Combining Deep Learning with Knowledge Graph for Design Knowledge Acquisition in Conceptual Product Design

The acquisition of valuable design knowledge from massive fragmentary data is challenging for designers in conceptual product design.This study proposes a novel method for acquiring design knowledge by combining deep learning with knowledge graph.Specifically,the design knowledge acquisition method utilises the knowledge extraction model to extract design-related entities and relations from fragmentary data,and further constructs the knowledge graph to support design knowledge acquisition for conceptual product design.Moreover,the knowledge extraction model introduces ALBERT to solve memory limitation and communication overhead in the entity extraction module,and uses multi-granularity information to overcome segmentation errors and polysemy ambiguity in the relation extraction module.Experimental comparison verified the effectiveness and accuracy of the proposed knowledge extraction model.The case study demonstrated the feasibility of the knowledge graph construction with real fragmentary porcelain data and showed the capability to provide designers with interconnected and visualised design knowledge.

CFD-Based Evaluation of Flowand Temperature Characteristics of Airflow in an Aircraft Cockpit

The rational design of airflow distribution is of great importance for comfort and energy conservation.Several numerical investigations of flow and temperature characteristics in cockpits have been performed to study the distinct airflow distribution.This study developed the coupled heat transfer model of radiation,convection,and heat conduction for the cockpit flight environment.A three-dimensional physical model was created and a shear stress transfer(SST)k-w turbulence model was well verified with a high prediction accuracy of 91%for the experimental data.The strong inhomogeneous flow and temperature distribution were captured for various initial operating conditions(inlet temperature,inlet pressure,and gravitational acceleration).The results indicated that the common feature of the flow field was stable in the middle part of the cockpit,while the temperature field showed a large temperature gradient near the cockpit’s top region.It was also found that there was remarkable consistency in the distributed features,regardless of the applied initial operating conditions.Additionally,the mass flux and the top heat source greatly affected the flow and temperature characteristics.This study suggests that an optimized operating condition does exist and that this condition makes the flow and temperature field more stable in the cockpit.The corresponding results can provide necessary theoretical guidance for the further design of the cockpit structure.