The anode effect is a common failure in the aluminium electrolysis industry.If the anode effect cannot be accurately predicted,it will cause increased energy consumption,harmful gas generation and even equipment damag...The anode effect is a common failure in the aluminium electrolysis industry.If the anode effect cannot be accurately predicted,it will cause increased energy consumption,harmful gas generation and even equipment damage in the aluminium electrolysis.In this paper,an anode effect prediction framework using multi-model merging based on deep learning technology is proposed.Different models are used to process aluminium electrolysis cell condition parameters with high dimensions and different characteristics,and hidden key fault information is deeply mined.A stacked denoising autoencoder is utilized to denoise and extract features from a large number of longperiod parameter data.A long short-term memory network is implemented to identify the intrinsic links between the realtime voltage and current time series and the anode effect.By setting the model time step,the anode effect can be predicted precisely in advance,and the proposed method has good robustness and generalization.Moreover,the traditional Adam algorithm is improved,which enhances the performance and convergence speed of the model.The experimental results show that the classification accuracy and F1score of the model are 97.14% and 0.9579%,respectively.The prediction time can reach 15 min.展开更多
This paper discusses the general characteristics of anode effect in aluminium electrolysis and pre- vious theories about the mechanism of anode effect. On the basis of laboratory experiments,the author suggests a new ...This paper discusses the general characteristics of anode effect in aluminium electrolysis and pre- vious theories about the mechanism of anode effect. On the basis of laboratory experiments,the author suggests a new contribution to the primary and di- rect reason for anode effect.展开更多
A model of butterfly catastrophe is confirmed based on the matching and fitting the previous experimental data from alumina electrolysis when anode effect occurs.The complicated behaviour of the cryolite-alumina melt ...A model of butterfly catastrophe is confirmed based on the matching and fitting the previous experimental data from alumina electrolysis when anode effect occurs.The complicated behaviour of the cryolite-alumina melt system with varying parameters could be generally described by this model.Therefore,the anode effect and its occurrence may be thoroughly understood.展开更多
A series of Si/C composites were fabricated based on pitch and Si powders with particle sizes of 30, 100, 500, and 3000 nm. The size effects of the Si particles in the Si/C composites were investigated for lithium-ion...A series of Si/C composites were fabricated based on pitch and Si powders with particle sizes of 30, 100, 500, and 3000 nm. The size effects of the Si particles in the Si/C composites were investigated for lithium-ion battery anodes. The nanoscale Si and Si/C composites exhibited good capacity retentions. Scanning electron microscopy showed that exterior and interior cracks emerging owing to volume expansion as well as parasitic reactions with the electrolyte could well explain the performance failure.展开更多
A method to investigate the effect of gas bubble on cell voltage oscillations was established. The whole aluminum electrolysis cell was treated as a resistance circuit, and the dynamic simulation of the cell equivalen...A method to investigate the effect of gas bubble on cell voltage oscillations was established. The whole aluminum electrolysis cell was treated as a resistance circuit, and the dynamic simulation of the cell equivalent circuit was modeled with Matlab/Simulink simulation software. The time-series signals of cell voltage and anode current were obtained under different bubble conditions, and analyzed by spectral and statistical analysis methods. The simulation results show that higher bubble release frequency has a significant effect on the cell voltage oscillations. When the bubble coverage of one anode block exceeds 80%, the cell voltage may exceed its normal fluctuation amplitude. The simulation also proves that the anode effect detected by computer in actual production is mainly the whole cell anode effect.展开更多
The anode processes of carbon electrode in LiF-70%NdF3 melt were studied by electroanalytical techniques, including cyclic voltammetry(CV) and chronoamperometry(CA). Anode gases were analyzed by gas chromatography(GC)...The anode processes of carbon electrode in LiF-70%NdF3 melt were studied by electroanalytical techniques, including cyclic voltammetry(CV) and chronoamperometry(CA). Anode gases were analyzed by gas chromatography(GC) on-line during controlled-potential electrolysis. Two anode peaks were observed. The first process starting at 2.0 V vs Li+/Li was corresponded to the discharge of residual oxide ions, with the generation of CO and CO2. The discharge of fluoride ions occurred at the potentials higher than 4.3 V vs Li+/Li, with the generation of a small amount of CF4 and C2F6, accompanied by a sudden drop in current, marking the onset of the anode effect. The second process occurred when the potential exceeded 5.5 V vs Li+/Li, with the generation of a large amount of CF4 and C2F6. When the temperature was changed from 1173 to 1273 K, the current of the second process decreased, leading to a stable anode effect.展开更多
基金financially supported by the General Program of National Natural Science Foundation of China(No.62373069)the Major Projects for Technological Transformation(No.H20201555)Chongqing Talent Innovation and Entrepreneurship Demonstration Team Project (No.CQYC202203091061)。
文摘The anode effect is a common failure in the aluminium electrolysis industry.If the anode effect cannot be accurately predicted,it will cause increased energy consumption,harmful gas generation and even equipment damage in the aluminium electrolysis.In this paper,an anode effect prediction framework using multi-model merging based on deep learning technology is proposed.Different models are used to process aluminium electrolysis cell condition parameters with high dimensions and different characteristics,and hidden key fault information is deeply mined.A stacked denoising autoencoder is utilized to denoise and extract features from a large number of longperiod parameter data.A long short-term memory network is implemented to identify the intrinsic links between the realtime voltage and current time series and the anode effect.By setting the model time step,the anode effect can be predicted precisely in advance,and the proposed method has good robustness and generalization.Moreover,the traditional Adam algorithm is improved,which enhances the performance and convergence speed of the model.The experimental results show that the classification accuracy and F1score of the model are 97.14% and 0.9579%,respectively.The prediction time can reach 15 min.
文摘This paper discusses the general characteristics of anode effect in aluminium electrolysis and pre- vious theories about the mechanism of anode effect. On the basis of laboratory experiments,the author suggests a new contribution to the primary and di- rect reason for anode effect.
文摘A model of butterfly catastrophe is confirmed based on the matching and fitting the previous experimental data from alumina electrolysis when anode effect occurs.The complicated behaviour of the cryolite-alumina melt system with varying parameters could be generally described by this model.Therefore,the anode effect and its occurrence may be thoroughly understood.
基金Project supported from the“Strategic Priority Research Program”of the Chinese Academy of Sciences(Grant No.XDA09010102)
文摘A series of Si/C composites were fabricated based on pitch and Si powders with particle sizes of 30, 100, 500, and 3000 nm. The size effects of the Si particles in the Si/C composites were investigated for lithium-ion battery anodes. The nanoscale Si and Si/C composites exhibited good capacity retentions. Scanning electron microscopy showed that exterior and interior cracks emerging owing to volume expansion as well as parasitic reactions with the electrolyte could well explain the performance failure.
基金Project(2012BAE08B09)supported by the National Key Technology R&D Program of China
文摘A method to investigate the effect of gas bubble on cell voltage oscillations was established. The whole aluminum electrolysis cell was treated as a resistance circuit, and the dynamic simulation of the cell equivalent circuit was modeled with Matlab/Simulink simulation software. The time-series signals of cell voltage and anode current were obtained under different bubble conditions, and analyzed by spectral and statistical analysis methods. The simulation results show that higher bubble release frequency has a significant effect on the cell voltage oscillations. When the bubble coverage of one anode block exceeds 80%, the cell voltage may exceed its normal fluctuation amplitude. The simulation also proves that the anode effect detected by computer in actual production is mainly the whole cell anode effect.
基金the National 973 Program (2007CB613301)the National Natural Science Foundation of China(50574012)
文摘The anode processes of carbon electrode in LiF-70%NdF3 melt were studied by electroanalytical techniques, including cyclic voltammetry(CV) and chronoamperometry(CA). Anode gases were analyzed by gas chromatography(GC) on-line during controlled-potential electrolysis. Two anode peaks were observed. The first process starting at 2.0 V vs Li+/Li was corresponded to the discharge of residual oxide ions, with the generation of CO and CO2. The discharge of fluoride ions occurred at the potentials higher than 4.3 V vs Li+/Li, with the generation of a small amount of CF4 and C2F6, accompanied by a sudden drop in current, marking the onset of the anode effect. The second process occurred when the potential exceeded 5.5 V vs Li+/Li, with the generation of a large amount of CF4 and C2F6. When the temperature was changed from 1173 to 1273 K, the current of the second process decreased, leading to a stable anode effect.
