Modeling, simulation and temperature compensation of porous polysilicon capacitive humidity sensor using ANN technique

Abstract The porous polysilicon capacitive sensor used for measuring relative humidity has the advantages of low cost, ease of fabrication and CMOS compatibility. However, the capacitance of the sensor, which is a function of concentration of water vapour, also depends on ambient temperature. Thus, variation of ambient temperature causes error in the performance of sensor outputs. In this paper, two ANN models have been developed. The first model is used to simulate the behavior of the capacitive humidity sensor (CHS). This model can also be used for on line monitoring of the fault of the sensor. The second model is based on inverse modeling, which can be used to compensate the effect of ambient temperature error. It is found from the simulation studies that the error of the direct model is within ±2% of full scale and for the inverse model the error is within ±0.5% of full scale over a temperature range from 20 to 70 °C. A hardware implementation scheme for realization of the CHS model is also proposed.

[1]  F. N. Trofimenkoff,et al.  Transducer output signal processing using an eight-bit microcomputer , 1986, IEEE Transactions on Instrumentation and Measurement.

[2]  P. G. Han,et al.  Study of luminescent porous polycrystalline silicon thin films , 1996 .

[3]  Hei Wong,et al.  Sensitivity and stability of porous polycrystalline silicon gas sensor , 2001 .

[4]  Hiranmay Saha,et al.  Role of parasitics in humidity sensing by porous silicon , 2001 .

[5]  Pasqualina M. Sarro,et al.  Comparison of porous silicon, porous polysilicon and porous silicon carbide as materials for humidity sensing applications , 2002 .

[6]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[7]  Hiranmay Saha,et al.  A hygrometer comprising a porous silicon humidity sensor with phase-detection electronics , 2003 .

[8]  J. Seto.  The electrical properties of polycrystalline silicon films , 1975 .

[9]  A. Bernieri,et al.  A neural network approach for identification and fault diagnosis on dynamic systems , 1993 .

[10]  Ning Wang,et al.  Porous polycrystalline silicon conductivity sensor , 1999 .

[11]  Ganapati Panda,et al.  An intelligent pressure sensor using neural networks , 2000, IEEE Trans. Instrum. Meas..

[12]  Hei Wong,et al.  Investigation of the surface silica layer on porous poly-Si thin films , 2001, Microelectron. Reliab..

[13]  Octavian Postolache,et al.  Minimizing temperature drift errors of conditioning circuits using artificial neural networks , 1998, IEEE Trans. Instrum. Meas..

[14]  Theodore I. Kamins,et al.  Hall Mobility in Chemically Deposited Polycrystalline Silicon , 1971 .