| 000 | 04540ntm a2200277 a 4500 | ||
|---|---|---|---|
| 001 | vtls000099795 | ||
| 003 | KUKTEM | ||
| 005 | 20251117113437.0 | ||
| 008 | 170503t2016 my a f a m 000 0 eng d | ||
| 020 | _aTHE0007928(Local) | ||
| 039 | 9 |
_a201906131056 _bazli _c201705171040 _dfateeha _y201705031004 _zfateeha |
|
| 040 | _aUMP | ||
| 090 | _aFTech .Y38 2016 r Thesis | ||
| 100 | 0 | _aYattapu Yaswanth | |
| 245 | 1 | 0 |
_aSimulation studies and experimental investigations of dissimilar aluminium alloys by friction stir welding / _cYattapu Yaswanth |
| 260 |
_aKuantan, Pahang : _bUMP, _c2016 |
||
| 300 |
_axii, 100 p. : _bill. (some col.) ; _c30 cm. + _e1 CD-ROM |
||
| 500 | _aFaculty of Engineering Technology | ||
| 502 | _aThesis (Master of Science in Manufacturing Engineering Technology) -- Universiti Malaysia Pahang – 2016 | ||
| 504 | _aBibliography : p. 88-95 | ||
| 520 | 3 | _aFriction stir welding (FSW) is a solid state hot joining process, in which a rotating tool with a shoulder and pin moves along the butting surfaces of two rigidly clamped plates. FSW has been evolved as an alternative joining technique for aluminium and is gaining research importance on non-conventional weldable alloys. Present research is focused on developing a simulated model for predicting the behaviour of FSW dissimilar joints and tried to validate the same by experimentation. To carryout simulations a module, manufacturing solution's, in Altair Hyperworks software was employed to predict the temperatures. Joining of dissimilar metal alloys Al 5xxx and Al 6xxx by FSW resulted in higher strength welds under all conditions of welding. Experimentation has been carried out on 300x125x5 mm (LxWxT) sheets of similar and dissimilar alloys of Al 5xxx and Al 6xxx series. The weld parameters have been varied as per the design plan of design of experiments (Taguchi's L8-Orthogonal array). A few 24 experiments with 120 samples for tensile test and micro-hardness were extracted from the electron discharge machine (Mitsubishi EDM Wire-cut). The tensile tests were carried out on Instron (30kN), while microhardness was measured using Wilson hardness tester. Adaptive neuro fuzzy inference system (ANFIS) was also used to predict the parameter sensitivity and to predict the tensile strength and microhardness of the dissimilar metal welded joints. The adaptive network based fuzzy inference system (ANFIS) is a data driven procedure representing a neural network approach for the solution of function approximation problems. Data driven procedures for the synthesis of ANFIS networks typically based on clustering a training set of numerical samples of the unknown function was used to approximated since introduction, ANFIS networks have been successfully applied to classification tasks, rule-based process control, pattern recognition and similar problems. Here a fuzzy inference system comprises of the fuzzy model proposed by Takagi, Sugeno and Kang was used to formalize a systematic approach to generate fuzzy rules from an input output data set. No close mathematical model, can describe the behaviour of FSW processes due to its complex nature. There exists a Non-linear relationship between the input parameters (welding speed and rotational speed) and the output parameters (tensile strength, yield strength and micro hardness). Artificial Intelligence has many applications in process modelling and control. In addition, the use of artificial intelligence offers cost effective and easy to understand presentation. Moreover, it allows the use of intelligent sensors for estimating variables that usually cannot be measured directly, in a dynamic system identification and fault detection and diagnosis. ANFIS (Adaptive Neuro Fuzzy Inference System) is a nonlinear methodology, and the combination of concept of Fuzzy Logic and Artificial Neural Network. The fuzzy logic is a decision-making system in the network, and helps to find the output for given set of inputs. ANN is like the biological Neural Network and it has learning capability. Each layer of the ANFIS structure depicts each step of Fuzzy Logic, training of network on the concept of Neural Network. So, for a given set of input and output network is trained, which acts in same manner as the set of input and output. | |
| 610 | 2 | 0 |
_aFaculty of Engineering Technology _xDissertations |
| 650 | 0 |
_aUniversities and Colleges _xDissertations |
|
| 650 | 0 | _aTheses | |
| 999 |
_aVIRTUA40 _c8749 _d8755 |
||
| 999 | _aVTLSSORT0080*0200*0400*0900*1000*2450*2600*3000*5000*5020*5040*5200*6100*6500*6501*9992 | ||