apparatus (103) is accessed and then sensed information that corresponds to that sensor information is input into a control circuit (101) configured to output virtual parameters corresponding to the apparatus as a function, at least in part, of the sensed information. A particular fault class is determined from amongst a plurality of fault classes as a function, at least in part, of the virtual parameters and at least one task is identified regarding the apparatus that corresponds to the particular fault class.