Practical aspects of application of artifi cial intelligence in metrology

Artifi cial intelligence as one of the main elements of digital transformation and promising directions of its application in metrology are considered. The main attention is paid to the application of artifi cial neural networks as a part of measuring instruments and measurement systems for obtaining measurement results in cases when the measurement function is unknown, not suffi ciently defi ned or too complicated for algorithmic formalization. More often in practice we meet problems with partially uncertain function, when in addition to the deterministic basis there is an additional unknown component that has a signifi cant impact on the measurement result. A simulation experiment was conducted to solve such a measurement problem using a neural network model. In the experiment, a measurement function with a linear deterministic basis and an additional nonlinear component of about 10 % of the relative standard deviation, that was implied by the unknown when the model was created, was used. The results of the experiment confi rmed the practical possibility and high effi ciency of using artifi cial neural networks to solve such measurement problems. The neural network model in the conditions of a noisy training sample, corresponding to real measurement conditions, almost completely restored the measurement function despite the fact that a linear neural network model was used, and the additional component of the measurement function was nonlinear. In this particular experiment, due to the use of neural network, the accuracy of measurements was improved by about an order of magnitude. Access to the machine code implementing this simulation experiment is provided.

1. K. Schwab. The Fourth Industrial Revolution, New York, Currency Books, 2017, 192 p.

2. Kroshkin A. N., Lishchuk A. N. A new technology of nonseparated measurement of oil well production. Automation in Industry, 2014, no. 5, pр. 25–29. (In Russ.)

3. Goodfellow I., Bengio Y., Courville A. Deep learning, Cambridge, MIT Press, 2016, 800 p.

4. Henry M., Tombs M., Zamora M., Zhou F. Flow Measurement and Instrumentation, 2013, vol. 30, рp. 112–122. https://doi.org/10.1016/j.flowmeasinst.2013.01.003

5. Kostarev K. G., Torohova S. V. Contraction of aqueous solutions of alcohols, salts acids and bases. Bulletin of Perm University. Physics, 2022, no. 1, рp. 5–15. (In Russ.) https://doi.org/10.17072/1994-3598-2022-1-05-15

6. D. I. Mendeleev. Rassuzhdenie o soedinenii spirta s vodoyu [The reasoning behind combining alcohol and water]. St. Peterburg, Obshchestvennaya pol’za Publ., 1865, 120 p.

7. V. M. Kapustin, E. A. Chernysheva, O. F. Glagoleva et al. Not additive changes of properties of hydrocarbon systems while mixing, Oil Processing and Petrochemistry, 2017, no. 4, pр. 3–9. (In Russ.)

8. Smyshlyaeva Y. A., Ivanchina E. D., Kravtsov A. V., Truong C. T., Phan F. Razrabotka bazy dannyh po oktanovym chislam dlya matematicheskoj modeli processa kompaundirovaniya tovarnyh benzinov [Development of a database of octane numbers for a mathematical model of the compounding process of commercial gasoline]. Bulletin of the Tomsk Polytechnic University, 2011, vol. 318, no. 3, pp.75–80. (In Russ.)

9. Gafarov F. M., Galimyanov A. F. Iskusstvennye nejronnye seti i prilozheniya [Artifi cial neural networks and applications]: textbook, Kazan, University press, 2018, 121 p. (In Russ.)

10. Antonio Gulli, Sujit Pal. Deep Learning with Keras. Implementing deep learning models and neural networks with the power of Python, Birmingham, Packt Publishing, 2017, 318 p.