Scribd
Upload
4 views6 pages

Module 1 Part 7 - Variability Basics

The document discusses the importance of understanding variability in production and service systems, focusing on both controllable and random variations. It highlights the need to quantify variability using absolute and relative measures, such as variance and coefficient of variation, and explains how variability can lead to disruptions like queues in production processes. Additionally, it categorizes variability into low, moderate, and high classes based on the coefficient of variation and identifies various causes of variability.

Uploaded by

devinbigelow16
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
4 views6 pages

Module 1 Part 7 - Variability Basics

The document discusses the importance of understanding variability in production and service systems, focusing on both controllable and random variations. It highlights the need to quantify variability using absolute and relative measures, such as variance and coefficient of variation, and explains how variability can lead to disruptions like queues in production processes. Additionally, it categorizes variability into low, moderate, and high classes based on the coefficient of variation and identifies various causes of variability.

Uploaded by

devinbigelow16
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

VARIABILITY BASICS

Module 1 | Part 7

SIME 6450 - Design of Production and Service Systems

Pedro Huebner | [Link]


Variability Basics
• So far, we have nearly ignored variability in our analyses.
• However, as we know… in practice, variability is all over the place.
• Different ways to approach the issue:
- Queuing models: purely mathematical analysis of well understood relationships.
- Simulation models: useful for validating qualitative relationships.

• Controllable variation occurs as a direct result of our decisions.


• Random variation is a consequence of events beyond our immediate control.

2
Random Variation
• Both types of variation can be disruptive to a production facility.
Here, we focus mainly on random variation as its effects are more difficult to
control and require sophisticated tools to describe.
• Probabilistic Intuition:
- Our intuition is usually good regarding first-order effects of decisions.
FIRST MOMENT or MEAN (average) of the random variables involved.
◦ If we speed up the bottleneck in a production line, without changing anything else, we expect to
get more product.
- Much less developed intuition for second-order effects.
SECOND MOMENT or VARIANCE of the random variables involved.
◦ Which is more variable: the time to process parts individually or the time to process a batch?
Which are more disruptive: short, frequent machine interruptions or long, infrequent ones?

3
Process Time Variability
• Of primary interest in factory physics:
- Effective process time: the total time seen by a job at the workstation.
- Includes processing time and many other detractors (setups, failures, rework…).

• We must be able to quantify variability:


- Absolute variability: variance (σ2), standard deviation (σ)
- Relative variability: squared coefficient of variation (c2), coefficient of variation (c)

𝜎𝜎 𝜎𝜎 2
Let t denote the mean, then: 𝑐𝑐 = 𝑐𝑐 2 = 2
𝑡𝑡 𝑡𝑡

• Can you explain why relative variability is often more important than absolute?

4
Variability, Variability, Variability…
Variability Class Coefficient of Variation Typical Situation
Low c < 0.75 Process times without outages
Moderate 0.75 ≤ c < 1.33 Process times with short adjustments (e.g., setups)
High c ≥ 1.33 Process times with long outages (e.g., failures)

• Variability in effective process time causes queues to form.


High variability causes longer queues! 
• Causes of variability:
- Natural variability - Setups
- Random outages - Operator availability
◦ Preemptive - Rework
◦ Non-preemptive

5
Natural Variability
• Inherent in natural process time, excluding external influences.
• Many sources may affect performance even in the most robust systems!
- A piece of dust in the operator’s eye?
- Slightly different material compositions requiring adjusted machining speeds?

• Quantifying natural variability:


𝜎𝜎0
𝑐𝑐0 =
Let t0 and σ0 denote the mean and SD, 𝑡𝑡0
respectively, of natural process time, then:
Coefficient of variation
of natural process time

You might also like