Event Model Training Using In Situ Multi-Sensor Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for identifying events in various settings often lack effectiveness due to the unavailability of necessary information and mismatched data across different locations, making it difficult to accurately detect and manage events such as security breaches, equipment operations, and environmental changes.
Innovation Solution
A system and method that utilize a combination of first and second sets of measurements, where the first set is used to identify events and train event models, which are then applied to identify additional events across multiple locations using different physical measurements, including temperature and acoustic data from distributed sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If event identification relies on information from known instances, then event detection can be performed, but the method fails when information is unavailable or mismatched across different settings
Solution Approach 1:
The system performs preliminary actions by collecting and storing measurements from multiple signal types (acoustic, temperature, vibration, etc.) before events occur. These pre-collected data form a training dataset that enables the machine learning model to identify events even when traditional known-instance information is unavailable or mismatched across different settings
Solution Approach 2:
The system changes parameters by transitioning from relying on single-type signal data to using multi-type signal data. By incorporating diverse physical measurements (acoustic signals, temperature, vibration) and transforming them into feature vectors, the system adapts to different event types and settings, improving both reliability and versatility
2Measurement precision
If multiple types of sensors and measurements are used to improve event identification, then accuracy improves, but system complexity increases
Solution Approach 1:
The system merges multiple signal types (acoustic, temperature, vibration) and measurement data into a unified feature vector representation. This consolidation allows the machine learning model to process diverse data sources through a single computational framework, improving measurement precision while managing system complexity through integration rather than separate processing systems
Solution Approach 2:
The machine learning model acts as an intermediary that receives complex multi-type signal data and transforms it into simplified event identification outputs. This intermediary layer handles the complexity of processing multiple sensor types, presenting a streamlined interface for event detection and reducing the apparent system complexity to end users
Data Source
AI summary
A method of identifying events comprises obtaining a first set of measurements comprising a first signal of field data at a location; identifying one or more events at the location using the first set of measurements; obtaining a second set of measurements comprising a second signal at the location, wherein the first signal and the second signal represent at least one different physical measurements; training one or more event models using the second set of measurements and the identification of the one or more events as inputs; and using the one or more event models to identify at least one additional event at one or more locations.