BASIC ARTIFICIAL INTELLIGENCE

CONCEPTS IN CIVIL ENGINEERING

GUIDED BY : PRESENTED BY :
JOE PRASAD AKHIL MADHU
(YC16CE010)
 OVER VIEW
1. INTRODUCTION

2. INTELLIGENT OPTIMIZATION METHODS IN CIVIL ENGINEERING

3. EVOLUTIONARY COMPUTATION

4. NEURAL NETWORKS

5. OPTIMISATION ALGORITHMS IN CIVIL ENGINEERING

6. CASE STUDY

7. FUTURE TRENDS

8. LITERATURE REVIEW
2
9. CONCLUSION
 INTRODUCTION
Artificial intelligence (AI) is a specialized system to understand intelligent entities,
construct them and make the process of decision making simple, quick and efficient.

Artificial intelligence is concerned with the automation of intelligent behavior that think
and act like humans.

Artificial intelligence is an extremely broad and deeply embedded in our daily lives .

Artificial intelligence is a concept already embedded in our day to day lives .

In speech recognition, computer's Reasoning, computer vision, EHS compliance, Neural

Network in construction and management etc .

3
In the field of civil engineering it covers a vast area for human benefits especially in
engineering design construction management and program decision-making .

AI helps to improve several aspects of construction engineering and management for

productivity assessment, safety management, idle time reduction, decision-making and
optimizing construction costs.

Neural networks are capable of collecting, memorizing, analysing and processing large
number of data gained from some experiments or numerical analyses .

ANN is efficient tool for engineering design, pavement maintenance, structural damage
assessment, risk analysis, HPC strength prediction, optimization, construction .

4
INTELLIGENT OPTIMISATION METHODS IN CIVIL ENGINEERING

In the field of civil engineering, many problems, especially in engineering design, construction
management, and program decision-making can be optimised.

Artificial intelligence has a broad application prospects in the practice of civil engineering.

Adam and Smith presented progress in the field of adaptive civil-engineering structures.

Self-diagnosis, multi-objective shape control, and reinforcement-learning processes were

implemented within a control framework on an active tensegrity structure.

5
Bassuoni and Nehdi developed neuro-fuzzy based prediction of the durability of self-
consolidating concrete to various sodium sulfate exposure regimes.

DR.Prasad presented an artificial neural network (ANN) to predict a 28-day compressive

strength of a normal and high strength self-compacting concrete (SCC) and high performance
concrete (HPC) with high volume fly ash.

Lee used an artificial intelligence technique of back-propagation neural networks to assess the
slope failure.

The numerical results demonstrate the effectiveness of artificial neural networks in the
evaluation of slope failure potential.

Shaheen presented a proposed methodology for extracting the information from experts to
develop the fuzzy expert system rules.
6
Das described two artificial intelligence techniques for prediction of maximum dry
density (MDD) and unconfined compressive strength (UCS) of cement stabilized soil.

Over the past 20 years, in the civil engineering field, development and application of
the expert system have made a lot of achievements.

Mainly used in :

Project Evaluation

Diagnosis, Decision-Making and Prediction

Building design and Optimization,

The Project Management Construction Technology,

Road and Bridge Health Detection . 7

 EVOLUTIONARY COMPUTATION

Evolutionary computation (EC) uses iterative process to evolve a population of solution to a

desired end.

EC has been applied to the domain of civil engineering for several decades

Mainly served as an effective method for solving complex optimization problems.

Genetic Algorithms

Artificial Immune Systems

Genetic Programming
8
 GENETIC ALGORITHMS

Genetic algorithms (GAs) has extensive application value in the civil engineering field.

In many aspects it needs to be further studied and improved.

According to the research progress above the genetic algorithm in civil engineering, due to
genetic algorithm developed rapidly, so there are still a lot of improvement measures.

Use of technology include :

The hybrid genetic algorithm,

The dynamic adaptive technology,

9
10
Senouci and Al-Derham presented a genetic-algorithm-based multiobjective optimization
model for the scheduling of linear construction projects.

The model allows construction planners to generate and evaluate optimal/near-optimal

construction scheduling plans that minimize both project time and cost. 11
 ARTIFICIAL IMMUNE SYSTEMS
Artificial immune system (AIS) stimulates the adaptive immune system of a living creature to
unravel the various complexities in real-world engineering .

A combination of the genetic algorithm and the least-squares method was used to find feasible
structures and the appropriate constants for those structures.

Dessalegne and Nicklow employed an artificial life algorithm, derived from the artificial life
paradigm.

The resulting multi-reservoir management model was successfully applied to a portion of the
Illinois River Waterway.

The realization of the algorithm, parameter selection, the theory discussion, and the immune
system in civil engineering application, still need further development.
12
 GENETIC PROGRAMMING
Genetic programming is a model of programming which uses evolution to handle complex
optimization problems.

Hsie proposed a novel approach, called “LMGOT,” that integrates two optimization
techniques: the Levenberg Marquardt (LM) Method and the genetic operation tree (GOT).

Results predict the length of pavement transverse cracking and indicate that the LMGOT was
an efficient approach to building an accurate crack model.

Cevik and Guzelbey presented two plate strength formulations applicable to metals with
nonlinear stress-strain curves.

The proposed formulations enable determination of the buckling strength of rectangular

plates in terms of Ramberg-Osgood parameters.
13
 NEURAL NETWORKS
Artificial neural networks emerged from the studies of how brain performs.

The human brain consists of many millions of individual processing elements called neurons
that are highly interconnected.

ANNs are made up of simplified individual models of the biological neurons that are
connected together to form a network.

Many different types of neural networks are available

Multi-layered neural network are the most popular which are extremely successful in pattern
reorganization problems.

14
15
16
ROLE OF ARTIFICIAL NEURAL NETWORKS (ANNs)
Neuro-modex -Neural Network System for Modular Construction Decision Making

Initial Design Process using Artificial Neural Networks

Planning of Construction Projects

Construction Robot Fleet Management System Prototype:

Bridge Planning Using GIS and Expert System Approach:

Artificial Neural Network Approach for Pavement Maintenance

ANN for EHS

17
Tidal Forecasting

Earthquake-Induced Liquefaction

Analogy-Based Solution to Markup Estimation Problem

Neuro-modex -Neural Network System for Modular Construction Decision Making

Neuroform - Neural Network System for Vertical Formwork Selection

Belief Networks for Construction Performance Diagnostics

Building KBES for Diagnosing PC Pile with Artificial Neural Network

Modeling Initial Design Process using Artificial Neural Networks

Intelligent Planning of Construction Projects 18

 EXPERT SYSTEM
An expert system is relying on human experts existing knowledge based on set up
knowledge system.

The expert system is widely used in :

Road and Bridge construction Engineering

Geotechnical Engineering

Underground Engineering

Disaster Prevention Project

Material Engineering
19
20
 FUZZY SYSTEMS

Zarandi develop fuzzy polynomial neural networks _x0005_FPNN_x0006_ to predict the

compressive strength of concrete.

The results show that FPNN-Type1 has strong potential as a feasible tool for prediction of
the compressive strength of concrete mix-design.

Sobhani and Ramezanianpour developed a soft computing system to estimate

the service life of reinforced concrete bridge deck .

The proposed system utilizes

Four fuzzy interfaces to quantify the exposure condition,

Required cover thickness 21

Corrosion current density,

Pitting corrosion ratio.

The results showed that the proposed system could effectively predict the service life.

22
OPTIMISATION ALGORITHMS USED IN CIVIL ENGINEERING

1. FIREFLY ALGORITHM

Gandomi used a recently developed metaheuristic optimization algorithm,

The Firefly Algorithm _x0005_FA_x0006_, for solving mixed continuous/discrete

structural optimization problems.

FA mimics the social behavior of fireflies based on their flashing characteristics.

23
2. CUCKOO SEARCH

Durgun and Yildiz introduced a new optimization algorithm, called the Cuckoo
Search _x0005_CS_x0006_ algorithm, for solving structural design optimization
problems.

Results show the ability of the CS to find better optimal structural design.

A new robust optimization algorithm, which can be regarded as a modification of the

recently developed cuckoo search by Walton was presented.

24
 CASE STUDY

TIDAL LEVEL FORCASTING

Tidal level record is an important factor in determining constructions or activity in maritime
areas.

Tsai and Lee applied the back propagation neural network to forecast the tidal level
using the historical observations of water levels.

Not for long-term tidal prediction.

D.S. Jeng, D. H. Cha and M. Blumenstein (2003) used different data based in the
training procedure to predict the one-year tidal level in Taichung Harbour.

25
26
Based on the 15- day collected data (1-15 Jan 2000), the one-year prediction of tidal level
(Jan 2000- Dec, 2000) in Fig .

In the figure, solid lines denote the observation data, and dashed lines are the predicted
values.

The prediction of the present model overall agree with the observation.

The correlation coefficient over one year is 0.9182, which is reasonable good.

27
 FUTURE TRENDS
In civil engineeringfield, in the present situation, the research and development of artificial
intelligence is only just starting, so far failing to play its proper role.

Fuzzy processing, integrated intelligent technology, intelligent emotion technology

in the civil engineering.

To deepen the understanding of the problems of uncertainty and to seek appropriate reasoning
mechanism is the primary task.

Hybrid intelligence system and a large civil expert system research.

28
 LITERATURE REVIEW

1. Russell, S. and Norvig, P. (1995)“Artificial Intelligence: A Modern Approach”, Prentice

Hall.
2. Luger & Stubbelfield(1993) “AI: Structures and Strategies for Complex Problem Solving”,
Benjamin Cummings.
3. Yeh, Yi-Cherng, Kuo, Yau-Hwaug, and Hsu, Deh-Shiu, (1993), American Society of Civil
Engineers Journal of Computing in Civil Engineering,Volume 7, Number 1,January 1993.
4.D.S. Jeng, D. H. Cha and M. Blumenstein (2003), "Application of Neural Network in
Civil Engineering Problems".
5. Schalkoff, R. J. (1990), “Artificial Intelligence: An Engineering Approach”, McGraw-Hill,
New York.
6. Haugeland, J., (1985) , Editor “Artificial Intelligence: The Very Idea”, MIT press,
Cambridge, Massachusetts.

29
 CONCLUSION
In many situations of civil engineering, various problems are encountered that are very
complex and not well understood.

AI has been successfully applied to many civil engineering areas like prediction, risk analysis,
decision-making, resources optimization, classification, and selection etc.

The artificial intelligence in civil engineering is playing a major role in constructing,

maintaining and managing different aspects of civil engineering problems.

In the field of waste management, database, or construction. AI has shown its potency to
perform better than the conventional methods.

AI has a number of significant benefits that make them a powerful and practical tool for
solving many problems in the field of civil engineering and are expected to be applicable in
near future by using sophisticated instruments based on the algorithms and database to reduce
30
the efforts and cost of construction and management.