Development of a Chemical Identification Algorithm for Gas Chromatography/Ion Mobility Spectrometry

Neural networks for whole ion mobility spectra from a standardized data base of 1295 spectra for 195 chemicals at various concentrations showed 92% successful classifications by functional group was throughout a range of concentrations. Application of neural networks in a two tier design where chemicals were first identified by class and as individual substances eliminated all but one false positive out of 161 test spectra. These findings establish that ion mobility spectra, even with low resolution instrumentation, contain sufficient detail to permit development of automated identification systems. Under certain conditions of temperature and moisture in the IMS drift tube, the identification of “blind unknowns” was better than 90%. This suggests that the volatile organic analyzer can be extended to completely unknown chemicals during air quality monitoring.