28

Protecting technical systems from loss of performance and failure, as well as the
need to comply with safety and efficiency requirements, poses more and more important problems
in diagnosing errors in measuring instruments. When designing smart sensors, one should take into
account the possibility of self-diagnostics of the system to prevent accidental failures of measuring
instruments. In the paper, the most used methods for detecting faults are investigated, on the
basis of which a classification of fault detection methods is given. The possibilities of using these
methods in intelligent measuring instruments are disclosed. As part of the work, the diagnostic
functions of autonomous sensors are considered, where methods of structural redundancy are
used, characterized by the fact that the sensitive elements of the sensor are located directly in the
technological process.
The developed measurement systems with several redundant sensors have a sufficiently low
uncertainty of the measured values even in complex technological processes. Frequently occurring
hardware and software failures in measuring instruments are identified, on the basis of which the
rules between errors and symptoms are determined. The function of self-diagnostics of the system
based on neural networks is proposed. A block diagram of a method for detecting errors based on
a process model is given. The paper considers the use of algorithms for determining faults in
measuring instruments based on neural networks. Based on the artificial intelligence algorithm, a
method for diagnosing measuring instruments has been improved, which is able to detect faults in
integrated circuits of instrumentation and primary converter with acceptable accuracy.
 

  • Web Address
  • DOI
  • Date of creation in the UzSCI system13-09-2023
  • Read count28
  • Date of publication11-09-2023
  • Main LanguageIngliz
  • Pages173-179
English

Protecting technical systems from loss of performance and failure, as well as the
need to comply with safety and efficiency requirements, poses more and more important problems
in diagnosing errors in measuring instruments. When designing smart sensors, one should take into
account the possibility of self-diagnostics of the system to prevent accidental failures of measuring
instruments. In the paper, the most used methods for detecting faults are investigated, on the
basis of which a classification of fault detection methods is given. The possibilities of using these
methods in intelligent measuring instruments are disclosed. As part of the work, the diagnostic
functions of autonomous sensors are considered, where methods of structural redundancy are
used, characterized by the fact that the sensitive elements of the sensor are located directly in the
technological process.
The developed measurement systems with several redundant sensors have a sufficiently low
uncertainty of the measured values even in complex technological processes. Frequently occurring
hardware and software failures in measuring instruments are identified, on the basis of which the
rules between errors and symptoms are determined. The function of self-diagnostics of the system
based on neural networks is proposed. A block diagram of a method for detecting errors based on
a process model is given. The paper considers the use of algorithms for determining faults in
measuring instruments based on neural networks. Based on the artificial intelligence algorithm, a
method for diagnosing measuring instruments has been improved, which is able to detect faults in
integrated circuits of instrumentation and primary converter with acceptable accuracy.
 

№ Author name position Name of organisation
1 Ruziev U.A. researcher TSTU
№ Name of reference
1 R. Isermann. Fault-diagnosis systems. An introduction from fault detection to fault tolerance. “Springer-Verlag”, Berlin, 2006. 365.
2 H. Singh., A.N. Meyer., E.J. Thomas. “The frequency of diagnostic errors in outpatient care: estimations from three large observational studies involving US adult populations”, 2014. 727.
3 O. Gultekin., E. Cinar., K. Ozkan., A. Yazici. Multisensory data fusion-based deep learning approach for fault diagnosis of an industrial autonomous transfer vehicle. “Expert Systems with Applications”, 2022. 117055.
4 B. Jiang., L. Wang., Y.C. Soh. An adaptive technique for robust diagnosis of faults with independent effects on system outputs. “International journal of control”, 2002. 792.
5 S.V. Kas’yanov., A.G. Kondrashov., D.T. Safarov. “Regulation of geometrical parameters deviations of automotive components parts through diagnostic measurements organization procedia engineering”, 2017. 206.
6 N.R. Yusupbekov., U.A. Ruziev., M.K Shodiev. Multi-model intellectual virtual Analyzers of Parameters of Technological Processes. Journal "Advances in Intelligent Systems and Computing. “Springer Nature”, Switzerland, 2021. 125
7 K. Stralen., V. Stel., J. Reitsma. Diagnostic methods I: Sensitivity, specificity, and other measures of accuracy. “Kidney international”, doi10.1038/ki, 2009. 1257.
8 F. Fiorenzo., G. Maurizio., M. Domenico., M. Luca., P. Barbara. Self-diagnostic tools. “Distributed large-scale dimensional metrology”, doi 10.1007/978-0-85729-543-9_6, 2011. 141.
9 S. Zhiyuan., W. Miao. “Self-test and self-calibration of digital closed-loop accelerometers, sensors”. Published online 2022 Dec doi : 10.3390/s22249933, Basel, 2022.
10 Y. Wang., A. Yang., Z. Li., X. Chen., P. Wang., H. Yang. Blind drift calibration of sensor networks using sparse bayesian learning. “IEEE Sensors Journal”, 2016. 6249.
11 C. Rojas., P. Morell. Guidelines for Industrial Ethernet infrastructure implementation: A control engineer's guide. Cement industry technical conference. “IEEE-IAS/PCA 52nd”, 2010. 8.
12 V. Denisenko. Hart protocol: general information and principles of building networks based on it. “Modern automation technologies”, 2010. 94.
13 R. Markus., K. Stephan., Z. Clemens. System Self Diagnosis for industrial devices. “IEEE International conference on emerging technologies and factory automation”, doi 10.1109/ETFA.2013.6648019, 2013. 8.
14 N.R. Yusupbekov., U.A. Ruziev. Identification approach for creating software algorithms for intelligent measuring instruments. “International conference scientific research of the SCO countries: synergy and integration”, Beijing, 2022. 145.
Waiting