Professional Documents
Culture Documents
Journal of Offshore Mechanics and Arctic Engineering NOVEMBER 2009, Vol. 131 / 041101-1
Copyright © 2009 by ASME
冦 冧
The idea of using fuzzy numbers to replace crisp numbers in 0x if P f 共A兲 ⴰ P f 共B兲 ⱕ 0x
Bayesian inference was proposed by Furthsirth-Schnater 关11兴 and = P f 共A兲 ⴰ P f 共b兲 if 0x ⱕ P f 共A兲 ⴰ P f 共B兲 ⱕ 1x
Halliwell and Shen 关30兴. To fit fuzzy numbers into the axiomatic
basis of probability theory, they defined “Bayesian fuzzy probabil- 1x if P f 共A兲 ⴰ P f 共B兲 ⱖ 1x
ity” as convex, normal fuzzy set of 关0,1兴. Using a new terminol-
ogy “subsumption,” they relaxed complementation law to extend In the above, 共⍀ , , P f 兲 is termed as a fuzzy probability space.
a partially defined linguistic probability measure. Their method “䊊” is denoted as one of the fuzzy number arithmetic operations,
has been successfully used in forensic statistics 关12兴. i.e., addition, subtraction, multiplication, and division. To distin-
In summary, on one hand, safety assessment and risk analysis guish fuzzy number arithmetic operations from classical arith-
should cover areas where it is difficult to apply traditional safety metic operations, “ 丣 ” and “ 丢 ” are used to denote fuzzy addition
assessment techniques. Lack of reliable safety data and lack of and multiplication, respectively. It should be noted that 1x stands
confidence in safety assessment have been two major challenges for a fuzzy subset of real number 1 and 0x stands for a fuzzy
in safety analysis of various engineering activities. On the other subset of real number 0.
hand, the existing algorithms capable of dealing with fuzzy and Based on the above four axioms, four fuzzy Bayesian rules can
judgmental variables are computationally complicated and time be defined to support a FBN model.
consuming in parameter estimation. So far few work has been
reported in offshore safety analysis in finding a right balance be- Fuzzy conditional independence
tween the above two issues. To solve such problems, this paper n
proposes a novel and flexible FBN method for dealing with un-
certainty including vagueness and randomness in offshore risk
P f 共X1,X2, . . . ,Xn兲 ⬵ 兿 P 共X 兩parents共X 兲兲
i=1
f i i 共1兲
3 Fuzzy Bayesian Network Model and Risk Analysis Fuzzy Bayesian rule
Diagram
P f 共X = xi兲 · P f 共Y = y j兩X = xi兲
P f 共X = xi兩Y = y j兲 ⬵ 共4兲
3.1 Fuzzy Probability Measure and FBN Model. A classi- P f 共Y = y j兲
cal BN is a pair N = 兵共V , E兲 , P其, where V and E are the nodes and
To distinguish fuzzy probability equations from conventional
the edges of a directed acyclic graph 共DAG兲, respectively, and P
equations, “⬵” is used instead of “=.” Using the above equations,
is a probability distribution over V. Discrete random variables V
fuzzy BN inference can be conducted.
= 兵X1 ; X2 ; . . . ; Xn其 are assigned to the nodes while the edges E
represent the causal probabilistic relationship among the nodes. 3.2 FBN Based Risk Analysis Flow Diagram. There is a
Each node in the network is annotated with a conditional prob- need for a generic FBN based offshore risk analysis flow diagram
ability table 共CPT兲 that represents the conditional probability of to be developed. In the flow diagram, offshore system hazards
the variable given the values of its parents in the graph. The CPT identification, and FBN inference should be dealt with in an inte-
contains, for each possible value of the variable associated with a grated manner. The flow diagram should include all processes in
node, all the conditional probabilities with respect to all the com- FBN inference and may provide a basis for the further develop-
binations of values of the variables associated with the parent ment of a generic offshore risk analysis framework. The proposed
nodes. For nodes that have no parents, the corresponding table flow diagram is suggested and depicted in Fig. 1. It outlines the
will simply contain the prior probabilities for that variable. The necessary steps required for risk analysis in a holistic way sup-
principles behind BN are Bayesian statistics and concentrate on ported by FBN. It is a guideline in carrying out cause-and-effect
Journal of Offshore Mechanics and Arctic Engineering NOVEMBER 2009, Vol. 131 / 041101-3
inference based on subjective judgments and thus provides a logi- able data included in regulatory rules and standards, data-
cal solution as it emulates the human reasoning process through bases and data networks, and, if necessary, also from simu-
forward/backward propagating within a specific domain of knowl- lations and experiments into the network structure.
edge, codes, and standards based on the company’s policy using a • Specify states and assign input values for the fuzzy condi-
FBN approach. tional probability table 共FCPT兲 of each variable 共node兲.
The proposed flow diagram consists of two major components. • Update the values of all nodes by calculating posterior prob-
Particularly, the FBN module describes the steps in Bayesian in- abilities via the four Bayesian equations 共i.e., Eqs. 共1兲–共4兲兲
ference and serves as integration interface of information that is when new information is available.
mainly caused by randomness and vagueness. This makes the flow • Interpret the causal relationships and provide the generated
diagram more functional and more effective to amalgamate safety results for approximate reasoning based safety synthesis.
of an offshore engineering system. The major steps of the compo-
nents used in the flow diagram are outlined as follows. 4 Case Study: Collision Risk of FPSO and Authorized
Component 1. Problem definition and potential failure identifi- Vessels
cation.
Human errors are the causes of many well-known major inci-
• Identify all anticipated causes/factors to potential failures of dents such as the loss of Piper Alpha tragedy. According to the
an offshore engineering system. Particular attention must be P&I Club studies into accidents and claims, approximately 80% of
paid to causal relationships among those anticipated causes/ maritime accidents are attributable to human errors 关32兴. Under-
factors. standing human errors and system failures is particularly impor-
• Define variables 共nodes兲 to represent the identified potential tant with respect to offshore installations. In this section, a case
failures. study of the collision risk between a FPSO unit and the authorized
vessels due to human errors during a tandem offloading operation
Component 2. Development of a FBN model. is addressed to illustrate the application of the proposed FBN
model. The analysis process follows the diagram proposed in Sec.
• Construct a BN structure from a generated list of identified 3 共see Fig. 1兲.
hazards specific to the problem under investigation.
• Select the types of fuzzy membership function used to de- 4.1 General Description and BN Model Establishment. A
lineate variables 共nodes兲 and provide interpretation for each FPSO unit is one of the most popular floating systems used by the
fuzzy set of each variable 共node兲. offshore oil and gas industry. In the UK, crude oil from a FPSO is
• Integrate domain specific knowledge obtained from avail- normally transported to shore using shuttle tankers specially de-
X P f 共X兲
x1 共0.39,0.4,0.41兲
x2 共0.59,0.6,0.61兲
Journal of Offshore Mechanics and Arctic Engineering NOVEMBER 2009, Vol. 131 / 041101-5
U P f 共W = w1 兩 U兲 P f 共W = w2 兩 U兲
= P f 共X = x1 ;Y = y 1 ;Z = z2兲 丣 P f 共X = x2 ;Y = y 1 ;Z = z2兲
u1 共0.740,0.750,0.760兲 共0.240,0.250,0.260兲 丣 P f 共X = x1 ;Y = y 2 ;Z = z2兲
u2 共0.001,0.002,0.003兲 共0.997,0.998,0.999兲
丣 P f 共X = x2 ;Y = y 2 ;Z = z2兲
P f 共U = u1兲 ⬵ 兺 P 共Z;V;U = u 兲
Z,V
f 1
= P f 共Z = z1 ;V = v1 ;U = u1兲 丣 P f 共Z = z2 ;V = v1 ;U = u1兲
丣 P f 共Z = z1 ;V = v2 ;U = u1兲
丣 P f 共Z = z2 ;V = v2 ;U = u1兲
= 共0.1103,0.1307,0.1534兲
P f 共U = u2兲 ⬵ 兺 P 共Z;V;U = u 兲
Z,V
f 2
= P f 共Z = z1 ;V = v1 ;U = u2兲 丣 P f 共Z = z2 ;V = v1 ;U = u2兲
丣 P f 共Z = z1 ;V = v2 ;U = u2兲
丣 P f 共Z = z2 ;V = v2 ;U = u2兲
Fig. 3 Prior fuzzy probability: Pf„X = x1… and posterior fuzzy
= 共0.7936,0.8693,0.9507兲 probability: Pf„X = x1 円 W = w1…
For node W,
P f 共W = w1兲 ⬵ 兺 P 共U;W = w 兲
f 1 fuzzy number 共0.3233,0.4614,0.6626兲, is represented by a solid
U curve, while the prior probability 共fuzzy number 共0.39,0.4,0.41兲兲
= P f 共U = u1 ;W = w1兲 丣 P f 共U = u2 ;W = w1兲 is represented by a dashed curve.
Comparing the posterior probability P f 共X = x1 兩 W = w1兲
= P f 共U = u1兲 丢 P f 共W = w1兩U = u1兲 丣 P f 共U = u2兲 = 共0.3233, 0.4614, 0.6626兲 with prior fuzzy probability P f 共X = x1兲
丢 P f 共W = w1兩U = u2兲 = 共0.39, 0.4, 0.41兲, it can be seen that there is a significant change
in the occurrence likelihood of human errors when a personnel
= 共0.0824,0.0997,0.1194兲 injury/loss accident has been observed. In fact, the most likely
value of fuzzy number P f 共X = x1兲 = 共0.39, 0.4, 0.41兲 is 0.4, while
P f 共W = w2兲 ⬵ 兺 P 共U;W = w 兲
f 2 the most likely value of fuzzy number P f 共X = x1 兩 W = w1兲
U = 共0.3233, 0.4614, 0.6626兲 is 0.4614. The lower and upper least
= P f 共U = u1 ;W = w2兲 丣 P f 共U = u2 ;W = w2兲 likely values of fuzzy number P f 共X = x1兲 = 共0.39, 0.4, 0.41兲 are 0.39
and 0.41, respectively, while the lower and upper least likely val-
= P f 共U = u1兲 丢 P f 共W = w2兩U = u1兲 ues of fuzzy number P f 共X = x1 兩 W = w1兲 = 共0.3233, 0.4614, 0.6626兲
丣 P f 共U = u2兲 丢 P f 共W = w2兩U = u2兲 are 0.3233 and 0.6626, respectively. This suggests that the poste-
rior probability changed significantly. This might imply that node
= 共0.8177,0.9003,0.9896兲 personnel injury/loss is quite sensitive to node human errors, that
What is really of interest, however, is how the prior probabilities is, once a personnel injury/loss accident caused by collision of
change when new observations are added into the BN for a par- FPSO is observed, it is more likely that human errors during op-
ticular node. Suppose it is observed that there is human injury, and eration are the causes. To further justify the conclusion, sensitivity
it is required to inference to what degree this human injury was analysis must be conducted.
caused by human errors during operations. This needs to calculate Sensitivity refers to how sensitive a model’s performance is to
posterior probability P f 共X = x1 兩 W = w1兲. Using Bayesian rule equa- minor changes in the input parameters. Sensitivity analysis is par-
tion 共4兲, the relevant calculation is ticularly useful in investigating the effects of inaccuracies or in-
completeness in the parameters of a FBN model on the model’s
P f 共X = x1 ;W = w1兲 output. The most natural way of performing sensitivity analysis is
P f 共X = x1兩W = w1兲 ⬵ to change the values of the parameters and then, using an evidence
P f 共W = w1兲
propagation method, monitor the effects of these changes on the
Therefore P f 共X = x1 ; W = w1兲 is calculated first 共the detailed calcu- posterior probabilities. In this case study, the preliminary conclu-
lation can be seen in Appendix C兲: sion 共i.e., node personnel injury/loss is quite sensitive to node
P f 共X = x1 ;W = w1兲 ⬵ 共0.0386,0.0461,0.0546兲 human errors兲 is drawn based on posterior probabilities, e.g.,
P f 共X = x1 兩 W = w1兲. Thus one of the most important sensitivity
Thus, analysis aspects is to analyze how they change when prior prob-
P f 共X = x1 ;W = w1兲 abilities take different values. Without loss of generality, P f 共X
P f 共X = x1兩W = w1兲 ⬵ = x1兲 takes eight different values, ranging from 共0.14,0.15,0.16兲 to
P f 共W = w1兲
共0.49,0.50,0.51兲 共see Table 7兲. A MATLAB calculation program has
共0.0386,0.0461,0.0546兲 been developed to implement the FBN inference. The results in
= Table 7 were generated using the program and graphically shown
共0.0824,0.0997,0.1194兲
in Fig. 4. As can be seen in Table 7, the values in the second and
= 共0.3233,0.4614,0.6626兲 third columns indicate that P f 共X = x1 兩 W = w1兲 clearly changes with
In fact, the above result is achieved using Eq. 共A4兲 共see Appendix P f 共X = x1兲. Figure 4 also shows a positively increasing trend in the
A兲. Note that 共0.0386,0.0461,0.0546兲 and 共0.0824,0.0997,0.1194兲 posterior probability when P f 共X = x1兲 steadily increases. Therefore
are two fuzzy numbers, and 共0.0824,0.0997,0.1194兲 does not con- there is a reason to believe that the above conclusion is reliable.
tain 0. Therefore using Eq. 共A4兲, the above posterior probability To reduce computational complexity and obtain significant sav-
can be obtained. As shown in Fig. 3, the posterior probability, i.e., ings in computation time, a MATLAB program has been developed.
Journal of Offshore Mechanics and Arctic Engineering NOVEMBER 2009, Vol. 131 / 041101-7
1 共0.14,0.15,0.16兲 共0.1182,0.1852,0.2847兲
2 共0.19,0.20,0.21兲 共0.1602,0.2493,0.3669兲
3 共0.24,0.25,0.26兲 共0.2019,0.3004,0.4468兲
4 共0.29,0.30,0.31兲 共0.2417,0.3529,0.5245兲
5 共0.34,0.35,0.36兲 共0.2817,0.4093,0.5959兲
6 共0.39,0.40,0.41兲 共0.3233,0.4614,0.6626兲
7 共0.44,0.45,0.46兲 共0.3578,0.5091,0.7400兲
8 共0.49,0.50,0.51兲 共0.3955,0.5634,0.8092兲
given in Tables 1–6 are simplified as crisp numbers, that is, fuzzy =
P共W = w1兲
numbers are replaced by their most likely values. Fuzzy probabil-
ity P f 共X = x1兲 = 共0.39, 0.4, 0.41兲, for example, is replaced by crisp = 46.21%
probability P共X = x1兲 = 0.4. The bold fonts in the bodies of Tables To save computation time, this result can be obtained using HUGIN
1, 2, and 4 are the prior probabilities of nodes X, Y and V, respec- software. For example, marginal probabilities of all the nodes and
tively. The bold fonts in the bodies of Tables 3, 5, and 6 are the posterior probabilities can be seen in Figs. 5 and 6. Comparing
the above result 共P共X = x1 兩 W = w1兲 = 46.21%兲 with prior probabil- Appendix A: Fuzzy Set, Fuzzy Numbers, and Their Op-
ity 共P f 共X = x1兲 = 40%, as shown in Table 1 using bold font in the erations
second row and second column兲, it is obvious that there is a sig-
Fuzzy sets were derived from generalizing the concept of set
nificant change between the posterior probability and prior prob-
theory. Fuzzy sets can be thought of as an extension of classical
ability. This suggests that node personnel injury/loss is related to
sets. In a classical set or crisp set, the objects in a set are called
node human errors. This result is consistent with that obtained
elements or members of the set. An element x belonging to a set A
using FBN. The proposed FBN approach is validated in this way.
By comparing the FBN inference and the conventional Bayesian is defined as x 苸 A, an element that is not a member in A is noted
inference, it is noted that although these two methods produce as x 苸 A. A characteristic function or membership function A共x兲
similar results given the same model and similar input data, FBN is defined as an element in the universe U having a crisp value of
seems more flexible and interpretable than conventional BN. 1 or 0. For every x 苸 U,
5 Conclusions
FBN is a technology with huge potential for application across
A共x兲 = 再 1
0
for x 苸 A
for x 苸 A
冎
many domains. This paper discusses FBN and its application in this can also be expressed as A共x兲 苸 兵0 , 1其. For the classical set or
offshore risk analysis. The proposed FBN approach uses fuzzy crisp set, membership functions take a value of 1 or 0. However,
number based probabilities to conduct Bayesian inference, which for fuzzy sets, a membership function can take values in the in-
includes risk factor inter-relationship identification, BN model es- terval 关0,1兴. The range between 0 and 1 is referred to as the mem-
tablishment, fuzzy prior probability and likelihood calculation, bership grade or degree of membership. A fuzzy set A is defined
and inference and interpretation. The FBN model explicitly rep- below:
resents cause-and-effect assumptions between system variables
that may be obscured under other modeling approaches like fuzzy A = 兵共x, A共x兲兲兩x 苸 A, A共x兲 苸 关0,1兴其
reasoning and Monte Carlo risk analysis. The flexibility of the
method allows for multiple forms of information to be used to where A共x兲 is a membership function belonging to the interval
quantify model relationships, including formally assessed expert 关0,1兴.
opinion when quantitative data are lacking or, only qualitative/ There are different kinds of membership functions. A triangular
vague statements can be made. The proposed FBN model is also a membership function 共Fig. 7兲, for example, is one of the most
modular representation of uncertainty knowledge caused due to popular ones. It is normally defined by parameters 共a, b, c兲,
randomness and vagueness and therefore can be potentially inte- where a is the membership function’s left intercept with the grade
grated into the existing risk assessment systems. In general, the equal to 0.2, b is the center point where the grade is 0.5, and c is
proposed model ensures that its applications are conducted in a the right intercept at grade equal to 0.8. The function y
disciplined, well-managed, and consistent manner that promotes = triangle共x , 共a , b , c兲兲 is written to return the membership values
the delivery of risk assessment results. corresponding to the defined universe of discourse x. The param-
eters that define the closed interval membership function 共a, b, c兲
must be in the discretely defined universe of discourse.
Acknowledgment Fuzzy numbers are very special fuzzy subsets of the real num-
This project is funded by the UK Engineering and Physical bers. The general definition of a fuzzy number X is a fuzzy subset
Sciences Research Council 共EPSRC兲 under Grant Nos. GR/ of R. If the membership function of X is denoted as X共x兲, X must
S85504/01 and GR/S85498/01. meet the following conditions.
Journal of Offshore Mechanics and Arctic Engineering NOVEMBER 2009, Vol. 131 / 041101-9
冎
U
P f 共X = x1 ;W = w1兲 ⬵ 兺
Y,Z,V,U
P f 共w1兩U兲 丢 P f 共U兩Z;V兲 丢 P f 共V兲
丢 P f 共z2兩x1 ;y 2兲 丣 P f 共 v 2兲
丢 P f 共Z兩x1 ;Y兲
= P f 共x1兲 丢
再
丢
P f 共y 1兲
P f 共x1兲
丢 兺
Z;V;U
丢 P f 共Y兲
P f 共w1兩U兲
丢
再兺 U
P f 共w1兩U兲 丢 P f 共U兩z1 ; v2兲
冎冎
U
冎
Z;V;U
再 再
丢 P f 共u1兩z1 ; v1兲 丢 P f 共z1兩x1 ;y 1兲 丣 P f 共w1兩u2兲
= P f 共x1兲 丢 P f 共y 1兲 丢 P f 共 v 1兲
丢 P f 共u2兩z1 ; v1兲 丢 P f 共z1兩x1 ;y 1兲 丣 P f 共w1兩u1兲
丢
再兺 U
P f 共w1兩U兲 丢 P f 共U兩z1 ; v1兲
丢
丢
P f 共u1兩z2 ; v1兲
P f 共u2兩z2 ; v1兲
丢
丢
P f 共z2兩x1 ;y 1兲
P f 共z2兩x1 ;y 1兲其
丣
丣
P f 共w1兩u2兲
P f 共 v 2兲
丢 P f 共z1兩x1 ;y 1兲 丣 兺 P 共w 兩U兲 f 1
丢 兵P f 共w1兩u1兲 丢 P f 共u1兩z1 ; v2兲
冎
U
丢 P f 共z1兩x1 ;y 1兲 丣 P f 共w1兩u2兲 丢 P f 共u2兩z1 ; v2兲
丢 P f 共U兩z2 ; v1兲 丢 P f 共z2兩x1 ;y 1兲 丣 P f 共 v 2兲 丢 P f 共z1兩x1 ;y 1兲 丣 P f 共w1兩u1兲 丢 P f 共u1兩z2 ; v2兲
丢
再 兺 P 共w 兩U兲 丢 P 共U兩z ; v 兲
U
f 1 f 1 2
丢
丢
P f 共z2兩x1 ;y 1兲
P f 共z2兩x1 ;y 1兲其其
丣
丣
P f 共w1兩u2兲
P f 共y 2兲 丢
丢 P f 共u2兩z2 ; v2兲
兵P f 共v1兲
丢 兵P f 共w1兩u1兲 丢 P f 共u1兩z1 ; v1兲
丢 P f 共z1兩x1 ;y 1兲 丣 兺 P 共w 兩U兲
U
f 1
丢 P f 共z1兩x1 ;y 2兲 丣 P f 共w1兩u2兲 丢 P f 共u2兩z1 ; v1兲
Journal of Offshore Mechanics and Arctic Engineering NOVEMBER 2009, Vol. 131 / 041101-11
冎
ment,” Centre for Research on Introduced Marine Pests Report No. 17.
关20兴 Kang, C. W., and Golay, M. W., 1999, “A Bayesian Belief Network–Based
丢 P f 共u2兩z2 ; v2兲 丢 P f 共z2兩x1 ;y 2兲其其其 Advisory System for Operational Availability Focused Diagnosis of Complex
Nuclear Power Systems,” Expert Sys. Applic., 17共1兲, pp. 21–32.
关21兴 Karwowski, W., and Mital, A., 1986, “Potential Applications of Fuzzy Sets in
= 共0.0386,0.0461,0.0546兲 Industrial Safety Engineering,” Fuzzy Sets Syst., 19共2兲, pp. 105–120.
关22兴 Zadeh, L. A., 1984, “Fuzzy Probabilities,” Inf. Process. Manage., 20, pp.
363–372.
关23兴 Chou, K. G., and Yuan, J., 1993, “Fuzzy-Bayesian Approach to Reliability of
References Existing Structures,” J. Struct. Eng., 119共11兲, pp. 3276–3290.
关1兴 Wang, J., Sii, H. S., Yang, J. B., Pillay, A., Yu, D., Liu, J., Maistralis, E., and 关24兴 Pericchi, L. R., and Walley, P., 1991, “Robust Bayesian Credible Intervals and
Saajedi, A., 2004, “Use of Advances in Technology for Marine Risk Assess- Prior Ignorance,” Int. Statist. Rev., 59共1兲, pp. 1–23.
ment,” Risk Anal., 24共4兲, pp. 1041–1063. 关25兴 Yang, C. C., and Cheung, K. M., 1995, “Fuzzy-Bayesian analysis With
关2兴 Wang, J., 2006, “Maritime Risk Assessment and its Current Status,” Qual. Continuous-Valued Evidence,” Proceedings of the IEEE International Confer-
Reliab. Eng. Int, 22共1兲, pp. 3–19. ence on Systems, Man, and Cybernetics, Vancouver, Canada, Oct. 22–25, pp.
关3兴 Wang, J., Yang, J. B., and Sen, P., 1995, “Safety Analysis and Synthesis Using 441–446.
Fuzzy Set Modelling and Evidential Reasoning,” Reliab. Eng. Syst. Saf., 关26兴 León-Rojas, J. M., Masero, V., and Morales, M., 2003, “On the Fuzzy Baye-
47共2兲, pp. 103–118. sian Inference of Population Annoyance Level Caused by Noise Exposure,”
关4兴 Yang, Z., Bonsall, S., and Wang, J., 2008, “Fuzzy Rule-Based Bayesian Rea- Symposium on Applied Computing, Proceedings of the 2003 ACM sympo-
soning Approach for Prioritisation of Failures in FMEA,” IEEE Trans. Reliab., sium on Applied Computing, Melbourne, FL, Mar. 9–12, pp. 227–234.
57共3兲, pp. 517–528. 关27兴 Eleye-Datubo, A., Wall, A., Saajedi, A., and Wang, J., 2008, “Marine and
关5兴 Wang, J., Yang, J. B., and Sen, P., 1996, “Multi-Person and Multi-Attribute Offshore Safety Assessment by Incorporative Risk Modelling in a Fuzzy-
Design Evaluations Using Evidential Reasoning Based on Subjective Safety Bayesian Network of an Induced Mass Assignment Paradigm,” Risk Anal.,
and Cost Analyses,” Reliab. Eng. Syst. Saf., 52共2兲, pp. 113–129. 28共1兲, pp. 95–112.
关6兴 Wang, J., and Kieran, O., 2000, “Offshore Safety Assessment and safety Based 关28兴 Darwiche, A., 2003, “A Differential Approach to Inference in Bayesian Net-
Decision Making – The Current Status and Future Aspects,” ASME J. Off- works,” J. ACM, 50共3兲, pp. 280–305.
shore Mech. Arct. Eng., 122共2兲, pp. 93–99. 关29兴 Li, H. L., and Kao, H. Y., 2005, “Constrained Abductive Reasoning With
关7兴 Ren, J., Wang, J., Jenkinson, I., Xu, D. L., and Yang, J. B., 2007, “A Bayesian
Fuzzy Parameters in Bayesian Networks,” Comput. Oper. Res., 32共1兲, pp.
Network Approach for Offshore Risk Analysis Through Linguistic Variables,”
87–105.
China Ocean Eng., 21共3兲, pp. 371–388.
关30兴 Halliwell, J., and Shen, Q., 2002, “Towards a Linguistic Probability Theory,”
关8兴 Ren, J., Jenkinson, I., Wang, J., Xu, D. L., and Yang, J. B., 2008, “A Method-
Proceedings of the 11th International Conference on Fuzzy Sets and Systems
ology to Model Causal Relationships on Offshore Safety Assessment Focusing
共FUZZ-IEEE ’02兲, Honolulu, HI, May 16–17, pp. 596–601.
on Human and Organisational Factors,” J. Safety Res., 39共1兲, pp. 87–100.
关9兴 Sii, H. S., Ruxton, T., and Wang, J., 2001, “A Synthesis Using Fuzzy Set 关31兴 Buckley, J. J., 2002, An Introduction to Fuzzy Logic and Fuzzy Sets, Springer-
Theory and Dempster-Shafer Based Approach to Compromise Decision Mak- Verlag, Heidelberg.
ing With Multiple Attribute Applied to Risk Control Options Selection,” Proc. 关32兴 Mitchell, K., and Bright, C. K., 1995, “Minimizing the Potential for Human
Inst. Mech. Eng., Part E: Journal of Process Mechanical Engineering, 212, pp. Error in Ship Operation,” IMAS 95, Management and Operation of Ships,
251–261. Practical Techniques for Today and Tomorrow.
关10兴 Pearl, J., 1988, “Probabilistic Reasoning in Intelligent Systems,” Networks of 关33兴 Jenson, F. V., 1993, Introduction to Bayesian Networks: HUGIN, Aalborg Uni-
Plausible Inference, Kaufmann, Palo Alto, CA. versity Press, Aalborg, Denmark.
关11兴 Frühwirth-Schnatter, S., 1993, “On Fuzzy Bayesian Inference,” Fuzzy Sets 关34兴 NETICA, 2002, “Netica-J Reference Manual-Version 2.21,” Java Version of