An intelligent approach to predict gas compressibility factor using neural network model

This research illustrates the utilization of a new model based on artificial neural networks (ANNs) in prediction of compressibility factor (z-factor) of natural gases using experimental data based on Standing and Katz z-factor diagram. Although equations of state and empirical correlations have been applied for predicting compressibility factor, the demands for the modern, more reliable and easy-to-use models encouraged the researchers to recommend modern facilities such as intelligent systems. This investigation describes a new technique for computing z-factor of natural gases. The base of the approach is ANN in which a 2:5:5:1 structure is used as an optimum network to predict the z-factor. The statistical results show that the developed ANN is an excellent tool for estimating z-factor values; therefore, it can be confidently used for natural gases with various compositions at a specific temperature and pressure.

     

Optimum model for bearing capacity of concrete-steel columns with AI technology via incorporating the algorithms of IWO and ABC

In a composite column, the performance of both the concrete and steel has a considerable effect on the structural behaviour under different loading conditions. This study applies several artificial intelligence (AI) techniques to optimise the bearing capacity of concrete-filled steel tube (CFST) columns. First, the bearing capacity values of the CFST columns are estimated by an artificial neural network (ANN) technique. Using 303 datasets, the outer diameter, concrete compressive strength, tensile yield stress of the steel column, thickness of the steel cover, and length of the applied samples are considered as the model inputs. Following a series of analyses, several ANN models are developed. The ANN model with 8 neurons and 250 iterations is determined as the best model to predict the bearing capacity of the CFST columns. Subsequently, the invasive weed optimisation (IWO) technique, which is considered the most current optimisation algorithm, is developed to maximise the results of the bearing capacity by considering the selected ANN model. To highlight the ability of IWO, the artificial bee colony (ABC) algorithm is also applied. Consequently, it is found that both optimisation algorithms can design input parameters such that the maximum value of the bearing capacity can be obtained. The bearing capacity of the CFST columns from the ABC and IWO techniques indicates that IWO has a better capability of maximising the bearing. Thus, IWO can optimise similar problems with a high rate of performance.

     

Application of a Kohonen neural network to the analysis of data regarding the alkylation of toluene with methanol catalyzed by ZSM-5 type zeolites

para-Xylene is widely used in chemical industry. It can be synthesized by alkylation of toluene with methanol using zeolite ZSM-5 as catalyst. The proportion of para-xylene, among its other isomers and other reaction byproducts, depends on the reaction conditions. As this process still remains largely empirical, we attempted to build a theoretical model able to predict the para-xylene yield under specific reaction conditions. We have consequently collected data regarding this reaction from the literature and exploited the potency of a particular artificial neural network (ANN), the counter-propagation ANN based on the Kohonen technique. The results show that such an approach is suitable to establish a predictive model of the yield in para-xylene on the basis of reaction parameters. The quality of the model could be further improved by considering a larger valuable data set, e.g. including experiments characterized by a low yield in para-xylene.     

Prediction of seismic slope stability through combination of particle swarm optimization and neural network

One of the main concerns in geotechnical engineering is slope stability prediction during the earthquake. In this study, two intelligent systems namely artificial neural network (ANN) and particle swarm optimization (PSO)–ANN models were developed to predict factor of safety (FOS) of homogeneous slopes. Geostudio program based on limit equilibrium method was utilized to obtain 699 FOS values with different conditions. The most influential factors on FOS such as slope height, gradient, cohesion, friction angle and peak ground acceleration were considered as model inputs in the present study. A series of sensitivity analyses were performed in modeling procedures of both intelligent systems. All 699 datasets were randomly selected to 5 different datasets based on training and testing. Considering some model performance indices, i.e., root mean square error, coefficient of determination (R ²) and value account for (VAF) and using simple ranking method, the best ANN and PSO–ANN models were selected. It was found that the PSO–ANN technique can predict FOS with higher performance capacities compared to ANN. R ² values of testing datasets equal to 0.915 and 0.986 for ANN and PSO–ANN techniques, respectively, suggest the superiority of the PSO–ANN technique.     

Modelling stress–strain and volume change behaviour of unsaturated soils using an evolutionary based data mining technique,an incremental approach

Modelling of unsaturated soils has been the subject of many research works in the past few decades. A number of constitutive models have been developed to describe the complex behaviour of unsaturated soils. However, many have proven to be unable to predict all aspects of the behaviour of unsaturated soils in a unified manner. In this paper an alternative new approach is presented, based on the Evolutionary Polynomial Regression (EPR) technique. EPR is a data mining technique that generates a transparent and structured representation of the behaviour of a system directly from input test data. The capabilities of the proposed EPR-based framework in modelling of behaviour of unsaturated soils are illustrated using results from a comprehensive set of triaxial tests on samples of compacted unsaturated soils from literature. The main parameters used for modelling of the behaviour of unsaturated soils during shearing are initial water content, initial dry density, mean net stress, axial strain, suction, volumetric strain, and deviator stress. The model developed is used to predict different aspects of the behaviour of unsaturated soils for conditions not used in the model building process. The results show that the proposed approach provides a useful framework for modelling of unsaturated soils. The merits and advantages of the proposed approach are highlighted.     

Robust feedforward and recurrent neural network based dynamic weighted combination models for software reliability prediction

Traditional parametric software reliability growth models (SRGMs) are based on some assumptions or distributions and none such single model can produce accurate prediction results in all circumstances. Non-parametric models like the artificial neural network (ANN) based models can predict software reliability based on only fault history data without any assumptions. In this paper, initially we propose a robust feedforward neural network (FFNN) based dynamic weighted combination model (PFFNNDWCM) for software reliability prediction. Four well-known traditional SRGMs are combined based on the dynamically evaluated weights determined by the learning algorithm of the proposed FFNN. Based on this proposed FFNN architecture, we also propose a robust recurrent neural network (RNN) based dynamic weighted combination model (PRNNDWCM) to predict the software reliability more justifiably. A real-coded genetic algorithm (GA) is proposed to train the ANNs. Predictability of the proposed models are compared with the existing ANN based software reliability models through three real software failure data sets. We also compare the performances of the proposed models with the models that can be developed by combining three or two of the four SRGMs. Comparative studies demonstrate that the PFFNNDWCM and PRNNDWCM present fairly accurate fitting and predictive capability than the other existing ANN based models. Numerical and graphical explanations show that PRNNDWCM is promising for software reliability prediction since its fitting and prediction error is much less relative to the PFFNNDWCM.     

Product form design using customer perception evaluation by a combined superellipse fitting and ANN approach

Product aesthetics plays an important role in new product design and development. Product form can deliver product images and affect customer’s impression to a product. However, it is usually difficult to apply conventional approaches to represent the product form precisely and effectively for modeling the relationship between product image and customer perception. The objective of this work is to develop a computational technique for product aesthetics design so that customer perception can be taken into product form design in a more systematic and intelligent manner. To achieve this aim, a novel parametric approach is proposed to introduce design parameters such as line, size, and ratio into product design model and the technique of generalized superellipse fitting is adopted to describe the outline pattern of a product. Since customer perception on a product is highly non-linear and very difficult to be described by any traditional mathematical approaches, an artificial neural network (ANN) model is therefore established to relate the design parameters and the perceptual values for the design of a new product. A case study of mobile phone design, in which twelve numerical parameters are defined for the conceptual model, has been conducted to explain the implementation of the proposed approach. A three-layered perceptron ANN model is developed to predict the perceptual values of stylishness based on a survey using 32 mobile phone samples. The results of the case study illustrate that the proposed approach can successfully generate an optimum design of a mobile phone by applying a genetic algorithm (GA) on the trained ANN model.     

Evaluation and prediction mental workload in user interface of maritime operations using eye response

Eye response measurement is one of the objective measure methods and useful for assessing of operators' mental workload (MWL). The main objectives of this paper are to consider the relationship between operators' MWL and eye responses in the task of operating marine engine interface. Also, an artificial neural network (ANN) model was developed to predict the operators' MWL based on integrating eye response data. Eye response indices (pupil dilation, blink rate, fixation rate, and saccadic rate) were recorded, and two subjective rating methods (The National Aeronautics and Space Administration's Task Load Index [NASA-TLX] and subjective workload assessment technique [SWAT]) were used for 27 participants. The results again confirm that the eye response is sensitive to MWL in workload levels of the task when using the interface control. The ANN model developed by measuring these indices can predict the operators' MWL with the determination coefficient (R²) of 0.971, 0.912 and 0.918 for training, validation, and testing, respectively. These results indicated that the ANN approach is quite accurate for the prediction of operators' MWL based on eye response indices.Relevance to industryThe developed model is expected to provide the operator with a reference value of their MWL by evaluating their physiological indices. This result might be applied for developing an intelligent prediction model in the actual work environment to inform or support the operator in a variety of ways. From this, the manager can organize the human resources for each task to sustain the appropriate MWL as well as to improve the work performance.     

Comparison of artificial neural network and fuzzy logic models for prediction of long-term compressive strength of silica fume concrete

In this study, an artificial neural network (ANN) and fuzzy logic (FL) study were developed to predict the compressive strength of silica fume concrete. A data set of a laboratory work, in which a total of 48 concretes were produced, was utilized in the ANNs and FL study. The concrete mixture parameters were four different water–cement ratios, three different cement dosages and three partial silica fume replacement ratios. Compressive strength of moist cured specimens was measured at five different ages. The obtained results with the experimental methods were compared with ANN and FL results. The results showed that ANN and FL can be alternative approaches for the predicting of compressive strength of silica fume concrete.     

Customer churn prediction by hybrid neural networks

As churn management is a major task for companies to retain valuable customers, the ability to predict customer churn is necessary. In literature, neural networks have shown their applicability to churn prediction. On the other hand, hybrid data mining techniques by combining two or more techniques have been proved to provide better performances than many single techniques over a number of different domain problems. This paper considers two hybrid models by combining two different neural network techniques for churn prediction, which are back-propagation artificial neural networks (ANN) and self-organizing maps (SOM). The hybrid models are ANN combined with ANN (ANN + ANN) and SOM combined with ANN (SOM + ANN). In particular, the first technique of the two hybrid models performs the data reduction task by filtering out unrepresentative training data. Then, the outputs as representative data are used to create the prediction model based on the second technique. To evaluate the performance of these models, three different kinds of testing sets are considered. They are the general testing set and two fuzzy testing sets based on the filtered out data by the first technique of the two hybrid models, i.e. ANN and SOM, respectively. The experimental results show that the two hybrid models outperform the single neural network baseline model in terms of prediction accuracy and Types I and II errors over the three kinds of testing sets. In addition, the ANN + ANN hybrid model significantly performs better than the SOM + ANN hybrid model and the ANN baseline model.     

基于蜜罐的入侵检测系统的设计与实现*

传统的入侵检测系统无法识别未知的攻击,提出在入侵检测系统中引入蜜罐技术来弥补其不足,并设计和实现了一个基于人工神经网络的入侵检测系统HoneypotIDS。该系统应用感知器学习方法构建FDM检测模型和SDM检测模型两阶段检测模型来对入侵行为进行检测。其中,FDM检测模型用于划分正常类和攻击类,SDM检测模型则在此基础上对一些具体的攻击类型进行识别。最后,设计实验对HoneypotIDS的检测能力进行了测试。实验结果表明,HoneypotIDS对被监控网络中的入侵行为具有较好的检测率和较低的误报率。     

基于CFNN的电火花加工工艺效果预测模型

针时常规神经网络和模糊神经网络的不足,介绍了一种具有快速算法的补偿模糊神经网络,并根据电火花加工的工艺特点及其复杂性,建立了基于补偿模糊神经网络的电火花加工工艺效果预测模型,可实现指定加工条件下的工艺效果预测.仿真结果显示了其良好的预测精度,其性能优于常规模糊神经网络.     

An optimized ANN model based on genetic algorithm for predicting ripping production

Due to the environmental constraints and the limitations on blasting, ripping as a ground loosening and breaking method has become more popular in both mining and civil engineering applications. As a result, a more applicable rippability model is required to predict ripping production (Q) before conducting such tests. In this research, a hybrid genetic algorithm (GA) optimized by artificial neural network (ANN) was developed to predict ripping production results obtained from three sites in Johor state, Malaysia. It should be noted that the mentioned hybrid model was first time applied in this field. In this regard, 74 ripping tests were investigated in the studied areas and the relevant parameters were also measured. A series of GA–ANN models were conducted in order to propose a hybrid model with a higher accuracy level. To demonstrate the performance capacity of the hybrid GA–ANN model, a pre-developed ANN model was also proposed and results of predictive models were compared using several performance indices. The results revealed higher accuracy of the proposed hybrid GA–ANN model in estimating Q compared to ANN technique. As an example, root-mean-square error values of 0.092 and 0.131 for testing datasets of GA–ANN and ANN techniques, respectively, express the superiority of the newly developed model in predicting ripping production.

     

An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring

Accurate equipment remaining useful life prediction is critical to effective condition based maintenance for improving reliability and reducing overall maintenance cost. In this paper, an artificial neural network (ANN) based method is developed for achieving more accurate remaining useful life prediction of equipment subject to condition monitoring. The ANN model takes the age and multiple condition monitoring measurement values at the present and previous inspection points as the inputs, and the life percentage as the output. A function generalized from the Weibull failure rate function is used to fit each condition monitoring measurement series for a failure history, and the fitted measurement values are used to form the ANN training set so as to reduce the effects of the noise factors that are irrelevant to the equipment degradation. A validation mechanism is introduced in the ANN training process to improve the prediction performance of the ANN model. The proposed ANN method is validated using real-world vibration monitoring data collected from pump bearings in the field. A comparative study is performed between the proposed ANN method and an adapted version of a reported method, and the results demonstrate the advantage of the proposed method in achieving more accurate remaining useful life prediction.     

Ability to forecast unsteady aerodynamic forces of flapping airfoils by artificial neural network

The ability of artificial neural networks (ANN) to model the unsteady aerodynamic force coefficients of flapping motion kinematics has been studied. A neural networks model was developed based on multi-layer perception (MLP) networks and the Levenberg–Marquardt optimization algorithm. The flapping kinematics data were divided into two groups for the training and the prediction test of the ANN model. The training phase led to a very satisfactory calibration of the ANN model. The attempt to predict aerodynamic forces both the lift coefficient and drag coefficient showed that the ANN model is able to simulate the unsteady flapping motion kinematics and its corresponding aerodynamic forces. The shape of the simulated force coefficients was found to be similar to that of the numerical results. These encouraging results make it possible to consider interesting and new prospects for the modelling of flapping motion systems, which are highly non-linear systems.     

Exploring the major factors affecting fly-ash concrete carbonation using artificial neural network

Concrete carbonation is one of the main causes of corrosion of the reinforcement and consequently causing damage to the reinforced concrete structures. The progress of the carbonation front depends on many factors including mixture proportions and exposure conditions. Several carbonation prediction models including mathematical and analytical predictions are available. Most of these models, however, are based on simple regression equations and cannot predict or accurately reflect the various factors involved in concrete carbonation. The current published results in this issue are in conflict. In view of this, our research aims to apply an artificial neural network (ANN) approach for predicting the carbonation of fly-ash concrete taking into account the most influential parameters, including mixture proportions and exposure conditions. Six parameters were considered as inputs to the ANN model, covering, binder and fly-ash content, water-to-binder ratio, CO₂ concentration, relative humidity, and time of exposure; one output is carbonation depth. The ANN model was prepared, trained, and tested with 300 datasets from experiments as well as past research. The performance of training, validation, and test sets shows a high correlation between the experimental and the ANN predicted values of the carbonation depth. In addition, the proposed prediction model was in good agreement with the experimental data in comparison with other model. This study concludes that the use of this model for numerical investigations on the parameters affecting the carbonation depth in fly-ash concrete is successful and provides scientific guidance for durability design.

     

Applying a meta-heuristic algorithm to predict and optimize compressive strength of concrete samples

The successful use of fly ash (FA) and silica fume (SF) materials has been reported in the design of concrete samples in the literature. Due to the benefits of using these materials, they can be utilized in many industrial applications. However, the proper use of them in the right mixes is one of the important factors with respect to the strength and weight of concrete. Therefore, this paper develops relationships based on meta-heuristic (MH) algorithms (artificial bee colony technique) to evaluate the compressive strength of concrete specimens using laboratory experiments. A database comprising silica fume replacement ratio, fly ash replacement ratio, total cementitious material, water content coarse aggregate, high-rate water-reducing agent, fine aggregate, and age of samples, as model inputs, was used to evaluate and predict the compressive strength of concrete samples. Developed models of the MH technique created relationships between the mentioned parameters. In the new models, the influence of each parameter on the compressive strength was determined. Finally, using the developed model, optimum conditions for compressive strength of concrete samples were presented. This paper demonstrated that the MH algorithms are able to develop relationships that can serve as good substitutes for empirical models.

     

The use of neural networks for the prediction of the settlement of one-way footings on cohesionless soils based on standard penetration test

In this study, artificial neural networks (ANNs) were used to predict the settlement of one-way footings, without a need to perform any manual work such as using tables or charts. To achieve this, a computer programme was developed in the Matlab programming environment for calculating the settlement of one-way footings from five traditional settlement prediction methods. The footing geometry (length and width), the footing embedment depth, the bulk unit weight of the cohesionless soil, the footing applied pressure, and corrected standard penetration test varied during the settlement analyses, and the settlement value of each one-way footing was calculated for each traditional method by using the written programme. Then, an ANN model was developed for each method to predict the settlement by using the results of the analyses. The settlement values predicted from each ANN model developed were compared with the settlement values calculated from the traditional method. The predicted values were found to be quite close to the calculated values. Additionally, several performance indices such as determination coefficient, variance account for, mean absolute error, root mean square error, and scaled percent error were computed to check the prediction capacity of the ANN models developed. The constructed ANN models have shown high prediction performance based on the performance indices calculated. The results demonstrated that the ANN models developed can be used at the preliminary stage of designing one-way footing on cohesionless soils without a need to perform any manual work such as using tables or charts.     

Estimation of significant wave height in shallow lakes using the expert system techniques

Significant wave height is an important hydrodynamic variable for the design application and environmental evaluation in coastal and lake environments. Accurate prediction of significant wave height can assist the planning and analysis of lake and coastal projects. In this study, the Genetic Algorithm (GA) is used as the optimization technique to better predict model parameters. Also, Kalman Filtering (KF) is used for prediction of significant wave height from wind speed. KF technique makes predictions based on stochastic and dynamic structures. The integrated Geno Kalman Filtering (GKF) technique is applied to develop predictive models for estimation of significant wave height at stations LZ40, L006, L005 and L001 in Lake Okeechobee, Florida. The results show that the GKF methodology can perform very well in predicting the significant wave height and produce lower mean relative error and mean-square error than those from Artificial Neural Network (ANN) model. The superiority of GKF method over ANN is presented with comparisons of predicted and observed significant wave heights.     

Multiple Decision Expert Systems for Performance Analysis of a Boiler System

Artificial neural networks (ANN)-based multiple decision expert systems (MDES) were developed for assessing the performance of a boiler system. Different configurations of ANN were used with different decision combination methods, including a neural combiner, to propose the model. The model was developed using the plant data collected over a period of five months to predict steam temperature, pressure, and mass flow rate, using feed water pressure, feed water temperature, conveyor speed, and incinerator exit temperature as the input parameters. The predictive capability of the model is evaluated in terms of both correlation coefficient (R) and mean absolute percentage error (MAPE). The results observed from this work demonstrate that neural combiner and ANN-based MDES can efficiently predict the data on steam properties consistently, and that the model can serve as an efficient tool for monitoring boiler behavior under real-time conditions. Superiority of the proposed model over others under various scenarios is also demonstrated.