Tabriz fault is one of the active and dangerous faults in the North West of Iran. The fault crosses the north through the city and put crossing towns at risk. The majority of marginal inhabitants within the city are settled there. Their buildings do not resist the slightest shake. Analysis of seismic data using Polynomial Regression for predicting future earthquake's magnitude and risks can be helpful to reduce disaster results. First of all, input data are extracted and normalized. At the second step, model is obtained. In the third step, the magnitude of earthquake for the test data is predicated. In the fourth step, the performance of predicting earthquake magnitude is evaluated.Finally, to estimate the magnitude of earthquakes using other attributes a formula is obtained that can be used to estimate the coefficients of each of the independent variables.

Rutting is among the most important distresses in flexible pavements, which is mainly influenced by asphalt mixes properties at high temperatures. There are different methods for measuring the rutting resistance of asphalt mixes. Flow number of asphalt mix, which is measured experimentally by dynamic creep test is one of the most commonly used rutting index, which requires advanced devices, notable cost and time. This paper aims to develop a simple model for predicting the flow number of asphalt mixes using Evolutionary Polynomial Regression (EPR). The developed model can be used for predicting flow number based on Marshall mix design parameters including percentage of fine and coarse aggregates, bitumen content, filler content, air void content, void in mineral aggregate, Marshall stability, and flow. The coefficient of determination (R2) of model in case of training and testing set is 0. 9714, and 0. 969, respectively, which confirms the high accuracy of model. Comparison of the developed model with the existing models shows the superior performance of the developed model. In addition, the parametric analysis indicates the proper conformity of the developed model with the physical behavior of the asphalt mixtures.

This paper presents a new approach, based on Evolutionary Polynomial Regression (EPR), for predicting the safety factors of a quay wall against sliding, overturning and bearing capacity failure as functions of the soil’s shear strength parameters, geometry of the wall and loading conditions. To this end, a database of around 80000 data sets was created based on a conceptual model, employing a MATLAB-aided program. Based on input and output values of this database and employing EPR, three different models for the estimation of safety factors were developed and their results were compared with the values in the database. Investigation into the performance of the developed models indicates that these models are capable of estimating the stability of quay walls with a precision of around 95%. Parametric analyses were performed on the models to identify parameters with a key role in the stability of quay walls. The parametric studies were indicative of the models’ ability in capturing the effects of individual parameters on the wall safety factors, therefore proving the models helpful as tools in the preliminary design of gravity quay walls.

In recent years the rupture of landfill centers has resulted in the importance of studying the behavior of municipal solid waste (MSW). MSW as the main constituent element in landfills has a complicated performance. In this study, by using the results of large – scale direct shear experiments with dimensions of 300 mm x 300 mm x 150 mm, 2 models to predict the behavior of MSW with ages of fresh and 3 months are presented. The purpose of this investigation is to predict MSW stress-strain behavior for kahrizak landfill as a sample of developing countries landfills under aging and by structural models. These models are Hyperbolic model and Evolutionary Polynomial Regression (EPR). In these collection of experiments, aging process up to 3 months, was artificially applied to samples. Three normal stresses 20, 50, 100 kpa and three shear strain rates 0. 8, 8, 19 mm per minute were used for samples with different ages. The results of these two models, in addition to predict MSW behavior under aging and degradation, shows high accordance with experimental results by direct shear apparatus. Finally this study states the advantage of EPR model relative to Hyperbolic model in higher accuracy for all experiments.

Computational complexity and time-consuming iteration of simulation for tuning of Proportional-Integral-Derivative (PID) controller is a common drawback in many types of existing methods. This paper aims to propose a new method for achieving an optimal design for PID gains parameters with the least number of simulation runs. To achieve this purpose, we combine Polynomial Regression and Latin Hypercube Sampling (LHS) in order to Design and Analyze of Computer Experiments (DACE). In this method, the LHS is performed three times to design the associated sample points for different usage that includes training sample points to fit Polynomial Regression as a common surrogate model; validating sample points to scale standardized residuals; grid search sample points for investigating optimal point over whole design space. To show the flexibility and applicability of the proposed method, we serve a numerical case in the tuning of PID controller for linear speed control of Direct Current (DC) motor. Four different Polynomial Regression fit input/output (I/O) data over separately four model’ s performances that includes Integral-Square-Error (ISE), Integral-Absolute-Error (IAE), Integral-Time-Square-Error (ITSE), and Integral-Time-Absolute-Error (ITAE). Comparison of the result with two existing approaches such as traditional Zeigler-Nichols method and Taguchi-Gray Relational Analysis (Taguchi-GRA) confirms the reliability and superiority of the proposed method.

A water distribution network is one of the important parts of infrastructure systems. The efficient management and proactive planning of capital investment of these assets are fundamental for efficient and effective service delivered by water companies. The direct economic costs (i.e. rehabilitation investment, repair costs, water loss, etc.) as well as indirect costs (i.e. service and traffic interruptions, etc.) related to water pipe bursts are rapidly increasing. The ability to predict burst rate in pipes is an important strategic key in order to optimization of rehabilitation decision in water distribution systems. Most networks suffer from lack of enough and reliable data for bursts and failures. In this study basic variables which influence on pipes burst and burst statistical analysis have been identified and evaluated. Then common methods for burst predicting are discussed. In order to identify logical, useful and understandable patterns of breaks data, a data mining methodology named evolutionary Polynomial Regression (EPR) is described. Starting from a hybrid evolutionary strategy, EPR searches for patterns in data and returns symbolic expressions/models. This approach is demonstrated through a detailed case study. Required data were collected from the Mashhad Water Company which includes both asset and bursts data recorded for year 1384. The whole database was divided into 8 material/diameter classes (from 64 mm to 300 mm). The resulting models for burst prediction in different zones contain explicitly recognizable independent variables. The expression models confirm that pipe age, diameter and length are the most important variables leading to pipe bursts. Also the effects of pressure on pipe burst prediction were implicitly investigated. It was found that pressure is an important parameter which influences number of breaks in a pipe network.

Surface-piercing propellers have been widely used in light and high-speed vessels because of their superior performance. One of the major steps in propeller selection algorithm is the determination of thrust as well as torque hydrodynamic coefficients. For the purpose of simplifying design and selection procedure, some relations are presented for determining hydrodynamic coefficients in some studies, precision, and accuracy of which must be validated due to the importance of the issue as well as having high development and operational costs. Therefore, these issues are evaluated in this study by field study and recognizing the presented relation set as well as acquiring experimental test data. The acquired results show lack of full agreement between semi-experimental relations and experimental data. In the following, due to the limitations of the Regression relations presented in the determination of hydrodynamic coefficients, the database was developed from experimental data, the number of series is determined by extracting the Regression relations for each series, these relations are used to determine the hydrodynamic coefficient of thrust and torque in the propeller selection algorithm. Finally, a suitable algorithm for selecting the surface-piercing propeller was presented and discussed.