Comprehensive CeMgA111O19： Tb3＋ （CTMA） disintegration via alkaline fusion was discussed. The rare earth （RE） elements in CTMA were dissolved by HC1 completely after alkaline fusion. Relationships between the alk...Comprehensive CeMgA111O19： Tb3＋ （CTMA） disintegration via alkaline fusion was discussed. The rare earth （RE） elements in CTMA were dissolved by HC1 completely after alkaline fusion. Relationships between the alkaline fusion temperature and various properties of the compounds were examined by various techniques to elu- cidate their roles in the expected CTMA disintegration. X-ray diffraction （XRD） analysis indicates the phase transformation sequence. A scientific hypothesis of crystal structure disintegration presents that sodium ions substitute for the europium and barium ions in the mirror plane and magnesium ions in the spinel block successively, resulting in that more oxygen vacancies and interstitial sodium ions appear. The unit cell [P63/mmc （194）] breaks from the mirror plane. Then it is decomposed into NaA102, and magnesium, cerium, and terbium ions combine with free OH- into MgO, Tb2O3 and CeO2; Tb2O3 and CeO2 change into Ceo.6Tbo.O2-x. In the end, the rare earth oxide is recycled easily by the acidolysis. The mechanism provides fundamental basis for recycling of REEs from waste phosphors.展开更多
The current life-prediction models for lithium-ion batteries have several problems, such as the construction of complex feature structures, a high number of feature dimensions, and inaccurate prediction results. To ov...The current life-prediction models for lithium-ion batteries have several problems, such as the construction of complex feature structures, a high number of feature dimensions, and inaccurate prediction results. To overcome these problems, this paper proposes a deep-learning model combining an autoencoder network and a long short-term memory network. First, this model applies the characteristics of the autoencoder to reduce the dimensionality of the high-dimensional features extracted from the battery data set and realize the fusion of complex time-domain features, which overcomes the problems of redundant model information and low computational efficiency. This model then uses a long short-term memory network that is sensitive to time-series data to solve the long-path dependence problem in the prediction of battery life. Lastly, the attention mechanism is used to give greater weight to features that have a greater impact on the target value, which enhances the learning effect of the model on the long input sequence. To verify the efficacy of the proposed model, this paper uses NASA's lithium-ion battery cycle life data set.展开更多
Target detection is an important task in computer vision research, and such an anomaly detection and the topic of small target detection task is more concerned. However, there are still some problems in this kind of r...Target detection is an important task in computer vision research, and such an anomaly detection and the topic of small target detection task is more concerned. However, there are still some problems in this kind of researches, such as small target detection in complex environments is susceptible to background interference and poor detection results. To solve these issues, this study proposes a method which introduces the attention mechanism into the you only look once(YOLO) network. In addition, the amateur-produced mask dataset was created and experiments were conducted. The results showed that the detection effect of the proposed mothed is much better.展开更多
Contrastive graph clustering(CGC)has become a prominent method for self-supervised representation learning by contrasting augmented graph data pairs.However,the performance of CGC methods critically depends on the cho...Contrastive graph clustering(CGC)has become a prominent method for self-supervised representation learning by contrasting augmented graph data pairs.However,the performance of CGC methods critically depends on the choice of data augmentation,which usually limits the capacity of network generalization.Besides,most existing methods characterize positive and negative samples based on the nodes themselves,ignoring the influence of neighbors with different hop numbers on the node.In this study,a novel self-cumulative contrastive graph clustering(SC-CGC)method is devised,which is capable of dynamically adjusting the influence of neighbors with different hops.Our intuition is that better neighbors are closer and distant ones are further away in their feature space,thus we can perform neighbor contrasting without data augmentation.To be specific,SC-CGC relies on two neural networks,i.e.,autoencoder network(AE)and graph autoencoder network(GAE),to encode the node information and graph structure,respectively.To make these two networks interact and learn from each other,a dynamic fusion mechanism is devised to transfer the knowledge learned by AE to the corresponding GAE layer by layer.Then,a self-cumulative contrastive loss function is designed to characterize the structural information by dynamically accumulating the influence of the nodes with different hops.Finally,our approach simultaneously refines the representation learning and clustering assignments in a self-supervised manner.Extensive experiments on 8 realistic datasets demonstrate that SC-CGC consistently performs better over SOTA techniques.The code is available at https://github.com/Xiaoqiang-Yan/JAS-SCCGC.展开更多
To enhance the video quality after encoding and decoding in video compression,a video quality enhancement framework is pro-posed based on local and non-local priors in this paper.Low-level features are first extracted...To enhance the video quality after encoding and decoding in video compression,a video quality enhancement framework is pro-posed based on local and non-local priors in this paper.Low-level features are first extracted through a single convolution layer and then pro-cessed by several conv-tran blocks(CTB)to extract high-level features,which are ultimately transformed into a residual image.The final re-constructed video frame is obtained by performing an element-wise addition of the residual image and the original lossy video frame.Experi-ments show that the proposed Conv-Tran Network(CTN)model effectively recovers the quality loss caused by Versatile Video Coding(VVC)and further improves VVC's performance.展开更多
The aerostatic spindle is a key component of ultra-precision machine tools,and its error motion is crucial to machining accuracy and reliability.Spindle error motion is unavoidable,and its online monitoring and predic...The aerostatic spindle is a key component of ultra-precision machine tools,and its error motion is crucial to machining accuracy and reliability.Spindle error motion is unavoidable,and its online monitoring and prediction are quite important.Currently,there are relatively few studies on the online monitoring and prediction methods for the aerostatic spindle,and the level of intelligence is relatively low.To address this problem,an error motion monitoring system based on digital twin(DT)technology was established for the aerostatic spindle.A spindle error motion prediction method based on a mechanism and data fusion model(MDFM)was proposed.Additionally,a highly available and interactive aerostatic spindle DT service platform was developed.Experimental results have verified the good performance of this platform.The platform facilitates interaction between the physical and virtual entities of the aerostatic spindle,enabling three-dimensional visualization,monitoring,prediction,and simulation of spindle error motion,and shows good potential for engineering applications.展开更多
Knowledge acquisition Is the bottleneck of expert system. To solve this problem, KD （D＆K）, which is a comprehensive knowledge discovery process model coopersting both database and knowledge base, and related techno...Knowledge acquisition Is the bottleneck of expert system. To solve this problem, KD （D＆K）, which is a comprehensive knowledge discovery process model coopersting both database and knowledge base, and related technology are proposed. Then based on KD （D＆K） and related technology, the new construction of Expert System based on Knowledge Discovery （ESKD） Is proposed. As the key knowledge acqulsltlon component of ESKD, KD （D＆K） Is composed of KDD＊ and KDK＊. KDD＊- the new process model based on double bases cooperating mechanism; KDK＊- the new process model based on double-basis fusion mechanism are Introduced, respectively. The overall framework of ESKD Is proposed. Some sub-systems and dynamic knowledge base system are discussed. Flnelly, the effectiveness and advantages of ESKD are tested In a real-world agriculture database. We hope that ESKD may be useful for the new generation of expert systems.展开更多
基金financially supported by the National Key Project of the Scientific and Technical Support Program of China(No.2012BAC02B01)the National Hi-Tech R&D Program of China(No.2012AA063202)+2 种基金the National Natural Science Foundation of China(No.51472030)the Fundamental Research Funds for the Central Universities(Project No.FRF-TP-14-043A1)the China Postdoctoral Science Foundation Funded Project(No.2014M560885)
文摘Comprehensive CeMgA111O19： Tb3＋ （CTMA） disintegration via alkaline fusion was discussed. The rare earth （RE） elements in CTMA were dissolved by HC1 completely after alkaline fusion. Relationships between the alkaline fusion temperature and various properties of the compounds were examined by various techniques to elu- cidate their roles in the expected CTMA disintegration. X-ray diffraction （XRD） analysis indicates the phase transformation sequence. A scientific hypothesis of crystal structure disintegration presents that sodium ions substitute for the europium and barium ions in the mirror plane and magnesium ions in the spinel block successively, resulting in that more oxygen vacancies and interstitial sodium ions appear. The unit cell [P63/mmc （194）] breaks from the mirror plane. Then it is decomposed into NaA102, and magnesium, cerium, and terbium ions combine with free OH- into MgO, Tb2O3 and CeO2; Tb2O3 and CeO2 change into Ceo.6Tbo.O2-x. In the end, the rare earth oxide is recycled easily by the acidolysis. The mechanism provides fundamental basis for recycling of REEs from waste phosphors.
基金supported by the National Natural Science Foundation of China (No.61871350)the Zhejiang Science and Technology Plan Project (No.2019C011123)the Zhejiang Province Basic Public Welfare Research Project (No.LGG19F030011)。
文摘The current life-prediction models for lithium-ion batteries have several problems, such as the construction of complex feature structures, a high number of feature dimensions, and inaccurate prediction results. To overcome these problems, this paper proposes a deep-learning model combining an autoencoder network and a long short-term memory network. First, this model applies the characteristics of the autoencoder to reduce the dimensionality of the high-dimensional features extracted from the battery data set and realize the fusion of complex time-domain features, which overcomes the problems of redundant model information and low computational efficiency. This model then uses a long short-term memory network that is sensitive to time-series data to solve the long-path dependence problem in the prediction of battery life. Lastly, the attention mechanism is used to give greater weight to features that have a greater impact on the target value, which enhances the learning effect of the model on the long input sequence. To verify the efficacy of the proposed model, this paper uses NASA's lithium-ion battery cycle life data set.
基金supported by the National Key Research and Development Program of China (No.2022YFE0196000)the National Natural Science Foundation of China (No.61502429)。
文摘Target detection is an important task in computer vision research, and such an anomaly detection and the topic of small target detection task is more concerned. However, there are still some problems in this kind of researches, such as small target detection in complex environments is susceptible to background interference and poor detection results. To solve these issues, this study proposes a method which introduces the attention mechanism into the you only look once(YOLO) network. In addition, the amateur-produced mask dataset was created and experiments were conducted. The results showed that the detection effect of the proposed mothed is much better.
基金supported by the National Natural Science Foundation of China(62371423,62450002,62425107)China Postdoctoral Science Foundation(2020M682357).
文摘Contrastive graph clustering(CGC)has become a prominent method for self-supervised representation learning by contrasting augmented graph data pairs.However,the performance of CGC methods critically depends on the choice of data augmentation,which usually limits the capacity of network generalization.Besides,most existing methods characterize positive and negative samples based on the nodes themselves,ignoring the influence of neighbors with different hop numbers on the node.In this study,a novel self-cumulative contrastive graph clustering(SC-CGC)method is devised,which is capable of dynamically adjusting the influence of neighbors with different hops.Our intuition is that better neighbors are closer and distant ones are further away in their feature space,thus we can perform neighbor contrasting without data augmentation.To be specific,SC-CGC relies on two neural networks,i.e.,autoencoder network(AE)and graph autoencoder network(GAE),to encode the node information and graph structure,respectively.To make these two networks interact and learn from each other,a dynamic fusion mechanism is devised to transfer the knowledge learned by AE to the corresponding GAE layer by layer.Then,a self-cumulative contrastive loss function is designed to characterize the structural information by dynamically accumulating the influence of the nodes with different hops.Finally,our approach simultaneously refines the representation learning and clustering assignments in a self-supervised manner.Extensive experiments on 8 realistic datasets demonstrate that SC-CGC consistently performs better over SOTA techniques.The code is available at https://github.com/Xiaoqiang-Yan/JAS-SCCGC.
基金supported by the Key R&D Program of China under Grant No. 2022YFC3301800Sichuan Local Technological Development Program under Grant No. 24YRGZN0010ZTE Industry-University-Institute Cooperation Funds under Grant No. HC-CN-03-2019-12
文摘To enhance the video quality after encoding and decoding in video compression,a video quality enhancement framework is pro-posed based on local and non-local priors in this paper.Low-level features are first extracted through a single convolution layer and then pro-cessed by several conv-tran blocks(CTB)to extract high-level features,which are ultimately transformed into a residual image.The final re-constructed video frame is obtained by performing an element-wise addition of the residual image and the original lossy video frame.Experi-ments show that the proposed Conv-Tran Network(CTN)model effectively recovers the quality loss caused by Versatile Video Coding(VVC)and further improves VVC's performance.
基金supported by the National Natural Science Foundation of China(Grant No.52475494)the Zhejiang Provincial Natural Science Foundation of China(Grant No.LY22E050003)the Fundamental Research Funds for the Provincial Universities of Zhejiang(Grant No.RF-A2020005).
文摘The aerostatic spindle is a key component of ultra-precision machine tools,and its error motion is crucial to machining accuracy and reliability.Spindle error motion is unavoidable,and its online monitoring and prediction are quite important.Currently,there are relatively few studies on the online monitoring and prediction methods for the aerostatic spindle,and the level of intelligence is relatively low.To address this problem,an error motion monitoring system based on digital twin(DT)technology was established for the aerostatic spindle.A spindle error motion prediction method based on a mechanism and data fusion model(MDFM)was proposed.Additionally,a highly available and interactive aerostatic spindle DT service platform was developed.Experimental results have verified the good performance of this platform.The platform facilitates interaction between the physical and virtual entities of the aerostatic spindle,enabling three-dimensional visualization,monitoring,prediction,and simulation of spindle error motion,and shows good potential for engineering applications.
基金Supported by the National Natural Science Foundation of China (Grant No. 69835001)the Ministry of Education of China (Grant No. [2000] 175),the Science Foundation of Beijing (Grant No. 4022008).
文摘Knowledge acquisition Is the bottleneck of expert system. To solve this problem, KD （D＆K）, which is a comprehensive knowledge discovery process model coopersting both database and knowledge base, and related technology are proposed. Then based on KD （D＆K） and related technology, the new construction of Expert System based on Knowledge Discovery （ESKD） Is proposed. As the key knowledge acqulsltlon component of ESKD, KD （D＆K） Is composed of KDD＊ and KDK＊. KDD＊- the new process model based on double bases cooperating mechanism; KDK＊- the new process model based on double-basis fusion mechanism are Introduced, respectively. The overall framework of ESKD Is proposed. Some sub-systems and dynamic knowledge base system are discussed. Flnelly, the effectiveness and advantages of ESKD are tested In a real-world agriculture database. We hope that ESKD may be useful for the new generation of expert systems.
