Issuu on Google+



Prepared by :



The research of artificial intelligence has been developed since 1956, when the term “Artificial Intelligence, AI� was used at the meeting hold in Dartmouth College. Artificial intelligence, a comprehensive discipline, was developed based on the interaction of several kinds of disciplines, such as computer science, cybernetics, information theory, psychology, linguistics, and neurophysiology. Artificial intelligence is a branch of computer science, involved in the research, design and application of intelligent computer. The goal of this field is to explore how to imitate and execute some of the intelligent function of human brain, so that people can develop technology products and establish relevant theories. The first step: artificial intelligence’s rise and fall in the 1950s. The second step: as the expert system emerging, a new upsurge of the research of artificial intelligence appeared from the end of 1960s to the 1970s. The third step: in the 1980s, artificial intelligence made a great progress with the development of the fifth generation computer. The fourth step: in the 1990s, there is a new upsurge of the research of artificial intelligence: with the development of network technology, especially the international internet technology, artificial intelligence research by a single intelligent agent began to turn to the study of distributed artificial intelligence based on network environment. People study not only the same goal-based distributed problem solving, but also the multiply intelligent agents problem solving, which made the artificial intelligence more practical. Additionally, a thriving scene of artificial neural network research and application emerged and it had been deep into all areas of life as the Hopfield multilayer neural network model put forward. The main theories and methods of artificial intelligence are summarized as symbolism, behaviorism, and connectionism approach. Since the appearance of Artificial intelligence AI in the 1950s, a lot of hopes and dreams about it has been generated. Now we will elaborate the latest progress of artificial

intelligence technology in all aspects of civil engineering and their relationship as follows. Artificial intelligence is a branch of computer science, involved in the research, design, and application of intelligent computer. Traditional methods for modeling and optimizing complex structure systems require 3 huge amounts of computing resources, and artificial-intelligence-based solutions can often provide valuable alternatives for efficiently solving problems in the civil engineering. This papers summarizes recently developed methods and theories in the developing direction for applications of artificial intelligence in civil engineering, including evolutionary computation, neural networks, fuzzy systems, expert system, reasoning, classification, and learning, as well as others like chaos theory, cuckoo search, firefly algorithm, knowledge-based engineering, and simulated annealing. The main research trends are also pointed out in the end. The paper provides an overview of the advances of artificial intelligence applied in civil engineering.

An artificial neural network, often just named a neural network, is a mathematical model inspired by biological neural networks. A neural network consists of an interconnected group of artificial neurons, and it processes information using a connectionist approach to computation. In most cases a neural network is an adaptive system changing its structure during a learning phase. Neural networks are used for modeling complex relationships between inputs and outputs or to find patterns in data.

Word network in the term 'artificial neural network' refers to the inter– connections between the neurons in the different layers of each system. An example system has three layers. The first layer has input neurons, which send data via synapses to the second layer of neurons, and then via more synapses to the third layer of output neurons. More complex systems will have more layers of neurons with some having increased layers of input neurons and output neurons. The synapses store parameters called "weights" that manipulate the data in the calculations. An ANN is typically defined by three types of parameters

1. The interconnection pattern between different layers of neurons 2. The learning process for updating the weights of theinterconnections 3. The activation function that converts a neuron's weighted input to its output activation.

Mathematically, a neuron's network function

is defined as a

composition of other functions , which can further be defined as a composition of other functions. This can be conveniently represented as a network structure, with arrows depicting the dependencies between variables. A widely used type of composition is the nonlinear weighted sum, where , where (commonly referred to as the activation function is some predefined function, such as the hyperbolic tangent. It will be convenient for the following to refer to a collection of functions as simply a vector .

ANN dependency graph

This figure depicts such a decomposition of with dependencies between variables indicated by arrows. These can be interpreted in twoways. The first view is the functional view: the input is transformed into a 3-dimensional vector into a 2-dimensional vector

, which is then transformed

, which is finally transformed into


This view is most commonly encountered optimization.The second view is the 5



probabilistic view: the random variable the random variable

which depends upon



depends upon , which

depends upon the random variable . This view is most commonly encountered in the context of graphical models. The two views are largely equivalent. In either case, for this particular network architecture, the components of individual layers are independent of each other (e.g., the components of are independent ofeach other given their input This naturally enables a degree of parallelism in the implementation.


Two separate depictions of the recurrent ANN dependency graph Networks such as the previous one are commonly called feedforward, because their graph is a directed acyclic graph. Networks with cycles are commonly calledrecurrent. Such networks are commonly depicted in the manner shown at the top of the figure, where is shown as being dependent upon itself. However, an implied temporal dependence is not shown.

Genetic Algorithms are a family of computational models inspired by evolution. These algorithms encode a potential solution to a speci_c problem on a simple chromosome-like data structure and apply recombination operators to these structures as as to preserve critical information. Genetic algorithms are often viewed as function optimizer, although the range of problems to which genetic algorithms have been applied are quite broad. An implementation of genetic algorithm begins with a population of (typically random) chromosomes. One then evaluates these structures and allocated reproductive opportunities in such a way that these 6 chromosomes which represent a better solution to the target problem are given more chances to `reproduce' than those chromosomes which are poorer solutions. The 'goodness' of a solution is typically de_ned with respect to the current population.

The working principle of GA is illustrated in Fig. 1. The major steps involved are the generation of a population of solutions, _nding the objective function and _tens function and the application of genetic operators. These aspects are described briey below. They are described in detail in the following subsection. /*Algorithm GA */ Formulate initial population Randomly initialize population Repeat Evaluate objective function _nd _tness function Apply genetic operators Reproduction Crossover Mutation Until stopping criteria Figure 1: The Working Principle of a Simple Genetic Algorithm

An important characteristic of genetic algorithm is the coding of variables that describes the problem. 7 The most common coding method is to transform the variables to a binary string or vector; GAs perform best when solution vectors arebinary.If the problem has more than one variable, a multi-variable coding is constructed by concatenating as many single variables coding as the number of variables in the problem. Genetic Algorithm processes a number of solutions simultaneously. Hence, in the _rst step a population having P individuals is generated by pseudo random generators whose individuals represent a feasible solution. This is a representation of solution vector in a solution space and is called initial solution. This ensures the search to be robust and unbiased, as it starts from wide range of points in the solution space. In the next step, individual members of the population are evaluated to _nd the objective function value. In this step, the exterior penalty function method is utilized to transform a constrained optimization problem to an unconstrained one. This is exclusively problem speci_c. In the third step, the objective function is mapped into a _tness function that computes a _tness value for each member of the population. This is followed by the application of GA operators.

In artificial intelligence, an expert system is a computer system that emulates the decision-making ability of a human expert. Expert systems are designed to solve complex problems by reasoning about knowledge, like an expert, and not by following the procedure of a developer as is the case in conventional programming. The first expert systems were created in the 1970s and then proliferated in the 1980s. Expert systems were among the first truly successful forms of AI software. An expert system has a unique structure, different from traditional computer programming. It is divided into two parts, one fixed, independent of the expert system: the inference engine, and one variable: the knowledge base. To run an expert system, the engine reasons about the knowledge base like a human. In the 80s a third part appeared: a dialog interface to communicate with users. This ability to conduct a conversation with users was later called "conversational".

In expert system technology, the knowledge base is expressed with natural language rules IF ... THEN ... For examples :

1. "IF it is living THEN it is mortal" 2. "IF his age = known THEN his year of birth = current year - his age in years" 3. "IF the identity of the germ is not known with certainty AND the germ is gram-positive AND the morphology of the organism is "rod" AND the germ is aerobic THEN there is a strong probability (0.8) that the germ is of type enterobacteriacae"

This formulation has the advantage of speaking in everyday language which is very rare in computer science (a classic program is coded). Rules express the knowledge to be exploited by the expert system. There exist other formulations of rules, which are not in everyday language, understandable only to computer scientists. Each rule style is adapted to an engine style.

The inference engine is a computer program designed to produce a reasoning on rules. In order to produce a reasoning, it should be based on logic. There are several kinds of logic: propositional logic, predicates of order 1 or more, epistemic logic, modal logic, temporal logic, fuzzy logic, probabilistic logic (implemented in a Bayesian network), etcPropositional logic is the basic human logic, that is expressed 9 in syllogisms. The expert system that uses that logic is also called a zeroth-order expert system. With logic, the engine is able to generate

new information from the knowledge contained in the rule base and data to be processed.

Fuzzy logic is a form of many-valued logic or probabilistic logic; it deals with reasoning that is approximate rather than fixed and exact. Compared to traditional binary sets (where variables may take on true or false values) fuzzy logic variables may have a truth value that ranges in degree between 0 and 1. Fuzzy logic has been extended to handle the concept of partial truth, where the truth value may range between completely true and completely false. Furthermore, when linguistic variables are used, these degrees may be managed by specific functions. Irrationality can be described in terms of what is known as the fuzzjective. The term "fuzzy logic" was introduced with the 1965 proposal of fuzzy set theory by Lotfi A. Zadeh Fuzzy logic has been applied to many fields, from control theory to artificial intelligence. Fuzzy logics however had been studied since the 1920s as infinite-valued logics notably by ナ「kasiewicz and Tarski.

Classical logic only permits propositions having a value of truth or falsity. The notion of whether 1+1=2 is absolute, immutable, mathematical truth. However, there exist certain propositions with variable answers, such as asking various people to identify a color. The notion of truth doesn't fall by the wayside, but rather a means of representing and reasoning over partial knowledge is afforded, by aggregating all possible

outcomes into a dimensional spectrum. Both degrees of truth and probabilities range between 0 and 1 and hence may seem similar at first. For example, let a 100 ml glass contain 30 ml of water. Then we may consider two concepts: Empty and Full. The meaning of each of them can be represented by a certain fuzzy set. Then one might define the glass as being 0.7 empty and 0.3 full. Note that the concept of emptiness would be subjective and thus would depend on the observer or designer. Another designer might equally well design a set membership function where the glass would be considered full for all values down to 50 ml. It is essential to realize that fuzzy logic uses truth degrees as a mathematical model of the vagueness phenomenon while probability is a mathematical model of ignorance.

A basic application might characterize subranges of a continuous variable. For instance, a temperature measurement for anti-lock brakes might have several separate membership functions defining particular temperature ranges needed to control the brakes properly. Each function maps the same temperature value to a truth value in the 0 to 1 range. These truth values can then be used to determine how the brakes should be controlled.

Fuzzy logic temperature In this image, the meanings of the expressions cold, warm, and hot are represented by functions mapping a temperature scale. A point on that scale has three "truth values"—one for each of the three functions. The vertical line in the image represents a particular temperature that the three arrows (truth values) gauge. Since the red arrow points to zero, this temperature may be interpreted as "not hot". The orange arrow (pointing at 0.2) may describe it as "slightly warm" and the blue arrow (pointing at 0.8) "fairly cold".

Artificial intelligent