Compound Fault Diagnosis for Rotating Machinery:State-of-the-Art,Challenges,and Opportunities

Compound fault,as a primary failure leading to unexpected downtime of rotating machinery,dramatically increases the difficulty in fault diagnosis.To deal with the difficulty encountered in implementing compound fault diagnosis(CFD),researchers and engineers from industry and academia have made numerous significant breakthroughs in recent years.Admittedly,many systematic surveys focused on fault diagnosis have been conducted by reputable researchers.Nevertheless,previous review articles paid more attention to fault diagnosis with several single or independent faults,resulting in that there is still lacking a comprehensive survey on CFD.Therefore,to fulfill the above requirements,it is necessary to provide an in-depth overview of fault diagnosis methods or algorithms for compound faults of rotating machinery and uncover potential challenges or opportunities that would guide and inspire readers to devote their efforts to promoting fault diagnosis technology more effective and practical.Specifically,the backgrounds,including the related definitions and a new taxonomy of CFD methods,are detailed according to the way of implementing compound fault recognition.Then,the stateof-the-art applications of CFD are overviewed based on relevant publications in the past decades.Finally,the challenges and opportunities associated with implementing CFD are concluded and followed by a conclusion for ending this survey.We believe that this review article can provide a systematic guideline of CFD from different aspects for potential readers and seasoned researchers.

The application on order analysis for the rotating machinery with LabVIEW

Order analysis is regarded as one of the most significant method for monitoring and analyzing rotational machinery for the phenomenon of " frequency smear".However,the order analysis based on resampling is a signal processingwhich converts the constant time interval sampling into constant angle interval sampling,while with the variety of the rotational speed.The superiority of the order analysis is investigatedon implement of order analysis.Andthrough comparing the advantage and disadvantage between spectrum and order analysis,the paper will discuss the order analysis form a deep perspective.

Influence of Operating Parameters on Unbalance in Rotating Machinery Using Response Surface Method

Wide range of rotating machinery contains an inherent amount of unbalance which leads to increase in the vibration level and related faults.In this work,the effect of different operating conditions viz.the unbalanced weight,radius,speed and position of the rotor disc on the unbalance in rotating machine are studied experimentally and analyzed by using Response Surface Methodology(RSM).RSM is a technique which consists of mathematical and statistical methods to develop the relationship between the inputs and outputs of a system by distinct functions.L27 Orthogonal Array(OA)was developed by using Design of Experiments(DOE)according to which experimentation has been carried out.Three accelerometer sensors were mounted to record the vibration responses(accelerations)in radially vertical,horizontal and axial directions.The responses recorded as root mean square values are then analysed using RSM.The relationship between response and operating factors has been established by developing a second order,non-linear mathematical model.Analysis of variance(ANOVA)has been performed for verification of the developed mathematical models.Results obtained from the analysis show that the unbalance weight and speed are most significant operating conditions that contribute the most to the effect the unbalance has on the rotating spindle.

Research on Rotating Machinery Fault Diagnosis Based on Improved Multi-target Domain Adversarial Network

Aiming at the problems of low efficiency,poor anti-noise and robustness of transfer learning model in intelligent fault diagnosis of rotating machinery,a new method of intelligent fault diagnosis of rotating machinery based on single source and multi-target domain adversarial network model(WDMACN)and Gram Angle Product field(GAPF)was proposed.Firstly,the original one-dimensional vibration signal is preprocessed using GAPF to generate the image data including all time series.Secondly,the residual network is used to extract data features,and the features of the target domain without labels are pseudo-labeled,and the transferable features among the feature extractors are shared through the depth parameter,and the feature extractors of the multi-target domain are updated anatomically to generate the features that the discriminator cannot distinguish.The modelt through adversarial domain adaptation,thus achieving fault classification.Finally,a large number of validations were carried out on the bearing data set of Case Western Reserve University(CWRU)and the gear data.The results show that the proposed method can greatly improve the diagnostic efficiency of the model,and has good noise resistance and generalization.

Bionics-Inspired Structure Boosts Drag and Noise Reduction of Rotating Machinery

As a global concern,environmental protection and energy conservation have attracted significant attention.Due to the large carbon emission of electricity,promoting green and low-carbon transformation of the power industry via the synergistic development of clean energy sources is essential.Rotating machinery plays a crucial role in pumped storage,hydropower generation,and nuclear power generation.Inspired by bionics,non-smooth features of creatures in nature have been introduced into the structure design of efficient rotating machines.First,the concept and classification of bionics are described.Then,the representative applications of non-smooth surface bionic structures in rotating machineries are systematically and comprehensively reviewed,such as groove structure,pit structure,and other non-smooth surfaces.Finally,conclusions are drawn and future directions are presented.The effective design of a bionic structure contributes toward noise reduction,drag reduction and efficiency improvement of rotating machineries.Green and ecological rotating machinery will remarkably reduce energy consumption and contribute to the realization of the“double carbon”goal.

A modified VLES model for simulation of rotating separation flow in axial flow rotating machinery

The internal flow in an axial flow rotating machinery is affected by the rotating characteristics, often accompanied by a strong rotating separation under small flow conditions. At present, the very large eddy simulation (VLES) model commonly used for the separation flow simulation still has certain limitations in simulating such rotating separation flow: (1) The Reynolds stress level is overestimated in the near-wall region. (2) The influence of the rotating effect cannot be effectively considered. The above two limitations affect the simulation accuracy of the VLES model for the rotating separation flow under small flow conditions in the axial flow rotating machinery. The objective of this paper is to provide a new hybrid unsteady Reynolds average Navier-Stokes/large eddy simulation (URANS/LES) model suitable for the simulation of the rotating separation flow in an axial flow rotating machinery. Compared with the original VLES method, the modifications are as follows: (1) A Reynolds stress damping function in the near-wall region is introduced to reduce the overestimation of the Reynolds stress caused by the near-wall Reynolds average Navier-Stokes (RANS) behavior of the VLES model. (2) A control function driven by the vortex is introduced to reflect the influence of the rotating effect. Three typical cases are used to verify the calculation accuracy of the modified model. It is shown that the modified model can capture more turbulent vortices based on the URANS grids, and the prediction accuracy of the rotating separation flow is effectively improved. Compared with the original VLES model, the modified model can accurately predict the head change in the hump region of the axial flow pump.

Imbalanced fault diagnosis of rotating machinery using autoencoder-based SuperGraph feature learning

Existing fault diagnosis methods usually assume that there are balanced training data for every machine health state.However,the collection of fault signals is very difficult and expensive,resulting in the problem of imbalanced training dataset.It will degrade the performance of fault diagnosis methods significantly.To address this problem,an imbalanced fault diagnosis of rotating machinery using autoencoder-based SuperGraph feature learning is proposed in this paper.Unsupervised autoencoder is firstly used to compress every monitoring signal into a low-dimensional vector as the node attribute in the SuperGraph.And the edge connections in the graph depend on the relationship between signals.On the basis,graph convolution is performed on the constructed SuperGraph to achieve imbalanced training dataset fault diagnosis for rotating machinery.Comprehensive experiments are conducted on a benchmarking publicized dataset and a practical experimental platform,and the results show that the proposed method can effectively achieve rotating machinery fault diagnosis towards imbalanced training dataset through graph feature learning.

A Three-Dimensional Gas-Kinetic BGK Scheme for Simulating Flows in Rotating Machinery

This paper focuses on the development and application of a threedimensional gas-kinetic Bhatnagar-Gross-Krook(BGK)method for the viscous flows in rotating machinery.For such flows,a rotating frame of reference is usually used in formulating the Navier-Stokes(N-S)equations,and there are two major concerns in constructing the corresponding BGK model.One is the change of the convective velocities in the N-S equations,which can be reflected through modification of the gas streaming velocity.The other one is the necessity to account for the effect of the additional Coriolis and centrifugal forces.Here,a specifically-designed acceleration term is added into the modified Boltzmann equation so that the source effects can be naturally included into the gas evolution process and the resulted fluxes.Under the finitevolume framework,the constructed BGK model is locally solved at each cell interface and then the numerical fluxes can be evaluated.When employing the BGK scheme,it is sometimes found that the calculated spatial derivatives of the initial and equilibrium distribution functions are sensitive to the mesh quality especially in complex rotating flow applications,which may significantly influence flux evaluation.Therefore,an improved approach for computing these slopes is adopted,through which the modeling capability for viscous flows is enhanced.For validation,several numerical examples are presented.The computed results show that the present method can be well applied to a wide range of flows in rotating machinery with favorable accuracy.

Gradient Optimizer Algorithm with Hybrid Deep Learning Based Failure Detection and Classification in the Industrial Environment

Failure detection is an essential task in industrial systems for preventing costly downtime and ensuring the seamlessoperation of the system. Current industrial processes are getting smarter with the emergence of Industry 4.0.Specifically, various modernized industrial processes have been equipped with quite a few sensors to collectprocess-based data to find faults arising or prevailing in processes along with monitoring the status of processes.Fault diagnosis of rotating machines serves a main role in the engineering field and industrial production. Dueto the disadvantages of existing fault, diagnosis approaches, which greatly depend on professional experienceand human knowledge, intellectual fault diagnosis based on deep learning (DL) has attracted the researcher’sinterest. DL reaches the desired fault classification and automatic feature learning. Therefore, this article designs a Gradient Optimizer Algorithm with Hybrid Deep Learning-based Failure Detection and Classification (GOAHDLFDC)in the industrial environment. The presented GOAHDL-FDC technique initially applies continuous wavelettransform (CWT) for preprocessing the actual vibrational signals of the rotating machinery. Next, the residualnetwork (ResNet18) model was exploited for the extraction of features from the vibration signals which are thenfed into theHDLmodel for automated fault detection. Finally, theGOA-based hyperparameter tuning is performedtoadjust the parameter valuesof theHDLmodel accurately.The experimental result analysis of the GOAHDL-FD Calgorithm takes place using a series of simulations and the experimentation outcomes highlight the better resultsof the GOAHDL-FDC technique under different aspects.

Study of Axial Vibration of a Motor-Compressor System Using Operational Modal Analysis

A case study of excessive vibration on a motor-compressor system is presented in this paper.After barely two months of operation,the reciprocating compressor motor’s routine monitoring revealed excessive axial vibration amplitude.For this reason,the Operational Modal Analysis(OMA)was carried out in order to identify the pri-mary cause.According to the investigation,one of the harmonic components which was 18 times the motor’s running speed matched with a resonance frequency of 112 Hz.According to OMA study,the motor was vibrating in torsional motion because the compressor’s load had stimulated the entire motor-compressor unit at this reso-nance frequency.The analysis also demonstrates the bulging effect of the motor shaft’s axial vibration on the motor’s endplate.

An Example of Multiplane Balancing Techniques in Situ

This paper presents the dynamic motion response by rotor unbalance malfunctions and the restraints available to oppose these applied forces and corrective techniques that can be used to reduce the effects of mass unbalance.The mass unbalance is the most common and frequent anomaly in rotating machines,and therefore,although there are many computer programs that solve many cases,we believe it is important to remember his theory here.About this subject should techniques for correcting unbalance problems described in this document be applied.And,more importantly,a tape is made without disassembling the machine,if the transducers described in this work are installed.

Magnetic circuit optimization and experimental study of new internally excited automatic balancing

Mass imbalance-induced vibration affects the rotating machinery very large,especially the highspeed types.Off-line balancing techniques have been widely developed for rejecting unbalance-induced vibration but do not eliminate unbalanced vibration in the working state.Moreover,multiple start-stops are required in off-line balancing techniques.Therefore,research on an efficient electromagnetically-driven auto-balancer is carried out in the present work,and an internal excitation actuator is designed in this balancer.The electromagnetic characteristics of the two copper coil bobbins in the internal excitation actuator are compared and analyzed.The permanent magnets inside the actuator are simulated and analyzed with different sections of round,rectangular,and elliptical.And the results show that the elliptic type has the largest self-locking force.Finally,the dynamic balance test is performed on a test bench equipped with a designed electromagnetic balancing actuator,and the unbalance vibration is reduced from 130.23 μm to 5.98 μm.

A Regularized LSTM Method for Predicting Remaining Useful Life of Rolling Bearings

Rotating machinery is important to industrial production. Any failure of rotating machinery, especially the failure of rolling bearings, can lead to equipment shutdown and even more serious incidents. Therefore, accurate residual life prediction plays a crucial role in guaranteeing machine operation safety and reliability and reducing maintenance cost. In order to increase the forecasting precision of the remaining useful life(RUL) of the rolling bearing, an advanced approach combining elastic net with long short-time memory network(LSTM) is proposed, and the new approach is referred to as E-LSTM. The E-LSTM algorithm consists of an elastic mesh and LSTM, taking temporal-spatial correlation into consideration to forecast the RUL through the LSTM. To solve the over-fitting problem of the LSTM neural network during the training process, the elastic net based regularization term is introduced to the LSTM structure.In this way, the change of the output can be well characterized to express the bearing degradation mode. Experimental results from the real-world data demonstrate that the proposed E-LSTM method can obtain higher stability and relevant values that are useful for the RUL forecasting of bearing. Furthermore, these results also indicate that E-LSTM can achieve better performance.

An experimental study of rotational pressure loss in rotor-stator gap

The annular gap between rotor and stator is an inevitable flow path of a throughflow ventilated electrical machine,but the flow entering the rotor-stator gap is subjected to the effects of rotation.The pressure loss and volumetric flow rate across the rotor-stator gap were measured and compared between rotating and stationary conditions.The experimental measurements found that the flow entering the rotor-stator gap is affected by an additional pressure loss.In the present study,the rotational pressure loss at the entrance of rotor-stator gap is characterised.Based upon dimensional analysis,the coefficient of entrance loss can be correlated with a dimensionless parameter,i.e.rotation ratio.The investigation leads to an original correlation for the entrance loss coefficient of rotor-stator gap arisen from the Coriolis and centrifugal effects in rotating reference frame.

Adaptive sensitive frequency band selection for VMD to identify defective components of an axial piston pump

The underlying study investigates single valued neutrosophic entropy based adaptive sensitive frequency band selection for variational mode decomposition(VMD)for the purpose of identifying defective components in an axial pump.The proposed methodology is applied in the following steps.First,VMD is applied for decomposing vibration signals into various frequency bands,called as modes.After computing energy of each VMD,the lower(minimum)and upper(maximum)bounds from these energy readings are extracted for defect conditions,such as outer race,inner race,worn piston,faulty cylinder and valve plate,and blocked hole of the piston.Thereafter,energy interval ranges are obtained and further converted into the form of single valued neutrosophic sets(SVNSs).Then,the proposed neutrosophic entropy measure is deployed for quantifying the non-linear connection between each bearing defect conditions and various frequency bands.The mode having maximum neutrosophic entropy value is designated to the“most sensitive”frequency band.Thereafter,envelope demodulation is applied to the most sensitive selected frequency band for finding defective components.The proposed neutrosophic entropy and VMD based methodology is effective in providing a better insight for selecting suitable frequency band for carrying out envelope demodulation in comparison to existing methods.