Structural damage detection by wavelet transform and probabilistic neural network

Nowadays, structural health monitoring has attracted much attention, due to the construction of important and complex structures and their safety. One branch of structural health monitoring is damage detection, estimating the location and extent of eventual damages in the structural systems. In this study, an efficient method is introduced to determine the location and extent of damage in the frame, beam and truss structures using time domain response and an optimization algorithm. First of all, the structural damage detection problem is formulated as a standard optimization problem. So that, the optimization objective function is defined by using the acceleration of damaged structures and analytical model acceleration. The acceleration is obtained using Newmark method. Damage is simulated by reducing the elasticity modulus of structural members. Then, damage problem converted to an optimization problem are solved by teaching–learning-based optimization (TLBO) algorithm therefore, the exact location and extent of damage in structure can be determined. In order to show the capabilities of the proposed approach for identifying structural damage, four illustrative test examples are considered with considering measurement noise effect. The results clearly show that the proposed method is as a powerful method to detect multiple damage in structures.

Artificial neural networks (ANNs) are systems which are derived from the field of neuroscience and are characterized by intensive arithmetic operations. These networks display interesting features such as parallelism, classification, optimization, adaptation, generalization and associative memories. Since the McCulloch and Pitts pioneering work (McCulloch, W.S., & Pitts, W. (1943), there has been much discussion on the topic of ANNs implementation, and a huge diversity of ANNs has been designed (C. Lindsey & T. Lindblad, 1994). The benefits of using such implementations is well discussed in a paper by R. Lippmann (Richard P. Lipmann, 1984): “The great interest of building neural networks remains in the high speed processing that can be achieved through massively parallel implementation”. In another paper Clark S. Lindsey (C.S Lindsey, Th. Lindbald, 1995) posed a real dilemma of hardware implementation: “Built a general, but probably expensive system that can be reprogrammed for several kinds of tasks like CNAPS for example? Or build a specialized chip to do one thing but very quickly, like the IBM ZISC Processor”. To overcome this dilemma, most researchers agree that an ideal solution should relay the performances obtained using specific hardware implementation and the flexibility allowed by software tools and general purpose chips. Since their commercial introduction in the mid- 1980’s, and due to the advances in the development of both of the microelectronic technology and the specific CAD tools, FPGAs devices have progressed in an evolutionary and revolutionary way. The evolution process has allowed faster and bigger FPGAs, better CAD tools and better technical support. The revolution process concerns the introduction of high performances multipliers, Microprocessors and DSP functions. This has a direct incidence to FPGA implementation of ANNs and a lot of research has been carried to investigate the use of FPGAs in ANNs implementation (Amos R. Omandi & Jagath C. rajapakse, 2006). Another attractive key feature of FPGAs is their flexibility, which can be obtained at different levels: exploitation of the programmability of FPGA, dynamic reconfiguration or run time reconfiguration (RTR), (Xilinx XAPP290, 2004) and the application of the design for reuse concept (Keating, Michael; Bricaud, Pierre, 2002). However, a big disadvantage of FPGAs is the low level hardware oriented programming model needed to fully exploit the FPGA’s potential performances. High level based VHDL synthesis tools have been proposed to bridge the gap between the high level application requirements and the low level FPGA hardware but these tools are not algorithmic or application specific. Thus, special concepts need to be developed for automatic ANN implementation before using synthesis tools. In this paper, we present a high level design methodology for ANN implementation that attempts to build a bridge between the synthesis tool and the ANN design requirements. This method offers a high flexibility in the design while achieving speed/area performances constraints. The three implementation figures of the ANN based back propagation algorithm are considered. These are the off-type implementation, the on-chip global implementation and the dynamic reconfiguration choices of the ANN. To achieve our goal, a design for reuse strategy has been applied. To validate our approach, three case studies are considered using the Virtex-II and Virtex-4 FPGA devices. A comparative study is done and new conclusions are given.

Genetic fuzzy system for damage detection in beams and helicopter rotor blades

Artificial neural networks (ANN) have been successfully applied to a multitude of problems in various fields. One of the most prominent application fields is time series forecasting. Although ANN produces accurate forecasts in many time series implementations, there are still some problems with using ANN. ANN approach is composed of some components which are architecture structure, learning algorithm and activation function. These components have important effect on the forecasting performance of ANN. An important decision is the selection of optimum architecture of neural network that consists of determining the numbers of neurons in the layers of the network. Therefore, various approaches have been proposed to find the best ANN architecture in the literature. However, the most preferred method is still trial and error method for finding a good architecture. In this study, the total health expenditures made by social security institution in Turkey is forecasted by using a hybrid heuristic method proposed by Aladag [10] which is based on feed forward neural networks and Tabu search algorithm. It is seen that the hybrid forecasting approach produces very accurate results.

The detection of structural damage from the high-frequency local impedance spectra is addressed with a spectral classification approach consisting of features extraction followed by probabilistic neural network pattern recognition. The paper starts with a review of the neural network principles, followed by a presentation of the state of the art in the use of pattern recognition methods for damage detection. The construction and experimentation of a controlled experiment for determining benchmark spectral data with know amounts of damage and inherent statistical variation is presented. Spectra were collected in the 10-40 kHz, 10-150 kHz, and 300-450 kHz for 5 damage situations, each situation containing 5 members, identical, but slightly different. A features extraction algorithm was used to determine the resonance frequencies and amplitudes contained in these high-frequency spectra. The feature vectors were used as input to a probabilistic neural network. The training was attained using one randomly selected member from each of the 5 damage classes, while the validation was performed on all the remaining members. When features vector had a small size, some misclassifications were observed. Upon increasing the size of the features vector, excellent classification was attained in all cases. Directions for further studies include the study of other frequency bands and different neural network algorithms.

Recently, the authors proposed computationally attractive algorithms to determine the location and extent of structural damage for undamped structures assuming damage results in a localized change in stiffness properties. The algorithms make use of a finite-element model and a subset of measured eigenvalues and eigenvectors. The developed theories approach the damage location and extent problem in a decoupled fashion. First, a theory is developed to determine the location of structural damage. With location determined, a damage extent theory is then developed. The damage extent algorithm is a minimum rank perturbation, which is consistent with the effects of many classes of structural damage on a finite-element model. In this work, the concept of the minimum rank perturbation theory (MRPT) is adopted to determine the damage extent on the mass properties of an undamped structure. In addition, the MRPT is extended to the case of proportionall y damped structures. For proportionally damped structures, the MRPT is used to find the damage extent in any two of the three structural property matrices (mass, damping, or stiffness). Finally, illustrative case studies using both numerical and actual experimental data are presented. HE advent of the Space Shuttle has prompted considerable attention to the design and control of large space structures. Due to the large size and complexity of envisioned structures, as well as the use of advanced materials to reduce structural weight, it may become necessary to develop a structural health monitoring system to detect and locate structural damage as it occurs. From experience gained in the machinery health monitoring field, one would expect the vibration signature of the structure, either frequency response functions and/or modal parameters, to provide useful information in determining the location and extent of structural damage. Assume that a refined finite element model (FEM) of the structure has been developed before damage has occurred. By refined, we mean that the measured and analytical modal properties are in agreement. Next, assume that at a later date some form of structural damage has occurred. If significant, the damage will result in a change in the structures modal parameters. The question is: can the discrepancy between the original FEM modal properties and postdamage modal properties be used to ascertain structural damage? Most prior work in damage detection has used the general framework of FEM refinement (system identification) in the development of damage assessment algorithms. The motivation behind the development of FEM refinement techniques is based on the need to validate engineering FEMs before their acceptance as the basis for final design analysis. The standard problem has been to seek a refined FEM that is as close to the original FEM and whose modal properties are in agreement with those that are measured subject to various constraints such as symmetry and sparsity preservation. A considerable amount of work in this area has been

Artificial neural network (ANN) shows good nonlinear mapping ability in many applications compared to traditional algorithms. In many applications, it is now widely used to extract knowledge from the train neural network. The fact that the model obtained with neural network is not understandable in terms of black box model is a brake to their use in this field. To enhance the explanation of ANN, a novel algorithm of regression rules extraction from ANN based on linear intelligent insertion is proposed in this paper. The linear function and symbolic rules is used to instead of ANN, and the rules are generated by the decision tree. The piecewise linear function and symbolic rules can not only ensure the accuracy but also enhance the explanation. Simulation experiments show that the proposed algorithm generates rules are more accurate than the existing algorithms based on decision trees or linear regression.

Artificial Neural Network (ANN) has been widely used for engineering monitoring and diagnosis. However, there are still several important problems unsolved and one of them is the architecture design of the ANN (namely, choosing the number of nodes in the hidden layer). In this technical brief, a new method of ANN architecture is introduced based on the idea that an ANN represents a mapping of training samples. Hence, the best ANN should represent the mapping that is most similar to the training samples. The method is tested using three practical engineering monitoring and diagnosis examples, including tool condition monitoring in turning, cutting condition monitoring in tapping, and metallographic condition monitoring in welding. It is demonstrated that the proposed method can improve the monitoring and diagnosis by approximately 3 percent.

Artificial neural networks (ANN) are among the nonlinear prediction techniques popular in the last two decades. Recent studies show that ANN can be modeled with different training techniques. ANN is usually trained by the backpropagation method (BP). In this study, ANN structures were trained by using artificial bee colony algorithm (ABC) and, weight and bias values were tried to be determined. ABC training (ANN-ABC) was tested over three different datasets and compared with the BP training (ANN-BP) results. In addition to use ABC in modeling, different error types such as mean square error (MSE), mean absolute percent error (MAPE) and adjusted coefficient of determination (R) have been used in the training. The results on popular time series datasets have shown that ABC based ANN training yields successful results in forecasting.

Artificial neural networks (ANN) is increasingly being used to solve engineering problems. Successful welding operations are at the top of engineering problems. The friction stir welding method, which is used to combine the materials under the melting temperature, is also a method that can be analyzed with ANN. In this study, Al-7075 workpieces (with and without aging treatment) were joined by the friction stir welding method. Tension tests were applied to the joined workpieces and the resulting values were modeled by ANN. In ANN model; The tensile strength of the assembled parts was tried to be estimated by input parameters (the type of the material, the number of revolutions and the feed rate). In the created ANN model; Different nerve numbers, different transfer functions, using different layer numbers, the models created by alternative network structures have been tested. In these experiments, prediction performance was measured using neuron and algorithm type variables. At the end of this study, it was seen that the ANN model for the parts joined with the FSW process made predictions with high consistency. The best estimates were obtained with the Levenberg Marquardt (LM) algorithm and the ANN model established with 3 neurons. This ANN model is seen as a suitable solution for this problem with 98% success.

Neural Networks with Asymptotics Control

Artificial Neural Networks (ANNs) have seen an explosion of interest over the last two decades and have been successfully applied in all fields of chemistry and particularly in analytical chemistry. Inspired from biological systems and originated from the perceptron, i.e. a program unit that learns concepts, ANNs are capable of gradual learning over time and modelling extremely complex functions. In addition to the traditional multivariate chemometric techniques, ANNs are often applied for prediction, clustering, classification, modelling of a property, process control, procedural optimisation and/or regression of the obtained data. This paper aims at presenting the most common network architectures such as Multi-layer Perceptrons (MLPs), Radial Basis Function (RBF) and Kohonen's self-organisations maps (SOM). Moreover, back-propagation (BP), the most widespread algorithm used today and its modifications, such as quick-propagation (QP) and Delta-bar-Delta, are also discussed. All architectures correlate input variables to output variables through non-linear, weighted, parameterised functions, called neurons. In addition, various training algorithms have been developed in order to minimise the prediction error made by the network. The applications of ANNs in water analysis and water quality assessment are also reviewed. Most of the ANNs works are focused on modelling and parameters prediction. In the case of water quality assessment, extended predictive models are constructed and optimised, while variables correlation and significance is usually estimated in the framework of the predictive or classifier models. On the contrary, ANNs models are not frequently used for clustering/classification purposes, although they seem to be an effective tool. ANNs proved to be a powerful, yet often complementary, tool for water quality assessment, prediction and classification.

Artificial neural network (ANN) is a non-linear statistical technique that being used to describe material behavior. This paper proposes using artificial neural networks (ANNS) in predicting silicon and nickel recovery. During the experimental work, the used optimum parameters are reaction time is 25 min., temperature is 950 ᵒC, Ni2O3 /Al wt. (weight) ratio is 0.082, and Na2SiF6 / Al wt. ratio is 1. Some tests such as chemical analysis, microstructure examination (EDX mapping), XRD diffraction were carried out on the produced alloys. The obtained experimental results are used to train the artificial neural network (ANN). While reaction time, temperature, Ni2O3 /Al wt. ratio, and Na2SiF6 / Al wt. ratio are used as ANN's inputs. Silicon and nickel recovery are used as ANN's outputs. The used ANN consists of three layers; Input layer that includes 4 neurons, the hidden layer includes 9 neurons, while the output layer contains 2 neurons. The Levenberg-Marquardt (LM) is used as the training function. Optimal mean square errors (MSE) for the ANN during predicting and estimating silicon and nickel recovery equal 0.0358, 0.0034, respectively, when reaction time is the variable and other parameters are kept constant, MSE equal 1.4007e-04, 1.3478e-04 when temperature is variable and other parameters are kept constant, MSE equal 1.3839e-04, 9.9891e-05 when Ni2O3/Al wt. ratio was the variable and other parameters are kept constant and finally MSE equal 0.0287, 0.0263 when Na2SiF6 / Al wt. ratio is variable and other parameters are kept constant.

Artificial neural networks (ANN) are receiving a lot of attention because of their nonlinear mapping ability in the field of short term load forecast (STLF). ANN based STLF model commonly use back propagation algorithm, that may not converge properly, that affects the forecast accuracy. A hybrid approach, based on artificial neural network (ANN) and genetic algorithm (GA) that combines the advantages of each technique is proposed in this research. Genetic algorithm is implemented for the optimization of the architecture of feedforward neural network and selection of its initial weight values. Error back propagation algorithm for the training of the optimized neural network will be implemented. The second stage of this research is related with the complete training of the neural network based on genetic algorithm, using genetic manipulation of chromosomes. The results show that this approach produced better output in terms of enhanced forecast accuracy.

Artificial neural network (ANN) can play a vital role in its application to on-load tap changer of distribution transformers since the input variation in practical field is enormous due to continuous changes in the power system conditions and neural network is capable of handling this variation due to its robust generalization capability. In this paper we use the two algorithms, namely, scaled conjugate gradient (SCG) and Bayesian regularization (BR) for training an ANN to control the automatic on load tap changer of two parallel transformers connected across the power network. Primarily five data sets are constructed considering voltage phase angle differences between the sources feeding the primary windings while the secondaries are connected in paralleling mode. For each data set, accuracy in ANN based tap changer decision is investigated and BR algorithm yields better results than SCG algorithm. In the second stage, another combined data set is formed by analyzing the trend of false responses in primary results. Results show significant improvement in performance when combined data set is used for training. With this data set, difference in performance between BR and SCG algorithms reduces, however BR still performs better with significantly high accuracy in tap changer operation. The results demonstrate the potential applicability of ANN in tap changer operation of parallel transformers.