Artificial intelligence in civil engineering

Artificial intelligence in civil engineering


With expenditures reaching over $900 billion, the United States is the second largest construction market worldwide. The US construction industry is being challenged to make large improvements, including speed of project delivery, out-turn cost and reducing carbon emissions. Traditional methods for modeling and optimizing complex structure systems require huge amounts of computing resources, and artificial-intelligence-based solutions can often provide valuable alternatives for efficiently solving problems in the civil engineering.

AI generally involves the development of a mathematical model derived from experimental data. In structural mechanics and construction materials contexts, recent experiments have reported that fuzzy logic (FL), artificial neural networks (ANNs), genetic algorithm (GA), and fuzzy genetic (FG) may offer a promising alternative. They are known as artificial intelligence. In civil engineering, AI methods have been extensively used in the fields of civil engineering applications such as construction management, building materials, hydraulic, optimization, geotechnical and transportation engineering.

Artificial intelligence has a broad application prospects in the practice of civil engineering. 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 and some special field, and so forth. 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.

Among artificial intelligence-based computational techniques, adaptive neuro-fuzzy inference systems were particularly suitable for modelling complex systems with known input-output data sets. Such systems can be efficient in modelling nonlinear, complex, and ambiguous behaviour of cement-based materials undergoing single, dual, or multiple damage factors of different forms in civil engineering.

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. In general, the improvement of genetic algorithm approaches include change the genetic algorithm component or the use of technology, the hybrid genetic algorithm, the dynamic adaptive technology, using non standard genetic operators, and the parallel genetic algorithm. In recent years, the improvement of the genetic algorithm introduced many new mathematical tools and absorbed civil engineering as the latest achievement of applications. We can expect, along with the computer technology, the genetic algorithm in civil engineering application will be more general and more effective.

For example, A. Senouci and H. R. 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.

Neural networks and fuzzy systems are currently used in civil engineering. Ricardo Bendaña presented a fuzzy-logic-based system for selecting contractors. As part of the validation process, a neural network was developed to prove that the fuzzy-control tool has a behavior that can be recognized by a neural network. Bilgil and Altun introduced an efficient approach to estimate the friction coefficient via an artificial neural network, which was a promising computational tool in civil engineering. The estimated value of the friction coefficient was used in Manning Equation to predict the open channel flows in order to carry out a comparison between the proposed neural networks based approach and the conventional ones.

In the last years were developed many applications also in civil engineering field. Particularly the genetic algorithms are employed in the field of structural optimization, in the allocation of resources for building problems and in the optimization of road infrastructure and water channel nets. In the field of analysis and planning of long suspension bridges, the genetic algorithms can be employed, other than structural optimization also for better define load scenarios and structural performances.

Artificial Intelligence techniques are now being used by the practicing engineers to solve a whole range of problems. Future advancements in ANN, fuzzy logic and genetic algorithms will mean that civil engineering and construction industry will benefit in terms of optimisation, speed of processes and cost reduction, while young inexperienced engineers will be replaced by technologies.

Author: AI Business Team