Modelling complex measurement processes for measurement uncertainty determination

Abstract

Purpose

Measurement uncertainty is present in all measurement processes in the field of production engineering. However, this uncertainty should be minimized to avoid erroneous decisions. Present methods to determine the measurement uncertainty are either only applicable to certain processes and do not lead to valid results in general or require a high effort in their application. To optimize the costs and benefits of the measurement uncertainty determination, a method has to be developed which is valid in general and easy to apply. The paper aims to discuss these issues.

Design/methodology/approach

This paper presents a new technique for determining the measurement uncertainty of complex measurement processes. The approximation capability of artificial neural networks with one hidden layer is proven for continuous functions and represents the basis for a method for determining a measurement model for continuous measurement values.

Findings

As this method does not require any previous knowledge or expertise, it is easy to apply to any measurement process with a continuous output. Using the model equation for the measurement values obtained by the neural network, the measurement uncertainty can be derived using common methods, like the Guide to the expression of uncertainty in measurement. Moreover, a method for evaluating the model performance is presented. By comparing measured values with the output of the neural network, a range in which the model is valid can be established. Combining the evaluation process with the modelling itself, the model can be improved with no further effort.

Originality/value

The developed method simplifies the design of neural networks in general and the modelling for the determination of measurement uncertainty in particular.

Citation

Mueller, T., Huber, M. and Schmitt, R. (2020), "Modelling complex measurement processes for measurement uncertainty determination", International Journal of Quality & Reliability Management, Vol. 37 No. 3, pp. 494-516. https://doi.org/10.1108/IJQRM-07-2019-0232