Software fault prediction (SFP) is a vital objective in software engineering. This might permit effective resource allocation and also enhance informed decisions about the release quality. SFP is being a critical issue for software professionals as well as the tech industry. Thus, SFP is necessary. The study intends to perform efficient error rate estimation using the proposed hybrid robust weight based optimization and Jacobian adaptive neural network (RWO-JANN). It also aims to classify the software faults in an efficient way using multi-layer perceptron neural network-random forest (MLPNN-RF). Various processes are involved to accomplish SFP. At first, the dataset is taken as input. After this, data preprocessing is performed. Subsequently, weights are initialized using the proposed RWO-JANN. Weight initialization is performed through a series of steps. Then, the position and the weight parameter are updated to perform weight initialization. After this, the error rate is estimated and the weight is updated on the basis of the learning rate and Jacobian matrix calculation. Lastly, the decay rate is analyzed. If the error rate extends beyond the threshold value, the process repeats from weight initialization. If not, the testing process is performed and lastly the classified output for SFP is obtained by the proposed MLPNN-RF. The proposed system is comparatively analyzed with the existing methods in terms of accuracy, precision, recall, F1 score, sensitivity, specificity, and error rate. The analytical results revealed effective outcomes of proposed system than the existing techniques with accuracy of 99.01%.
Friction Stir Welding is a solid-state process where a tool which is not consumable rotates between two metals or alloy. In FSW process heat is generated because of the friction that is developed between the tool and the work piece below the melting point of the material. Compared to conventional welding this FSW process can be used for welding alloys such as aluminium, copper, etc. In this process, we can even weld two different types of alloy together which is not possible in conventional welding. Aluminium alloy AA7075 (Al-Zn-Mg-Cu) is a type of alloy which shows high strength and corrosive resistant because of the zinc content in the alloy. This zinc act as a sacrificial anode for the alloy which forms a outer covering on the surface of the alloy which is the one which gets corroded first and then followed by the alloy. In this FSW the parameters play the significant role that determines the weld characteristics. Here, aluminium alloy of series AA7075 of thickness 6mm is welded by Friction Stir Welding Process. This alloy contains zinc with a minimum amount of 5.8%. This zinc acts as a sacrificial-anode in sub-marines application, where this zinc forms like an outer covering layer on the surface of the submarine. So, this zinc gets corroded first keeping the sub-marine safe for a long period. After the Friction Stir Welding Process is completed, different tests are performed in the welded portion of the alloy. The test starts with the Ultimate Tensile Test followed by the Impact hardness test and the microstructure of the welded portion is studied. The welding parameter such as rotational speed, transverse speed is optimized in this process by using the Taguchi analysis. Taguchi method greatly improves the design and engineering productivity. This method is very effective on regard of its simple experimental design and systematic approach to produce better quality at lower costs. The optimum results can be obtained by providing the input functions and can easily produce better results. By this effect of input variables the results can be formed by S/N ratio and response means. The Larger is better criteria is employed to our problems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.