A sub-microwatt self-powered fatigue sensor

Fatigue and overload of mechanical, civil and aerospace structures remains a major problem that can lead to costly repair and catastrophic failure. Long term monitoring of mechanical loading for these structures could reduce maintenance cost, improve longevity and enhance safety. However, the powering of these sensors during the lifetime of the monitored structure remains a major problem. In this paper we describe an implementation of a novel self-powered fatigue monitoring sensor. The sensor is based on the integration of piezoelectric transduction with floating gate avalanche injection. The miniaturized sensor enables self-powered continuous battery free monitoring and time-to-failure predictions of mechanical and civil structures. Measured results from a fabricated prototype in a 0.5 mu m CMOS process indicate that the device can compute cumulative statistics of electrical signals generated by the piezoelectric transducer, while consuming less that one microwatt of power. Furthermore, the sensor is capable of storing this information in non-volatile memory which makes it an attractive alternative when the converted electrical energy levels are low due to small mechanical force inputs. The current microchip is less than 2 square millimeters in area. The non volatile memory storage is coupled to a radio frequency (RF) identification microchip which allows the sensor to be interrogated asynchronously through a RF reader. We are currently developing a state vector machine (SVM), neural network based hardware to be included on the microchip. The SVM hardware will enable low-power processing and computation of the incoming mechanical loading cycle data.