Статья. Опубликована в Systems Engineering. — 2006. — T.9 . — №1 . — С. 45-61.
The design of technical systems such as automobiles and spacecraft has traditionally focused exclusively on performance maximization. Many organizations now realize that such an approach must be balanced against competing objectives of cost, risk, and other criteria. If one is willing to give up some amount of performance relative to the best achievable performance level, one introduces slack into system design. This slack can be invested in creating better outcomes overall. One way to achieve this is to balance the requirements among contributing subsystems such that the number of active constraints is minimized, while still achieving the desired system performance. This paper introduces a methodology called isoperformance as a means of identifying and evaluating a performance-invariant set of design solutions, which are efficient in terms of other criteria such as cost, risk, and lifecycle properties. Isoperformance is an inverse design method that starts from a desired vector of performance requirements and works backwards to identify acceptable solutions in the design space. To achieve this, gradient-based contour following is implemented as a multivariable search algorithm that manipulates the null set of the Jacobian matrix. Use of the method is illustrated with two examples from spacecraft design and human performance in sports.
