Negative Group Delay Predictor Application for CO2 Gas Concentration Real-Time Forecasting

An innovative prediction method of CO2 gas concentration in real time by using the uncommon negative group delay (NGD) function is investigated. The environmental scenario of CO2 gas sensing is described. The design methodology of the uncommon NGD predictor in the function of the desired time advance and the gas concentration signal specifications is established. The analysis and transient characterization of the low-pass (LP) NGD function constituting the predictor under study are formulated. The testability of the innovative NGD predictor is validated by well-correlated simulations and experimentations. The NGD predictor calibration is presented with deterministic ramp signal tested on the proof-of-concept (POC) designed and prototype implemented on microcontroller-based digital platform. The characterization results show real-time signal advance of some minutes in good agreement between analog circuit LTSPICE simulation compared to experimental results obtained from the NGD predictor prototype. The NGD prediction feasibility study is confirmed by real environment demonstration based on commercial CO2 gas sensor acting as an electronic nose (e-nose). It was observed that the test results show the CO2 gas concentration prediction in several minutes time advance. Thanks to the design simplicity and flexibility to operate over wide range of time advance, the developed NGD predictor is very useful in the future for forecasting air quality and urban pollution.