An Improvement of decision making for project risk assessment using the fuzzy logic concept
This thesis proposes an improved decision-making approach for project risk assessment by applying fuzzy logic concepts. It aims to enhance accuracy and reliability in evaluating risks, with a particular focus on complex projects such as solar energy initiatives.
Northwestern Polytechnical University
School of management
西北工业大学硕士学位论文
A thesis dissertation submitted in Partial fulfilment of the requirement for the degree of
Master of Project Management
At
School of management,
Northwestern polytechnical University
Title:
An Improvement of decision making for project risk assessment using the fuzzy logic concept
By
Bouba Oumarou Aboubakar
Supervisor：
Dr. Fang Wei
Xi’an, P.R.China
December, 2015
Acknowledgement
First of all, I would like to thank both the Chinese Scholarship Council and Cameroon’s Government, for giving me this bilateral scholarship to come here at Northwestern Polytechnical University, in the international and Management Colleges to peruse my Studies.
Then, I would like to offer my sincerest gratitude to my supervisor, Dr. FANG WEI , for giving me the opportunity to carry out my graduate study at Northwestern Polytechnical University and to work under his supervision.
His encouragement, guidance and support throughout all stages of the thesis process enabled me
To conduct the research and finalized this thesis. I am indebted to him more than he
Realizes, without his support, I would not be able to complete this program.
Moreover, I would like to show my appreciation to my family and friends, whose love and reassurance allowed me to do my best in school and encouraged me through the entire difficult path in my academic journey.
Finally, I should acknowledge all faculties of NWPU which were part of my education program, namely, Dr Sun Wubin, Dr Yuming Zhu, and Dr Keqin Wang… I offer my regards to everyone who has been a part of this journey and has supported me in any respect during the completion of my study.
Thanks God,
Thanks, to all of you…!
Table of Contents
Abstract. II
Table of Contents IV
List of Figures VII
List of Tables. IX
1.INTRODUCTION1
1.1.Motivation1
1.2.Research Questions2
1.3.Purpose of the study2
1.4.Research Contributions2
1.5.Thesis structure3
2.LITTERATURE REVIEW4
2.1.Project risk management framework4
2.1.1.Risk definition and principles4
2.1.2.Concept of Project risk management5
2.1.3.Risk management benefits7
2.1.4.Purpose of Project risk assessment7
2.1.4.1.Quantitative methods8
2.1.4.2.Qualitative methods9
2.2.Fuzzy logic theory and systems13
2.2.1.Introduction to fuzzy logic13
2.2.2.Fuzzification16
2.2.3.Inference process16
2.2.4.Defuzzification17
2.2.5.Fuzzy logic advantages and limits in PRA19
2.3.Fuzzy Risk assessment and decision making20
3.CURRENT APPROACHES FOR DECISION MAKING IN SOLAR ENERGY PROJECT RISK ASSESSMENT22
3.1.General situation of solar energy risk assessment22
3.2.Current approaches for decision making24
3.2.1.Influence Diagram methods25
3.2.2.Value risk analysis with a Monte Carlo simulation26
3.3.Limitation analysis28
4.AN IMPROVED FUZZY MODEL FOR PROJECT RISK ASSESSMENT30
4.1.A brief Summary of the proposed Approach30
4.2.Step 1: Establish a risk assessment group32
4.3.Step 2: Preliminary Step32
4.3.1.Problem Analysis32
4.3.2.Task allocation33
4.3.3.Use of experience data33
4.3.4.Risk identification34
4.3.5.Risk classification39
4.3.6.Construction of a risk brake down structure40
4.4.Step 3: Risk level measurement42
4.4.1.Measure the risk factors function level43
4.4.2.Risk ranking43
4.4.3.Evaluate low effect risks44
4.5.Step4: Fuzzy Inference Step44
4.5.1.Experts Opinion45
4.5.2.Determine the membership functions45
4.5.3.Determine the Inference rules46
4.5.4.Input the calculated value47
4.5.5.Fuzzification Interface47
4.5.6.Fuzzy inference48
4.5.7.Defuzzification Interface49
4.6.Step 5: Final risk level and Interpretation49
4.6.1.Final risk level49
4.6.2.Explanations50
4.7.Step 6: Advices step51
4.7.1.Recommendation for acceptance51
4.7.2.Redirection to risk control for modification51
5.IMPLEMENTATION AND CASE STUDY53
5.1.Implementation of the model: the software tool53
5.1.1.Objectives53
5.1.2.System architecture and program sequence53
5.1.3.Challenges and coding environment55
5.1.4.Installing55
5.1.5.Presentation of the interfaces56
5.2.Case study: OUARZAZATE SOLAR COMPLEX PROJECT60
5.2.1.Project description60
5.2.2.STEP 1: Establish a risk assessment group61
5.2.3.STEP 2: Preliminary Step62
5.2.4.THE MATLAB TOOLS FOR THE STEPS 3, 4, 567
5.2.5.Step 3: Risk level measurement71
5.2.6.Step4: Fuzzy Inference Step76
5.2.7.Step 5: Final risk level and Interpretation80
5.2.8.Step 6: Advices step81
5.3.Serat evaluation of steps 3,4,582
6.VALIDATION AND DISCUSSION84
6.1.Sensitivity analysis of the model84
6.2.Validation survey85
6.3.Discussion87
7.CONCLUSION89
8.REFERENCES90
9. ANNEX
List of figures
Figure 1.1: the outline of the thesis3
Figure 2.1: The process of managing risks (Smith et al. 2006)6
Figure 2.2: Fuzzy membership functions14
Figure 2.3: Demonstrating membership levels15
Figure 2.4: Fuzzy inference system: source (Shin Y. C. and Xu C. 2009).16
Figure 2.5: Defuzzification by centroid method17
Figure 2.6: Overall fuzzy inference process source: (simulink fuzzy logic toolbox)18
Figure 2.7: Fuzzy decision making process20
Figure 2.8: Basic architecture of an Expert System source (L. Nunes and Mario S., 2012)21
Figure 3.1: Risks perceived as being most serious by investors (n = 18). Source: (Komendantova N, Patt AG, Barras L, Battaglini, 2009)24
Figure 3.2: Influence diagram, the decision of investing in a PV project26
Figure 3.3: Risk premium for an investment project (VAR = 0).28
Figure 4.1: The proposed Approach……………………………………………………………..…….31
Figure 4.2: Risk rating factors38
Figure 4.3: General structure of the risk breakdown structure41
Figure 4.4: Basic Hierarchical architecture for risk groups42
Figure 4.5: Risk factor evaluation43
Figure 4.6: Fuzzy membership triangular functions (source Ebrahimnejad, Mousavi, and Seyrafianpour 2010)46
Figure 4.7: final Risk level Decision52
Figure 5.1: SERAT system architecture54
Figure 5.2: Application Installation55
Figure 5.3: The home welcoming interface56
Figure 5.4: Information about the SERAT57
Figure 5.5: steps of computing the final risk level57
Figure 5.6: Authors information58
Figure 5.7: Starting a new project evaluation58
Figure 5.8: Project manager’s basic information58
Figure 5.9: Project evaluation interface59
Figure 5.10: risk breakdown structure66
Figure 5.11: Fuzzy inference editor67
Figure 5.12: MFE overview: severity variable68
Figure 5.13: Rule editor69
Figure 5.14: Rule Viewer70
Figure 5.15: Surface Viewer71
Figure 5.16: risk factor level calculation for R2073
Figure 5.17: Membership functions for the variable “likelihood”73
Figure 5.18: Membership functions for the variable “severity”74
Figure 5.19: Membership functions for the output “risk factor”74
Figure 5.20: Rules viewer for the risk function evaluation75
Figure 5.21: risk subsection histogram75
Figure 5.22: membership functions for a fuzzy bloc with two entries77
Figure 5.23: The seven membership functions for a given risk level output77
Figure 5.24: Fuzzy rules for a risk bloc of two inputs78
Figure 5.25: Input of the time delay risks into the next step78
Figure 5.26: Reception of the calculated values in the next levels79
Figure 5.27: Final risk level80
Figure 5.28: Acceptance scheme82
Figure 5.29: Application of the method using SERAT83
Figure 6.1: sensitivity analysis85
List of Tables
Table 2.1: rating impact for a risk source (PMI 2004)11
Table 2.2: Probability-Impact risk matrix (source PMBOOK)12
Table 4.1: Respondents age and experience36
Table 4.2: Respondents geographical repartition36
Table 4.3: Respondents study level36
Table 4.4: Risk factors appreciation level37
Table 4.5: Risk categories rates38
Table 4.6: The relation between linguistic variables and triangular fuzzy numbers46
Table 4.7: fuzzy control rules47
Table 5.1: Project Components60
Table 5.2: Project financing sources (in Million EUR)61
Table 5.3: Identified sources of hazards for the selected project.65
Table 5.4: Risk classification65
Table 5.5: Risk register72
Table 6.1: Sensitivity analysis84
Table 6.2: model validity results86