Presentation Details
  1. Home
  2. Presentation List
  3. Presentation Details
MEMS Gas sensor array self-detection and self-correction algorithm for environment-aware microsystems
ID：18 View Protection：ATTENDEE Updated Time：2026-09-11 22:55:08 Hits：33 Poster Presentation

Start Time：Pending（Asia/Shanghai）

Duration：Pending

Session：No Session »

No files

Abstract
近年来，结合MEMS气体传感器阵列与模式识别算法的环境感知机器嗅觉微系统能够监测气体，并在工业生产、医疗诊断和战场侦察等领域具有重要应用价值。 然而，气体传感器容易出现故障，如功率丢失和长时间运行时输出恒定，导致信号失真，影响后续模式识别算法的性能。 因此，本文提出了一种轻量级的微系统自我检测和自我校正算法。该算法基于 CNN-LSTM神经网络，能够有效识别常见的单传感器故障，并通过分析不同传感器输出之间的时空相关性来修正数据。本文完成了该算法在微系统平台上的嵌入式实现，并测试其功能和性能。测试结果显示，所提算法的故障检测准确率达到95.12%，修正后数据与无故障数据之间的平均绝对百分比误差为5。13%。
 
Keywords
environment-aware microsystems; MEMS gas sensor array; self-detection and self-correction algorithm; embedded implementation
Speaker
Wenyan Li
student Harbin Institute of Technology

Submission Author
Wenyan Li Harbin Institute of Technology
Bing Liu Harbin Institute of Technology;School of Electronics and Information Engineering
Submit Comment
Verify Code Change Another
All Comments
Important Date

  • Conference Date

    Nov 06

    2026

    to

    Nov 08

    2026

  • Oct 15 2026

    Draft paper submission deadline

Sponsored By
IEEE Instrumentation and Measurement Society
Organized By
Sichuan University
Contact Information
Login to view full contact details
Previous Conferences