Artificial Intelligence Algorithms and Process in Manufacturing Planning and Supply Chain Operations

1. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
L | C | LOGISTICS
PLANT MANUFACTURING AND BUILDING FACILITIES EQUIPMENT
Engineering-Book
ENGINEERING FUNDAMENTALS AND HOW IT WORKS
MAY 2020
Expertise in Process Engineering Optimization Solutions & Industrial Engineering Projects Management
Supply Chain Manufacturing & DC Facilities Logistics Operations Planning Management

2. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
Database
AI ApplicationPlanner
Dash Board
Production
Maintenance Warehouse
Transporation
ERP
Management
Dash Board
Planning
Quality
Customer Service
ProcurementFinance &
Accounting

3. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
(AI) is defined as a simulation of human intelligence
used in computers to internally, through computer
procedures and algorithms, communicate production
operations process status, internally use the feedback
data from the operator at the field; internally analyze
the feedback data, and internally perform the required
task, in real time, and continuously update the AI
Manufacturing Dashboard; used by the management
team
Traditionally, in known manufacturing management
environments with available models, production planning
can be done offline; solutions can be found and evaluated
prior to execution by the management team
The fact is AI will soon be able to do administrative tasks
that consume much of the manager’s team time, faster,
better and at lower cost
Traditionally most management team spends their time
as follows:
Administrative coordination and control 54%
Solving problems and collaborating 30%
In strategy and innovation 10%
Developing people and engaging with stakeholders 7%

4. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
Many business decisions require insight
beyond what artificial intelligence can squeeze
from data alone. Managers use their
knowledge of organizational history and
culture, as well as empathy and ethical
reflection. This is the essence of human
judgment — the application of experience and
expertise to critical business decisions and
practices.
However this is different from the daily routine
decisions to be taken in the Manufacturing
Operations Management; where (AI) in
computer systems can take out the 84% of the
management team time off
While managers’ own creative abilities are
vital, perhaps even more important is their
ability to harness others’ creativity.
Manager-designers bring together diverse
ideas into integrated, workable, and
appealing solutions. They embed design
thinking into the practices of their teams
and organizations.
Manufacturing Operations Management
team need to understand the following:
Digital Media Technology
Creative thinking and experimentation
Strategy development
Quality management and standards
Sharpen their current domain of expertise

5. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT

6. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
To understand what (AI) is supported by in computer
systems, lets mention the following definitions
Machine learning (ML) is the study of computer
algorithms that improve automatically through
experience. It is seen as a subset of artificial
intelligence. Machine learning algorithms build a
mathematical model based on sample data, known as
"training data", in order to make predictions or decisions
without being explicitly programmed to do so. Machine
learning algorithms are used in a wide variety of
applications, such as email filtering and computer vision,
where it is difficult or infeasible to develop conventional
algorithms to perform the needed tasks.
Machine learning is closely related to computational
statistics, which focuses on making predictions using
computers. The study of mathematical optimization
delivers methods, theory and application domains to the
field of machine learning. Data mining is a related field
of study, focusing on exploratory data analysis through
unsupervised learning. In its application across business
problems, machine learning is also referred to as
predictive analytics.

7. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
In computer programming, a procedure is a set of coded
instructions that tell a computer how to run a program
or calculation
Many different types of programming languages can be
used to build a procedure
Depending on the programming language, a procedure
may also de called a subroutine, subprogram or function
Object Oriented Programming OOP is a
software programming model
constructed around objects
This model compartmentalizes data into
objects (data fields) and describes
object content and behavior through the
declaration of classes (methods)
In OOP, computer programs are
designed in such a way where
everything is an object that interact with
one another
Most popular programming language like
Java, C++, C#, Ruby follow an object
programming paradigm
An object based application in Java is
based on declaring classes

8. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
Example of a Manufacturing Operations Algorithm & Process Application
New Customer
Order
information
Production line
machines status
Production line
machines quality
Production line
utilities status
Production line
operators
machine setting
production line
process status
WH raw
materials status
WIP materials
status
scraps, spoils,
waste status
WIP materials
transportation
inbound
materials &
SOH
production line
production
status
FG SOH &
Customer
Goods
Customer Order
Delivery
Transport status
Productio
n Planning
Algorithm
Demand
Planning
Forecast
Algorithm
Supply
Chain
Purchase
Algorithm
Productio
n Control
Algorithm
Inbound /
WIP /
outbound
transport
Algorithm
Production Line
Maintenance
Sanitation
status
AI DASHBOARD

9. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
Get Production Lines m and
Customers Orders Products n
matrix m x n
add columns: $ value, Qty
add column Time factor :
= 1 for Min, Expected, Max,
= 1.w for FIFO, LIFO, Urgent,
w = +/- { 0.1, 0.2, 0.3}
add column compound:
= factor x $ value/Qty
make a matrix Aij product i
line j, indicate time Aij to
produce for each related line
top of columns is the time
ready to start each line
based on game theory there
are two strategies to find the
product maxmin value and
production line minmax value
multiplay the product i compund
value for each line j time to
produce, generating a new
matrix Bij with fractions
once the new generated matrix
Bij is complete add up new
right column and new bottom
line m+1 x n+1
identify the minmax value
and the maxmin value, then
assign one product to one
line use the minmax column
repeat the same procedure
till all products or lines are
already assigned
if there is a product or line
not assigned, these will go in
the next production cycle
if more than one product is
assigned to a line; choose
the lowest line compound
value to assign that product
first; followed by the next
product in the same line for
next production
Objective is to assign each
product to a corresponding
line in the best sequence
with a minmax and maxmin
strategy "Game Theory"
in the next line production
cycle, the starting time is the
last ending time, plus new
setting or available line time
available time depends on
required maintenance,
sanitation and/or setting time
Line Production Time factor :
= 1 for Min, Expected, Max,
= +/- 0.1, 0.2, 0.3 for either
FIFO, LIFO, Urgent you
choose based on your
strategy to weight a low/high
priority to FIFO, LIFO, Urgent
whenever there is only one
product to be produced in only
one line, the allocation is
unique, there is no choice

10. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
Line 1 Line 2 Line 3 Line 4 Line 5
Line 6 Line 7 Line 8 Line t+1
product
i
product
i+1
product
i+n
product
i+n+1
line 1 line 2
line 3
line 3
line 4 line 5
line 7 line 8
line 6 line t+1

11. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
factor value qty compoundLInea1 LInea2 LInea3 LInea4 LInea5 LInea6 LInea7 LInea8 LInea9 LInea10 maxmin
Product1 1 1 1
Product2 1 1
Product3 1
Product4 1 1
Product5 1 1
Product6 1 1 1
Product7 1 1 1
Product8 1 1 1
Product9 1 1 1
Product10 1 1 1
factor value qty compoundLInea1 LInea2 LInea3 LInea4 LInea5 LInea6 LInea7 LInea8 LInea9 LInea10 maxmin
50 0 30 20 0 20 30 30 10 0
150 90 130 120 40 90 110 120 60 120 1030
Product1 time 0 0 0.000769 0.000833 0.001 0 0 0 0 0 0.002603
Product2 time 0.001286 0.002 0 0 0 0 0 0 0 0 0.003286
Product3 time 0 0 0 0 0 0.00014286 0 0 0.000167 0 0.00031
Product4 time 0 0 0 0 0 0 0.000889 0.000677 0 0 0.001566
Product5 time 0 0 0 0 0 0 0 0 0.0024 0.0026 0.005
Product6 time 0.000627 0.000889 0.000711 0 0 0 0 0 0 0 0.002227
Product7 time 0 0.002143 0.001429 0.001429 0 0 0 0 0 0 0.005
Product8 time 0 0 0.013 0.01625 0.028889 0 0 0 0 0 0.058139
Product9 time 0 0 0 4.17E-05 0.00004 0.0000370 0 0 0 0 0.000119
Product1
0 time 0 0 0 0 0.0005 0.00039286 0.000458 0 0 0 0.001351
minmax 0.001913 0.005032 0.015909 0.018554 0.030429 0.00057275 0.001347 0.000677 0.002567 0.0026 0.0796
0.000627 0.002 0.000769 0.001429 0.028889 0.0000370 0.000458 0.000677 0.000167 0.0026 0.037653

12. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
factor value qty compoundLInea1 LInea2 LInea3 LInea4 LInea5 LInea6 LInea7 LInea8 LInea9 LInea10 maxmin
product1 day 50 0 30 20 0 20 30 30 10 0
min 1 1000 10000 0.1 0 0 100 100 100 0 0 0 0 0 0.000769
exp 1 1000 10000 0.1 0 120 120 130 0.000435
max 1 1000 10000 0.1 0 150 140 140 0.000370
FIFO 1.1 1000 10000 0.11 0 120 120 130 0.000407
LIFO 1 1000 10000 0.1 0 120 120 120 0.0004
urgent 1 1000 10000 0.1 0 120 120 120 0.000417
product1 minmax 0 0 0.000769 0.000833 0.001 0 0 0 0 0L3
130
product2 day 50 0 30 20 0 20 30 30 10 0
min 1 900 5000 0.18 90 90 0.001286
exp 1 900 5000 0.18 100 100 0.000947
max 1 900 5000 0.18 105 105 0.000878
FIFO 1 900 5000 0.18 100 100 0.000878
LIFO 1 900 5000 0.18 100 100 0.0009
urgent 1 900 5000 0.18 100 100 0.0009
product2 minmax 0.001286 0.002 0 0 0 0 0 0 0 0L2
90

13. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
factor value qty compoundLInea1 LInea2 LInea3 LInea4 LInea5 LInea6 LInea7 LInea8 LInea9 LInea10 maxmin
product3 day 50 0 30 20 0 20 30 30 10 0
min 1 500 50000 0.01 0 50 50 0.000143
exp 1 500 50000 0.01 0 70 80 7.69E-05
max 1 500 50000 0.01 0 90 100 5.56E-05
FIFO 1 500 50000 0.01 0 70 80 5.56E-05
LIFO 1.2 500 50000 0.012 0 70 80 0.000075
urgent 1 500 50000 0.01 0 70 80 6.25E-05
product3 minmax 0 0 0 0 0 0.00014286 0 0 0.000167 0L9
60
product4 day 50 0 30 20 0 20 30 30 10 0
min 1 800 10000 0.08 0 60 90 0.000667
exp 1 800 10000 0.08 0 100 110 0.0004
max 1 800 10000 0.08 0 120 120 0.000348
FIFO 1.1 800 10000 0.088 0 100 100 0.0004
LIFO 1 800 10000 0.08 0 100 100 0.0004
urgent 1 800 10000 0.08 0 100 100 0.0004
product4 minmax 0 0 0 0 0 0 0.000889 0.000677 0 0L8
120

14. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
factor value qty compoundLInea1 LInea2 LInea3 LInea4 LInea5 LInea6 LInea7 LInea8 LInea9 LInea10 maxmin
product5 day 50 0 30 20 0 20 30 30 10 0
min 1 1200 5000 0.24 0 100 120 0.002
exp 1 1200 5000 0.24 0 120 120 0.001
max 1 1200 5000 0.24 0 130 120 0.00096
FIFO 1 1200 5000 0.24 0 120 120 0.00096
LIFO 1 1200 5000 0.24 0 120 120 0.001
urgent 1.3 1200 5000 0.312 0 120 120 0.0013
product5 minmax 0 0 0 0 0 0 0 0 0.0024 0.0026L10
120
product6 day 50 0 30 20 0 20 30 30 10 0
min 1 800 90000.0888889 100 100 100 0.000593
exp 1 800 90000.0888889 120 120 130 0.000386
max 1 800 90000.0888889 140 140 140 0.000329
FIFO 1 800 90000.0888889 120 120 130 0.000329
LIFO 1.2 800 90000.1066667 120 120 120 0.000427
urgent 1 800 90000.0888889 120 120 120 0.00037
product6 minmax 0.000627 0.000889 0.000711 0 0 0 0 0 0 0L1
150

15. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
factor value qty compound LInea1 LInea2 LInea3 LInea4 LInea5 LInea6 LInea7 LInea8 LInea9 LInea10 maxmin
product7 day 50 0 30 20 0 20 30 30 10 0
min 1 1200 70000.1714286 0 80 90 100 0.001429
exp 1 1200 70000.1714286 0 100 100 110 0.000816
max 1 1200 70000.1714286 0 110 105 115 0.000762
FIFO 1 1200 70000.1714286 0 100 100 110 0.000762
LIFO 1 1200 70000.1714286 0 100 100 110 0.000779
urgent 1 1200 70000.1714286 0 100 100 110 0.000779
product7 minmax 0 0.002143 0.001429 0.001429 0 0 0 0 0 0L4
120
product8 day 50 0 30 20 0 20 30 30 10 0
min 1 4000 4000 1 0 50 50 40 0.0125
exp 1 4000 4000 1 70 60 45 0.008333
max 1 4000 4000 1 90 65 50 0.00625
FIFO 1 4000 4000 1 70 60 45 0.00625
LIFO 1 4000 4000 1 70 60 45 0.007143
urgent 1.3 4000 4000 1.3 70 60 45 0.009286
product8 minmax 0 0 0.013 0.01625 0.028889 0 0 0 0 0L5
40

16. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
factor value qty compoundLInea1 LInea2 LInea3 LInea4 LInea5 LInea6 LInea7 LInea8 LInea9 LInea10 maxmin
product9 day 50 0 30 20 0 20 30 30 10 0
min 1 100 300000.0033333 60 90 70 0 0 3.7E-05
exp 1 100 300000.0033333 100 110 90 0 0 1.67E-05
max 1 100 300000.0033333 120 120 100 0 0 1.45E-05
FIFO 1 100 300000.0033333 100 100 90 0 0 1.52E-05
LIFO 1.2 100 30000 0.004 100 100 90 0 0 0.00002
urgent 1 100 300000.0033333 100 100 90 0 0 1.67E-05
product9 minmax 0 0 0 4.17E-05 0.00004 3.7037E-05 0 0 0 0L6
90
product1
0 day 50 0 30 20 0 20 30 30 10 0
min 1 500 10000 0.05 100 120 80 0 0 0.000357
exp 1 500 10000 0.05 120 120 90 0 0 0.000208
max 1 500 10000 0.05 130 120 100 0 0 0.0002
FIFO 1.1 500 10000 0.055 120 120 90 0 0 0.00022
LIFO 1 500 10000 0.05 120 120 90 0 0 0.000208
urgent 1 500 10000 0.05 120 120 90 0 0 0.000208
product1
0 minmax 0 0 0 0 0.0005 0.00039286 0.000458 0 0 0L7
110

17. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
Make Anm matrix, Products n
and machines m
make product columns:
$ value, Qty
before matrix n x m
product column Time factor :
= 1 for Min, Expected, Max,
= 1.w for FIFO, LIFO, Urgent,
w = +/- { 0.1, 0.2, 0.3}
before matrix n x m
product column compound:
= factor x $ value/Qty
before matrix n x m
put the value Aij product i
machine j, with time Aij to
assemble in related product
machine, top of columns is
time ready to start machine
based on game theory there
are two strategies to find the
product assembly maxmin
value and machine minmax
multiplay the product i compund
value to the sum of machines j
time to assembly, generating a
new column Aij+1
once the new generated
column Aij+1 is complete add
up new bottom line Ai+1,j
identify the product minmax
Aij+1 descending value; sort
and assign one product Aij+1
descending minmax column
check the start/end time of
the assembly machine Aij per
descending sequence
next product n, machines
start stop time dependes on
the higer sequence machine
if more than one product n is
assigned to a machine m; it
has to wait the start/stop
machine m time, fore the
next product to use that
machine, then write the new
start/stop machine m time
Objective: to assemble each
product with best sequence
using all the machines tools
with a minmax and maxmin
strategy "Game Theory"
in the next product assembly
cycle, the starting time is the
last ending time, plus new
setting or available time
available time depends on
required maintenance,
sanitation and/or setting time
productTime factor :
= 1 for Min, Expected, Max,
= +/- 0.1, 0.2, 0.3 for either
FIFO, LIFO, Urgent you
choose based on your
strategy to weight a low/high
priority to FIFO, LIFO, Urgent
whenever there is only one
product to be produced in only
one machine, the allocation is
no choice

18. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
product
i
product
i+1
product
i+n
product
i+n+1
line 1 line 2
line 3
line 3
line 4 line 5
line 7 line 8
line 6 line t+1
line 1 line 2 line 3line 1 line 2 line 3line 1 line 2 line 3
line 1
line 3
line 4 line 5
line 1

19. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
LInea1 LInea2 LInea3 LInea4 LInea5 LInea6 LInea7 LInea8 LInea9 LInea10 maxmin maxmin
Product1 1 1 1
Product2 1 1 1
Product3 1 1 1 1
Product4 1 1 1 1 1
Product5 1 1
Product6 1 1 1
Product7 1 1 1
Product8 1 1 1
Product9 1 1 1
Product10 1 1 1
LInea1 LInea2 LInea3 LInea4 LInea5 LInea6 LInea7 LInea8 LInea9 LInea10 maxmin sequence
0 0 0 0 0 0 0 0 0 0
0
Product1 0 0 0.0010.0001428570.000125 0 0 0.00000 0 00.001268 0.000333 9
Product2 0.002 0.0010.000643 0 0 0 0 0.00000 0 00.003643 0.000643 4
Product3 6.89655E-05 0 4.88E-05 0 0 2.46914E-05 0 0.000002.326E-05 00.000166 0.000063 10
Product4 0 0 00.0001481480.000138 00.000125 0.00011 0 00.000521 0.000195 7
Product5 0 0 0 0 0 0 0 0.00000 0.00240.0010910.003491 0.001091 3
Product6 0.0004678360.0002470.000189 0 0 0 0 0.00000 0 00.000904 0.000296 6
Product7 00.0006590.0004630.000364742 0 0 0 0.00000 0 00.001487 0.000635 5
Product8 0 0 0.02 0.010.007143 0 0 0.00000 0 00.037143 0.007143 1
Product9 0 0 00.000333333 0.00029 0.00026316 0 0.00000 0 00.000886 0.000909 8
Product1
0 0 0 0 00.0029170.0019444440.001591 0.00000 0 00.006452 0.002333 2
0.0025368020.0019060.022344 0.010989080.0106120.0022322940.001716 0.00011
0.002423
30.001091 0.05596 0.013641

20. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
LInea1 LInea2 LInea3 LInea4 LInea5 LInea6 LInea7 LInea8 LInea9 LInea10 maxmin start finish sequence
0 0 0 0 0 0 0 0 0 0
0 50 100 -
Product8 1
50 100 140 140
140 240 360 140
Product10 2
240 360 440 440
0 100 -
Product5 3
100 220 220
0 90 180 -
Product2 4
90 180 280 280
90 180 280 370 90
Product7 5
90 260 370 470 470
90 260 370 90
Product6 6
190 360 470 470
470 540 580 640 470
Product4 7
540 580 640 730 730
540 580 690 540
Product9 8
600 690 760 760
470 600 700 470
Product1 9
100 700 800 800
190 290 760 810 190
Product3 10
290 410 810 860 860

21. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
factor value qty compound LInea1 LInea2 LInea3 LInea4 LInea5 LInea6 LInea7 LInea8 LInea9 LInea10 maxmin maxmin
product1 day 0 0 0 600 700 800 800 800 800 800
min 1 1000 10000 0.1 0 0 100 100 100 0 0 0 0 0 0.000125 0.000333
exp 1 1000 10000 0.1 0 0 110 110 110 0.000476 0.000303
max 1 1000 10000 0.1 0 0 120 120 120 0.000435 0.000278
FIFO 0.9 1000 10000 0.09 0 0 120 120 120 0.000375 0.000250
LIFO 1 1000 10000 0.1 0 0 120 120 120 0.000417 0.000278
urgent 1 1000 10000 0.1 0 0 120 120 120 0.000417 0.000278
product1 minmax 0 0 0.001 0.000142857 0.000125 0 0 0 0 0L3
0 0 100 700 800 800 800 800 800 800
product2 day 0 90 180 280 280 280 280 280 280 280
min 1 900 5000 0.18 90 90 100 0.000643 0.000643
exp 1 900 5000 0.18 100 100 110 0.000857 0.000581
max 1 900 5000 0.18 105 105 115 0.0008 0.000554
FIFO 1 900 5000 0.18 100 100 115 0.000783 0.000571
LIFO 1 900 5000 0.18 100 100 115 0.000783 0.000571
urgent 1 900 5000 0.18 100 100 115 0.000783 0.000571
product2 minmax 0.002 0.001 0.000643 0 0 0 0 0 0 0L2
90 180 280 280 280 280 280 280 280 280
product3 day 190 290 290 410 410 760 810 810 810 860
min 1 1000 50000 0.02 100 120 50 50 2.33E-05 0.000063
exp 1 1000 50000 0.02 120 130 70 80 0.00008 0.000050
max 1 1000 50000 0.02 130 150 90 100 7.14E-05 0.000043
FIFO 1 1000 50000 0.02 130 150 70 80 6.67E-05 0.000047
LIFO 0.8 1000 50000 0.016 130 150 70 80 5.33E-05 0.000037
urgent 1 1000 50000 0.02 130 150 70 80 6.67E-05 0.000047
product3 minmax 0.000069 0 4.88E-05 0 0 2.46914E-05 0 0 2.326E-05 0L6
290 290 410 410 410 810 810 810 860 860

22. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
factor value qty compound LInea1 LInea2 LInea3 LInea4 LInea5 LInea6 LInea7 LInea8 LInea9 LInea10 maxmin maxmin
product4 day 190 340 340 470 540 580 580 640 730 730
min 1 800 10000 0.08 150 70 40 60 90 0.00011 0.000195
exp 1 800 10000 0.08 200 75 50 100 110 0.000229 0.000150
max 1 800 10000 0.08 210 80 60 120 120 0.000195 0.000136
FIFO 0.9 800 10000 0.072 210 80 60 100 100 0.000171 0.000131
LIFO 1 800 10000 0.08 210 80 60 100 100 0.00019 0.000145
urgent 1 800 10000 0.08 210 80 60 100 100 0.00019 0.000145
product4 minmax 0 0 0 0.000148148 0.000138 0 0.000125 0.00011 0 0L8
340 340 340 540 580 580 640 730 730 730
product5 day 0 0 0 0 0 0 0 0 0 100
min 1 1200 5000 0.24 0 100 120 0.001091 0.001091
exp 1 1200 5000 0.24 0 120 120 0.001 0.001000
max 1 1200 5000 0.24 0 130 120 0.00096 0.000960
FIFO 1 1200 5000 0.24 0 120 120 0.00096 0.001000
LIFO 1 1200 5000 0.24 0 120 120 0.001 0.001000
urgent 0.7 1200 5000 0.168 0 120 120 0.0007 0.000700
product5 minmax 0 0 0 0 0 0 0 0 0.0024 0.001091L9
0 0 0 0 0 0 0 0 100 220
factor value qty compound LInea1 LInea2 LInea3 LInea4 LInea5 LInea6 LInea7 LInea8 LInea9 LInea10 maxmin maxmin
product6 day 90 260 370 470 470 470 470 470 470 470
min 1 800 9000 0.0888889 100 100 100 0.000189 0.000296
exp 1 800 9000 0.0888889 120 120 130 0.000386 0.000240
max 1 800 9000 0.0888889 140 140 140 0.000329 0.000212
FIFO 1 800 9000 0.0888889 120 120 130 0.000329 0.000240
LIFO 0.8 800 9000 0.0711111 120 120 120 0.000284 0.000198
urgent 1 800 9000 0.0888889 120 120 120 0.00037 0.000247
product6 minmax 0.000467836 0.000247 0.000189 0 0 0 0 0 0 0L1
190 360 470 470 470 470 470 470 470 470

23. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
factor value qty compound LInea1 LInea2 LInea3 LInea4 LInea5 LInea6 LInea7 LInea8 LInea9 LInea10 maxmin maxmin
product7 day 0 180 280 370 470 470 470 470 470 470
min 1 1200 7000 0.1714286 0 80 90 100 0.000365 0.000635
exp 1 1200 7000 0.1714286 0 100 100 110 0.000816 0.000553
max 1 1200 7000 0.1714286 0 110 105 115 0.000762 0.000519
FIFO 1 1200 7000 0.1714286 0 100 100 110 0.000762 0.000553
LIFO 1 1200 7000 0.1714286 0 100 100 110 0.000779 0.000553
urgent 1 1200 7000 0.1714286 0 100 100 110 0.000779 0.000553
product7 minmax 0 0.000659 0.000463 0.000364742 0 0 0 0 0 0L4
0 260 370 470 470 470 470 470 470 470
product8 day 0 0 0 50 100 140 140 140 140 140
min 1 4000 4000 1 0 50 50 40 0.007143 0.007143
exp 1 4000 4000 1 70 60 45 0.008333 0.005714
max 1 4000 4000 1 90 65 50 0.00625 0.004878
FIFO 1 4000 4000 1 70 60 45 0.00625 0.005714
LIFO 1 4000 4000 1 70 60 45 0.007143 0.005714
urgent 0.7 4000 4000 0.7 70 60 45 0.005 0.004000
product8 minmax 0 0 0.02 0.01 0.007143 0 0 0 0 0L5
0 0 50 100 140 140 140 140 140 140
factor value qty compound LInea1 LInea2 LInea3 LInea4 LInea5 LInea6 LInea7 LInea8 LInea9 LInea10 maxmin maxmin
product9 day 0 0 0 540 600 690 760 760 760 760
min 1 6000 30000 0.2 60 90 70 0 0 0.000263 0.000909
exp 1 6000 30000 0.2 100 110 90 0 0 0.001 0.000667
max 1 6000 30000 0.2 120 120 100 0 0 0.00087 0.000588
FIFO 1 6000 30000 0.2 100 100 90 0 0 0.000909 0.000690
LIFO 0.8 6000 30000 0.16 100 100 90 0 0 0.0008 0.000552
urgent 1 6000 30000 0.2 100 100 90 0 0 0.001 0.000690
product9 minmax 0 0 0 0.000333333 0.00029 0.000263158 0 0 0 0L6
0 0 0 600 690 760 760 760 760 760
product10 day 0 0 0 0 140 240 360 440 440 440
min 1 7000 10000 0.7 100 120 80 0 0 0.001591 0.002333
exp 1 7000 10000 0.7 120 120 90 0 0 0.002917 0.002121
max 1 7000 10000 0.7 130 120 100 0 0 0.0028 0.002000
FIFO 0.9 7000 10000 0.63 120 120 90 0 0 0.00252 0.001909
LIFO 1 7000 10000 0.7 120 120 90 0 0 0.002917 0.002121
urgent 1 7000 10000 0.7 120 120 90 0 0 0.002917 0.002121
product10 minmax 0 0 0 0 0.002917 0.001944444 0.001591 0 0 0L7
0 0 0 0 240 360 440 440 440 440

24. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
customer Order
ETD/ETA
Customer
Service
ETA/ETD/ETA
Procurement
Inventory
Control
Production
Planning &
SOH Allocation
WH Operations
ETD/ETA
Production
Operations
Start/Finish
Maintenance &
Machine Setting
Operations
Start/Finish
Transport
Operations
ETD/ETA
QC product-line
% scraps %
waste
Raw Materials
Suppliers

25. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
Product qty lit QC scraps QC waste WH SOH buy
Customer Order Water Melon 100,000 6% 2%
days order processing 1
ETA 1/10/2020
LDT days 28
EDT 29/10/2020
Procurement water melon 400,000 24,000 8,000 0 432,000
days Planning 1 days to supply w. melon 1
single machines 40 days in production 1
lit/w.melon/machine 0.25
sec/w.melon 5.25
lit/min 2.86 w.melon per min/machine 11.43
lit/hr 171.43 w.melon/hr/machine 686
hrs/day 16
lit/day 2,742.86 w.melon/day/machine 10,971
lit all machines/day 108,000 w.melon all machines/day 432,000
lit for customer order 99,360 hrs production all machines 15.75
invoicing & land transport 1
customs clearance outbound 3
sea transport shipment days 15
customs clearance inbound 3
land transport 1
download to wh 1
days in transportation 24
Total days to deliver order 28

26. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
Product qty pcs QC scraps QC waste WH SOH buy
Customer Order fungicida tank 1,000 2% 1%
days order processing 1
ETA 1/10/2020
LDT days 31
EDT 1/11/2020
Procurement water melon 4,000 80 40 150 3,970
4,120
days Planning 1 days to supply w. melon 1
single assembly machines
steps 4 days in production 4
tank component/machine step 0.25
sec per component/machine 120
component/min/machine 0.50 component per min 0.50
component/hr/machine 30 component/hr/machine 30
working hrs/day 8
component/day/machine step 240 component/day/machine 240
component all machines/day 960
component all
machines/day 960
components available 4,120
components for customer
order 4,000 fungicida tanks 1,000
invoicing & land transport 1
customs clearance outbound 3
sea transport shipment days 15
customs clearance inbound 3
land transport 1
download to wh 1
days in transportation 24
Total days to deliver order 31

27. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
customer Order
ETD/ETA
Customer Service
ETA/ETD/ETA
Procurement
Inventory Control
Production
Planning &
SOH Allocation
WH Operations
ETD/ETA
Production
Operations
Start/Finish
Maintenance &
Machine Setting
Operations
Start/Finish
Transport
Operations
ETD/ETA
QC product-line
% scraps % waste
Raw Materials
Suppliers
Customer Service
Demand Plan
Forecasting
Customer Service
Materials Supply
Chain LTD

28. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
month 6 month 5 month 4 month 3 month 2 month 1
product sales 180,000 200,000 150,000 130,000 120,000 120,000
1 1 2 2 3 3
W.Average 1,660,000 12 138,333 SOH QTY 155,000
S.Deviation 33,466 Outstanding O 0
U.limit 160,740 transit week 1 30000
L.limit 115,927 transit week 2 30000
transit week 3 50000
transit week 4 50000
high risk medium risk low risk 160,000
Alpha factor 0.3 0.2 0.1
Forecast 126,833 130,667 134,500 total Expected 315,000
customer order 100,000
Stock left 215,000
Triangle Ave=Demand 140,151 (U.limit + 4 x W.Ave + Forecast) / 6 coverage mths 1.53
coverage days 46
Supply Chain Days
P. Order 1 order week 6 40,185
Finance Aprove 3 order week 7 40,185
PO to supplier 1 order week 8 40,185
WH loading 3 order week 9 40,185
customs outbound 3 order week 10 27,130
sea transport 30 order week 11 27,130
customs inbound 2 New Oders 215,000
land transport 1
download WH 0
Total days to deliver 44

29. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
Product qty lit QC scraps QC waste
WH
SOH buy
Customer Order
Dairy
Product 100,000 6% 2%
days order processing 1
ETA 1/10/2020
LDT days 28
EDT 29/10/2020
Procurement Raw
Materials 400,00024,000 8,000 0 432,000
days Planning 1 days to supply w. melon 1
single machines 40 days in production 1
lit/dairy product/machine 0.25
sec/dairy product 5.25
lit/min 2.86
dairy product per
min/machine 11.43
lit/hr 171.43 dairy product/hr/machine 686
hrs/day 16
lit/day 2,742.86 dairy product/day/machine 10,971
lit all machines/day 108,000
dairy product all
machines/day 432,000
lit for customer order 99,360
hrs production all
machines 15.75
invoicing & land
transport 1
customs clearance
outbound 3
sea transport shipment
days 15
customs clearance
inbound 3
land transport 1
download to wh 1
days in transportation 24
Total days to deliver
order 28

30. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
CAL seasonal
Demand
NY seasonal
Demand
1.33 X 40' week
FFW CAL
Tuesday
FFW NY
Tuesday
WH CAL
WH NY
Saturday
Cold Storage
Thursday
Factory
Th-Sat
Mo-Wen
CAL SOH
CAL in Transit
CAL WH SOH
NY SOH
6 wks
seasonal
NY in Transit
NY WH SOH
SOH
Th-Sun
Mon-Wen
Throughput
qty
CAPACITY
Production
Requirement
qty
NJ C1
defreeze
HPP & stock
NJ C2
defreeze
HPP & stock
NJ C3
defreeze
HPP & stock
CAL C1
Defreeze
HPP & stock
CAL C2
defreeze
HPP & stock
CAL C3
defreeze
HPP & stock
Customer DC
CAL
Sales Demand
Customers DC
NJ
Sales Demand
Seasonality
availability
throughput
Packaging
Materials

31. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
Demand Process:
Every item is purchased, used or consumed based on multiple criteria's as perceived by the user/consumer benefits,
including total ownership cost, acceptance, popularity, performance vs expectations, easiness, flexibility, reliability, and
a great number of other consumer preferences attributes; and so, every item has a life cycle which can last for a short
time or a very extensive period of time
The life process of any item can be analyzed over time within an upper limit, a lower limit process boundaries, and an
average measured value, within the boundaries, indicating its performance. When the item performance fluctuates at
random, within the upper and lower process boundaries, we can say that the behavior within the process is under
control, on the other hand when the fluctuations are outside the upper and lower process boundaries, we say the
behavior is out of the process control
When the range between upper and lower limits boundaries is big statistically speaking, we can say the item behaves
unpredictable, when the range between boundaries is closed to the average value, we can say the item behaves very
predictable
There is also a series path which follows cycles, and the cycles are also predictable, these are translated as seasonality,
trend, and randomness factors from other non measured parameters affecting the item behavior, such as innovation
technology, marketing campaigns, design, packaging, pricing, and many others like company mergers, bankruptcy, new
market entry barriers, competitive advantages among companies and products
The important point here is to understand that an item demand behavior is part of the item life cycle process; which
lead us to use the concept from Statistical Process Control SPC where:
UL = average value + standard deviation/ square root of the N observations
LL = average value – standard deviation/ square root of the N observations
Where for a given N observations of an item Xi,….,N
We calculate its average value and it standard deviation
Then we can plot the Upper Limit boundary and the Lower Limit over a Period of time observations, and the item
Xi,…,N graph can be observed

32. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
Demand Trend or behavior: marketing events have a direct effect on each period, and so demand behavior
follows that collateral effect, for example a change on pack size, premium packing, sales discount, a change of
season, and many other factors will generate certain trend or behavior. In this respect a weighted average value
is better than an arithmetic average value, where the last 6 observations have more meaning; and so it is
calculated as: WA = (X6 + X5 + 2X4 + 2X3 + 3X2 + 3X1) / 12
Where X1 is the last new observation and X6 is the last 6th observation, and so in SPC we replace the plotting of
the average value by the weighted average value
UL= WA + standard deviation / square root of N
LL= WA – standard deviation / square root of N
Marketing Sales Forecast: is the figure provided by the expected sales for the coming period and can be
measured as follows:
Ratio of Accuracy = SUM(Xi,…,N) actual sales / SUM(Xi,…,N) marketing sales forecast figures
0 <= RA<= 1
Besides the provided marketing sales forecast figure, there is also the additional sales expected value due to
special marketing campaign events, or as a down effect due to last period campaign results and so this
adjustment is measured in % of +/- future sales for the coming forecasted period
DELPHI Method: within the forecasting process, there is room for discussion for each sales figure for each item
or group of items among the sales marketing team members, and/or the production-manufacturing and
procurement planning team members; reviewing the reliability of stocks supply, based on lead time & other
supply and production factors. This final reviewed figure is to be considered the minimum expected sales forecast

33. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
Sales Target Marketing Sales Forecast for the following period: with the 3 found forecast values, the
minimum sales forecast, the weighted average, the adjusted marketing sales forecast, we now proceed to
calculate what we call the marketing sales forecast target Tfo
Tfo = [ (minimum sales forecast value + 4{weighted average} + adjusted marketing sales forecast) / 6] *
(1+/-% adjustment for future
sales)
Inventory Planning: is based in the Upper Limit of our SPC using weighted average values UL>= Tfo
If Tfo>UL the inventory level should not be greater than <= UL + Alpha * standard deviation/square root N
Where Alpha = 0.1, 0.2, 0.3
Where 0.1 is for high risk and 0.3 is for moderate risk of getting over stocks
With the official sales target, then it follows to distribute the gross figure into all sales distribution channels &
territories as per their corresponding sales target share, or if within manufacturing, distribute the target sales
forecast among their customers portfolio share
Inventories then have to be planned & deployed as per the distribution points of the organization
This is the basic way to plan for the manufacturing-production inventories to support their marketing sales
counterpart, which is different from OEM customers sales orders placed and paid in advance by a letter of credit
or other financial instrument
Procurement planning, base their purchases based on the Demand Plan Inventories, considering existing stocks,
outstanding orders, and other redeployment of available stocks

34. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
Develop a Simulation tool to get quick answers to specific changes in parameters or variable values,
which are key components within the current running production lines machines performance
Such as break down and expected repair time; production process issues affecting the quality, such as
temperature, speed, pressure, and many more others
There could also be the issues related to shortages on energy, raw materials, packaging materials,
manpower, transportation
There are also unexpected high demand, cancellations or reduction in customer orders, change of product
and many other commercial situations affecting the production plan process

35. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT

36. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
Production planning Information Dash Board with Artificial Intelligence Computer System
Maintenance
Engineering
Production Line
Operations & QC
Planning Operations
& Customer Service
Materials & FG
Warehouse
Logistics
ID/OD Transport
Production
Process
Simulation
Production Line
Information
Real Time
Maintenance
Information
Real Time
Materials
Information
Real Time
Forklift
Information
Real Time
Optimization
Algorithms
RM shortage %
RM quality stop time
Energy supply stop time
Manpower shortage %
Packaging shortage %
Storage shortage %
Water supply stop time
line quality stop time
Machine breakdown time
Start line delay time
WIP transport delay time
PLC/SCADA down time
Increase/reduce speed
Increase/reduce qty
CAPACITY << / >> qty
Close/open capacity qty
Repairs time start/finish
Repairs time start/finish
Repairs time start/finish
Repairs time start/finish
delivery start/finish
Change RM start/finish
delivery start/finish
WH ready start/finish
delivery start/finish
Maintenance start/finish
Maintenance start/finish
Maintenance start/finish
Maintenance start/finish
delivery start/finish delivery start/finish
Optimize
consolidate
Inventory SOH
WH locations
Update
KANBAN ticket #
line # WI ref #
Customer #
product #
Calculate queue
IN/OUT machines
production time
Simulate which
sequence has
the lowest queue
IN / OUT time
KANBAN ticket #
Line # WI ref #
Customer Order #
product #
production
schedule
KANBAN ticket # WI
ref # Customer Order #
product # line #
schedule Optimize
materials handling
transportation vehicle
route schedule
Production
Materials product
Demand
Planning,
Forecast
Spoils %
Scraps %
Waste %
Re-works %
delivery start/finish delivery start/finish
delivery start/finish delivery start/finish
delivery start/finish delivery start/finish
delivery start/finish delivery start/finish

37. ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT
Database
AI ApplicationPlanner
Dash Board
Production
Maintenance Warehouse
Transporation
ERP
Management
Dash Board
Planning
Quality
Customer Service
ProcurementFinance &
Accounting

38. Thank You
L | C | LOGISTICS
PLANT MANUFACTURING AND BUILDING FACILITIES EQUIPMENT
Engineering-Book
ENGINEERING FUNDAMENTALS AND HOW IT WORKS
ARTIFICIAL INTELLIGENCE ALGORITHMS & PROCESS IN MANUFACTURING OPERATIONS MANAGEMENT