Hybrid Intelligence Modeling using Genetic Algorithm for optimizing welding process parameters of Mod. 9Cr-1Mo Stee

• Autorzy: Vasudevan M. , Gowtham K. N. , Jayakumar T.
• Języki publikacji: EN

Abstrakty

EN

This abstract is for Mini symposium on Genetic Algorithm in Materials Design and Processing Modified 9Cr-1Mo ferritic steel is used as structural material for stream generator components of power plants. Generally, Tungsten Inert Gas (TIG) welding is preferred for welding these steels in which the depth of penetration achievable during autogenous welding is very limited and hence productivity is less. Therefore, Activated flux Tungsten Inert Gas (A-TIG) welding, a novel welding technique has been developed in house to increase the depth of penetration. In modified 9Cr-1Mo steel joints produced by A-TIG welding process, weld bead width, depth of penetration and Heat Affected Zone (HAZ) width play an important role in determining the mechanical properties and also the performance of the weld joints during service. To obtain the desired weld bead geometry, HAZ width and make a good weld, it becomes important to set the welding process parameters. Since the experimental optimization of these parameters is time consuming, soft-computing techniques are commonly used for optimization of the welding process parameters (welding voltage, current and torch speed). In this work, Adaptative Neuro Fuzzy Inference System (ANFIS), one of the soft-computing tools, is used to develop independent models correlating the welding process parameters like current, voltage and speed with weld bead shape parameters like depth of penetration, bead width and HAZ width. Then Genetic Algorithm is employed to determine the optimum A-TIG welding process parameters in order to obtain the desired weld bead shape parameters and HAZ width. Validation of the GA model is completed by carrying out experiments to compare the target values with that of the actual values of the weld bead shape parameters obtained. There is good agreement between the target values and the actual values.

PL

Modyfikowana stal ferrytyczna 9Cr-1MoDo wykorzystywana jest do budowy generatorów stosowanych w elektrowniach. Tego typu stale spawane są najczęściej metodą TIG (Tungsten Inert Gas), charakteryzującą się bardzo małą głębokością przetopu podczas spawania, a tym samym niską sprawnością. Dla zwiększenia głębokości przetopu opracowana została nowa technika spawania, tzw. A-TIG (Activated flux Tungsten Inert Gas). Własności mechaniczne oraz jakość wykonania spawów metodą A-TIG zależy w dużej mierze od szerokości spoiny, głębokości przetopu oraz wielkości strefy wpływu ciepła (Heat Affected Zone). Kontrola jakości spawu, czyli dobranie odpo-wiedniej szerokości spoiny oraz utrzymanie strefy ciepła HAZ, zależy od parametrów procesu. Ze względu na czasochłonności optymalizacji doświadczalnej, do określenia optymalnych para-metrów spawania zastosowano model obliczeniowy procesu połączony z algorytmem genetycznym (GA). Do wyznaczenia niezależnych modeli korelacji pomiędzy parametrami procesu: natężeniem i napięciem prądu oraz prędkością spawania, a szerokością spawu, głębokością przetopu oraz wielkością HAZ wykorzystano jedno z narzędzi ANFIS (Adaptive Neuro Fuzzy Interface System). Następnie za pomocą algorytmu genetycznego oszacowano optymalne parametry procesu spawania metodą A-TIG. W celu weryfikacji modelu wykonano doświadczenia i porównano wartości otrzymane z rzeczywistymi potwierdzając poprawność otrzymanych wyników obliczeń.

Słowa kluczowe

EN

ANFIS; genetic algorithm (GA); A-TIG welding; welding process optimization; mod. 9Cr-1 Mo steel

• Wydawca: Wydawnictwa AGH
• Czasopismo: Computer Methods in Materials Science
• Rocznik: 2011
• Tom: Vol. 11, No. 1
• Strony: 16--22
• Opis fizyczny: Bibliogr. 20 poz., rys.

Twórcy

autor

Vasudevan M.

autor

Gowtham K. N.

autor

Jayakumar T.

Bibliografia

• Bag, S., De, A., 2009, Development of efficient numerical heat transfer model coupled with genetic algorithm based optimization for prediction of process variables in GTA spot welding. Science and Technology of welding and Joining, 14, 633-645.
• Chakraborti, N., 2004, Genetic algorithm in materials design and Processing. International Material Reviews, 49 (3-4), 246-260.
• Chen, M.Y., Linkens, D.A., 2006, Impact Toughness Prediction for TMCP Steels Using Knowledge-based Neural-fuzzy Modelling. ISIJ International, 46, 586-590.
• Datta, S., Pettersson, F., Ganguly, S., Saxen, H., Chakraborti, N., 2007, Designing high strength multi-phase steel for improved strength-ductility balance using neutral networks and Multi-objective genetic algorithm. ISIJ International, 47, 1193-2001.
• Deb, K., 1999, An Introduction to Genetic Algorithms. Sadhana, 24, 239-315.
• Dey, S., Datta, S., Chattopadhyay, P.P., Sil, J., 2008, Modeling the properties of TRIP steel using AFIS: A distributed approach. Computational Materials Science, 43, 501-511.
• Dhas, J.E.R., Kumanan, S., 2007, ANFIS for predicted of weld bead width in a submerged arc welding process. Journal of Scientific and Industrial Research, 66,335-338.
• Ghanty, P., Paul, S., Roy, A., Mukherjee, D.P., Pal, N.R., Vasudevan, M., Kumar, H., Bhaduri, A.K., 2008, Fuzzy rule based approach for predicting weld bead geometry in gas tungsten arc welding. Science and technology of Welding and Joining, 13, 167-175.
• Hancheng, Q., Bocai, X., Shangzheng, L., Fagen, W., 2002, Fuzzy neural network modelling of material properties. Journal of Materials Processing Technology, 122, 196-200.
• Kovacevic, R., Zhang, Y.M., 1997, Neurofuzzy Model-Based weld Fusion State Estimation. IEEE control Systems, 30-42.
• Lucas, W., 2000, Activating flux-improving the performance of the TIG process. Welding and Metal Fabrication, 68(2),7-10.
• Odetunji A. Odejobi and Laisisi E. Umoru, 2009, Applications of soft computing techniques in materials engineering: A review, African Journal of Mathematics and Computer Science Research Vol. 2(7), 104-131.
• Paskell, T., Lundin, C, Castner, H., 1997, GTAW flux increases weld joint penetration. Welding Journal, 76(4), 57-62.
• Vasudevan, M., 2007, Computational and experimental studies on arc welded austenitic stainless steels. PhD thesis, Indian Institute of Technology, Chennai, India.
• Vasudevan, M., Bhaduri, A.K., Raj, B., 2008, Developmental Evaluation of activated Flux for TIG welding of Type 304LN and 316LN stainless steels. Proceedings of the International Institute of Welding, International congress, January, 8-10, Chennai.
• Vasudevan, M., Raj, B., 2009, Soft computing in Materials Science and Engineering. IIM Metal News, 12, 15-21.
• Vasudevan, M., 2009, Soft computing techniques in Stainless steel Welding. Materials and Manufacturing Processes, 24, 209-218.
• Vasudevan, M., Kupuswamy, M.V., Bhaduri, A.K., 2010, Optimizing process parameters for Gas Tunsten arc welding of an austenitic stainless steel using genetic algorithm. Transactions of The Indian Institute of Metals, 63 (3), 1-10.
• Vasudevan, M., ArunKumar, V., Chandrasekhar, N., Maduraimuthu, V., 2010, Genetic Algorithm for optimisation of A-TIG welding process for modified 9Cr-1Mo steel. Science and Technology of welding and Joining, 15,117-123.
• Vasudevan, M., Bhaduri, A.K., Raj, B., Rao, K.P., 2007, Genetic Algorithm-Based Computational Models for Optimizing the Process Parameters in A-TIG Welding to Achieve Target Bead geometry in Type 304 L(N) and 316 L(N) Stainless Steels. Materials Manufacturing Process, 22, 641-649.