Professional Documents
Culture Documents
Imp 290899-1561291928550)
Imp 290899-1561291928550)
Abstract: Proportioning of concrete mixes is carried out in accordance with specified code information, specifications, and past expe-
riences. Typically, concrete mix companies use different mix designs that are used to establish tried and tested datasets. Thus, a model can
Downloaded from ascelibrary.org by University of Notre Dame on 08/24/14. Copyright ASCE. For personal use only; all rights reserved.
be developed based on existing datasets to estimate the concrete strength of a given mix proportioning and avoid costly tests and
adjustments. Inherent uncertainties encountered in the model can be handled with fuzzy based methods, which are capable of incorpo-
rating information obtained from expert knowledge and datasets. In this paper, the use of adaptive neuro-fuzzy inferencing system is
proposed to train a fuzzy model and estimate concrete strength. The efficiency of the proposed method is verified using actual concrete
mix proportioning datasets reported in the literature, and the corresponding coefficient of determination r2 range from 0.970–0.999.
Further, sensitivity analysis is carried out to highlight the impact of different mix constituents on the estimate concrete strength.
DOI: 10.1061/共ASCE兲0899-1561共2007兲19:7共550兲
CE Database subject headings: Fuzzy sets; Compressive strength; Concrete; Mixing; Strength.
a model developed based on expert knowledge and/or input- It has been demonstrated 共Sugeno and Tanaka 1991兲 that the
output data. The inference mechanism then uses the knowledge TSK models can accurately represent complex behavior with a
base to estimate the output of the system for given inputs. A few rules. Although the TSK fuzzy models are computationally
modularized design of the FIS enables it to maintain a generic less involved than the Mamdani type fuzzy models, the difficulty
processing structure that is capable of dealing with various in defining a numerical function for the output propositions has
systems in different application domains 共e.g., physical, medical, often made them less attractive in fuzzy applications. This prob-
financial兲 as long as a relevant knowledge base is defined. Also, lem is resolved when the model is constructed automatically
the FIS can be readily updated by modifying the knowledge base based on input-output data acquired from the systems. Another
using new information as it becomes available. problem with the TSK models is that it is difficult to assign an
appropriate linguistic term to the consequence propositions of the
TSK models, but this will not be a problem if a qualitative model
Knowledge Base
of the system is not required.
The knowledge base defines the relationships between the input The rule base of a complex system usually requires a large
and output parameters of a system. The most commonly used number of rules to describe the behavior of a system for all
representation of the input-output relationships is Mamdani type possible values of the input variables. This is referred to as the
fuzzy models 共after Mamdani, 1977兲. In this type of fuzzy “completeness” of a fuzzy model. The aggregation of the rules
models, linguistic propositions are used both in antecedent and described in Eq. 共1兲 forms a rule base that is valid over the entire
consequent parts of the IF-THEN rules. application domain. The aggregation is obtained using the union
Another type of representing the input-output relationships is of the rules or subsystems as
Takagi-Sugeno-Kang 共TSK兲 共Takagi and Sugeno 1985兲 fuzzy
models in which the antecedent part of the rules is composed of n
linguistic propositions, but the consequent parts is defined by R = 艛 Ri = R1 ALSO R2 ALSO . . . ALSO Rn 共2兲
i=1
either a constant number 共zeroth order兲 or linear equations 共first
order兲. A first-order TSK model of a multi-input-single-output
system may be represented by a set of linear subsystems 共rules兲 Inference Mechanism
each of which defined by a linear consequent statement
The inference mechanism of Mamdani type and TSK fuzzy mod-
Ri:IF x1 is Ai1 AND . . . xm is Aim els are slightly different. Mamdani’s inference mechanism 关Fig.
3共a兲兴 consists of three connectives: The aggregation of anteced-
THEN y i = bi0 + bi1x1 + ¯ + bimxm, i = 1, . . . ,n 共1兲
ents in each rule 共AND connectives兲, implication 共i.e., IF-THEN
where Ri represents the ith rule, n⫽total number of rules, x j connectives兲, and aggregation of the rules 共ALSO connectives兲.
共j = 1 , . . . , m兲⫽input variables, y i⫽output variable, Aij⫽input The operators performing the connectives distinguish the type of
fuzzy set defined in the input space U j, and bij⫽consequent pa- fuzzy inferencing. The AND and ALSO connectives are chosen
rameters. Thus, every rule is a local fuzzy relationship that maps from a family of t-norm and t-conorm operators, respectively.
a part of the multidimensional input space U into a certain part of Comprehensive discussions on t-norm 共e.g., minimum and prod-
the output space V. uct operators兲 and t-conorm 共e.g., maximum and sum operators兲
Clearly, the appropriate number of rules depends on the where aij and cij⫽antecedent parameters of the FIS.
complexity of the system. According to Sugeno and Yasukawa 2. Layer 2: Every node i in this layer is a fixed node, labeled ⌸,
共1993兲, the number of fuzzy rules corresponds to the order of a which multiplies the incoming signals and sends the product
conventional model where an optimal model minimizes both the out
order and the output error. A statistical analysis for evaluating the m
optimal order of a model is discussed by Akaike 共1974兲. A large
number of rules, similar to a high order of a model, will bias the
O2,i = wi = 兿
j=1
A 共x j兲
ij
共8兲
model towards specific data that can be imprecise or even
erroneous. On the other hand, less number of rules will likely where wi⫽degree of firing strength 共dof兲 of rule i. Any
increase the output error, which is essentially equivalent to t-norm operator that performs AND connective can be used
Downloaded from ascelibrary.org by University of Notre Dame on 08/24/14. Copyright ASCE. For personal use only; all rights reserved.
disregarding the effect of some of the data points containing as the node function in this layer.
valuable information. Thus, the optimal number of rules n can be 3. Layer 3: Every node in this layer is a fixed node labeled N.
obtained from a tradeoff between the number of rules and the The ith node calculates the ration of the ith rule’s firing
output error. The number of rules will be automatically strength to the sum of all rules’ firing strength
determined through clustering the input and output spaces. Each
wi
cluster center is used as the basis of a rule that describes the O3,i = w̄i = n 共9兲
system behavior. Thus, the neighborhood radii ra and rb can be
selected such that an optimal number of rules is achieved. 兺
k=1
wk
similar to those used in Kim et al. 共2004兲 and Kim et al. 共2005兲.
The reported data were gathered from actual mix proportions of
two companies, Company A and Company B. The overall basic
material properties between the two companies are similar, with
the exception of sand used. Company B uses only natural sand,
whereas, Company A mixes both natural and crushed sand.
Sample input data of the specified concrete mix proportions of
Company A and B are presented in Table 1, respectively. Further,
the main difference between the reported Kim et al. 共2004兲 and
Kim et al. 共2005兲 data is the units assigned to the mix proportions.
Kim et al. 共2004兲 use kN / m3 for water, cement, fine aggregate,
and coarse aggregate contents, whereas, Kim et al. 共2005兲 use
kg/ m3 for those proportions. Consequently, to combine the two
datasets, the kN / m3 units 共shown in Table 1兲 are converted into
kg/ m3.
Fig. 4. Flowchart of ANFIS model development for concrete The Company A and B data were combined for model training
strength modeling under the assumption that the data are commensurate. Hence, the
final training data for Company A and B consist of 45 data points
each. Further, a combined model of Company A and B, hence-
forth, described as Company A-B is generated using a total of 90
rates propagate backward and the antecedent parameters are up- training data points. It is noted that Company A and B have dif-
dated by the gradient descent. The learning process is continued ferent fine aggregate constituents. Thus, for combined Company
based on a learning rule, usually represented by the discrepancy A-B data, the natural and crushed sand of Company A are com-
between the desired output and the network output under the bined and represented with a single fine aggregate 共FA兲 label. For
same input conditions. This discrepancy is called the error mea- brevity, data are not repeated here; curious readers are referred to
sure, which is usually defined as the sum of the squared differ- Kim et al. 共2004兲 and Kim et al. 共2005兲.
ences between the desired and network outputs. Kim et al. 共2004兲 and Kim et al. 共2005兲 have considered nine
Table 1. Sample Input Data, Specified Concrete Mix Proportions of Company A and Company B for Traininga
Fine Unit Unit fine aggregate content Unit coarse
Specified Water-cement aggregate Unit water cement 共kN/ m3兲 aggregate
strength Slump ratio percentage content content content Admixture
共MPa兲 共cm兲 共w/c兲 共%兲 共kN/ m3兲 共kN/ m3兲 Natural sand 共s1兲 Crushed sand 共s2兲 共kN/ m3兲 共%兲
Company A
15.68 10 64.2 46.6 1.75 2.73 3.28 4.93 9.67 0.84
15.68 15 64.2 47.6 1.86 2.90 3.27 4.92 9.26 0.89
— — — — — — — — — —
39.20 15 32.1 41.2 1.76 5.50 2.53 3.79 9.26 1.68
39.20 18 32.1 41.8 1.82 5.67 2.51 3.77 8.99 1.74
Company B
15.68 10 63.1 50.9 1.68 2.66 9.23 — 9.08 1.36
15.68 15 63.2 50.4 1.76 2.79 8.98 — 9.01 1.43
— — — — — — — — — —
39.20 15 33.2 44.4 1.71 5.14 7.11 — 9.08 2.62
39.20 18 33.2 44.1 1.75 5.28 6.96 — 9.00 2.70
a
From Kim et al. 2004.
ANFIS is used for structure and parameter identification as out- wi = Slump共Slump兲 ⫻ w/c共w/c兲 ⫻ FA共FA兲 ⫻ CA共CA兲
lined in the previous section. The models are generated using
datasets of Company A, Company B, and the combination of ⫻ Amix共Amix兲
Company A and B that are referred to as Model A, Model B, and Layer three entails normalization of the ith rule strength to the
Model A-B, respectively. Moreover, each of the three models is sum of all rules firing strength Eq. 共9兲
implemented for absolute variables and relative variables, which
are referred to as absolute model and relative model, respectively.
wi
In this way, a total of six models are generated. Initial sensitivity w̄i =
analysis is carried out to observe if there is any significant differ- w1 + w3 + w3 + w4
ence between the actual concrete strength and those predicted Hence, w̄i is called normalized firing strengths. Layer four com-
using the six models. The analysis showed that the results are putes the corresponding output Oi strength estimation of Rule i
only slightly different. Nevertheless, for a pragmatic model appli- Eq. 共10兲
cation, where a more generic model with the minimum number of
inputs is typically more desirable, Model A-B is preferable. The Oi = w̄iy i = w̄i共b1 ⫻ slump + b2 ⫻ w/c + b3 ⫻ FA + b4 ⫻ CA + b5
ensuing discussion is only for the relative Model A-B, but the
derived conclusion is equally applicable to the other five models. ⫻ Amix + b0兲
The FIS generated for the five relative input parameters 共Table The parameters, 兵b1, b2, b3, and b4其 are referred as consequent
2: Slump, w / c ratio, FA, CA, Amix兲 has four rules. Each input parameters 共Table 4兲. For example, the model output from Rule 1
parameter is modeled using a Gaussian type membership function can be shown as
Eq. 共7兲. Result of coefficients of the Gaussian type membership
function, for slump 共Slump兲, w / c ratio 共w/c兲, FA 共FA兲, CA
O1 = w̄1共− 0.0471 ⫻ slump − 0.4684 ⫻ w/c + 0.4255 ⫻ FA %
共CA兲, and Amix 共Amix兲 are summarized in Table 3. For ex-
ample, from Table 3, the Slump associated with Rule 1 is + 0.000988 ⫻ CA − 8.866 ⫻ Amix + 34.46兲
Fig. 6. Comparison of target and predicted concrete strength for a combined and relative model
Discussion
Fig. 7. Sensitivity analysis of concrete strength input parameters
Concrete mix proportioning is a highly nonlinear process that is
using a tornado graphs
also subject to experimental error 共Kim et al. 2004兲. Reliable
prediction of concrete strength necessitates the development of
models which are tolerant of various manifestations of that stringent quality control of the in situ w / c ratio should be
uncertainty. Identification of dominant parameters can help to implemented.
implement stringent monitoring and quality control during mix Further, two parameters at a time simulation is carried out for
proportioning 共Jain et al. 2005兲. A sensitivity analysis is the three most dominant variables; w / c ratio, CA, and FA. Fig.
commonly carried out using random sampling 共Monte Carlo-type 8共a兲 shows the simulation between the w / c ratio and CA. At a
simulations兲 where the probability distributions for input data can higher CA content, e.g., 60%, there is a linear decrease in con-
either be assumed or derived from observations. Thereafter, the crete strength with an increase in the w / c ratio. At a lower CA
rank correlation method 共Cullen and Frey 1999兲 is applied to the content, e.g., 10%, the variation of the w / c ratio from 40% to
results of the Monte Carlo simulations to identify input data/ roughly 65% show negligible variation. However, at CA= 10%,
parameters that dominate the output. The rank correlation method significant decrease in concrete strength is observed with an in-
crease in the w / c ratio from 65% to 80%. At a lower w / c ratio,
involves the determination of coefficient of determinations, which
e.g., ⬍50%, an increase in CA content 共from 10% to 30%兲 is
measure the strength of the linear relationship between two
followed by a decrease in concrete strength. However, with fur-
variables. The procedure utilized for the sensitivity analysis is as
ther increase in the CA content 共from 30% to 60%兲, the concrete
reported in Tesfamariam et al. 共2006兲 and the basic steps are
strength increases. This relation is in agreement with a reported
outlined here. For ns number of realization,
共Neville 1997兲 relationship, and Neville underlined that the rea-
1. For i = 1 to ns,
son for this effect is not clear. At a higher w / c ratio, an increase
• Generate a uniformly distributed random numbers for the
in the CA content 共beyond 35%兲 reaches minima and the variation
five input parameters 共ranging between the min and max
is not significant.
values兲, x j;
Fig. 8共b兲 shows the relationship between FA and w / c ratio. In
• Compute the corresponding membership function Eqs. 共6兲
general, an increase in FA and a decrease in the w / c ratio are
and 共7兲, Aij共x j兲;
followed by a linear increase in concrete strength. Fig. 8共c兲 shows
• Compute the dof Eq. 共8兲 and normalized dof Eq. 共9兲; and
the variation of CA and FA in the estimated concrete strength. At
• Compute the output of each layer Eq. 共10兲 and normalized
any level of the FA content, increase in CA is followed by a
output Eq. 共11兲.
decrease in concrete strength; however, after 35% CA content, it
2. Next i
reaches minima. Similarly, and increase in FA is followed by an
• For the n input-output results, rank order the results and increase in concrete in strength, however, after 48% FA, it reaches
perform rank correlation; and a maxima.
• Normalize the rank correlation results and show the result The accuracy of the ANFIS model generated from the input
on a tornado graph. parameters may be compromised outside the range of the training
Sensitivity analysis of the FIS model is carried out for 3,000 datasets. The input parameters for the proposed ANFIS model
realizations from the relative Model A-B, and the results of the discussed in this paper are bounded within the following ranges:
rank correlation are normalized to the sum of one and are plotted Slump, mm 关5, 18兴; unit water content 关160, 185兴; unit cement
in a tornado graph 共Fig. 7兲. Fig. 7 shows that an increase in CA content, kg/ m3 关228, 524兴; unit FA content, kg/ m3 共663, 1004兲;
共16% contribution兲 and w / c ratio 共72% contribution兲 decreases unit CA content, kg/ m3 关882, 1060兴; admixture, % 关0.7, 2.6兴; and
the concrete strength. Clearly, the contribution of Slump is not specified strength, MPa 关10.8, 39.2兴. Extrapolating the model out-
considerable. On other hand, an increase in FA 共11% contribution兲 side these limits should be carried out with caution.
and Amix 共1% contribution兲, albeit to a smaller degree, is fol-
lowed by an increase in the concrete strength. It is interesting to
note that the impact of CA, w / c ratio, Amix, and FA is in agree- Conclusions
ment with the results reported in Neville 共1997兲. Overall the w / c
ratio is the most dominant parameter towards the variability of Concrete mix proportioning is a nonlinear process, for which de-
the concrete strength. This reinforces our intuitive understanding veloping a comprehensive and reliable analytical model is rather
Notation
vergence theory for fuzzy c-means: Counterexamples and repairs.” neural networks for proportioning of concrete mixes.” ACI Mater. J.,
The analysis of fuzzy information, Bezdek, J., ed., CRC, 3, Chap. 8. 96共1兲, 61–67.
Chang, F.-J., and Chang, Y.-T. 共2006兲. “Adaptive neuro-fuzzy inference Rumelhart, D. E., Hinton, G. E., and Williams, R. J. 共1986兲. “Learning
system for prediction of water level in reservoir. Advances in Water internal representations by error propagation.” Parallel distributed
Resources.” Adv. Water Resour., 29共1兲, 1–10. processing: Explorations in the microstructure of cognition, D. E.
Chau, K. W., Wu, C. L., and Li, Y. S. 共2005兲. “Comparison of several Rumelhart and J. L. McClelland, eds., MIT Press, Cambridge, Mass.,
flood forecasting models in Yangtze River.” J. Hydrol. Eng., 10共6兲, 1, 318–362.
485–491. Sugeno, M., and Yasukawa, T. 共1993兲. “A fuzzy-logic-based approach to
Chiang, C-H., and Yang, C.-C. 共2005兲. “Artificial neural networks in qualitative modeling.” IEEE Trans. Fuzzy Syst., 1共1兲, 7–31.
prediction of concrete strength reduction due to high temperature.” Sugeno, T., and Tanaka, K. 共1991兲. “Successive identification of systems
ACI Mater. J., 102共2兲, 93–102. and its application to modeling and control.” Fuzzy Sets Syst., 42共3兲,
Chiu, S. L. 共1994兲. “Fuzzy model identification based on cluster estima- 315–334.
tion.” J. Intell. Fuzzy Syst., 2, 267–278. Takagi, T., and Sugeno, M. 共1985兲. “Fuzzy identification of systems and
Cullen, A. C., and Frey, H. C. 共1999兲. Probabilistic techniques in expo- its applications to modeling and control.” IEEE Trans. Syst. Man Cy-
sure assessment: A handbook for dealing with variability and uncer- bern., 15共1兲, 116–131.
tainty in models and inputs, Plenum, New York, 352. Tesfamariam, S., Rajani, B., and Sadiq, R. 共2006兲. “Consideration of
Emami, M. R., Turksen, I. B., and Goldenberg, A. A. 共1998兲. “Develop- uncertainties to estimate structural capacity of ageing cast iron water
ment of a systematic methodology of fuzzy logic modeling.” IEEE mains—A possibilistic approach.” Can. J. Civ. Eng., 33共8兲, 1050–
Trans. Fuzzy Syst., 6共3兲, 346–361. 1064.
Hong-Guang, N., and Ji-Zong, W. 共2000兲. “Prediction of compressive Vernieuwe, H., et al. 共2005兲. “Comparison of data-driven Takagi—
strength of concrete by neural networks.” Cem. Concr. Res., 30, Sugeno models of rainfall—Discharge dynamics.” J. Hydrol., 302,
1245–1250. 173–186.
Jain, A., Misra, S., and Jha, S. K. 共2005兲. “Discussion of ‘Application of Werbos, P. 共1974兲. “Beyond regression: New tools for prediction and
neural networks for estimation of concrete strength.’ ” J. Mater. Civ. analysis in the behavioral sciences.” Ph.D. dissertation, Harvard
Eng., 17共6兲, 736–738. Univ., Cambridge, Mass.
Jang, J. S. R. 共1993兲. “ANFIS: Adaptive-network-based fuzzy inference Yager, R. R., and Filev, D. P. 共1994a兲. “Generation of fuzzy rules by
system.” IEEE Trans. Syst. Man Cybern., 23共3兲, 665–685.
mountain clustering.” J. Intell. Fuzzy Syst., 2, 209–219.
Jang, J. S. R., and Sun, C. T. 共1995兲. “Neuro-fuzzy modeling and con-
Yager, R. R., and Filev, D. P. 共1994b兲. Essentials of fuzzy modeling and
trol.” Proc. IEEE, 83共3兲, 378–406.
Kim, D. K., Lee, J. J., Lee, J. H., and Chang, S. K. 共2005兲. “Application control, Wiley, New York.
of probabilistic neural networks for prediction of concrete strength.” Yeh, I.-C. 共1998兲. “Modeling of strength of high-performance concrete
J. Mater. Civ. Eng., 17共3兲, 353–362. using artificial neural networks.” Cem. Concr. Res., 28共12兲, 1797–
Kim, J. I., Kim, D. K., Feng, M. Q., and Yazdani, F. 共2004兲. “Application 1808.
of neural networks for estimation of concrete strength.” J. Mater. Civ. Zadeh, L. A. 共1965兲. “Fuzzy sets.” Information Control., 8, 338–353.
Eng., 16共3兲, 257–264. Zadeh, L. A. 共1973兲. “Outline of a new approach to the analysis of com-
Klir, G. J., and Yuan, B. 共1995兲. Fuzzy sets and fuzzy logic—Theory and plex systems and decision processes.” IEEE Trans. Syst. Man Cy-
bern., 3, 28–44.
applications, Prentice-Hall, Englewood Cliffs, N.J.
Lai, S., and Serra, M. 共1997兲. “Concrete strength prediction by means of Zadeh, L. A. 共1991兲. “From circuit theory to system theory.” Facets of
neural network.” Constr. Build. Mater., 11共2兲, 93–98. systems science, G. J. Klir, ed., Plenum, New York.
Lee, C. C. 共1990a兲. “Fuzzy logic in control systems: Fuzzy logic control- Zadeh, L. A. 共1997兲. “The role of fuzzy logic and soft computing in the
ler. Part I.” IEEE Trans. Syst. Man Cybern., 20共2兲, 404–418. conception, design and deployment of intelligent systems.” Software
Lee, C. C. 共1990b兲. “Fuzzy logic in control systems: Fuzzy logic control- agents and soft computing, Springer, New York.