The common design of serial civil aircraft, an important strategy of modern civil aircraft research and develop-ment, minimizes the whole life cycle cost of civil aircraft through asset reuse and resource sharing. How...The common design of serial civil aircraft, an important strategy of modern civil aircraft research and develop-ment, minimizes the whole life cycle cost of civil aircraft through asset reuse and resource sharing. However, the existing estimating model for the R&D cost of civil aircraft ignores the effects of common design, so the value estimated by estimating derivative models is significantly inconsistent with the actual one. To solve this problem, a novel assessment method for civil aircraft commonality indicators is developed based on fuzzy set in the present study, exploiting the attributes and structural parameters of the aircraft to be assessed as input to determine the degree of membership that pertains to the commonality sub-interval as the commonality indicator.Then the BP(Back Propagation) neural network algorithm is adopted to establish the relationship between the common index and the decrease rate of the R&D cost of derivative models. The model employs over a dozen typical civil aircraft models(e.g., Boeing, Airbus, and Bombardier) as the sample data for network learning training to build a mature neural network model for estimating the R&D cost of novel derivative models. As revealed from the comparative analysis on the calculated results of the samples, the estimated results of the model given the effects of commonality in the present study exhibit higher estimation accuracy and value for future work.展开更多
文摘The common design of serial civil aircraft, an important strategy of modern civil aircraft research and develop-ment, minimizes the whole life cycle cost of civil aircraft through asset reuse and resource sharing. However, the existing estimating model for the R&D cost of civil aircraft ignores the effects of common design, so the value estimated by estimating derivative models is significantly inconsistent with the actual one. To solve this problem, a novel assessment method for civil aircraft commonality indicators is developed based on fuzzy set in the present study, exploiting the attributes and structural parameters of the aircraft to be assessed as input to determine the degree of membership that pertains to the commonality sub-interval as the commonality indicator.Then the BP(Back Propagation) neural network algorithm is adopted to establish the relationship between the common index and the decrease rate of the R&D cost of derivative models. The model employs over a dozen typical civil aircraft models(e.g., Boeing, Airbus, and Bombardier) as the sample data for network learning training to build a mature neural network model for estimating the R&D cost of novel derivative models. As revealed from the comparative analysis on the calculated results of the samples, the estimated results of the model given the effects of commonality in the present study exhibit higher estimation accuracy and value for future work.
