Mobile Sensor Monitoring for Adaptive Equipment Behavior Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for monitoring equipment behavior are costly and time-consuming, especially when equipment undergoes gradual changes due to wear or maintenance, and are ineffective for un-sensored or under-sensored devices in remote or hazardous locations.
Innovation Solution
The use of trained models to detect anomalous behavior in monitored devices, allowing for automatic generation and deployment of behavior models based on historic data, and the integration of un-sensored or under-sensored equipment into a monitoring environment using a mobile sensor platform.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If rules are established by subject matter experts or physics-based models to detect abnormal behavior, then detection accuracy is improved, but cost and time consumption increase significantly
Solution Approach 1:
The system performs preliminary actions by automatically generating and training behavior models using historical data before actual monitoring begins. This preliminary model training phase captures normal behavior patterns, so that during operation, anomaly detection can proceed quickly without requiring expert rule establishment for each new equipment or operational state.
Solution Approach 2:
The system enables self-service by allowing equipment to monitor itself through automatically generated behavior models that adapt to the equipment's own historical data. The models are trained on-site using the equipment's own operational data, eliminating the need for external experts to establish rules for each specific device.
2Adaptability or versatility
If equipment undergoes gradual changes due to wear or maintenance, then operational adaptability is improved, but rule-based monitoring effectiveness deteriorates
Solution Approach 1:
The behavior models are dynamic and can be retrained as equipment evolves. When equipment undergoes gradual changes due to wear or maintenance, the system can update the behavior models with new historical data reflecting the current operational state, allowing the monitoring system to adapt dynamically rather than relying on static rules that become obsolete.
Solution Approach 2:
The system handles parameter changes by retraining behavior models with updated historical data that reflects new operational parameters. When equipment characteristics change due to wear or maintenance, the model training process incorporates these changes, adjusting the baseline behavior patterns to match the new operational reality.
3Adaptability or versatility
If mobile sensor platforms are deployed to monitor un-sensored or under-sensored equipment in remote locations, then monitoring coverage is improved, but system complexity increases
Solution Approach 1:
The mobile sensor platform is designed as a universal monitoring system that can deploy to various remote locations and monitor different types of equipment. By using standardized sensor suites and a unified behavior model training framework, the system achieves multi-functionality without proportionally increasing complexity for each deployment scenario.
Solution Approach 2:
The system introduces a centralized model training and deployment server as an intermediary between the mobile sensor platforms and the equipment being monitored. This intermediary handles the complex tasks of data aggregation, model training, and model distribution, allowing the mobile platforms themselves to remain relatively simple while achieving sophisticated monitoring capabilities.
Data Source
AI summary
A method of behavior monitoring includes receiving, from a first sensor of a mobile sensor platform, first sensor data indicative of operation of a monitored device, wherein the monitored device is distinct from the mobile sensor platform; providing, as input to a trained behavior model associated with the monitored device, input data based at least in part on the first sensor data to generate behavior model output data; generating, based on the behavior model output data, a control command; and sending the control command to the mobile sensor platform or the monitored device.