Vensim software work required for 3 students 3 copies
Lisa09
02.pdf
Dr. Daniel Xing Email: [email protected]
EBUS-504
Operations Modelling and Simulation
Lecture 1
Principles of Simulation and modelling
University of Liverpool
Management School,
UK
Background of your lecturer
Dr. Xinjie (Daniel) Xing. Module leader – [email protected]
o Senior lecturer in operations management (deputy director for BABD programme)
o PhD in operations research in maritime logistics
o Research interests lie in transport & logistics, sustainable supply chain, and
blockchain applications.
o Publications available at world leading journals such EJOR, TRE, IJOPM, ANOR etc.
o Leading a few (both internal and external) research projects in logistics and
blockchain fields.
Office hours: appointment by emails (email manners!!)
Email turnaround time: Three working days (i.e. exclude weekends and national holidays).
Objective
Learning objective from this module
• Understand the dynamic nature of systems and their behavioural characteristics
• Understand a range of modelling analytical methods and their appropriate applications
• Understand how models are developed, tested and validated from real system
• Understand basic concepts of optimisation
• Be confident in use of commercially available tools (Witness, Vensim and Matlab)
Curriculum overview
• 1. Introduction to modelling and simulation and first look of Witness(wk1)
• 2. Process mapping techniques + Witness functions and advance rules (wk2)
• 3. Model state analysis + Bottleneck analysis (wk3)
• 4. Bottleneck analysis 2 and queues (wk4)
• 5. Use of variables and attributes (wk5)
• 6. Optimisation in Witness (wk6)
• 7. Introduction to linear programming and integer programming (wk7&8) (Matlab
application)
• 8. System dynamics (wk9-11) （Vensim application）
• 9. Revision week (wk12)
System
System
System
System
A collection of interacting entities that produces some form of
behaviour that can be observed over an interval of time (Birta
and Arbez, 2013).
It is inherently complex with high level of granularity.
Example of systems:
Tangible:
1. Transportation system
2. Power-generating system
3. Warehouse system
Intangible:
1. Health care system
2. Social systems
3. Economic systems
Modelling and simulation
Models and real world systems
Types of systems
A discrete system is one in which the state variables change
only at discrete or countable points in time.
✓ Customers arrives at different time points
✓ Car production scheduling
A continuous system is one in which the state variables change
continuously over time.
✓ The amount of water flow over a dam
✓ Vibration of materials
✓ Evaluation of radioactive decay
From system to modelling and simulation
1. Cost effective approach for analysis
It is always resource consuming to run the actual system for analysis purposes.
2. Simplification
A real system contains many branches and noises which cause difficulties for
understanding its key behaviours and logic.
3. Repetition
For various reasons, the run of a system cannot be slowed down or rewinded.
4. Hazards
Some systems are highly uncertain and hazards involved, which may not easy to be
observed or analysed directly.
Simulation and modelling
Simulation and modelling refer to a type of tools which helps to
gain insight into features of systems’ behaviours.
✓ A model is a representation or abstraction of the system under
investigation (the SUI)
✓ Normally computer-based but not always (manual simulation will be
discussed in later slides)
Role of modelling and simulation:
1. Comparison of control policy options;
2. Education and training;
3. Engineering design;
4. Evaluation of decision or action
alternatives;
5. Evaluation of strategies for
transformation or change;
6. Forecasting;
7. Prototyping and concept evaluation;
8. Risk/safety assessment;
9. Uncertainty reduction in decision
making;
Pros and Cons of simulation modelling
Advantages:
1. Cheaper to execute;
2. Alternative strategies for
dangerous scenarios;
3. Saves time;
4. Get away with anything morally or
ethically unacceptable (e.g.
assessing radiation dispersion);
5. Effective tool for something
irreversible (e.g. change of country
policy)
Disadvantages:
1. Inappropriate statement of goals
(project management);
2. Inappropriate granularity of the
model;
3. Ignoring unexpected behaviour;
4. Inappropriate mix of essential
skills;
5. Inadequate flow of information to
the client (big data management);
Building a Simulation Model
3. STRUCTURED
WALK-THROUGH
2. PROBLEM
FORMULATION
1. DATA AND
MODEL DEFINITION
6. VALIDATE
MODEL
5. PERFORM
PILOT RUNS
4. BUILD MODEL
AND VERIFY
10. DOCUMENT AND
IMPLEMENT RESULTS
9. ANALYSE OUTPUT
DATA
8. MAKE PRODUCTION
RUNS
7. DESIGN
EXPERIMENTS
•Define goals, boundaries, and assumptions;
• Define concepts (entities, attributes, event list, etc…)
• Define interactions and relationships;
• Define data
Define your model
- Goals
What is the ultimate purpose of the SUI?
What are the key indicators of the SUI?
- Boundaries
The context of the model (geographical boundaries, physical
boundaries, timeframes etc.)?
What terminates the model?
- Assumptions
Level of granularity
Effective simplification to achieve the goal
Goals, boundaries, and assumptions
System goals
• Objectives must be clear and specific and agreed upon.
• Some Examples of Objectives
o Identify the best design to meet output targets
o Identify the optimum number of operators/machines/vehicles etc. to use
o Maximise the utilisation of resources
o Identify the maximum output you can produce from a system
o Identify the main bottleneck resources
o How to improve performance of -----?
o What is the impact of changing -------?
o Where is the waste in the system?
o Which of these scenarios do I adopt?
System Boundary
• Academic Institution
✓ Academic Department
✓ Academic Programme
✓ Computer Services Department
▪ Manufacturing Company
✓ Subsidiary
✓ Accounts Department
✓ Manufacturing System
✓ Materials Management
• Retail Sector
✓ One Shop
✓ Computer System
✓ Logistics
System
System
System
A group of
interrelated elements
operating to achieve
a goal.
Quick questions
• Why clear definitions of model goals are critical to modelling
projects?
• How does a model goal affect the future project
implementation?
• How does a model goal affect the boundary definition of a
model?
Pieces of a Simulation Model
• Entities
• “Players” that move around, change status, affect and are affected by other entities
• Dynamic objects — get created, move around, leave (maybe)
• Usually represent “real” things
• Our model: entities are the parts
• Can have “fake” entities for modeling “tricks”
• Breakdown demon, break angel
Though Arena has built-in ways to model these examples directly
• Usually have multiple realizations floating around
• Can have different types of entities concurrently
• Usually, identifying the types of entities is the first thing to do in building a model
Examples of entities
Birta and
Arbez, 2013
Data Collection
• Internal Documents
• Observations (Work Study)
• Survey data
o Internal: company specific
o External: Industry/Sector standards, Benchmarking
• Own Knowledge
• Interviews with experts
o Fact finding
o Problem identification
o Solution Review
Define your data
• Constant and parameters – serve simply as names for the values of features
or properties within a model which remain invariant over the course of any
particular experiment with the model
• Time and other variables – Variables provide an abstraction for features of
the model whose values typically change as the model evolves over the course of
the observation interval. Time is a special variable: (1) never depend upon any
other variables; (2) most other variables are dependent on time
• Input, state and output variables – Variables for defining the specifications
of the inputs, and outputs of the SUI and dynamic behaviors of different entities
within the SUI
Pieces of a Simulation Model
• Attributes
• Characteristic of all entities: describe, differentiate
• All entities have same attribute “slots” but different values for different
entities, for example:
• Time of arrival
• Due date
• Priority
• Color
• Attribute value tied to a specific entity
• Like “local” (to entities) variables
• Some automatic in Arena, some you define
Pieces of a Simulation Model
• Event
An instantaneous occurrence that changes the state of a system (such as the completion of a service, or the arrival of an entity).
• Event notice
A record of an event to occur at the current or some future time, along with any associated data necessary to execute the event; at a minimum the record includes the event type and the event time.
• Event list
A list of event notices for future events, ordered by time of occurrence; also known as the Future Events List.
Pieces of a Simulation Model
• Activity
A duration of time of specified length (e.g. a service time or inter-arrival time), which is known when it begins (although it may be defined in terms of a statistical distribution).
• Delay
A duration of time of unspecified indefinite length, which is not known until it ends (e.g. a customer’s delay in a last-in-first-out waiting line which, when it begins, depends on future arrivals).
• Simulation Clock
A variable representing simulated time.
Simulator Elements
Exercise
• Company ABC is a car parts supplier focusing on side panels and car floors. They currently have 5 moulds and two ovens used for making panels. 3 different side panels are being produced and each of them require different raw materials and production processes. Both ovens are automatic and are associated with the same unit production costs and unit carbon emission rate. All the panels need to be fully cooled down in a cooling pool before they are split from moulds. Also, floor mats are being produced in parrel by a different machine, but they share the same painting station with panels. Some labours are required to do painting and setup oven. Each panel has its own market price and they can also be bundled (and with floors) for different bundle prices as well.
(a) Develop a list of possible goals for this model?
(b) Define the different data to be used by this model. (e.g. entities? Parameters? Variables? Attributes? Events? Etc.)
Building a Simulation Model
3. STRUCTURED
WALK-THROUGH
2. PROBLEM
FORMULATION
1. DATA AND
MODEL DEFINITION
6. VALIDATE
MODEL
5. PERFORM
PILOT RUNS
4. BUILD MODEL
AND VERIFY
10. DOCUMENT AND
IMPLEMENT RESULTS
9. ANALYSE OUTPUT
DATA
8. MAKE PRODUCTION
RUNS
7. DESIGN
EXPERIMENTS
Model formulation and conceptual model
“Model formulation is the step where our knowledge of a natural system is
translated in mathematical form.” (Soetaert and Herman, 2009)
❖ It is primarily quantitative but can be supported with qualitative
descriptions;
❖ It is the first key document of modelling and simulation;
❖ Normally supported with charts and graphs;
❖ It helps to build the conceptual model
Conceptual Model is a refinement process that consolidates all relevant
structural and behavioural features of a SUI in a concise and precise
manner.
Examples of conceptual model and the corresponding
model formulation
Xing et al. (2022)
Example of conceptual model
Project-based learning process
Company ABC uses 5 moulds to produce side panels for its car manufacturer.
There are currently 2 automatic ovens are being used and side panel A, B, & C
need to be produced. Each side panel requires the use of different raw materials,
different heating time in ovens and each material has different procurement
settings. There are currently 3 labours working in the shopfloor to set up ovens
and split panels from moulds. All moulds need to be fully cooled down in cooling
before they are split and returned back to use. Side panels can be despatched
for sales after split process.
➢ Freely select your group members and your team can work on
this project together throughout the whole semester.
➢ New challenges will be added continuously.
➢ Part of the project results will be used for your final assessment.
✓ Beginning of your project
First look of Witness and build the first model for your
project
Please see separate slides for the intro of Witness.
✓ Build your first sample model
Panel type: A
Required materials: P1- coming every 4 mins with lot size 1 (and
one mould: no need at this moment!!)
Machines: Oven (configuration 3 mins, process time 5 mins), Split
(2 mins)
Buffers: Cooling and storages.
Labour: L1
Dr. Daniel Xing Email: [email protected]
EBUS-504
Operations Modelling and Simulation
Lecture 1
Principles of Simulation and modelling
University of Liverpool
Management School,
UK
