298
Engineering Systems Integration
A simple, yet instructive, portrayal of a loss function is to view the seller
as having a decreasing value function as performance increases and the
buyer in the opposite position of having a decreasing value function as the
performance decreases (Langford 2009). This can be represented as
L(y) = k 0 + k
2
1 y + k 1 m , where L(y) is the combined loss of the buyer and seller,
and k 0 is a constant equal to −2k 1 m.
Between any two contra-posed positions (whether weakly or strongly
held), the loss function indicates the minimum loss that can result from the
positions (assuming that both sides are willing to not gain any advantage
over the other). In essence, a loss function is useful in determining the
amount of EMMI that is used (i.e., lost) to achieve various levels of performance for individual or aggregated functions. For integration, the functionality of a system can be measured by both the performances of the
functions and the losses that are attributable to achieving those performance. There is a direct correlation between a loss in EMMI and “utility,”
where utility is a measure of relative satisfaction (e.g., in economics or systems engineering). By applying the loss function to the management processes, the workforce can be monitored in real time, the projection of
predicted work can be evaluated against current status, and metrics can be
established to analyze the impacts of applying resources (e.g., engineering
labor) to particular problem areas. By applying the loss function to the integration activities, the various functions can be evaluated by both their
demonstrations of performances as well as their losses in achieving those
performances. This determination of functional effectiveness helps to
define and design tests, revise integration sequencing, and outline validation schemes to facilitate better determination of the usefulness of a product or service.
Types of Quality Loss Functions
For each quality characteristic, NTB, STB, and LTB, there exists some function that uniquely defines the relationship between economic loss and the
deviation of the quality characteristic from its target value. Taguchi has demonstrated through practice the quadratic representation of the quality loss
function to be an efficient and effective way to assess the loss due to deviation of a quality characteristic from its target value. For a product with a
target value m, from a customers’ perspective, m ± ∆ 0 represents the deviation at which functional failure of the product’s or service’s component
occurs. When a product is manufactured or a service is provided with its
quality characteristic at the extremes, m + Δ 0 or m − Δ 0 , some measure to
counter the loss must be undertaken by the customer.
Following the simplified loss function L(y) (average loss) with the characteristic of NTB is the combined buyer–seller dynamics that can be described
as follows:
Engineering Systems Integration
A simple, yet instructive, portrayal of a loss function is to view the seller
as having a decreasing value function as performance increases and the
buyer in the opposite position of having a decreasing value function as the
performance decreases (Langford 2009). This can be represented as
L(y) = k 0 + k
2
1 y + k 1 m , where L(y) is the combined loss of the buyer and seller,
and k 0 is a constant equal to −2k 1 m.
Between any two contra-posed positions (whether weakly or strongly
held), the loss function indicates the minimum loss that can result from the
positions (assuming that both sides are willing to not gain any advantage
over the other). In essence, a loss function is useful in determining the
amount of EMMI that is used (i.e., lost) to achieve various levels of performance for individual or aggregated functions. For integration, the functionality of a system can be measured by both the performances of the
functions and the losses that are attributable to achieving those performance. There is a direct correlation between a loss in EMMI and “utility,”
where utility is a measure of relative satisfaction (e.g., in economics or systems engineering). By applying the loss function to the management processes, the workforce can be monitored in real time, the projection of
predicted work can be evaluated against current status, and metrics can be
established to analyze the impacts of applying resources (e.g., engineering
labor) to particular problem areas. By applying the loss function to the integration activities, the various functions can be evaluated by both their
demonstrations of performances as well as their losses in achieving those
performances. This determination of functional effectiveness helps to
define and design tests, revise integration sequencing, and outline validation schemes to facilitate better determination of the usefulness of a product or service.
Types of Quality Loss Functions
For each quality characteristic, NTB, STB, and LTB, there exists some function that uniquely defines the relationship between economic loss and the
deviation of the quality characteristic from its target value. Taguchi has demonstrated through practice the quadratic representation of the quality loss
function to be an efficient and effective way to assess the loss due to deviation of a quality characteristic from its target value. For a product with a
target value m, from a customers’ perspective, m ± ∆ 0 represents the deviation at which functional failure of the product’s or service’s component
occurs. When a product is manufactured or a service is provided with its
quality characteristic at the extremes, m + Δ 0 or m − Δ 0 , some measure to
counter the loss must be undertaken by the customer.
Following the simplified loss function L(y) (average loss) with the characteristic of NTB is the combined buyer–seller dynamics that can be described
as follows: