Polynominal Identification of Strain Gauge Thermal Output for the Determination of Deformations with Neural Networks

Strain gauges are used in different areas, especially in the design and development of new technical constructions and their model testing. Also, the strain gauges are incorporated in functional parts of many instruments and devices. They are mostly used as sensors in transducers designed to measure such mechanical quantities as forces, moments, pressures, accelerations etc. They have an important role in shipbuilding and in marine generally. In this paper, we have suggested and shown an approach to the identification of strain gauges thermal output curve on the example of the product available at the market. Neural network simulated in MatLab has been applied. The neural network was adapted to simulate real system with 10-9 order of magnitude error. As it is well known, strain gauges measure deformations of 10-6 order of magnitude. It is obvious that the error of network can not influence the measurement results, because of its being smaller by three orders of magnitude