Contemporary engine tests are performed based on the theory of experiment. The available versions of programmes used for analysing experimental data make frequent use of the multiple regression model, which enables examining effects and interactions between input model parameters and a single output variable. The use of multi-equation models provides more freedom in analysing the measured results, as those models enable simultaneous analysis of effects and interactions between many output variables. They can also be used as a tool in preparing experimental material for other advanced diagnostic tools, such as the models making use of neural networks which, when properly prepared, enable also analysing measurement results recorded during dynamic processes.
The article presents advantages of the use of the abovementioned analytical tools and a sample application of the neural model developed based on the results of examination carried out on the engine research rig.
4. Krishnamoorth C.S., Rajeev S.: Artifcial Intelligence and Expert Systems for Engineers. CRC Press, Boca Raton 1996.
5. Kufel T.: Econometrics. Solving Problems Using GRETL Sofware, in Polish, Polish Scientifc Publishers PWN, Warszawa. 2007.
6. Kukiełka L.: Basics of Engineering Research. (in Polish), Polish Scientifc Publishers PWN, Warszawa 2002.
7. Piaseczny L. Zadrąg R.: The infuence of selected damages of engine SI type on the changes of emission of exhaust gas components, Diesel Engines, Opole 2009.
8. Polański Z.: Design of Experiments in Technology, (in Polish) Scientifc Publishers PWN, Warszawa 1984.
9. Skoundrianos E.N., Tzafestas S.G.: Fault diagnosis via local neural networks. Mathematics and Computers in Simulation 60 (2002) 169-180. Elsevier Science 2002.
10. Tadeusiewicz R.: Neural networks (in Polish). Warszawa, Akademicka Ofcyna Wydawnicza RM 1993.
11. Tzafestas S.G., Dalianis P.J.: Fault Diagnosis in Complex Systems using Artifcial Neural Networks. 3rd IEEE CCA, 0-7803-1872-2/94 1994 IEEE.
12. Zadrąg R.: Criteria for the selection of the diagnostic parameter for diagnosis of marine diesel engine. LOGISTYKA No. 4/2010, ISSN 1231-5478, Poznań 2010.
13. Zadrąg R.: The Multi-equational models of leakproofness of charge exchange system of ship engine. (in Polish), in monograph 'Gaseous engines – selected issues'' edited by Adam Dużyński, University of Czestochowa Publishing, ISBN 978-83-7193-461-2, ISSN 0860-501., Częstochowa 2010.
14. Zadrąg R.: The multi-equational models in the analysis of results of marine diesel engines research. International Conference Eksplodiesel & Gas Turbine'2009, Międzyzdroje- Kopenhaga 2009.
15. Zadrąg R. et al.: Identifcation models for the technical condition of the engine on the basis of exhaust component emissions. (in Polish), The report of the research project no. 4T12D 055 29, AMW, Gdynia 2008.
16. Zadrąg R., Zellma M.: Analysis of the results of internal combustion engines using multivariate models. (in Polish), Symposium on Marine Power Plants Symso'2009, Gdynia 2009.
17. Zadrąg R., Zellma M.: The usage of multi-equation models in analysis of dynamic process in marine diesel engine research. JOURNAL OF POLISH CIMAC, Vol.7, No 1, ISSN 1231-3998, str. 295-304, Gdańsk 2012.
18. Zadrąg R., Zellma M.: Modelling of toxic compounds emission in marine diesel engine during transient states at variable angle of fuel injection. JOURNAL OF POLISH CIMAC, Vol.8, No 1, ISSN 1231-3998, Gdańsk 2013.
19. Zadrąg R., Zellma M.: Modelling of toxic compounds emission in marine diesel engine during transient states at variable pressure of fuel injection. JOURNAL OF POLISH CIMAC, Vol.9, No 1, Gdańsk 2014.
20. STATISTICA Neural Networks TM. Przewodnik problemowy. StatSof, Kraków 2001.
21. Neural Network Toolbox. Matlab. User's guide. The MathWorks, Inc. 2014.