Delamination detection using methods of computational intelligence

Delamination detection with error and noise polluted natural frequencies using computational intelligence concepts

This research work deals with aspects concerned with delamination detection in composite structures as revealed by an approach based on vibration measurements. Variations in vibration characteristics generated in composite laminates indicate the existence of delaminations because degradation due to delamination causes reduction in flexural stiffness and strength of the material and as a result vibration parameters like natural frequency responses are changed. Hence, it is possible to monitor the variation in natural frequencies to identify the presence of delamination, and assess its size and location for online structural health monitoring (SHM). The approach to this paper, therefore, typically depends on undertaking the analysis of structural models implemented by finite element analysis (FEA). The numerical solutions using FE models known as the simulator computes the natural frequencies for the delaminated and undelaminated specimens of composite laminates. However, these FE models are computationally expensive, and surrogate (approximation) models are introduced to curtail the computational expense. The simulator is employed to solve the inverse problem using algorithms based on computational intelligence concepts. An artificial neural network (ANN) model is developed to also solve the inverse problem for delamination detection directly and to provide surrogate models integrated with optimization algorithms (the gradient-based local search and non-dominated sorting genetic algorithm-II) to contain the computationally expensive simulations by FEA. This approach is termed as surrogate assisted optimization and it is seen that the engagement of surrogate models in lieu of the FE models in the optimization loop greatly enhances the accuracy of delamination detection results within an affordable computational cost and provides control over handling different variables. Meanwhile, to aid with the building of effective surrogate models using substantial number of training datasets, K-means clustering algorithm is harnessed and this effectively reduces the large training datasets usually required for ANN training. This paper demonstrated that ANN and optimization algorithms with surrogates show immense potentialities for use in delamination damage detection scenarios. Prediction errors of the algorithms were quantified and they were shown to be satisfactory when applied to previously experimental data. The algorithms in their inverse formulations are capable of predicting accurately delamination parameters. Hence, these algorithms should be employed for application in the domain of SHM where their small computational requirements could be exploited for online damage detection.

In this paper, a new analytical model is presented to detect the presence, size, and location of a delamination embedded in a laminated composite beam. The sensors bonded on the top and bottom surfaces of a host beam are made from PZT piezoelectric layers. By employing this analytical model, the first three natural frequencies and sensor charge output distribution for the beams with different delamination length, axial and through-the-thickness delamination location, and delamination gap can be predicted, when a beam is excited by an external force. An approach is also proposed to obtain the sensor charge output distribution along the beam length using evenly distributed electrode strips. Subsequently, the present model is applied to a laminated plain weave composite beam with an embedded and through-width delamination, followed by an extensive numerical study. An investigation is carried out on the influence of the boundary condition, delamination length, axial delamination location, through-the-thickness delamination location, delamination gap on the first three natural frequency change and sensor charge output distribution along the beam length. The effects of number and size of electrode strips on the sensor charge output distribution is also studied. A comparison of the first three natural frequencies between the present predicted and finite element analysis results reveals that there is a good agreement between these two models.

The detailed procedure for the calculation of thermodynamic properties based on formulations explicit in Helmholtz energy (Lemmon & Starling, 2003) and on AGA-8 detail characterization equation (Starling & Savidge, 1992) is given in (ISO-207651-1, 2005). Here we elaborate an alternative procedure for the calculation of properties of a natural gas that was originally published in the Journal Flow Measurement and Instrumentation (Maric, 2005 & 2007). The procedure is derived using fundamental thermodynamic equations (Olander, 2007), DIPPR AIChE (DIPPR® Project 801, 2005) generic ideal heat capacity equations, and AGA-8 (Starling & Savidge, 1992) extended virial-type equations of state. The procedure specifies the calculation of specific heat capacities at a constant pressure cp and at a constant volume cv, the JT coefficient μJT, and the isentropic exponent κ of a natural gas. The effect of a JT expansion on the accuracy of natural gas flow rate measurements will be pointed out. The possibilities of using the computational intelligence methods - Artificial Neural Networks - ANNs (Ferrari & Stengel, 2005, Wilamowski et al., 2008) and machine learning tools - Group Method of Data Handling - GMDH (Ivakhnenko, 1971, Nikolaev & Iba, 2003) for meta-modeling the effects of natural gas properties in flow rate measurements (Maric & Ivek, 2010) will be illustrated. The practical examples of ANN and GMDH surrogate models for the compensation of natural gas flow rate measurement error caused by the thermodynamic effects, with the corresponding accuracies and execution times will be given. The models are particularly suitable for implementation in low computing power embedded systems.

Process control strategies for a steel making furnace using ANN with bayesian regularization and ANFIS

Department of Management Sciences, City University of Hong Kong, Tat Chee Avenue, Kowloon, Hong Kong As a multidisciplinary field, financial engineering is becoming increasingly important in today’s economic and financial world, especially in areas such as portfolio management, asset valuation and prediction, fraud detection, and credit risk management. For example, in a credit risk context, the recently approved Basel II guidelines advise financial institutions to build comprehensible credit risk models in order to optimize their capital allocation policy. Computational methods are being intensively studied and applied to improve the quality of the financial decisions that need to be made. Until now, computational methods and models are central to the analysis of economic and financial decisions. However, more and more researchers have found that the financial environment is not ruled by mathematical distributions or statistical models. In such situations, some attempts have also been made to develop financial engineering models using some emerging intelligent computing approaches. For example, an artificial neural network (ANN) is a non-parametric estimation technique which does not make any distributional assumptions regarding the underlying asset. Instead, ANN approach develops a model using sets of unknown parameters and lets the optimization routine seek the best fitting parameters to obtain the desired results. That is, these emerging intelligent solutions can efficiently improve the decisions for financial engineering problems. Having agreed on this basic fact, the guest editors determined that the main purpose of this special issue is not to merely illustrate the superior performance of a new intelligent computational method, but also to demonstrate how it can be used effectively in a financial engineering environment to improve and facilitate financial decision making. For this purpose, this special issue presents some new progress in intelligent computational methods for financial engineering In particular, the special issue addresses how the emerging intelligent computational methods (e.g., ANN, support vector machines, evolutionary algorithm, and fuzzy models etc.) can be used to develop intelligent, easy-to-use and/or comprehensible computational systems (e.g., decision support systems, agent-based system, and web-based systems etc.), which is expected to trigger some thoughts and deepen further research. In this special issue, 12 papers were selected from 26 submissions related to intelligent computational methods for financial engineering from different countries and regions. The authors of

Electricity load demand is the fundamental building block for all utilities planning. The load demand data has nonlinear and non-stationary characteristics, which make it difficult to be predicted accurately by just computational intelligence or ensemble methods. Ensemble methods like Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) is a powerful tool to forecast power load demand time series. Heterogeneous ensemble, a combination of two base models, will be distinct or more powerful in forecasting power load demand. In this paper, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) method is hybridized with three computational intelligence-based predictors: support vector regression (SVR), artificial neural network (ANN) and random forest (RF). The basis of this paper was to conduct a comparative study on the accuracy of the forecasting result from using heterogeneous ensemble method to individual computational intelligence or ensemble method for four different horizons. The performances of the heterogeneous method are compared and discussed. It shows that heterogeneous method has outperformed the individual computational intelligence and ensemble methods. Possible future works are also recommended for power load demand forecasting.

A study was initiated to predict water quality index (WQI) using artificial neural networks (ANNs) with respect to the concentrations of 16 groundwater quality variables collected from 47 wells and springs in Andimeshk during 2006–2013 by the Iran’s Ministry of Energy. Such a prediction has the potential to reduce the computation time and effort and the possibility of error in the calculations. For this purpose, three ANN’s algorithms including ANNs with early stopping, Ensemble of ANNs and ANNs with Bayesian regularization were utilized. The application of these algorithms for this purpose is the first study in its type in Iran. Comparison among the performance of different methods for WQI prediction shows that the minimum generalization ability has been obtained for the Bayesian regularization method (MSE = 7.71) and Ensemble averaging method (MSE = 9.25), respectively and these methods showed the minimum over-fitting problem compared with that of early stopping method. The correlation coefficients between the predicted and observed values of WQI were 0.94 and 0.77 for the test and training data sets, respectively indicating the successful prediction of WQI by ANNs through Bayesian regularization algorithm. A sensitivity analysis was implemented to show the importance of each parameter in the prediction of WQI during ANN’s modeling and showed that parameters like Phosphate and Fe are the most influential parameters in the prediction of WQI.

This work is devoted to synthesis of adaptive hybrid systems based on the Computational Intelligence (CI) methods (especially artificial neural networks (ANNs)) and the Group Method of Data Handling (GMDH) ideas to get new qualitative results in Data Mining, Intelligent Control and other scientific areas. The GMDH-artificial neural networks (GMDH-ANNs) are currently well-known. Their nodes are two-input N-Adalines. On the other hand, these ANNs can require a considerable number of hidden layers for a necessary approximation quality. Introduced Q-neurons can provide a higher quality using the quadratic approximation. Their main advantage is a high learning rate. Universal approximating properties of the GMDH-ANNs can be achieved with the help of compartmental R-neurons representing a two-input RBFN with the grid partitioning of the input variables' space. An adjustment procedure of synaptic weights as well as both centers and receptive fields is provided. At the same time, Epanechnikov kernels (their derivatives are linear to adjusted parameters) can be used instead of conventional Gauss functions in order to increase a learning process rate. More complex tasks deal with stochastic time series processing. This kind of tasks can be solved with the help of the introduced adaptive W-neurons (wavelets). Learning algorithms are characterized by both tracking and smoothing properties based on the quadratic learning criterion. Robust algorithms which eliminate an influence of abnormal outliers on the learning process are introduced too. Theoretical results are illustrated by multiple experiments that confirm the proposed approach's effectiveness.

The past decade has witnessed an increasing interest in the application of Computational Intelligence methods to problems derived from the field of cryptography and cryptanalysis. This phenomenon can be attributed both to the effectiveness of these methods to handle hard problems, and to the major importance of automated techniques in the design and cryptanalysis of cryptosystems. This chapter begins with a brief introduction to cryptography and Computational Intelligence methods. A short survey of the applications of Computational Intelligence to cryptographic problems follows, and our contribution in this field is presented. Specifically, some cryptographic problems are viewed as discrete optimization tasks and Evolutionary Computation methods are utilized to address them. Furthermore, the effectiveness of Artificial Neural Networks to approximate some cryptographic functions is studied. Finally, theoretical issues of Ridge Polynomial Networks and cryptography are presented. The experimental results reported suggest that problem formulation and representation are critical determinants of the performance of Computational Intelligence methods in cryptography. Moreover, since strong cryptosystems should not reveal any patterns of the encrypted messages or their inner structure, it appears that Computational Intelligence methods can constitute a first measure of the cryptosystems’ security.

Spam detection is one of the major problems which considered by many researchers by different developed strategies. Artificial Neural Network (ANN) is one of many others being proposed. However designing an ANN is a difficult task as it requires setting of ANN structure and tuning of some complex parameters. In this study, ANN was hybridized with Genetic algorithm (GA) in order to optimize the performance of ANN for spam detection. GA was used to determine some ANN parameters and suggest optimum weights to efficiently enhance the ANN learning. Experimental results show that the hybrid ANN and GA has superior performance when compared to conventional ANN.

Locating and sizing of delamination in composite laminates using computational and experimental methods

This study presents a novel methodology that integrates piezoelectric actuation and sensing with regression models and neural networks for high-accuracy detection and localization of multiple delamination and crack defects in composite laminates. An eight-layer graphite/epoxy composite plate, instrumented with piezoelectric patches, is excited using random voltage stimuli, generating structural responses captured by sensors. The proposed framework employs six regression techniques and artificial neural networks, achieving localization accuracy with R^2 values exceeding 99.6%. Additionally, combining five signal decomposition methods with four classifiers enables defect type identification with up to 98.26% accuracy. The methodology demonstrates exceptional precision in detecting previously unseen delamination and crack defects down to the lamina level, optimized through grid search cross-validation. A comparative analysis highlights that piezoelectric sensor voltage signals outperform acceleration signals for defect characterization. This integrated piezoelectric-regression/neural network framework establishes a robust foundation for non-destructive evaluation, offering significant potential for real-time structural health monitoring applications.

An artificial neural network (ANN) is a network designed with adaptation to a computer system. The developed computer system will perform functions oriented to the way the brain works (neuron concept). This study is an extension to the study of the suitability of ANN to be applied in numbers of applications, especially in the field of medical engineering. ANN has been widely being used in medicine, ANN is widely applied in education, research, and even decision making. In this study, ANN will be trained for pre-testing to predict the cardiac abnormalities symptom based on selected reference parameters. This reference parameter is better known as the input parameter to the ANN to detect cardiac abnormalities, among which are the of the height of peak/wave (amplitude) and time occurrence of peak/wave (duration of time) extracted from the electrocardiogram (ECG) signal. A complete ECG complex contains a P peak, a QRS wave, and a T peak. For each P peak, QRS wave, and T peak, amplitude height and duration will be measured to serve as input parameters. This makes six parameters defined as inputs to the ANN. This study has used a Multilayer Perceptron (MLP) network as ANN structure by being trained using three different training algorithms namely Backpropagation (BP), Lavenberg Marquardt (LM) and Bayesian Regularization (BR). At the end of the study, it showed the MLP network which by BR training algorithm gave the highest accuracy prediction (94.04%), followed by LM (92.95%) and BP (88.77%). In this study all MLP networks were activated using the Tansig activation function.

To investigate the feasibility of artificial neural networks (ANN) to reconstruct dose maps for intensity modulated radiation treatment (IMRT) fields compared with those of the treatment planning system (TPS). An artificial feed forward neural network and the back-propagation learning algorithm have been used to replicate dose calculations of IMRT fields obtained from PINNACLE(3) v9.0. The ANN was trained with fluence and dose maps of IMRT fields for 6 MV x-rays, which were obtained from the amorphous silicon (a-Si) electronic portal imaging device of Novalis TX. Those fluence distributions were imported to the TPS and the dose maps were calculated on the horizontal midpoint plane of a water equivalent homogeneous cylindrical virtual phantom. Each exported 2D dose distribution from the TPS was classified into two clusters of high and low dose regions, respectively, based on the K-means algorithm and the Euclidian metric in the fluence-dose domain. The data of each cluster were divided into two sets for the training and validation phase of the ANN, respectively. After the completion of the ANN training phase, 2D dose maps were reconstructed by the ANN and isodose distributions were created. The dose maps reconstructed by ANN were evaluated and compared with the TPS, where the mean absolute deviation of the dose and the γ-index were used. A good agreement between the doses calculated from the TPS and the trained ANN was achieved. In particular, an average relative dosimetric difference of 4.6% and an average γ-index passing rate of 93% were obtained for low dose regions, and a dosimetric difference of 2.3% and an average γ-index passing rate of 97% for high dose region. An artificial neural network has been developed to convert fluence maps to corresponding dose maps. The feasibility and potential of an artificial neural network to replicate complex convolution kernels in the TPS for IMRT dose calculations have been demonstrated.