Search

Improving the reactant mass transfer on the catalyst surface is a feasible approach to fabricate a robust solid catalyst for efficiently promoting the biomass macromolecules-involving reactions, specifically for biodiesel production by using non-edible acidic oils as feedstocks. In this premise, to reduce the mass transfer resistance, the hierarchical porous SOM-ZIF-8 was firstly synthesized using polystyrene spheres (PS) as templates and then employed as catalyst supports for loading of Keplerate-type polyoxomolybdates {Mo 132 } to prepare a novel {Mo 132 }@SOM-ZIF-8 solid acid catalyst. The catalyst characterization results revealed that the active species of {Mo 132 } clusters were well-dispersed on the SOM-ZIF-8 support and the primary framework of the SOM-ZIF-8 support remained nearly unaltered after the preparation processes. This prepared catalyst featured three-dimensional ordered hierarchical porous structure and dual Bronsted-Lewis acid sites, with a large surface area of 736.26 m2/g and high acidity of 903 μmol/g, presenting high activities for concurrent triglyceride transesterification and free fatty acids (FFAs) esterification. With the acidic soybean oils as feedstocks, 93.9 % of oil conversion and full FFA conversion to biodiesel were achieved over this solid catalyst at 130 °C for 8 h with a catalyst loading of 2 wt%, thus imparting the great potential for a one-pot efficient biodiesel manufacture from the acidic oils to comply with the demand of green and clean production. The synergy between the hierarchical porous structure and the strong acidity emerged, thus boosting the catalytic performance of this solid catalyst for the heterogeneous biodiesel production. The good FFA and moisture-resistance capacity was shown for this catalyst even in the case of moisture content of 3 % and FFA content of 25 %. Further, this catalyst showed excellent reusability without significantly losing its catalytic performance even after five runs, providing a deeper insight into constructing efficient solid catalysts with hierarchical porous structure that are utilized for cost-effective production of biodiesel from the non-edible acidic oils. [Display omitted] [ABSTRACT FROM AUTHOR]

It is an important but challenging work to develop novel fault diagnosis (FD) methods of offshore wind turbines (WTs) for their maintenance cost that accounts for 20%–35% of the total lifecycle cost. In FD of offshore WTs, there are two common problems: lack of high-quality label data and ignoring fault severity. In this study, we apply the prototypical networks in few-short learning to cope with a small high-quality label data, and adopt the ordinal regression method to consider fault severity. To sum up, we develop a novel ordinal classification prototypical networks (OCPN) model by introducing ordinal regression into prototypical networks, which is suitable for the FD of offshore WTs. The real case data gathered by an enterprise engaging in equipment condition monitoring and fault diagnosis in China is used to verify OCPN's effectiveness. The experimental results show that the OCPN model outperforms several competing models in terms of better multi-classification performance. In practical engineering applications, the OCPN model is flexible for diagnostic experts to consider the priority of fault levels by introducing decision preference into the loss function. • The OCPN model is proposed by introducing ordinal regression into prototypical networks. • The OCPN model is suitable for the fault diagnosis of offshore wind turbines. • Its effectiveness is illustrated with our real case data of offshore wind turbines. • It outperforms several competing models in multi-classification fault diagnosis. • It is flexible for diagnostic experts to consider the priority of fault levels. [ABSTRACT FROM AUTHOR]

In fault diagnosis, deep learning plays an important role, but still lacks good interpretability. To address this issue, we develop a novel fault frequency priors fusion deep learning (FFP-DL) framework by introducing fault frequency priors into deep learning. The FFP-DL framework contains two branches: fault frequency priors learning branch (FFPLB) and self-learning branch (SLB). We then propose a pre-training algorithm which can shorten the overall training time especially for training multiple models simultaneously. To illustrate its efficacy, we take convolutional neural network (CNN) as the specific deep learning model in the FFP-DL framework (FFP-CNN), and apply the FFP-CNN model to a private offshore wind turbines (OWTs) data. The experimental results show that the FFP fusion does help improve the performance of fault diagnosis in terms of accuracy and Marco-F1-score and provide good interpretability to the diagnosis results with the distinguished feature of predicted FFP. With the training data reduction, the performance of the FFP-CNN model does not deteriorate quickly, which implies that this framework is also suitable for less data. In addition, the result reveals the fact that the pre-training algorithm does reduce convergence epochs, which will help the FFP-CNN model train faster during the training process. • The FFP-DL framework is proposed by adding fault frequency priors to deep learning. • It is a flexible framework by considering different deep learning structures. • It contains two branches for both frequency priors learning and self-learning. • Its efficacy has been demonstrated on the fault diagnosis of offshore WTs. • The empirical results show that the FFP fusion does make sense in fault diagnosis. [ABSTRACT FROM AUTHOR]