Search

The large-scale machinery generally requires multiple accelerometers for condition monitoring. The multi-channel vibration signals carry a wealth of fault information. Synchronous fault feature extraction using multi-channel signals will significantly improve the diagnostic performance. The multivariate entropy method is able to synchronously extract the fault features from multiple sensors, but how to recognize the single fault occurring on different channels remains unexplored. Here, we propose a novel feature extraction method called variational embedding multiscale diversity entropy (veMDE) which constructs the phase space with different structures. The proposed variational phase space construction strategy will generate a different probability distribution for each channel, which results in a better separability for multi-channel feature extraction. Combined with the random forest classifier, a novel fault diagnosis scheme is developed for condition monitoring of the large-scale machinery. One simulated signal and two experimental data are designed to validate the effectiveness of the proposed strategy. The results demonstrate that the proposed method has the best multi-channel feature extraction ability compared with three existing methods: multivariate multiscale sample entropy, multivariate multiscale fuzzy entropy, and multivariate multiscale permutation entropy.

The health condition monitoring of planetary gearboxes has drawn increasing attention due to the importance for safety operation and failure prevention. A novel diagnosis methodology based on multiscale symbolic diversity entropy (SDivEn) is proposed in this article. Herein, dynamical complexity of measured data is quantified by SDivEn. Compare to other entropy-based descriptors, SDivEn has advantages in its robustness and computation efficiency. To increase the feature representation capability of entropy descriptors, multiscale analysis is performed, where the measurement data in time series is decomposed into multiple scaled series by using the coarse graining process and then processed individually by using SDivEn method. The proposed multiscale SDivEn method is applied for fault recognition of planetary gearboxes. Experimental results indicate that the proposed method obtains the highest accuracy in recognizing seven health conditions of planetary gearboxes in comparison with three other existing entropy-based methods.

Fault diagnosis of rotary machinery plays a significant role in the prognostic and health management system, which aims to identify the root causes of system failures and provide effective information for prognostics and maintenance. Recently, Lempel–Ziv complexity (LZC) method has been employed for fault diagnosis of rotary machinery. However, one actual problem is that LZC fails to account for the multiscale information inherent in measured vibration signals. We first introduce a method to compute the multi-scale LZC for a signal. However, the variance of LZC values becomes larger as the scale factor increases. To solve this actual problem, this paper proposes refined composite multi-scale Lempel-Ziv complexity (RCMLZC) to estimate the complexity. We find that the proposed RCMLZC method consistently yields better performance when analyzing three simulated noisy and impulsive signals. Based on RCMLZC, a novel intelligent fault diagnosis method is designed to recognize various fault types of rotating machinery. Comparative experiments are performed to confirm the effectiveness of proposed method including single fault and compound fault working conditions. Experimental results indicate that RCMLZC is more accurate than multi-scale LZC, multi-scale entropy, and LZC in extracting fault features from vibration signal and that RCMLZC performs best to recognize the various fault types of rotary machinery.

In this article, a fault diagnosis scheme based on multiscale diversity entropy (MDE) and extreme learning machine (ELM) is presented. First, a novel entropy method called diversity entropy (DE) is proposed to quantify the dynamical complexity. DE utilizes the distribution of cosine similarity between adjacent orbits to track the inside pattern change, resulting in better performance in complexity estimation. Then, the proposed DE is extended to multiscale analysis called MDE for a comprehensive feature description by combining with the coarse gaining process. Third, the obtained features using MDE are fed into the ELM classifier for pattern identification of rotating machinery. The effectiveness of the proposed MDE method is verified using simulated signals and two experimental signals collected from the bearing test and the dual-rotator of the aeroengine test. The analysis results show that our proposed method has the highest classification accuracy compared with three existing approaches: sample entropy, fuzzy entropy, and permutation entropy.

To understand surrounding scenes accurately, the semantic segmentation of images is vital in autonomous driving tasks, such as navigation, and route planning. Currently, convolutional neural networks (CNN) are widely employed in semantic segmentation to perform precise prediction in the dense pixel level. A recent trend in network design is the stacking of small convolution kernels. In this work, small convolution kernels (3 × 3) are decomposed into complementary convolution kernels (1 × 3 + 3 × 1, 3 × 1 + 1 × 3), the complementary small convolution kernels perform better in the classification and location tasks of semantic segmentation. Subsequently, a complementary convolution residual network (CCRN) is proposed to improve the speed and accuracy of semantic segmentation. To further locate the edge of objects precisely, A coupled Gaussian conditional random field (G-CRF) is utilized for CCRN post-processing. Proposal approach achieved 81.8% and 73.1% mean Intersection-over-Union (mIoU) on PASCAL VOC-2012 test set and Cityscapes test set, respectively.

Using transfer learning (TL) for fault detection and diagnosis has been a hot topic in prognostic and health management (PHM) field. In this article, a systematic framework is established to solve the cross-domain fault diagnosis for rotary machines of the same type using entropy-based TL. The multiscale symbolic dynamic entropy (MSDE) is first proposed to extract features from vibration signals. Then, TL model is trained to get a mapping matrix, which can preserve the structure properties of prior distribution and minimize the discrepancies between different datasets. The mapped features are called multiscale transfer symbolic dynamic entropy (MTSDE). Finally, the support vector machine (SVM) classifier is utilized to accomplish the cross-domain intelligent fault-type recognition. To demonstrate the superiority of the proposed MTSDE method, the comparative experiments of nine methods are carried out under different datasets including gearboxes and bearings. Experimental results demonstrate that our proposed MTSDE method performs best in recognizing various fault types comparing with other nine methods. To the best knowledge of the authors, this is the first attempt of using entropy-based TL for cross-domain fault diagnosis of rotating machinery.

A novel rotating machine fault diagnosis method based on multi-scale transfer fuzzy entropy (MTFE) and support vector machine (SVM) is proposed in this paper. Compared with traditional machine learning methods, our proposed method can identify various fault types of rotating machinery with different data distribution by learning the transfer knowledge from different distribution source domains. First, multi-scale fuzzy entropy (MFE) features of all samples are extracted as input. Second, build a transfer learning model to find a projection matrix to map the MFE features of the source and target domains into a common subspace, called MTFE features. In this process, the distribution structure of training data is maintained and the distribution difference between training data and test data is reduced. Finally, the SVM classifier identifies the fault type of the test data. Two cases including gearbox and rolling bearing are used for validation. Experimental results demonstrate that our proposed MTFE method performs best in recognizing various fault types comparing with other six methods.

In this article, a novel intelligent fault diagnosis method based on multiscale symbolic Lempel-Ziv (MSLZ) is proposed to identify several faults of railway vehicle systems (RVSs). The proposed MSLZ is essentially for the purpose of estimating the irregularity of a given time series. In the proposed MSLZ method, the symbolization and multiscale techniques are combined with Lempel–Ziv (LZ) to enhance its feature extraction ability. First, the symbolization can facilitate LZ to remove the noises and reserve the fault information. Second, multiscale analysis can extend LZ to multiple time scales, which can further enhance the description ability of dynamic characteristics. Using numerical data and experimental signals collected from RVSs, the performance of the MSLZ method is demonstrated to be sensitive to periodical impulses and robust to environmental noise. Moreover, it has been demonstrated that MSLZ has superiority in extracting fault information of the RVS compared with LZ, symbolic LZ, and multiscale LZ methods.

Rotating machinery is widely applied in industrial applications. Fault diagnosis of rotating machinery is vital in manufacturing system, which can prevent catastrophic failure and reduce financial losses. Recently, Deep Learning (DL)-based fault diagnosis method becomes a hot topic. Convolutional Neural Network (CNN) is an effective DL method to extract the features of raw data automatically. This paper develops a fault diagnosis method using CNN for InfRared Thermal (IRT) image. First, IRT technique is utilized to capture the IRT images of rotating machinery. Second, the CNN is applied to extract fault features from the IRT images. In the end, the obtained features are fed into the Softmax Regression (SR) classifier for fault pattern identification. The effectiveness of the proposed method is validated using two different experimental data. Results show that the proposed method has a superior performance in identification various faults on rotor and bearings comparing with other deep learning models and traditional vibration-based method. Keywords: Convolutional neural network, Feature extraction, Infrared thermography (IRT), Intelligent fault diagnosis, Rotating machinery

A Data Processing Network (DPN) streams massive volumes of data collected and stored by the network to multiple processing units to compute desired results in a timely fashion. Due to ever-increasing traffic, distributed cache nodes can be deployed to store hot data and rapidly deliver them for consumption. However, prior work on caching policies has primarily focused on the potential gains in network performance, e.g., cache hit ratio and download latency, while neglecting the impact of cache on data processing and consumption. In this paper, we propose a novel framework, DeepChunk, which leverages deep Q-learning for chunk-based caching in wireless DPN. We show that cache policies must be optimized for both network performance during data delivery and processing efficiency during data consumption. Specifically, DeepChunk utilizes a model-free approach by jointly learning limited network, data streaming, and processing statistics at runtime and making cache update decisions under the guidance of deep Q-learning. It enables a joint optimization of multiple objectives including chunk hit ratio, processing stall time, and object download time while being self-adaptive under the time-varying workload and network conditions. We build a prototype implementation of DeepChunk with Ceph, a popular distributed object storage system. Based on real-world Wifi and 4G traces, our extensive experiments and evaluation demonstrate significant improvement, i.e., 52% increase in total reward and 68% decrease in processing stall time, over a number of baseline caching policies.

Fault feature extraction of rotating machinery is crucial and challenging due to its nonlinear and nonstationary characteristics. In order to resolve this difficulty, a quality nonlinear fault feature extraction method is required. Hierarchical permutation entropy has been proven to be a promising nonlinear feature extraction method for fault diagnosis of rotating machinery. Compared with multiscale permutation entropy, hierarchical permutation entropy considers the fault information hidden in both high frequency and low frequency components. However, hierarchical permutation entropy still has some shortcomings, such as poor statistical stability for short time series and inability of analyzing multichannel signals. To address such disadvantages, this paper proposes a new entropy method, called refined composite multivariate hierarchical permutation entropy. Refined composite multivariate hierarchical permutation entropy can extract rich fault information hidden in multichannel signals synchronously. Based on refined composite multivariate hierarchical permutation entropy and random forest, a novel fault diagnosis framework is proposed in this paper. The effectiveness of the proposed method is validated using experimental and simulated signals. The results demonstrate that the proposed method outperforms multivariate multiscale fuzzy entropy, refined composite multivariate multiscale fuzzy entropy, multivariate multiscale sample entropy, multivariate multiscale permutation entropy, multivariate hierarchical permutation entropy, and composite multivariate hierarchical permutation entropy in recognizing the different faults of rotating machinery.

Accurately determining the network energy consumption of each software principal when multiple ones are active is the key to mobile energy optimization. Tail energy accounting, which attributes tail energy to individual software principals, remains an open problem. Besides, tail energy has also become a major energy drain, especially in mobile ad modules that generate frequent, intermittent network traffics by on-demand ad downloading. In this paper, we propose a systematic framework for mobile ad prefetching and energy optimization, based on a novel tail energy accounting policy using cooperative game theory. In particular, we maximize the sum of deadline- and energy-aware ad utility, by jointly determining apps’ aggressiveness in ad prefetching. The proposed tail energy accounting not only characterizes the energy profile of each app's ad module, a crucial input in energy optimization, but also enables an efficient solution by decoupling decision making of individual apps. The proposed framework is implemented on Android with negligible performance/network overhead. Using real-world apps and usage traces, we demonstrate a significant reduction in mobile network energy consumption by up to 45 percent compared with existing approaches. To the best of our knowledge, it is the first fully implemented ad management system transparent to apps and ad ecosystem.

Fault diagnosis of rotating machinery is crucial to improve safety, enhance reliability and reduce maintenance cost. The manual feature extraction and selection of traditional fault diagnosis methods depend on signal processing skills and expert experience, which is labor-intensive and time-consuming. As a typical intelligent fault diagnosis method, the convolutional neural network automatically learns features from original data, but it is extremely difficult to design and train a deep network architecture. This paper proposes a fault diagnosis scheme combined of hierarchical symbolic analysis (HSA) and convolutional neural network (CNN), which achieves laborsaving and timesaving preliminary feature extraction and accomplishes automatically feature learning with simplified network architecture. Firstly, hierarchical symbolic analysis is employed to extract features from original signals. The extracted features are able to identify different health conditions under various operating conditions. Then, convolutional neural network instead of human labor is used to learn the complex non-linear relationship between features and health conditions automatically. The architecture of CNN diagnosis model is simple and convenient to implement. Finally, a centrifugal pump dataset and a motor bearing dataset are adopted to validate the effectiveness of the proposed method. The diagnosis results show that the proposed method exhibits superior performance compared with shallow methods and deep learning methods.

Vehicle routing problem (VRP) is one of the widely researched areas in transportation science, mainly due to the potential cost savings and service improvement opportunities which brings to organizations involved in physical distribution of goods. In this paper, we develop a multi-depot green vehicle routing problem (MDGVRP) by maximizing revenue and minimizing costs, time and emission, and then, apply an improved ant colony optimization (IACO) algorithm that aims to efficiently solve the problem. The IACO model developed in this research uses an innovative approach in updating the pheromone that results in better solutions. The results achieved through the IACO demonstrate satisfying performance, which have higher solution quality when compared to the conventional ACO. The IACO algorithm used in this paper demonstrated a good level of responsiveness and simplicity when solving MDGVRP with multiple objectives.

This paper assesses the interrelationships between hazards/risks (considered as barriers) for the effective implementation of Occupational Health and Safety (OHS) measures using Interpretive Structural Modeling (ISM). We investigate within and among hazard/risk classes and formulate a structural model that identifies and prioritizes their levels. Mitigation strategies for the identified barriers make the research outcome more useful and applicable. Results reveal that insulation failure, barrier (B7), is the most influential hazard; hence, it must be addressed first for the effective implementation of OHS measures in coal-fired thermal power plants. The second barrier in the ISM hierarchy, (B6) fire (mill/pool/jet), and additional hazards and risks require further assessment.

With the integration of the ultra-high-voltage direct-current (UHVDC) of large capacity, the scheduled outputs of the power plants are limited, and the direct power purchase (DPP) by large consumers is influenced. The negative impact caused by the failure modes of the UHVDC on the economic dispatch (ED) and the security of the power system is to be studied. Here, the derated capacities of the UHVDC are described together with their state probabilities. To maximise the profit of power plants, an ED model with the DPP is proposed. The relationship between the amount of the DPP and the power transmission by the UHVDC is decided based on two contract strategies for the DPP. The interior-point method is applied to solve the ED problem. The simulation results validate the feasibility and accuracy of the proposed model, which is beneficial to the development of the power market and the UHVDC in China.

This paper presents a novel signal processing scheme by combining an improved Vold-Kalman filter and the multi-scale sample entropy (IVKF-MSSE) for planetary gearboxes under non-stationary working conditions. In this scheme, we propose a method based on the characteristic frequency ratio (CFR) to select the VKF bandwidth. First, a CFR is adopted to select a VKF bandwidth with the largest CFR value as the optimal VKF bandwidth. Second, IVKF is used to extract fault-induced information under time-varying speed conditions. Because an optimal bandwidth is used in VKF, the feature extraction capability of VKF is enhanced. Then, the MSSE is applied to extract gearbox fault features. After that, the Laplacian score (LS) approach is introduced to refine the fault features by sorting the scale factors. At the end, the selected features are fed into the least square support vector machine (LSSVM) for effective fault pattern identification. Simulation and experimental vibration signals are employed to evaluate the effectiveness of the proposed method. Results show that the proposed method outperforms the auto-regressive AR-MSSE, VKF-MSSE and EEMD-MSSE in identifying fault types of planetary gearboxes.

A novel hybrid fault diagnosis method based on ensemble empirical mode decomposition and weighted adaptive multi-scale morphological analysis (WAMMA) is proposed to detect the early damage of gearboxes. In this method, we propose a characteristic frequency ratio (CFR) method to determine the weighted coefficient for each scale of AMMA. First, multiple scales are obtained using the AMMA method. Second, the weighted coefficient of each scale in the AMMA method is calculated using the CFR. Third, the final results can be obtained by multiplying the weighted coefficients and filtering results with all scales. Since the performance of each scale of AMMA is evaluated using the CFR, the demodulation ability can be effectively improved. However, the WAMMA is easily disturbed by heavy noise when extracting early fault feature directly. A method combined EEMD with the WAMMA is proposed. The effectiveness of the proposed method has been verified using two experimental vibration signals of gearboxes. The results demonstrate that the proposed method has a superior performance in the extraction of weak fault characteristics of gearboxes in comparison with the WAMMA and EEMD-AMMA methods.

Data-driven fault diagnosis has been a hot topic in recent years with the development of machine learning techniques. However, the prerequisite that the training data and the test data should follow an identical distribution prevents the conventional data-driven diagnosis methods from being applied to the engineering diagnosis problems. To tackle this dilemma, cross-domain fault diagnosis using knowledge transfer strategy is becoming popular in the past five years. The diagnosis methods based on transfer learning aim to build models that can perform well on target tasks by leveraging knowledge from semantic related but distribution different source domains. This paper for the first time summarizes the state-of-art cross-domain fault diagnosis research works. The literatures are introduced from three different viewpoints: research motivations, cross-domain strategies, and application objects. In addition, the corresponding open-source fault datasets and several future directions are also presented. The survey provides readers a framework for better understanding and identifying the research status, challenges and future directions of cross-domain fault diagnosis.

Multiscale symbolic dynamic entropy (MSDE) has been recently proposed to characterize the dynamical behavior of time series, which has merits of high computational efficiency and robustness to noise comparing with multiscale sample entropy (MSE) and multiscale permutation entropy (MPE). However, the variance of the MSDE values increases as the length of a time series becomes shorter using multiscale analysis. To address this shortcoming, a new method, namely refined composite multi-scale symbolic dynamic entropy (RCMSDE), is proposed to extract the fault information of rotating machinery. Then, Laplacian score (LS) is utilized to reduce the dimension of eigenvectors. In the end, the selected features are taken as the input of the improved support vector machine based on binary tree (ISVM-BT) for fault type identification. The effectiveness of the proposed method is validated using both the simulation and two experimental tests. Results demonstrate that the proposed method generates highest classification accuracy in comparison with existing methods such as MSDE, refined composite multiscale sample entropy (RCMSE) and refined composite multiscale permutation entropy (RCMPE).

Intelligent fault diagnosis provides great convenience for the prognostic and health management of the rotating machinery. Recently, the entropy-based feature extraction method has aroused researchers’ attentions due to its independence with prior knowledge, unnecessary of preprocessing, and easy to perform. The multiscale diversity entropy has been proven to be a promising feature extraction method for the intelligent fault diagnosis. Compared to the existing entropy methods, the multiscale diversity entropy has advantages of high consistency, strong robustness and high calculation efficiency. However, the multiscale diversity entropy encounters the challenge to extract features for early fault diagnosis due to the weak fault symptoms and strong noise. This can be attributed to the multiscale diversity entropy only concerns the fault information embedded in the low frequency, which ignores the information hidden in the high frequency. To address this defect, the hierarchical diversity entropy (HDE) is proposed, which can synchronously extract fault information hidden in both high and low frequency. Based on HDE and random forest, a novel intelligent fault diagnosis frame has been proposed. The effectiveness of the proposed method has been evaluated through simulated and experimental bearing signals. The results show that the proposed HDE has the best feature extraction ability compare to multiscale sample entropy, multiscale permutation entropy, multiscale fuzzy entropy, and multiscale diversity entropy.

Gearbox is one of the most important parts of the rotating machinery, so health monitoring of the gearbox is essential. The accurate positioning of tooth failure of gear is an important function of the fault diagnosis system. This paper proposes a detection strategy based on designed convolutional neural networks to detect and locate gear tooth failure. The detection strategy aims to compare the characteristic gap between the normal gear and the faulty gear in the same period extracted by the convolutional neural network, and assign weights to the faulty gear vibration signal to obtain the weight sequence of the faulty vibration signal, so as to obtain the faulty tooth weight. Finally, the health condition of the gear can be evaluated by comparing the weight between all teeth of the gear. The proposed detection strategy is tested through simulation vibration signal and experiment vibration signal. The result shows that the proposed method can successfully identify gear failure and effectively detect single tooth failure on gear.

Three-dimensional hand detection from a single RGB-D image is an important technology which supports many useful applications. Practically, it is challenging to robustly detect human hands in unconstrained environments because the RGB-D channels can be affected by many uncontrollable factors, such as light changes. To tackle this problem, we propose a 3D hand detection approach which improves the robustness and accuracy by adaptively fusing the complementary features extracted from the RGB-D channels. Using the fused RGB-D feature, the 2D bounding boxes of hands are detected first, and then the 3D locations along the z-axis are estimated through a cascaded network. Furthermore, we represent a challenging RGB-D hand detection dataset collected in unconstrained environments. Different from previous works which primarily rely on either the RGB or D channel, we adaptively fuse the RGB-D channels for hand detection. Specifically, evaluation results show that the D-channel is crucial for hand detection in unconstrained environments. Our RGB-D fusion-based approach significantly improves the hand detection accuracy from 69.1 to 74.1 comparing to one of the most state-of-the-art RGB-based hand detectors. The existing RGB- or D-based methods are unstable in unseen lighting conditions: in dark conditions, the accuracy of the RGB-based method significantly drops to 48.9, and in back-light conditions, the accuracy of the D-based method dramatically drops to 28.3. Compared with these methods, our RGB-D fusion based approach is much more robust without accuracy degrading, and our detection results are 62.5 and 65.9, respectively, in these two extreme lighting conditions for accuracy.

To solve the defects that the generalization ability of the traditional data-driven fault diagnosis model reduces or even fails in mechanical system diagnosis, a multi-scale transfer sample entropy is proposed based on the idea of transfer learning. First, the multi-scale transfer sample entropy method is proposed to extract fault features based on multi-scale sample entropy and feature transfer learning. Second, the parameters of the multiscale transfer sample entropy method are optimized to further improve the fault identification accuracy. Finally, the experiment results of rolling bearing show that the proposed multi-scale transfer sample entropy can effectively improve the generalization ability of the data-driven model and realize the accurate identification of different fault locations of the rolling bearing under a small number of samples.

With fast development of the retail market of China in recent years, the risk of the market needs to be quantified. This paper provides a detailed framework to assess and classify the risk of the market. The neural network is used to predict the risk. Time-dependent weight is used to describe cumulative effect. With the S-shaped curve, the risk factors are classified by safety, competition and elimination. The entropy method is used to set weights of the risk factors. The K-means clustering is used to classify the companies or periods. The risk factors, the operational risk, and the risk indicators form a hierarchical framework. The state aggregation based on serial tracking and incidence matrix finds transition rate matrix for early warning and coordination. The numerical results of a market with 9 companies are provided to validate the effectiveness of the proposed model.

Sample entropy (SE) has been employed for fault diagnosis of rotary machinery (FDRM). However, SE has low computation efficiency for long time series. To solve this problem, symbolic sample entropy (SSE), a novel measure of time series regularity, is proposed to estimate the complexity. However, SSE fails to account for the multiple scale information inherent in measured vibration signals. Therefore, we combine the concept of multi-scale analysis with SSE, called multi-scale SSE (MSSE). To evaluate the effectiveness of the proposed MSSE method, we apply several simulated signals to verify the merits of SSE in impulsion detection and calculation efficiency. Furthermore, we utilize one experimental data to validate its effectiveness in recognizing several fault types of rotary machinery. Experimental results indicate that MSSE has an advantage in extracting fault features compared with multi-scale entropy (MSE), multi-scale fuzzy entropy (MFE), and multi-scale permutation entropy (MPE) methods.

The health condition monitoring of rotating machinery can avoid the disastrous failure and guarantee the safe operation. The vibration-based fault diagnosis shows the most attractive character for fault diagnosis of rotating machinery (FDRM). Recently, Lempel-Ziv complexity (LZC) has been investigated as an effective tool for FDRM. However, the LZC only performs single-scale analysis, which is not suitable to extract the fault features embedded in vibrational signal over multiple scales. In this paper, a novel complexity analysis algorithm, called hierarchical Lempel-Ziv complexity (HLZC), was developed to extract the fault characteristics of rotating machinery. The proposed HLZC method considers the fault information hidden in both low-frequency and high-frequency components, resulting in a more accurate fault feature extraction. The superiority of the proposed HLZC method in detecting the periodical impulses was validated by using simulated signals. Meanwhile, two experimental signals were utilized to prove the effectiveness of the proposed HLZC method in extracting fault information. Results show that the proposed HLZC method had the best diagnosing performance compared with LZC and multi-scale Lempel-Ziv complexity methods.

The entropy-based method has been demonstrated to be an effective approach to extract the fault features by estimating the complexity of signals, but how to remove the strong background noises in analyzing early weak impulsive signal remains unexplored. To solve this problem, this paper proposes symbolic fuzzy entropy (SFE) based on symbolic dynamic filtering and fuzzy entropy to eliminate the noises and improve the calculation efficiency. The main idea of SFE is to use symbolic dynamic filtering to remove the noise-related fluctuations while significantly simplifying the circulation calculation, thereby, generating better performance in resisting the background noises and high computation efficiency. The superiority of SFE is verified via two simulated signals and other three entropy methods. For comprehensive feature description, we further extend SFE into multiscale analysis by incorporating with the coarse gaining process, called MSFE. Experimental results demonstrate that the proposed MSFE method has the best performance in extracting weak fault characteristics compared with three existing MSE, MFE, and MPE methods.

Hand detection is a crucial pre-processing procedure for many human hand related computer vision tasks, such as hand pose estimation, hand gesture recognition, human activity analysis, and so on. However, reliably detecting multiple hands from cluttering scenes remains to be a challenging task because of complex appearance diversities of dexterous human hands (e.g., different hand shapes, skin colors, illuminations, orientations, and scales, etc.) in color images. To tackle this problem, an accurate hand detection method is proposed to reliably detect multiple hands from a single color image using a hybrid detection/reconstruction convolutional neural networks (CNN) framework, in which regions of hands are detected and appearances of hands are reconstructed in parallel by sharing features extracted from a region proposal layer, and the proposed model is trained in an end-to-end manner. Furthermore, it is observed that the generative adversarial network (GAN) could further boost the detection performance by generating more realistic hand appearances. The experimental results show that the proposed approach outperforms the state-of-the-art on public challenging hand detection benchmarks.

Supply chain performance evaluation problems are evaluated using data envelopment analysis. This paper proposes a fuzzy network epsilon-based data envelopment analysis for supply chain performance evaluation. In the common data envelopment analysis models which are used for evaluation of decision-maker units efficiency, there are several inputs and outputs. One of the bugs of such models is that the intermediate products and linking activities are overlooked. Considering these intermediate activities and products, the current study evaluates the performance of decision-maker units in an automotive supply chain. There are ten decision-maker units in the supply chain in which there are three suppliers, two manufacturers, two distributors, and four customers. Moreover, the overall efficiency of input-oriented (input-based) model and input-oriented divisional efficiency are calculated. In order to improve the efficiencies, the projections onto the frontiers are obtained by using the outputs of the solved model and Lingo software. In order to show the applicability of the proposed model, it is applied on automotive industry, as a case study, to evaluate supply chain performance. Then, the overall efficiencies of DMUs and each sections (divisions) of DMUs were calculated separately. Therefore, every organization can apply this evaluation method for improving the performance of alternative factors.

Early fault diagnosis of rolling bearings is crucial to operating and maintenance cost reduction of the equipment with bearings. This paper aims to propose a novel early fault feature extraction method based on the proposed hierarchical symbol dynamic entropy (HSDE) and the binary tree support vector machine (BT-SVM). Multiscale symbolic dynamic entropy (MSDE) has been recently proposed to characterize the dynamical behavior of time series. MSDE has several merits comparing with multiscale sample entropy (MSE) and multiscale permutation entropy (MPE), such as high computational efficiency and robustness to noise. However, MSDE only utilizes the fault information in the low frequency components and consequently the fault information hidden in the high frequency components is discarded. To address this shortcoming, a new method, namely HSDE, is proposed to extract the fault information in the high frequency components. Then, the BT-SVM is utilized to automatically complete the fault type identification. The effectiveness of the proposed method is validated using simulated and experimental vibration signals. Meanwhile, a comparison is conducted between MPE, hierarchical permutation entropy (HPE), MSE, hierarchical sample entropy (HSE), MSDE and HSDE. Results show that the proposed method performs best to recognize the early fault types of rolling bearings.

The fault diagnosis of planetary gearboxes is crucial to reduce the maintenance costs and economic losses. This paper proposes a novel fault diagnosis method based on adaptive multi-scale morphological filter (AMMF) and modified hierarchical permutation entropy (MHPE) to identify the different health conditions of planetary gearboxes. In this method, AMMF is firstly adopted to remove the fault-unrelated components and enhance the fault characteristics. Second, MHPE is utilized to extract the fault features from the denoised vibration signals. Third, Laplacian score (LS) approach is employed to refine the fault features. In the end, the obtained features are fed into the binary tree support vector machine (BT-SVM) to accomplish the fault pattern identification. The proposed method is numerically and experimentally demonstrated to be able to recognize the different fault categories of planetary gearboxes.

Product recovery, accompanied by cradle to cradle policies from the contemporary supply chain, becomes an essential element in meeting environmental compliance and waste management policies. Incorporation of reverse logistics into the traditional supply chains becomes a complementary factor for efficient product recovery. To begin with product recovery, consumers are encouraged to return their end-of-use/end-of-life products, and the steps of collecting and planning the movement of returned products are crucial decisions. The efficient planning of a cost effective recovery process in reverse logistics requires dealing with the uncertainty underlying in the quantity and quality of the returned products. In this paper, we propose establishing an initial collection point within a permissible radius of the customer zones to overcome some of the issues of uncertainty. The uncertainty in the quantity and quality of the returned products are modelled using fuzzy triangular numbers. To capture the real world conditions of the proposed problem, our model aims at maximizing the profit incurred in the recovery process in an uncertain environment. The model was solved with the help of fuzzy mathematical programming. The model is validated by a company case belonging to the manufacturing of electronic products. To increase the applicability of the product recovery process in the industry, we propose a recovery process for the planning horizon consisting of multi periods and multi products. The outcomes of the proposed model indicate that for the successful realisation of such network, customers need to be legally enforced to return their end of used products in the channels established for value recovery.

Despite rapid advances in the field of image denoising, heavy noise removal has remained an under-explored area. When the strength of noise becomes comparable to or even more dominating than that of signal, restoration of important structures from such heavily-contaminated images becomes more challenging. Existing model-based and learning-based image denoising techniques often cannot delivery satisfactory results, which call for new insights and algorithmic tools. In this paper, we propose to remove heavy noise with the help of similar images retrieved from datasets, which leads to a hybrid approach combining sparsity-based and learning-based methods. Specifically, the parametric sparse prior of underlying clean image is learned from the retrieved reference images and the input noisy image. Leveraging prior from the reference images, the estimated parametric model contains much more accurate information of image details. When compared against existing conventional methods, the proposed hybrid approach is more capable of restoring fine-detailed structures in the presence of heavy noise. Experimental results show that the proposed method dramatically outperforms current state-of-the-art image denoising methods both subjectively and objectively.

Rolling bearings' operation under variable speed conditions exhibits complex time-varying modulations and spectral structures, resulting in difficulty in the fault diagnosis. In order to effectively remove the influence of the rotational speed and extract the fault characteristics, this paper develops a fault diagnosis scheme based on the Vold-Kalman filter (VKF), refined composite multi-scale fuzzy entropy (RCMFE), and Laplacian score (LS). In the proposed method, the VKF is first adopted to remove the fault-unrelated components and give a clear representation of the fault symptoms. Second, the RCMFE is applied to extract fault features from the denoised vibration signal. Third, the LS approach is introduced to refine the fault features by sorting the scale factors. In the end, the selected features are fed into the logistic regression to automatically complete the fault pattern identifications. The proposed method is experimentally demonstrated to be able to recognize the localized defect on the inner race, outer race, and rolling element under variable speed conditions.

Rotating machines have been widely used in industrial engineering. The fault diagnosis of rotating machines plays a vital important role to reduce the catastrophic failures and heavy economic loss. However, the measured vibration signal of rotating machinery often represents non-linear and non-stationary characteristics, resulting in difficulty in the fault feature extraction. As a statistical measure, entropy can quantify the complexity and detect dynamic change through taking into account the non-linear behavior of time series. Therefore, entropy can be served as a promising tool to extract the dynamic characteristics of rotating machines. Recently, many studies have applied entropy in fault diagnosis of rotating machinery. This paper aims to investigate the applications of entropy for the fault characteristics extraction of rotating machines. First, various entropy methods are briefly introduced. Its foundation, application, and some improvements are described and discussed. The review is divided into eight parts: Shannon entropy, Rényi entropy, approximate entropy, sample entropy, fuzzy entropy, permutation entropy, and other entropy methods. In each part, we will review the applications using the original entropy method and the improved entropy methods, respectively. In the end, a summary and some research prospects are given.

According to the performance degradation law of aeroengine in operation, we proposed a method of aeroengine performance degradation evaluation based on the fusion decision of Hierarchical Bayes method (HB) and deep neural network (DNN). Hierarchical Bayes method was used to build the aeroengine reliability model. Then Based on the aeroengine operation monitoring parameters and reliability model, we used deep learning method to extract the performance degradation law and to evaluate aeroengine performance level, realized the fusion decision of engine performance degradation assessment. 9467 monitoring samples, contaminated with sensor noise, collected from 50 aeroengines was used to evaluate the quality of the network, and the average accuracy is 92.01%. The results showed that this method showed good robustness and reduced the risk of the evaluation results error caused by noise.

This paper presents a semantics-aware rule recommendation and enforcement (SARRE) system for taming information leakage on Android. SARRE leverages statistical analysis and a novel application of minimum path cover algorithm to identify system event paths from dynamic runtime monitoring. Then, an online recommendation system is developed to automatically assign a fine-grained security rule to each event path, capitalizing on both known security rules and application semantic information. The proposed SARRE system is prototyped on Android devices and evaluated using real-world malware samples and popular apps from Google Play spanning multiple categories. Our results show that SARRE achieves 93.8% precision and 96.4% recall in identifying the event paths, compared with tainting technique. Also, the average difference between rule recommendation and manual configuration is less than 5%, validating the effectiveness of the automatic rule recommendation. It is also demonstrated that by enforcing the recommended security rules through a camouflage engine, SARRE can effectively prevent information leakage and enable fine-grained protection over private data with very small performance overhead.

Unmanned Aerial Vehicles (UAVs) are widely used for various civilian, security and military applications. UAVs are equipped with a number of sensors such as accelerometers and gyroscopes, the measured data reliability of these sensors is critical and data obtained from these sensors must be accurate. Sometimes, sensors are prone to damage because of various electric/communication problems. This paper proposes a statistical scheme for catering real-time experimental results of fault detection for inertial measurement unit sensors (accelerometer and gyroscope) by using statistical analysis measures. The objective is to detect sensor bias fault, total sensor failure and drift or additive type fault in gyroscope and accelerometer measurements by processing their data via statistical measures. The scheme of processing the sensor data aims to suggest best statistical measures for fault detection in a multiple-sensor setting, after graphical signal analysis (comparison of the graphs of signal overture of all sensors) has been completed. This scheme can be helpful in diagnosis and subsequent isolation of sensors with fault in high-reliability applications where accuracy of data is critical.

We consider the problem of optimally mapping an edge computing service that is modeled as a tree with multiple processing sub-tasks and data flows onto the underlying physical network. As new computing and data analytics applications require more complicated data processing structures, and different types of data (e.g., images, videos, and numbers) sensed at geographically distributed locations must be collected and processed to obtain a complex and comprehensive result, highly intelligent algorithms are needed to solve this challenging problem. In this paper, we propose a learning-based hierarchical service tree placement strategy that aims to optimize the net utility, defined as achieved utility minus network congestion. The key idea is to decouple a service tree into appropriate sub-trees each containing a single computing sub-task as well as associated data flows and to recursively leverage Q-learning to place each sub-tree while maintaining the dependencies of sub-tasks in the service tree structure. It enables a scalable solution for large networks with unknown arrival statistics and complex service structures. Numerical results show that our solution can significantly outperform baseline heuristics in online service tree placement.

Diagnosis of gearbox is crucial to prevent catastrophic failure and reduce financial losses. In this study, we introduce a novel fault diagnosis technique using the infrared thermography (IRT). The IRT-based techniques have merits of non-contact measurement and high-scalability. Since the convolutional neural network (CNN) is proven to be powerful in image processing, a fault diagnosis strategy is designed by combining the IRT and CNN. Then, the pattern identification is achieved by using softmax regression (SR) classifier. One experimental data is used to validate the effectiveness of the proposed method. Results demonstrate that this diagnosis strategy can recognize gearbox with various oil-level faults. Furthermore, some important distinguishable areas of IRT images are marked for further focused research field.

A Data Processing Network (DPN) streams massive volumes of data collected and stored by the network to multiple processing units to compute desired results in a timely fashion. Due to ever-increasing traffic, distributed cache nodes can be deployed to store hot data and rapidly deliver them for consumption. However, prior work on caching policies has primarily focused on the potential gains in network performance, e.g., cache hit ratio and download latency, while neglecting the impact of cache on data processing and consumption.In this paper, we propose a novel framework, DeepChunk, which leverages deep Q-learning for chunk-based caching in DPN. We show that cache policies must be optimized for both network performance during data delivery and processing efficiency during data consumption. Specifically, DeepChunk utilizes a model-free approach by jointly learning limited network, data streaming, and processing statistics at runtime and making cache update decisions under the guidance of powerful deep Q-learning. It enables a joint optimization of multiple objectives including chunk hit ratio, processing stall time, and object download time while being self-adaptive under the time-varying workload and network conditions. We build a prototype implementation of DeepChunk with Ceph, a popular distributed object storage system. Our extensive experiments and evaluation demonstrate significant improvement, i.e., 43% in total reward and 39% in processing stall time, over a number of baseline caching policies.

Hand pose estimation is a critical technology of computer vision and human-computer interaction. Deep-learning methods require a considerable amount of tagged data. Accordingly, numerous labeled training data are required. This paper aims to generate depth hand images. Given a ground-truth 3D hand pose, the developed method can generate depth hand images. To be specific, a ground truth can be 3D hand poses with the hand structure contained, while the synthesized image has an identical size to that of the training image and a similar visual appearance to the training set. The developed method, inspired by the progress in the generative adversarial network (GAN) and image-style transfer, helps model the latent statistical relationship between the ground-truth hand pose and the corresponding depth hand image. The images synthesized using the developed method are demonstrated to be feasible for enhancing performance. On public hand pose datasets (NYU, MSRA, ICVL), comprehensive experiments prove that the developed method outperforms the existing works.

As an important machine component, the gearbox is widely used in industry for power transmission. Condition monitoring (CM) of a gearbox is critical to provide timely information for undertaking necessary maintenance actions. Massive research efforts have been made in the last two decades to develop vibration-based techniques. However, vibration-based methods usually include several inherent shortages including contact measurement, localized information, noise contamination, and high computation costs, making it difficult to be a cost-effective CM technique. In this paper, infrared thermal (IRT) images, which can contain information covering a large area and acquired remotely, are based on developing a cost-effective CM method. Moreover, a convolutional neural network (CNN) is employed to automatically process the raw IRT images for attaining more comprehensive feature parameters, which avoids the deficiency of incomplete information caused by various feature-extraction methods in vibration analysis. Thus, an IRT&ndash, CNN method is developed to achieve online remote monitoring of a gearbox. The performance evaluation based on a bevel gearbox shows that the proposed method can achieve nearly 100% correctness in identifying several common gear faults such as tooth pitting, cracks, and breakages and their compounds. It is also especially robust to ambient temperature changes. In addition, IRT also significantly outperforms its vibration-based counterparts.

Multi-scale permutation entropy (MPE) is a statistic indicator to detect nonlinear dynamic changes in time series, which has merits of high calculation efficiency, good robust ability, and independence from prior knowledge, etc. However, the performance of MPE is dependent on the parameter selection of embedding dimension and time delay. To complete the automatic parameter selection of MPE, a novel parameter optimization strategy of MPE is proposed, namely optimized multi-scale permutation entropy (OMPE). In the OMPE method, an improved Cao method is proposed to adaptively select the embedding dimension. Meanwhile, the time delay is determined based on mutual information. To verify the effectiveness of OMPE method, a simulated signal and two experimental signals are used for validation. Results demonstrate that the proposed OMPE method has a better feature extraction ability comparing with existing MPE methods.

A novel systematic framework, infrared thermography- (IRT-) based method, for rotating machinery fault diagnosis under nonstationary running conditions is presented in this paper. In this framework, IRT technique is first applied to obtain the thermograph. Then, the fault features are extracted using bag-of-visual-word (BoVW) from the IRT images. In the end, support vector machine (SVM) is utilized to automatically identify the fault patterns of rotating machinery. The effectiveness of proposed method is evaluated using lab experimental signal of rotating machinery. The diagnosis results show that the IRT-based method has certain advantages in classification rotating machinery faults under nonstationary running conditions compared with the traditional vibration-based method.

Mobile Edge Computing has quickly become a promising paradigm to meet the ever-increasing data-processing demands imposed by emerging applications, by shifting computations to network edge. In this paper, we address two problems unique in edge computing: How to determine the execution cost contributed by each computing task in an edge environment, and how to distributively assign tasks to heterogeneous edge nodes to minimize total execution cost? Cost accounting is a long-standing hard problem for multiprocessing systems, e.g., when edge nodes jointly process tasks from different users. We propose a new framework that models the problem as a multichoice cooperative game, and use Shapley Value for cost accounting. The result enables us to decouple the cost of concurrent task executions and to efficiently solve the task assignment problem through a distributive Hungarian algorithm. To evaluate the performance, we conduct hybrid experiments by collecting trace from a fully implemented edge testbed and generating cost profiles to drive extensive simulations. Numerical results show that our solution guided by multichoice Shapley value is able to consistently outperform two baseline strategies using oblivious cost accounting policies, for task assignment in heterogeneous edge networks. Our solution's advantages become more significant for edge networks with higher levels of heterogeneity (either computation- or network-wise).

Since the vibration signals of gearbox are non-linear and non-stationary, it is difficult to accurately evaluate the working conditions. Therefore, a fault feature extraction technique based on intrinsic characteristic-scale decomposition (ICD) and multi-scale entropy (MSE) is presented in this paper. The measured signals are firstly decomposed into a series of product components (PCs) by ICD. Secondly, the main product component is selected, and then MSE is used to extract the feature vectors from the selected PCs. Finally, the obtained feature vectors of gearbox with different scale factors are adopted as inputs of support vector machine (SVM) to fulfill the fault patterns identification. The superiority of the proposed technique is verified through comparing with three other methods.

A novel rolling bearing fault diagnosis method based on hierarchical fuzzy entropy (HFE), Laplacian score (LS) and improved support vector machine based binary tree (ISVM-BT) is proposed in this paper. Focus on the difficulty of extracting fault feature from the non-linear and non-stationary vibration signal under complex operating conditions, HFE method is utilized for fault feature extraction. Compared with multi-scale fuzzy entropy (MFE) method, HFE method considers both the low and high frequency components of the vibration signals, which can provide a much more accurate estimation of entropy. Besides, Laplacian score (LS) method is introduced to refine the fault feature by sorting the scale factors. Subsequently, the obtained features are fed into the multi-fault classifier ISVM-BT to automatically fulfill the fault pattern identifications. The experimental results demonstrate that the proposed method is effective in recognizing the different categories and severities of rolling bearings faults.

In this paper, we mainly study the application of a multi-objective optimization algorithm based on the black hole algorithm in motor optimization. Using the combination of global search and local search, the continuous search area is better. The random search method is used in the global search, and a momentum gradient method is used in the local search, which makes the search results have faster convergence rates and easier convergence to the global optimal. A new file management strategy is used to make the optimization results more global and have better generalization ability. in practical application, the design of motor is often affected by manufacturing error, so random noise is added to the selection of optimization results, which can be more in line with the practical application. Finally, the actual motor model and complex function are used to test the performance of the optimization algorithm. Finally, the actual motor model and complex function are used to verify the performance of the optimization algorithm.