Multi-aspect component models: enabling the reuse of engineering analysis models in SysML
Jobe, Jonathan Michael
MetadataShow full item record
Today s market is driven by the desire for increasingly complex products that perform well from manufacturing to disposal. Designing these products for multiple lifecycle phases requires effective management of engineering knowledge and integration of this knowledge across multiple disciplines. By managing this knowledge, products can be realized faster, perform better and be more complex. However, management techniques are often very costly and managers can easily become bogged down with large quantities of information, slowing the design process and degrading knowledge transfer. Thus, a need exists for effective yet inexpensive knowledge management. One approach for decreasing the costs associated with generating design knowledge is to reuse modules of existing knowledge. In Model-Based Systems Engineering (MBSE), information about a design is stored formally in many knowledge structures, or models, including requirements, stakeholders, and analyses. To support the reuse of the existing knowledge in design, MBSE is used as a basis for integrating engineering analysis models. In this thesis, a framework is presented for model classification that organizes models by components and aspects. This scheme is found to be useful in classifying engineering analysis models for reuse by storing them as a set in containers known as Multi-Aspect Component Models (MAsCoMs). Each model in a MAsCoM is related to the formal structure model of a physical component, and to the many aspects of the component that the model represents. The Systems Modeling Language, OMG SysML, is used to implement MAsCoMs and support MBSE. Validation of the MAsCoM concept is performed with fluid-power design examples, including a log splitter, scissor lift, and hydraulic excavator. In these examples, MAsCoMs improve design value by 1) Classifying modular and composable engineering analysis models for reuse in multiple disciplines, and 2) Providing knowledge modules to computer-automated algorithms for the future automated composition of component models into system models to perform system-level analyses.