Fault diagnosis of electric motors is a fundamental task for production line testing, and it is usually performed by experienced human operators. In the recent years, several methods have been proposed in the literatu...Fault diagnosis of electric motors is a fundamental task for production line testing, and it is usually performed by experienced human operators. In the recent years, several methods have been proposed in the literature for detecting faults automatically. Deep neural networks have been successfully employed for this task, but, up to the authors' knowledge, they have never been used in an unsupervised scenario. This paper proposes an unsupervised method for diagnosing faults of electric motors by using a novelty detection approach based on deep autoencoders. In the proposed method, vibration signals are acquired by using accelerometers and processed to extract LogMel coefficients as features. Autoencoders are trained by using normal data only, i.e., data that do not contain faults. Three different autoencoders architectures have been evaluated: the multilayer perceptron(MLP) autoencoder, the convolutional neural network autoencoder, and the recurrent autoencoder composed of long short-term memory(LSTM) units. The experiments have been conducted by using a dataset created by the authors, and the proposed approaches have been compared to the one-class support vector machine(OC-SVM) algorithm. The performance has been evaluated in terms area under curve(AUC) of the receiver operating characteristic curve, and the results showed that all the autoencoder-based approaches outperform the OCSVM algorithm. Moreover, the MLP autoencoder is the most performing architecture, achieving an AUC equal to 99.11 %.展开更多
Li–S and Li–Se batteries have attracted tremendous attention during the past several decades, as the energy density of Li–S and Li–Se batteries is high（several times higher than that of traditional Li-ion batter...Li–S and Li–Se batteries have attracted tremendous attention during the past several decades, as the energy density of Li–S and Li–Se batteries is high（several times higher than that of traditional Li-ion batteries）.Besides, Li–S and Li–Se batteries are low cost and environmental benign. However, the commercial applications of Li–S and Li–Se batteries are hindered by the dissolution and shuttle phenomena of polysulfide（polyselenium）, the low conductivity of S（Se）, etc. To overcome these drawbacks, scientists have come up with various methods, such as optimizing the electrolyte, synthesizing composite electrode of S/polymer, S/carbon, S/metal organic framework（MOF） and constructing novelty structure of battery.In this review, we present a systematic introduction about the recent progress of Li–S and Li–Se batteries, especially in the area of electrode materials, both of cathode material and anode material for Li–S and Li–Se batteries. In addition, other methods to lead a high-performance Li–S and Li–Se batteries are also briefly summarized, such as constructing novelty battery structure, adopting proper charge–discharge conditions, heteroatom doping into sulfur molecules, using different kinds of electrolytes and binders. In the end of the review, the developed directions of Li–S and Li–Se batteries are also pointed out. We believe that combining proper porous carbon matrix and heteroatom doping may further improve the electrochemical performance of Li–S and Li–Se batteries. We also believe that Li–S and Li–Se batteries will get more exciting results and have promising future by the effort of battery community.展开更多
目的研究澳门红树林植物内生放线菌多样性及新颖性,为放线菌新物种及新抗生素发现奠定基础。方法 12份采集自澳门红树林的植物样品,消毒粉碎后,撒在10种分离培养基上分离内生放线菌,采用ISP2培养基进行菌株纯化;通过PCR扩增和测序获得16...目的研究澳门红树林植物内生放线菌多样性及新颖性,为放线菌新物种及新抗生素发现奠定基础。方法 12份采集自澳门红树林的植物样品,消毒粉碎后,撒在10种分离培养基上分离内生放线菌,采用ISP2培养基进行菌株纯化;通过PCR扩增和测序获得16S r RNA基因序列,并提交到数据库中进行搜索比对,开展内生放线菌多样性和新颖性分析;放线菌潜在新物种经液体发酵、离心后,上清液经乙酸乙酯萃取,菌丝经丙酮浸泡,分别获得发酵液水相样品、发酵液酯相样品和菌丝丙酮浸提液3类样品;样品通过纸片扩散法进行抗菌活性初筛。结果从12份植物样品中得到192株内生放线菌,分布于8个目17个科30个属,其中链霉菌为优势菌属;16S r RNA基因序列相似性低于98.6%的菌株共有22株,其中菌株4Q3S-3和2Q3S-4-2分别为弗莱德门菌属(Friedmanniella)和中村菌属(Nakamurella)的新种,放线菌潜在新物种的鉴定工作正在进行;2株放线菌新种及6株潜在放线菌新种的抗菌活性筛选结果表明,5株具有抗菌活性。结论澳门红树林植物内生放线菌资源丰富多样,新颖性高,具有从中发现放线菌新物种和新抗生素的潜力,值得深入研究。展开更多
基金supported by the Italian University and Research Consortium CINECA
文摘Fault diagnosis of electric motors is a fundamental task for production line testing, and it is usually performed by experienced human operators. In the recent years, several methods have been proposed in the literature for detecting faults automatically. Deep neural networks have been successfully employed for this task, but, up to the authors' knowledge, they have never been used in an unsupervised scenario. This paper proposes an unsupervised method for diagnosing faults of electric motors by using a novelty detection approach based on deep autoencoders. In the proposed method, vibration signals are acquired by using accelerometers and processed to extract LogMel coefficients as features. Autoencoders are trained by using normal data only, i.e., data that do not contain faults. Three different autoencoders architectures have been evaluated: the multilayer perceptron(MLP) autoencoder, the convolutional neural network autoencoder, and the recurrent autoencoder composed of long short-term memory(LSTM) units. The experiments have been conducted by using a dataset created by the authors, and the proposed approaches have been compared to the one-class support vector machine(OC-SVM) algorithm. The performance has been evaluated in terms area under curve(AUC) of the receiver operating characteristic curve, and the results showed that all the autoencoder-based approaches outperform the OCSVM algorithm. Moreover, the MLP autoencoder is the most performing architecture, achieving an AUC equal to 99.11 %.
基金financially supported by the National Natural Science Foundation of China(Nos.21373195 and 51622210)the Fundamental Research Funds for the Central Universities(No.WK3430000004)
文摘Li–S and Li–Se batteries have attracted tremendous attention during the past several decades, as the energy density of Li–S and Li–Se batteries is high（several times higher than that of traditional Li-ion batteries）.Besides, Li–S and Li–Se batteries are low cost and environmental benign. However, the commercial applications of Li–S and Li–Se batteries are hindered by the dissolution and shuttle phenomena of polysulfide（polyselenium）, the low conductivity of S（Se）, etc. To overcome these drawbacks, scientists have come up with various methods, such as optimizing the electrolyte, synthesizing composite electrode of S/polymer, S/carbon, S/metal organic framework（MOF） and constructing novelty structure of battery.In this review, we present a systematic introduction about the recent progress of Li–S and Li–Se batteries, especially in the area of electrode materials, both of cathode material and anode material for Li–S and Li–Se batteries. In addition, other methods to lead a high-performance Li–S and Li–Se batteries are also briefly summarized, such as constructing novelty battery structure, adopting proper charge–discharge conditions, heteroatom doping into sulfur molecules, using different kinds of electrolytes and binders. In the end of the review, the developed directions of Li–S and Li–Se batteries are also pointed out. We believe that combining proper porous carbon matrix and heteroatom doping may further improve the electrochemical performance of Li–S and Li–Se batteries. We also believe that Li–S and Li–Se batteries will get more exciting results and have promising future by the effort of battery community.
文摘目的研究澳门红树林植物内生放线菌多样性及新颖性,为放线菌新物种及新抗生素发现奠定基础。方法 12份采集自澳门红树林的植物样品,消毒粉碎后,撒在10种分离培养基上分离内生放线菌,采用ISP2培养基进行菌株纯化;通过PCR扩增和测序获得16S r RNA基因序列,并提交到数据库中进行搜索比对,开展内生放线菌多样性和新颖性分析;放线菌潜在新物种经液体发酵、离心后,上清液经乙酸乙酯萃取,菌丝经丙酮浸泡,分别获得发酵液水相样品、发酵液酯相样品和菌丝丙酮浸提液3类样品;样品通过纸片扩散法进行抗菌活性初筛。结果从12份植物样品中得到192株内生放线菌,分布于8个目17个科30个属,其中链霉菌为优势菌属;16S r RNA基因序列相似性低于98.6%的菌株共有22株,其中菌株4Q3S-3和2Q3S-4-2分别为弗莱德门菌属(Friedmanniella)和中村菌属(Nakamurella)的新种,放线菌潜在新物种的鉴定工作正在进行;2株放线菌新种及6株潜在放线菌新种的抗菌活性筛选结果表明,5株具有抗菌活性。结论澳门红树林植物内生放线菌资源丰富多样,新颖性高,具有从中发现放线菌新物种和新抗生素的潜力,值得深入研究。
