Sie sind auf Seite 1von 40

Modeling Condition And Performance

Of Mining Equipment
Tad S. Golosinski and Hui Hu

Mining Engineering
University of
Missouri-Rolla

1
Condition and Performance Monitoring
Systems

 Machine health monitoring


• Allows for quick diagnostics of problems
 Payload and productivity
• Provides management with machine and fleet
performance data
 Warning system
• Alerts operator of problems, reducing the risk
of catastrophic failure

2
CAT’s VIMS
(Vital Information Management System)

 Collects / processes  Installed on…


information on major • Off-highway trucks
machine components • 785, 789, 793, 797
• Engine control • Hydraulic shovels
• Transmission/chassis • 5130, 5230
control • Wheel loaders
• Braking control • 994, 992G (optional)
• Payload measurement
system

3
Other, Similar Systems
 Cummins
• CENSE (Engine Module)
 Euclid-Hitachi
• Contronics & Haultronics
 Komatsu
• VHMS (Vehicle Health Monitoring System)
 LeTourneau
• LINCS (LeTourneau Integrated Network Control System)

4
Round Mountain Gold Mine

Truck Fleet
17 CAT 785 (150t)
11 CAT 789B (190t)
PSA
(Product Support
Agreement) CAT
dealer guarantees
88% availability

5
VIMS in RMG Mine
 Average availability is 93%
over 70,000 operating hours
 VIMS used to help with
preventive maintenance
• Diagnostics after engine failure
• Haul road condition assessment
• Other

Holmes Safety Association Bulletin 1998 6


CAT MineStar

 CAT MineStar - Integrates …


• Machine Tracking System
(GPS)
• Computer Aided Earthmoving System
(CAES)
• Fleet scheduling System
(FleetCommander)
• VIMS

7
Cummins Mining Gateway

Modem

MiningGateway.com Database CENSE

Base
Cummins
Engine Station

RF Receiver Modem

8
VIMS Data & Information Flow
VIMS
Mine Legacy
Site 1 Database

Mine Data Extract VIMS Data


Site 2 Data Cleanup Warehouse
Data Load

Mine
Site 3
Information
Extraction

Information
Data Mining
Apply
Tools
9
Earlier Research:
Data Mining of VIMS

 Kaan Ataman tried modeling using:


• Major Factor Analysis
• Linear Regression Analysis
• All this on datalogger data
 Edwin Madiba tried modeling using:
• Data formatting and transferring
• VIMS events association
• All this on datalogger and event data

10
Research Objectives
 Build the VIMS data warehouse to
facilitate the data mining
 Develop the data mining application for
knowledge discovery
 Build the predictive models for prediction
of equipment condition and performance

11
Interactions

Data Data
Acquisition Preparation

Result
Interpretation Data Mining

12
VIMS Features
Operator

Download

Sensors & Controls


Monitor & Store Maintenance
• Event list
• Event recorder
• Data logger
• Trends Wireless Link
• Cumulative data
• Histograms
• Payloads Management
VIMS wireless

13
Data Source

14
VIMS Statistical Data Warehouse
1-3 minute interval statistical data
• Minimum • Regression Intercept
• Maximum • Regression Slope
• Average • Regression SYY
• Data Range • Standard Deviation
• Variance
EVENT ID TC_OUT_TEMP_AVG TC_OUT_TEMP_MAX TC_OUT_TEMP_MIN TC_OUT_TEMP_RANGE
0_6 70.35 73 65 8
0_7 64.95 66 64 2
0_8 65.67 66 65 1
0_9 66.30 67 66 1
767_1 80.00 80 80 0
767_2 80.37 81 80 1
767_3 80.95 81 80 1
767_4 81.32 82 81 1
767_5 81.83 82 81 1
767_6 83.43 87 82 5

15
VIMS Data Description
 Six CAT 789B trucks
 300 MB of VIMS data
 79 “High Engine Speed” events
One-minute data statistics

Dataset Count of Record


Training Set 1870 86.4%
Test set 1 (#1) 98
13.6%
Test set 2 (#2) 196
Total 2164
16
SPRINT -A Decision Tree Algorithm
IBM Almaden Research Center

 GINI index for the split point

gini (s)  1   p 2
j

n1 n2
gini split ( s)  gini ( s1 )  gini ( s2 )
n n
 Strictly binary tree
 Built-in v-fold cross validation
17
18
VIMS EVENT PREDICTION

High Engine Speed


Normal Engine Speed Normal Engine Speed
Snapshot
VIMS
0 0 0 0 0 0 1 2 3 4 5 6 0 0 0 0 0
Data
High Eng

Event_ID 767_1 767_2

Predicted Other Other Eng_1 Eng_2 Other Other


Label

19
“One-Minute”
decision tree 20
Decision Tree: Training on One-Minute Data
Total Errors = 120 (6.734%)

Predicted Class --> | Other | Eng1 | Eng3 | Eng2 | Eng4 | Eng6 | Eng5 |
----------------------------------------------------------------------------------------------------------------
Other | 1331 | 18 | 9| 5| 16 | 6| 1 | total = 1386
Eng1 | 0| 62 | 1| 3| 0| 0| 0 | total = 66
Eng3 | 0| 11 | 51 | 2| 2| 1| 0 | total = 67
Eng2 | 0| 12 | 8| 38 | 7| 0| 0 | total = 65
Eng4 | 0| 3| 7| 2| 55 | 0| 1 | total = 68
Eng6 | 0| 0| 0| 1| 0| 61 | 4 | total = 66
Eng5 | 0| 0| 0| 0| 0| 0| 64 | total = 64
--------------------------------------------------------------------------------------------------------------
1331 | 106 | 76 | 51 | 80 | 68 | 70 | total = 1782

21
Decision Tree: Test#1 on One-Minute Data
Total Errors = 24 (24%)

Predicted Class --> | Other | Eng1 | Eng3 | Eng2 | Eng4 | Eng6 | Eng5 |
-----------------------------------------------------------------------------------------------------------
Other | 59 | 3| 0| 2| 3| 0| 1 | total = 68
Eng1 | 4| 1| 0| 1| 0| 0| 0 | total = 6
Eng3 | 0| 3| 1| 0| 1| 0| 0 | total = 5
Eng2 | 1| 1| 1| 1| 0| 0| 0 | total = 4
Eng4 | 1| 1| 0| 1| 1| 0| 0 | total = 4
Eng6 | 0| 0| 0| 0| 0| 7| 0 | total = 7
Eng5 | 0| 0| 0| 0| 0| 0| 6 | total = 6
-----------------------------------------------------------------------------------------------------------
65 | 9| 2| 5| 5| 7| 7 | total = 100

22
Decision Tree: Test#2 on One-Minute Data
Total Errors = 35 (17.86%)

Predicted Class --> | Other | Eng1 | Eng3 | Eng2 | Eng4 | Eng6 | Eng5 |
--------------------------------------------------------------------------------------------------------
Other | 141 | 9| 2| 4| 4| 0| 0 | total = 160
Eng1 | 2| 2| 1| 1| 0| 0| 0 | total = 6
Eng3 | 2| 1| 2| 0| 1| 0| 0 | total = 6
Eng2 | 2| 1| 2| 1| 0| 0| 0| total = 6
Eng4 | 1| 0| 1| 1| 3| 0| 0| total = 6
Eng6 | 0| 0| 0| 0| 0| 6| 0| total = 6
Eng5 | 0| 0| 0| 0| 0| 0| 6| total = 6
---------------------------------------------------------------------------------------------------------
148 | 13 | 8| 7| 8| 6| 6 | total = 196

23
“Two-Minute”
decision tree
24
Decision Tree
Training on Two-Minute Data Sets

Total Errors = 51 (5.743%)

Predicted Class --> | OTHER | ENG1 | ENG2 | ENG3 |


---------------------------------------------------------------------
OTHER | 657 | 6| 19 | 3| total = 685
ENG1 | 0| 62 | 10 | 0| total = 72
ENG2 | 0| 13 | 54 | 0| total = 67
ENG3 | 0| 0| 0| 64 | total = 64
---------------------------------------------------------------------
657 | 81 | 83 | 67 | total = 888

25
Decision Tree
Test #1 on Two-Minute Data

Total Errors = 14 (29.79%)

Predicted Class --> | OTHER | ENG1 | ENG2 | ENG3 |


---------------------------------------------------------------------
OTHER | 28 | 5| 4| 1| total = 38
ENG1 | 1| 0| 0| 0| total = 1
ENG2 | 2| 1| 1| 0| total = 4
ENG3 | 0| 0| 0| 4| total = 4
---------------------------------------------------------------------
31 | 6| 5| 5| total = 47

26
Decision Tree
Test #2 on Two-Minute Data

Total Errors = 15 (15.31%)

Predicted Class --> | OTHER | ENG1 | ENG2 | ENG3 |


---------------------------------------------------------------------
OTHER | 71 | 8| 1| 0| total = 80
ENG1 | 3| 3| 0| 0| total = 6
ENG2 | 0| 3| 3| 0| total = 6
ENG3 | 0| 0| 0| 6| total = 6
---------------------------------------------------------------------
74 | 14 | 4| 6| total = 98

27
“Three-Minute”
decision tree
28
Decision Tree
Training on Three-Minute Data

Total Errors = 28 (4.878%)

Predicted Class --> | OTHER | ENG1 | ENG2 |


----------------------------------------------------
OTHER | 411 | 23 | 4| total = 438
ENG1 | 1| 65 | 0| total = 66
ENG2 | 0| 0| 70 | total = 70
----------------------------------------------------
412 | 88 | 74 | total = 574

29
Decision Tree
Test #1 on Three-Minute Data

Total Errors = 12 (19.05%)

Predicted Class --> | OTHER | ENG1 | ENG2 |


----------------------------------------------------
OTHER | 42 | 9| 0| total = 51
ENG1 | 3| 5| 0| total = 8
ENG2 | 0| 0| 4| total = 4
----------------------------------------------------
45 | 14 | 4| total = 63

30
Decision Tree
Test #2 on Three-Minute Data

Total Errors = 9 (14.06%)

Predicted Class --> | OTHER | ENG1 | ENG2 |


----------------------------------------------------
OTHER | 47 | 5| 0| total = 52
ENG1 | 4| 2| 0| total = 6
ENG2 | 0| 0| 6| total = 6
----------------------------------------------------
51 | 7| 6| total = 64

31
Decision Tree Summary
 “One-Minute model” needs more complex tree
structure
 “One-Minute model” gives low accuracy of
predictions
 “Three-Minute” decision tree model gives
reasonable accuracy of predictions
• Based on test #1 &#2
• Other - 13% error rate
• Eng1 - 50% error rate
• Eng2 – 0 error rate
 Other approach?

32
Backpropagation
A Neural Network Classification Algorithm

Node
Node Detail

x1
w1
w2
x2 f(z)
w3
x3
z = S iw ix i
Input Hidden Out
Layer
Some choices for F(z):
Characteristic: Each output f(z) = 1 / [1+e-z] (sigmoid)
corresponds to a possible classification. f(z) = (1-e-2z) / (1+e-2z) (tanh)

33
Minimize the Sum of Squares
SSQ Error Function

1 m
E   ( t k  yk ) 2
2 k 1
1 m
min E   ( t k  yk )2
2 k 1

yk (output) is a function of
the weights wj,k. Freeman & Skapura, Neural Networks,
tk is the true value. Addison Wesley, 1992
In the graph:

• Ep is the sum of
E
EW j ,k  and solve EW j ,k  0 for W j,k
squares error

W j ,k • Ep is the gradient,


(direction of maximum
function increase)

More
34
Neural Network Modeling Results
“Three-Minute training set”

35
Neural Network Modeling Result
“Three-Minute set”: test #1 and #2
Test #1

Test #2

36
NN Summary
 Insufficient data for one-minute and two-
minute prediction models
 Three-minute network shows better
performance than the decision tree
model:
• Other - 17% error rate
• Eng1 - 28% error rate
• Eng2 - 20% error rate

37
Conclusions
 Predictive model can be built
 Neural Network model is more accurate
than the Decision Tree one
• Based on all data
 Overall accuracy is not sufficient for
practical applications
 More data is needed to train and test the
models

38
References
 Failure Pattern Recognition of a Mining
Truck with a Decision Tree Algorithm
• Tad Golosinski & Hui Hu, Mineral Resources
Engineering, 2002 (?)
 Intelligent Miner-Data Mining Application
for Modeling VIMS Condition Monitoring
Data
• Tad Golosinski and Hui Hu, ANNIE, 2001, St. Louis
 Data Mining VIMS Data for Information on
Truck Condition
• Tad Golosinski and Hui Hu, APCOM 2001, Beijing, P.R.
China
39
40

Das könnte Ihnen auch gefallen