A neural flow estimator

This paper proposes a new way to estimate the flow in a micromechanical flow channel. A neural network is used to estimate the delay of random temperature fluctuations induced in a fluid. The design and implementation of a hardware efficient neural flow estimator is described. The system is implemented using switched-current technique and is capable of estimating flow in the μl/s range. The neural estimator is built around a multiplierless neural network, containing 96 synaptic weights which are updated using the LMS¹-algorithm. An experimental chip has been designed that operates at 5 V with a total current consumption of 2 mA, resulting in a power consumption of 10 mW. The dimensions of the clip core are 3 mm×4.5 mm