No abstract

COVID-19 syndrome has extensively escalated worldwide with the induction of the year 2020 and has resulted in the illness of millions of people. COVID-19 patients bear an elevated risk once the symptoms deteriorate. Hence, early recognition of diseased patients can facilitate early intervention and avoid disease succession. This article intends to develop a hybrid deep neural networks (HDNNs), using computed tomography (CT) and X-ray imaging, to predict the risk of the onset of disease in patients suffering from COVID-19. To be precise, the subjects were classified into 3 categories namely normal, Pneumonia, and COVID-19. Initially, the CT and chest X-ray images, denoted as ‘hybrid images’ (with resolution 1080 × 1080) were collected from different sources, including GitHub, COVID-19 radiography database, Kaggle, COVID-19 image data collection, and Actual Med COVID-19 Chest X-ray Dataset, which are open source and publicly available data repositories. The 80% hybrid images were used to train the hybrid deep neural network model and the remaining 20% were used for the testing purpose. The capability and prediction accuracy of the HDNNs were calculated using the confusion matrix. The hybrid deep neural network showed a 99% classification accuracy on the test set data.

The start-up transient signals have been widely used for fault diagnosis of induction motor because they can reveal early defects in the development process, which are not easily detected with the signals in the steady state operation. However, transient signals are non-linear and contain multi components which need a suitable technique to process and identify the fault pattern. In this paper, the fault diagnosis problem of induction motor is conducted by a data driven framework where the Fourier-Bessel (FB) expansion is used as a tool to decompose transient current signal into series of single components. For each component, the statistical features in the time and the frequency domains are extracted to represent the characteristics of motor condition. The high dimensionality of the feature set is solved by generalized discriminant analysis (GDA) implementation to decrease the computational complexity of classification. In the meantime, with the aid of GDA, the separation of the feature clusters is increased, which enables the more classification accuracy to be achieved. Finally, the reduced dimensional features are used for classifier to perform the fault diagnosis results. The classifier used in this framework is the simplified fuzzy ARTMAP (SFAM) which belongs to a special class of neural networks (NNs) and provides a lower training time in comparison to other traditional NNs. The proposed framework is validated with transient current signals from an induction motor under different conditions including bowed rotor, broken rotor bar, eccentricity, faulty bearing, mass unbalance and phase unbalance. Additionally, this paper provides the comparative performance of (i) SFAM and support vector machine (SVM), (ii) SVM in the framework and SVM combined with wavelet transform in previous studies, (iii) the use of FB decomposition and Hilbert transform decomposition. The results show that the proposed diagnosis framework is capable of significantly improving the classification accuracy.

Nowadays, condition-based maintenance (CBM) and fault diagnosis (FD) of rotating machinery (RM) has a vital role in the modern industrial world. However, the remaining useful life (RUL) of machinery is crucial for continuous monitoring and timely maintenance. Moreover, reduced maintenance costs, enhanced safety, efficiency, reliability, and availability are the main important industrial issues to maintain valuable and high-cost machinery. Undoubtedly, induction motor (IM) is considered to be a pivotal component in industrial machines. Recently, acoustic emission (AE) becomes a very accurate and efficient method for fault, leaks and fatigue detection and monitoring techniques. Moreover, CM and FD based on the AE of IM have been growing over recent years. The proposed research study aims to review condition monitoring (CM) and fault diagnosis (FD) studies based on sound and AE for four types of faults: bearings, rotor, stator, and compound. The study also points out the advantages and limitations of using sound and AE analysis in CM and FD. Existing public datasets for AE based analysis for CM and FD of IM are also mentioned. Finally, challenges facing AE based CM and FD for RM, especially for IM, and possible future works are addressed in this study.

A low-profile frequency reconfigurable monopole antenna operating in the microwave frequency band is presented in this paper. The proposed structure is printed on Flame Retardant-4 (FR-4) substrate having relative permittivity of 4.3 and tangent loss of 0.025. Four pin diode switches are inserted between radiating patches for switching the various operating modes of an antenna. The proposed antenna operates in five modes, covering nine different bands by operating at single bands of 5 and 3.5 GHz in Mode 1 and Mode 2, dual bands (i.e., 2.6 and 6.5 GHz, 2.1 and 5.6 GHz) in Mode 3 and 4 and triple bands in Mode 5 (i.e., 1.8, 4.8, and 6.4 GHz). The Voltage Standing Waves Ratio (VSWR) of the presented antenna is less than 1.5 for all the operating bands. The efficiency of the designed antenna is 84 % and gain ranges from 1.2 to 3.6 dBi, respectively, at corresponding resonant frequencies. The achieve bandwidths at respective frequencies ranges from 10.5 to 28%. The proposed structure is modeled in Computer Simulation Technology microwave studio (CST MWS) and the simulated results are experimentally validated. Due to its reasonably small size and support for multiple wireless standards, the proposed antenna can be used in modern handheld fifth generation (5G) devices as well as Internet of Things (IoT) enabled systems in smart cities.

In this paper, a hybrid deep belief network is proposed to diagnose single and combined faults of suction and discharge valves in a reciprocating compressor. This hybrid integrates the deep belief network structured by multiple stacked restricted Boltzmann machines for pre-training and simplified fuzzy ARTMAP (SFAM) for fault classification. In the pre-training procedure, an algorithm for selecting local receptive fields is used to group the most similar features into the receptive fields of which top values are the units of each layer, and then restricted Boltzmann machine is applied to these units to construct a network. Unsupervised learning is also carried out for each restricted Boltzmann machine layer in this procedure to compute the network weights and biases. Finally, the network output is fed into SFAM to perform fault classification. In order to diagnose the valve faults, three signal types of vibration, pressure, and current are acquired from a two-stage reciprocating air compressor under different valve conditions such as suction leakages, discharge leakages, spring deterioration, and their combination. These signals are subsequently processed so that the useful fault information from the signals can be revealed; next, statistical features in the time and frequency domains are extracted from the signals and used as the inputs for hybrid deep belief network. Performance of hybrid deep belief network in fault classification is compared with that of the original deep belief network and the deep belief network combined with generalized discriminant analysis, where softmax regression is used as a classifier for the latter two models. The results indicate that hybrid deep belief network is more capable of improving the diagnosis accuracy and is feasible in industrial applications.

Pumps are the largest single consumer of power in industry. This means that faulty pumps cause a high rate of energy loss with associated performance degradation, high vibration levels and significant noise radiation. This paper investigates the correlations between pump performance parameters including head, flow rate and energy consumption and surface vibration for the purpose of both pump condition monitoring and performance assessment. Using an in-house pump system, a number of experiments have been carried out on a centrifugal pump system using five impellers: one in good condition and four others with different defects, and at different flow rates for the comparison purposes. The results have shown that each defective impeller performance curve (showing flow, head, efficiency and NPSH (Net Positive Suction Head) is different from the benchmark curve showing the performance of the impeller in good condition. The exterior vibration responses were investigated to extract several key features to represent the healthy pump condition, pump operating condition and pump energy consumption. In combination, these parameter allow an optimal decision for pump overhaul to be made [1].

The massive increase in disposable plastic globally can be addressed through effective recovery methods, and one of these methods is pyrolysis. R software may be used to statistically model the composition and yield of pyrolysis products, such as oil, gas, and waxes to deduce an effective pyrolysis mechanism. To date, no research reports have been documented employing the Arrhenius equation in R software to statistically forecast the kinetic rate constants for the pyrolysis of high-density plastics. We used the Arrhenius equation in R software to assume two series of activation energies (Ea) and pre-exponential factors (Ao) to statistically predict the rate constants at different temperatures to explore their impact on the final pyrolysis products. In line with this, MATLAB (R2020a) was used to predict the pyrolysis products of plastic in the temperature range of 370–410 °C. The value of the rate constant increased with the temperature by expediting the pyrolysis reaction due to the reduced frequency factor. In both assumed series of Ea and Ao, a significantly larger quantity of oil (99%) was predicted; however, the number of byproducts increased in the first series analysis compared to the second series analysis. It was revealed that an appropriate combination of Ea, Ao, and the predicted rate constants could significantly enhance the efficiency of the pyrolysis process. The major oil recovery in the first assumed series occurred at 390 °C to 400 °C, whereas the second assumed series of Ea and Ao occurred at 380 °C to 390 °C. In the second series at 390 °C to 400 °C, the predicted kinetic rate constants behaved aggressively after 120 min of the pyrolysis process. The second assumed series and anticipated rate constants at 380 °C to 390 °C can be applied commercially to improve oil production while saving energy and heat.