You are on page 1of 40

Modeling Condition And Performance Of Mining Equipment

Tad S. Golosinski and Hui Hu

Mining Engineering University of Missouri-Rolla

Condition and Performance Monitoring Systems

Machine health monitoring

Allows for quick diagnostics of problems Provides management with machine and fleet
performance data

Payload and productivity


Warning system

Alerts operator of problems, reducing the risk


of catastrophic failure
2

CATs VIMS

(Vital Information Management System)

Collects / processes information on major machine components

Installed on

Off-highway trucks Hydraulic shovels

785, 789, 793, 797

Engine control Transmission/chassis control Braking control Payload measurement system

5130, 5230

Wheel loaders

994, 992G (optional)

Other, Similar Systems


Cummins

CENSE (Engine Module) Contronics & Haultronics VHMS (Vehicle Health Monitoring System)

Euclid-Hitachi

Komatsu
LeTourneau

LINCS (LeTourneau Integrated Network Control System)

Round Mountain Gold Mine


Truck Fleet
17 CAT 785 (150t) 11 CAT 789B (190t)

PSA
(Product Support Agreement) CAT dealer guarantees 88% availability

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


6

Holmes Safety Association Bulletin 1998

CAT MineStar

CAT MineStar - Integrates

Machine Tracking System

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

Cummins Mining Gateway


Modem MiningGateway.com Database CENSE

Cummins Engine

Base Station

RF Receiver

Modem
8

VIMS Data & Information Flow


Mine Site 1 VIMS Legacy Database

Mine Site 2
Mine Site 3

Data Extract Data Cleanup Data Load

VIMS Data Warehouse

Information Extraction Information Apply

Data Mining 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 Acquisition

Data Preparation

Result Interpretation

Data Mining

12

VIMS Features
Operator

Download

Sensors & Controls Monitor & Store


Maintenance

Event list Event recorder Data logger Trends Cumulative data Histograms Payloads

Wireless Link

VIMS wireless

Management

13

Data Source

14

VIMS Statistical Data Warehouse 1-3 minute interval statistical data



0_6 0_7 0_8 0_9 767_1 767_2 767_3 767_4 767_5 767_6

Minimum Maximum Average Data Range Variance


TC_OUT_TEMP_AVG 70.35 64.95 65.67 66.30 80.00 80.37 80.95 81.32 81.83 83.43 73 66 66 67 80 81 81 82 82 87


TC_OUT_TEMP_MAX

Regression Intercept Regression Slope Regression SYY Standard Deviation


TC_OUT_TEMP_MIN 65 64 65 66 80 80 80 81 81 82 TC_OUT_TEMP_RANGE 8 2 1 1 0 1 1 1 1 5

EVENT ID

15

VIMS Data Description


Six CAT 789B trucks 300 MB of VIMS data 79 High Engine Speed events
One-minute data statistics

Dataset Training Set Test set 1 (#1) Test set 2 (#2) Total

Count of Record 1870 86.4% 98 13.6% 196 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 ginisplit ( s) gini( s1 ) gini( s2 ) n n


Strictly binary tree Built-in v-fold cross validation


17

18

VIMS EVENT PREDICTION


Normal Engine Speed High Engine Speed Snapshot Normal Engine Speed

VIMS Data Event_ID Predicted Label

0 0 0 0 0 0 1 2 3 4 5 6 0 0 0 0 0
High Eng

767_1 Other Other Eng_1

767_2
Eng_2 Other Other

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 Other Eng1 Eng3 Eng2 Eng4 Eng6 | 1331 | | | | | | 0| 0| 0| 0| 0| 18 | 62 | 11 | 12 | 3| 0| 9| 1| 51 | 8| 7| 0| 5| 3| 2| 38 | 2| 1| | Eng6 | Eng5 | 6| 0| 1| 0| 0| 61 | 1 | total = 1386 0 | total = 66 0 | total = 67 0 | total = 65 1 | total = 68 4 | total = 66

---------------------------------------------------------------------------------------------------------------16 | 0| 2| 7| 55 | 0|

Eng5

0|
1331 |

0|
106 |

0|
76 |

0|
51 |

0|
80 |

0|
68 |

64 | total = 64
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 Eng1 Eng3 Eng2 Eng4 Eng6 Eng5 | | | | | | | 59 | 4| 0| 1| 1| 0| 0| 65 | 3| 1| 3| 1| 1| 0| 0| 9| 0| 0| 1| 1| 0| 0| 0| 2| 2| 1| 0| 1| 1| 0| 0| 5| 3| 0| 1| 0| 1| 0| 0| 5| 0| 0| 0| 0| 0| 7| 0| 7| 1 | total = 68 0 | total = 6 0 | total = 5 0 | total = 4 0 | total = 4 0 | total = 7 6 | total = 6 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 Eng1 Eng3 Eng2 Eng4 Eng6 | | | | | | 141 | 2| 2| 2| 1| 0| 9| 2| 1| 1| 0| 0| 2| 1| 2| 2| 1| 0| 4| 1| 0| 1| 1| 0| 4| 0| 1| 0| 3| 0| 0| 0| 0| 0| 0| 6| 0 | total = 160 0 | total = 6 0 | total = 6 0| 0| 0| total = 6 total = 6 total = 6

Eng5

0|
148 |

0|
13 |

0|
8|

0|
7|

0|
8|

0|
6|

6|

total = 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
ENG1 ENG2 ENG3

|
| | |

657 |
0| 0| 0| 657 |

6|
62 | 13 | 0| 81 |

19 |
10 | 54 | 0| 83 |

3|
0| 0| 64 | 67 |

total = 685
total = 72 total = 67 total = 64 total = 888
25

---------------------------------------------------------------------

Decision Tree
Test #1 on Two-Minute Data

Total Errors = 14 (29.79%)


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

---------------------------------------------------------------------

OTHER
ENG1 ENG2 ENG3

|
| | |

28 |
1| 2| 0| 31 |

5|
0| 1| 0| 6|

4|
0| 1| 0| 5|

1|
0| 0| 4| 5|

total = 38
total = 1 total = 4 total = 4 total = 47
26

---------------------------------------------------------------------

Decision Tree
Test #2 on Two-Minute Data

Total Errors = 15 (15.31%)


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

---------------------------------------------------------------------

OTHER
ENG1 ENG2 ENG3

|
| | |

71 |
3| 0| 0| 74 |

8|
3| 3| 0| 14 |

1|
0| 3| 0| 4|

0|
0| 0| 6| 6|

total = 80
total = 6 total = 6 total = 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 OTHER ENG1 ENG2 | | | 411 | 1| 0| 412 | | ENG2 23 | 65 | 0| 88 | | 4| 0| 70 | 74 | total = 438 total = 66 total = 70 total = 574

----------------------------------------------------

----------------------------------------------------

29

Decision Tree
Test #1 on Three-Minute Data

Total Errors = 12 (19.05%)


Predicted Class --> | OTHER OTHER ENG1 ENG2 | | | | ENG1 | ENG2 9| 5| 0| 14 | | 0| 0| 4| 4| total = 51 total = 8 total = 4 total = 63

---------------------------------------------------42 | 3| 0| 45 |

----------------------------------------------------

30

Decision Tree
Test #2 on Three-Minute Data

Total Errors = 9 (14.06%)


Predicted Class --> | OTHER OTHER ENG1 ENG2 | | | | ENG1 47 | 4| 0| 51 | | ENG2 5| 2| 0| 7| | 0| 0| 6| 6| total = 52 total = 6 total = 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
32

Other approach?

Backpropagation
A Neural Network Classification Algorithm

Node
x1 x2 x3 Input Hidden Layer Out w1

Node Detail

w2
w3

f(z)

z = Siw ix i
Some choices for F(z): f(z) = 1 / [1+e-z] (sigmoid) f(z) = (1-e-2z) / (1+e-2z) (tanh)
33

Characteristic: Each output corresponds to a possible classification.

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. tk is the true value.

Freeman & Skapura, Neural Networks, Addison Wesley, 1992


In the graph:

EW j ,k

E and solve EW j ,k 0 for W j ,k W j ,k

Ep is the sum of squares error


Ep is the gradient, (direction of maximum function increase)

34 More

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 twominute 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

You might also like