Authors S.I. Klevtsov
Month, Year 03, 2016 @en
Index UDC 681.3.01
Abstract A model and a generalized warning algorithm Inappropriate variation of the parameter of a technical object. The parameter is considered as a rapidly varying physical quantity. The algorithm is based on processing diagrams generated in real time. Figure formed a local array of time series points, consisting of the values of the physical quantity. Each point on the graph formed by the current and the following parameter values. An array of cut predetermined fixed time window in the process of moving from a time series consisting of the physical quantity values. To remove the parameter values used for monitoring the system"s sensor. For each chart is determined by the standard deviation of the points from the center point of the chart of the masses. Formed dependence of the standard deviation points from time to time. Process etsya done in real time. Determine critical level changes srednekvadratical deviation that characterizes the border-allowable change of signal level over a specified period of time. Intermediate dangerous levels is also determined at which state Ob-project is considered to be extraordinary. In the real-time calculated value of the standard deviation compared with the values of hazardous levels. Depending on the result of the comparison circuit is implemented previously defined prevent dangerous situation. Determination of Hazardous parameter changes is performed using a modified Hamming neural network. Hamming neural network implements a simple algorithm works, a simple learning algorithm. Its capacity is independent of the dimension of the signal on the WMO de. On the network input binary input signals are supplied that can be used effectively in the implementation of the algorithm in the microcontroller. Information processing and control of hazardous changes made in real time by a microprocessor unit located on the lower level technical object monitoring system. Determination of opportunities for the emergence of an emergency at an early stage of its development model provides real-time. The algorithm is characterized by ease of implementation, low resource consumption, it can be used for processing signals with a high noise level.

Download PDF

Keywords Time series; change in the parameter; model; algorithm; neural network; microprocessor module; real time.
References 1. Klevtsov S.I. Prognozirovanie izmereniya sostoyaniya parametrov tekhnicheskogo ob"ekta s pomoshch'yu intellektual'nogo mikroprotsessornogo modulya [Forecasting the measurement of
the state parameters of technical object using the intellectual microprocessor module], Cb. trudov «Problemy razrabotki perspektivnykh mikro- i nanoelektronnykh sistem – 2010» [proceedings "problems of development of perspective micro- and nanoelectronic systems –
2010"]. Moscow: IPPM RAN, 2010, pp. 619-622.
2. Bassvil' M., Banvenista A. Obnaruzhenie izmeneniya svoystv signalov i dinamicheskikh system [Detection of changes in properties of signals and dynamic systems]: translation from english. Moscow: Mir, 1989, 278 p.
3. Klevtsov S.I. Mul'tisegmentnaya prostranstvennaya approksimatsiya graduirovochnoy kharakteristiki mikroprotsessornogo datchika [Multi-segment spatial approximation of the calibration ha characteristics of the microprocessor sensor], Metrologiya [Metrology], 2011, No. 7, pp. 26-36.
4. Klevtsov S.I., Udod Y.V. Model of the Spatial Conversion Characteristics for Graduation of the Microprocessor-Based Sensor's with Indemnification of Influence Destabilizing Factors, International Siberian Conference on Control and Comunications (SIBCON). Proceedings. – Omsk: Omsk State Technical University. Russia, Omsk, May 21-23, 2015. Available at:,147,097.
5. Novoselov O.N. Identifikatsiya i analiz dinamicheskikh sistem: monografiya [Identification and analysis of dynamical systems: monograph]. 3rd ed. – Moscow: GOU VPO MGUL, 2010, 424 p.
6. Klevtsov S.I. Osobennosti vybora parametrov nastroyki modeli sglazhivayushchego vremennogo ryada dlya osushchestvleniya kratkosrochnogo prognozirovaniya izmeneniya fizicheskoy velichiny [Features choice of model settings smoothing time series for the implementation of short-term forecasting of physical size], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2011, No. 5 (118), pp. 133-138.
7. Klevtsov S.I. Prognozirovanie izmeneniy fizicheskoy velichiny v real'nom vremeni s ispol'zovaniem lineynogo adaptivnogo fil'tra [Prediction of changes in physical quantities in real time using a linear adaptive filter], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2013, No. 5 (142), pp. 180-185.
8. Klevtsov S.I. Modelirovanie algoritma kratkosrochnogo prognozirovaniya izmeneniya bystroizmenyayushcheysya fizicheskoy velichiny v real'nom vremeni [Modeling of algorithm of short-term forecasting is developed for definition of physical quantity in real time], Inzhenernyy vestnik Dona [Engineering journal of Don], 2012, No. 3 (21), pp. 199-205.
9. Klevtsov S.I. Osobennosti vybora parametrov nastroyki modeli sglazhivayushchego vremennogo ryada dlya osushchestvleniya kratkosrochnogo prognozirovaniya izmeneniya fizicheskoy velichiny [Features choice of model settings smoothing time series for the implementation of short-term forecasting of physical size], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2011, No. 5 (118), pp.133-138.
10. Klevtsov S.I. Predvaritel'naya otsenka sostoyaniya sovokupnosti parametrov tekhnicheskogo ob"ekta s ispol'zovaniem intellektual'nogo mikroprotsessornogo modulya [Preliminary assessment of the set of parameters of a technical object with the use of intelligent microprocessor module], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 20110, No. 5 (106), pp. 43-48.
11. Lipman R. An introdaction to computing with neural nets, IEEE Acoustic, Speech and Signal Processing Magazine, 1987, No. 2, pp. 4-22.
12. Golovko V.A. Neyronnye seti: obuchenie, organizatsiya i primenenie [Neural networks: training, organization and application].Book 4. Moscow: IPRZhR, 2001, 256 p.
13. Nazarov A.V., Loskutov A.I. Neyrosetevye algoritmy prognozirovaniya i optimizatsii system [Neural network algorithms for forecasting and optimization systems]. St. Petersburg: Nauka i tekhnika, 2003, 384 p.
14. Kruglov V.V. Borisov V.V. Iskusstvennye neyronnye seti. Teoriya i praktika [An artificial neural network. Theory and practice]. Moscow: Goryachaya liniya – Telekom, 2001, 382 p.
15. Wei Lu, Zhijian Li, Bingxue Shi. A modified Hamming neural network, Solid-State and Integrated Circuit Technology, 1995 4th International Conference. IEEE. Beijing. 1995, pp. 694-696.
16. Gupta A.K., Singh Y.P. Analysis of Hamming Network and MAXNET of Neural Network Method in the String Recognition, Communication Systems and Network Technologies (CSNT), 2011 International Conference. Katra, Jammu. 2011. IEEE, pp. 38-42.
17. Gaitanis, N., Kapogianopoulos, G., Karras, D.A. Pattern classification using a generalised Hamming distance metric, Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference, Vol. 2, pp. 1293-1296.
18. Kwan H.K. One-layer feedforward neural network for fast maximum/minimum determination, Electronics Letters, 2002, Vol. 28, Issue 17, pp. 1583-1585.
19. Wei Lu, Bingxue Shi, Zhijian Li. A modified Hamming neural network with different thresholds and multi-valued weights, Neural Networks, 1996. IEEE International Conference, Vol. 2. Washington, DC, pp. 1012- 016
20. Feng K., Hoberock L.L. An optimal scheduling of pick place operations of a robot-vision-tracking system by using back-propagation and Hamming networks, Robotics and Automation, 1992. Proceedings., 1992 IEEE International Conference, Vol. 2. Nice. IEEE, pp. 1201-1206.
21. Klevtsov S.I. Razrabotka modeli i algoritma otslezhivaniya izmeneniya sostoyaniya tekhnicheskogo ob"ekta na osnove modifitsirovannoy neyronnoy seti Khemminga [Development of a model and tracking algorithm changes the state of the technical object based on the modified neural network Hamming], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2014, No. 11 (160), pp. 42-52.

Comments are closed.