Вы находитесь на странице: 1из 96

ROAD

SAFETY
ANALYTICS

Objectives:
Analysis of road safety data in
Tata
Steel and to give prediction
model and recommendations
for reducing accidents and
better management of road
incidents.

Tools and Techniques

Pareto charts
Pie Charts
Cluster Analysis
Histograms
Arena
SAS
PHP

Methodology

Cause and Effect diagram

Pareto Charts In general we can say that 20% of factors


are responsible for 80% of the problems. For finding this
we use pareto charts.

Clustering We can group the data points in different


clusters based on their location (co-ordinates) and risk
score.

Distributions We find the closest fit distribution to


estimate the time between incidences(TBI).

Pie Charts We can show contribution of factors with the


help of pie charts.

Prescriptions.

Data Analysis

Injury Type Pareto


2013-14
Injury

2012-13

Injury Type

frequency

cum.

percent

F/A

57

57

45.96774

NO

49

106

LTI

15

FATAL
MTO

Injury Type

frequency

cum.

percent

85.48387

NO

81

81

27.46479

121

97.58065

F/A

39

120

84.50704

123

99.19355

LTI

21

141

99.29577

124

100

FATAL

142

100

Pareto Chart

Pareto Chart
frequency

60

100

50

80

40

60

30

40

20

20

10
0

F/A

NO

Injury

LTI FATAL MTO

injury
frequency

percent

Cumm percent

100
80
60
frequency 40
20
0

100
80
60
40 Cumm percent
20
0

injury
Frequency

Cummulative

Vehicle Type
2013-14
Pareto
2012-13

Vehicle Type
Vehicle
Type

Frequency

prob

Two

60

0.3774

0.3774

37.7358

HV

55

0.3459

0.7233

FW

26

0.1635

Cycle

18

0.1132

Vehicle Type

Vehicle
Type

Frequency

prob

cumm prob

percentage

HV

81

0.5094

0.5094

50.9434

72.3270

FW

37

0.2327

0.7421

74.2138

0.8868

88.6792

Two

27

0.1698

0.9119

91.1950

1.0000

100.0000

Cycle

14

0.0881

1.0000

100.0000

cumm prob percentage

Pareto Chart
70

100

90

80

40

60

30

40

20
20

10

80

70

50

100

80

60

FREQUENCY

Pareto Chart

60

CUMM PERCENT

60

50

FREQUENCY 40

40

30
20

20

10
Two

HV

FW

VEHICLE

Cycle

VEHICLE

CUMM PERCENT

Control chart for no. of


incidents per month
25

20

15

10 Incidents
No. of

Separation between 2012-13 and 2013-14 control chart

Probability

Risk Score CalculationConsequence

25

24

22

19

15

23

21

18

14

10

20

17

13

16

12

11

Cluster Analysis combined for


2012-13 and 2013-14

Cluster Analysis for 2013-14


Cluster Analysis for 2012-13

Plot of
incident
s based
on
injury
Fatal
LTI
First Aid
No Injury

Plot of
incidents
based on
property
damage risk
score
19 to 25
13 to 18
7 to 12
1 to 6

Plot of
incidents
based on
both type
risk score
19 to 25
13 to 18
7 to 12
1 to 6

Clusterin
g of
incident
locations
Represents
cluster

Cluster

Xcord

Ycord

count

cum.

829.421

749.14

57

57

721.296 263.241

54

111

40

151

1227.9

791.95

342.892 194.757

37

188

451.419 1174.77

31

219

215

506.389

18

237

1109

298.471

17

254

154.455 964.545

11

265

percent
Location
21.5094
East plant drop gate,LD#3 Traffic Signal,Near
3
LD#3 Office Turning
41.8867 L Town Gate, Diamond Crossing, G Blast Furncae
9
Ramp and crossing
56.9811
HSM Gate, WRP Weigh Bridge, Canteen turning
3
70.9434 Security Office Traffic signal,Coke plant Drop Gate
82.6415
Cabin#4 drop Gate,Near Merchant Mill Office
1
89.4339
West side peripheral Road,Near WGO
6
95.8490
Slag Road Gate
6
100
Pellet Plant Turning, Near PH#3 Gate

count

frequency

percent

60

100

50

80

40

60

30
40

20

20

10
0

CLUSTER NO.

CUMM. PERCENT

Cluster
Analysis
overlapped
for
2012-13
and 2013-14
Represents
cluster of
2012-13
Represents
cluster of
2013-14

Clusteri
ng
based
on risk
score

Belong to cluster 2
Belong to cluster 4
Belong to cluster 3
Belong to cluster 1

Distribution of Time
between incidents

Distribution of Time between


incidents

2013-14

2012-13

Distribution Parameters

Distribution Parameters

Distribution Name: Weibull

Distribution Name: Weibull

Alpha: 3.64

Alpha: 3.33

Beta: 1.26

Beta: 1.29

Expression: -0.5 + WEIB


(3.64, 1.26)

Expression: -0.5 + WEIB(3.33,


1.29)

Square Error:

Square Error:

0.007550

Sample Mean
= 2.87

0.004127

Sample Mean
2.57

LTI
First Aid
No Injury

Control Chart for Time between


Incidents
2013-14
CONTROL CHART FOR TBI(2013-14)
TBI

Linear (TBI)

UCL=11.759

2012-13

CONTROL CHART FOR TBI(2012-13)


TBI

LCL=0.113

16

14

14

12

12

Linear (TBI)

UCL=10.468

10

10

8
TBI

TBI

6
4

DATE

DATE

LCL=0.112

Distribution of Time between


injury
2013-14

2012-13

Distribution Parameters

Distribution Parameters

Distribution Name: Weibull

Distribution Name: Weibull

Alpha: 5.32

Alpha: 6.73

Beta: 1.26

Beta: 1.13

Expression: -0.5 + WEIB(5.32, 1.26)

Expression: -0.5 + WEIB(6.73, 1.13)

Square Error:

Square Error:

0.003990

Sample Mean
Sample Std. Dev

= 4.44
= 4.02

0.015753

Sample Mean
Sample Std. Dev

= 5.92
= 6.08

Control Chart for Injury


2013-14
2012-13

CONTROL CHART FOR TBI(2012-13)

CONTROL CHART FOR TBI(2013-14)


TBI

Linear (TBI )

UCL=17.186

TBI

LCL=0.165

25

Linear (TBI)

UCL=24.88

30

25

20

20
15
15
TBI

TBI

10

10
5

DATE

DATE

LCL=0.14

Correlation between different


Vehicles involved
25

19.5

20
15.5
RISK SCORE

15

10

14
10.29
8.24
4.75

7.75

8.8
7

9
7

6
4.67

4.31

4
0.88

HV

HV-FW

HV-TW

HV-CYCLIST
0

FW

FW-TW

FW-CYCLIST
0

VEHICLE COMBINATION
Average Injury Risk score

Average Property Damage Risk score

TW

TW-CYCLIST
0
CYCLIST
0

Correlation between different


Vehicles involved
Frequency Contribution

Combinatio Incident
n
count
HV

32

HV-FW

16

HV-TW

HV-CYCLIST

FW

FW-TW

FW-CYCLIST

TW

48

TW-CYCLIST

CYCLIST

TW-CYCLIST; 6%

CYCLIST; 3%
HV; 26%

HV-TW; 2%
TW; 39%

HV-CYCLIST; 3%
HV-FW; 13%

FW-TW;
2% FW; 4%
FW-CYCLIST;
2%

Contribution of different Vehicle


combinations in risk
Cumulative
Combi
Risk
nation
materi
Injury
al
HV
152 263.68
HV-FW 68.96
HV-TW
HVCYCLIS
T
FW

14
62
44

FW-TW 14.01
FWCYCLIS 39
T
TW 493.92
TWCYCLIS 56
T
CYCLIS
56
T

Property Damage risk


Contribution

Injury Risk Contribution

124
12
0
45
12
0
42

TW-CYCLIST; 6%

HV; 15%

CYCLIST; 6%HV-FW; 7%
HV-TW; 1%
HV-CYCLIST; 6%
FW; 4%
TW; 49%

HV-TW; 2%

FW-TW; 1%
FW-CYCLIST; 4%
HV-FW; 25%

0
0

FW-TW; 2% TW; 8%
FW; 9%

HV; 53%

MASTER LOGIC
DIAGRAM

PHYSICAL
(1)

EXTERNAL
(6)

BEHAVIORAL
(2)

Inciden
t

VEHICULAR
(5)

SYSTEM
(3)

INFRASTRUCTU
RE
(4)

PHYSICAL
(1)

OBSTRUCTIO
N

DIVIDER

SPILLAGE

DROP GATE

HEIGHT
BARRIER

ILLUMINATION

BEHAVIORAL
(2)

NON
INTENTIONAL

INTENTIONAL

CARELESS
DRIVING

TRAFFIC NORMS
VIOLATION

ALCOHOL

OVERTAKING

HIGH SPEED

SLEEPY

NOT
KNOWLEDGEABLE

SYSTEM
(3)

DESIGN

ZEBRA
CROSSING

TRAFFIC LIGHT

SUPERVISION

CONVEX MIRROR

SIGN BOARD

OTHERS(ROUTE
SURVEY,SECURIT
Y

VEHICULAR
ISSUES
(5)

BRAKE
FAILURE

INDICATOR
LIGHT

TYRE BURST

FAIL SAFE
BRAKE
FAILURE

STEERING
JAMMED

HAND
BRAKE NOT
WORKING

EXTERNA
L
(6)
STREET
DOGS

Contribution of
Organizational
factors and Use of
proactive data(FY14)

Issues

Physical

Behavioral

System
Infrastructure
Vehicular
Issues
External Issues

Count

Divider
Spillage (material/water)
Environmental (Illumination)
Height Barrier
Drop Gate
Overtaking
Alcoholic
Sleepy
Not knowledgeable
Traffic norms violation
Careless Driving
High Speed
No Zebra Crossing
Traffic Light
Convex Mirror
Others (supervision, route survey)
No Sign Board
Bad Road Condition /intersection issue
level crossing
Narrow Road (Congestion)
Blind Turn
No separate cyclist/pedestrian pathway
Brake Failure
Steering problem
Indicator Light Failure
Others (No reverse mirror)
Tyre Burst

2
13
11
2
6
28
1
0
11
5
107
40
1
11
3
6
11
6
17
13
6
11
4
4
0
6
2

Street dogs

cumulative count
34

192

32

53

16
6

Histogram of various Factor


Contributions
Frequency
120

100

80

60

40

20

13

11

28

11
0

107

40

11

11

17

13

11

6
0

Factor Contribution
Based on Occurrence
Physical

28

Behavioral

109

System

27

Infrastructure

42

Vehicular
Issues

16

External Issues

VEHICULAR ISSUES; 7% EXTERNAL; 3%

PHYSICAL; 12%

INFRASTRUCTURE; 18%

SYSTEM; 12%

BEHAVIORAL; 48%

Factor Contribution
Based on Frequency
Physical

34

Behavioral

192

System

32

Infrastructure

53

Vehicular
Issues

16

External Issues

Physical; 10%
Infrastructure; 16%
Vehicular Issues; 5% External Issues; 2%

System; 10%

Behavioral; 58%

Sub factor Contribution in


Physical Factor
Count

Divider

cumulativ
e count

PHYSICAL

2
Drop Gate; 18%

Spillage
(material/water 13
)

Phy
sic Environmental
al (Illumination)

Height Barrier
Drop Gate

Divider; 6%

Height Barrier; 6%

34
11
2
6

Environmental (Illumination); 32%

Spillage (material/water); 38%

Sub factor Contribution in


Behavioral Factor

Count

Overtaking

28

Alcoholic

Be Sleepy
Not
ha knowledgeable
vi Traffic norms
or violation
al Careless
Driving
High Speed

cumulativ
e count

BEHAVIORAL

High Speed; 21%

Overtaking ; 15%

Alcoholic; 1%
Not knowledgable; 6%

11
192

Traffic norms violation; 3%

5
107
40

Careless Driving; 56%

Sub factor Contribution in


System Factor

Sy
st
e
m

Coun cumulativ
t
e count

No Zebra
Crossing

Traffic Light

11

Convex Mirror

SYSTEM
No Zebra Crossing; 3%

No Sign Board; 34%

Traffic Light ; 34%

3
32

Others
(supervision,
route survey)

6
Others (supervision, route survey); 19%

No Sign Board

11

Convex Mirror ; 9%

Sub factor Contribution in


Infrastructure Factor

Infr
ast
ruc
tur
e

cumulativ
Count
e count

Bad Road
Condition
/intersection issue

level crossing

17

Narrow Road
(Congestion)

13

Blind Turn

No separate
cyclist/pedestrian
pathway

11

INFRASTRUCTURE

No separate cyclist/padestrian pathway; 21%

Blind Turn; 11%

53

Narrow Road (Congestion); 25%

Bad Road Condition /intersection issue; 11%

level crossing; 32%

b factor Contribution in Vehicular Issues


Factor

Brake Failure

Count

cumulativ
e count

VEHICULAR ISSUES

4
Tyre Burst; 13%

Steering
problem

Vehi
cula
Indicator Light
r
Failure
Issu Others (No
reverse
es

Brake Failure; 25%

camera)

Tyre Burst

16

Others (No reverse mirror); 38%

Steering problem; 25%

Factor Contribution in
total Injury Score
PROCEDURE:

Assumption : Each contributing sub factor is equally responsible for any


incident.

For every incident, Score is divided by no. of sub factors to get score/sub
factor.

Finding no. of sub factors of each factor in each incident.

Multiply no. of sub factors to score/sub factor to get contributing score of


each factor.

Add all incidents score for each factor.

Factor Contribution in Total


Injury Score
Factors

Physical
Behavioral
System
Infrastructure
Vehicular
Issues
External
Issues

Injury
Risk
Score

87.85
558.12
126.53
130.50

Contribution in total risk(Injury)

Infrastructure; 13%

System; 13%

External Issues; 3%
Vehicular Issues; 6%
physical; 9%

62.33
25.67
Behavioral; 56%

Factor Contribution in Total


Property Damage
Factors

Physical
Behavioral
System
Infrastructur
e
Vehicular
Issues
External
Issues

Contribution in total risk(Property Damage)

Property
damage Risk
score

53.32
280.53
69.05
28.27
75.33

Vehicular Issues; 15%

External Issues; 0%
physical; 11%

Infrastructure; 6%

System; 14%

0.50
Behavioral; 55%

Comparison of contribution
based on Frequency and Total
Risk

FACTOR CONTRIBUTION BASED ON FREQUENCY FACTOR CONTRIBUTION IN TOTAL RISK(INJURY)

Infrastructure; 13%
Vehicular Issues; 5%
Infrastructure; 16%

Physical; 10%
System; 13%

External Issues; 2%

External Issues; 3%
physical; 9%
Vehicular Issues; 6%

System; 10%

Behavioral; 58%
Behavioral; 56%

Comparison of contribution
based on Frequency and Total
Risk
FACTOR CONTRIBUTION IN TOTAL RISK(PROPERTY DAMAGE)
FACTOR CONTRIBUTION BASED ON FREQUENCY

Vehicular Issues; 5%
Infrastructure; 16%

Physical; 10%

External Issues;physical;
0%
11%
Vehicular Issues; 15%
Infrastructure; 6%

External Issues; 2%

System; 14%

System; 10%

Behavioral; 58%

Behavioral; 55%

Correlation between
different organizational
measures and number of
incidents

Effect of Speed violations on Total


incidents due to high speed
Speed
No. of
Month Violation incidents(Hi
s
gh speed)
April
May
June
July
August
September
October
November
December
January
February
March

334
414
326
410
296
321
330
311
231
215
126
114

2
2
0
0
0
1
14
1
7
5
4
3

Speed violations vs No. of incidents due to High Speed


450

414

410

400
350 334

326
296

300

330

321

311
231

250

215

200
FREQUENCY
150

126

114

100
50
0

1
0

14

MONTH
Speed Violations

No. of incidents(Highspeed)

Effect of Speed violations on Total

Effect of Heavy vehicle inspection on


Total incidents due to vehicular issues

April

434

No. of
incidents
due to
vehicular
issues
1

May

362

June

403

July

368

300

August

308

200

September

330

100

October

334

November

417

December

395

January

528

February

421

March

288

No. of
MONTHS inspectio
ns

No. of HV inspection vs No. of incidents due to vehicular issues


600

528

500

434
FREQUENCY
400

417

403

362

368

2
0

334

330

308

421

395

2
0

288

MONTH
No. of incidents due to vehicular issues

No. of inspections

Effect of HV inspection on Total

Effect of R-SAP on Total incidents due


to careless driving
No. of
R-SAP
Incidents due
Month Conducte to careless
d
driving

R-SAP conducted Vs No. of incidents due to Careless driving


140

April

106

May

98

June

116

July

101

August

89

September

92

11

40

October

110

18

20

November

102

December

115

10

104

January

116

120
106

104

102

101

98

100

115

110
92

89

80
FREQUENCY
60

5
0

Apr'13

8
May'13

June'13

July'13

18

11

Aug'13

Sep'13

8
Oct'13

Nov'13

10

Dec'13

Jan'14

MONTH
R-SAP Conducted

Careless Driving

Effect of R-SAP on Total inciden

Analysis of Variance
Source

DF

Sum of
Squares

Mean Square

Model

26.757535

8.919178

Error

91.492465

11.436558

Corrected Total

11

118.25

F Value

Pr > F

0.78

0.538

Model Fit Statistics


R-Square

0.226

Adj R-Sq.

-0.0639

Analysis of Maximum Likelihood Estimates


Parameter

DF

Estimate

Standard
Error

F Value

Pr > |t|

Intercept

0.4805

13.2828

0.34

0.745

HVC

-0.0235

0.0173

-1.36

0.212

RSAP

0.1562

0.1376

1.14

0.289

SV

-0.00463

0.0106

-0.44

0.674

6
10
9
7
11
11
18
9
13
8
13
8

MONT Speed Heavy Vehicle RSA


H
Violation
Checking
P

1
2
3
4
5
6
7
8
9
10
11
12

334
414
326
410
296
321
330
311
231
215
126
114

434
362
403
368
308
330
334
417
395
528
421
288

106
98
116
101
89
92
110
102
115
104
103
98

Forecasting using
Decomposition
Method

Validation for number of Incidents


Model Building Data: April2011-Aug2013
Sep2013-March2014
Month

Forecast

Actual

Sum
Square
Error

Septembe
r

12.62

11.00

2.61

October

17.48

18.00

0.27

November

7.00

9.00

3.98

December

11.03

13.00

3.88

January

7.39

8.00

0.37

February

13.41

13.00

0.17

March

8.60

8.00

0.36

MSE 1.67

Validation Data:

Forecast for number of incidents


Month

Polynomial

Actual FY-15

April
May
June
July
August
September
October
November
December
January
February
March

7.23
10.61
14.49
10.00
13.53
6.77
10.29
7.52
11.46
8.39
7.87
11.51

10
10
8

Quarter wise

Injury per month


2011-12

2012-13

2013-14

15
10
No. of Injuries

5
0
0

6
Month

10

12

Validation for number of injury


Model Building Data: April2011-Aug2013
Sep2013-March2014
Month

Forecast
(2013-14)

Actual
2013-14

SS

September

7.74

9.00

1.5952

October

10.08

13.00

8.5452

November

-0.75

3.00

14.065

December

4.92

8.00

9.4715

January

5.09

7.00

3.6291

February

6.27

8.00

3.0020

March

-0.39

1.00

1.9424

MSE

Validation Data:

Forecast for No. of Injury type Incidents


Month

Polynomial

Actual FY-15

April
May
June
July
August
September
October
November
December
January
February
March

4.65
8.83
9.60
8.64
9.73
7.39
7.61
5.96
10.47
8.17
9.36
8.46

4
4
5

Forecast for First Aid


Forecast for LTI

Prescriptions:
In 2013-14, 6 incidents happened due to street dogs which mostly resulted in LTI.
Inside a steel plant, presence of street dogs should not be tolerated and street
actions should be taken to eliminate this hazard.

In some incidents, illumination was also a major contributing factor. (E.g. Near pellet
plant level crossing, illumination is poor as well as road condition is also poor.)
These types of roads should be identified and proper action should be taken)

Over 3 years, there is an increasing trend of incidents near Diamond crossing; even
then there is no traffic signal at the crossing. It should be implemented as soon as
possible.
Also at major crossings (Diamond, LD#2, LD#3, Cabin#4), most near misses are
either due to crossing with high speed or carelessness of cyclists/pedestrians. To
reduce this no. ,there must be a speed limit (say 20kmph) at all crossings and if
possible separate pathways for cyclists/pedestrians.

In some areas, proper sign boards are not present at roads. This should be

Vehicle failure (mainly steering jammed and brake failure) may lead to a very serious
accident inside plant. So these types of incidents should have separate investigation to
take preventive actions.

In case of property damages, more than 50% incidents happened due to dashing in
which a major contribution is, while reversing a heavy vehicle.
So if we strictly implement the availability of reverse camera, these types of
incidents can be reduced.

As far as behavioral related issues are concerned, careless driving and high speed are
long term issues. But sleepiness and alcohol must not be tolerated. In such cases heavy
penalty should be imposed to avoid any future serious accident.

Spillage prone roads should be identified (like near sinter and pellet plant) and there
should be warning about spillage to avoid any skidding/slipping.

With the help of regression it is evident that heavy vehicle inspection and speed
violation checking are helping in reducing road accidents but RSAP is not up to the
mark. More needs to be done in that area.

Thank You

Rohit Raj
Sonu Kumar

Backup Slides

Cause
Cause and
and Effect
Effect diagram
diagram for
for Road
Road Incidents
Incidents

Human
Human Factors(83)
Factors(83)

External
External Factors(17)
Factors(17)
Material /
Water
Spillage
Stones and
other
obstruction
s

Slope
(increasing
or
decreasing)
Sharp
and blind
turns

Driver
mentally
stressed or
tired

Sudden
appearance of
Street
Dogs/animals

Uneven
or
damaged
road

Unskilled in
driving/driving
a new Vehicle

Lack of sleep,
carelessness
(taking risks,
overtaking)
Fail safe brake,
blinker, wiper,
hand brake not
working

Tyre
bursted

Steering
jammed

Rainy or
windy
conditions
(seasonality
)

Incidents/
Incidents/
Accidents
Accidents on
on
Road(124)
Road(124)

Low
Visibility
due to fog
or night
time

Road
Road conditions(15)
conditions(15)
Vehicle
Vehicle Breakdown
Breakdown (9)
(9)

Environmental
Environmental Factors
Factors (N/A)
(N/A)

Cause type
Pareto
2013-14
CAUSES

Real Causes
Frequency
cum.

Human Factors

83

83

External Factor

17

100

Road Condition

15

115

Vehicle
Breakdown

124

2012-13

percent
66.935483
9
80.645161
3
92.741935
5

CAUSES
Human Factors

100

14

119

85

Vehicle Breakdown

12

131

93.5714286

External Factor

140

100

Pareto Chart

100

80
80

70
60

60

50
40

40

30

FREQUENCY
20

CUMM PERCENT
20

10
0

120

100

100

80

80
FREQUENCY

60

60

CUMM PERCENT
40

40

20

20
0

CAUSE

percent
75

Road Condition

Pareto Chart
90

Real Causes
Frequency
cum.
105
105

3
CAUSE

Month type
Pareto

Month

2013-14

Frequency Cum. Freq. percent

April,13

0.04878

May,13

10

16

0.130081

June,13

25

0.203252

July,13

32

0.260163

August,13

11

43

0.349593

September,13

11

54

0.439024

October,13

18

72

0.585366

November,13

81

0.658537

December,13

13

94

0.764228

January,14

102

0.829268

February,14

13

115

0.934959

March,14

123

Frequency
18
16
14
12
10
8
6
4
2
0

20
18
16
14
12
10
Frequency
8
6
4
2
0

8
Month

10

12

14

Month type
Pareto

Month

Frequency

Cum. Freq.

percent

April,12
May,12
June,12
July,12
August,12
September,12
October,12
November,12
December,12
January,13
February,13
March,13

8
11
21
9
21
6
8
9
10
11
10
18

8
19
40
49
70
76
84
93
103
114
124
142

5.633803
13.38028
28.16901
34.50704
49.29577
53.52113
59.15493
65.49296
72.53521
80.28169
87.32394
100

2012-13
No. of incidents
25
20

21

21
18

15
10
5

11

Scatter Plot

25
20
15
10
5
0
0

10

12

14

10

11

10

Month wise comparison


frequency 13

frequency 14

25

20

15

10

0
0

10

12

14

Cluster Analysis for 2013-2014

Plot of
incident
s based
on
injury
Fatal
LTI
First Aid
No Injury

Plot of
incidents
based on
property
damage risk
score
19 to 25
13 to 18
7 to 12
1 to 6

Plot of
incidents
based on
both type
risk score
19 to 25
13 to 18
7 to 12
1 to 6

Clusteri
ng of
incident
location
s
Represents
cluster

Cluster Means

Cluster

Xcord

Ycord

826.25 722.84

count

cum

percent

Important locations

32

32

26.0163

LD 2 traffic signal, LD 3 traffic signal, level crossing


near LD 3

709.9

254.6

30

62

50.4065 Diamond Crossing, L Town Gate,

1225.3

791.5

18

80

65.0407

356.56 177.44

16

96

78.0488

7
2
1
3

456.22 1205.2
1064.1
224
127.2 492.2
131.2 935.8

9
8
5
5

105
113
118
123

85.3659
91.8699
95.935
100
frequency

G Blast furnace Turning


HSM Gate, WRP weighbridge
Security Office traffic Signal, West Plant level
Crossing
Cabin 4
Slag Road Gate
West Peripheral Road
Near Power House 3 Gate

cum %

35

120

30

100

25

80

Frequency
20
60
15
40

10

20

5
0

4
5
Cluster NO.

Cumm. percent

Clusteri
ng
based
on risk
Belong
to cluster 2
score
Belong to cluster 4
Belong to cluster 3
Belong to cluster 1

Cluster Analysis for 2012-2013

Plot of
incident
s based
on
injury
Fatal
LTI
First Aid
No Injury

Plot of
incidents
based on
property
damage risk
score
19 to 25
13 to 18
7 to 12
1 to 6

Plot of
incidents
based on
both type
risk score
19 to 25
13 to 18
7 to 12
1 to 6

Clusteri
ng of
incident
location
s
Represents
cluster

Cluster
Xcord

Ycord

count

cum.

percent

Location

805.423

387.308

26

26

18.30986

LD#2 Traffic Signal, G Blast furnace turning

389.962

199.692

26

52

36.61972

Security Office Traffic Signal,coke plant drop gate

6
7
5
3
1
8

366.077
1229.57
850.118
164.222
517.375
1155.71

1121.96
779.13
916.647
512.778
578.25
315.143

26
23
17
9
8
7

78
101
118
127
135
142

54.92958
71.12676
83.09859
89.43662
95.07042
100

cabin#4 drop gate, near merchant mill


HSM Gate, WRP Weigh Bridge
LD#2 Traffic Signal, CRM Island
west side peripheral road
East plant drop gate
slag road gate

Clusteri
ng
based
on risk
Belong
to cluster 3
score
Belong to cluster 1
Belong to cluster 2
Belong to cluster 4

Distribution of Time
between LTIs
2013-14
2012-13

Distribution Parameters

Distribution Parameters

Distribution Name: Weibull

Distribution Name: Weibull

Alpha: 23

Alpha: 16.8

Beta: 1.34

Beta: 1.21

Expression: -0.5 + WEIB(23, 1.34)

Expression: -0.5 + WEIB(16.8, 1.21)

Square Error:

Square Error:

0.070247

Sample Mean
Sample Std. Dev

= 20.8
= 15.8

0.047390

Sample Mean
Sample Std. Dev

= 15.3
= 12.2

CONTROL CHART FOR LTI


2013-14
CONTROL CHART FOR TBI(2013-14)
TBI

Linear (TBI)

UCL=69.28

2012-13

LCL=0.88

CONTROL CHART FOR TBI(2012-13)


TBI

80

Linear (TBI)

UCL=56.97

60

70

50

60
40

50
40
TBI

30
TBI

30

20

20
10

10
0

DATE

DATE

LCL=0.45

Distribution of Time
between First Aid
2013-14
2012-13

Distribution Parameters

Distribution Parameters

Distribution Name: Weibull

Distribution Name: Weibull

Alpha: 6.88

Alpha: 9.32

Beta: 1.27

Beta: 1.15

Expression:

-0.5 + WEIB(6.88, 1.27)

Square Error: 0.006406

Sample Mean
Sample Std. Dev

Expression:

-0.5 + WEIB(9.32, 1.15)

Square Error: 0.019446

: 5.88
: 5.32

Sample Mean
Sample Std. Dev

= 8.39
= 7.43

CONTROL CHART FOR FIRST AID


2013-14
2012-13

CONTROL CHART FOR TBI(2013-14)


TBI

Linear (TBI)

UCL=22.02

CONTROL CHART FOR TBI(2012-13)

LCL=0.22

TBI

30

Linear (TBI)

UCL=33.68

40
35

25

30
20
25
15

20

TBI

TBI
10

15
10

5
5
0

DATE

DATE

LCL=0.21

Distribution of Time
between No Injury
2013-14
2012-13

Distribution Parameters

Distribution Parameters

Distribution Name: Weibull

Distribution Name: Weibull


Alpha: 5.18

Alpha: 8.76

Beta: 1.1

Beta: 1.24
Expression:

Expression:
-0.5 + WEIB(8.76, 1.24)

Square Error:

-0.5 + WEIB(5.18, 1.1)

Square Error: 0.005930

0.015624

Sample Mean
Sample Std. Dev

= 7.66
= 6.64

Sample Mean

= 4.47

Sample Std. Dev

= 4.87

CONTROL CHART FOR NO INJURY


2013-14
2012-13

CONTROL CHART FOR TBI(2013-14)


TBI

Linear (TBI)

UCL

CONTROL CHART FOR TBI(2012-13)

LCL

TBI

35

Linear (TBI)

30

30

25

25
20
20
15
TBI

15

TBI
10

10

DATE

DATE

UCL

LCL

Effect of Speed violations on Total incidents


Month

Speed
Violations

No. of
incidents(over
all)

April

334

May

414

10

June

326

July

410

August

296

11

September

321

11

October

330

18

November

311

December

231

13

January

215

February

126

13

March

114

Speed violations vs Road Incidents


450

414

410

400
350 334

326

321

330

296

300

311

250

231

215

200
FREQUENCY
150

126

114

100
50
0

10

Speed Violations

11

No. of incidents(overall)

11

18

MONTH

13

13

Effect of Heavy vehicle inspection on


Total incidents
MONTHS

No. of
Total no. of
inspections incidents

No. of HV inspection vs Total no. of incidents


600
528

April

434

May

362

10

June

403

July

368

August

308

11

September

330

11

October

334

18

November

417

December

395

13

January

528

February

421

13

March

288

500
434

417

403

400

368

362

300
FREQUENCY

334

330

308

421

395

288

200

100

6
1

10
2

9
3

7
4

11
5

11
6

18
7

9
8

MONTH
No. of inspections

Total no. of incidents

13
9

8
10

13
11

8
12

Effect of R-SAP on Total incidents


Month

R-SAP
No. of
Conducted Incidents

R-SAP conducted Vs No. of incidents


140

April

106

116

120

May

98

10

June

116

July

101

August

89

11

September

92

11

40

October

110

18

20

November

102

December

115

13

January

104

104

102

101

98

100

115

110

106

92

89

80
FREQUENCY
60

6
0

Apr'13

10

May'13 June'13

7
July'13

11

11

Aug'13

Sep'13

18
9
Oct'13

MONTH
R-SAP Conducted

No. of Incidents

Nov'13

13
Dec'13

8
Jan'14

USING DECOMPOSITION METHOD


(Quarter wise)
Forecast for No. Of Incidents

Polynomial
29.7
28.3
26.9
23.4
22.2
19.8
17.5
13.0

Quarter
Q1
Q2
Q3
Q4
Q1
Q2
Q3
Q4

Actual
28

Forecast for First Aid


Month
Polynomial Actual FY-15
April
May
June
July
August
September
October
November
December
January
February
March

2.64
7.02
7.08
8.11
7.58
5.88
5.92
4.75
8.64
7.93
7.95
7.82

2
4
5

Month
April
May
June
July
August
September
October
November
December
January
February
March

Forecast for LTI


Polynomial Actual FY-15
2.13
1.52
2.42
1.00
2.53
1.72
1.86
1.38
2.01
0.42
1.33
0.95

2
0
0

Usefulness to Tata Steel


Here with the help of Cause and Effect diagram we can
identify all the possible causes responsible for the
incidents taking place here related to human, vehicle,
road, environmental and external factors.
Next with the help of Pareto Chart we can identify major
factors responsible for the occurrence of incidents. Using
this we were able to identify major type of vehicles, type of
injury, type of causes, months which constitutes maximum
(here 80%) of incidents.
Moreover, We can also use Pareto chart for identifying highly
frequent
incident occurring areas which were identified
by Cluster Analysis, explained in next slide.

Cluster Analysis :
This is a mathematical tool for grouping a set of
objects in such a way that objects in the same group
are more similar and within cluster sum of squares is
minimum.
This can be used in Tata Steel to group all incidents in
a few clusters identified by their co-ordinates on a
map of size (width: 1332px, height: 1447px) .
Also, these clusters can be utilised as input for
predicting various injury type incidents in a particular
area. Here we have used k-means clustering and have
taken k =8.

Probability Distribution:
We have fit time between occurrences of
incidents both frequency wise and injury type
wise (No injury, First aid, LTI).
Using this fitting, we will be able to say what is
the pattern of time between occurrences as well
it's parameters
can be used in prediction.
E.g.- We have found that TBO follows Weibull
distribution with parameters alpha = 1.26 and
beta =3.64. So we can say that a particular
incident will occur with a particular probability
after a certain number of days.

Вам также может понравиться