Online Validation of Soft Calibration Circuit for Capacitance Pressure Sensor Santhosh K V a , B K Roy b a Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal India, Contact: kv.santhu@gmail.com. b Department of Electrical Engineering, National Institute of Technology Silchar, India. Support Vector Machine (SVM) based intelligent pressure measurement technique operating in harsh envi- ronments is proposed in this paper. The technique that automatically calibrates, linearizes and compensates for the nonlinear response characteristics and complex nonlinear dependency of the sensor characteristics on elasticity modulus, thickness, dielectric materials, and temperature. To show the potential of the proposed soft calibration circuit, it is subjected to simulation. Further, validated online by real life data. Results show that the proposed intelligent technique has fulfilled the objectives. Keywords : Adaptive, Calibration, Nonlinear Estimation, Sensor Modelling, Support Vector Machine. 1. INTRODUCTION With the steam age came the demand for pres- sure measuring instruments. Bourdon tubes or bellows, where mechanical displacements were transferred to an indicating pointer were the first pressure instruments, and are still in use today. Pressure metrology is the technology of transducing pressure into an electrical quan- tity. Normally, a diaphragm construction is used with strain gauges either bonded to, or diffused into it, acting as resistive elements. Under the pressure-induced strain, the resistive values change. In capacitive technology, the pressure diaphragm is one plate of a capacitor that changes its value since pressure-induced displacement. Among all, capacitive technolo- gies play an increasingly important role in the fields of industrial and automotive sensors be- cause of its low power consumption and high sensitivity. However, its highly nonlinear re- sponse characteristics give rise to several diffi- culties. Literature survey reveals a lot of reported work in [1], linearization of pressure sensors for a cer- tain range is carried on with analog circuits. A generalised method for linearization of sen- sors using neural network is discussed in [2]. A computing method for linearization of pres- sure sensor is reported in [3] and compensa- tion for zero drift is carried on using redun- dant sensors. In [4], calibration of fibre optic pressure sensor is carried on using signal pro- cessing. Calibration of pressure sensor using neural network algorithm and its compensation for temperature changes is carried on using re- dundant sensor [5]. In [6], an implementation of calibration circuit for pressure transmitter is discussed. Design of calibration circuit for pressure transmitter using HART protocol is reported in [7]. Calibration of CPS using analog circuits is re- ported in [8]. In [9], calibration of pressure sen- sor using digital signal processing techniques is discussed. A method for calibration of pressure sensor is discussed in [10]. In [11], calibration of CPS using functional link artificial neural network is discussed. Laguerre neural network algorithm is reported for calibration of CPS is reported in [12][13]. In [14], a calibration tech- nique for reluctance type pressure transducer is discussed using analog circuits. In [15], re- lation between diaphragm properties and CPS output is discussed. In [16], effect of dielec- 62 International Journal of Information Processing, 8(2), 62-70, 2014 ISSN : 0973-8215 IK International Publishing House Pvt. Ltd., New Delhi, India