Você está na página 1de 6

Underground Space – the 4th Dimension of Metropolises – Barták, Hrdina, Romancov & Zlámal (eds)

© 2007 Taylor & Francis Group, London, ISBN 978-0-415-40807-3

Expert system for D&B tunnel construction

C.W. Yu & J.C. Chern


Sinotech Engineering Consultants, Inc., Taipei, Taiwan

ABSTRACT: To improve the technology for drill and blast tunnel construction in Taiwan, an expert system
consisted of data bank, tool bank and decision making auxiliary system has been developed. Various tools
can be used efficiently in carrying out data collection, processing, analysis and evaluation work required in
the tunneling process. Using the successful tunnel case histories data learned from the past experiences, the
system can provide multi-expertise assistance on the decision of support system and excavation procedures to be
adopted in the construction site. The system can also provide rational estimation on the tunnel deformation under
the selected support system and construction procedure with the aid of an artificial neural network approach.
Application of the system to actual tunnel construction is given for demonstrating the capability of the system.

1 INTRODUCTION

The engineering practice for drilling and blasting


(D&B) tunnel construction in Taiwan adopts similar
approach used in the western countries. In the design
stage, support requirements and construction proced-
ures were pre-determined by using empirical rock
classification method, mainly based on limited geo-
logical information and rock mass conditions obtained
from the preliminary investigations.
During construction, actual rock mass rating was
obtained at the tunnel face, and appropriate support
system and construction procedures were selected and
implemented. Monitoring instruments were installed
for observing the performance of rock masses sur- Figure 1. Systematic pre-stressed tendons, re-mining and
rounding the tunnel. Revision and remediation were re-supporting had to be used to control large deformation of
made on the support system or construction proced- tunnel through a dry fault zone in the construction of the
ures, if necessary, to achieve a safe and economic Second Freeway in northern Taiwan.
tunnel construction.
However, due to the poor rock condition often
encountered in Taiwan, excavation large span tunnel different geological environments have become issues
through poor quality rock mass has resulted in numer- for the local tunneling community. This also calls for
ous engineering difficulties in the past two decades. the development of a more rational system to deal
These difficulties included uncontrolled excessive tun- with the processes in D&B tunnel construction. This
nel deformation, serious damage to the support system paper presents the system and its application in a tunnel
and even tunnel cave-in. construction project.
Figure 1 shows an example of driving a large
span tunnel through a fault zone in northern Taiwan
by using the traditional rock classification method. 2 EXPERT SYSTEM FOR TUNNEL
It required systematic pre-stressed tendons and re- CONSTRUCTION
mining and re-supporting the tunnel to overcome
the uncontrolled excessive deformation. Controver- The tunnel expert system compiles expert knowledge
sies over the adequacy of tunnel support design and tools for facilitating the data collection and pro-
and construction procedures based on experiences of cessing, data analysis and evaluation, and decision

799
and production of developed geological map of
tunnel surface.
(2) Key Block Analysis System (TUN_KBL) can
be used to perform key block analysis from the
actual recorded joint information or statistically
generated joint information.
(3) Construction Decision Making Auxiliary System
(TUN_AUX) is a case history based artificial
intelligence system for making multi-expertise
recommendations on tunnel support system and
construction procedures.
(4) Tunnel Deformation Prediction System (TUN_
DEF) is an numerical analysis data based artifi-
cial neural network system for providing a rational
estimation on the tunnel deformation under vari-
ous geological and construction conditions.
(5) Tunnel Construction Simulation System (TUN_
CAD) provides numerical analysis programs for
carrying out back analysis of monitoring data and
Figure 2. Working processes of the expert system forward prediction analysis of tunnel performance
developed. by simulating the construction processes in the
field.
Table 1. Tool bank of the expert system. (6) Tunnel Safety Evaluation System (TUN_SAF)
utilizes the monitoring tunnel deformation for
Tools Main functions evaluating the safety of tunnel construction by
using a case history based empirical tunnel safety
TUN_MAP Geological Information Collecting and
criterion.
Processing
TUN_KBL Key Block Analysis (7) Construction Status Demonstration System
TUN_AUX Construction Decision-making Assistance (TUN_STA) uses the records collected during
TUN_DEF Deformation Prediction tunnel excavation, including geological informa-
TUN_CAD Construction Simulating tion, monitoring data and construction progress
TUN_SAF Tunnel Safety Evaluation records, for demonstrating the status of tunnel
TUN_STA Construction Status Demonstrating construction.
The application for some of the systems will be
demonstrated by the results of case study presented.
making in the tunnel construction processes. Figure 2
shows the working processes of the system.
The working processes contain 3 major blocks, i.e., 4 DECISION-MAKING MODULES
(1) construction data collection at the site, (2) tool bank
for various data processing, analysis, simulation and Decision-making modules include the recommen-
evaluation, and (3) decision making for support design dation of optimum tunnel support requirement and
and construction procedures recommendation, safety construction procedures, tunnel deformation estima-
evaluation and construction status demonstration. tion and safety evaluation during tunnel construction
The functions of each module in the tool bank stages. It also provides the status of tunnel construc-
are outlined in Table 1. The working process will be tion for better control of construction progress and
described further in the following sections. tunneling conditions by the tunnel engineer.

3 TOOL BANK 4.1 Optimum support requirement


A Decision Making Auxiliary System (TUN_AUX)
The tool bank of the expert system comprises of 7
is a case-based artificial intelligence system together
subsystems as shown inTable 1, and the main functions
with the traditional empirical rock classification sys-
of the subsystems are:
tem. The working processes of system TUN_AUX are
(1) Geological Information Collecting and Process- shown in Figure 3.
ing System (TUN_MAP) utilizes digital image In the field, the parameters, including the tunnel
taken on the tunnel face to retrieve the geological span, strength of rock material, rock mass classifica-
information for statistical analysis of joint systems tion and overburden depth, collected are used for the

800
Figure 3. Flow chart of application of rock support decision- Figure 4. Optimized chart for selecting a suitable excav-
making auxiliary system. ation procedure according to tunnel span and the strength
stress ratio.
expert system. TUN_AUX can give a multi-expertise
recommendations on the major support elements such
as the length and spacing of rock bolts, thickness of
shotcrete, size and spacing of steel sets, etc.

4.2 Optimum construction procedures


The Decision Making Auxiliary System (TUN_AUX)
also provides a function for the recommendation of
optimum construction procedure. The excavation pro-
cedures suitable for various tunnel spans and ground
conditions were categorized into full face, central
diaphragm (CD) and side drift. Based on the expert
knowledge collected from experienced tunnel engin-
eers and the results of construction simulation under
various tunneling conditions, the optimum construc-
tion procedure is suggested by the tunnel span and
strength/stress ratio at the construction site. The chart Figure 5. Four-lane freeway tunnel driven by dual side-drift
for selecting a suitable construction procedure is excavation method adjacent to a shallow slope.
shown in Figure 4. Figure 5 shows the construc-
tion of a four-lane freeway tunnel under poor ground
and very shallow rock cover by using dual side-drift 4.4 Tunnel safety evaluation
method. Severe unstable condition was developed in a
3-lane adjacent tunnel with top heading and benching Empirical tunnel safety criterion based on case histor-
procedure. ies in Taiwan (Chern, et al. 1998) is used in the safety
evaluation of tunnel. In the criterion, the information
of the tunnel inward movement (δ), tunnel radius (R),
4.3 Tunnel deformation estimation
rock mass strength (UCS) and actual performance of
Tunnel Deformation Prediction System (TUN_DEF) tunnel case histories were used to establish 3 warning
provides an estimation on the magnitude of tunnel levels of tunnel safety and the necessary measures to
deformation expected under various geological and be taken.
construction conditions. The system was developed Below warning level I, tunnel is considered to be in
based on large amount of 3-D numerical simulations stable condition, and no special measure is required.
of the tunnel construction under various geological Between warning levels II and III, tunnel is susceptible
conditions, excavation sequences and support meas- to instability, and review of support system and con-
ures. Tunnel deformations, including roof settlement, struction procedures adopted should be made. Above
horizontal convergency, as well as plastic zone thick- warning level III, tunnel is in unstable condition, and
ness were given by a back propagation artificial neural remedial measures should be taken to stabilize the
network from the data base. It is intended to provide tunnel.
a rough estimate on the order of magnitude of tunnel Figure 6 shows the flow chart of tunnel safety
deformation expected as guidance for tunnel engineer. evaluation using TUN_DEF and TUN_SAF systems.

801
Table 2. Suggested support elements predicted by the
system.

Advance Rockbolt Shotcrete Steel-


Support type per round length thickness rib size

Design Type III 1.0–1.4 m 4 m 20 cm G220∗


Design Type IV 0.8–1.2 m 6 m 25 cm G220∗
Suggested 1.5–2.0 m 6–8 m 20–25 cm H125†
Type III
Suggested 1.0–1.5 m 8–10 m 20–25 cm H150†
Type IV
Figure 6. Flow chart of tunnel deformation prediction and
safety evaluation. ∗
Use lattice girdle. †Use H-beam.

Figure 7. Geological profile of the flood diversion tunnel. Figure 9. The highly disturbed rock exposed at 2k+008.

Five support types were proportioned according to the


RMR rating. The rock support requirements were also
examined by using the expert system TUN_AUX dur-
ing construction. The results for type III and type IV
rock are shown inTable 2 along with the original design
of support system.
Most of the tunnel sections belong to the good qual-
ity rock with type II and type III support systems. The
type III support adopted worked quite well. However,
in a disturbed zone adjacent to the volcanic intrusion
near station 2k+008, the poor quality rock mass (Fig-
Figure 8. Tunnel section showing the excavation span and ure 9) with RMR values in the range of 28 to 34 showed
excavation steps.
squeezing behavior under 140 m overburden stress.
The monitoring results during tunnel excavation are
5 CASE STUDY shown in Figure 10.
The monitoring data for top heading excavation
To illustrate the application of the system developed, showed potential unstable condition according to the
a case study on a flood diversion tunnel in northern tunnel safety evaluating system TUN_SAF as shown
Taiwan is presented. in Figure 11. This proved to be true by the tunnel
The diversion tunnel is 2,835 m long driving convergence occurred during subsequent benching.
through sedimentary rock formation of Miocene Age. Reviewing the support requirement and excavation
The geological profile is shown in Figure 7. The max- procedure, it was found that the expert system would
imum excavation span is 14.1 m and was excavated in suggest a more conservative support system and exca-
3 stages as shown in Figure 8. The major difficulties vation procedure. These can be shown by the longer
encountered in tunneling are associated with the fault bolt length as suggested in Table 2, and excavation by
zones and the disturbed zones adjacent to a volcanic CD or side drift method recommended as shown in
intrusion. Figure 12.
The rock support system was designed according Before benching, various remedial measures were
to the traditional RMR rock classification method. further studies by using 3-D numerical simulations.

802
enhance the tunnel stability. The tunnel did not suffer
from severe unstable condition during benching, but
rather large tunnel convergence occurred with accom-
panying cracks of shotcrete in the tunnel crown area.
This is also predicted by the tunnel safety evaluation
system as shown in Figure 11.

6 CONCLUSIONS

An expert system consisted of tools and expert know-


ledge for performing construction data collection and
processing, data evaluation and analysis, and decision
making assistance in the working process of D&B
Figure 10. Monitoring results during tunnel excavation in tunneling was developed. The results of preliminary
disturbed zone near 2k+008. application of the system in the construction of a
flood diversion tunnel showed the system can provide
efficient tools for carrying out various data collec-
tion, analysis and evaluation work in the tunneling
process. Rational suggestions on support require-
ment, construction procedure and safety evaluation
can also assist the field engineer in the decision making
process.
However, In a practical application sense, the sys-
tem developed is considered to be a prototype due
to the lack of precedence and case histories with
sufficient accuracy covering wide range of tunnel
conditions. For further improvement of the system,
trial application and collection of additional case
information are still needed.

REFERENCES
Figure 11. Potential unstable condition according to
TUN_SAF evaluation. Hoek, E. and Brown, E.T. 1980, Underground excavations in
rock, London: Institution of Mining and Metallurgy.
Dershowitz, W.S. and Einstein, H.H. 1984, Application of
Artificial Intelligence to Problems of Rock Mechanics,
25th W. S. Symp. Rock Mechanics, pp.483–494.
Zhang, Q., Mo, Y. and Tian, S. 1988, An Expert System
for Classification of Rock Masses, Proc. 29th U.S. Symp.
Rock Mech., pp.283–288.
Butler, A.G. and Franklin, J. A. 1990, Classex: Expert System
for Rock Mass Classification, Proc. ISRM Int. Symp. Rock
Mech., Mbabane, Swaziland, pp.73–80.
Zhang, Q., Nie, X.Y. and Tian, W.T. 1995, A Case-Based
Reasoning for Tunnel Support, Proc. 8th Int. Cong. Rock
Mech., Tokyo, pp.907–909.
Chern, J.C., Shiao, F.Y. and Yu, C.W. 1998, An empirical
safety criterion for tunnel construction. Proc., Reg. Symp.
Sedimentary Rock Engineering, Taipei, 325–330.
Palassi, M. and Franklin, J.A. 1998,Tunnex:An Expert System
for Tunnelling through Rock. Tunnelling Association of
Figure 12. Excavation by CD or side drift method as Canada (TAC) News, Vol. 16, No. 1, pp.12–18.
recommended. Hoek, E. 2001. Big tunnel in bad rock. Journal of Geotech-
nical & Geoenvironment Engineering, Vol.127, 726–740.
The predicted tunnel deformations after benching Liu, J.M. 2005. River Yuanshantzu flood-diversion project.
down are shown in Figure 11. Due to limited option Proc., Int. Symp. Design, Construction and Operation of
available at the construction site, only additional Long Tunnel, Taipei: 923–933.
9-meter long systematic bolts were installed to

803

Você também pode gostar