Search

Various creative multi-response optimisation approaches have been developed in the literature. Most of these researches are based on the normality assumption of the response distribution. However, this assumption does not necessarily hold in some real cases, such as non-normal multiple responses. Also, the reproducibility of optimisation results does not hold in some practical applications due to the variability of predicted responses associated with model uncertainty. In this paper, a novel approach is proposed to address the issues for non-normal multi-response optimisation. The proposed method not only identifies significant effects for each response by incorporating factorial effect principles into the framework of the Bayesian generalised linear models (GLMs) but also takes into account the model uncertainty and the variability of predicted responses by using the Bayesian sampling technique and Pareto optimal strategy. Furthermore, the optimal parameter settings are found by using grey incidence analysis (GIA). Besides, two examples are used to illustrate the effectiveness of the proposed method. The results show that the proposed method not only effectively identify significant factors but also find more satisfactory parameter settings when the reliability and reproducibility of optimisation results are considered simultaneously. [ABSTRACT FROM AUTHOR]

Effective process monitoring and fault diagnosis are of great significance to the safe operation of industrial processes as production scale increases and production systems become more and more complex. Identifying fault types in complex industries by fault classification can help workers to determine the source of the fault as soon as possible, which is crucial to timely recover work. In this paper, a fault classification method based on a variable‐weighted dynamic sparse stacked autoencoder is proposed. First, considering the dynamic characteristics of process data, the input data are processed dynamically by a sliding window. Then, in the pre‐training stage, the weight of each variable is calculated by Fisher discriminant analysis for the reconstruction of the loss function. The sparse term is added to the loss function so that it can learn the effective representation of data in a harsh environment. Finally, the proposed method is applied to the Tennessee‐Eastman benchmark to evaluate the classification performance. The result shows the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

The separation of graphites and cathode materials from spent lithium-ion batteries (LIBs) is essential to close the loop of material used in LIBs. In this study, the roasting characteristics of the spent LIB materials are carefully analyzed, and the effects of roasting on the surface morphology and elemental chemical states of electrode materials are fully investigated by thermogravimetric analysis, SEM-EDS, and XPS to explore the roasting–flotation enhancement mechanism. Then, froth flotation is utilized to separate the graphites and cathode materials from the spent LIB materials. The optimal roasting temperature is determined by thermogravimetric analysis and the SEM-EDS analysis of the spent LIB materials. The results suggest that the organic binder can be effectively removed from the spent LIB materials at the roasting temperature of 500 °C, and there is almost no loss of graphite. The XPS results indicate that, in the process of roasting, the decomposition products of the organic binder can easily react with valuable metals (Ni, Co, and Mn) to produce corresponding metal fluoride. The flotation results of the spent LIB materials after roasting at the optimal conditions indicate that graphites and cathode materials can be efficiently recovered through roasting–froth flotation. When the dosage of kerosene is 200 g/t and the dosage of methyl isobutyl carbinol (MIBC) is 150 g/t, the cathode materials grade is 91.6% with a recovery of 92.6%, while the graphite grade is 84.6% with a recovery of 82.7%. The roasting–froth flotation method lays the foundation for the subsequent metallurgical process. [ABSTRACT FROM AUTHOR]

The application of lithium-ion batteries (LIBs) in electric vehicles has attracted wide attention in recent years, especially LiFePO 4 batteries that have been extensively used in large electric buses and cars. The increased demand for LIBs has greatly stimulated lithium-ion battery production, which subsequently has led to greatly increased quantities of spent LIBs. From the perspective of environmental protection and resource recovery, the recycling of spent LIBs is of great significance. In this study, the roasting flotation technology was applied to enrich valuable metals from the mixed electrode powder of spent LiFePO 4 batteries. Roasting could thoroughly remove the organic outer layer coated on the surface of electrode-active materials, which improved the flotation enrichment efficiency of valuable metals in the mixed electrode powder of spent LiFePO 4 batteries. Under the optimum conditions of roasting at 500 °C for 1 h, the enrichment efficiency of Li and Fe reached the best. The recovery and the enrichment ratio of Li were 95.87% and 1.37, respectively, while the recovery and the enrichment ratio of Fe were 95.25% and 1.36, respectively. Roasting flotation was an efficient process to enrich valuable metals from spent LiFePO 4 batteries without wasting graphite resources., Competing Interests: The authors declare no competing financial interest., (© 2022 The Authors. Published by American Chemical Society.)