Flexible job shop scheduling problem (FJSP) which is an extension of the classical job shop scheduling problem is a very important problem in the modern manufacturing system. It allows an operation ...to be processed by any machine from a given set. It has been proved to be a NP-hard problem. In this paper, an effective hybrid algorithm (HA) which hybridizes the genetic algorithm (GA) and tabu search (TS) has been proposed for the FJSP with the objective to minimize the makespan. The GA which has powerful global searching ability is utilized to perform exploration, and TS which has good local searching ability is applied to perform exploitation. Therefore, the proposed HA has very good searching ability and can balance the intensification and diversification very well. In order to solve the FJSP effectively, effective encoding method, genetic operators and neighborhood structure are used in this method. Six famous benchmark instances (including 201 open problems) of FJSP have been used to evaluate the performance of the proposed HA. Comparisons among proposed HA and other state-of-the-art reported algorithms are also provided to show the effectiveness and efficiency of proposed method. The computational time of proposed HA also has been compared with other algorithms. The experimental results demonstrate that the proposed HA has achieved significant improvement for solving FJSP regardless of the solution accuracy and the computational time. And, the proposed method obtains the new best solutions for several benchmark problems.
•We propose an algorithm which hybridizes the GA and TS for solving FJSP.•The proposed algorithm combines the global search and local search by using GA to perform exploration and TS to perform exploitation.•The proposed algorithm has achieved significant improvement for solving FJSP regardless of the solution accuracy and the computational time, and obtained the new best solutions for several benchmark problems.
We describe a new approach to estimating relative risks in time-to-event prediction problems with censored data in a fully parametric manner. Our approach does not require making strong assumptions ...of constant proportional hazards of the underlying survival distribution, as required by the Cox-proportional hazard model. By jointly learning deep nonlinear representations of the input covariates, we demonstrate the benefits of our approach when used to estimate survival risks through extensive experimentation on multiple real world datasets with different levels of censoring. We further demonstrate advantages of our model in the competing risks scenario. To the best of our knowledge, this is the first work involving fully parametric estimation of survival times with competing risks in the presence of censoring.
Fault diagnosis is vital in manufacturing system, since early detections on the emerging problem can save invaluable time and cost. With the development of smart manufacturing, the data-driven fault ...diagnosis becomes a hot topic. However, the traditional data-driven fault diagnosis methods rely on the features extracted by experts. The feature extraction process is an exhausted work and greatly impacts the final result. Deep learning (DL) provides an effective way to extract the features of raw data automatically. Convolutional neural network (CNN) is an effective DL method. In this study, a new CNN based on LeNet-5 is proposed for fault diagnosis. Through a conversion method converting signals into two-dimensional (2-D) images, the proposed method can extract the features of the converted 2-D images and eliminate the effect of handcrafted features. The proposed method which is tested on three famous datasets, including motor bearing dataset, self-priming centrifugal pump dataset, and axial piston hydraulic pump dataset, has achieved prediction accuracy of 99.79%, 99.481%, and 100%, respectively. The results have been compared with other DL and traditional methods, including adaptive deep CNN, sparse filter, deep belief network, and support vector machine. The comparisons show that the proposed CNN-based data-driven fault diagnosis method has achieved significant improvements.
A compact accretion disk may be formed in the merger of two neutron stars or of a neutron star and a stellar-mass black hole. Outflows from such accretion disks have been identified as a major site ...of rapid neutron-capture (r-process) nucleosynthesis and as the source of "red" kilonova emissions following the first observed neutron-star merger GW170817. We present long-term general-relativistic radiation magnetohydrodynamic simulations of a typical postmerger accretion disk at initial accretion rates of ˙ M ∼ 1 M⊙ s−1 over 400 ms postmerger. We include neutrino radiation transport that accounts for the effects of neutrino fast flavor conversions dynamically. We find ubiquitous flavor oscillations that result in a significantly more neutron-rich outflow, providing lanthanide and 3rd-peak r-process abundances similar to solar abundances. This provides strong evidence that postmerger accretion disks are a major production site of heavy r-process elements. A similar flavor effect may allow for increased lanthanide production in collapsars.
Full text
Available for:
CMK, CTK, FMFMET, NUK, UL
Fault diagnosis plays an important role in modern industry. With the development of smart manufacturing, the data-driven fault diagnosis becomes hot. However, traditional methods have two ...shortcomings: 1) their performances depend on the good design of handcrafted features of data, but it is difficult to predesign these features and 2) they work well under a general assumption: the training data and testing data should be drawn from the same distribution, but this assumption fails in many engineering applications. Since deep learning (DL) can extract the hierarchical representation features of raw data, and transfer learning provides a good way to perform a learning task on the different but related distribution datasets, deep transfer learning (DTL) has been developed for fault diagnosis. In this paper, a new DTL method is proposed. It uses a three-layer sparse auto-encoder to extract the features of raw data, and applies the maximum mean discrepancy term to minimizing the discrepancy penalty between the features from training data and testing data. The proposed DTL is tested on the famous motor bearing dataset from the Case Western Reserve University. The results show a good improvement, and DTL achieves higher prediction accuracies on most experiments than DL. The prediction accuracy of DTL, which is as high as 99.82%, is better than the results of other algorithms, including deep belief network, sparse filter, artificial neural network, support vector machine and some other traditional methods. What is more, two additional analytical experiments are conducted. The results show that a good unlabeled third dataset may be helpful to DTL, and a good linear relationship between the final prediction accuracies and their standard deviations have been observed.
Convolutional neural network (CNN) has gained increasing attention in fault classification. However, the performance of CNN is sensitive to its learning rate. Some previous works have been done to ...tune the learning rate, including the "trial and error" and manual search, which heavily depend on the experts' experiences and should be conducted repeatedly on every dataset. Because of the variety of the fault data, it is time-consuming and labor intensive to use these traditional tuning methods for fault classification. To overcome this problem, in this article, we develop a novel learning rate scheduler based on the reinforcement learning (RL) for convolutional neural network (RL-CNN) in fault classification, which can schedule the learning rate efficiently and automatically. First, a new RL agent is designed to learn the policies about the learning rate adjustment during the training process. Second, a new structure of RL-CNN is developed to balance the exploration and exploitation of the agent. Third, the bagging ensemble version of RL-CNN (RL-CNN-Ens) is presented. Three bearing datasets are used to test the performance of RL-CNN-Ens. The results show that RL-CNN-Ens outperforms the traditional DLs and machine learning methods. Meanwhile, RL-CNN-Ens can find the state-of-the-art learning rate schedulers as human designed, showing its potential in fault classification.
MAGNETAR HEATING Beloborodov, Andrei M.; Li, Xinyu
The Astrophysical journal,
12/2016, Volume:
833, Issue:
2
Journal Article
Peer reviewed
Open access
ABSTRACT We examine four candidate mechanisms that could explain the high surface temperatures of magnetars. (1) Heat flux from the liquid core heated by ambipolar diffusion. It could sustain the ...observed surface luminosity erg s−1 if core heating offsets neutrino cooling at a temperature K. This scenario is viable if the core magnetic field exceeds 1016 G and the heat-blanketing envelope of the magnetar has a light-element composition. However, we find that the lifetime of such a hot core should be shorter than the typical observed lifetime of magnetars. (2) Mechanical dissipation in the solid crust. This heating can be quasi-steady, powered by gradual (or frequent) crustal yielding to magnetic stresses. We show that it obeys a strong upper limit. As long as the crustal stresses are fostered by the field evolution in the core or Hall drift in the crust, mechanical heating is insufficient to sustain persistent erg s−1. The surface luminosity is increased in an alternative scenario of mechanical deformations triggered by external magnetospheric flares. (3) Ohmic dissipation in the crust, in volume or current sheets. This mechanism is inefficient because of the high conductivity of the crust. Only extreme magnetic configurations with crustal fields G varying on a 100 meter scale could provide erg s−1. (4) Bombardment of the stellar surface by particles accelerated in the magnetosphere. This mechanism produces hot spots on magnetars. Observations of transient magnetars show evidence of external heating.
Radar, as one of the sensors for human activity recognition (HAR), has unique characteristics such as privacy protection and contactless sensing. Radar-based HAR has been applied in many fields such ...as human–computer interaction, smart surveillance and health assessment. Conventional machine learning approaches rely on heuristic hand-crafted feature extraction, and their generalization capability is limited. Additionally, extracting features manually is time–consuming and inefficient. Deep learning acts as a hierarchical approach to learn high-level features automatically and has achieved superior performance for HAR. This paper surveys deep learning based HAR in radar from three aspects: deep learning techniques, radar systems, and deep learning for radar-based HAR. Especially, we elaborate deep learning approaches designed for activity recognition in radar according to the dimension of radar returns (i.e., 1D, 2D and 3D echoes). Due to the difference of echo forms, corresponding deep learning approaches are different to fully exploit motion information. Experimental results have demonstrated the feasibility of applying deep learning for radar-based HAR in 1D, 2D and 3D echoes. Finally, we address some current research considerations and future opportunities.
•Labeling large-scale data for steel surface defect recognition is costly and hard.•A semi-supervised learning method is proposed with limited labeled data.•This method has better performances with ...17.53% improvement.•The proposed method is successfully applied into a real-world case.
Automatic defect recognition is one of the research hotspots in steel production, but most of the current methods focus on supervised learning, which relies on large-scale labeled samples. In some real-world cases, it is difficult to collect and label enough samples for model training, and this might impede the application of most current works. The semi-supervised learning, using both labeled and unlabeled samples for model training, can overcome this problem well. In this paper, a semi-supervised learning method using the convolutional neural network (CNN) is proposed for steel surface defect recognition. The proposed method requires fewer labeled samples, and the unlabeled data can be used to help training. And, the CNN is improved by Pseudo-Label. The experimental results on a benchmark dataset of steel surface defect recognition indicate that the proposed method can achieve good performances with limited labeled data, which achieves an accuracy of 90.7% with 17.53% improvement. Furthermore, the proposed method has been applied to a real-world case from a Chinese steel company, and obtains an accuracy of 86.72% which significantly better than the original method in this workshop.
Age-associated changes in mitochondria are closely involved in aging. Apart from the established roles in bioenergetics and biosynthesis, mitochondria are signaling organelles that communicate their ...fitness to the nucleus, triggering transcriptional programs to adapt homeostasis stress that is essential for organismal health and aging. Emerging studies revealed that mitochondrial-to-nuclear (mito-nuclear) communication via altered levels of mitochondrial metabolites or stress signals causes various epigenetic changes, facilitating efforts to maintain homeostasis and affect aging. Here, we summarize recent studies on the mechanisms by which mito-nuclear communication modulates epigenomes and their effects on regulating the aging process. Insights into understanding how mitochondrial metabolites serve as prolongevity signals and how aging affects this communication will help us develop interventions to promote longevity and health.
Mito-nuclear communication plays an integral role in cellular homeostasis and aging.Mitochondrial metabolites are substrates or mediators of epigenetic modifications.Mitochondrial-to-nuclear stress signals modulate lifespan via epigenetic regulations.