Purpose The purpose of this paper is to find a method for key assembly structure identification in complex mechanical assembly. Three-dimensional model reuse plays an increasingly important role in complex product design and innovative design. Assembly model has become important resource of models reuse in enterprises, which contains certain function assembly structures. These assembly structures implicating plenty of design intent and design experience knowledge can be used to support function-structure design, modular design reuse and semantics analysis for complex product. Design/methodology/approach A method for identifying key assembly structures in assembly model is presented from the viewpoint of assembly topology and multi-source attributes. First, assembly model is represented based on complex network. Then, a two-level evaluation model is put forward to evaluate importance of parts assembled, and the key function parts in assembly can be obtained. After that, on the basis of the function parts, a heuristic algorithm upon breadth first searching is given to identify key assembly structures. Findings The method could be used to evaluate key function parts and identify key assembly structures in complex mechanical assembly according to the specific circumstances. Practical implications The method can not only help designers find the key assembly structure in complex mechanical assembly model, facilitate the function-structure designing and semantics analyzing, and thereby improve the efficiency of product knowledge reuse, but also assist in analyzing influence scope of key function part changing and optimization of the assembly process for complex mechanical assembly. Originality/value The paper is the first to propose a method for key assembly structure identification in complex mechanical assembly, where the key function parts can be evaluated through a two-level evaluation model, and the key assembly structures are identified automatically based on complex network.

No abstract

To solve the problem of difficulty in mechanical CAD assembly model retrieval and low level of the model reuse, provide effective support for module reuse in assembly model, a novel module partition method for mechanical CAD assembly model is proposed. Firstly, the correlation strength between assembled parts is analyzed and evaluated based on multi-source correlation information including assembly structure, function and flows. Then, the weighted network is constructed for expressing correlation relationships between assembled parts in the assembly model. After that, a community detection algorithm upon greedy thought is given to discover communities in weighted network, thereby realizing the modularization of mechanical CAD assembly model. Finally, two CAD assembly models are employed to verify feasibility and effectiveness of the proposed method.

PurposeThree-dimensional computer-aided design (CAD) assembly model has become important resource for design reuse in enterprises, which implicates plenty of design intent, assembly intent, design experience knowledge and functional structures. To acquire quickly CAD assembly models associated with specific functions by using product function requirement information in the product conceptual design phase for model reuse, this paper aims to find an approach for structure-function correlations analysis and functional semantic annotation of mechanical CAD assembly model before functional semantic-based assembly retrieval.Design/methodology/approachAn approach for structure-function correlations analysis and functional semantic annotation of CAD assembly model is proposed. First, the product knowledge model is constructed based on ontology including design knowledge and function knowledge. Then, CAD assembly model is represented by part attributed adjacency graph and partitioned into multiple functional regions. Assembly region and flow-activity region are defined for structure-function correlations analysis of CAD assembly model. Meanwhile, the extraction process of assembly region and flow-activity region is given in detail. Furthermore, structure-function correlations analysis and functional semantic annotation are achieved by considering comprehensively assembly structure and assembled part shape structure in CAD assembly model. After that, a structure-function relation model is established based on polychromatic sets for expressing explicitly and formally relationships between functional structures, assembled parts and functional semantics.FindingsThe correlation between structure and function is analyzed effectively, and functional semantics corresponding to structures in CAD assembly model are labeled. Additionally, the relationships between functional structures, assembled parts and functional semantics can be described explicitly and formally.Practical implicationsThe approach can be used to help designers accomplish functional semantic annotation of CAD assembly models in model repository, which provides support for functional semantic-based CAD assembly retrieval in the product conceptual design phase. These assembly models can be reused for product structure design and assembly process design.Originality/valueThe paper proposes a novel approach for structure-function correlations analysis and functional semantic annotation of mechanical CAD assembly model. Functional structures in assembly model are extracted and analyzed from the point of view of assembly structure and function part structure. Furthermore, the correlation relation between structures, assembled parts and functional semantics is expressed explicitly and formally based on polychromatic sets.

At present, the uncertainty and randomness between equipment are not fully considered in the remaining useful life (RUL) prediction. In order to solve this problem, firstly, we use the Weibull distribution to describe the influence of various uncertain factors on the RUL of equipment, and introduce the Weibull Time-To-Event Recurrent Neural Network (WTTE-RNN) framework to transform the RUL of equipment from the prediction of single life value to the prediction of Weibull distribution parameters. Then, in view of the problem that RNN is prone to have low prediction accuracy due to the vanishing of gradient, considering the advantages of Long-Short Term memory (LSTM) in time series modeling, we replace RNN with LSTM to improve the model and construct WTTE-LSTM model. Furthermore, in order to further improve the model's ability to extract data features, Convolutional Neural Network (CNN) is added after the original data is normalized because of its excellent feature extraction ability, and the time series features extracted by CNN are used as the input of LSTM to construct the WTTE-CNN-LSTM model. Finally, the LSTM life prediction model, WTTE-LSTM model and WTTE-CNN-LSTM model are established by taking a data set from a core component of construction machinery as an example. The results demonstrate that the improved WTTE-CNN-LSTM model has the highest prediction accuracy and the smallest error.