Adaptive multiscale wavelet-guided periodic sparse representation for bearing incipient fault feature extraction

Currently, accurately extracting early-stage bearing incipient fault features is urgent and challenging. This paper introduces a novel method called adaptive multiscale wavelet-guided periodic sparse representation(AMWPSR) to address this issue. For the first time, the dual-tree complex wavelet transform is applied to construct the linear transformation for the AMWPSR model.This transform offers superior shift invariance and minimizes spectrum aliasing. By integrating this linear transformation with the generalized minimax concave penalty term, a new sparse representation model is developed to recover faulty impulse components from heavily disturbed vibration signals. During each iteration of the AMWPSR process, the impulse periods of sparse signals are adaptively estimated, and the periodicity of the latest sparse signal is augmented using the final estimated period. Simulation studies demonstrate that AMWPSR can effectively estimate periodic impulses even in noisy environments, demonstrating greater accuracy and robustness in recovering faulty impulse components than existing techniques.Further validation through research on two sets of bearing life cycle data shows that AMWPSR delivers superior fault diagnosis results.

A Novel De-noising Method Based on Discrete Cosine Transform and Its Application in the Fault Feature Extraction of Hydraulic Pump

Aiming at the existing problems of discrete cosine transform(DCT) de-noising method, we introduce the idea of wavelet neighboring coefficients(WNC) de-noising method, and propose the cosine neighboring coefficients(CNC) de-noising method. Based on DCT, a novel method for the fault feature extraction of hydraulic pump is analyzed. The vibration signal of pump is de-noised with CNC de-noising method, and the fault feature is extracted by performing Hilbert-Huang transform(HHT) to the output signal. The analysis results of the simulation signal and the actual one demonstrate that the proposed CNC de-noising method and the fault feature extraction method have more superior ability than the traditional ones.

Fault diagnosis of rolling bearings with noise signal based on modified kernel principal component analysis and DC‐ResNet

In view of the influence of aliasing noise on the effectiveness and accuracy of bearing fault diagnosis,a bearing fault diagnosis algorithm based on the spatial decoupling method of modified kernel principal component analysis(MKPCA)and the residual network with deformable convolution(DC‐ResNet)is innovatively proposed.Firstly,the Gaussian noise with different signal‐to‐noise ratios(SNRs)is added to the data to simulate the different degrees of noise in the actual data acquisition process.The MKPCA is used to project the fault signal with different SNRs in the kernel space to reduce the data dimension and eliminate some noise effects.Finally,the DC‐ResNet model is used to further filter the noise effects and fully extract the fault features through the training of the preprocessed data.The proposed algorithm is tested on the Case Western Reserve University(CWRU)and Xi'an Jiaotong University and Changxing Sumyoung Technology Co.,Ltd.(XJTU‐SY)bearing data sets with different SNR noise.The fault diagnosis accuracy can reach 100%within 30 min,which has better performance than most of the existing methods.The experimental results show that the algorithm has an excellent effect on accuracy and computation complexity under different noise levels.

Machine learning based online fault prognostics for nonstationary industrial process via degradation feature extraction and temporal smoothness analysis

Fault degradation prognostic, which estimates the time before a failure occurs and process breakdowns, has been recognized as a key component in maintenance strategies nowadays. Fault degradation processes are, in general,slowly varying and can be modeled by autoregressive models. However, industrial processes always show typical nonstationary nature, which may bring two challenges: how to capture fault degradation information and how to model nonstationary processes. To address the critical issues, a novel fault degradation modeling and online fault prognostic strategy is developed in this paper. First, a fault degradation-oriented slow feature analysis(FDSFA) algorithm is proposed to extract fault degradation directions along which candidate fault degradation features are extracted. The trend ability assessment is then applied to select major fault degradation features. Second, a key fault degradation factor(KFDF) is calculated to characterize the fault degradation tendency by combining major fault degradation features and their stability weighting factors. After that, a time-varying regression model with temporal smoothness regularization is established considering nonstationary characteristics. On the basis of updating strategy, an online fault prognostic model is further developed by analyzing and modeling the prediction errors. The performance of the proposed method is illustrated with a real industrial process.

Geophysical Features of the Ore-Controlling Fault in the Chang'an Gold Deposit, Southern Yunnan Province

The Ailao Mountain is one of the most important metallogenic belts ofpolymetallic deposits in the Sanjiang region, southwestern China. Located in the southern segment of this metallogenic belt, the newly-discovered Chang＇an gold deposit is large in scale （Fig. 1A）, and has attracted much attention among geologists. The ore-hosted rocks in the district include the Late Ordovician Xiangyang Fm. sandstone and clastic rocks and the Early Silurian Kanglang Fm. dolomite. Affected by the multistage tectonic activities, stocks and dykes of lamprophyre, dolerite, syenite porphyry and orthoclasite are widely exposed, and the orebodies are in symbiosis with or crosscut the dyke rocks.

2D-HIDDEN MARKOV MODEL FEATURE EXTRACTION STRATEGY OF ROTATING MACHINERY FAULT DIAGNOSIS

A new feature extraction method based on 2D-hidden Markov model（HMM） is proposed. Meanwhile the time index and frequency index are introduced to represent the new features. The new feature extraction strategy is tested by the experimental data that collected from Bently rotor experiment system. The results show that this methodology is very effective to extract the feature of vibration signals in the rotor speed-up course and can be extended to other non-stationary signal analysis fields in the future.

Active Feature of the Ganzi-Yushu Fault Zone in the Late Quaternary

Based on regional geological mapping results and interpretation of satellites images and areophotos in combination with detailed field study,this paper gives the spatial distribution of recent surface activity of the Ganzi-Yushu fault zone(GYF).According to faulted landform as well as deformation and displacement of young deposit layers,the slip rates of GYF since the late Quaternary are briefly studied,combined with the results of geological chronology(14C and Thermoluminescene dating).The result shows that the average slip rates of GYF is differentiate along different segments:Ganzi segment:horizontal rate is 3.4±0.3 mm/a,vertical rate is 2.2±0.1 mm/a;Manigange segment:horizontal rate is 7.0±0.7 mm/a;Denke segment:horizontal rate is 7.2±1.2 mm/a;Dangjiang segment:horizontal rate is 7.3±0.6 mm/a.

Cultural Binary Particle Swarm Optimization Algorithm and Its Application in Fault Diagnosis

Binary particle swarm optimization algorithm(BPSOA) has the excellent characters such as easy to implement and few set parameters.But it is tendentious to stick in the local optimal solutions and has slow convergence rate when the problem is complex.Cultural algorithm(CA) can exploit knowledge extracted during the search to improve the performance of an evolutionary algorithm and show higher intelligence in treating complicated problems.So it is proposed that integrating binary particle swarm algorithm into cultural algorithm frame to develop a more efficient cultural binary particle swarm algorithm (CBPSOA) for fault feature selection.In CBPSOA,BPSOA is used as the population space of CA;the evolution of belief space adopts crossover,mutation and selection operations;the designs of acceptance function and influence function are improved according to the evolution character of BPSOA.The tests of optimizing functions show the proposed algorithm is valid and effective.Finally,CBPSOA is applied for fault feature selection.The simulations on Tennessee Eastman process (TEP) show the CBPSOA can perform better and more quickly converge than initial BPSOA.And with fault feature selection,more satisfied performance of fault diagnosis is obtained.

Component fault diagnosis for nonlinear systems

In the field of fault diagnosis, the state equation of nonlinear system, including the actuator and the component, has been established. When the faults in the system appear, it is difficult to observe the fault isolation between the actuator and the component. In order to diagnose the component fault in the nonlinear systems, a novel strategy is proposed. The nonlinear state equation with only the component system is built on mathematical equations. The nonlinearity of the component equation is expanded and estimated with Taylor series. If the actuator is perfect, the anomaly of the state equations reflects the component fault. The fault feature index is defined to detect the component fault and the initial fault. The numerical examples of the component faults are simulated for multiple-input multiple-output(MIMO)nonlinear systems. The results show that the component faults,as well as the incipient faults, can be detected. Furthermore, the effectiveness of the proposed strategy is verified. This method can also provide a foundation for the component fault reconfiguration control.

AUTO-EXTRACTING TECHNIQUE OF DYNAMIC CHAOS FEATURES FOR NONLINEAR TIME SERIES

The main purpose of nonlinear time series analysis is based on the rebuilding theory of phase space, and to study how to transform the response signal to rebuilt phase space in order to extract dynamic feature information, and to provide effective approach for nonlinear signal analysis and fault diagnosis of nonlinear dynamic system. Now, it has already formed an important offset of nonlinear science. But, traditional method cannot extract chaos features automatically, and it needs man＇s participation in the whole process. A new method is put forward, which can implement auto-extracting of chaos features for nonlinear time series. Firstly, to confirm time delay r by autocorrelation method; Secondly, to compute embedded dimension m and correlation dimension D; Thirdly, to compute the maximum Lyapunov index λmax; Finally, to calculate the chaos degree Dch of Poincare map, and the non-circle degree Dnc and non-order degree Dno of quasi-phase orbit. Chaos features extracting has important meaning to fault diagnosis of nonlinear system based on nonlinear chaos features. Examples show validity of the proposed method.

Characteristics of fault structures in the south coastal zone of Taizhou based on aeromagnetic data

The south coastal of Taizhou lies on the magmatic rock belt along the southeast coast of China,which has a complex regional geological structures,intense tectonic movement,and frequent magmatic activities.On the basis of the latest aeromagnetic data,combined with regional geology,gravity,and magnetic susceptibility information,integrated interpretation of the regional aeromagnetic anomalies and their refl ected faults was completed.According to the block features in diff erent zones of the reduction to the pole aeromagnetic data,the magnetic field characteristics and relationship with the structure division were described in detail.The different characteristics of the magnetic field are the concentrated reflection of tectonic movements,magmatic activities,and stratigraphic distributions;the fault structure,especially deep and large fault structures,was inferred and studied.The fault structures were mainly distributed in the NE,NNE,and NW directions,with approximately equal spacing between them.The magnetic anomaly is mainly characterized by the boundary,gradient zones,and beaded anomalies in a different magnetic field.The faults are not only important tectonic boundaries in this region but also tectonic belts that control the distribution of mineralization.Under the interaction of these faults,they form the basic structural pattern of the east-west zone and the north-south block.The NE faults have the largest scale and obviously control the diff erent magnetic fi elds and magmatic activities.The results can provide a reference for further study of the distribution and activity characteristics of magmatic rocks in the coastal zone.

Simulation analysis of wear characteristics of connecting rod bearing bush based on improved mixed lubrication model

The failure rate of crankpin bearing bush of diesel engine under complex working conditions such as high temperature,dynamic load and variable speed is high.After serious wear,it is easy to deteriorate the stress state of connecting rod body and connecting rod bolt,resulting in serious accidents such as connecting rod fracture and body damage.Based on the mixed lubrication characteristics of connecting rod big endbearing shell of diesel engine under high explosion pressure impact load,an improved mixed lubrication mechanism model is established,which considers the influence of viscoelastic micro deformation of bearing bush material,integrates the full film lubrication model and dry friction model,couples dynamic equation of connecting rod.Then the actual lubrication state of big end bearing shell is simulated numerically.Further,the correctness of the theoretical research results is verified by fault simulation experiments.The results show that the high-frequency impact signal with fixed angle domain characteristics will be generated after the serious wear of bearing bush and the deterioration of lubrication state.The fault feature capture and alarm can be realized through the condition monitoring system,which can be applied to the fault monitoring of connecting rod bearing bush of diesel engine in the future.

Investigation of Bearing Fault Diagnosis Based on Explicit Dynamics Analysis in ANSYS/LS-DYNA

In this paper, deep grove ball bearing GB6206 has been chosen as research object, and the explicit dynamics analysis method in ANSYS/LS-DYNA has been used to study features of fault bearing which with a tiny pit in the inner ring raceway. In the process of building this bearing FEM, the following parameters have been well considered, such as boundary conditions, friction, contaction, loads and so on. Through simulation, the corresponding equivalent stress nephograms and acceleration of nodes on the inner ring raceway has been obtained. According to features of acceleration which occurs neighbor to fault pit, bearing＇s fault diagnosis has been realized. This paper provides a new way in monitoring bearing status and diagnosing fault of bearing.