Development of a Committee of Artificial Neural Networks for the Performance Testing of Compressors for Thermal Machines in Very Reduced Times

• Autorzy: Coral R. , Flesch C. A. , Penz C. A. , Borges M. R.

Identyfikatory

DOI

10.1515/mms-2015-0003

• Języki publikacji: EN

Abstrakty

EN

This paper presents a new test method able to infer - in periods of less than 7 seconds - the refrigeration capacity of a compressor used in thermal machines, which represents a time reduction of approximately 99.95% related to the standardized traditional methods. The method was developed aiming at its application on compressor manufacture lines and on 100% of the units produced. Artificial neural networks (ANNs) were used to establish a model able to infer the refrigeration capacity based on the data collected directly on the production line. The proposed method does not make use of refrigeration systems and also does not require using the compressor oil.

Słowa kluczowe

EN

refrigeration compressor; artificial neural networks; performance test

• Wydawca: Komitet Metrologii i Aparatury Naukowej PAN
• Czasopismo: Metrology and Measurement Systems
• Rocznik: 2015
• Tom: Vol. 22, nr 1
• Strony: 79--88
• Opis fizyczny: Bibliogr. 27 poz., rys., tab., wyk., wzory

Twórcy

autor

Coral R.

• Dep. de Eletroeletrônica, Instituto Federal de Santa Catarina, 89220-200, Joinville, SC, Brazil

autor

Flesch C. A.

• Dep. de Engenharia Mecânica, Universidade Federal de Santa Catarina, 88040-970, Florianópolis, SC, Brazil

autor

Penz C. A.

• Dep. de Engenharia Mecânica, Universidade Federal de Santa Catarina, 88040-970, Florianópolis, SC, Brazil

autor

Borges M. R.

• Whirlpool S.A., Unidade EMBRACO 89219-901, Joinville, SC, Brazil

Bibliografia

• [1] ASHRAE STANDARD, (2005). ANSI/ASHRAE 23: Methods of testing for rating positive displacement refrigerant compressors and condensing units. USA.
• [2] DIN - DEUTSCHES INSTITUT FÜR NORMUNG, (2008). EN 13771-1: Compressors and condensing units for refrigeration - Performance testing and test methods - Part 1: Refrigerant compressors. Germany.
• [3] ISO - INTERNATIONAL ORGNIZATION FOR STANDARDIZATION., (1989). ISO 917 - Testing of refrigerant compressors, second ed., Switzerland.
• [4] Penz, C. A., Flesch, C. A., Nassar, S. M., Flesch, R. C. C., Oliveira, M. A., (2012). Fuzzy-Bayesian network for refrigeration compressor performance prediction and test time reduction. Expert Syst. with Appl., 39, 4268-4273.
• [5] Flesch, R. C. C., Normey-Rico, J. E., (2010). Modelling, identification, and control of a calorimeter used for performance evaluation of refrigerant compressors. Control Eng. Pract., 18, 254-261.
• [6] Gustafson, S., Little, G. R., (1992). Correlation of transient and steady-state compressor performance using neural networks. In Proc. of the AutoTest Conf. 92, USA, 69-72.
• [7] Stoecker, W. J., Jabardo, J. M. S., (2002). Industrial refrigeration, second ed., Edgard Blücher, São Paulo.
• [8] Haykin, S., (1999). Neural Networks: a comprehensive foundation. NJ: Pearson Education, India.
• [9] Singaram, L. A., (2011). Prediction models for mechanical properties of AZ61 MG alloy fabricated by equal channel angular pressing. Int. J. of Res. and Rev. in Appl. Sci., 8, 337-345.
• [10] Ghobadian, B., Rahimi, H., Nikbakht, A. M., Najafi, G., Yusaf, T. F., (2009). Diesel engine performance and exhaust emission analysis using waste cooking biodiesel fuel with an artificial neural network. Renew. Energy, 34, 976-982.
• [11] Ertunc, H. M., Hosoz, M., (2005). Artificial neural network analysis of a refrigeration system with an evaporative condenser. Appl. Therm. Eng., 26, 627-635.
• [12] Arcaklioğlu, E., Çavuşoğlu, A., & Erişen, A., (2004). Thermodynamic analysis of refrigerant mixtures using artificial neural networks. Appl. Energy, 78, 219-230.
• [13] Russel, S., Norvig, P., (2003). Artificial Intelligence: A Modern Approach, second ed. Prentice Hall, New York.
• [14] Hu, Y. H., Hwang, J., (2002). Handbook of neural network signal processing. CRC Press, New York.
• [15] Granitto, P. M., Verdes, P. F., Ceccatto, H. A., (2005). Neural Networks Ensembles: Evaluation of Aggregation algorithms. Artif. Intelligence, 163, 139-162.
• [16] Zio, E., (2006). A study of the bootstrap method for estimating the accuracy of artificial neural networks in predicting nuclear transient processes. IEEE Trans. on Nucl. Sci., 53, 1460-1478.
• [17] Trichakis, I., Nikolos, I., Karatzas, G. P., (2011). Comparison of bootstrap confidence intervals for an ANN model of a karstic aquifer response. Hydrol. Processes, 25, 2827-2836.
• [18] Papadopoulos, G., Edwards, P. J., Murray, A. F., (2000). Confidence estimation methods for neural networks: a practical comparison. In Proc. of the Eur. Symp. on Artif. Neural Netw., Bruges, Belgium, 75-80.
• [19] BIPM, IEC, IFCC, ILAC, ISO, IUPAC, IUPAP, OIML, (2008). JCGM 100: Evaluation of measurement data - Guide to the expression of uncertainty in measurement, France.
• [20] Efron, B., Tibshirani, R., (1993). An introduction to the bootstrap. Chapman & Hall, New York.
• [21] Sharkey, A. J. C., (1999). Combining artificial neural networks: ensemble and modular multi-net systems. Springer-Verlag, London.
• [22] Zhang, J., (1999). Developing robust non-linear models through bootstrap aggregated neural networks. Neurocomputing, 25, 93-113.
• [23] Yu, J. B., Xi, L. F. A., (2009). Neural network ensemble-based model for online monitoring and diagnosis of out-of-control signals in multivariate manufacturing processes. Expert Syst. with Appl., 36, 909-921.
• [24] Wu, B., Yu, J., (2010). A neural network ensemble model for on-line monitoring of process mean and variance shifts in correlated processes. Expert Syst. with Appl., 37, 4058-4065.
• [25] Gayeski, N.T., Zakula, T., Armstrong, P.R., (2010). Empirical modeling of a rolling-piston compressor heat pump for predictive control in low lift cooling. ASHRAE Trans., 116.
• [26] Swider, D. J., Browne, P. K., Bansal, V., (2001). Modelling of vapour-compression liquid chillers with neural networks. Appl. Therm. Eng., 21, 311-329.
• [27] Kim, T., Li, C. J., (1995). Feedforward neural networks for fault diagnosis and severity assessment of a screw compressor. Mech. Syst. and Signal Processing, 9, 485-496.

Uwagi

EN

The authors would like to express their sincere gratitude to the Laboratory for Metrology and Automation (Labmetro) of the Mechanical Engineering Department of the Federal University of Santa Catarina. The authors also thank the Compressors and Cooling Solutions division of Whirlpool Brazil for their financial and technical support. Finally, the financial support from the Brazilian funding agencies CNPq (311775/2011-0), CAPES/PNPD (23038.007820/2011-61) and the Federal Institute of Santa Catarina which enabled the principal author to carry out this study are gratefully acknowledged.