Search

Thermoplastic vulcanizates (TPVs) is composed of crosslinked rubber and plastic and have recently been used to replace traditional rubber. To investigate their constitutive behavior throughout the fatigue life, a series of tensile fatigue tests were carried out. The experimental results show significant fatigue softening of TPV, which can be regarded as the joint action of fatigue damage and fatigue creep. After many cycles, the viscous flow can also be restored; thus, the fatigue creep was eliminated by the cyclic‐pause‐cyclic experiment. The cyclic curves were obtained when the fatigue damage was the only effect. Based on a visco‐hyperelastic constitutive model, the evolution rate of the constitutive model parameters during fatigue damage was obtained using the network alteration theory. Considering fatigue damage and fatigue creep effect together, a fatigue‐softening constitutive model is proposed. The model can predict the constitutive behavior of TPVs over their entire fatigue life. Highlights: A fatigue softening constitutive model for thermoplastic vulcanizates is proposed.A fatigue softening mechanism of thermoplastic vulcanizates is proposed.Fatigue behavior of thermoplastic vulcanizates were tested and modeled. [ABSTRACT FROM AUTHOR]

In recent years, deep transfer learning techniques have been successfully applied to solve RUL prediction across different working conditions. However, for RUL prediction across different machines in which the data distribution and fault evolution characteristics vary largely, the extraction and transition of prognostic knowledge become more challenging. Even if fault mode information can assist in the knowledge transfer, model bias will inevitably exist on the target machine with mixed or unknown faults. To address this issue from a transferability perspective, this paper proposes a novel selective transfer learning approach for RUL prediction across machines. First, the paper utilizes the tensor representation to construct the meta-degradation trend of each fault mode and evaluates the transferability of source domain data from fault mode and degradation characteristics through a new cross-machine transfer degree indicator (M-TDI). Second, a Long Short-Term Memory (LSTM)-based selective transfer strategy is proposed using the M-TDIs. The paper designs a training algorithm with an alternating optimization scheme to seek the optimal tensor decomposition and knowledge transfer effect. Theoretical analysis proves that the proposed approach significantly reduces the upper bound of prediction error. Furthermore, experimental results on three benchmark datasets prove the effectiveness of the proposed approach. • We propose a novel tensor representation-based transferability evaluation metric. • We propose a selective transfer learning method for RUL prediction across machines. • We design a new training algorithm to guarantee prognostic knowledge transfer effect. • We theoretically prove the upper bound of prediction error is significantly reduced. • Transferability analytics is helpful to task with large data distribution divergence. [ABSTRACT FROM AUTHOR]

In many applications, it is not easy to generate enough whole-life data for training a deep neural network, which may reduce the performance of a health indicator (HI). To solve this problem, a new HI construction method based on deep transfer learning is proposed in this article. First, a new multiscale domain-adversarial neural network is proposed to extract representative features from the data collected under different working conditions. By introducing the maximum mean discrepancy regularizer and the Laplace regularizer, this model can enhance features’ discriminant ability for incipient fault and exploit overall degradation information simultaneously. Then, a new HI is obtained via dimensionality reduction based on the extracted features. Moreover, a new HI assessment metric is proposed to effectively estimate the performance of the obtained HI. This new index considers not only the nonlinear correlation but also the geometric similarity of the degradation processes under different working conditions. Comparative experiments are conducted on the IEEE PHM Challenge 2012 bearing data set and the XJTU-SY bearing data set. The results show that the proposed method outperforms several typical transfer learning methods and nontransferable deep learning methods in terms of monotonicity and correlation. [ABSTRACT FROM AUTHOR]

This article presents a new deep transfer learning method, named structured domain adversarial neural network (SDANN), for bearing fault diagnosis with the data collected under different working conditions. The key idea of this method is integrating the strong adaptability of domain adversarial neural network (DANN) and structured relatedness information among multiple failure modes to improve the effect of transfer learning. First, for fine-grained alignment between the data collected from different working conditions, a new loss function with a discriminative regularizer is designed for DANN by using maximum correlation entropy constraint. Second, to improve the stability of DANN on an insufficient amount of data, a relatedness matrix is introduced, and a new regularizer with symmetry constraint on this matrix is designed to capture the intrinsic similarity structure among multiple fault types. Finally, a stochastic gradient descent optimization strategy is used to train the network and establish an end-to-end diagnostic model. Comparative experiments are conducted on two widely used bearing data sets. The results show that the proposed method has good diagnosis performance on insufficient monitoring data and outperforms several state-of-the-art transfer diagnosis methods and deep learning-based diagnosis methods in terms of diagnostic accuracy and numerical stability. [ABSTRACT FROM AUTHOR]

Aiming to identify incipient fault as earlier as possible, early fault detection (EFD) becomes the key step to trigger predictive maintenance. To lower deployment burden, pre-training techniques are employed to provide well-initialized features before fine-tuning different EFD tasks. Current large-scale pre-training models focus on seeking uniformity features to align every task's characteristic. But in practical engineering, degradation data is usually small-scale and under irregular noise interference. The pre-trained uniformity features are easily biased and less discriminative to early fault. To address this concern, this paper proposes a pre-training anomaly detection method with tensor domain adaptation. Running on the classical contrastive learning architecture, the proposed method first builds hypersphere-formed representation of anomaly detection rule. With the merit of tensor decomposition in extracting the intrinsic information from raw signals, the proposed method second designs a new tensorized rule adaptation mechanism to learn the task-invariant detection rule from normal state data that are used for pre-training. The pre-trained feature representation is then obtained from the feature extractor in contrastive learning via back-propagation. This paper takes rolling bearing as the validation object. Experimental results on the IEEE PHM Challenge 2012 and XJTU-SY datasets show that the proposed method can effectively improve the convergence speed and detection accuracy on different EFD tasks with shallow model, deep model and transfer learning, and also prove that the harmony on task-invariant detection rule and task-specific information facilitates the universal applicability of EFD pre-trained features in small scale. Harmony is then believed better than uniformity for the EFD pre-training. • We propose a new pre-training anomaly detection method for cross-machine early fault detection. • We build a tensorized rule adaptation mechanism on contrastive learning architecture to enhance pre-training. • We find a new harmony property of pre-trained feature covering task-invariant detection rule and task-specific information. • We find harmony property better than uniformity property in pre-training with small-scale data. • The proposed method can improve convergence and accuracy on various kinds of downstream tasks. [ABSTRACT FROM AUTHOR]

For the data-driven remaining useful life (RUL) prediction for rolling bearings, the traditional machine learning-based methods generally provide insufficient feature representation and adaptive extraction. Although deep learning-based RUL prediction methods can solve these problems to some extent, they still do not yield satisfactory predictive results due to less degradation data and inconsistent data distribution among different bearings. To solve these problems, a new RUL prediction method based on deep feature representation and transfer learning is proposed in this paper. This method includes an off-line stage and an online stage. In the off-line stage, the Hilbert–Huang transform marginal spectra of the raw vibration signal of auxiliary bearings are first calculated as the input, and then contractive denoising autoencoder is introduced to extract deep features with good and stable fault representation. Second, by using the obtained deep features and Pearson’s correlation coefficient, a new health condition assessment method is proposed to divide the whole life of each bearing into a normal state and a fast-degradation state. Finally, using the extracted deep features and their RUL values, an RUL prediction model for the fast-degradation state is trained by means of a least-square support vector machine. In the online stage, a kind of transfer learning algorithm, i.e., transfer component analysis, is introduced to sequentially adjust the features of target bearing from auxiliary bearings, and then the corresponding RUL is predicted using the corrected features. Results using the PHM Challenging 2012 data set show a significant performance improvement when using the proposed method in terms of predictive accuracy and numerical stability. [ABSTRACT FROM AUTHOR]

This paper presents a new online detection approach for rolling bearing’s incipient fault based on self-adaptive deep feature matching (SDFM). This approach includes offline and online stages. At the offline stage, a new health state assessment algorithm is first proposed based on singular value decomposition (SVD) and Kurtosis criterion. Based on the assessment results, a kind of deep learning algorithm, i.e., stacked denoising autoencoder (SDAE), is introduced to extract the common deep features of normal state and early fault state. Support vector data description (SVDD) is applied to establish the offline detection model using the obtained features. At the online stage, a self-adaptive matching strategy with 1-Dimensional anchor is proposed. By utilizing the SDAE model established at offline stage, this strategy can extract more representative deep features of the target bearing via generating various proposal fragments and then determining the fault occurrence time in a self-adaptive way by feeding the online features into the SVDD model. Experiments run on the bearing data set of IEEE prognostic and health management (PHM) Challenge 2012. The results show the proposed approach has good detection performance in real time and much lower false alarm rate, with no need to acquire fault characteristic frequency in advance. [ABSTRACT FROM AUTHOR]

Highlights • We propose a new deep learning method to conduct structural diagnosis of multiple bearing faults. • This method improves diagnosis accuracy and numerical stability by introducing fault structural information. • We find some inner structures among multiple fault types in view of output kernel. Abstract In recent years, machine learning techniques have been proved a promising tool for bearing fault diagnosis. However, in the traditional machine learning-based diagnosis methods, the fault features tend to be relatively simple and couldn’t work well for different fault type once a specific feature extraction method is determined. Meanwhile, although deep learning techniques can adaptively extract more representative features from bearing fault data, they are generally computationally expensive with slow convergence speed. Even if some deep learning algorithms like Multi-Layer Extreme Learning Machine (ML-ELM) can get fast training speed by means of non-tuned training strategy, they are inevitably of randomness to some extents. To solve this problem, a new deep learning method called deep output kernel learning is proposed in this paper to conduct collaborative diagnosis of multiple bearing fault types. The initial motivation is using the structural domain information among multiple bearing fault types to improve the diagnosis model’s generalization ability and robustness. By adopting ML-ELM as baseline algorithm, this paper firstly utilizes autoencoder to adaptively extract deep features, and then uses them to construct an objective function with output kernel regularizer. Finally, after solving this optimization problem, an output kernel matrix is obtained, and with this matrix, the final diagnosis model is built by fusing the multiple outputs of fault classifier. Experimental results on CWRU and IMS bearing data sets show that, compared to one state-of-the-art signal analysis method and eight typical machine learning-based diagnosis methods including four shallow learning algorithms and four deep learning algorithms, the proposed method can effectively improve the accuracy of bearing fault diagnosis in an acceptable time. Moreover, the results from the Kruskal-Wallis Test also indicate the proposed method has good numerical stability. [ABSTRACT FROM AUTHOR]

In many practical engineering applications, data tend to be collected in online sequential way with imbalanced class. Many traditional machine learning methods such as support vector machine and so on generally get biased classifier which leads to lower classification precision for minor class than major class. To get fast and efficient classification, a new online sequential extreme learning machine method with two-stage hybrid strategy is proposed. In offline stage, data-based strategy is employed, and the principal curve is introduced to model the distribution of minority class data. In online stage, algorithm-based strategy is employed, and a new leave-one-out cross-validation method using Sherman–Morrison matrix inversion lemma is proposed to tackle online imbalance data, meanwhile, with add-delete mechanism for updating network weights. And the rationality of this strategy is proved theoretically. The proposed method is evaluated on four UCI datasets and the real-world Macau air pollutant forecasting dataset. The experimental results show that, the proposed method outperforms the classical ELM, OS-ELM and meta-cognitive OS-ELM in terms of generalization performance and numerical stability. [ABSTRACT FROM AUTHOR]

This paper tries to address the concerns about online early fault detection in non-stop scenarios: (1) no information of running status and operating condition is available for online data; (2) False alarms are raised by irregular noise. This paper proposes a new self-supervised deep tensor domain-adversarial anomaly detection model, named Tensor-DAAD. A contrastive learning network is first built to generate pre-trained features and pseudo-labels for online data. Second, a new tensor hypersphere-adversarial network is designed. By calculating core tensors of two domains' features, this network builds hypersphere-based one-class detection rules from noisy data, and then realizes rule adaptation between the domains through adversarial training. Finally, a training algorithm with alternating minimization scheme is proposed to seek the optimal tensor decomposition and domain-invariant feature representation. Results on the two widely-used bearing datasets demonstrate that Tensor-DAAD can find early fault occurrence in an earlier location with a much lower false alarm rate. • We propose a self-supervised deep tensor domain-adversarial anomaly detection model. • We build a contrastive learning network to generate pre-trained features and labels. • We build a tensor adversarial training mechanism to transfer one-class detection rule. • We find tensor decomposition avoids feature deterioration in adversarial training. • We find pre-training is vital to unsupervised anomaly detection with transfer learning. [ABSTRACT FROM AUTHOR]

Diagnosis of bearings generally plays an important role in fault diagnosis of mechanical system, and machine learning has been a promising tool in this field. In many real applications of bearings fault diagnosis, the data tend to be online imbalanced, which means, the number of fault data is much less than the normal data while they are all collected in online sequential way. Suffering from this problem, many traditional diagnosis methods will get low accuracy of fault data which acts as the minority class in the collected bearing data. To address this problem, an online sequential prediction method for imbalanced fault diagnosis problem is proposed based on extreme learning machine. This method introduces the principal curve and granulation division to simulate the flow distribution and overall distribution characteristics of fault data, respectively. Then a confident over-sampling and under-sampling process is proposed to establish the initial offline diagnosis model. In online stage, the obtained granules and principal curves are rebuilt on the bearing data which are arrived in sequence, and after the over-sampling and under-sampling process, the balanced sample set is formed to update the diagnosis model dynamically. A theoretical analysis is provided and proves that, even existing information loss, the proposed method has lower bound of the model reliability. Simulation experiments are conducted on IMS bearing data and CWRU bearing data. The comparative results demonstrate that the proposed method can improve the fault diagnosis accuracy with better effectiveness and robustness than other algorithms. [ABSTRACT FROM AUTHOR]

The demand for complex equipment aftermarket parts is mostly sporadic, showing typical intermittent characteristics as a whole, resulting in the evolution law of a single demand series having insufficient information, which restricts the prediction effect of existing methods. To solve this problem, this paper proposes a prediction method of intermittent feature adaptation from the perspective of transfer learning. Firstly, to extract the intermittent features of the demand series, an intermittent time series domain partitioning algorithm is proposed by mining the demand occurrence time and demand interval information in the series, then constructing the metrics, and using a hierarchical clustering algorithm to divide all the series into different sub-source domains. Secondly, the intermittent and temporal characteristics of the sequence are combined to construct a weight vector, and the learning of common information between domains is accomplished by weighting the distance of the output features of each cycle between domains. Finally, experiments are conducted on the actual after-sales datasets of two complex equipment manufacturing enterprises. Compared with various prediction methods, the method in this paper can effectively predict future demand trends, and the prediction's stability and accuracy are significantly improved. [ABSTRACT FROM AUTHOR]

Accurate and fast prediction of nonstationary time series is challenging and of great interest in both practical and academic areas. In this paper, an online sequential extreme learning machine with new weighted strategy is proposed for nonstationary time series prediction. First, a new leave-one-out (LOO) cross-validation error estimation for online sequential data is proposed based on inversion of block matrix. Second, a new weighted strategy based on the proposed LOO error estimation is proposed. This strategy ranks the samples’ importance by means of the LOO error of each new added sample and then assigns various weights. Performance comparisons of the proposed method with other existing algorithms are presented based on chaotic and real-world nonstationary time series data. The results show that the proposed method outperforms the classical ELM and OS-ELM in terms of generalization performance and numerical stability. [ABSTRACT FROM AUTHOR]

As an important branch of neural network, extreme learning machines (ELMs) have attracted wide interests in the fields of pattern classification and regression estimation. However, when facing learning problems with multi-dimensional outputs, named multi-dimensional regression, the conventional ELMs could not generally get satisfactory results because it is incapable of exploiting the relatedness among outputs efficiently. To solve this problem, a new regularized ELM is firstly proposed in this paper by introducing a hyper-spherical loss function as regularizer. As the regularization form with this loss function cannot be solved directly, an solution with iterative procedure is presented. For improving the learning performance, the algorithm proposed above is further reformulated to identify the inner grouping structure hidden in outputs by assuming that the grouping structure is determined by different linear combinations of a small number of latent basis neurons. This is achieved as a mixed integer programming, and finally an alternating minimization method is presented to solve this problem. Experiments on two multi-dimensional data sets, a toy problem and a real-life dynamical cylindrical vibration data set, are conducted, and the results demonstrate the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Considering the uncertainty of hidden neurons, choosing significant hidden nodes, called as model selection, has played an important role in the applications of extreme learning machines(ELMs). How to define and measure this uncertainty is a key issue of model selection for ELM. From the information geometry point of view, this paper presents a new model selection method of ELM for regression problems based on Riemannian metric. First, this paper proves theoretically that the uncertainty can be characterized by a form of Riemannian metric. As a result, a new uncertainty evaluation of ELM is proposed through averaging the Riemannian metric of all hidden neurons. Finally, the hidden nodes are added to the network one by one, and at each step, a multi-objective optimization algorithm is used to select optimal input weights by minimizing this uncertainty evaluation and the norm of output weight simultaneously in order to obtain better generalization performance. Experiments on five UCI regression data sets and cylindrical shell vibration data set are conducted, demonstrating that the proposed method can generally obtain lower generalization error than the original ELM, evolutionary ELM, ELM with model selection, and multi-dimensional support vector machine. Moreover, the proposed algorithm generally needs less hidden neurons and computational time than the traditional approaches, which is very favorable in engineering applications. [ABSTRACT FROM AUTHOR]

Abstract: Multi-Input Multi-Output (MIMO) regression estimation problems widely exist in engineering fields. As an efficient approach for MIMO modeling, multi-dimensional support vector regression, named M-SVR, is generally capable of obtaining better predictions than many traditional methods. However, M-SVR is sensitive to the perturbation of hyper-parameters when facing small-scale sample problems, and most of currently used model selection methods for conventional SVR cannot be applied to M-SVR directly due to its special structure. In this paper, a fast and robust model selection algorithm for M-SVR is proposed. Firstly, a new training algorithm for M-SVR is proposed to reduce efficiently the numerical errors in training procedure. Based on this algorithm, a new leave-one-out (LOO) error estimate for M-SVR is derived through a virtual LOO cross-validation procedure. This LOO error estimate can be straightway calculated once a training process ended with less computational complexity than traditional LOO method. Furthermore, a robust implementation of this LOO estimate via Cholesky factorization is also proposed. Finally, the gradients of the LOO estimate are calculated, and the hyper-parameters with lowest LOO error can be found by means of gradient decent method. Experiments on toy data and real-life dynamical load identification problems are both conducted, demonstrating comparable results of the proposed algorithm in terms of generalization performance, numerical stability and computational cost. [Copyright &y& Elsevier]

As an effective approach for multi-input multi-output regression estimation problems, a multi-dimensional support vector regression (SVR), named M-SVR, is generally capable of obtaining better predictions than applying a conventional support vector machine (SVM) independently for each output dimension. However, although there are many generalization error bounds for conventional SVMs, all of them cannot be directly applied to M-SVR. In this paper, a new leave-one-out (LOO) error estimate for M-SVR is derived firstly through a virtual LOO cross-validation procedure. This LOO error estimate can be straightway calculated once a training process ended with less computational complexity than traditional LOO method. Based on this LOO estimate, a new model selection methods for M-SVR based on multi-objective optimization strategy is further proposed in this paper. Experiments on toy noisy function regression and practical engineering data set, that is, dynamic load identification on cylinder vibration system, are both conducted, demonstrating comparable results of the proposed method in terms of generalization performance and computational cost. [ABSTRACT FROM AUTHOR]

In this paper, the mechanism of the effect of V doping on the thermoelectric properties of ZnO is studied by experimental test and first principles calculation. The results show that the carrier concentration and conductivity increase significantly after V doping, which is mainly due to the donor effect caused by V substituting for Zn site, and the band gap becomes narrower. Due to the influence of 3d orbit of V ion, the density of states near Fermi level increases. The effective mass decreases and the Seebeck coefficient decreases with V doping. The thermal conductivity decreases with the decrease of lattice thermal conductivity, which is mainly due to the decrease of Young's modulus due to the change of strain and stress field caused by V doping. While the power factor increases, the thermal conductivity decreases, and the ZT value increases significantly in the whole temperature range, with the highest value reaching 0.302 ​at 873 ​K for Zn 0.985 V 0.015 O, which is 3.02 times of undoped ZnO. Sm doping at Zn site can effectively enhance the thermoelectric properties for ZnO [Display omitted] • The effects of V doped ZnO based bulks were investigated in detail. • The 3d orbits of V ion increase the density of states near Fermi level. • V doping causes the decrease of effective mass and Seebeck coefficient. • V doping can reduce Young's modulus, enhance phonon scattering. • The highest value reaches 0.302 ​at 873 ​K for Zn 0.985 V 0.015 O, which is 3.02 times of undoped ZnO. [ABSTRACT FROM AUTHOR]

As a novel learning algorithm for single-hidden-layer feedforward neural networks, extreme learning machines (ELMs) have been a promising tool for regression and classification applications. However, it is not trivial for ELMs to find the proper number of hidden neurons due to the nonoptimal input weights and hidden biases. In this paper, a new model selection method of ELM based on multi-objective optimization is proposed to obtain compact networks with good generalization ability. First, a new leave-one-out (LOO) error bound of ELM is derived, and it can be calculated with negligible computational cost once the ELM training is finished. Furthermore, the hidden nodes are added to the network one-by-one, and at each step, a multi-objective optimization algorithm is used to select optimal input weights by minimizing this LOO bound and the norm of output weight simultaneously in order to avoid over-fitting. Experiments on five UCI regression data sets are conducted, demonstrating that the proposed algorithm can generally obtain better generalization performance with more compact network than the conventional gradient-based back-propagation method, original ELM and evolutionary ELM. [ABSTRACT FROM AUTHOR]

In the actual maintenance of manufacturing enterprises, abnormal changes in after-sale parts demand data often make the inventory strategies unreasonable. Due to the intermittent and small-scale characteristics of demand sequences, it is difficult to accurately identify the anomalies in such sequences using current anomaly detection algorithms. To solve this problem, this paper proposes an unsupervised anomaly detection method for intermittent time series. First, a new abnormal fluctuation similarity matrix is built by calculating the squared coefficient of variation and the maximum information coefficient from the macroscopic granularity. The abnormal fluctuation sequence can then be adaptively screened by using agglomerative hierarchical clustering. Second, the demand change feature and interval feature of the abnormal sequence are constructed and fed into the support vector data description model to perform hypersphere training. Then, the unsupervised abnormal point location detection is realized at the micro-granularity level from the abnormal sequence. Comparative experiments are carried out on the actual demand data of after-sale parts of two large manufacturing enterprises. The results show that, compared with the current representative anomaly detection methods, the proposed approach can effectively identify the abnormal fluctuation position in the intermittent sequence of small samples, and also obtain better detection results. [ABSTRACT FROM AUTHOR]

Abstract: Model selection plays a key role in the application of support vector machine (SVM). In this paper, a method of model selection based on the small-world strategy is proposed for least squares support vector regression (LS-SVR). In this method, the model selection is treated as a single-objective global optimization problem in which generalization performance measure performs as fitness function. To get better optimization performance, the main idea of depending more heavily on dense local connections in small-world phenomenon is considered, and a new small-world optimization algorithm based on tabu search, called the tabu-based small-world optimization (TSWO), is proposed by employing tabu search to construct local search operator. Therefore, the hyper-parameters with best generalization performance can be chosen as the global optimum based on the powerful search ability of TSWO. Experiments on six complex multimodal functions are conducted, demonstrating that TSWO performs better in avoiding premature of the population in comparison with the genetic algorithm (GA) and particle swarm optimization (PSO). Moreover, the effectiveness of leave-one-out bound of LS-SVM on regression problems is tested on noisy sinc function and benchmark data sets, and the numerical results show that the model selection using TSWO can almost obtain smaller generalization errors than using GA and PSO with three generalization performance measures adopted. [ABSTRACT FROM AUTHOR]

Most traditional approaches to load identification usually perform not very well because the inverse identification problem in most practical cases is ill-posed. In this paper, a new approach to the identification of dynamic loads based on the solution path algorithm of support vector regression is proposed. A general framework of dynamic load identification using support vector regression is derived and the corresponding identification model using solution path algorithm is established. The results of numerical and experimental tests on cylinder vibration system show that the proposed approach greatly outperforms existing methods, i.e., direct inverse identification method, ℇ-SVR and LS-SVM, in terms of identification accuracy and numerical stability. As a conclusion, the proposed approach is applicable to a wide variety of mechanical cases. [ABSTRACT FROM AUTHOR]

Abstract: In the conventional solution path algorithm of support vector regression, the ε-insensitive error of every training sample is equally penalized, which means every sample affects the generalization ability equally. However, in some cases, e.g. time series prediction or noisy function regression, the ε-insensitive error of the sample which could provide more important information should be penalized more heavily. Therefore, the weighted solution path algorithm of support vector regression is proposed in this paper. Error penalty parameter of each training sample is weighted differently, and the whole solution path is modified correspondingly. More importantly, by choosing Arc Tangent function as the prototype to generate weights with various characteristics, a heuristic weight-setting optimization algorithm is proposed to compute the optimal weights using particle swarm optimization (PSO). This method is applicable to different applications. Experiments on time series prediction and noisy function regression are conducted, demonstrating comparable results of the proposed weighted solution path algorithm and encouraging performance of the heuristic weight-setting optimization. [Copyright &y& Elsevier]

• We propose a new deep auto-encoder method with fusing discriminant information. • We presents a gradient descent method to optimize the new model. • This method can improve features' representative ability with no fine-tuning operation. • This method can improve model's numerical stability on insufficient amount of training data. • We find a symmetric structure among multiple fault conditions in form of relatedness matrix. In recent years, deep learning techniques have been proved a promising tool for bearing fault diagnosis. However, to extract deep features with better representative ability, how to introduce discriminant information about different fault types into the deep learning model is still challenging. Moreover, as deep learning techniques heavily rely on mass of measuring data, relatively small amounts of data may cause over-fitting and reduce model stability as well. To solve such problems, a new deep auto-encoder method with fusing discriminant information about multiple fault types is proposed for bearing fault diagnosis. First, a new loss function is designed by introducing structural discriminant information. Specifically, to improve the feature's representative ability, a new discriminant regularizer is designed in the loss function by using maximum correlation entropy. And to represent the structural information among multiple fault types, a relation matrix for fault types is introduced, then a new regularizer with a symmetric constraint on this matrix is constructed. Second, a gradient descent method is provided to optimise this loss function, and the optimal deep features, as well as fault relatedness, are learned simultaneously. Experimental results on CWRU and IMS bearing data sets show that, compared to several state-of-the-art diagnosis methods, the proposed method can effectively improve the diagnostic accuracy with acceptable time efficiency. And the results on the Kruskal–Wallis Test indicate the proposed method has better numerical stability. [ABSTRACT FROM AUTHOR]

With the quick development of sensor technology in recent years, online detection of early fault without system halt has received much attention in the field of bearing prognostics and health management. While lacking representative samples of the online data, one can try to adapt the previously-learned detection rule to the online detection task instead of training a new rule merely using online data. As one may come across a change of the data distribution between offline and online working conditions, it is challenging to utilize the data from different working conditions to improve detection accuracy and robustness. To solve this problem, a new online detection method of bearing early fault is proposed in this paper based on deep transfer learning. The proposed method contains an offline stage and an online stage. In the offline stage, a new state assessment method is proposed to determine the period of the normal state and the degradation state for whole-life degradation sequences. Moreover, a new deep dual temporal domain adaptation (DTDA) model is proposed. By adopting a dual adaptation strategy on the time convolutional network and domain adversarial neural network, the DTDA model can effectively extract domain-invariant temporal feature representation. In the online stage, each sequentially-arrived data batch is directly fed into the trained DTDA model to recognize whether an early fault occurs. Furthermore, a health indicator of target bearing is also built based on the DTDA features to intuitively evaluate the detection results. Experiments are conducted on the IEEE Prognostics and Health Management (PHM) Challenge 2012 bearing dataset. The results show that, compared with nine state-of-the-art fault detection and diagnosis methods, the proposed method can get an earlier detection location and lower false alarm rate. [ABSTRACT FROM AUTHOR]

• We propose a new deep transfer learning model to enhance common feature representation of bearings. • We propose a new health indicator with better description of bearing degradation trend. • We propose a new transfer learning-based online detection method of bearing incipient fault. In order to achieve effective online detection of bearing incipient fault, it's necessary to adaptively extract representative features to incipient fault. However, the traditional feature extraction methods are less adaptive to online detection problem. In this paper, a new online detection method of incipient fault based on deep transfer learning is proposed. In the offline stage, a three-channel data set is first built by merging time/frequency/time-frequency domain information. Second, a new transfer learning model is constructed on auxiliary bearings data from a pre-trained VGG-16 model built on image data. Through a fine-tuning process, common deep features are extracted and the detection model is trained by using support vector data description. In the online stage, deep transfer features of target bearing are directly extracted, and final detection results are obtained. The experimental results on the bearing dataset of IEEE PHM Challenge 2012 show the comparative performance of the proposed method. [ABSTRACT FROM AUTHOR]

Superamphiphobic surfaces have been arousing great attention in recent years for improved durability in practical applications. In this study, composites of dual‐sized porous silicas of micro‐/nanoparticles and silicic acid binder were coated on the glassy substrate as the micro‐/nano‐structure, then 60 nm porous silica particles modified by 3‐aminopropyltriethoxysilane (APTS) were coated. With the aid of the efficient, rapid, and stoichiometric reaction of amino group and epoxy group, the monolayer low‐surface‐energy long perfluorinated chains self‐assembled in the surface. Field emission scanning electron microscope (FESEM) and atomic force microscopy (AFM) verified the concave–convex surface topological features. This surface realized super‐repellency to liquids (surface tension ranging from 72.0 to 27.2 mN/m). This surface sustains superamphiphobicity after 15 times of the tape tearing test. After soaking in base (pH = 14), acid (pH = 1), and n‐heptane for 20 days, this surface still holds superamphiphobicity. Its heat‐resistant ability is so outstanding that it keeps superamphiphobicity after drying for 3 h at 250°C. [ABSTRACT FROM AUTHOR]

The original version of this article unfortunately contained a mistake in “Acknowledgement” section. The funding information of “National Natural Science Foundation of China (No. U1704158)” is missing in the original publication. The corrected Acknowledgements section is given below: [ABSTRACT FROM AUTHOR]

Demand for spare parts, which is triggered by element failure, project schedule and reliability demand, etc., is a kind of sensing data to the aftermarket service of large manufacturing enterprises. Prediction of the demand for spare parts plays a crucial role in inventory management and lifecycle quality management for the aftermarket service of large-scale manufacturing enterprises. In real-life applications, however, demand for spare parts occurs randomly and fluctuates greatly, and the demand sequence shows obvious intermittent distribution characteristics. Additionally, due to factors such as reporting mistakes made by personnel or environmental changes, the actual data of the demand for spare parts are prone to abnormal variations. It is thus hard to capture the evolutional pattern of the demand for spare parts by traditional time series forecasting methods. The reliability of prediction results is also reduced. To address these concerns, this paper proposes a tensor optimization-based robust interval prediction method of intermittent time series for the aftersales demand for spare parts. First, using the advantages of tensor decomposition to effectively mine intrinsic information from raw data, a sequence-smoothing network based on tensor decomposition and a stacked autoencoder is proposed. Tucker decomposition is applied to the hidden features of the encoder, and the obtained core tensor is reconstructed through the decoder, thus allowing us to smooth outliers in the original demand sequence. An alternating optimization algorithm is further designed to find the optimal sequence feature representation and tensor decomposition factors for the extraction of the evolutionary trend of the intermittent series. Second, an adaptive interval prediction algorithm with a dynamic update mechanism is designed to obtain point prediction values and prediction intervals for the demand sequence, thereby improving the reliability of the forecast. The proposed method is validated using the actual aftersales data from a large engineering manufacturing enterprise in China. The experimental results demonstrate that, compared with typical time series prediction methods, the proposed method can effectively grab the evolutionary trend of various intermittent series and improve the accuracy of predictions made with small-sample intermittent series. Moreover, the proposed method provides a reliable elastic prediction interval when distortion occurs in the prediction results, offering a new solution for intelligent planning decisions related to spare parts in practical maintenance. [ABSTRACT FROM AUTHOR]

Earthquake-induced landslides caused lots of deaths and economic loss in the active tectonic region, like the South-West of China. Soft and hard rock interbedding slopes are easy to fail and slide under earthquake loadings which result in catastrophic disasters. The seismic response and failure evolution of the slope subjected to the earthquake are key to revealing the mechanism of the earthquake-induced landslide and adopting engineering reinforcement in the future. In this study, a series of shaking table tests were performed to reveal the seismic response and failure mechanism of low-angled bedding rock slopes with interbedding of the soft and hard rock layers. Test results show that the acceleration amplification coefficients in the horizontal direction increase first and then decrease with the increase of the slope elevation. The seismic response of the sandstone sandwiching mudstone slope is stronger than that of the mudstone sandwiching sandstone slope. The thicker the middle rock strata, the greater the difference in seismic response between the uppermost and lowest strata. The failure evolution of the interbedding soft and hard rock layer slope can be summarized into three stages with the increase of the amplitude of the input ground motion. The novel findings can provide a basis for post-earthquake disaster investigation and disaster prevention and mitigation in active seismic areas. [ABSTRACT FROM AUTHOR]

Aiming at the online detection problem of rolling bearings, the limited amount of target bearing data leads to insufficient model in training and feature representation. It is difficult for the online detection model to construct an accurate decision boundary. To solve the problem, a multi-scale robust anomaly detection method based on data enhancement technology is proposed in this paper. Firstly, the training data are transformed into multiple subspaces through the data enhancement technology. Then, a prototype clustering method is introduced to enhance the robustness of features representation under the framework of the robust deep auto-encoding algorithm. Finally, the robust multi-scale Deep-SVDD hyper sphere model is constructed to achieve online detection of abnormal state data. Experiments are conducted on the IEEE PHM Challenge 2012 bearing data set and XJTU-TU data set. The proposed method shows much greater susceptibility to incipient faults, and it has fewer false alarms. The robust multi-scale Deep-SVDD hyper sphere model significantly improves the performance of incipient fault detection for rolling bearings. [ABSTRACT FROM AUTHOR]

Natural image reconstruction based on compressive sensing (CS) has shown a promising performance in recent years. However, sometimes the restoration precision is not high enough. A novel CS algorithm using vector quantisation (VQ) error is proposed. First, the original image is compressed by VQ due to its extremely high compression ratio and strong ability to preserve details. Then compute the VQ error matrix and ignore the three least significant bits, which makes the error matrix much sparser. Next, to ensure a uniform distribution of sparsity of blocks, the error matrix is scrambled. Since the huge diversity among blocks has been largely reduced, they can be sensed with the same sensing matrix in space domain. At last, the reconstruction effect of the error matrix decides the total restoration performance. Experimental results have demonstrated the proposed method, at low measurement ratio, performs better in the aspects of perception and peak signal‐to‐noise ratio. [ABSTRACT FROM AUTHOR]

Abstract: The heteroassociative morphological memories (HMMs) are one kind of morphological associative memories (MAMs). Although they have many advantages, there is a serious shortcoming: HMMs are incomplete, that is, they cannot give a guarantee of perfect recall memories, even though without any input noises. This problem has become a bottleneck in the development and applications of HMMs, and also one of difficult subjects in this field. Aiming at the problem, this paper presents a new method of HMMs, called four-dimensional stored HMMs (FDSHMMs). It includes three work stages: pretreatment, memory, and recall. Both computational method and experimental method show that FDSHMMs can significantly improve the HMMs. They can guarantee perfect recall memories for perfect inputs or within a certain noise range, just like the auto-associative morphological memories (AMMs) can do. FDSHMMs remove the bottleneck of HMMs and bring us a bright prospect of applications. [Copyright &y& Elsevier]

Abstract: We study multiple solutions of asymptotically linear Duffing equations satisfying Neumann boundary value conditions with resonance by using index theory and Lusternik–Schnirelmann theory, and obtain some new results. [Copyright &y& Elsevier]

• A linearly dynamic random heuristic crossover is presented to get stronger local search ability. • An exponentially dynamic random differential mutation strategy is used to strengthen the global search ability. • A global-best Gaussian mutation operator is adopted to balance exploitation and exploration better. • A random opposition learning strategy is used to avoid getting stuck in local optima. • The proposed algorithm is verified on the classical functions, CEC-2013 and CEC-2017, and two practical problems. The Biogeography-Based Optimization algorithm and its variants have been used widely for optimization problems. To get better performance, a novel Biogeography-Based Optimization algorithm with Hybrid migration and global-best Gaussian mutation is proposed in this paper. Firstly, a linearly dynamic random heuristic crossover strategy and an exponentially dynamic random differential mutation one are presented to form a hybrid migration operator, and the former is used to get stronger local search ability and the latter strengthen the global search ability. Secondly, a new global-best Gaussian mutation operator is put forward to balance exploration and exploitation better. Finally, a random opposition learning strategy is merged to avoid getting stuck in local optima. The experiments on the classical benchmark functions and the complexity functions from CEC-2013 and CEC-2017 test sets, and the Wilcoxon, Bonferroni-Holm and Friedman statistical tests are used to evaluate our algorithm. The results show that our algorithm obtains better performance and faster running speed compared with quite a few state-of-the-art competitive algorithms. In addition, experimental results on Minimum Spanning Tree and K -means clustering optimization show that our algorithm can cope with these two problems better than the comparison algorithms. [ABSTRACT FROM AUTHOR]

In a large-scale data center, it is vital to precisely recognize the termination statuses of applications at an early stage. In recent years, many machine learning techniques have been applied to this issue, which is beneficial for optimizing the scheduling policy and improving the efficiency of resource utilization. However, if the application's dynamic information is insufficient at the early stage, the generalization performance of the machine learning model will be lessened, and the prediction accuracy could be low. To overcome this problem, a novel failure prediction method that is based on the association relationships between similar jobs is proposed in this paper to jointly predict task's termination statuses at an earlier stage. The similar jobs whose tasks have similar changing modes of consumed resources, an inherent structural correlation may exist, and the correlation information is significant for improving the prediction model's generalization performance. First, a job clustering algorithm is proposed for identifying the jobs with higher similarity from jobs that have various numbers of tasks. Second, based on the job clustering results, the robust multi-task learning algorithm is introduced to effectively utilize the domain information among jobs (i.e. interactional relationship among jobs on the termination statuses of task). Experiments are conducted on a Google cluster workload traces dataset. The results show that the proposed method can realize higher prediction accuracy, lower misjudgment rate, and higher predictive stability than several state-of-the-art methods at 1/3 the running time of the tasks. [ABSTRACT FROM AUTHOR]

Accurate remaining useful life (RUL) prediction for rolling bearings encounters many challenges such as complex degradation processes, varying working conditions, and insufficient run-to-failure data. Transfer learning (TL), one paradigm of artificial intelligence technology, has demonstrated its powerful performance and great effectiveness for such challenges. As a result, many TL-based solutions have been widely developed and extensively studied for rolling bearing RUL prediction. Admittedly, several review articles have been published on RUL prediction. Nevertheless, the majority of these articles only concentrated on deep learning-based RUL prediction methods, and a review article that systematically overviews the status of TL-based RUL prediction has not been published. Therefore, it is urgent and significant to thoroughly summarize the academic publications and industrial applications related to TL-based RUL prediction, and present its potential challenges and future research directions. With such goals, the problem definitions of TL-based RUL prediction, the general procedure of RUL prediction, and typical TL-based RUL prediction algorithms are first introduced to help researchers quickly overview the state-of-the-art approaches and recent developments. Thereafter, relevant TL-based RUL prediction solutions are comprehensively discussed from the perspectives of three industrial scenarios, providing suggestions to researchers and engineers for selecting appropriate solutions in practical industrial applications. Finally, the key challenges and future trends in RUL prediction are presented to conclude this paper. We hope that this review of TL-based RUL prediction for rolling bearings can contribute to a better understanding of intelligent prognostic technology and will inspire researchers to extend their work on RUL prediction. [ABSTRACT FROM AUTHOR]

Gearbox has a compact structure, a stable transmission capability, and high transmission efficiency. Thus, it is widely applied and used as a critical transmission system in intelligent manufacturing systems, such as machine tools and robotics. The gearbox usually operates in harsh and non-stationary working environments, making the gear surface prone to wear. The progression of gear surface wear may lead to severe gear failures, such as gear tooth breakage and root crack, potentially damaging the whole gear transmission system. Therefore, it is essential to assess the gear surface wear progression and predict its remaining useful life (RUL) in order to ensure the reliable operation of the gear transmission system. To this end, this paper developed a novel gear wear prognostic scheme based on vibration analysis for gear health management. More specifically, a novel health indicator (HI) is first developed for gear wear monitoring in the proposed prognostic scheme. The novel HI, inferred from the cyclic correntropy and Wasserstein distance (WD), can accurately reflect the wear-induced cyclic correntropy spectra distribution change over time. Therefore, the novel HI can robustly evaluate the gear wear severity with high accuracy. With the developed HI, a network, namely the optimized gated recurrent unit (GRU), is applied for predicting the gear transmission system RUL during surface wear progression. As for the optimized GRU network, the genetic algorithm (GA) is applied to find the optimal hyperparameters adaptively, which can significantly improve the practicality of the developed prognostic scheme. To conclude, the developed prognostic scheme can effectively reveal the gear wear propagation characteristics and predict the RUL accurately. A series of endurance tests are conducted to verify the effectiveness of the developed prognostic scheme for gear health management in surface wear progression. • A novel gear wear prognostic scheme is proposed for RUL prediction of the gear transmission system. • A novel health indicator is developed for monitoring the gear wear progression. • An optimized GRU network is achieved with the help of the GA algorithm. • Run-to-failure tests are applied for demonstration and validation of the proposed methodology. [ABSTRACT FROM AUTHOR]

Abstract: In practical engineering, small-scale data sets are usually sparse and contaminated by noise. In this paper, we propose a new sequence of orthogonal polynomials varying with their coefficient, unified Chebyshev polynomials (UCP), which has two important properties, namely, orthogonality and adaptivity. Based on these new polynomials, a new kernel function, the unified Chebyshev kernel (UCK), is constructed, which has been proven to be a valid SVM kernel. To find the optimal polynomial coefficient and the optimal kernel, we propose an adaptive algorithm based on the evaluation criterion for adaptive ability of UCK. To evaluate the performance of the new method, we applied it to learning some benchmark data sets for regression, and compared it with other three algorithms. The experiment results show that the proposed adaptive algorithm has excellent generalization performance and prediction accuracy, and does not cost more time compared with other SVMs. Therefore, this method is suitable for practical engineering application. [Copyright &y& Elsevier]

Compared with continuous elements, discontinuous elements advance in processing the discontinuity of physical variables at corner points and discretized models with complex boundaries. However, the computational accuracy of discontinuous elements is sensitive to the positions of element nodes. To reduce the side effect of the node position on the results, this paper proposes employing partially discontinuous elements to compute the time-domain boundary integral equation of 3D elastodynamics. Using the partially discontinuous element, the nodes located at the corner points will be shrunk into the element, whereas the nodes at the non-corner points remain unchanged. As such, a discrete model that is continuous on surfaces and discontinuous between adjacent surfaces can be generated. First, we present a numerical integration scheme of the partially discontinuous element. For the singular integral, an improved element subdivision method is proposed to reduce the side effect of the time step on the integral accuracy. Then, the effectiveness of the proposed method is verified by two numerical examples. Meanwhile, we study the influence of the positions of the nodes on the stability and accuracy of the computation results by cases. Finally, the recommended value range of the inward shrink ratio of the element nodes is provided. [ABSTRACT FROM AUTHOR]

Most regression techniques assume that the noise characteristics are subject to single noise distribution whereas the wind speed prediction is difficult to model by the single noise distribution because the noise of wind speed is complicated due to its intermittency and random fluctuations. Therefore, we will present the ν -support vector regression model of Gauss-Laplace mixture heteroscedastic noise (GLM-SVR) and Gauss-Laplace mixture homoscedastic noise (GLMH-SVR) for complex noise. The augmented Lagrange multiplier method is introduced to solve models GLM-SVR and GLMH-SVR. The proposed model is applied to short-term wind speed forecasting using historical data to predict future wind speed at a certain time. The experimental results show that the proposed technique outperforms the single noise technique and obtains good performance. [ABSTRACT FROM AUTHOR]