Robust Parameter Design of Shielded Metal Arc Welding (SMAW) for Optimum Tensile Strength

Shielded Metal Arc Welding (SMAW), an arc welding process, is widely used in applications. In practice, SMAW is widely applied to the welding process on hollow square pipe. Performance expected from this welding is the tensile strength of weld joint. The tensile strength is influenced by parameters process which have possibility for an optimization process to become ‘robust’. Robust is a design which less sensitive to the effect of uncertain quantities or noise factors. Taguchi method is the most efficient optimization method which accommodates the noise factors effect and requires less experiment. This study is focusing on optimizing the welding process on hollow square pipe. Parameters process such as welding current (I), electrode angle (θ), root gap (d) and electrode type (E) are adopted as parameters design. Taguchi method are chosen as a strategy and L9 fractional orthogonal array are chosen as the design experiment, which only 9 experiment samples needed from 81 experiments that should have been carried out for full factorial design. The objectivity is to maximize the tensile strength of weld joint. Three replications of L9 fractional orthogonal array Taguchi had been performed to generate the tensile strength and estimates the fluctuation of the output caused by noise factors. This study found that the welding current of 100A (I), electrode angle (θ) of 90°, root gap (d) of 2 mm, and electrode type (E) of E7018 produce the optimum results. Tensile strength improved from this robust parameter design is about 98.39 MPa based on initial parameter design.

Imbalanced Fault Diagnosis of Rotating Machinery Based on Deep Generative Adversarial Networks with Gradient Penalty

In practical industrial application, the fault samples collected from rotating machinery are frequently unbalanced, which will create difficulties when it comes to diagnosis. Besides, the variation of working conditions and noise factors will further reduce the diagnosis’s accuracy and stability. Considering the above problems, we established a model based on deep Wasserstein generative adversarial network with gradient penalty (DWGANGP). In this model, the unbalanced fault data set will first be trained by the sample generation network to generate synthetic samples, which will be used to restore the balance. A one-dimensional convolutional neural network with a specific structure is then used as the fault diagnosis network to classify the reconstructed equilibrium samples. The experimental results show that the proposed sample generation network can generate high-quality synthetic samples under highly imbalanced data, and the diagnostic network has a fast training convergence. Compared to the combination methods of support vector machines, back propagation neural network and deep belief network, our method has a 74% average accuracy in all unbalanced experimental conditions, which has 64%, 69% and 87% averages leading, respectively.

Where is victory most certain? The level of luck-based noise factor in Summer Olympic Games

We describe a statistical approach for the measurement of the newly defined luck-based noise factor in sports. It is defined as the difference between the actual outcome and the expected outcome based on the model predictions. We raise the question whether some sports exhibit a higher level of noise-factor than others, making investments in that sport riskier. Data from 14 individual sports in six Summer Olympic Games between 1996 and 2016 were included in the analysis. Market shares are predicted by the autoregressive linear and zero-inflated beta regression models with exogenous variables, where the higher Normalized Mean Squared Error indicates a higher noise-factor. Modern pentathlon, tennis and cycling showed the highest noise-factors, whereas swimming, table tennis and athletics were the least noisy. Possible reasons are discussed in the paper. Our analysis indicates that countries with suitable resources producing leading elite Olympic athletes are predicted to achieve higher success in sports with a lower noise-factor such as swimming. In contrast, investments in noisy sports, such as e.g., modern pentathlon, are associated with a higher risk.

Multi-Dimension and Multi-Channel Seismic-Ionospheric Coupling: Case Study of Mw 8.8 Concepcion Quake on 27 February 2010

GPS radio occultation (RO) technology can fully describe the subtle structure of the ionosphere. This paper discusses the dynamic abnormity observed by the RO data from the Constellation Observing System for Meteorology Ionosphere and Climate (FORMOSAT-3/COSMIC) before the great earthquake case in Concepcion, Chile (27 February 2010, Mw 8.8). Traditional ground-based GPS monitoring was considered as the external conditions and references to the excitation response. Using kriging interpolation, the global Nmf2 map (GNM) was first constructed to study the ionosphere deviation from the normal state. Successively, the ionosphere abnormality in the F2 region (Nmf2), vertical structure (RO profiles), and multiple heights (electron density) of traveling are unfolded. The Nmf2 disturbances in the possibility of seismic influences were excluded from non-seismic noise factors, including the external input (e.g., space weather activity, 15 February) and meteorological events (e.g., lower atmospheric forcing in quiet periods). However, the results show that there were apparent local Nmf2 perturbations for up to 5 h in the epicenter area on 21 and 25 February. The disturbances of the RO profiles and the interaction of other layers of the ionosphere implied the fluctuation signals of prominent long-wavelength fluctuations >50 km in the F layer. The ionospheric fluctuates wildly, and these wave signals considered as the trace of gravity wave propagating upward are mainly distributed at the elevation of 200–300 km. The simultaneous reaction of GNSS TEC further evidenced the potential possibility of acoustic gravity by the COSMIC RO profiles, reflecting the compounding couplings of seismo-ionosphere effects. In terms of the presentation of VLF radiation noise and the aerosol ion clusters, the electromagnetic and chemical channels have been previously completed by DEMETER and Terra/Aqua satellites. These findings implied the great potential of the FORMOSAT-7/COSMIC-2 system (now in the testing phase), with ~5000 soundings to investigate the subtle atmospheric stratification.

An efficient FPGA implementation of hand gestures recognition based on neural networks

Different gestures of hand which is a powerful communication channel between man to man and/or man to machine transfers a large amount of information in our daily lives. For example, sign languages are widely used by individuals with speech handicaps. Recognizing hand gestures in the image can be considered a powerful parameter in man-to-machine communication. Although researchers have been trying to implement different hand gestures on several hardware platforms over the past years, their attempts have been confronted by many challenges including restricted resources of hardware platforms, noise factors in the environment, or insufficient accuracy of output in high numbers of experimental samples. In this work, an optimum and parallelized method is developed to implement recognition of different hand gestures in the image on FPGA. The introduced method uses an MLP network with high numbers of hidden layers without wasting resources of the hardware platform. The results comparing the proposed optimized method with the state-of-the-art methods show that the suggested method can be implemented on an FPGA platform with high output accuracy and lower resources.

Classification of Weld Defects Based on Convolution Neural Network

Automatic welding technology has been widely applied in many industrial fields. It is a complex process with many nonlinear parameters and noise factors affecting weld quality. Therefore, it is necessary to inspect and evaluate the quality of the weld seam during welding process. However, in practice there are many types of welding seam defects, causes and the method of corrections are also different. Therefore, welding seam defects need to be classified to determine the optimal solution for the control process with the best quality. Previously, the welder used his experience to classify visually, or some studies proposed visual classification with image processing algorithms and machine learning. However, it requires a lot of time and accuracy is not high. The paper proposes a convolutional neural network structure to classify images of welding seam defects from automatic welding machines on pipes. Based on comparison with the classification results of some deep machine learning networks such as VGG16, Alexnet, Resnet-50, it shows that the classification accuracy is 99.46 %. Experimental results show that the structure of convolutional neural network is proposed to classify images of weld seam defects have availability and applicability

Applied Mechatronics: Designing a Sliding Mode Controller for Active Suspension System

The suspension system is referred to as the set of springs, shock absorbers, and linkages that connect the car to the wheel system. The main purpose of the suspension system is to provide comfort for the passengers, which is created by reducing the effects of road bumpiness. It is worth noting that reducing the effects of such vibrations also diminishes the noise and undesirable sound as well as the effects of fatigue on mechanical parts of the vehicle. Due to the importance of the abovementioned issues, the objective of this article is to reduce such vibrations on the car by implementing an active control method on the suspension system. For this purpose, a conventional first-order sliding mode controller has been designed for stochastic control of the quarter-car model. It is noteworthy that this controller has a significant ability to overcome the stochastic effects, uncertainty, and deal with nonlinear factors. To design a controller, the governing dynamical equation of the quarter-car system has been presented by considering the nonlinear terms in the springs and shock absorber, as well as taking into account the uncertainty factors in the system and the actuator. The design process of the sliding mode controller has been presented and its stability has been investigated in terms of the Lyapunov stability. In the current research, road surface variations are considered as Gaussian white noise. The dynamical system behavior for controlled and uncontrolled situations has been simulated and the extracted results have been presented. Besides, the effects of existing uncertainty in the suspension system and actuator have been evaluated and controller robustness has been checked. Also, the obtained quantitative and qualitative compressions have been presented. Moreover, the effect of controller parameters on the basin of attraction set and its extensiveness has been assessed. The achieved results have indicated the good performance and significant robustness of the designed controller to stabilize the suspension system and mitigate the effects of road bumpiness in the presence of uncertainty and noise factors.