APPLICATION OF BAYESIAN BELIEVE NETWORKS FOR CONTINUOUS RISK EVALUATION AND DECISION SUPPORT OF SAFETY MANAGEMENT IN MINING

1
APPLICATION OF BAYESIAN BELIEVE NETWORKS FOR
CONTINUOUS RISK EVALUATION AND DECISION SUPPORT
OF SAFETY MANAGEMENT IN MINING

• Todor P. Petrov
• University of Minig and Geology St. Ivan Rilsky
  - Sofia
• Department of Mine Safety and Ventilation
• e-mail tpp_at_mgu.bg

2
Today the investigation and registering of an
accident requires

• more than 60 fields of different data format
  describing quantitative and qualitative
  characteristics
• more than 3000 massive of data for description of
  approximately 50 accidents annually

3
The psychology and cognitive sciences are
ascertain the fact that

• the human mind cannot effectively manipulate a
  large amount of data streams and meet serious
  difficulties to make an inference when the
  possible decision have more than three
  alternatives
• the chance of bad decisions runs high, the
  frequency of wrong actions increasing and the
  safety become pursuit rather than achieved
  purpose.

4
Practical decision making

• It is well known that taking into account only
  quantificators of occupational safety risk like
  coefficients and indexes of frequency and
  severity of the accidents are not sufficient for
  characterization of safety state.

5
Important features of safety management

• the probability and fuzzy uncertainty
• manipulating of multisource quantitative and
  qualitative data
• rendering the expert opinion.

6
The inherited disease of the typical approach
for safety analisys

• Analyzing the safety risk by separately studying
  of isolated factors inevitably relates to loses
  of information about the mutuality in the
  examined system
• In the terms of information such a disjoint is
  irreversible process

7
New synergetic approach should perceive for
decision support in occupational safety

• A model putting together the dangers, the human
  factors and the control impacts including their
  mutual influences is needed.

8
MAR.NET project

• Mine Accident Risk dot Net is an expert system
  for decision support of mine safety management
• providing information fusion of different sources
  and types of evidence such as history databases,
  real time control systems and expert opinions.

9
CALCULATION OF RISK LEVEL

• Risk Probability x Severity (1)

10

• The low threshold of occupational risk can be
  calculated on

• In practice the accident without looses of
  working days are not registered.
• We can thing about Ro as a threshold of
  sensitivity of the safety monitoring system

11
Calculation of RISK LEVEL
Where Rc is the current risk Ro is the
low threshold of occupational risk.

• The purpose of risk level is to give one-value
  quantification of the current state of the safety
  relative to the acceptable threshold taking into
  account the sensitivity of the risk measuring.

12
Properties of LR

• LR is dimensionless
• LR is always positive
• If the current and the threshold risk are become
  equal than the safety level is calculated to
  zero. LR0 means no risk upper the threshold
  limit is detected.

Natural way of risk representation because the
human perceptions are determined exactly from
logarithmic levels as stated in psychophysical
law of Veber-Fehner
13
DRAWING OF INFERENCES FOR OCCUPATIONAL RISK
Fig. 1. Annually accident distribution
14
DRAWING OF INFERENCES FOR OCCUPATIONAL RISK
Fig. 2. Time row of accident frequencies
15
DRAWING OF INFERENCES FOR OCCUPATIONAL RISK
Reconstruction of phase space of the accident
frequency per month in 3D Fmonth, Fmonth-1,
Fmonth-2
16
DRAWING OF INFERENCES FOR OCCUPATIONAL RISK
Time row and reconstructed phase space of 15
minutes beats of a human heart
Panchev S. Chaos Theory, Academic Publisher,
Sofia 1996
17
Bayesian approach for statistical inference

• (1) is a result known as law for complete
  probability
• (2) is a result known as Bayes Theorem and
• (3) is a result known as chain rule, with
  significant importance in Bayesian believe
  networks (BBN)

18
MAR.NET project
MAR.NET project Structure of the network
TM Powered by Hugin Lite
19
MAR.NET project
Initial probability table of the chance node 10.
Job
State Probability
A. Transport and load 0.2
B. Ordinary exploration 0.2
0.2
E. Other 0.2
20
MAR.NET project
Initial conditional probability table
P(17.Body18.Injury)
18.Injury A B Z
17.Body
A.Head 0.25 0.25 0.25 0.25
B.Hands 0.25 0.25 0.25 0.25
C.Legs 0.25 0.25 0.25 0.25
D.Body 0.25 0.25 0.25 0.25
Total 1 1 1 1
21
MAR.NET project
Learning and adoption of MAR.NET
Learning and adoption of MAR.NET
Learning and adoption of MAR.NET
Posterior probability distribution of node
10.Job about all given states from A to E
22
Learning and adoption of MAR.NET

• Learning of MAR.NET from data cases

Node01 Node02 Node03 Node21
A N/A Q D
C I N/A N/A

The machine learning method used in MAR.NET is
known as EM-algorithm and it is commonly used in
BBN for graphical associated models with missing
data.
23
Structure Learning of MAR.NET

• The algorithms for structure learning of BBN are
  known as PC-algorithms

24
Structure Learning of MAR.NET

• As a result of the structure machine learning of
  MAR.NET with 122 data cases for registered
  accidents in coal mine of Babino Bobov dol, the
  conditional dependency of the following variables
  was accepted in LC0.05
• Occupation gtgt Time of occurrence of the accident
• Length of service gtgt Human factor
• Education Level gtgt Day after weekend
• Day after weekend gtgt Deviation from ordinary
  actions.

25
Entering Expert Opinions in MAR.NET

• The algorithm for entering of expert opinion
  used in MAR.NET allows control of the actuality
  of learned experience. The control of the
  actuality uses special data structures for
  reducing the impact of past called fading tables.

26
Simulation of data cases

• A way to test the safety system in lack of data
  and uncertainty
• Three approaches for obtaining simulated
  experience are easy applicable in MAR.NET model
• generating of simulated data cases based on
  variations of the current prior distribution
• generating data cases with simulation model of
  the object using advanced tools as special
  languages
• to change structure of the net depending of new
  knowledge, and to derive conclusions against the
  direction of the edges

27
MAR.NET example

• Example is based on the real data for a Bulgarian
  coal mining company with underground mining, open
  pit mining and dress factory.
• Structural changes in company are provided in the
  future time. From the company structure will be
  ousting the underground mines and the repair
  shops, but the steam power plant will be
  incorporated.

28
MAR.NET example

• What we need to expect about the risk for
  different groups of workers and the probabilities
  of environment causes?

29
Prior distributions
The knowledge about the object is extracted from
data cases about registered accidents with
learning algorithm
30
Posterior distribution

• Structural changes in the company are reflected
  in BBN node structure
• After Bayesian propagation through the network
  the posterior distribution is computed.

31
Back propagation.Obtaining inference against
the edges of MAR.NET

• Let now to propagate the opinion that in future
  the fatalities will increase twice
• It will change the Bayesian probability in
  station F. Fatalities of node 3 from 0.08 to
  0.16
• Let start the back-propagation of this new prior
  probability distribution
• The new posterior distribution is achieved.

32
The new posterior distributionis the answer of
the question

• What we need to expect about the risk for
  different groups of workers and the probabilities
  of environment causes?
• Using of faulty, unassured machines and
  facilities
• Using equipment inadequate of working conditions.
• Will lead to increasing of risk of fatalities in
  the groups of
• Staff at the surface and
• Open pit mine workers.

33
Conclusions

• MAR.NET project produced a decision support
  method with a supporting tool for quantifying
  safety in complex systems using Bayesian Networks
  as a core technology.
• The system can be adopted for different
  industries
• The well learned MAR.NET models can be used for
  decision support of safety management, education
  and training.

34
MAR.NET key benefits

• rationally combine different sources and types of
  evidence in single model
• identify weaknesses in the safety argument such
  that it can be improved
• specify degrees of confidence associated with
  prediction
• provide a sound basis for rational discussion and
  negotiation about the safety system development
  and deployment.

35

• Thank You