Search

The growing demand for Magnesium in the automotive and aviation industries has enticed the need to improve its corrosive properties. In this study, the WE43 magnesium alloys were friction stir welded (FSW) by varying the traverse speed. FSW eliminates defects such as liquefication cracking, expulsion, and voids in joints encountered frequently in fusion welding of magnesium alloys. The microstructural properties were scrutinized using light microscopy (LM) and scanning electron microscopy (SEM). Additionally, the elemental makeup of precipitates was studied using electron dispersive X-ray spectroscopy (EDS). The electrochemical behavior of specimens was evaluated by employing potentiodynamic polarization tests and was correlated with the microstructural properties. A defect-free weldment was obtained at a traverse and rotational speed of 100 mm/min and 710 rpm, respectively. All weldments significantly improved corrosion resistance compared to the base alloy. Moreover, a highly refined microstructure with redistribution/dissolution of precipitates was obtained. The grain size was reduced from 256 µm to around 13 µm. The corrosion resistance of the welded sample was enhanced by 22 times as compared to the base alloy. Hence, the reduction in grain size and the dissolution/distribution of secondary-phase particles within the Mg matrix are the primary factors for the enhancement of anti-corrosion properties.

In this study, the Integral Resonant Controller (IRC) is presented along with the Proportional-Derivative (PD) controller as a novel control technique to control the dynamical behaviors of the 12-pole rotor active magnetic bearing system. According to the proposed control strategy, the system model has been derived as a two-degree-of-freedom nonlinear dynamical system coupled with two first-order filters. The obtained mathematical model has been analyzed utilizing the asymptotic analysis. The nonlinear algebraic system that governs the steady-state vibration amplitudes and corresponding phase angles of the considered system has been extracted. The influence of the IRC control parameters on the rotor dynamics has been explored by plotting the different bifurcation diagrams. The analytical investigations demonstrated that the vibration suppression efficiency of the combined controller (i.e., PD and IRC) is proportional to the product of control and feedback gains of the IRC as well as the derivative gain of the PD-controller. In addition, it is found that the controller efficiency is inversely proportional to both the square of the internal loop feedback gain of the IRC and the position gain of the PD-controller. Accordingly, an objective function has been derived to design the best control gains of the proposed controller strategy. The analytical and numerical simulations confirmed that the suggested control method can suppress the system vibration and eliminate the catastrophic bifurcation behaviors if the control gains are selected according to the proposed objective function. Finally, the effect of failing one of the coupled integral resonant controllers on the rotor dynamics has been explored as a precautionary procedure. It is found that the failure of one of the coupled integral resonant controllers may breakdown the bifurcation symmetry of the rotor system, but the system does not lose its stability.

Industry 5.0 provides resource-efficient solutions compared to Industry 4.0. Edge Computing (EC) allows data analysis on edge devices. Artificial intelligence (AI) has become the focus of interest in recent years, particularly in industrial applications. The coordination of AI at the edge will significantly improve industry performance. This paper integrates AI and EC for Industry 5.0 to defend against data poisoning attacks. A hostile user or node injects fictitious training data to distort the learned model in a data poisoning attack. This research provides an effective data poisoning defense strategy to increase the learning model’s performance. This paper developed a novel data poisoning defense federated split learning, DepoisoningFSL, for edge computing. First, a defense mechanism is proposed against data poisoning attacks. Second, the optimal parameters are determined for improving the performance of the federated split learning model. Finally, the performance of the proposed work is evaluated with a real-time dataset in terms of accuracy, correlation coefficient, mean absolute error, and root mean squared error. The experimental results show that DepoisoningFSL increases the performance accuracy.

Generally, the risks associated with malicious threats are increasing for the IIoT and its related applications due to dependency on the Internet and the minimal resource availability of IoT devices. Thus, anomaly-based intrusion detection models for IoT networks are vital. Distinct detection methodologies need to be developed for the IIoT network as threat detection is a significant expectation of stakeholders. Machine learning approaches are considered to be evolving techniques that learn with experience, and such approaches have resulted in superior performance in various applications, such as pattern recognition, outlier analysis, and speech recognition. Traditional techniques and tools are not adequate to secure IIoT networks due to the use of various protocols in industrial systems and restricted possibilities of upgradation. In this paper, the objective is to develop a two-phase anomaly detection model to enhance the reliability of an IIoT network. In the first phase, SVM and Naive Bayes are integrated using an ensemble blending technique. K-fold cross-validation is performed while training the data with different training and testing ratios to obtain optimized training and test sets. Ensemble blending uses a random forest technique to predict class labels. An Artificial Neural Network (ANN) classifier that uses the Adam optimizer to achieve better accuracy is also used for prediction. In the second phase, both the ANN and random forest results are fed to the model's classification unit, and the highest accuracy value is considered the final result. The proposed model is tested on standard IoT attack datasets, such as WUSTL_IIOT-2018, N_BaIoT, and Bot_IoT. The highest accuracy obtained is 99%. The results also demonstrate that the proposed model outperforms traditional techniques and thus improves the reliability of an IIoT network.

The active magnetic bearings system plays a vital role in high-speed rotors technology, where many research articles have discussed the nonlinear dynamics of different categories of this system such as the four-pole, six-pole, eight-pole, and sixteen-pole systems. Although the twelve-pole system has many advantages over the eight-pole one (such as a negligible cross-coupling effect, low power consumption, better suspension behaviors, and high dynamic stiffness), the twelve-pole system oscillatory behaviors have not been studied before. Therefore, this article is assigned to explore the effect of the magneto-electro-mechanical nonlinearities on the oscillatory motion of the twelve-pole system controlled via a proportional derivative controller for the first time. The normalized equations of motion that govern the system vibrations are established by means of classical mechanics. Then, the averaging equations are extracted utilizing the asymptotic analysis. The influence of all system parameters on the steady-state oscillation amplitudes is explored. Stability charts in a two-dimensional space are constructed. The stable margin of both the system and control parameters is determined. The obtained investigations reveal that proportional gain plays a dominant role in reshaping the dynamics and motion bifurcation of the twelve-pole systems. In addition, it is found that stability charts of the system can be controlled by simply utilizing both the proportional and derivative gains. Moreover, the numerical simulations showed that the twelve-poles system can exhibit both quasiperiodic and chaotic oscillations besides the periodic motion depending on the control parameters’ magnitude.

Laser processing of materials finds application in micro-nano devices mainly because of its accuracy, flexibility, and ability to machine almost any material. Although it offers numerous advantages, it is a complex process involving a large number of factors. The quality of machining often depends on the appropriate selection of parameters. Moreover, the output responses in machining processes have conflicting nature; some are to be minimized, and others have to be maximized. This work uses grey relationship analysis coupled with principal component analysis for multi-response optimization of conflicting responses during laser machining of micro-channels. Micro-channels with a cross-sectional size of 200 × 100 µm were created using Nd:YAG laser beam micro-milling in steel alloy (AISI 1045). The scan speed, layer thickness, and scan strategy were found to have a significant effect on the dimensional accuracy of the microchannel. At the same time, the material removal rate was mostly influenced by layer thickness. Multi-response optimization results suggest low pulse frequency, high scan speed, low layer thickness, and S3 scan strategy for accurately fabricating micro-channels.

Data classification has been considered extensively in different fields, such as machine learning, artificial intelligence, pattern recognition, and data mining, and the expansion of classification has yielded immense achievements. The automatic classification of maintenance data has been investigated over the past few decades owing to its usefulness in construction and facility management. To utilize automated data classification in the maintenance field, a data classification model is implemented in this study based on the analysis of different mechanical maintenance data. The developed model involves four main steps: (a) data acquisition, (b) feature extraction, (c) feature selection, and (d) classification. During data acquisition, four types of dataset are collected from the benchmark Google datasets. The attributes of each dataset are further processed for classification. Principal component analysis and first-order and second-order statistical features are computed during the feature extraction process. To reduce the dimensions of the features for error-free classification, feature selection was performed. The hybridization of two algorithms, the Whale Optimization Algorithm (WOA) and Spotted Hyena Optimization (SHO), tends to produce a new algorithm&mdash, i.e., a Spotted Hyena-based Whale Optimization Algorithm (SH-WOA), which is adopted for performing feature selection. The selected features are subjected to a deep learning algorithm called Recurrent Neural Network (RNN). To enhance the efficiency of conventional RNNs, the number of hidden neurons in an RNN is optimized using the developed SH-WOA. Finally, the efficacy of the proposed model is verified utilizing the entire dataset. Experimental results show that the developed model can effectively solve uncertain data classification, which minimizes the execution time and enhances efficiency.

Clustering in wireless sensor networks plays a vital role in solving energy and scalability issues. Although multiple deployment structures and cluster shapes have been implemented, they sometimes fail to produce the expected outcomes owing to different geographical area shapes. This paper proposes a clustering algorithm with a complex deployment structure called radial-shaped clustering (RSC). The deployment structure is divided into multiple virtual concentric rings, and each ring is further divided into sectors called clusters. The node closest to the midpoint of each sector is selected as the cluster head. Each sector&rsquo, s data are aggregated and forwarded to the sink node through angular inclination routing. We experimented and compared the proposed RSC performance against that of the existing fan-shaped clustering algorithm. Experimental results reveal that RSC outperforms the existing algorithm in scalability and network lifetime for large-scale sensor deployments.

Inspection planning is considered an essential practice in the manufacturing industries because it ensures enhanced product quality and productivity. A reasonable inspection plan, which can reduce inspection costs and achieve high customer satisfaction, is therefore very important in the production industry. Considerations such as preparations for part inspection, measuring machines, and their setups as well as the measurement path are described in an inspection plan which is subsequently translated into part inspection machine language. Therefore, the measurement of any component using a coordinate measuring machine (CMM) is the final step preceded by several other procedures, such as the preparation of the part setup and the generation of the probe path. Effective measurement of components using CMM can only be done if the preceding steps are properly optimized to automate the whole inspection process. This paper has proposed a method based on artificial intelligence techniques, namely, artificial neural network (ANN) and genetic algorithm (GA), for fine-tuning output from the different steps to achieve an efficient inspection plan. A case study to check and validate the suggested approach for producing effective inspection plans for CMMs is presented. A decrease of nearly 50% was observed in the travel path of the probe, whereas the CMM measurement time was reduced by almost 25% during the actual component measurement. The proposed method yielded the optimum part setup and the most appropriate measuring sequence for the part considered.

A mixture of Titanium and silicon-carbide powders was embedded in the AA5083 matrix by Friction Stir Processing (FSP). Experiments were performed as per Taguchi L8 orthogonal array, and the effect of reinforcement on hot strength (at 100 °C), processed zone (PZ) geometry, and microstructure were investigated. The effect of PZ geometry on the surface properties was also analyzed. The effect of heating the tensile test specimens to 540 °C on the strength at 100 °C was also separately investigated. It was observed that surface hardness was significantly enhanced by FSP, and the highest mean hardness of 90.4 HV was observed. Furthermore, it was observed that the surface properties also significantly depend on PZ geometry. From experimental results, it was found that the specimens with the lowest width to depth ratio bears the highest hardness and vice versa. A clear effect of parameters was evident on the geometry of processed zones with a deep bowl, and shallow cup-shaped zones were formed with smaller and larger shoulder diameters, respectively. The samples were processed at 355 rpm, 63 mm min−1, 17 mm shoulder, and 355 rpm, 80 mm min−1. The 20 mm shoulder showed high tensile strength 292 MPa and 294 Mpa, respectively. The strength of these samples did not reduce much even after heating to 540 °C.

Intelligent machining has become an important part of manufacturing systems because of the increased demand for productivity. Tool condition monitoring is an integral part of these systems. Airborne acoustic emission from the machining process is a vital indicator of tool health, however, it is highly affected by background noise. Reducing the background noise helps in developing a low-cost system. In this research work, a feedforward neural network is used as an adaptive filter to reduce the background noise. Acoustic signals from four different machines in the background are acquired and are introduced to a machining signal at different speeds and feed-rates at a constant depth of cut. These four machines are a three-axis milling machine, a four-axis mini-milling machine, a variable speed DC motor, and a grinding machine. The backpropagation neural network shows an accuracy of 75.82% in classifying the background noise. To reconstruct the filtered signal, a novel autoregressive moving average (ARMA)-based algorithm is proposed. An average increase of 71.3% in signal-to-noise ratio (SNR) is found before and after signal reconstruction. The proposed technique shows promising results for signal reconstruction for the machining process.