Background/Objectives: Nowadays artificial intelligence plays an important role in manufacturing sector. How to utilize that in an effective manner is a key factor of optimization. So identification of optimal modeling tool for effective manufacturing gives an extraordinary output. Methods/Statistical Analysis: This paper develops an Adaptive Neuro Fuzzy Inference System (ANFIS) model with hybrid model to predict the Surface Roughness (SR) of the H13 tool steel work piece of 45 HRC hardness value. The investigation of operation has been done in hard turning using minimal cutting fluid application. Findings: The effect of the different input parameters like cutting force, temperature and vibration has been analyzed. Here the hybrid type of ANFIS model is created with triangular membership function and the observed results indicated that the predicted output surface roughness is almost very close to the actual output obtained in the experimental work.

Background/Objectives: Saddles are one of the important parts of vessel as they support the vessel. In this study, how Mode II type crack propagated inside the junction of saddle and vessel connection would spoil the entire setup of the vessel was investigated. The main intention of this work was to avoid the repeated failures of saddles during operation in energy development industries and wherever it is used. Methods/Statistical Analysis: Two different types of saddles were considered and fabricated using IS2060 Grade B material. The saddle parts were welded as per the code rule of API. Findings: Normally, welding in inclined saddle is difficult in comparison with straight saddle. This may be reason; the failure rate of inclined saddle is high in comparison with straight saddles during operation and loading conditions. The other possibility of failure is the gap formation inside the weld during joining the plates. This is due to non-deposition of weld materials. The gap would grow during operation and loaded conditions. To avoid these types of failures, external and internal crack inspections were done. Once the inspection was done, it was examined the load carrying of the fabricated saddles using FEM. Then the solid works software was used to simulate the solid model which it’s developed similar like original saddle fabricated for estimating the load carrying capacities. The obtained results of NDT and FEM were presented and the design recommendations based on investigation and study are also suggested. Applications/Improvements: The obtained results of NDT and FEM were presented and the design recommendations based on investigation and study are also suggested.

Investigation of Biodiesel Production from High Free Fatty Acid through RSM

A ceramic monolith heat exchanger has been learnt for finding out heat transfer performance and effectiveness on computing numerically and ξ-NTU method. In entire domain computation numerically has been performed along with fluid region in rectangular ducts of exhaust gas side, ceramic core and rectangular duct fluid region in air side with the air exhaust in direction of cross flow. Additionally, the heat exchanger has been examined for estimating the functionality via ξ-NTU technique that is conventional along numerous Nusselt number links for rectangular duct flow for the literature. Based on the research, it has been performed on the ceramic heat exchangers and on the ceramic materials and the demand in utilizing the ceramic materials in heat exchangers. Then the recuperator is modeled by using GAMBIT and it is analyzed using FLUENT. The effectiveness and the heat transfer rate are also calculated. Then those outcomes have been assessed along the experimental data. By comparison of both functionality by computing numerically and the ξ-NTU technique, the efficiency by ξ-TU technique has been identified to be nearest to product by the numerical computation among the associative of 2.15% when Stephan's Nusselt number association has been adapted to the ξ-NTU technique within numerous connections. The total heat transfer and effectiveness by ξ-NTU method relative errors utilizing five Nusselt number correlations from literature have been lesser than 14.5% comparative to numerical computation. Associated to Nusselt number correlations, the entire heat transfer utilizing ξ-NTU technique with Stephan's correlation is highly nearest to numerical computation. For that reason, the exit temperature by ξ-NTU method with Stephan's correlation simulates within 1.2% of the relative error for exhaust exist temperature and 0.45% for the air exit temperature assessed against the numerical computation. Overall heat transfer coefficient's relative errors by ξ-NTU technique utilizing five Nusselt number correlations for the literature have been more than 17.5% to that on computing numerically.

Background/Objectives: Surface roughness plays a major role in determining how an original component will interact with its environment. For getting a good surface finish industries spent huge cost for introducing new technologies. The use of advanced engineering ceramics and composites in the aerospace and defense industries is continuous and increases day by day. Surface Roughness (SR) prediction plays a vital role in improving the surface finish in industries. The present work deals with predicting the surface roughness of AISI1020 steel material in Electrical Discharge Machining (EDM) by using Adaptive Neuro Fuzzy Inference System (ANFIS). Methods/Statistical Analysis: The discharge voltage, discharge current, pulse on time, pulse off time, gap between tool and workpiece and oil pressure are taken as the input parameters, whereas SR is the output machining parameter. Design of Experiment (DoE) is based on Response Surface Methodology (RSM). ANFIS model has been constructed using Gaussian membership function (Gaussmf) with 2 membership function for each and every input parameter and linear membership function for output parameter SR and MRR. Findings: We employed both the back propagation method and the hybrid method for membership function parameter training. Based on the conclusion from the comparison of ANFIS with two types of membership function parameter training, hybrid method provides accurate results. Applications/Improvements: It is further used that the maximum error when the network is optimized by the intelligent technique has been reduced considerably. Sensitivity analysis is also done to find the relative influence of factors on the performance measures. It is observed that type of material is having more influence on the performance measures.

Experimental Study of Heat Transfer on a Plate Impinged with Cold Air Jet