FUZZY LOGIC APPROACH FOR

MINING ENGINEERING

MARLIANTONI
DEPARTEMENT OF MINING ENGINEERING
UNIVERSITAS MUARA BUNGO
OUTLINES
Introduction To Fuzzy Logic

GIS-Based Multi Criteria Decision Analysis

(MCDA)
Case Study
INTRODUCTION TO FUZZY LOGIC
 Fuzzy Logic

 Fuzzy logic is a form of many-valued logic in which the truth

values of variables may be any real number between 0 and 1
both inclusive.
 It is employed to handle the concept of partial truth, where the
truth value may range between completely true and
completely false.
 By contrast, in Boolean logic, the truth values of variables may
only be the integer values 0 or 1.
 Fuzzy Logic

 The term fuzzy logic was introduced with the 1965 proposal of
fuzzy set theory by Lotfi Zadeh.
 Fuzzy logic is based on the observation that people make
decisions based on imprecise and non-numerical information.
 Fuzzy models or sets are mathematical means of representing
vagueness and imprecise information (hence the term fuzzy).
 Fuzzy Logic

 These models have the capability of recognising, representing,

manipulating, interpreting, and utilising data and information
that are vague and lack certainty.
 Fuzzy logic has been applied to many fields, from control
theory to artificial intelligence.
A non spatial example comparing Boolean
logic with fuzzy logic. In Boolean logic, truth
is “crisp,” zero or one. In fuzzy logic, truth has
degrees between zero and one. Fuzzy tallness
and fuzzy oldness are the membership in the
concepts tallness and oldness.
Boolean tallness and Boolean oldness are
binary memberships in these concepts. Thus
in Boolean logic, a person is either tall or not;
whereas in fuzzy logic, a person can be
somewhat tall. The operators AND and OR
are used for combining evidence in both
methods.
A spatial example comparing
Boolean logic with fuzzy logic.

8
 Fuzzy Logic

Process :
 Fuzzify all input values into fuzzy membership functions.
 Execute all applicable rules in the rule base to compute the
fuzzy output functions.
 De-fuzzify the fuzzy output functions to get "crisp" output
values
 Fuzzy Logic

Fuzzification
 Fuzzification is the process of assigning the numerical input of a system to
fuzzy sets with some degree of membership. This degree of membership
may be anywhere within the interval [0,1].
 If it is 0 then the value does not belong to the given fuzzy set, and if it is 1
then the value completely belongs within the fuzzy set. Any value between
0 and 1 represents the degree of uncertainty that the value belongs in the
set.
 These fuzzy sets are typically described by words, and so by assigning the
system input to fuzzy sets, we can reason with it in a linguistically natural
manner.
 Fuzzy Logic

Linear
 Fuzzy Logic

Triangular Shoulder
 Fuzzy Logic

For example, in the image below the meanings of the expressions cold, warm, and hot are represented by
functions mapping a temperature scale.

The vertical line in the image represents a particular temperature that the three arrows (truth values) gauge.
Since the red arrow points to zero, this temperature may be interpreted as "not hot"; i.e. this temperature has
zero membership in the fuzzy set "hot". The orange arrow (pointing at 0.2) may describe it as "slightly warm"
and the blue arrow (pointing at 0.8) "fairly cold". Therefore, this temperature has 0.2 membership in the fuzzy
set "warm" and 0.8 membership in the fuzzy set "cold". The degree of membership assigned for each fuzzy set
is the result of fuzzification.
 Fuzzy Logic

Fuzzy Rule
Fuzzy rules are used within fuzzy logic systems to infer an output based on input variables. Modus ponens
and modus tollens are the most important rules of inference. A modus ponens rule is in the form
Premise: x is A
Implication: IF x is A THEN y is B
Consequent: y is B
In crisp logic, the premise x is A can only be true or false. However, in a fuzzy rule, the premise x is A and
the consequent y is B can be true to a degree, instead of entirely true or entirely false. This is achieved by
representing the linguistic variables A and B using fuzzy sets. In a fuzzy rule, modus ponens is extended to
generalised modus ponens:
Premise: x is A*
Implication: IF x is A THEN y is B
Consequent: y is B*
The key difference is that the premise x is A can be only partially true. As a result, the consequent y is B is
also partially true. Truth is represented as a real number between 0 and 1, where 0 is false and 1 is true.
GIS-BASED MULTI CRITERIA DECISION

ANALYSIS (MCDA)
 GIS-Based Multi Criteria
Decision Analysis (MCDA)

• Steps
 Define The Problem And Set The Goal
GOAL
 Determine The Criteria (Factors And
Constraints)
 Standardize The Factors (Criterion
Scores)
Factor 1 Factor 2 Factor 3 Constraints
 Determine The Weight Of Each Factor
 Aggregate The Criteria
Attributes Attributes Attributes Attributes
 Validate/Verify The Result
 GIS-Based Multi Criteria
Decision Analysis (MCDA)

• Steps As a general rule, a goal must be:

 Define The Problem And Set The Goal S - Specific
 Determine The Criteria (Factors And M - Measurable
A - Attainable
Constraints)
R - Relevant
 Standardize The Factors (Criterion Scores) T - Time Bound
 Determine The Weight Of Each Factor
 Aggregate The Criteria
 Validate/Verify The Result
 GIS-Based Multi Criteria
Decision Analysis (MCDA)

 How much details are needed in the

• Steps analysis affects the set of criteria to be
 Define The Problem And Set The Goal used
i.e. main roads only vs. including minor
 Determine The Criteria (Factors And roads; no. of houses vs. no. of residents;
Constraints) etc.
 Standardize The Factors (Criterion Scores)  Criteria should be measurable
 If not determinable, use
 Determine The Weight Of Each Factor
proxies
 Aggregate The Criteria i.e. slope stability can be represented by
 Validate/Verify The Result slope gradient
 GIS-Based Multi Criteria
Decision Analysis (MCDA)

Fuzzy Membership Functions are used to

• Steps standardize the criterion scores.
 Define The Problem And Set The Goal Steps :
 Determine The Criteria (Factors And  Reclassify
 Fuzzy membership functions
Constraints)
 Standardize The Factors (Criterion
Scores)
 Determine The Weight Of Each Factor
 Aggregate The Criteria
 Validate/Verify The Result
 GIS-Based Multi Criteria
Decision Analysis (MCDA)

Determine the weight of each factor (Using AHP)

• Steps Steps :
 Compare the factors
 Define The Problem And Set The Goal
 Complete the matrix
 Determine The Criteria (Factors And  Normalization and weight determination
Constraints)  Calculate the Consistency Ratio (CR)
 Standardize The Factors (Criterion Scores)
 Determine The Weight Of Each Factor
 Aggregate The Criteria
 Validate/Verify The Result
 GIS-Based Multi Criteria
Decision Analysis (MCDA)
Compare the factors Complete the matrix

Basic rules:
 If the judgment value is on the left side of 1, we put
the actual judgment value.
 If the judgment value is on the right side of 1, we put
the reciprocal value
 GIS-Based Multi Criteria
Decision Analysis (MCDA)
Normalization and weight determination Calculate the Consistency Ratio (CR)
CR = Consistency index (CI)/Random Consistency Index (RI)
 CI = (λ max – n)/n – 1
 λ max is the Principal Eigen Value; n is the number of
factors
 λ max = ∑ of the products between each element of the
priority vector and column totals.

  λ max = (1.44*0.67) + (15*0.06) + (4.20*0.27) = 3.0445

 CI = (3.0445 – 3)/3-1 CI = 0.0445/2 CI = 0.0222
 To normalize the values, divide the cell  CR = 0.0222/0.58 CR = 0.04 < 0.10 (Acceptable)
value by its column total.
 To calculate the priority vector or
weight, determine the mean value of
the rows.
 GIS-Based Multi Criteria
Decision Analysis (MCDA)

Aggregate The Criteria (Using Weighted Linear

• Steps Combination)
 Define The Problem And Set The Goal Weighted Linear Combination is the most
commonly used decision rule :
 Determine The Criteria (Factors And
Constraints)
 Standardize The Factors (Criterion Scores) Where:
S : is the composite suitability score
 Determine The Weight Of Each Factor
Xi : factor scores (cells)
 Aggregate The Criteria Wi : weights assigned to each factor
 Validate/Verify The Result Cj : constraints (or Boolean factors)
∑ : sum of weighted factors
∏ : product of constraints (1-suitable, 0-
unsuitable)
CASE STUDY
 CASE STUDY

1. Decision Support System (Case Study : Safety Campaign)

2. Integration Of GIS Modeling With Multi Criteria Decision Analysis (MCDA) For Land
Optimization Of Post-Mining On Coal Mine In Jambi Province : A Case Study Of PT XYZ
 CASE STUDY

• Decision Support System (Case Study : Health & Safety Program)

 CASE STUDY

• Decision Support System (Case Study : Health & Safety Program)

 CASE STUDY

• Decision Support System (Case Study : Health & Safety Program)

CASE STUDY
 CASE STUDY

• Suitability Post-Mining Land Use For Conservation

Conservation

Distance To Distance To Distance To

Slope Rain Fall
Main Road Settlement River
 CASE STUDY

DEM Slope
Elevation Slope (%)
Input DEM

Convert To Slope

Reclassify

Fuzzy Linear
Membership
Function
 CASE STUDY

Reclass Slope Fuzzification

Score Fuzziness
Slope Score Fuzziness
(%)
0–8 5 1
8 – 15 4 0.75
15 – 25 3 0.5
25 -45 2 0.25
>45 1 0
 CASE STUDY

Constraints Factor Distance To Settlement Rain Fall

Distance To Boolean
Main Road Logic
(Km)
Fuzziness

Fuzziness
0-5 0
>5 1

Distance To Boolean
River (Km) Logic
0-5 0
>5 1
 CASE STUDY

Suitability Post-Mining Land Use For Conservation Suitability

Factor Weight Suitability Value

Slope 30 High 61 - 100
Rainfall 40 Medium 41 - 60
Distance To 30 Low 0 - 40
Settlement

Suitability = ((SlopeFuzziness * 30)+(Rainfall*40)+(Settlement*30))*Cons

THANK YOU

35