Multi-response optimization in small scale resistance spot welding of titanium alloy by principal component analysis and genetic algorithm

The prediction and optimization of weld quality characteristics in small scale resistance spot welding of TC2 titanium alloy were investigated. Grey relational analysis, neural network and genetic algorithm were applied separately. Quality characteristics were selected as nugget diameter, failure load, failure displacement and failure energy. Welding parameters to be optimized were set as electrode force, welding current and welding time. Grey relational analysis was conducted for a rough estimation of the optimum welding parameters. Results showed that welding current played a key role in weld quality improvement. Different back propagation neural network architectures were then arranged to predict multiple quality characteristics. Interaction effects of welding parameters were analyzed with the proposed neural network. Failure load was found more sensitive to the change of welding parameters than nugget diameter. Optimum welding parameters were determined by genetic algorithm. The predicted responses showed good agreement with confirmation experiments.

The progressive trends of product miniaturization and light-weighting necessitate the effective microjoining of ultra-thin metal foils with high reliability and performance. In this experimental investigation, Ti-1Al-1Mn foils of 0.05 mm thickness were welded by small-scale resistance spot welding (SSRSW). The experiments based on Taguchi L27 orthogonal array have been implemented to examine the effects, significances and optimal combination of welding parameters, namely welding current, electrode force, ramping time and welding time. Performance measures viz., tensile-shear force, peel force, variances of tensile-shear and peel force were optimized by a hybrid approach comprising gray relational analysis (GRA) with principal component analysis (PCA). Furthermore, two kinds of weighted gray relational grade which extracted different numbers of principal components were put into comparison for better comprehensive performance by analysis of variance (ANOVA) and confirmation tests. It indicated that the procedure of parameter optimization should only extract all the principal components that correspond to eigenvalues larger than one. The ANOVA results showed that welding current was the most significant impact on multi-performance, followed by electrode force and ramp time, while welding time showed little effect. Finally, the optimal welding parameters combination was at welding current of 800 A, electrode force of 35.6 N, ramp time of 5 ms, and welding time of 8 ms.

In the present study, a quality monitoring system in small scale resistance spot welding based on dynamic resistance and neural network was proposed. A precise dynamic resistance curve was obtained directly from the welding machine. Dynamic resistance and nugget development were found sensitive to the change of welding current. The second resistance peak gradually disappeared as welding current increased. Weld expulsion occurrence could be detected through the obvious fluctuation in dynamic electrical signals. The resistance valley and end resistance were found highly correlated with the nugget development. Features extracted from the dynamic resistance curve were selected as inputs in the neural network analysis. A reliable weld quality estimation through the neural network approach could be finally achieved.

Microstructure and tensile behavior of small scale resistance spot welded sandwich bulk metallic glasses

Many Industrial processes have multiple quality characteristics to be optimized. However, among them some are conflicting with each other and optimizing one response causes loss in the other response. Such a problem is called Multiresponse optimization (MRO) problem which involves optimizing conflicting multiple responses simultaneously. Unifying approaches are the most common approaches to solve MRO problem, theses approaches convert a MRO problem into a single response optimization problem by combining the multiple responses into one index, which is used for optimization. Principal Component Analysis (PCA) is one of the tool used to unify the responses. The major advantage of PCA is it takes consideration of correlation among responses. However, there are certain shortcomings as well, this paper address those shortcomings and proposes an Weighted PCA- Artificial Neural Network- Genetic Algorithm (WPCA-ANN-GA ) approach to perform multi response optimization. A case study using data from published literature is presented at the end to demonstrate the WPCA-ANN-GA approach.

Today, with the development of industrial automation, reasonable robot welding parameters are of great significance to obtain the ideal weld quality. It not only enables a stricter guarantee of the weld quality, but also greatly improves the production efficiency. Firstly, after consulting literature and experimental practice on the welding process, the whole robot welding process and the key influencing factors on the welding seam quality are analyzed in detail. Secondly, the genetic algorithm is used in section 4 to optimize the BP neural network to optimize the parameters of the identified welding seam quality reference index-welding time, which realizes the effective measurement of welding time with less experimental data, and enhances the local search ability of the algorithm. Finally, the optimized results are obtained. The optimal welding time is 218.0899s under the data of five layers of currents of 341A, 348A, 345A, 345A, and 345A, due to the welding time of the conventional equal area model. It can be concluded that the BP neural network algorithm optimized by the genetic algorithm is used to optimize the parameters of the welding robot.

The quality of the joints is essential to achieve customer satisfaction and earning profit in manufacturing industries. This work investigates the multi-response optimization of the plasma arc welded (PAW) process parameters of the dissimilar Ti-3Al-2.5V titanium alloy and AA8011-H24 aluminium alloy joints using RSM based GRA coupled with PCA. The principal component analysis is incorporated into the response surface methodology based grey relational analysis to achieve the optimum responses viz., tensile strength and tensile elongation with the welding parameters, viz., welding current, torch angle, gas flow rate and welding speed of the PAW joints. The response surface and contour plots are used to study the effect of parameters of the joints. The welding speed is the most significant parameter on the composite welding quality index (CWQI) followed by welding current, gas flow rate and torch angle to decide the quality of the joints at the optimal levels.

The extent of genetic differentiation among 17 Ethiopian populations (249 individuals) of Phytolacca dodecandra (Endod) sampled along altitudinal gradients that varied from 1600 to 3000 m was investigated using random amplified polymorphic DNA (RAPD). The populations were classified into three altitude groups: lowland (1600–2100 m), central-highland (2101–2500 m) and highland (2500–3000 m). Seventy polymorphic loci scored from 12 RAPD primers, singly or in combination with ecogeographical variables (altitude, longitude, latitude, temperature and rainfall), were used for principal component, discriminant, correlation, and stepwise multiple regression analyses. Principal component analysis (PCA) clearly differentiated lowland and the central-highland populations from those of the highlands independent of their geographical regions. Canonical discriminant analysis separated the lowland plants from those of the highlands with the central-highland plants being intermediate. Classificatory discriminant analysis corrected classification of 92.8% of the 249 plants into their respective three altitude groups. Multiple regression analysis identified a strong association between some RAPDs and altitude, temperature and rainfall, while the variation in most RAPDs was explained by combinations of the different ecogeographical variables. It is hypothesised that the different altitude groups may be (1) chemical and/or physiological ecotypes produced as a result of complex interactions of altitude with climatic and/or edaphic factors, or (2) different in ploidy levels. The significant correlations obtained between population means from some RAPDs and altitude and temperature as well as the strong association of some RAPDs with the ecogeographical variables in the multiple regression analysis suggest that part of the RAPD polymorphism could be adaptive, and responsive to environmental selection.

The weld quality is generally controlled by the welding parameters. In gas metal arc welding process, the welding parameters are inter related and the adjustment of one parameter may affect another parameter and hence it is considered as a non-linear process. The non-linear nature of the welding system makes it difficult to implement a conventional control method. Fuzzy logic control is an attractive alternative approach. The performance of fuzzy controller will be very much dependent on the knowledge provided to the system. Therefore in recent years, more research has been devoted to augment the approximate reasoning method of fuzzy systems with genetic algorithms. In the present work, genetic algorithm tuned conventional controller is implemented for gas metal arc welding system. Its performance is compared with that of genetic algorithm based fuzzy logic controller.

Ultrasonic spot welding of Al-Cu sheets: A comprehensive study

Genome-wide association studies (GWAS) are susceptible to bias due to population stratification (PS). The most widely used method to correct bias due to PS is principal components (PCs) analysis (PCA), but there is no objective method to guide which PCs to include as covariates. Often, the ten PCs with the highest eigenvalues are included to adjust for PS. This selection is arbitrary, and patterns of local linkage disequilibrium may affect PCA corrections. To address these limitations, we estimate genomic propensity scores based on all statistically significant PCs selected by the Tracy-Widom (TW) statistic. We compare a principal components and propensity scores (PCAPS) approach to PCA and EMMAX using simulated GWAS data under no, moderate, and severe PS. PCAPS reduced spurious genetic associations regardless of the degree of PS, resulting in odds ratio (OR) estimates closer to the true OR. We illustrate our PCAPS method using GWAS data from a study of testicular germ cell tumors. PCAPS provided a more conservative adjustment than PCA. Advantages of the PCAPS approach include reduction of bias compared to PCA, consistent selection of propensity scores to adjust for PS, the potential ability to handle outliers, and ease of implementation using existing software packages.

Tungsten inert gas (TIG) welding on Duplex stainless steel (DSS) is more easy, comfortable and useful, if the process is precisely understood and controlled through development of the science & technology. TIG welding on DSS has been performed with the help of specific controlled welding process parameters. Welding quality has been strongly depended on these process parameters. In this study, some valuable welding parameters are chosen. These are welding current, shielding gas flow rate and speed of welding. These process parameters of TIG welding for ASTM/UNS 2205 DSS welds are optimized by using Principal Component Analysis (PCA) method and Grey based Taguchi’s L9 Orthogonal array (OA) experimental plan with the conception of signal to noise ratio (N/S). After that, compression results of above mentioned two analyses of TIG welding process parameters have been calculated. The quality of the TIG welding on DSS has been evaluated in term of ultimate tensile strength, yield strength and percentage of elongation. Compression results of both analyses indicate application feasibility for continuous improvement of welding quality on DSS in different components of chemical, oil and gas industries.

Effect of external magnetic field on resistance spot welds of aluminum alloy

An electronic nose (E-nose) was developed to distinguish different stored eggs by using principal component analysis (PCA),linear discriminant analysis (LDA),BP neural network (BPNN) and the combination of a genetic algorithm and BP neural network (GANN). Results showed that the E-nose can distinguish eggs of different storage time under cool and room-temperature storage by LDA and PCA. LDA preceded PCA. Better prediction values were obtained by GANN than by BPNN. Relationships were established between the E-nose signal and egg quality indices by quadratic polynomial step regression (QPSR). The prediction models indicated good prediction performance with correlation coefficient between predicted and measured values greater than 0.90.

In this paper, a condition monitoring and fault diagnosis system for induction motors is proposed by integrating artificial intelligence algorithms: principal component analysis (PCA), genetic algorithm (GA) and an artificial neural network (ANN). As main diagnosis media of fault motor, three-direction vibration signals and three-phase stator current signals are selected to measure. Multi-sensor measurement results in lots of data transfer that makes on-line or continuous condition monitoring and fault diagnosis difficult. Data transform into feature information provides a solution. Features are calculated from many domains to keep original data information at the highest level. In order to avoid the curse of dimensionality phenomenon and improve fault identification accuracy rate, PCA and GA are employed to reduce the feature dimensionality of the measured data. PCA removes the relative features, and extracts the principal components (PCs) from the original features. Then the significant features are selected from the extracted features by GA as inputs to the neural network. GA is also used to optimize the ANN parameters. The efficiency of the proposed system is validated through monitoring and diagnosing induction motor conditions, and comparing with other systems. The results show good performance of the proposed system and promising application