Structural damage detection using frequency response functions and neural networks

This paper illustrates the damage identification and condition assessment of a three story bookshelf structure using a new frequency response functions (FRFs) based damage index and Artificial Neural Networks (ANNs). A major obstacle of using measured frequency response function data is a large size input variables to ANNs. This problem is overcome by applying a data reduction technique called principal component analysis (PCA). In the proposed procedure, ANNs with their powerful pattern recognition and classification ability were used to extract damage information such as damage locations and severities from measured FRFs. Therefore, simple neural network models are developed, trained by Back Propagation (BP), to associate the FRFs with the damage or undamaged locations and severity of the damage of the structure. Finally, the effectiveness of the proposed method is illustrated and validated by using the real data provided by the Los Alamos National Laboratory, USA. The illustrated results show that the PCA based artificial Neural Network method is suitable and effective for damage identification and condition assessment of building structures. In addition, it is clearly demonstrated that the accuracy of proposed damage detection method can also be improved by increasing number of baseline datasets and number of principal components of the baseline dataset.

Inferencing design styles using Baysian Networks

Reasoning with uncertain knowledge and belief has long been recognized as an important research issue in Artificial Intelligence (AI). Several methodologies have been proposed in the past, including knowledge-based systems, fuzzy sets, and probability theory. The probabilistic approach became popular mainly due to a knowledge representation framework called Bayesian networks. Bayesian networks have earned reputation of being powerful tools for modeling complex problem involving uncertain knowledge. Uncertain knowledge exists in domains such as medicine, law, geographical information systems and design as it is difficult to retrieve all knowledge and experience from experts. In design domain, experts believe that design style is an intangible concept and that its knowledge is difficult to be presented in a formal way. The aim of the research is to find ways to represent design style knowledge in Bayesian net works. We showed that these networks can be used for diagnosis (inferences) and classification of design style. The furniture design style is selected as an example domain, however the method can be used for any other domain.

Damage identification and condition assessment of building structures using frequency response functions and neural networks

This thesis investigated the viability of using Frequency Response Functions in combination with Artificial Neural Network technique in damage assessment of building structures. The proposed approach can help overcome some of limitations associated with previously developed vibration based methods and assist in delivering more accurate and robust damage identification results. Excellent results are obtained for damage identification of the case studies proving that the proposed approach has been developed successfully.

Portfolio selection using artificial intelligence

The application of artificial intelligence in finance is relatively new area of research. This project employed artificial neural networks (ANNs) that use both fundamental and technical inputs to predict future prices of widely held Australian stocks and use these predicted prices for stock portfolio selection over a long investment horizon. The research involved the creation and testing of a large number of possible network configurations and draws conclusions about ANN architectures and their overall suitability for the purpose of stock portfolio selection.

An Artificial Neutral Network (ANN) model for predicting biodiesel kinetic viscosity as a function of temperature and chemical compositions

An Artificial Neural Network (ANN) is a computational modeling tool which has found extensive acceptance in many disciplines for modeling complex real world problems. An ANN can model problems through learning by example, rather than by fully understanding the detailed characteristics and physics of the system. In the present study, the accuracy and predictive power of an ANN was evaluated in predicting kinetic viscosity of biodiesels over a wide range of temperatures typically encountered in diesel engine operation. In this model, temperature and chemical composition of biodiesel were used as input variables. In order to obtain the necessary data for model development, the chemical composition and temperature dependent fuel properties of ten different types of biodiesels were measured experimentally using laboratory standard testing equipments following internationally recognized testing procedures. The Neural Networks Toolbox of MatLab R2012a software was used to train, validate and simulate the ANN model on a personal computer. The network architecture was optimised following a trial and error method to obtain the best prediction of the kinematic viscosity. The predictive performance of the model was determined by calculating the absolute fraction of variance (R2), root mean squared (RMS) and maximum average error percentage (MAEP) between predicted and experimental results. This study found that ANN is highly accurate in predicting the viscosity of biodiesel and demonstrates the ability of the ANN model to find a meaningful relationship between biodiesel chemical composition and fuel properties at different temperature levels. Therefore the model developed in this study can be a useful tool in accurately predict biodiesel fuel properties instead of undertaking costly and time consuming experimental tests.

Predicting freeway pavement construction cost using a back-propagation neural network : a case study in Henan, China

The objective of this research was to develop a model to estimate future freeway pavement construction costs in Henan Province, China. A comprehensive set of factors contributing to the cost of freeway pavement construction were included in the model formulation. These factors comprehensively reflect the characteristics of region and topography and altitude variation, the cost of labour, material, and equipment, and time-related variables such as index numbers of labour prices, material prices and equipment prices. An Artificial Neural Network model using the Back-Propagation learning algorithm was developed to estimate the cost of freeway pavement construction. A total of 88 valid freeway cases were obtained from freeway construction projects let by the Henan Transportation Department during the period 1994−2007. Data from a random selection of 81 freeway cases were used to train the Neural Network model and the remaining data were used to test the performance of the Neural Network model. The tested model was used to predict freeway pavement construction costs in 2010 based on predictions of input values. In addition, this paper provides a suggested correction for the prediction of the value for the future freeway pavement construction costs. Since the change in future freeway pavement construction cost is affected by many factors, the predictions obtained by the proposed method, and therefore the model, will need to be tested once actual data are obtained.

Review of vibration-based damage detection and condition assessment of bridge structures using structural health monitoring

As a part of vital infrastructure and transportation networks, bridge structures must function safely at all times. However, due to heavier and faster moving vehicular loads and function adjustment, such as Busway accommodation, many bridges are now operating at an overload beyond their design capacity. Additionally, the huge renovation and replacement costs always make the infrastructure owners difficult to undertake. Structural health monitoring (SHM) is set to assess condition and foresee probable failures of designated bridge(s), so as to monitor the structural health of the bridges. The SHM systems proposed recently are incorporated with Vibration-Based Damage Detection (VBDD) techniques, Statistical Methods and Signal processing techniques and have been regarded as efficient and economical ways to solve the problem. The recent development in damage detection and condition assessment techniques based on VBDD and statistical methods are reviewed. The VBDD methods based on changes in natural frequencies, curvature/strain modes, modal strain energy (MSE) dynamic flexibility, artificial neural networks (ANN) before and after damage and other signal processing methods like Wavelet techniques and empirical mode decomposition (EMD) / Hilbert spectrum methods are discussed here.

Does chemometrics enhance the performance of electroanalysis?

This review explores the question whether chemometrics methods enhance the performance of electroanalytical methods. Electroanalysis has long benefited from the well-established techniques such as potentiometric titrations, polarography and voltammetry, and the more novel ones such as electronic tongues and noses, which have enlarged the scope of applications. The electroanalytical methods have been improved with the application of chemometrics for simultaneous quantitative prediction of analytes or qualitative resolution of complex overlapping responses. Typical methods include partial least squares (PLS), artificial neural networks (ANNs), and multiple curve resolution methods (MCR-ALS, N-PLS and PARAFAC). This review aims to provide the practising analyst with a broad guide to electroanalytical applications supported by chemometrics. In this context, after a general consideration of the use of a number of electroanalytical techniques with the aid of chemometrics methods, several overviews follow with each one focusing on an important field of application such as food, pharmaceuticals, pesticides and the environment. The growth of chemometrics in conjunction with electronic tongue and nose sensors is highlighted, and this is followed by an overview of the use of chemometrics for the resolution of complicated profiles for qualitative identification of analytes, especially with the use of the MCR-ALS methodology. Finally, the performance of electroanalytical methods is compared with that of some spectrophotometric procedures on the basis of figures-of-merit. This showed that electroanalytical methods can perform as well as the spectrophotometric ones. PLS-1 appears to be the method of practical choice if the %relative prediction error of not, vert, similar±10% is acceptable.

Simultaneous kinetic-spectrophotometric determination of maltol and ethyl maltol in food samples by using chemometrics

A fast and accurate procedure has been researched and developed for the simultaneous determination of maltol and ethyl maltol, based on their reaction with iron(III) in the presence of o-phenanthroline in sulfuric acid medium. This reaction was the basis for an indirect kinetic spectrophotometric method, which followed the development of the pink ferroin product (λmax = 524 nm). The kinetic data were collected in the 370–900 nm range over 0–30 s. The optimized method indicates that individual analytes followed Beer’s law in the concentration range of 4.0–76.0 mg L−1 for both maltol and ethyl maltol. The LOD values of 1.6 mg L−1 for maltol and 1.4 mg L−1 for ethyl maltol agree well with those obtained by the alternative high performance liquid chromatography with ultraviolet detection (HPLC-UV). Three chemometrics methods, principal component regression (PCR), partial least squares (PLS) and principal component analysis–radial basis function–artificial neural networks (PC–RBF–ANN), were used to resolve the measured data with small kinetic differences between the two analytes as reflected by the development of the pink ferroin product. All three performed satisfactorily in the case of the synthetic verification samples, and in their application for the prediction of the analytes in several food products. The figures of merit for the analytes based on the multivariate models agreed well with those from the alternative HPLC-UV method involving the same samples.

Multicomponent kinetic spectrophotometric determination of pefloxacin and norfloxacin in pharmaceutical preparations and human plasma samples with the aid of chemometrics

A spectrophotometric method for the simultaneous determination of the important pharmaceuticals, pefloxacin and its structurally similar metabolite, norfloxacin, is described for the first time. The analysis is based on the monitoring of a kinetic spectrophotometric reaction of the two analytes with potassium permanganate as the oxidant. The measurement of the reaction process followed the absorbance decrease of potassium permanganate at 526 nm, and the accompanying increase of the product, potassium manganate, at 608 nm. It was essential to use multivariate calibrations to overcome severe spectral overlaps and similarities in reaction kinetics. Calibration curves for the individual analytes showed linear relationships over the concentration ranges of 1.0–11.5 mg L−1 at 526 and 608 nm for pefloxacin, and 0.15–1.8 mg L−1 at 526 and 608 nm for norfloxacin. Various multivariate calibration models were applied, at the two analytical wavelengths, for the simultaneous prediction of the two analytes including classical least squares (CLS), principal component regression (PCR), partial least squares (PLS), radial basis function-artificial neural network (RBF-ANN) and principal component-radial basis function-artificial neural network (PC-RBF-ANN). PLS and PC-RBF-ANN calibrations with the data collected at 526 nm, were the preferred methods—%RPET not, vert, similar 5, and LODs for pefloxacin and norfloxacin of 0.36 and 0.06 mg L−1, respectively. Then, the proposed method was applied successfully for the simultaneous determination of pefloxacin and norfloxacin present in pharmaceutical and human plasma samples. The results compared well with those from the alternative analysis by HPLC.

Intelligent prognostics of machinery health utilising suspended condition monitoring data

The ability to forecast machinery failure is vital to reducing maintenance costs, operation downtime and safety hazards. Recent advances in condition monitoring technologies have given rise to a number of prognostic models for forecasting machinery health based on condition data. Although these models have aided the advancement of the discipline, they have made only a limited contribution to developing an effective machinery health prognostic system. The literature review indicates that there is not yet a prognostic model that directly models and fully utilises suspended condition histories (which are very common in practice since organisations rarely allow their assets to run to failure); that effectively integrates population characteristics into prognostics for longer-range prediction in a probabilistic sense; which deduces the non-linear relationship between measured condition data and actual asset health; and which involves minimal assumptions and requirements. This work presents a novel approach to addressing the above-mentioned challenges. The proposed model consists of a feed-forward neural network, the training targets of which are asset survival probabilities estimated using a variation of the Kaplan-Meier estimator and a degradation-based failure probability density estimator. The adapted Kaplan-Meier estimator is able to model the actual survival status of individual failed units and estimate the survival probability of individual suspended units. The degradation-based failure probability density estimator, on the other hand, extracts population characteristics and computes conditional reliability from available condition histories instead of from reliability data. The estimated survival probability and the relevant condition histories are respectively presented as “training target” and “training input” to the neural network. The trained network is capable of estimating the future survival curve of a unit when a series of condition indices are inputted. Although the concept proposed may be applied to the prognosis of various machine components, rolling element bearings were chosen as the research object because rolling element bearing failure is one of the foremost causes of machinery breakdowns. Computer simulated and industry case study data were used to compare the prognostic performance of the proposed model and four control models, namely: two feed-forward neural networks with the same training function and structure as the proposed model, but neglected suspended histories; a time series prediction recurrent neural network; and a traditional Weibull distribution model. The results support the assertion that the proposed model performs better than the other four models and that it produces adaptive prediction outputs with useful representation of survival probabilities. This work presents a compelling concept for non-parametric data-driven prognosis, and for utilising available asset condition information more fully and accurately. It demonstrates that machinery health can indeed be forecasted. The proposed prognostic technique, together with ongoing advances in sensors and data-fusion techniques, and increasingly comprehensive databases of asset condition data, holds the promise for increased asset availability, maintenance cost effectiveness, operational safety and – ultimately – organisation competitiveness.

Condition-based prognosis of machine health

Modern machines are complex and often required to operate long hours to achieve production targets. The ability to detect symptoms of failure, hence, forecasting the remaining useful life of the machine is vital to prevent catastrophic failures. This is essential to reducing maintenance cost, operation downtime and safety hazard. Recent advances in condition monitoring technologies have given rise to a number of prognosis models that attempt to forecast machinery health based on either condition data or reliability data. In practice, failure condition trending data are seldom kept by industries and data that ended with a suspension are sometimes treated as failure data. This paper presents a novel approach of incorporating historical failure data and suspended condition trending data in the prognostic model. The proposed model consists of a FFNN whose training targets are asset survival probabilities estimated using a variation of Kaplan-Meier estimator and degradation-based failure PDF estimator. The output survival probabilities collectively form an estimated survival curve. The viability of the model was tested using a set of industry vibration data.