MEASUREMENT UNCERTAINTY CONTRIBUTION TO THE MLP NEURAL NETWORK LEARNING ALGORITHM APPLIED TO AERODYNAMIC EXTERNAL BALANCE CALIBRATION CURVE FITTING

Journal Title: Metrology and Measurement Systems - Year 2007, Vol 14, Issue 1

Abstract

The aim of this study is to fit a calibration curve to a multivariate measurement system considering uncertainty in load measurements. The experimental data are generated from the calibration of the aerodynamic external balance of the subsonic wind tunnel n.o 2, at the Brazilian Institute of Aeronautics and Space. To fit the calibration curve, Multilayer Perceptron Artificial Neural Networks are submitted to the learning process. Studies employing several different architectures were carried out in order to improve the MLP convergence. The uncertainty in measurements is taken into consideration, through the modification of the learning algorithm, which in its classical approach, considers the data points free from error sources. The results of both methodologies, learning algorithm endowed with and without uncertainties, are compared. The artificial neural network performance in predicting future calibration data is explored through the simulation process.

Authors and Affiliations

I. BARBOSA, E. HERNANDEZ, M. REIS, O. MELLO

Keywords

Related Articles

INFLUENCE OF SELECTED FACTORS FOR LOCALIZATION ACCURACY IN THE OPTICAL VORTEX INTERFEROMETER

Optical vortices were intensively studied during the last decade. In the literature there are papers presenting applications of the optical vortices. The regular net of optical vortices generated by the three plane waves...

APPLICATION OF SOM IN CLASSIFICATION OF EGG SIGNALS

The report presents problems associated with computer aided gastric diagnosis. The subject of the study are electrogastrographic (EGG) signals (non-invasively measured electrical signals generated by the human stomach)....

OPTIMAL MEASUREMENT POLICY FOR DECISION MAKING: A CASE STUDY OF QUALITY MANAGEMENT BASED ON LABORATORY MEASUREMENTS

Measurement information generates value, when it is applied in the decision making. An investment cost and maintenance costs are associated with each component of the measurement system. Clearly, there is - under a given...

MIGRATION MEASUREMENTS FROM PLASTIC PACKAGING: A SIMULATION STUDY ON INFLUENCE OF INITIAL CONCENTRATION PROFILE<br />

Migration of components from plastic packaging into foodstuffs or into medicines is a very important issue, concerning public health. Using experimental techniques, like gas chromatography-mass spectrometry, these essays...

THE DEPENDENCE OF BRASS HARDNESS MEASUREMENT SYSTEM ON TIME

Measurement system analysis (MSA) was used for estimation of hardness (HBS) measure- ment system capability. The time dependence of capability was evaluated. Experimental material Cu-Zn-Al cast alloy was used as shape me...

Download PDF file
  • EP ID EP160107
  • DOI -
  • Views 82
  • Downloads 0

How To Cite

I. BARBOSA, E. HERNANDEZ, M. REIS, O. MELLO (2007). MEASUREMENT UNCERTAINTY CONTRIBUTION TO THE MLP NEURAL NETWORK LEARNING ALGORITHM APPLIED TO AERODYNAMIC EXTERNAL BALANCE CALIBRATION CURVE FITTING. Metrology and Measurement Systems, 14(1), 101-116. https://europub.co.uk/articles/-A-160107