MOS Sensor Array with Hybrid ML for Gas Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Legacy gas detection methods are difficult to miniaturize and require extensive data processing, making them unsuitable for micro-environmental monitoring and IoT applications, especially in dense wireless sensor networks due to high power requirements.
Innovation Solution
A hybrid multi-staged machine learning system combining metal oxide semiconductor (MOS) sensors with regression models and artificial neural networks to identify gases, allowing for efficient gas detection and concentration estimation in a miniaturized form.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If legacy gas detection methods are used, then gas detection capability is achieved, but device size becomes large and power consumption increases
Solution Approach 1:
The gas detection system is segmented into multiple independent MOS sensor elements, each detecting different gas components. This segmentation allows for miniaturization while maintaining detection capability, as each sensor element can operate independently with lower power requirements compared to a single complex detection system.
Solution Approach 2:
The patent replaces complex mechanical gas detection systems with electronic/MOS-based detection. The MOS sensor elements use electrical resistance changes to detect gas presence, eliminating the need for bulky mechanical components and reducing power consumption while maintaining or improving detection precision.
2Measurement precision
If legacy gas detection methods are used, then gas detection capability is achieved, but device complexity increases
Solution Approach 1:
The detection system is divided into multiple simple MOS sensor elements rather than one complex system. Each sensor element has a straightforward resistance-based detection mechanism, reducing individual component complexity while achieving comprehensive gas detection through the array of sensors.
Solution Approach 2:
The patent utilizes changes in electrical resistance parameters of MOS sensors to detect gas presence. This parameter-based approach simplifies the detection mechanism compared to legacy methods, as it relies on straightforward electrical measurements rather than complex mechanical or optical systems.
3Measurement precision
If extensive data processing is used, then gas identification accuracy is improved, but processing time and computational power increase
Solution Approach 1:
The system uses a subset of sensor elements and selective data processing rather than analyzing all sensor data comprehensively. This partial action approach maintains gas identification accuracy for target gases while reducing processing time and computational requirements by focusing only on relevant detection signals.
Solution Approach 2:
The patent extracts and processes only the essential detection signals from the sensor array that are relevant to identifying target gases. By taking out and processing only the necessary data elements rather than performing extensive analysis on all sensor outputs, the system achieves accurate gas identification with reduced processing time.
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 and efficient gas detection and concentration estimation in a compact, low-power form, suitable for micro-environmental monitoring and IoT applications, reducing the complexity and power demands of existing systems.
Implementation Method 1
a set of heterogeneous metal oxide semiconductor (MOS) sensors to provide different response patterns for the presence of different gases
Data Source
AI summary
Embodiments herein relate to gas identification with a gas identification apparatus having a plurality of metal oxide semiconductor (MOS) sensors. In various embodiments, a gas identification apparatus may include a set of heterogeneous MOS sensors to provide different response patterns for the presence of different gases and an identification engine coupled with the sensors, and having a plurality of regression models and one or more artificial neural networks, to analyze a response pattern to identify presence of a gas, based at least in part on a plurality of property measurements of the MOS sensors when exhibiting the response pattern, and using one or more of the plurality of regression models and the one or more artificial neural networks. Other embodiments may be described and/or claimed.