Algoritmos inteligentes para auto-correção, auto-verificação e auto-validação de medidas em sensores

This work presents a set of intelligent algorithms with the purpose of correcting calibration errors in sensors and reducting the periodicity of their calibrations. Such algorithms were designed using Artificial Neural Networks due to its great capacity of learning, adaptation and function approximation. Two approaches willbe shown, the firstone uses Multilayer Perceptron Networks to approximate the many shapes of the calibration curve of a sensor which discalibrates in different time points. This approach requires the knowledge of the sensor s functioning time, but this information is not always available. To overcome this need, another approach using Recurrent Neural Networks was proposed. The Recurrent Neural Networks have a great capacity of learning the dynamics of a system to which it was trained, so they can learn the dynamics of a sensor s discalibration. Knowingthe sensor s functioning time or its discalibration dynamics, it is possible to determine how much a sensor is discalibrated and correct its measured value, providing then, a more exact measurement. The algorithms proposed in this work can be implemented in a Foundation Fieldbus industrial network environment, which has a good capacity of device programming through its function blocks, making it possible to have them applied to the measurement process

Uma metodologia para redução de incertezas em sistema de medição de vazão de óleo e gás

The objective of this research is to discuss about the need for implementation of new alternatives for the implementation on the metrological control: on the findings of initial and subsequent measurements, the control procedures of measurement uncertainty applied in assessing the loss or remains found in handling operations of bulk liquids, when used turbine meters used in measuring the tax on the business of Petrobras, due to the current environment of legal metrology and scientific, both domestic and international. We aim, with these alternatives: standardizing the minimization of random and systematic errors, the estimate of the remaining errors, as well as the management control of metrological calibration procedures, control of measurement uncertainty, and contribute to the change in the form of performance of legal metrology and scientific disseminating new information to change management of metrological control, objectively focused on aspects of supervision in implementing these activities in the control of the uncertainties of measurement used in our processes in the fiscal measurement system Petrobras. Results are presented, information and comments on the influence of measurement uncertainty in the current results of the fiscal and transfer of custody. This will emphasize the need, among other things, improvement and expansion of metrological control monitored by setting a better meet demand, calibration equipment and measuring instruments for Petrobras. Finally, we intend to establish the need for improving the method of evaluation of the data meter applied to the current management control of measurement uncertainty by proposing a methodology for addressing the problem, as well as highlighting the expected results.