### presentation

```Simulation-based GA Optimization
for Production Planning
Bioma 2014
September 13, 2014
Juan Esteban Díaz Leiva
Dr Julia Handl
Production Planning
Production
levels
Production Plan
Allocation of
resources
2
Production Planning
Experience
&
“Sixth sense”
Lack of
appropriate
instrument
Inappropriate methods
3
Simulation-based
Optimization
Simulation
Optimization
DES
GA
Aplicable solution
4
Objective
Support decision
making
Production
Planning
Feasibility
Simulation-based
optimization
Uncertainty
&
Real-life
complexity
Applicablility
Robustness
5
Simulation-based Optimization Model
6
Figure 1. Order processing subsystem for work centre .
Simulation-based Optimization Model
Figure 2. Production subsystem for work centre .
Figure 3. Repair service station of work centre .
7
Simulation-based Optimization Model
minimize:
1
==

( = 1, 2, . . . , )
=1
subject to :
∈ S
∈ ℤ≥
( = 1, 2, . . . , 41)
( = 1, 2, . . . , 41)
: number of replications
: fitness function value
: vector of decision variables
expected sum of backorders and inventory costs
8
Simulation-based Optimization Model
31
=
+
=1
where
=
−  ×
0
=
−  ×
0
: demand
if  >
if  ≤
if  <
if  ≥
9
Simulation-based Optimization Model
Requirement of sub-products
41
×  ≤
( = 1,2, … , 4)
=1
: quantity available of sub-product
: amount required of sub-product  to produce one lot in process
10
Simulation-based Optimization Model
GA (MI-LXPM) [2]
•
•
•
•
•
•
real coded
Laplace crossover
power mutation
tournament selection
truncation procedure for integer restrictions
parameter free penalty approach [1]
[1] K. Deb. An efficient constraint handling method for genetic algorithms. Computer methods in applied mechanics
and engineering, 186(2):311-338, 2000.
[2] K. Deep, K. P. Singh, M. Kansal, and C. Mohan. A real coded genetic algorithm for solving integer and mixed
integer optimization problems. Applied Mathematics and Computation, 212(2):505-518, 2009.
11
Results
Original model
Figure 4. Best, mean and worst fitness value of the population at each iteration.
12
Results
Model modifications
Figure 5. Order processing subsystem for work centre .
13
Results
Model modifications
Figure 6. Production subsystem for work centre .
14
Results
Profit maximization
15
Figure 7. Best, mean and worst fitness value of the population at each iteration (time: 8.17 h).
Results
ILP
CDF
deterministic
Stochastic
Simulation
Simulation-based
optimization
CDF
uncertainty
16
Results
Profit maximization
17
Figure 8. CDFs of profit obtained through stochastic simulation.
Conclusions
Production plan
• production levels and allocation of work centres
Process uncertainty
• delays
Real life complexity
• no complete analytic formulation
Better performance of solutions
• stochastic simulation
18
Post-doc Position
Constrained optimization
(applied in the area of protein structure prediction)
Start date: November 2014
in collaboration between:
Computer Sciences (Joshua Knowles),
Faculty of Life Sciences (Simon Lovell)
and MBS (Julia Handl).
Info: [email protected]/* <![CDATA[ */!function(t,e,r,n,c,a,p){try{t=document.currentScript||function(){for(t=document.getElementsByTagName('script'),e=t.length;e--;)if(t[e].getAttribute('data-cfhash'))return t[e]}();if(t&&(c=t.previousSibling)){p=t.parentNode;if(a=c.getAttribute('data-cfemail')){for(e='',r='0x'+a.substr(0,2)|0,n=2;a.length-n;n+=2)e+='%'+('0'+('0x'+a.substr(n,2)^r).toString(16)).slice(-2);p.replaceChild(document.createTextNode(decodeURIComponent(e)),c)}p.removeChild(t)}}catch(u){}}()/* ]]> */
19
Q&A
20
Thank you
September 13, 2014
Juan Esteban Diaz Leiva
Dr Julia Handl
21
```