Condition Monitoring to Enable Predictive Maintenance on a Six-Die Nut Manufacturing Machine through Force Data Analysis

Nut fasteners are produced by machines working around the clock. Companies generally operate with a run-to-failure or planned maintenance approach. Even with a planned maintenance schedule, however, undetected damage to the dies and non-die parts occurring between maintenance periods can cause considerable downtime and pervasive damage to the machine. To address this shortcoming, force data from the fourth and sixth dies of a six-die nut manufacturing machine were analysed using correlation to the best health condition on the force profile and on the force shock response spectrum profile. Fault features such as quality adjustments and damage to both die and non-die parts were detectable prior to required maintenance or machine failure. This detection was facilitated by the determination of health thresholds, whereby the force SRS profile generated a longer warning period prior to failure. The analytical approach could benefit the industry by identifying damage that would normally go undetected by operators, thereby reducing downtime, extending die life, enabling “as needed” maintenance, and optimising machine operation.

Bearing Intelligent Fault Diagnosis Based on Convolutional Neural Networks

The traditional intelligent identification method requires a complex feature extraction process and much diagnosis experience, considering the characteristics of one dimension of bearing vibration signals, a new method of intelligent fault diagnosis based on 1-dimensional convolutional neural network is presented. This method automatically extracts features from frequency domain signals and avoids artificial feature selection and feature extraction. The proposed method is validated on bearing benchmark datasets, these datasets are collected in different fault location, different health conditions and different operating conditions. The result shows that the proposed method can not only adaptively obtain representative fault features from the datasets, but also achieve higher diagnosis accuracy than the existing methods.

A frequency-weighted energy operator and swarm decomposition for bearing fault diagnosis

The weak fault characteristics of rolling bearings are difficult to identify due to strong background noise. To address this issue, a bearing fault detection scheme combining swarm decomposition (SWD) and frequency-weighted energy operator (FWEO) is presented. First, SWD is applied to decompose the bearing fault signal into single mode components. Then, a new evaluation index termed LEP is constructed by combining the advantages of envelope entropy, Pearson correlation coefficient and L-kurtosis, and it is utilized to choose the sensitive component containing the richest bearing fault characteristics. Finally, FWEO is employed for extracting the bearing fault features from the sensitive component. Simulation and experimental analyses indicate that the LEP index has better performance than the L-kurtosis index in determining the sensitive component. The method has the effect of suppressing noise and enhancing impulse characteristics, which is superior to the SWD-based envelope demodulation method.

Fault diagnosis of rolling bearings based on improved direct fast iterative filtering and spectral amplitude modulation

As the transient impulse components in early fault signals are weak and easily buried by strong background noise, the fault features of rolling bearings are difficult to be extracted effectively. Focusing on this issue, a novel method based on improved direct fast iterative filtering and spectral amplitude modulation (IDFIF-SAM) is presented for detecting the early fault of rolling bearings. First, the ratio of the average crest factor of autocorrelation envelope spectrum to the average envelope entropy is taken as the fitness function to search the optimal parameters of direct fast iterative filtering (DFIF) adaptively via particle swarm optimization (PSO). Then, the efficient kurtosis entropy (EKE) index is being employed to choose the suitable components to reconstruct the signal. Finally, the reconstructed signal is subjected to spectral amplitude modulation (SAM) to strengthen the impulse features. The superiority of improved direct fast iterative filtering (IDFIF) over fixed-parameter DFIF, fast iterative filtering (FIF), and hard thresholding fast iterative filtering (HTFIF) is clarified through the simulated signal. Moreover, the comparative experimental analysis shows that the proposed IDFIF-SAM method can identify the early fault feature of rolling bearings more effectively.

Fault diagnosis of rolling bearings based on multi-scale deep subdomain adaptation network

This study presents a fault diagnosis method for rolling bearing based on multi-scale deep subdomain adaptation network (MSDSAN). The proposed MSDSAN, as improvement of deep subdomain adaptation network (DSAN), is an unsupervised transfer learning method. MSDSAN reduces the subdomain distribution discrepancy between domains rather than marginal distribution discrepancy, and so better domain invariant fault features are derived to avoid misalignment between domains. Aiming at avoiding fault information loss by fixed receptive fields feature extraction, selective kernel convolution module is introduced into feature extraction of MSDSAN, by which multiple receptive fields are applied to ensure an optimal receptive field for each working condition. Moreover, contribution rates are adaptively assigned to all receptive fields, and the disturbing information extracted by inappropriate receptive fields is further eliminated. As a result, more comprehensive and effective fault information is derived for bearing fault diagnosis. Fault diagnosis experiment of bearings is performed to verify the superiority of the proposed method, and the experimental results demonstrate that MSDSAN achieves better transfer effects and higher accuracy than SOTA methods under varying working conditions.

Weak Fault Feature Extraction of Rolling Bearing Based on SVMD and Improved MOMEDA

In order to solve the problem that it is very difficult to extract fault features directly from the weak impact component of early fault signal of rolling bearing, a method combining continuous variational mode decomposition (SVMD) with modified MOMEDA based on Teager energy operator is proposed. Firstly, the low resonance impulse component in the fault signal is separated from the harmonic component and noise by SVMD, and then the Teager energy operator is used to enhance the impulse feature in the low resonance component to ensure that the accurate fault period is selected by the MOMOEDA algorithm. After further noise reduction by MOMEDA, the envelope spectrum of the signal is analyzed, and finally the fault location is determined. The results of simulation and experimental data show that this method can accurately and effectively extract the characteristic frequency of rolling bearing weak fault.

A New Fault Diagnosis Model for Circuits in Railway Vehicle Based on the Principal Component Analysis and the Belief Rule Base

Circuits are considered an important part of railway vehicles, and circuit fault diagnosis in the railway vehicle is also a research hotspot. In view of the nonlinearity and diversity of track circuit components, as well as the diversity and similarity of fault phenomena, in this paper, a new fault diagnosis model for circuits based on the principal component analysis (PCA) and the belief rule base (BRB) is proposed, which overcomes the shortcomings of the circuit fault diagnosis method based on data, model, and knowledge. In the proposed model, to simplify the model and improve the accuracy, PCA is used to reduce the dimension of the key fault features, and varimax rotation is used to deduce the fault features. BRB is used to combine qualitative knowledge and quantitative data effectively, and evidential reasoning (ER) algorithm is used to carry out the inference of knowledge. The initial parameters of the model are optimized, and the optimal precondition attributes, rule weights, and belief degree parameters are obtained to improve the accuracy. Through the training and testing of the model, the experimental results show that the method can accurately diagnose the fault of the driver controller potentiometer in the railway vehicle. Compared with other methods, the model shows high accuracy.

Reliable Fault Diagnosis of Bearings Using an Optimized Stacked Variational Denoising Auto-Encoder

Variational auto-encoders (VAE) have recently been successfully applied in the intelligent fault diagnosis of rolling bearings due to its self-learning ability and robustness. However, the hyper-parameters of VAEs depend, to a significant extent, on artificial settings, which is regarded as a common and key problem in existing deep learning models. Additionally, its anti-noise capability may face a decline when VAE is used to analyze bearing vibration data under loud environmental noise. Therefore, in order to improve the anti-noise performance of the VAE model and adaptively select its parameters, this paper proposes an optimized stacked variational denoising autoencoder (OSVDAE) for the reliable fault diagnosis of bearings. Within the proposed method, a robust network, named variational denoising auto-encoder (VDAE), is, first, designed by integrating VAE and a denoising auto-encoder (DAE). Subsequently, a stacked variational denoising auto-encoder (SVDAE) architecture is constructed to extract the robust and discriminative latent fault features via stacking VDAE networks layer on layer, wherein the important parameters of the SVDAE model are automatically determined by employing a novel meta-heuristic intelligent optimizer known as the seagull optimization algorithm (SOA). Finally, the extracted latent features are imported into a softmax classifier to obtain the results of fault recognition in rolling bearings. Experiments are conducted to validate the effectiveness of the proposed method. The results of analysis indicate that the proposed method not only can achieve a high identification accuracy for different bearing health conditions, but also outperforms some representative deep learning methods.

A multiscale kernel-based network with improved attention mechanism for rotating machinery fault diagnosis under noisy environment

Considering the vibration signals are easily contaminated by the strong and highly non-stationary noise, extracting more sensitive and effective features from the noised vibration signals is still a great challenge for intelligent fault diagnosis of rotating machinery. This paper proposed a multiscale kernel-based network with improved attention mechanism (IA-MKNet) to overcome this challenge. In the proposed method, an improved attention mechanism (IAM) for multiscale convolution is firstly developed to adaptively extract the meaningful fault features and automatically suppress noise. Then, due to the inherent multiple time characteristics of vibration signals, an adaptive multiscale kernel-based residual block (AMKRB) with IAM is designed to capture fault features in multi-time scales of vibration signals. Finally, a combination strategy based on an adaptive ensemble learner is proposed to increase the diversity of features by fusing the outputs of multiple IA-MKNets, which further improves diagnosis accuracy and stability. The experimental results, verified by two bearing datasets with noise interference, confirm that the proposed method improves the fault diagnosis accuracy of rotating machinery under noisy environment, which performance is superior to the other five benchmark methods.

Gearbox compound fault diagnosis based on a combined MSGMD-MOMEDA method

Weak fault detection is a complex and challenging task when two or more faults (compound fault) with discordant severity occur in different parts of a gearbox. The weak fault features are prone to be submerged by the severe fault features and strong background noise, which easily lead to a missed diagnosis. To solve this problem, a novel diagnosis method combining muti-symplectic geometry mode decomposition and multipoint optimal minimum entropy deconvolution adjusted (MSGMD-MOMEDA) is proposed for gearbox compound fault in this paper. Specifically, different fault components are separated by the improved symplectic geometry mode decomposition (SGMD), namely, multi-SGMD (MSGMD) method. The weak fault features are enhanced by the multipoint optimal minimum entropy deconvolution adjusted (MOMEDA). In the process of research, a new scheme of selecting key parameters of MOMEDA is proposed, which is a key step in applying MOMEDA. Compared with SGMD, the proposed MSGMD has two main improvements, including suppressing mode mixing and preventing the generation of the pseudo components. Compared with the original method of selecting parameters based on multipoint kurtosis, the proposed MOMEDA parameters selecting scheme has more merits of high accuracy and precision. The analysis results of two cases of simulation and experiment signal reveal that the MSGMD-MOMEDA method can accurately diagnose the gearbox compound fault even under strong background noise.