The selective detection and classification of NH₃ and H₂S gases with H₂S gas interference based on conventional SnO₂ thin film sensors is still the main problem. In this work, three layers of SnO₂/Pt/WO₃ nanofilms with different WO₃ thicknesses (50, 80, 140, and 260 nm) were fabricated using the sputtering technique. The WO₃ top layer were used as a gas filter to further improve the selectivity of sensors. The effect of WO₃ thickness on the (NH₃, H₂, and H₂S) gas-sensing properties of the sensors was investigated. At the optimal WO₃ thickness of 140 nm, the gas responses of SnO₂/Pt/WO₃ sensors toward NH₃ and H₂ gases were slightly lower than those of Pt/SnO₂ sensor film, and the gas response of SnO₂/Pt/WO₃ sensor films to H₂S gas was almost negligible. The calcification of NH₃ and H₂ gases was effectively conducted by machine learning algorithms. These evidences manifested that SnO₂/Pt/WO₃ sensor films are suitable for the actual NH₃ detection of NH₃ and H₂S gases.

主要的问题仍然是基于传统的SnO ₂薄膜传感器对具有H ₂ S气体干扰的NH ₃和H ₂ S气体进行选择性检测和分类。在这项工作中，使用溅射技术制造了三层具有不同WO ₃厚度（50、80、140和260 nm）的SnO ₂ / Pt / WO ₃纳米膜。WO ₃顶层用作气体过滤器，以进一步提高传感器的选择性。WO ₃厚度对（NH ₃，H ₂和H _2的影响S）研究了传感器的气敏特性。在最佳WO ₃厚度为140 nm时，SnO ₂ / Pt / WO ₃传感器对NH ₃和H ₂气体的气体响应略低于Pt / SnO ₂传感器膜的气体响应，而SnO ₂ /对于H ₂ S气体，Pt / WO ₃传感器膜几乎可以忽略不计。通过机器学习算法可以有效地进行NH ₃和H ₂气体的钙化。这些证据表明，SnO ₂ / Pt / WO ₃传感器膜适合实际的NH ₃检测NH ₃和H ₂ S气体。