Single-Point EMI Sensing for Appliance State Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting the operating states of electronic devices are either costly and invasive, requiring multiple sensors or raise privacy concerns, and typically only detect on- or off-states without providing granular information on device usage.
Innovation Solution
A sensing device coupled to an electrical outlet that captures and processes Electromagnetic Interference (EMI) signals to identify different operating states of electronic devices using a single sensing point, leveraging domain knowledge for semi-supervised learning to reduce the need for extensive data labeling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If distributed sensing with dedicated sensors per device is used, then device state detection accuracy is improved, but installation cost and complexity increase
Solution Approach 1:
The patent merges multiple sensing functions into a single sensing device that monitors electromagnetic interference from multiple electronic devices simultaneously. Instead of deploying dedicated sensors at each device, one sensing device captures EMI signals from the power line that carry information about multiple devices' operating states, thereby reducing installation complexity while maintaining detection capability
Solution Approach 2:
The sensing device is designed with universal functionality to detect operating states of various types of electronic devices (microwave ovens, coffee makers, blenders, etc.) through a single unit. The device can identify different appliance types and their respective states by analyzing characteristic EMI patterns, eliminating the need for device-specific sensors
2Measurement precision
If distributed sensing with dedicated sensors per device is used, then device state detection accuracy is improved, but maintenance cost increases
Solution Approach 1:
By combining multiple sensing functions into a single device, the patent reduces the total number of components that require maintenance. Instead of maintaining numerous distributed sensors across different locations, only one sensing device needs periodic calibration and repair, significantly lowering maintenance costs
3Measurement precision
If indirect sensing techniques with microphones, accelerometers, and video cameras are used, then device activity detection is improved, but installation cost and privacy concerns increase
Solution Approach 1:
The patent replaces mechanical and optical sensing systems (microphones, accelerometers, video cameras) with electromagnetic field sensing. By detecting EMI signals on the power line, the system achieves appliance activity detection without the complexity and privacy issues associated with audio-visual sensors
Solution Approach 2:
The patent uses electromagnetic interference on the power line as an intermediary carrier of device state information. Instead of directly observing devices with microphones or cameras, the sensing device extracts information from EMI signals that naturally propagate through the power infrastructure, providing an indirect but effective measurement approach
4Device complexity
If EMI-based sensing from a single point is used, then installation cost is reduced, but measurement precision for operating states deteriorates
Solution Approach 1:
The patent analyzes multiple parameters of the EMI signal including frequency spectrum characteristics, signal amplitude variations, and temporal patterns to distinguish different operating states. By examining these diverse signal parameters, the system achieves accurate device state detection from a single sensing point without requiring multiple physical sensors
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables accurate detection of operating states, providing richer feature sets for energy disaggregation and activity inference, while being low-cost and unobtrusive, with high accuracy across various appliances.
Implementation Method 1
captures and processes Electromagnetic Interference (EMI) signals to identify different operating states of electronic devices
Data Source
AI summary
An apparatus including a sensing device configured to be coupled to an electrical outlet is provided. The sensing device can include a data acquisition receiver configured to receive electrical noise via the electrical outlet when the sensing device is coupled to the electrical outlet. The electrical outlet can be electrically coupled to an electrical power infrastructure. One or more electrical devices can be coupled to the electrical power infrastructure and can generate at least a portion of the electrical noise on the electrical power infrastructure. The data acquisition receiver can be configured to convert the electrical noise into one or more first data signals. The apparatus also can include a processing module configured to run on a processor of a computational unit. The sensing device can be in communication with the computational unit. The processing module can be further configured to identify each of two or more operating states of each of the one or more electrical devices at least in part using the one or more first data signals. The two or more operating states of each electrical device of the one or more electrical devices can be each different user-driven operating states of the electrical device when the electrical device is in an on-power state. Other embodiments are provided.