Scribd
Upload
35 views14 pages

MEE 1015 Total Quality Management & Reliability

1) Reliability is defined as the probability that a system will function over some time period t. It can be expressed as R(t), which is the reliability function. 2) Other important terms include the cumulative distribution function F(t), the probability density function f(t), the mean time to failure (MTTF), and the variance which measures the spread of failure times. 3) Two systems can have the same MTTF but different reliabilities for a given time period. Other measures like the variance are needed to fully characterize the failure distribution.

Uploaded by

HarishVenkatesan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
35 views14 pages

MEE 1015 Total Quality Management & Reliability

1) Reliability is defined as the probability that a system will function over some time period t. It can be expressed as R(t), which is the reliability function. 2) Other important terms include the cumulative distribution function F(t), the probability density function f(t), the mean time to failure (MTTF), and the variance which measures the spread of failure times. 3) Two systems can have the same MTTF but different reliabilities for a given time period. Other measures like the variance are needed to fully characterize the failure distribution.

Uploaded by

HarishVenkatesan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 14

MEE 1015

Total Quality Management & Reliability

Dr.S.Thiagarajan
Professor, SMEC
VIT University
Mail id: thiagarajan.s@vit.ac.in
Ph: 9944357451
Reliability
• Reliability Function

• Reliability is defined as the probability that a system (component) will function


over some time period 𝒕
• Define the continuous random variable 𝑻to be the time to failure of the system
(component); 𝑻 ≥ 𝟎
• Reliability is then expressed as
• 𝑹 𝒕 = 𝑷𝒓 𝑻 ≥ 𝒕 , where 𝑹 𝒕 ≥ 𝟎, 𝑹 𝟎 = 𝟏, 𝒍𝒊𝒎 𝑹 𝒕 = 𝟎
𝒕→∞

• For a given value of 𝒕, 𝑹(𝒕) is the probability that the time to failure is greater than
or equal to 𝒕
Reliability

• If we define 𝑭 𝒕 = 𝟏 − 𝑹 𝒕 = 𝑷𝒓(𝑻 < 𝒕),


where 𝑭 𝟎 = 𝟎 and 𝒍𝒊𝒎 𝑭 𝒕 = 𝟏
𝒕→∞

then 𝑭 𝒕 is the probability that a failure occurs before time 𝒕


• 𝑹 𝒕 is referred to as the reliability function and 𝑭 𝒕 as the cumulative distribution
function (CDF) of the failure distribution
𝒅𝑭(𝒕) 𝒅𝑹(𝒕)
• A third function, defined by 𝒇 𝒕 = =− , is called the probability density
𝒅𝒕 𝒅𝒕
function (PDF)
• This function describes the shape of the failure distribution
Reliability
(a) Reliability function
(b) Cumulative distribution function
(c) Probability density function

• The pdf, 𝒇(𝒕), has two properties


∞
𝒇(𝒕)=0 and 𝟎
𝒇 𝒕 𝒅𝒕 = 𝟏
• Given the pdf, 𝒇(𝒕), then
𝒕
𝑭 𝒕 = 𝟎
𝒇 𝝉 𝒅𝝉 and
∞
𝑹 𝒕 = 𝒕
𝒇 𝝉 𝒅𝝉
Reliability

• In other words, both the reliability function and the CDF represent areas under the
curve defined by 𝒇(𝒕)
• Therefore, since the area beneath the entire curve is equal to one, both the reliability
and the failure probability will be defined so that
𝟎 ≤ 𝑹(𝒕) ≤ 𝟏 and 𝟎 ≤ 𝑭(𝒕) ≤ 𝟏
• The function 𝑹(𝒕)is normally used when reliabilities are computed, and the function
𝑭(𝒕)is normally used when failure probabilities are being computed
Reliability
•
• Example 1

• Given the following PDF for the random variable 𝑻, the time (in operating hours)
to failure for a compressor, what is its reliability for a 100-hr operating life?
𝟎.𝟎𝟎𝟏
𝒕≥𝟎
𝒇 𝒕 = 𝟎.𝟎𝟎𝟏𝒕+𝟏 𝟐
𝟎 𝒐𝒕𝒉𝒆𝒓𝒘𝒊𝒔𝒆
• Solution
∞ 𝟎.𝟎𝟎𝟏 −𝟏 ∞ 𝟏
′
𝑹 𝒕 = ′
𝒕 𝟎.𝟎𝟎𝟏𝒕 +𝟏 𝟐 𝒅𝒕 = ′ =
𝟎.𝟎𝟎𝟏𝒕 +𝟏 𝒕 𝟎.𝟎𝟎𝟏𝒕+𝟏
𝟏 𝟎.𝟎𝟎𝟏𝒕
and 𝑭 𝒕 = 𝟏 − 𝑹 𝒕 = 𝟏−
𝟎.𝟎𝟎𝟏𝒕+𝟏
=
𝟎.𝟎𝟎𝟏𝒕+𝟏
𝟏
Then 𝑹 𝟏𝟎𝟎 = 𝟎.𝟏+𝟏 = 𝟎. 𝟗𝟎𝟗
Reliability
• Design Life

• A design life is defined to be the time to failure that corresponds to a specified


reliability
• To find the design life if a reliability of 0.95 is desired, then set
𝟏
𝑹 𝒕 = = 𝟎. 𝟗𝟓
𝟎.𝟎𝟎𝟏𝒕+𝟏
𝟏
• Solving for 𝒕, we get 𝒕 = 𝟏𝟎𝟎𝟎 − 𝟏 = 𝟓𝟐. 𝟔 𝒉𝒓
𝟎.𝟗𝟓

• The probability of a failure occurring within some interval time 𝒂, 𝒃 may be


found using
𝒃
𝑷𝒓 𝒂 ≤ 𝑻 ≤ 𝒃 = 𝑭 𝒃 − 𝑭 𝒂 = 𝑹 𝒂 − 𝑹 𝒃 = 𝒇 𝒕 𝒅𝒕
𝒂
𝟏 𝟏
𝑷𝒓 𝟏𝟎 ≤ 𝑻 ≤ 𝟏𝟎𝟎 = 𝑹 𝒂 − 𝑹 𝒃 = − = 𝟎. 𝟎𝟖𝟏
𝟎. 𝟎𝟏 + 𝟏 𝟎. 𝟏 + 𝟏
Reliability
• MTTF
• Mean Time To Failure
• The mean time to failure (MTTF) is defined by
∞
MTTF = 𝑬 𝑻 = 𝟎
𝒕𝒇 𝒕 𝒅𝒕
which is the mean, or expected value, of the probability distribution defined by
𝒇(𝒕)
∞
• It can also be shown that MTTF = 𝟎
𝑹𝒕)𝒅𝒕
• Another measure is the median time to failure, defined by
𝑹 𝒕𝒎𝒆𝒅 = 𝟎. 𝟓 = 𝑷𝒓 𝑻 ≥ 𝒕𝒎𝒆𝒅
• The median may be preferred to the mean when the distribution is highly skewed
• The mode, or most likely observed failure time, is defined by
𝒇 𝒕𝒎𝒐𝒅𝒆 = 𝒎𝒂𝒙 𝒇(𝒕)
𝟎≤𝒕≤∞
Reliability

Mode, Median , and MTTF


Reliability
• Example 2
• Consider the probability density function
−𝟎.𝟎𝟎𝟐𝒕
𝒇 𝒕 = 𝟎. 𝟎𝟎𝟐𝒆 𝒕 ≥𝟎; with 𝒕 in hours
𝟎 𝒐𝒕𝒉𝒆𝒓𝒘𝒊𝒔𝒆
∞
• Then, 𝑹 𝒕 = 𝒕
𝟎. 𝟎𝟎𝟐𝒆−𝟎.𝟎𝟎𝟐𝒕 𝒅𝒕 = 𝒆−𝟎.𝟎𝟎𝟐𝒕
∞
∞ −𝟎.𝟎𝟎𝟐𝒕 𝒆−𝟎.𝟎𝟎𝟐𝒕 𝟏
• and MTTF = 𝟎
𝒆 𝒅𝒕 = = = 𝟓𝟎𝟎 𝒉𝒓
−𝟎.𝟎𝟎𝟐 𝟎 𝟎.𝟎𝟎𝟐

• Median time to failure


Set 𝑹 𝒕𝒎𝒆𝒅 = 𝒆−𝟎.𝟎𝟎𝟐𝒕𝒎𝒆𝒅 = 𝟎. 𝟓
𝒍𝒏𝟎.𝟓
Solving for 𝒕𝒎𝒆𝒅 , 𝒕𝒎𝒆𝒅 = −𝟎.𝟎𝟎𝟐 = 𝟑𝟒𝟔. 𝟔 𝒉𝒓
• Mode: The function 𝒇(𝒕) is monotonically decreasing and positive
Maximum value occurs at 𝒕 = 𝟎, and 𝒕𝒎𝒐𝒅𝒆 = 𝟎
Reliability
• Example 3

• Even if two reliability functions have the same mean, their reliabilities may be quite
different for the same operating time
• For example, let 𝑹𝟏 𝒕 = 𝒆−𝟎.𝟎𝟎𝟐𝒕 𝒕 ≥ 𝟎 with 𝑴𝑻𝑻𝑭𝟏 = 𝟓𝟎𝟎 𝒉𝒓 and
𝟏𝟎𝟎𝟎−𝒕
𝑹𝟐 𝒕 = 𝟎 ≤ 𝒕 ≤ 𝟏𝟎𝟎𝟎
𝟏𝟎𝟎𝟎
𝟏𝟎𝟎𝟎
𝟏𝟎𝟎𝟎 𝒕 𝒕𝟐
with 𝑴𝑻𝑻𝑭𝟐 = 𝟎
𝟏− 𝒅𝒕 = 𝒕 − = 𝟓𝟎𝟎 𝒉𝒓
𝟏𝟎𝟎𝟎 𝟐𝟎𝟎𝟎 𝟎

• Reliabilities for an operating time of 400 hr


𝑹𝟏 𝟒𝟎𝟎 = 𝒆−𝟎.𝟎𝟎𝟐(𝟒𝟎𝟎) = 𝟎. 𝟒𝟒𝟗
𝟏𝟎𝟎𝟎−𝟒𝟎𝟎𝟎
𝑹𝟐 𝟒𝟎𝟎 = = 𝟎. 𝟔𝟎
𝟏𝟎𝟎𝟎
• Obviously, the MTTF alone will not uniquely characterize a failure distribution
• Other measures are necessary
Reliability

• One measure that is often used to further describe a failure distribution is its
variance 𝝈𝟐 , defined by
∞
𝝈𝟐 = 𝟎
𝒕 − 𝑴𝑻𝑻𝑭 𝟐 𝒇 𝒕 𝒅𝒕
• The variance represents an average squared distance a failure time will be from
the MTTF
• It is a measure of the spread, or dispersion, of the failure times about the mean
• The variance can also be written as
∞ 𝟐
𝝈𝟐 = 𝟎
𝒕 𝒇 𝒕 𝒅𝒕 − 𝑴𝑻𝑻𝑭 𝟐
Reliability
• Example 4

• The two reliability functions of the previous example are


𝑹𝟏 𝒕 = 𝒆−𝟎.𝟎𝟎𝟐𝒕 𝒕 ≥ 𝟎 with 𝑴𝑻𝑻𝑭𝟏 = 𝟓𝟎𝟎 𝒉𝒓 and
𝟏𝟎𝟎𝟎−𝒕
𝑹𝟐 𝒕 = 𝟎 ≤ 𝒕 ≤ 𝟏𝟎𝟎𝟎
𝟏𝟎𝟎𝟎
𝟏𝟎𝟎𝟎
𝟏𝟎𝟎𝟎 𝒕 𝒕𝟐
with 𝑴𝑻𝑻𝑭𝟐 = 𝟎
𝟏− 𝒅𝒕 = 𝒕 − = 𝟓𝟎𝟎 𝒉𝒓
𝟏𝟎𝟎𝟎 𝟐𝟎𝟎𝟎 𝟎

• And the corresponding probability density functions are


𝒇𝟏 𝒕 = 𝟎. 𝟎𝟎𝟐𝒆−𝟎.𝟎𝟎𝟐𝒕 , 𝒇𝟐 𝒕 = 𝟏/𝟏𝟎𝟎𝟎
• The variances and standard deviations are
∞ 𝟐
𝝈𝟐𝟏 = 𝟎
𝒕 𝟎. 𝟎𝟎𝟐𝒆−𝟎.𝟎𝟎𝟐𝒕 𝒅𝒕 − 𝟓𝟎𝟎 𝟐
= 𝟐, 𝟓𝟎, 𝟎𝟎𝟎; 𝝈𝟏 = 𝟓𝟎𝟎
𝟏𝟎𝟎𝟎 𝟐 𝟏
𝝈𝟐𝟐 = 𝟎
𝒕 𝒅𝒕 − 𝟓𝟎𝟎 𝟐
= 𝟖𝟑, 𝟑𝟑𝟑. 𝟑𝟑; 𝝈𝟐 = 𝟐𝟖𝟖. 𝟔𝟕
𝟏𝟎𝟎𝟎
Reliability
• Example 4

• Therefore, although the MTTFs are identical, the standard deviations are
considerably different
• It can be concluded that the reliability distributions should be inherently
different
• The distribution having the smaller variance is generally preferred

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy