MXene/WO₃ Sensor Array with Improved SNN Algorithm for Accurate Identification of Toxic Gases

Area of Science:

• Materials Science
• Chemical Sensing
• Artificial Intelligence

Background:

• Gas sensing is crucial for industrial production and food safety.
• MXene materials offer promising properties for gas sensor development.
• Accurate identification of toxic gases remains a challenge.

Purpose of the Study:

• To explore the gas classification capabilities of MXene-based gas sensors.
• To investigate the effect of WO3 nanoparticles on sensor performance.
• To develop an accurate method for toxic gas identification using a spiking neural network (SNN).

Main Methods:

• Synthesis of pure V2CTx MXene and MXene/WO3 nanocomposite.
• Fabrication of a 2x2 MXene-based gas sensor array.
• Integration with a memristive system-based SNN for gas classification.
• Gas sensitivity and stability testing at room temperature.

Main Results:

• MXene/WO3 nanocomposite enhanced NO2 sensor response.
• Rapid response/recovery times (74.5/149.0 s) and excellent stability were observed.
• The SNN-based method achieved 95.83% accuracy in identifying four toxic gases.
• The SNN demonstrated a 5% higher accuracy compared to other algorithms.

Conclusions:

• MXene-based gas sensors, particularly with WO3, show high potential for gas detection.
• The SNN offers a powerful and accurate approach for toxic gas identification.
• This technology can significantly enhance industrial safety and environmental monitoring.