Link Prediction Based on the Relational Path Inference of Triangular Structures

Link prediction is used to complete the knowledge graph.Convolu-tional neural network models are commonly used for link prediction tasks,but they only consider the direct relations between entity pairs,ignoring the semantic information contained in the relation paths.In addition,the embedding dimension of the relation is generally larger than that of the entity in the ConvR model,which blocks the progress of downstream tasks.If we reduce the embedding dimension of the relation,the performance will be greatly degraded.This paper proposes a convolutional model PITri-R-ConvR based on triangular structure relational infer-ence.The model uses relational path inference to capture semantic information,while using a triangular structure to ensure the reliability and computational effi-ciency of relational inference.In addition,the decoder R-ConvR improves the initial embedding of the ConvR model,which solves the problems of the ConvR model and significantly improves the prediction performance.Finally,this paper conducts sufficient experiments in multiple datasets to verify the superiority of the model and the rationality of each module.

Some kinds of falling fuzzy filters of lattice implication algebras

In this paper, the concepts of falling fuzzy(implicative, associative) filters of lattice implication algebras based on the theory of falling shadows and fuzzy sets are presented at first. And then the relations between fuzzy(implicative, associative) filters and falling fuzzy(implicative, associative) filters are provided. In particular, we put forward an open question on a kind of falling fuzzy filters of lattice implication algebras. Finally, we apply falling fuzzy inference relations to lattice implication algebras and obtain some related results.

Hybrid fuzzy-grey-Taguchi based multi weld quality optimization of Al/Cu dissimilar friction stir welded joints

Nowadays aluminum alloys substitute copper in various applications for weight reduction and cost savings. This paper presents fuzzy-grey Taguchi technique for optimization of friction stir welding condition with seven weld quality attributes of dissimilar A1/Cu joints with the minimum number of experiments for effective productivity and product quality. Taguchi＇s L16 orthogonal array was used to conduct the experiments. Fuzzy inference system was adapted to convert the multi quality characteristics into an equivalent single quality parameter which was opti- mized by Taguchi approach. Four parameters namely, rotational speed of the tool, welding speed, plunging depth and tool pin offset were varied in four levels for investi- gating the effects on the process output like tensile strength, compressive strength, percentage of elongation, bending angle, weld bead thickness and average hardness at the nugget zone. The hardness profile is consistent with the variation of the structure within the nugget zone （NZ）. Confirmation experiment was conducted using predicted optimum parameter setting and it showed that the proposed approach could efficiently optimize weld quality parame- ters. The microstructural analyses were also performed for all the zones of the joints at both Al and Cu sides. It revealed the finer grain size at the NZ compared to the base material due to dynamic recrystallization.