Genetic Algorithm Calibration Research Articles

Multi-objective genetic algorithm calibration of colored self-compacting concrete using DEM: an integrated parallel approach.

A detailed numerical simulation of Colored Self-Compacting Concrete (CSCC) was conducted in this research. Emphasis was placed on an innovative calibration methodology tailored for ten unique CSCC mix designs. Through the incorporation of multi-objective optimization, MATLAB's Genetic Algorithm (GA) was seamlessly integrated with PFC3D, a prominent Discrete Element Modeling (DEM) software package. This integration facilitates the exchange of micro-parameter values, where MATLAB's GA optimizes these parameters, which are then input into PFC3D to simulate the behavior of CSCC mix designs. The calibration process is fully automated through a MATLAB script, complemented by a fish script in PFC, allowing for an efficient and precise calibration mechanism that automatically terminates based on predefined criteria. Central to this approach is the Uniaxial Compressive Strength (UCS) test, which forms the foundation of the calibration process. A distinguishing aspect of this study was the incorporation of pigment effects, reflecting the cohesive behavior of cementitious components, into the micro-parameters influencing the cohesion coefficient within DEM. This innovative approach ensured significant alignment between simulations and observed macro properties, as evidenced by fitness values consistently exceeding 0.94. This investigation not only expanded the understanding of CSCC dynamics but also contributed significantly to the discourse on advanced concrete simulation methodologies, underscoring the importance of multi-objective optimization in such studies.

Poisson rectangular pulse (PRP) model establishment based on uncertainty analysis of urban residential water consumption patterns

The commonly used Poisson rectangular pulse (PRP) model, employed for simulating high-resolution residential water consumption patterns (RWCPs), relies on calibration via medium-resolution RWCPs obtained from practical measurements. This introduces inevitable uncertainty stemming from the measured RWCPs, which consequently impacts the precision of model simulations. Here we enhance the accuracy of the PRP model by addressing the uncertainty of RWCPs. We established a critical sampling size of 2000 household water consumption patterns (HWCPs) with a data logging interval (DLI) of 15 min to attain dependable RWCPs. Through Genetic Algorithm calibration, the optimal values of the PRP model's parameters were determined: pulse frequency λ = 91 d−1, mean of pulse intensity E(I) = 0.346 m3 h−1, standard deviation of pulse intensity STD(I) = 0.292 m3 h−1, mean of pulse duration E(D) = 40 s, and standard deviation of pulse duration STD(D) = 55 s. Furthermore, validation was conducted at both HWCP and RWCP levels. We recommend a sampling size of ≥2000 HWCPs and a DLI of ≤30 min for PRP model calibration to balance simulation precision and practical implementation. This study significantly advances the theoretical foundation and real-world application of the PRP model, enhancing its role in urban water supply system management.

Agent-Based Simulations Using Genetic Algorithm Calibration: A Children’s Services Application

With increased pressures and tightening budgets within English Children’s Services in the UK, seeking more effective operational and financial management is becoming a more significant topic of discussion. In other sectors, complex data analysis methods provide the aforementioned management improvements through better understanding of current situations leading to better decision making. Currently, investment remains at a slow pace in English Local Authorities due to budget restrictions. In this paper, a potential opportunity is explored with existing publicly available data related to this area. With the help of industry experts, an Agent-Based Model is created to emulate basic Children’s Services operations and optimised to fit existing data using NSGA-III. With relatively close matches being achieved with sample authorities, this approach demonstrates promise in advancing analytics capabilities for Children’s Services and practical solutions are discussed. With this presented work, it is shown that further expansion and exploration into real-world applications is warranted.

S-PLACE GA for optimal water quality sensor locations in water distribution network for dual purpose: regular monitoring and early contamination detection – a software tool for academia and practitioner

Abstract Security concerns about water distribution networks (WDNs) have led to increased interest in optimizing sensor locations in WDNs achieved through a calibrated hydraulic model. This paper presents a methodology, which consists of two stages. The first stage consists of calibration of a hydraulic model using a genetic algorithm (GA). A real-life network of one of the hydraulic zones of Nagpur city, India, is considered, which optimizes the settings of a throttled controlled valve at different timings for calibration. In this stage, a detailed case study, GA calibration model, methodology and results of calibrated models are discussed. The second stage consists of identifying optimal sensor locations using a newly developed software tool named ‘S-PLACE GA’ and its efficiency and effectiveness are discussed. It can be used for the dual purpose of routine monitoring of water quality and for early detection of contamination. The optimal locations are obtained considering two objective metrics, ‘Demand Coverage’ and ‘Time-Constrained Detection Likelihood’. These two objectives are combined into a single objective by using weights. Key features, input data required for the software and their applications on (1) BWSN network 1 and result comparison with others and (2) calibrated model of the first stage are discussed. Results showed the effectiveness of S-PLACE GA for practical applications.

Evaluating the Effect of Incidents on Freeway Facilities and Updating the Incident Capacity Adjustments for HCM

This paper investigates the effect of incidents on freeway segment capacity. Currently, the Highway Capacity Manual (HCM) provides a look-up table linking the remaining segment capacity fraction during an incident to the total and closed number of lanes on the segment. In reality, segment capacity during an incident will tend to vary over time, with the most severe effects felt early on before any type of response is initiated, with congestion progressively improving as the appropriate incident management actions are implemented. By applying a genetic algorithm calibration method on each incident day and calibrating the incident capacity adjustment factors (CAFs), optimal time-dependent CAFs were derived that best represented the effect of incidents on the freeway segment capacity. By analyzing the optimal CAFs, the strongest relationship was revealed to be between the optimal time-dependent CAF and the temporal progression of the incident. A regression model was developed to represent this behavior. This was formulated in a manner that can directly adjust the current HCM’s fixed CAF values (for a specific lane closure configuration) for modeling incidents both in single day, seed file application, or for an entire year reliability analysis. A portion of WB I-540 in Raleigh, NC was selected as the study area in which the proposed method was tested. Between January 2014 and December 2018, the team identified 22 isolated incidents (away from the recurring congestion period) that closed one or two lanes of traffic, creating a distinct congestion pattern.

Freeway travel time estimation based on the general motors model: a genetic algorithm calibration framework

Travel time estimation plays an important role in freeway performance assessment and reliability management. Conventional estimation methods based on speed information do not consider the level of congestion during modelling, leading to unreliable estimations under congested conditions. This study presents a freeway travel time estimation method based on the general motors (GM) model, where the concept ‘virtual vehicle’ was proposed to apply macroscopic traffic flow data to the microscopic GM model. First, a GM-based travel time estimation (GMTTE) model was developed to estimate link travel time. Three sets of parameters l , m and α were separately used under free-flowing, congestion and transition conditions. Next, two corridor estimation models, namely GMTTE time-slice-based (GMTTE-TSB) model and GMTTE continuous-speed (GMTTE-CS) model, were proposed. To calibrate the three parameters, a genetic algorithm framework was developed. The proposed method was calibrated and evaluated using traffic data collected from seven freeway segments in the greater St. Louis, Missouri region. Results show that (i) the GMTTE-CS model outperformed the GMTTE-TSB model; (ii) the optimal parameters of the GMTTE-CS model under free-flowing and congested conditions are l = 1.1 , m = 2.0 , α = 8.0 and l = 1 , m = 0.1 , α = 8.0 , respectively; (iii) the GMTTE-CS model outperformed the instantaneous and time-slice models under congested conditions, while showing similar accuracies with the two models under free-flowing and status-transition conditions; and (iv) the optimal time interval was found to be 9–10 min for free-flowing conditions and 6–7 min for congested conditions.

Genetic Algorithm Calibration Method and PnP Platform for Multimodal Sensor Systems

Genetic Algorithm Calibration Method and PnP Platform for Multimodal Sensor Systems

MOESHA: A Genetic Algorithm for Automatic Calibration and Estimation of Parameter Uncertainty and Sensitivity of Hydrologic Models.

Characterization of the uncertainty and sensitivity of model parameters is an essential facet of hydrologic modeling. This article introduces the multi-objective evolutionary sensitivity handling algorithm (MOESHA) that combines input parameter uncertainty and sensitivity analyses with a genetic algorithm calibration routine to dynamically sample the parameter space. This novel algorithm serves as an alternative to traditional static space-sampling methods, such as stratified sampling or Latin hypercube sampling. In addition to calibrating model parameters to a hydrologic model, MOESHA determines the optimal distribution of model parameters that maximizes model robustness and minimizes error, and the results provide an estimate for model uncertainty due to the uncertainty in model parameters. Subsequently, we compare the model parameter distributions to the distribution of a dummy variable (i.e., a variable that does not affect model output) to differentiate between impactful (i.e., sensitive) and non-impactful parameters. In this way, an optimally calibrated model is produced, and estimations of model uncertainty as well as the relative impact of model parameters on model output (i.e., sensitivity) are determined. A case study using a single-cell hydrologic model (EXP-HYDRO) is used to test the method using river discharge data from the Dee River catchment in Wales. We compare the results of MOESHA with Sobol's global sensitivity analysis method and demonstrate that the algorithm is able to pinpoint non-impactful parameters, demonstrate the uncertainty of model results with respect to uncertainties in model parameters, and achieve excellent calibration results. A major drawback of the algorithm is that it is computationally expensive; therefore, parallelized methods should be used to reduce the computational burden.

A High Performance Computing Framework for Continental-Scale Forest Fire Spread Prediction

Many scientific works have focused on developing propagation models that predict forest fire behavior. These models require a precise knowledge of the environment where the fire is taking place. Geographical Information Systems allow us determining and building the different information layers that define the terrain and the fire. These data, along with meteorological information from weather services, enables the simulation based on real conditions. However, fire spread prediction models require a set of input parameters that, in some cases, are difficult to know or even estimate precisely. Therefore, a framework, based on a genetic algorithm calibration stage, was introduced to reduce the uncertainty in the input parameters and improve the accuracy of the predictions. This stage is implemented using a MPI master/worker scheme and an OpenMP parallel version of the fire spread simulator. Additionally, the whole system is run using suitable automatic worker-assignment and core-allocation policies to respect the existing time restrictions, inherent to this real-world problem. This paper details the process of obtaining the necessary input data as well as the parallel evolutionary framework that delivers the final prediction. A real case study is presented to illustrate the way this framework works.

Measuring the safety impact of road infrastructure systems on driver behavior: Vehicle instrumentation and real world driving experiment

ABSTRACTFeatured in this pilot experimental study is the construction and design of an instrumented vehicle that is able to capture vehicle trajectory data with an extremely high level of accuracy and time resolution. Once constructed and properly instrumented, the various data collection systems were integrated with one another and a driving experiment was conducted on northern Virginia roadways with 18 participants taking part in the study. Trajectory data were collected for each of the drivers as they traversed a predefined loop of four roadway segments with varying numbers of lanes and varying shoulder widths. Data collected from the experiment were then used to calibrate the parameters of the prospect theory car-following model through a genetic algorithm calibration procedure. Once all model parameters were successfully calibrated, significance testing was carried out to determine the impacts that the varying roadway infrastructure had on driving behavior. Results indicated that there were significant changes in behavior when comparing one lane roadways to their two lane counterparts—specifically in cases where the roadway featured a wide shoulder. Additional testing was conducted to ensure that there was no variation based on gender, as nine study participants were female and nine were male. The successfulness of this first study conducted with the newly constructed instrumented vehicle creates the opportunity for a variety of additional studies to be conducted in the future.

Genetic Algorithm Calibration of Seasonal BVAR Models

In this paper we explore the use of Genetic Algorithms (GA) to calibrate seasonal BVAR models. In this way, the mechanistic use of seasonal adjustment procedures is avoided, since seasonality becomes a structural, basic and explicit part of the BVAR model. At the same time, the use of GA allows calibration to be performed on a diffuse setting, preserving as much as possible the flexible nature of BVAR and revealing interesting features of the data. The well-known U.S. housing data are used to illustrate the procedures outlined in the paper.

Seasonal and Regional Patterns in Performance for a Baltic Sea Drainage Basin Hydrologic Model

AbstractThis study evaluates the ability of the Catchment SIMulation (CSIM) hydrologic model to describe seasonal and regional variations in river discharge over the entire Baltic Sea drainage basin (BSDB) based on 31 years of monthly simulation from 1970 through 2000. To date, the model has been successfully applied to simulate annual fluxes of water from the catchments draining into the Baltic Sea. Here, we consider spatiotemporal bias in the distribution of monthly modeling errors across the BSDB since it could potentially reduce the fidelity of predictions and negatively affect the design and implementation of land‐management strategies. Within the period considered, the CSIM model accurately reproduced the annual flows across the BSDB; however, it tended to underpredict the proportion of discharge during high‐flow periods (i.e., spring months) and overpredict during the summer low flow periods. While the general overpredictions during summer periods are spread across all the subbasins of the BSDB, the underprediction during spring periods is seen largely in the northern regions. By implementing a genetic algorithm calibration procedure and/or seasonal parameterization of subsurface water flows for a subset of the catchments modeled, we demonstrate that it is possible to improve the model performance albeit at the cost of increased parameterization and potential loss of parsimony.

Using characteristics of the optimisation problem to determine the Genetic Algorithm population size when the number of evaluations is limited

The Genetic Algorithm (GA) parameter values that result in the best possible solutions being found are generally problem specific, and therefore expected to be related to the characteristics of the fitness function. In this work, statistics that characterise the fitness function have been related to the convergence of a GA population due to the repetitive application of tournament selection. Assuming that this operator has the dominant influence on the variance of the population, and that the computational time available is limited, the result can be used to determine a suitable population size. The methodology developed has been compared to other GA calibration methodologies, and was found to be the best of the different methods considered across a range of stopping criteria and problem formulations. This result demonstrates the potential usefulness of fitness function characteristics to inform the configuration of GAs, and in turn find the best possible solutions.

Determination of Woody Fuel Flame Properties by Means of Emission Spectroscopy Using a Genetic Algorithm

Because radiation from flames is often the dominant mechanism for wildfire spread, detailed information on flame properties is required. The proposed procedure combines a spectrally resolved radiation model for simulating the line-of-sight infrared emission intensity and spectroscopy data and uses a genetic algorithm (GA) to determine a set of flame properties, allowing optimal agreement between model and outdoor experiments. GA calibration and sensitivity analysis were conducted using well-defined reference flames. The combined GA/radiation model was used with emission data to estimate the effective properties of flames from the combustion of woody fuel beds from 0.5 to 4 m in thickness. Experimental results show that the contribution of soot particles to flame emission increases with flame thickness. The GA was found to be robust and efficient in providing relevant flame properties from line-of-sight intensities on the infrared spectrum of radiation.

An Estimation of Rainfall using Fuzzy Set-Genetic Algorithms Model

Problem statement: Damaged by floods are natural disasters that have violence cause significant damage and economic and social. If we can prevent disasters that may occur in advance is important. So an estimated rainfall data is important information for prevention disasters. Approach: The objective of this study is to apply a fuzzy set theory to estimate rainfall. The genetic algorithm was applied to calibrate the fuzzy set model. The proposed model considered only a few basic hydrological parameters including temperature, humidity, wind speed and solar radiation. The proposed model was applied to estimate the rainfall in the Chi River Basin (in the northeast region of Thailand) using 5- minute historic data. Results: The results have shown that the obtained rainfalls of the improved model are close to the rainfall of the actual rainfall record. Furthermore, the results presented that the genetic algorithm calibration provided the optimal condition of membership function. Conclusions/Recommendations: The proposed fuzzy-GA model can be used to estimate the rainfall, given only the basic hydrological parameters; temperature, humidity, wind speed and solar radiation. The fuzzy set model considering 4 variables using rainfall duration data is more effective than the model using the continuous rainfall data.

Adapting empirical equations to Lake Kinneret data by using three calibration methods

This paper examines whether the relationships between a number of characteristic limnological variables (suspended particulate matter, turbidity, Secchi depth, light attenuation, and chlorophyll a) determined for temperate lakes are consistent with the relationships found in Mediterranean lakes such as Lake Kinneret. We found that the use of published relationships between lake variables may lead to erroneous results when applied indiscriminately to other lake types. We applied linear regression, nonlinear regression and genetic algorithm (GA) approaches in order to fit the relationships to Lake Kinneret data. We showed that linear equations, simple or multivariate that do not require transformation prior to calibration, can be calibrated by simple and quick methods such as linear regression. However, when linear transformation is required prior to calibration the GA calibration produced better results. In addition, we found that the nonlinear regression method yielded a weak prediction, while the GA led to more accurate results. A sensitivity analysis of the GA operators’ values indicated that using a crossover probability of 80% produced the best prediction. Furthermore, since the GA sometimes converges to local optimum, it must operate for a number of runs. We found that in our case 20 GA runs provided the most robust results.

A genetic algorithm calibration method based on convergence due to genetic drift

The selection of Genetic Algorithm (GA) parameters is a difficult problem, and if not addressed adequately, solutions of good quality are unlikely to be found. A number of approaches have been developed to assist in the calibration of GAs, however there does not exist an accepted method to determine the parameter values. In this paper, a GA calibration methodology is proposed based on the convergence of the population due to genetic drift, to allow suitable GA parameter values to be determined without requiring a trial-and-error approach. The proposed GA calibration method is compared to another GA calibration method, as well as typical parameter values, and is found to regularly lead the GA to better solutions, on a wide range of test functions. The simplicity and general applicability of the proposed approach allows suitable GA parameter values to be estimated for a wide range of situations.

Determining Peak Flow Recurrence in Combined Basins with Limited Flow Data Using Genetic Algorithm Calibration

The City of Columbus, Ohio, completed a comprehensive Wet Weather Management Plan (WWMP) to mitigate hydraulic deficiencies in the City’s main trunk sewers and…

Calibration of Distributions of Commercial Motor Vehicles in CORSIM

One of the most critical aspects of effective microscopic traffic simulation models is proper calibration for accurate replication of both supply and demand characteristics, as well as their interaction. Recent research has begun automating the calibration process by using intelligent transportation system data. This research, however, has targeted automobile traffic and has not generally included commercial motor vehicle (CMV) impacts. Because CMVs are a significant part of the traffic stream and tend to have a disproportionate effect on the transportation system, it is theorized that these vehicles should be included in the calibration process. The objective of this research, therefore, is ( a) to outline calibration parameters and network properties available (including site-specific vehicle distributions with weigh-in-motion and automatic vehicle classification data) for a freeway simulation of both passenger cars and CMVs and ( b) to apply these parameters and network properties on an urban freeway system in Texas by using the microscopic traffic simulation model CORSIM and an auto-mated genetic algorithm calibration methodology. The results of the analysis indicate that the overall calibration measurably improves the ability of the model to replicate observed conditions. The results for this corridor, however, do not support the need to include maximum nonemergency deceleration rates in the calibration process. The inclusion of site-specific vehicle distributions, however, was observed to provide a more accurate representation of vehicle composition and overall network results. This methodology has not been explored previously and provides a strong base for evaluating the impacts of CMVs on the transportation network by the use of microscopic traffic simulation models.

Prediction of amino acid profiles in feed ingredients:: Genetic algorithm calibration of artificial neural networks

Linear regression (LR) has been used to predict the amino acid (AA) profiles of feed ingredients, given proximate analysis (PA) input. Artificial neural networks (ANN) have also been trained to predict AA levels, generally with better results. Past projects have indicated that ANN more effectively identified the complex relationship between nutrients and feed ingredients than did LR. It was shown that the maximum R 2 value, a measurement of the amount of variability explained by the model, was highest when a general regression neural network (GRNN) with iterative calibration (GRNNIT) was used to train the ANN. This was in comparison to LR, Ward backpropagation (WBP) or 3-layer backpropagation (3BP) architectures. The current study investigated the potential of a new, advanced method of calibration using the genetic algorithm (GA) to optimize GRNN smoothing values. Calibration of an ANN allows the neural network to generalize well and therefore provide good results on new data. A GRNN architecture (NeuroShell 2 ® Software) with GA calibration (GRNNGA) was used to train an ANN to predict AA levels in maize, soya bean meal (SBM), meat and bone meal, fish meal and wheat, based on proximate analysis input. Within the GRNNGA architecture, ANN were trained with either an Euclidean or City Block distance metric and a (0,1), (−1,1), (logistic) or (tanh) input scale. Predictive performance was judged on the basis of the maximum R 2 value. In general, maximum R 2 values were higher when the GA calibration was used in comparison to LR. For example, the highest methionine (MET) R 2 value for SBM was 0.54 (LR), 0.81 (3BP), 0.87 (WBP), 0.92 (GRNNIT) and 0.98 (GRNNGA). Genetic algorithm calibration of GRNN architecture led to further improvements in ANN performance for AA level predictions in most of the cases studied. Exceptions were the TSAA level in SBM (0.94 with GRNNIT vs. 0.90 with GRNNGA) and the TRY level in maize (0.88 with GRNNIT vs. 0.61 with GRNNGA).