Research About Electronic Nose System For Halitosis Detection Based On FPGA

In real life,people often suffer from bad breath.Bad breath problem has seriously affected people's normal life and work.With the improvement of the quality of people's life,bad breath has attracted more and more attention.Research shows that volatile sulfide in the mouth is the main source of bad breath.It is important to realize the type and concentration of volatile sulfides in the mouth for definite diagnosis and further treatment.Therefore,the electronic nose system based on metal oxide semiconductor sensor array,FPGA,BP artificial neural network is proposed,which can be used to assist doctors in diagnosing halitosis.In this article,H2 S and CH3 SH gas are mixed with air to simulate the breath of halitosis patients.The qualitative and quantitative analysis on the simulated gas is made by electronic nose system.First,the typical electronic nose system is studied.A typical electronic nose system generally includes three parts: sensor array,data acquisition system and pattern recognition algorithm.According to the structure and working principle of electronic nose,the system block diagram and working process of the electronic nose system for halitosis detection are designed.The system consists of gas acquisition system and pattern recognition system.Secondly,The gas acquisition system consists of two parts: sensor circuit and data acquisition circuit.The sensor array and the small signal amplification circuit are assembled on a printed circuit board to form a sensor circuit,which is placed in a glass container,and the gas is sampled under the condition of constant temperature and humidity.The data acquisition system which is composed of a A/D conversion circuit and a communication circuit is connected with a sensor circuit through a cable to complete data acquisition.Using UART(Universal Asynchronous receiver/transmitter)to realize the RS232 communication to transmit data to PC.Finally,the working principle and hardware implementation of BP neural network are studied.MATLAB PC software is used to handle the data from gas acquisition system through BP neural network.A mathematical model between gas and species as well as a mathematical model between gas and concentration is established.Then,the type and concentration of the tested gas which are achieved through these models and test gas response signal are compared with the actual type and concentration in order to verify the accuracy and reliability of the system.The experimental results show that the electronic nose system using the gas sensor array and the pattern recognition algorithm based on software simulation has proved to be able to identify the H2 S and CH3 SH and to detect concentration of H2 S.To sum up,the electronic nose system based on FPGA developed in this paper can be feasible in the aspects of qualitative and quantitative analysis of a single gas.The utility of electronic nose needs more research work,which has important research significance and broad prospects for development.