查看更多>>摘要：? 2022 Elsevier LtdCurrently, the analysis method based on monitoring data has become an effective means of machinery fault diagnosis, and the fault diagnosis with obvious data features has achieved fruitful results. However, the incipient fault signals of equipment not only show the characteristics of weak intensity, quasi periodic and non-stationary, but also are submerged in strong background noise, which often makes it difficult to extract effective information directly from the original signals. Therefore, in order to effectively solve the problem of incipient fault diagnosis, and considering the capability of sparse autoencoder (SAE) to extract features automatically, this paper proposes a key-factor denoising strategy and an improved SAE network, and then an improved SAE network with key-factor denoising strategy (KF-ISAE) based intelligent diagnosis method for quasi periodic non-stationary incipient faults is proposed. The main contributions of the proposed method are as follows. On the one hand, signal denoising that cannot be ignored in fault diagnosis is achieved by the developed incipient faults sensitivity based key-factor denoising strategy, and on the other hand, for SAE, the blindness of feature learning is handled by the formed weights constraints. In addition, the health condition identification and the fault severity level determination of machinery are completed by the improved SAE network designed in this paper. Finally, verification and comparative experiments show the effectiveness and practicability of the proposed method.
查看更多>>摘要：? 2022 Elsevier LtdFor the hybrid magnetically suspended flywheel (MSFW) with radial two degrees of freedom (DOFs) active magnetic bearing (AMB) and axial three DOFs AMB, the vibration analysis, measurement and balancing are conducted to mitigate the influences caused by unbalance terms in this article. Firstly, the force models of MSFW rotor are developed, and the vibration phenomenon caused by the residual unbalance mass of flywheel rotor is analyzed. Furthermore, the vibration testing platform for measuring the vibration of MSFW on five DOFs is introduced, and then the vibration balancing method is investigated. Finally, the vibration magnitude of MSFW rotor induced by the residual unbalance mass is analyzed by measuring dynamic displacements, and the effectiveness of vibration balancing method is verified by comparing vibration magnitudes and power spectrum densities of the MSFW system with different situations, the static unbalance term is reduced by 90.5%, and the dynamic unbalance term is reduced by 82.4%.
查看更多>>摘要：? 2022 Elsevier LtdEffective use of biomedical sensor image can help locate diseased tissues and tissue structures clearly presented, and clinical diagnosis and treatment can assist doctors in making appropriate treatment plans. In order to efficiently process the images acquired by biomedical sensors, we propose a biomedical sensor image segmentation method with improved fully convolutional network, which firstly extracts the local spatial and frequency domain information of the images acquired by biomedical sensors and enhances the texture information of the images. Secondly, the background interference is suppressed by increasing the target region weights to refine the processing of the image and enhance the features of the image while reducing the information redundancy. It is experimentally proved that the model in this paper can effectively reduce the phenomenon of cell adhesion after image segmentation, has better segmentation effect and segmentation accuracy, and can more effectively utilize the images acquired by biomedical sensors.
Guru Prathap Reddy V.Tadepalli T.Kumar Pancharathi R.
14页
查看更多>>摘要：? 2022 Elsevier LtdThis study presents a methodology for imaging-based quantification of deterioration in concrete structures due to various chemical attacks, using HSI colour space. In this study, M30 grade of concrete samples are exposed to various deterioration agents like 5% concentrated solutions of NaCl, HCl, H2SO4 and MgSO4 for a period of 3,7,14 and 28 days respectively. The changes in surface colour profiles over time, due to chemical attack, are quantified within the HSI space. The numerical values of H show a little variation in the range of chemical exposure studied in the research. However, when combined with the variations of S and I, the deterioration of concrete structures can be assessed. Further, the correlation between the change of surface colour and deterioration of compressive strength is established by destructive testing. The change in surface colour between any two time intervals enables identification of the specific attacking chemical and estimation of the duration of attack as well as the residual strength of concrete. This novel approach enables establishment of empirical relationships between HSI values and residual compressive strength, towards visual-spectrum based quantification of the extent and duration of deterioration.
查看更多>>摘要：? 2022Online signature verification (OSV) as a critical link of the paperless office still has tremendous challenges. In this paper, we propose a novel Writer-Independent (WI) OSV framework that includes three parts. (1) The two-dimensional (2D) representation method is designed to transform the original time-series signature data into stroke images with dynamic-static hybrid information. (2) The Channel-wise Weight Learning (CWL) mechanism is integrated into the feature extractor to mine the potential relationship between three dynamic attributes (altitude, azimuth, and pressure). (3) A new Triplet Supervised Network (TSN) that contains three weight-shared convolution neural network (CNN) streams was provided to measure the distance of [Anchor, Positive, Test]. The experimental results show that our model has at least 1.29% accuracy improvement when confronted with skilled forgery signatures than that of other classical CNNs and 11.43% than lightweight models. Moreover, the TSN model is superior to the previous OSV algorithms in the WI pattern.
查看更多>>摘要：? 2022 Elsevier LtdThe objective of this work is to study the response of phase calibrated Phase Doppler Particle Analyser (PDPA) in presence of various arrangement schemes of optical materials and thickness of the test section window. The standard “Mono sized droplet generator” (MDG) has been used as a source of mono sized droplets stream. Receiving optics collection angle, Bandpass filter, and Photo-multiplier tube (PMT) voltage has been optimized using a known mono-size droplet stream. The results indicate that maximum perturbation in response occurs in presence of 17.5 mm Plexiglas thickness. The reduction in 97% of data rate is noted in Scheme B, whereas no data has been observed for the case of Scheme D. The maximum data rate reduction of 15.9% is observed in 17.5 mm Plexiglas of Scheme D for aligned PDPA subsystem. The results of the experiment also reveal that when unpolished glass is used instead of Plexiglas, the maximum date rate reduction is 70% for 17.5 mm for Scheme D whereas when subsystems are aligned then maximum loss of data rate is 11.3%, which are significantly higher to losses due to Plexiglas.
查看更多>>摘要：? 2022 Elsevier LtdDetecting main shaft bearing anomaly is crucial to ensure the safe operation of wind turbines. However, existing anomaly detection methods have a limitation that anomaly samples are required for hyper-parameters tuning. Because of the scarcity of anomaly samples in the real-world scenarios, it is difficult to implement such existing methods in real-world applications. This paper proposes an end-to-end anomaly detection algorithm named one-class Shapelet dictionary learning. Firstly, the loss function of Shapelet dictionary learning is modified by integrating a soft-boundary term, so that the features and decision boundary can be learnt jointly. Then, a hyper-parameter setting strategy is introduced, so that anomaly samples are not needed in the training stage. The proposed method is validated through a case study collected from a real-world wind power farm. Results shown that the proposed method has a better F1 score than all baselines while anomaly samples are totally banded in the training stage.
查看更多>>摘要：? 2022 Elsevier LtdVibration-based approaches have been widely adopted in determining the cable tension force. The development of effective length concept has been successfully applied in revealing the cable force regardless type of end-restraints. Simultaneously, the two-mode frequency approach can determine the tension force without knowing the bending stiffness of cables, but the formulas are limited only for the cable with hinged-hinged restraints. By taking advantage of these two methods, the present study aims to extend the two-mode frequency approach by introducing equivalent effective length for any mode pairs regardless type of end-restraints. To verify the proposed formula, three cases of cable end-restraints: hinged–hinged, fixed–fixed and hinged–fixed with the same tensioning force and cross-sectional properties, are studied. Validation using laboratory data and demonstration in a real cable force identification are also presented.
查看更多>>摘要：? 2022 The AuthorsThe physics and quantification of sediment transport are still a challenge for scientists and engineers. Measurements of wave-induced sediment velocities may be conducted only in selected laboratories and require weeks of pre-tests and a very experienced team. In this study, student psychology-based optimization (SPBO) algorithm was applied to develop new integrated machine learning methods for the determination of wave-induced non-cohesive sediment particle velocities over a rippled bed by incorporating the outcome of particle image velocimetry. Easily measurable data comprising sediment characteristics, bedform details, and hydrodynamic conditions were used to train the machine learning models. The developed techniques determine well the sediment particle horizontal velocity over a horizontal profile. The analysis shows that the derived models nearly perfectly predict observed data. The proposed methodology provides insight into the physics of sediment processes and may also be applied to interpret measurement data and verify sediment transport models.
查看更多>>摘要：? 2022 Elsevier LtdIn recent statistics, lung cancer is the most severe cause of death among all type of cancers. Here, we are presenting a nondestructive and noninvasive imaging methodology for lung cancer detection i.e., microwave holographic reflectometry. A precise tissue equivalent lung phantom is proposed and developed with the tumor inside for various depth and positions. Multiple experiments have been performed with the tumor at multiple depths inside the lung at operating frequency i.e., 10 GHz. The qualitative findings show that the tumor of size 5 mm is detected and identified at various depths during multiple experiments. The reconstructed phase values and dielectric properties are used to calculate the exact depth of tumors. The proof of concept presented in the paper determines the position and depth of the tumor within the lungs. Since, there is a utilization of miniaturized components, the entire system becomes small, which can be further improved to make the technique a viable alternative to CT scanning.
NSTL
Elsevier