RF Gas Sensor Array With ML Compensation for Cross-Sensitivity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Microwave sensors face challenges in detecting specific gases in complex mixtures due to cross-sensitivities and environmental interferences like humidity and temperature fluctuations, limiting their deployability in real-world conditions.
Innovation Solution
A gas sensor array system using a combination of RF passive sensors and a trained machine learning model to mitigate cross-sensitivities and environmental interferences, enabling accurate detection of gases in complex mixtures by correlating sensor responses with environmental parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If microwave sensors are used for gas detection, then measurement sensitivity is improved, but cross-sensitivities to multiple gas components and environmental interferences worsen detection accuracy
Solution Approach 1:
The patent divides the detection task into multiple independent sensor channels, each functionalized with a different sensitive material tailored to detect specific gas components. This segmentation allows each sensor to specialize in detecting particular gases while the collective array handles complex mixtures, resolving the contradiction between high sensitivity and accuracy in complex environments.
Solution Approach 2:
The patent changes the chemical parameters of the sensor surfaces by applying different sensitive materials (metal oxides, polymers, carbon-based materials) with distinct selectivity characteristics. This parameter variation enables the sensor array to differentiate between multiple gas components simultaneously, maintaining high sensitivity while achieving accurate detection in complex gas mixtures through pattern recognition algorithms.
2Use of energy by moving object
If passive microwave sensors are used, then energy consumption is reduced, but susceptibility to environmental interferences like humidity and temperature increases
Solution Approach 1:
The patent incorporates environmental sensors that continuously monitor humidity and temperature conditions, feeding this information back to the data processing system. The system uses this feedback to compensate for environmental interferences in the gas detection signals, allowing passive microwave sensors to maintain low energy consumption while achieving robust detection accuracy despite environmental variations.
Solution Approach 2:
The patent employs composite sensor structures combining microwave-sensitive materials with environmentally stable substrates and protective layers. These composite materials provide both the desired microwave interaction for gas detection and resistance to environmental factors like humidity and temperature, enabling passive sensors to operate reliably in real-world conditions without requiring active compensation.
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
The system provides accurate, selective, and sensitive gas detection in real-world conditions with low energy consumption, effectively discriminating specific gases despite environmental interferences.
Implementation Method 1
measuring physical properties like wave propagation, wave speed (physical gas sensors)
Implementation Method 2
Microwave transduction-based sensors with their high operating frequency (300 MHz - 300 GHz)
Implementation Method 3
the microwave sensors detect, and measure gases based on the physical-chemical interactions. They are composed of two parts: a sensitive material and a transducer. The sensitive material, when exposed to the surrounding atmosphere, interacts with target gas. The interaction induces a change in one or more physicochemical properties of the material, such as electrical conductivity, permittivity
Data Source
Figure 1~2A
Figure 2B~3
Figure 4~5
AI summary
Gas radiofrequency sensing system and method for sensing at least one gas present in a mixture of gases and vapors, and environment interferents, comprise a plurality of radiofrequency "RF" passive sensors (100, 101, 102, 103, 104) and a trained machine learning model to predict from the trained machine learning model at least one first quantitative value corresponding to a concentration of one target environmental gas from said mixture of gases and vapors and at least one second quantitative value corresponding to an interferent parameter corresponding to operating conditions of the gas sensing system.