MEMS Seismic Sensor with FPAA-Based Interface Circuit for Frequency-Drift Compensation Using ANN

Electrochemical micro-electro mechanical systems (MEMS) seismic sensor is limited by its nonideality of frequency dependent characteristics hence interface circuits for compensation is necessary. The conventional compensation circuits are limited by high power consumption, bulky external hardware. These digital circuits are limited by inherent analog to digital conversions which consumes significant power, acquires more size and limits processing speed. This system presents field programmable analog array (FPAA) (Anadigm AN231E04) based hardware implementation of artificial neural network (ANN) model with minimized error in frequency drift in the range of 3.68% to about 0.64% as compared to ANN simulated results in the range of 23.07% to 0.99%. Single neuron consumes power of 206.62 mW with minimum block wise resource utilization. The proposed hardware uses all analog blocks removing the requirement of analog to digital converter and digital to analog converter, reducing significant power and size of interface circuit and enhancing processing speed. It gives the reliable, SMART MEMS seismic sensor with ANN-based intelligent interface circuit implemented in FPAA hardware.