What is QFD (Quality Function Deployment)?
Quality function deployment (QFD) is a method developed in Japan beginning in 1966 to help transform the voice of the customer into engineering characteristics for a product. (quality is a measure of customer satisfaction with a product or a service)
What are the 6 related matrices in the house of quality used in QFD?
- Customer attributes
- Engineering characteristics
- Technical matrix
- Technical correlations
- Planning matrix
What is in the customer attributes matrix
Structure list of consumer wants and needs, determined by market research , along with a priority quantitative value.
What’s in the Engineering characteristics matrix?
Matrix of how the wants may be achieved, in general/not solution specific terms, representing the voice of the designer, can be quantified eg. weight, size, battery life…
What’s in the relationships matrix?
To what extent does the Engineering characteristic contribute to meeting the consumer attributes. Can be signified by symbols representing Strong relationship, moderate relationship, weak relationship (nothing = no relationship)
What’s in the technical matrix?
Calculates a numerical value for each engineering characteristic so that the characteristics that have the greatest impact on consumer satisfaction can be identified. (multiply the priority of the consumer attribute by the strength of the relationship that the EC has)
What’s in the technical correlations matrix?
TCs are the ‘roof’ of the house of quality, it correlates the engineering characteristics that have an influence on one another, with different symbols for different strengths of positive/negative correlations.
What’s in the planning matrix?
Quantitative market data comparing consumer satisfaction levels. Looks at consumer attributes and quantifies how well the need is currently met my existing competitor products, can be scored on 1-5 scale where 5 represents a need that is met v well currently.
What is QFD useful for?
As a method to structure product planning and design, relating customer needs to technical characteristics. it exists in the intersection f quality assurance, quality control and value engineering
Why is reliability engineering important?
All physical components eventually fail so it isi important to estimate the probability of component or system failure as a function of time, which is done by calculating the reliability function.
What is a series topology?
Means all components must work satisfactorily for the system to function correctly (Therefore reliability of series topology is the product of all the individual reliabilities)
What is a parallel topology?
Means all components must fail for the system to fail (therefore the probability of failure is the product of all the individual failure probabilities)
What is the equation for component reliability?
1 - Probability of failure
What does the reliability function model?
The probability of no failure before time t
What 3 curves sum to give the ‘bathtub curve’ of observed failure rate with time?
Early “infant mortality” failure
Wear out failures
What is the hazard (failure rate) function?
It is the failure rate of the component at the next time instant, given that the component has not failed up to time t. Therefore it is a CONDITIONAL probability density function. Also considered the conditional probability of an instantaneous failure at the given time t.
What is a probability density function?
A probability density function (PDF) is a function whose value at any given sample (or point) in the sample space (the set of possible values taken by the random variable) can be interpreted as providing a relative likelihood that the value of the random variable would equal that sample. Other words: PDF is used to specify the probability of the random variable falling within a particular range of values, as opposed to taking on any one value.
How can we obtain the probability density function for failure time?
By fitting a curve to the histogram of failures
How do we obtain the cumulative distribution for failure?
By integrating the probability distribution function
How do we obtain the reliability function?
By doing 1 - (failure cumulative distribution function)
What is the equation for conditional probabilities?
P(A given B) = P(A and B) / P(B)
How do you express the probability of a failure in the interval t,t+dt in terms of the hazard function h(t)
h(t) * dt
similar to how the probability of failure in a time interval given the probability density function f(t) is f(t) * dt (however it is important to note how this expression is not CONDITIONAL, thus doesn’t take into account how the fact the component has survived this far changes the probability of failure in the given time interval.
If the time to failure is exponentially distributed, what does that mean for the hazard function?
The hazard function will be constant, determined by the rate parameter of the exponential probability distribution. This follows from the MEMORYLESS property of the exponential distribution, meaning that the remaining time to failure, given that it has not yet failed, is independent of the time already elapsed.
What is the equation for a hazard function and reliability function where the failure rate is constant
h(t) = λ where λ is the rate parameter of the reliability function e^-λt where t is the time passed. (Probability density distribution is λe^-λt (integrating this gives you the cumulative density distribution, and minusing this from one gives you the reliability function)
What is the equation for the hazard function?
h(t) = f(t) / R(t) (derivation in notes, should know it, uses the fact that the hazard function is a conditional probability density function)
What is value?
The ratio of function to cost
Steps in value engineering
- Identify the main components, modules or processes in a product, system or service
- Carry out a function analysis on these components, modules or processes
- Discover or developing alternative implementations of the identified functions
- Then assess the feasibility, estimate the cost, and refine the most promising implementations.