Search results

Rotating machinery is a crucial component of large equipment, and detecting faults in it accurately is critical for reliable operation. Although fault diagnosis methods based on deep learning have been significantly developed, the existing methods model spatial and temporal features separately and then weigh them, resulting in the decoupling of spatiotemporal features.

The authors propose a spatiotemporal long short-term memory (ST-LSTM) method for fault diagnosis of rotating machinery. The authors collected vibration signals from real rolling bearing and gearing test rigs for verification.

Through these two experiments, the authors demonstrate that machine learning methods still have advantages on small-scale data sets, but our proposed method exhibits a significant advantage due to the simultaneous modeling of the time domain and space domain. These results indicate the potential of the interactive spatiotemporal modeling method for fault diagnosis of rotating machinery.

The authors propose a ST-LSTM method for fault diagnosis of rotating machinery. The authors collected vibration signals from real rolling bearing and gearing test rigs for verification.

Rotating machineries are widely used in manufacturing, petroleum, chemical, aircraft, and other industries. To accurately identify the operating conditions of such rotating machineries, this paper aims to propose a fault diagnosis method based on sensitive dimensionless parameters and particle swarm optimization (PSO)–support vector machine (SVM) for reducing the unexpected downtime and economic losses.

A relatively new hybrid intelligent fault classification approach is proposed by integrating multiple dimensionless parameters, the Fisher criterion and PSO–SVM. In terms of data pre-processing, a method based on wavelet packet decomposition (WPD), empirical mode decomposition (EMD) and dimensionless parameters is proposed for the extraction of the vibration signal features. The Fisher criterion is applied to reduce the redundant dimensionless parameters and search for the sensitive dimensionless parameters. Then, PSO is adapted to optimize the penalty parameter and kernel parameter for SVM. Finally, the sensitive dimensionless parameters are classified with the optimized model.

As two different time–frequency analysis methods, a method based on a combination of WPD and EMD used to extract multiple dimensionless parameters is presented. More vital diagnosis information can be obtained from the vibration signals than by only using a single time–frequency analysis method. Besides, a fault classification approach combining the sensitive dimensionless parameters and PSO-SVM classifier is proposed. The comparative experiment results show that the proposed method has a high classification accuracy and efficiency.

To the best of the authors’ knowledge, very few efforts have been performed for fault classification using multiple dimensionless parameters. In this paper, eighty dimensionless parameters have been studied intensively, which provides a new strategy in fault diagnosis field.

A numerical study is performed to investigate turbulent flow characteristics in a pipe rotating around the axis. Emphasis is placed on the effect of pipe rotation on the friction coefficient and velocity distribution in the hydrodynamically, fully‐developed flow region. The k—ε turbulence model is modified by taking the swirling effect into account, in which the model function including the Richardson number is introduced to the ε equation. The governing boundary‐layer equations are discretized by means of a control volume finite‐difference technique for numerical computation. Results obtained from the modified model agree well with experiment data in the existing literature. It is found from the study that (i) an axial rotation of the pipe induces an attenuation in the turbulent kinetic energy, resulting in a reduction in the friction coefficient, the turbulent and (ii) an increase in the velocity ratio causes substantial decreases in the friction coefficient, the turbulent kinetic energy and the streamwise velocity gradient near the wall.

This paper aims to present the analytical investigation on an unsteady magneto-convective rotation of an electrically conducting non-Newtonian Casson hybrid nanoliquid past a vertical porous plate. The effects of thermal radiation, heat source/sink and hydrodynamic slip phenomenon are also taken into account. Ethylene glycol (EG) is adopted as a base Casson fluid. The Casson fluid model is accounted for to describe the rheological characteristics of non-Newtonian fluid. EG with copper and alumina nanoparticles is envisaged as a non-Newtonian Casson hybrid nanoliquid. The copper-alumina-ethylene glycol hybrid nanoliquid is considered as the regenerative coolant.

The perturbation method is implemented to develop the analytical solution of the modeled equations. Acquired solutions are used to calculate the shear stresses and the rate of heat transfer in terms of amplitudes and phase angles. Numerical results are figured out and tabled to inspect the physical insights of various emerging parameters on the pertinent flow characteristics.

This exploration discloses that the velocity profiles are strongly diminished by the slip parameter. Centrifugal and Coriolis forces caused by the plate rotation are found to significantly change the entire flow regime. The supplementation of nanoparticles is to lessen the amplitude of the heat transfer rate. A comparative study is carried out to understand the improvement of heat transfer characteristics of Casson hybrid nanoliquid and Casson nanoliquid. However, the Casson hybrid nanoliquid exhibits a lower rate of heat transfer than the usual Casson nanoliquid.

This proposed model would be pertinent in oceanography, meteorology, atmospheric science, power engineering, power and propulsion generation, solar energy transformation, thermoelectric and sensing material processing, tumbler in polymer manufacturing, etc. Motivated by such practical implications, the proposed study has been unfolded.

The novelty of this paper is to examine the simultaneous effects of the magnetic field, Coriolis force, suction/injection, slip condition and thermal radiation on non-Newtonian Casson hybrid nanoliquid flow past an oscillating vertical plate subject to periodically heating in a rotating frame of reference. A numerical comparison is also made with the existing published results under some limiting cases and it is found that the results are in good agreement with them. An in-depth review of the literature and the author’s best understanding find that such aspects of the problem have so far remained unexplored.

The purpose of this study is to analyze an unsteady MHD Darcy flow of nonNewtonian hybrid nanoliquid past an exponentially accelerated vertical plate under the influence of velocity slip, Hall and ion slip effects in a rotating frame of reference. The fluids in the flow domain are assumed to be viscously incompressible electrically conducting. Sodium alginate (SA) has been taken as a base Casson liquid. A strong uniform magnetic field is applied under the assumption of low magnetic Reynolds number. Effect of Hall and ion-slip currents on the flow field is examined. The ramped heating and time-varying concentration at the plate are taken into consideration. First-order homogeneous chemical reaction and heat absorption are also considered. Copper and alumina nanoparticles are dispersed in base fluid sodium alginate to be formed as hybrid nanoliquid.

The model problem is first formulated in terms of partial differential equations (PDEs) with physical conditions. Laplace transform method (LTM) is used on the nondimensional governing equations for their closed-form solution. Based on these results, expressions for nondimensional shear stresses, rate of heat and mass transfer are also determined. Graphical presentations are chalked out to inspect the impacts of physical parameters on the pertinent physical flow characteristics. Numerical values of the shear stresses, rate of heat and mass transfer at the plate are tabulated for various physical parameters.

Numerical exploration reveals that a significant increase in the secondary flow (i.e. crossflow) near the plate is guaranteed with an augmenting in Hall parameter or ion slip parameter. MHD and porosity have an opposite effect on velocity component profiles for both types of nanoliquids. Result addresses that both shear stresses are strongly enhanced by the Casson effect. Also, hybrid nanosuspension in Casson fluid (sodium alginate) exhibits a lower rate of heat transfer than usual nanoliquid.

This model may be pertinent in cooling processes of metallic infinite plate in bath and hybrid magnetohydrodynamic (MHD) generators, metallurgical process, manufacturing dynamics of nanopolymers, magnetic field control of material processing, synthesis of smart polymers, making of paper and polyethylene, casting of metals, etc.

The originality of this study is to obtain an analytical solution of the modeled problem by using the Laplace transform method (LTM). Such an exact solution of nonNewtonian fluid flow, heat and mass transfer is rare in the literature. It is also worth remarking that the influence of Hall and ion slip effects on the flow of nonNewtonian hybrid nanoliquid is still an open question.

Condition monitoring using sensing techniques to predict disaster before it happens, is becoming increasingly important. Stephen McClelland reports.

The purpose of this study is to analyze the Entropy generation analysis and heat transport in three-dimensional flow between two stretchable disks. Joule heating and heat generation/absorption are incorporated in the thermal equation. Thermo-diffusion effect is also considered. Flow is conducting for time-dependent applied magnetic field. Induced magnetic field is not taken into consideration. Velocity and thermal slip conditions at both the disks are implemented. The flow problem is modeled by using Navier–Stokes equations with entropy generation rate and Bejan number.

Von Karman transformations are used to reduce the nonlinear governing expressions into an ordinary one and then tackled by homotopy analysis method for convergent series solutions. The nonlinear expressions for total entropy generation rate are obtained with appropriate transformations. The impacts of different flow variables on velocity, temperature, entropy generation rate and Bejan number are described graphically. Velocity, temperature and concentration gradients are discussed in the presence of flow variables.

Axial, radial and tangential velocity profiles show decreasing trend for larger values of velocity slip parameters. For a larger Brinkman number, the entropy generation increases, while a decreasing trend is noticed for Bejan number.

To the best of the authors’ knowledge, no such analyses have been reported in the literature.

At present, one of the key equipment in pillar industries is a large rotating machinery. Conducting regular health monitoring is important for ensuring safe operation of the large rotating machinery. Because vibrations sensors play an important role in the workings of the rotating machinery, measuring its vibration signal is an important task in health monitoring. This paper aims to present these.

In this work, the contact vibration sensor and the non-contact vibration sensor have been discussed. These sensors consist of two types: the electric vibration sensor and the optical fiber vibration sensor. Their applications in the large rotating machinery for the purpose of health monitoring are summarized, and their advantages and disadvantages are also presented.

Compared with the electric vibration sensor, the optical fiber vibration sensor of large rotating machinery has unique advantages in health monitoring, such as provision of immunity against electromagnetic interference, requirement of less insulation and provision of long-distance signal transmission.

Both contact vibration sensor and non-contact vibration sensor have been discussed. Among them, the electric vibration sensor and the optical fiber vibration sensor are compared. Future research direction of the vibration sensors is presented.

This paper aims to develop a theoretical method to analyze the rotation accuracy of rotating machinery with multi-support structures. The method effectively considers the geometric errors and assembly deformation of parts.

A method composed of matrix and FEA methods is proposed to do the analysis. The deviation propagation analysis results and external loads are set as boundary conditions of the model which is built with Timoshenko beam elements to calculate the spatial pose of the rotor. The calculation is performed repeatedly as the rotation angle increased to get the rotation trajectories of concerned nodes, and further evaluation is done to get the rotation accuracy. Additionally, to get more reliable results, the bearing motion errors and stiffness are analyzed by a static model considering manufacturing errors of parts.

The feasibility of the proposed method is verified through a case study of a high-precision spindle. The method reasonably predicts the rotation accuracy of the spindle.

For rotating machinery with multi-support structures, the paper proposes a modeling method to predict the rotation accuracy, simultaneously considering geometric errors and assembly deformation of parts. This would improve the accuracy of tolerance analysis.