Case Number 103034 - An Active Fiber Continuous Sensor
Contact: Geoffrey Pinski
Description: The artificial neural system (ANS) uses a large array of continuous sensors with a minimum number of data acquisition channels. The artificial neural system detects the damage and locates it within the grid of the array. Each continuous sensor will form a neuron and the array will act as a biological neural system. The neurons will measure the dynamic strains and these signals will be interpreted to indicate if the structure is operating within the limits of its design specifications, and if there is any damage occurring to the structure.
The Artificial Neural System (ANS) provides highly distributed sensing and massively parallel signal processing and significantly improves the sensing of acoustic waves or other anomalous events while tremendously simplifying the signal processing instrumentation as compared to conventional sensors.
The primary use of the ANS is to detect and quantify cracks and damage in a structure. The ANS can detect the high frequency acoustic emissions and resulting waves associated with damage propagation. The major advantages are as follows:
The sensitivity of acoustic emission sensing is improved
The instrumentation required for acoustic emission sensing is simplified
The ANS provides parallel monitoring and processing of signals from tens to hundreds of neurons
The ANS provides highly distributed sensor coverage on a structure
Individual continuous sensors can be formed into an artificial neural system of different configurations by using the continuous sensor approach