Simultaneous Flow and Thermal Conductivity Sensing on a Single Chip Using Artificial Neural Networks

Abstract

A thin-film CMOS MEMS thermal sensor has been designed, fabricated and tested with the addition of through-membrane isolating holes. These holes have been shown to enhance the discrimination towards gases with differing thermal conductivity in the presence of flow. Using three on-membrane resistors as inputs, linear statistical methods alongside Artificial Neural Network pattern recognition techniques have been investigated for decoupling the two parameters of thermal conductivity and flow rate using a single sensor. In addition to this, the addition of the membrane holes increases the sensitivity towards flow rate by 10 times and the sensitivity towards thermal conductivity by 2 times. This sensor design coupled with well-known post-processing techniques will enable a new generation of multi-parameter sensing solutions.

Micromachined Thermal Gas Sensors—A Review

“…Gardner et al [ 114 ] used a mechanical design to increase gas sensitivity of a tungsten heater as well as post-processing using Artificial Neural Networks (ANN) and liner statistical methods to simultaneously measure percentage CO 2 (through thermal conductivity) and flow.…”

Thermal Conductivity Gas Sensor with Enhanced Flow-Rate Independence

“…Currently, as one of the important detection principles of MEMS sensors, thermal detection has been widely used in fluid sensing fields, especially in gas-related detection, such as gas flow [ 1 , 2 , 3 ], thermal conductivity [ 4 , 5 , 6 ], shear-stress [ 7 , 8 , 9 ], and vacuum [ 10 , 11 , 12 ], etc. Compared to normal chemical sensors, thermal MEMS sensors have the advantages of broad-spectrum, fast response, low power consumption, and long-term stability, becoming a major, long-standing research focus [ 13 , 14 , 15 ].…”