Building knowledge from plant operating data for process improvement. applications

Size: px
Start display at page:

Download "Building knowledge from plant operating data for process improvement. applications"

Transcription

1 Building knowledge from plant operating data for process improvement applications Ramasamy, M., Zabiri, H., Lemma, T. D., Totok, R. B., and Osman, M. Chemical Engineering Department, Universiti Teknologi PETRONAS, Tronoh, Malaysia. ABSTRACT: Large amounts of data collected and stored in process control computers are rich in information but poor in knowledge. Careful and systematic selection and analysis of data can provide more insight (knowledge) into the equipment/process. This knowledge in the form of mathematical models (empirical or semi-empirical) provide the basis for the process improvement applications such as system identification for control, process monitoring, fault detection, soft sensor development, etc. In this paper, four case studies have been presented to illustrate the potential for building knowledge from plant operating data using multivariate statistical analysis and neural networks. In the first case study, a MIMO parsimonious orthonormal basis filter based prediction model has been developed for a pilot scale distillation column. The second example illustrates the detection of control valve stiction using nonlinear principal component analysis (NLPCA) using data collected from an operating plant. In the third example, data from a refinery crude preheat train is analyzed for monitoring the thermal efficiency of the heat exchangers and a fouling prediction model was developed. The last case study illustrates the development of a soft sensor in a pilot scale distillation column. In conclusion, the potential of historical operating data in providing information to build knowledge which in turn can be used for the process operational excellence has been demonstrated. KEYWORDS: Megavariate data, prediction model, fault detection, process monitoring, soft sensor, neural networks

2 1 INTRODUCTION Globally, process and manufacturing industries are striving to improve product quality and efficiencies through excellence in operation. Significant investments have been made in upgrading instrumentation, data acquisition, computing infrastructures and advanced control systems. It is expected that with more process and product data readily available, useful information and better process knowledge can be gained and used in process operation improvement applications. The modern measurement techniques in process industries enable large amounts of operating data to be collected and stored. With large volumes of data available in the plant historians, the associated data analysis and modeling have become increasingly complex. As a result, much of the available data is either ignored or heavily compressed. A significant amount of the information resident in the data and the potential knowledge derived from this information is not discovered, diminishing the results from the investment made in the information technology infrastructure. The key challenge is how to exploit all the useful information content from a multivariate data. Generally, the process industries data are characterized by missing values, presence of outliers, drifting data, co-linearity in data, multisampling rates and measurement delays. Analysis and interpretation of such complex data is a challenging task and building models (knowledge) require robust mathematical techniques that are capable of dealing with all the above complexities and drawbacks. Moreover, difficulties in developing accurate mechanistic models shifted the attention of the researchers from mechanistic modeling to sophisticated use of historical plant data to develop empirical models. Although several techniques were developed and used, the two major techniques that were widely and

3 successfully used since the mid 1980s are the multivariate statistical analysis and artificial neural networks (ANN). In this article, a brief introduction is given to multivariate statistical analysis (Section 2) and artificial neural networks (Section 3). Subsequently, four examples dealing with the above techniques are provided that illustrate the potential for building knowledge from historical data. input/output measurements for the prediction of quality variables (Martin et al., 1995). It is possible to effectively treat noisy and highly correlated process measurements using PCA and PLS. PCA models a set of data X onto itself. The data typically contain measurements taken on a process which are highly correlated and as a consequence their covariance matrix Σ is nearly singular. PCA explains the variance of this matrix in terms of a number 2 MULTIVARIATE STATISTICAL ANALYSIS The multivariate statistical techniques, such as principal component analysis (PCA) and projection to latent structures (PLS), project multivariate data down onto lower dimensional space which contains the relevant process information in two or three latent variables. The linear technique of PCA seeks to explain the variance in the data matrix, whilst PLS allows models to be developed which relate the process of new latent variables called principal components. The first principal component is that linear combination of original variables which explains the greatest amount of variability (t i = Xp i ). The loadings, p i, define the direction of greatest variability, and the score vector, t i, represents the projection of each object onto p i. The second principal component is defined to be orthogonal to the first and explains the next greatest amount of variability, i.e., t 2 = E 1 p 2 where E 1 = X t 1 p T 1.

4 3 ARTIFICIAL NEURAL NETWORKS (ANN) Over the years, the application of ANN in process industries has been growing in acceptance. ANN is attractive due to its information processing characteristics such as nonlinearity, high parallelism, fault tolerance as well as capability to generalize performance. The third factor is the model size and complexity. A small network may not able to represent the real situation due to its limited capability, while a large network may over fit noise in the training data and fail to provide good generalization ability. Finally, the quality of a process model is also strongly dependent on network training. and handle imprecise information (Haskins and Himmelblau, 1988). Such characteristics have made ANN suitable for solving a variety of problems. This has been proven in various fields such as pattern recognition, system identification, prediction, signal processing, fault detection, soft sensors and others. In general, the development of a good ANN model depends on several factors. The first factor is related to the data being used. The model qualities are strongly influenced by the quality of data used. The second factor is network architecture or model structure. Different network architecture results in different estimation 4 ILLUSTRATIVE EXAMPLES The type of model, the model structure and configuration mainly depend on the objective of the model. It could be to estimate a quality parameter that is slow, expensive, or difficult to measure and infrequent quality variables (soft sensors) or to predict multi-step ahead such as in model predictive control or to diagnose a fault in the process/equipment (instrument failure, control valve stiction) or to monitor the process performance. The examples below illustrate each one of them from case studies being studied by our group.

5 Temperature, Temperature, o C 4.1 Example 1: Prediction Model Development model can be developed from the innovation sequence of the GOBF model. Model predictive control (MPC) applications largely depend on the accuracy T 14 (Top Temperature) Measured Predicted of the models used for prediction. Since MPC involves optimization of a cost function to estimate, present and future, optimal control moves, the prediction model should be simple and parsimonious in parameters and thus making less computationally intensive. A Box-Jenkins type model involving a generalized orthonormal basis filter (GOBF) model as the deterministic part and auto regressive moving average (ARMA) noise model was developed for a pilot scale binary distillation column (Lemma et al. 2009). The major advantages of this type of model are: (i) the GOBF model is parsimonious; (ii) the model parameters can be estimated using least squares; (iii) a priori information on the time delay is not required; and (iv) the noise o C k o C (a) T 1 (Bottom Temperature) k (b) Measured Predicted Figure 1. Prediction of temperatures by the GOBF-ARMA model: (a) top temperature and (b) bottom temperature Figure 1 shows the prediction of top and bottom temperatures by the multi-input multi-output GOBF-ARMA model. The input variables are the reflux and steam flow rates while the output variables are tray 1 and tray 14 temperatures.

6 4.2 Example 2: Fault detection Nonlinear principal component analysis (NLPCA) is a nonlinear generalization of PCA for feature extraction and was introduced by Kramer (1991). This autoassociative neural-network based generalization of PCA allows nonlinear mapping between the original and the reduced dimensional spaces. Applications of NLPCA can be found in many fields. The NLPCA structure is shown in Fig. 2. Both the first and final hidden layers have dimensions greater than the input/output layer. The key feature of the network is the bottleneck inner layer. The use of a single neuron in the bottleneck layer allows compression of the inputs to a onedimensional time series before the outputs are reconstructed in the demapping layer. Following convergence, the network bottleneck provides information which describes significant features or signatures of the original data. Input Layer Mapping Layer Bottleneck Layer Demapping Layer Output Layer m m p Fig. 2. The architecture of the five-layer feedforward auto-associative neural network. The network bottleneck, which represents the optimal one-dimensional curve, called the principal curve, characterizing the inputs, allows the usage of simple coefficient of determination R 2 in quantifying the nonlinear behavior of the loop. If R 2 value is much less than 1, then there is a possibility of presence of nonlinearity or Non-Gaussianity. The presence of nonlinearity or stiction is then detected via an index called the NLPCA curvature index, I NC, value. The proposed method has been successfully applied in the detection of stiction for some industrial control loops Zabiri and Ramasamy (2009). One of the control loops is a Liquified Petroleum Gas

7 y pv op pv and sp (LPG) bottom flow control loop. Data on controller output (op) and controlled variable (pv) were collected from the plant. Figure 3(a) shows the time trends of pv, op and the set-point (sp), where oscillations in the pv and op are significantly obvious. The (a) (b) op u (c) Fig. 3. Analysis of data from an industrial LPG bottom flow control loop: (a) Time trend; (b) pv-op plot; (c) NLPCA s output. presence of stiction nonlinearity was confirmed by the very high I NC value of 78.63, and the corresponding NLPCA output is as shown in Fig. 3(c). This can further be verified by the distinct cycles in the characteristics of pv-op plot in Fig. 3(b) which is typical of stiction. 4.3 Example 3: Process Monitoring - Heat Exchanger Performance Analysis Fouling in Crude Preheat Train (CPT) in oil refineries is a serious problem that consumes additional energy and affects the plant economy. Understanding or predicting the fouling characteristics in CPT is imperative to operate the CPT in an optimal manner, with minimum or no fouling. However, fouling is very complex and determined by the crude/crude blend being processed in CPT, the temperatures and flow rates.

8 Fouling resistance (m 2 C/W)) C/W)) Fouling mechanism is very complex and it is difficult to develop a fundamental model to predict the fouling rate for different crude blends and different operating conditions. Recently, neural networks have been shown to approximate nonlinear functions up to any desired level of accuracy. In this study, a Multi Layer Perceptron (MLP) neural network with Nonlinear Auto Regressive with exogenous input (NARX) structure is used to model a heat exchanger in the CPT. In the heat exchanger chosen for the study, crude oil flows through the tube side and kerosene flows through the shell side. Data were collected from the plant historian for a period of two years consisting of: (i) operational data (cold and hot stream inlet and outlet temperatures, and flow rates); (ii) crude blend information; (iii) crude and product properties; (iv) operation and maintenance reports; and (v) heat exchanger design data. The data were analyzed for outliers using PCA and reconciled. Relevant input variables were selected through PLS. The data set was divided into training and validation sets. A neural network model with one hidden layer was chosen for modeling the heat exchanger. The number of nodes in the input layer was 13, equal to the number of input variables, and the number of neurons in the hidden layer was chosen as 18 by trial and error. Tangent hyperbolic activation function was used in the hidden layer. Figure 4 shows the comparison of prediction of fouling resistance over time with the actual fouling resistance. 10 x Day Actual Predicted Figure 4. Actual and predicted fouling resistance during the validation period

9 4.4 Example 4: Soft Sensor Application Soft-sensor is a model that utilizes the measured values of some secondary variables of a process in order to estimate the value of an immeasurable primary variable of particular importance. Soft was built for predicting the composition in the top product. Figure 5 shows the comparison between the actual top product composition and predictions by the feedforward network with sigmoidal and linear transfer functions and one hidden layer. sensors have been widely reported to supplement online instrument measurements for process monitoring and control. The availability of large volume of data renders data-driven soft-sensor development a viable alternative. In this example, a pilot scale distillation column was operated with acetone-isopropyl alcohol as the feed material. Experiments were performed for variations in reflux flow rate, steam flow rate and feed flow rate. Samples were collected at the top product stream every six minutes and analyzed using a gas chromatography (GC). Other measurements include temperatures, flow rates, pressure, etc. were acquired through the data acquisition system. A neural network model Figure 5. Prediction of top-product composition by neural network models 5 CONCLUSIONS The potential of historical operating data in providing information to build knowledge which in turn can be used for operational excellence through various applications such as system identification, fault detection, process monitoring and soft sensor development has been demonstrated through appropriate case studies.

10 6 ACKNOWLEDGEMENTS The authors gratefully acknowledge the support and facilities from Universiti Teknologi PETRONAS. of knowledge presentation in chemical engineering. Computers and Chemical Engineering 12(9/10), pp Kramer, M.A., Nonlinear principal 7 REFERENCES Champagne, M., and Dudzic, M., Industrial use of multivariate statistical analysis for process monitoring and control, In the Proceedings of the American Control Conference, 2002, Anchorage, pp Choudhury, M.A.A.S., Shah, S.L., and Thornhill, N.F., Diagnosis of poor control-loop performance using higherorder statistics, Automatica, 40, pp Eriksson, L., Johansson, E., Kettaneh-Wold, N., and Wold, S., Multi- and megavariate data analysis, Umetircs Academy, Sweden. Hoskins, J. C., and Himmelblau, D. M., Artificial neural network models component analysis using autoassociative neural networks, AIChE Journal, 37, 2, pp Lemma, T.D., Ramasamy, M., Patwardhan, S.C., and Shuhaimi, M., Development of Box-Jenkins type time series models by combining conventional and orthonormal basis filter approaches, Journal of Process Control, Under Revision. Martin, E.B., Morris, A.J., and Zhang, J., Artificial neural networks and multivariate statistics, Ed. Bulsari, A.B., Neural Networks for Chemical Engineers, Elsevier, pp Zabiri, H., and Ramasamy, M., NLPCA as a diagnostic tool for control valve stiction, Journal of Process Control, In Press.

A Black-Box Approach in Modeling Valve Stiction

A Black-Box Approach in Modeling Valve Stiction Vol:4, No:8, A Black-Box Approach in Modeling Valve Stiction H. Zabiri, N. Mazuki International Science Index, Mechanical and Mechatronics Engineering Vol:4, No:8, waset.org/publication/46 Abstract Several

More information

Artificial Neural Networks Francesco DI MAIO, Ph.D., Politecnico di Milano Department of Energy - Nuclear Division IEEE - Italian Reliability Chapter

Artificial Neural Networks Francesco DI MAIO, Ph.D., Politecnico di Milano Department of Energy - Nuclear Division IEEE - Italian Reliability Chapter Artificial Neural Networks Francesco DI MAIO, Ph.D., Politecnico di Milano Department of Energy - Nuclear Division IEEE - Italian Reliability Chapter (Chair) STF - China Fellow francesco.dimaio@polimi.it

More information

CBE495 LECTURE IV MODEL PREDICTIVE CONTROL

CBE495 LECTURE IV MODEL PREDICTIVE CONTROL What is Model Predictive Control (MPC)? CBE495 LECTURE IV MODEL PREDICTIVE CONTROL Professor Dae Ryook Yang Fall 2013 Dept. of Chemical and Biological Engineering Korea University * Some parts are from

More information

Advanced Methods for Fault Detection

Advanced Methods for Fault Detection Advanced Methods for Fault Detection Piero Baraldi Agip KCO Introduction Piping and long to eploration distance pipelines activities Piero Baraldi Maintenance Intervention Approaches & PHM Maintenance

More information

System Identification for Process Control: Recent Experiences and a Personal Outlook

System Identification for Process Control: Recent Experiences and a Personal Outlook System Identification for Process Control: Recent Experiences and a Personal Outlook Yucai Zhu Eindhoven University of Technology Eindhoven, The Netherlands and Tai-Ji Control Best, The Netherlands Contents

More information

Synergy between Data Reconciliation and Principal Component Analysis.

Synergy between Data Reconciliation and Principal Component Analysis. Plant Monitoring and Fault Detection Synergy between Data Reconciliation and Principal Component Analysis. Th. Amand a, G. Heyen a, B. Kalitventzeff b Thierry.Amand@ulg.ac.be, G.Heyen@ulg.ac.be, B.Kalitventzeff@ulg.ac.be

More information

CONTROLLER PERFORMANCE ASSESSMENT IN SET POINT TRACKING AND REGULATORY CONTROL

CONTROLLER PERFORMANCE ASSESSMENT IN SET POINT TRACKING AND REGULATORY CONTROL ADCHEM 2, Pisa Italy June 14-16 th 2 CONTROLLER PERFORMANCE ASSESSMENT IN SET POINT TRACKING AND REGULATORY CONTROL N.F. Thornhill *, S.L. Shah + and B. Huang + * Department of Electronic and Electrical

More information

Using Principal Component Analysis Modeling to Monitor Temperature Sensors in a Nuclear Research Reactor

Using Principal Component Analysis Modeling to Monitor Temperature Sensors in a Nuclear Research Reactor Using Principal Component Analysis Modeling to Monitor Temperature Sensors in a Nuclear Research Reactor Rosani M. L. Penha Centro de Energia Nuclear Instituto de Pesquisas Energéticas e Nucleares - Ipen

More information

ARTIFICIAL NEURAL NETWORKS گروه مطالعاتي 17 بهار 92

ARTIFICIAL NEURAL NETWORKS گروه مطالعاتي 17 بهار 92 ARTIFICIAL NEURAL NETWORKS گروه مطالعاتي 17 بهار 92 BIOLOGICAL INSPIRATIONS Some numbers The human brain contains about 10 billion nerve cells (neurons) Each neuron is connected to the others through 10000

More information

Deep Learning Architecture for Univariate Time Series Forecasting

Deep Learning Architecture for Univariate Time Series Forecasting CS229,Technical Report, 2014 Deep Learning Architecture for Univariate Time Series Forecasting Dmitry Vengertsev 1 Abstract This paper studies the problem of applying machine learning with deep architecture

More information

Analyzing Control Problems and Improving Control Loop Performance

Analyzing Control Problems and Improving Control Loop Performance OptiControls Inc. Houston, TX Ph: 713-459-6291 www.opticontrols.com info@opticontrols.com Analyzing Control s and Improving Control Loop Performance -by Jacques F. Smuts Page: 1 Presenter Principal Consultant

More information

Lecture 4: Feed Forward Neural Networks

Lecture 4: Feed Forward Neural Networks Lecture 4: Feed Forward Neural Networks Dr. Roman V Belavkin Middlesex University BIS4435 Biological neurons and the brain A Model of A Single Neuron Neurons as data-driven models Neural Networks Training

More information

MULTIVARIATE STATISTICAL METHODS FOR INDUSTRIAL PROCESS PROGNOSTICS

MULTIVARIATE STATISTICAL METHODS FOR INDUSTRIAL PROCESS PROGNOSTICS MULTIVARIATE STATISTICAL METHODS FOR INDUSTRIAL PROCESS PROGNOSTICS Bratina Božidar and Boris Tovornik University of Maribor, Faculty of Electrical Engineering and Computer Science Smetanova 17, 000 Maribor,

More information

Chapter 4 Neural Networks in System Identification

Chapter 4 Neural Networks in System Identification Chapter 4 Neural Networks in System Identification Gábor HORVÁTH Department of Measurement and Information Systems Budapest University of Technology and Economics Magyar tudósok körútja 2, 52 Budapest,

More information

An Introduction to Nonlinear Principal Component Analysis

An Introduction to Nonlinear Principal Component Analysis An Introduction tononlinearprincipal Component Analysis p. 1/33 An Introduction to Nonlinear Principal Component Analysis Adam Monahan monahana@uvic.ca School of Earth and Ocean Sciences University of

More information

Valve Stiction - Definition, Modeling, Detection, Quantification and Compensation

Valve Stiction - Definition, Modeling, Detection, Quantification and Compensation Valve Stiction - Definition, Modeling, Detection, Quantification and Compensation Dr. M. A. A. Shoukat Choudhury Department of Chemical Engineering Bangladesh University of Engineering & Technology ()

More information

Virtual Sensor Technology for Process Optimization. Edward Wilson Neural Applications Corporation

Virtual Sensor Technology for Process Optimization. Edward Wilson Neural Applications Corporation Virtual Sensor Technology for Process Optimization Edward Wilson Neural Applications Corporation ewilson@neural.com Virtual Sensor (VS) Also known as soft sensor, smart sensor, estimator, etc. Used in

More information

In Situ Adaptive Tabulation for Real-Time Control

In Situ Adaptive Tabulation for Real-Time Control In Situ Adaptive Tabulation for Real-Time Control J. D. Hedengren T. F. Edgar The University of Teas at Austin 2004 American Control Conference Boston, MA Outline Model reduction and computational reduction

More information

Introduction to Neural Networks

Introduction to Neural Networks Introduction to Neural Networks What are (Artificial) Neural Networks? Models of the brain and nervous system Highly parallel Process information much more like the brain than a serial computer Learning

More information

Implementation issues for real-time optimization of a crude unit heat exchanger network

Implementation issues for real-time optimization of a crude unit heat exchanger network 1 Implementation issues for real-time optimization of a crude unit heat exchanger network Tore Lid a, Sigurd Skogestad b a Statoil Mongstad, N-5954 Mongstad b Department of Chemical Engineering, NTNU,

More information

Plant-wide Root Cause Identification of Transient Disturbances with Application to a Board Machine

Plant-wide Root Cause Identification of Transient Disturbances with Application to a Board Machine Moncef Chioua, Margret Bauer, Su-Liang Chen, Jan C. Schlake, Guido Sand, Werner Schmidt and Nina F. Thornhill Plant-wide Root Cause Identification of Transient Disturbances with Application to a Board

More information

MODELING COMBINED VLE OF FOUR QUATERNARY MIXTURES USING ARTIFICIAL NEURAL NETWORK

MODELING COMBINED VLE OF FOUR QUATERNARY MIXTURES USING ARTIFICIAL NEURAL NETWORK MODELING COMBINED VLE OF FOUR QUATERNARY MIXTURES USING ARTIFICIAL NEURAL NETWORK SHEKHAR PANDHARIPANDE* Associate Professor, Department of Chemical Engineering, LIT, RTMNU, Nagpur, India, slpandharipande@gmail.com

More information

STA 414/2104: Lecture 8

STA 414/2104: Lecture 8 STA 414/2104: Lecture 8 6-7 March 2017: Continuous Latent Variable Models, Neural networks With thanks to Russ Salakhutdinov, Jimmy Ba and others Outline Continuous latent variable models Background PCA

More information

Prediction of Hourly Solar Radiation in Amman-Jordan by Using Artificial Neural Networks

Prediction of Hourly Solar Radiation in Amman-Jordan by Using Artificial Neural Networks Int. J. of Thermal & Environmental Engineering Volume 14, No. 2 (2017) 103-108 Prediction of Hourly Solar Radiation in Amman-Jordan by Using Artificial Neural Networks M. A. Hamdan a*, E. Abdelhafez b

More information

Principal Component Analysis vs. Independent Component Analysis for Damage Detection

Principal Component Analysis vs. Independent Component Analysis for Damage Detection 6th European Workshop on Structural Health Monitoring - Fr..D.4 Principal Component Analysis vs. Independent Component Analysis for Damage Detection D. A. TIBADUIZA, L. E. MUJICA, M. ANAYA, J. RODELLAR

More information

Artificial Neural Networks Examination, June 2004

Artificial Neural Networks Examination, June 2004 Artificial Neural Networks Examination, June 2004 Instructions There are SIXTY questions (worth up to 60 marks). The exam mark (maximum 60) will be added to the mark obtained in the laborations (maximum

More information

Using Neural Networks for Identification and Control of Systems

Using Neural Networks for Identification and Control of Systems Using Neural Networks for Identification and Control of Systems Jhonatam Cordeiro Department of Industrial and Systems Engineering North Carolina A&T State University, Greensboro, NC 27411 jcrodrig@aggies.ncat.edu

More information

Dynamic-Inner Partial Least Squares for Dynamic Data Modeling

Dynamic-Inner Partial Least Squares for Dynamic Data Modeling Preprints of the 9th International Symposium on Advanced Control of Chemical Processes The International Federation of Automatic Control MoM.5 Dynamic-Inner Partial Least Squares for Dynamic Data Modeling

More information

Non-linear Measure Based Process Monitoring and Fault Diagnosis

Non-linear Measure Based Process Monitoring and Fault Diagnosis Non-linear Measure Based Process Monitoring and Fault Diagnosis 12 th Annual AIChE Meeting, Reno, NV [275] Data Driven Approaches to Process Control 4:40 PM, Nov. 6, 2001 Sandeep Rajput Duane D. Bruns

More information

UPSET AND SENSOR FAILURE DETECTION IN MULTIVARIATE PROCESSES

UPSET AND SENSOR FAILURE DETECTION IN MULTIVARIATE PROCESSES UPSET AND SENSOR FAILURE DETECTION IN MULTIVARIATE PROCESSES Barry M. Wise, N. Lawrence Ricker and David J. Veltkamp Center for Process Analytical Chemistry and Department of Chemical Engineering University

More information

Moshood Olanrewaju Advanced Filtering for Continuum and Noncontinuum States of Distillation Processes

Moshood Olanrewaju Advanced Filtering for Continuum and Noncontinuum States of Distillation Processes PhD projects in progress Fei Qi Bayesian Methods for Control Loop Diagnosis The main objective of this study is to establish a diagnosis system for control loop diagnosis, synthesizing observations of

More information

Introduction to Machine Learning

Introduction to Machine Learning 10-701 Introduction to Machine Learning PCA Slides based on 18-661 Fall 2018 PCA Raw data can be Complex, High-dimensional To understand a phenomenon we measure various related quantities If we knew what

More information

PCA Based Data Reconciliation in Soft Sensor Development Application for Melt Flow Index Estimation

PCA Based Data Reconciliation in Soft Sensor Development Application for Melt Flow Index Estimation A publication of CHEMICAL ENGINEERING TRANSACTIONS VOL. 43, 215 Chief Editors: Sauro Pierucci, Jiří J. Klemeš Copyright 215, AIDIC Servizi S.r.l., ISBN 978-88-9568-34-1; ISSN 2283-9216 The Italian Association

More information

A predictive control system for concrete plants. Application of RBF neural networks for reduce dosing inaccuracies.

A predictive control system for concrete plants. Application of RBF neural networks for reduce dosing inaccuracies. A predictive control system for concrete plants. Application of RBF neural networks for reduce dosing inaccuracies. Antonio Guerrero González, Juan Carlos Molina Molina, Pedro José Ayala Bernal and Francisco

More information

DEEP LEARNING AND NEURAL NETWORKS: BACKGROUND AND HISTORY

DEEP LEARNING AND NEURAL NETWORKS: BACKGROUND AND HISTORY DEEP LEARNING AND NEURAL NETWORKS: BACKGROUND AND HISTORY 1 On-line Resources http://neuralnetworksanddeeplearning.com/index.html Online book by Michael Nielsen http://matlabtricks.com/post-5/3x3-convolution-kernelswith-online-demo

More information

STA 414/2104: Lecture 8

STA 414/2104: Lecture 8 STA 414/2104: Lecture 8 6-7 March 2017: Continuous Latent Variable Models, Neural networks Delivered by Mark Ebden With thanks to Russ Salakhutdinov, Jimmy Ba and others Outline Continuous latent variable

More information

Artificial Neural Networks Examination, March 2004

Artificial Neural Networks Examination, March 2004 Artificial Neural Networks Examination, March 2004 Instructions There are SIXTY questions (worth up to 60 marks). The exam mark (maximum 60) will be added to the mark obtained in the laborations (maximum

More information

Artificial Neural Networks Examination, June 2005

Artificial Neural Networks Examination, June 2005 Artificial Neural Networks Examination, June 2005 Instructions There are SIXTY questions. (The pass mark is 30 out of 60). For each question, please select a maximum of ONE of the given answers (either

More information

Artificial Neural Network Simulation of Battery Performance

Artificial Neural Network Simulation of Battery Performance Artificial work Simulation of Battery Performance C.C. O Gorman, D. Ingersoll, R.G. Jungst and T.L. Paez Sandia National Laboratories PO Box 58 Albuquerque, NM 8785 Abstract Although they appear deceptively

More information

Unit III. A Survey of Neural Network Model

Unit III. A Survey of Neural Network Model Unit III A Survey of Neural Network Model 1 Single Layer Perceptron Perceptron the first adaptive network architecture was invented by Frank Rosenblatt in 1957. It can be used for the classification of

More information

Bearing fault diagnosis based on EMD-KPCA and ELM

Bearing fault diagnosis based on EMD-KPCA and ELM Bearing fault diagnosis based on EMD-KPCA and ELM Zihan Chen, Hang Yuan 2 School of Reliability and Systems Engineering, Beihang University, Beijing 9, China Science and Technology on Reliability & Environmental

More information

Nonlinear Robust PLS Modeling of Wastewater Effluent Quality Indices

Nonlinear Robust PLS Modeling of Wastewater Effluent Quality Indices JOURNAL OF SOFTWARE, VOL. 6, NO. 6, JUNE 0 067 Nonlinear Robust PLS Modeling of Wastewater Effluent Quality Indices Liie Zhao,, Decheng Yuan Shenyang University of chemical technology / Provincial key

More information

DETECTION OF DISTRIBUTED OSCILLATIONS AND ROOT-CAUSE DIAGNOSIS

DETECTION OF DISTRIBUTED OSCILLATIONS AND ROOT-CAUSE DIAGNOSIS roceedings of CHEMFAS 4, June 7-8, 2001, Jejudo(Chejudo) Island, Korea, pp 167-172 DETECTION OF DISTRIBUTED OSCILLATIONS AND ROOT-CAUSE DIAGNOSIS N.F. Thornhill *, S.L. Shah + and B. Huang + * Centre for

More information

Learning and Memory in Neural Networks

Learning and Memory in Neural Networks Learning and Memory in Neural Networks Guy Billings, Neuroinformatics Doctoral Training Centre, The School of Informatics, The University of Edinburgh, UK. Neural networks consist of computational units

More information

EEE 241: Linear Systems

EEE 241: Linear Systems EEE 4: Linear Systems Summary # 3: Introduction to artificial neural networks DISTRIBUTED REPRESENTATION An ANN consists of simple processing units communicating with each other. The basic elements of

More information

Progress in MPC Identification: A Case Study on Totally Closed-Loop Plant Test

Progress in MPC Identification: A Case Study on Totally Closed-Loop Plant Test Progress in MPC Identification: A Case Study on Totally Closed-Loop Plant Test Yucai Zhu Grensheuvel 10, 5685 AG Best, The Netherlands Phone +31.499.465692, fax +31.499.465693, y.zhu@taijicontrol.com Abstract:

More information

Estimation of the Pre-Consolidation Pressure in Soils Using ANN method

Estimation of the Pre-Consolidation Pressure in Soils Using ANN method Current World Environment Vol. 11(Special Issue 1), 83-88 (2016) Estimation of the Pre-Consolidation Pressure in Soils Using ANN method M. R. Motahari Department of Civil Engineering, Faculty of Engineering,

More information

Iterative face image feature extraction with Generalized Hebbian Algorithm and a Sanger-like BCM rule

Iterative face image feature extraction with Generalized Hebbian Algorithm and a Sanger-like BCM rule Iterative face image feature extraction with Generalized Hebbian Algorithm and a Sanger-like BCM rule Clayton Aldern (Clayton_Aldern@brown.edu) Tyler Benster (Tyler_Benster@brown.edu) Carl Olsson (Carl_Olsson@brown.edu)

More information

ECE 521. Lecture 11 (not on midterm material) 13 February K-means clustering, Dimensionality reduction

ECE 521. Lecture 11 (not on midterm material) 13 February K-means clustering, Dimensionality reduction ECE 521 Lecture 11 (not on midterm material) 13 February 2017 K-means clustering, Dimensionality reduction With thanks to Ruslan Salakhutdinov for an earlier version of the slides Overview K-means clustering

More information

Dynamic Data Modeling of SCR De-NOx System Based on NARX Neural Network Wen-jie ZHAO * and Kai ZHANG

Dynamic Data Modeling of SCR De-NOx System Based on NARX Neural Network Wen-jie ZHAO * and Kai ZHANG 2018 International Conference on Modeling, Simulation and Analysis (ICMSA 2018) ISBN: 978-1-60595-544-5 Dynamic Data Modeling of SCR De-NOx System Based on NARX Neural Network Wen-jie ZHAO * and Kai ZHANG

More information

ANALYSIS OF NONLINEAR PARTIAL LEAST SQUARES ALGORITHMS

ANALYSIS OF NONLINEAR PARTIAL LEAST SQUARES ALGORITHMS ANALYSIS OF NONLINEAR PARIAL LEAS SQUARES ALGORIHMS S. Kumar U. Kruger,1 E. B. Martin, and A. J. Morris Centre of Process Analytics and Process echnology, University of Newcastle, NE1 7RU, U.K. Intelligent

More information

DYNAMIC SIMULATOR-BASED APC DESIGN FOR A NAPHTHA REDISTILLATION COLUMN

DYNAMIC SIMULATOR-BASED APC DESIGN FOR A NAPHTHA REDISTILLATION COLUMN HUNGARIAN JOURNAL OF INDUSTRY AND CHEMISTRY Vol. 45(1) pp. 17 22 (2017) hjic.mk.uni-pannon.hu DOI: 10.1515/hjic-2017-0004 DYNAMIC SIMULATOR-BASED APC DESIGN FOR A NAPHTHA REDISTILLATION COLUMN LÁSZLÓ SZABÓ,

More information

Neural-wavelet Methodology for Load Forecasting

Neural-wavelet Methodology for Load Forecasting Journal of Intelligent and Robotic Systems 31: 149 157, 2001. 2001 Kluwer Academic Publishers. Printed in the Netherlands. 149 Neural-wavelet Methodology for Load Forecasting RONG GAO and LEFTERI H. TSOUKALAS

More information

Neurocomputing 131 (2014) Contents lists available at ScienceDirect. Neurocomputing. journal homepage:

Neurocomputing 131 (2014) Contents lists available at ScienceDirect. Neurocomputing. journal homepage: Neurocomputing 131 (214) 59 76 Contents lists available at ScienceDirect Neurocomputing journal homepage: www.elsevier.com/locate/neucom Composition Prediction of a Debutanizer Column using Equation Based

More information

Unsupervised Learning Methods

Unsupervised Learning Methods Structural Health Monitoring Using Statistical Pattern Recognition Unsupervised Learning Methods Keith Worden and Graeme Manson Presented by Keith Worden The Structural Health Monitoring Process 1. Operational

More information

Dimensionality Reduction

Dimensionality Reduction Lecture 5 1 Outline 1. Overview a) What is? b) Why? 2. Principal Component Analysis (PCA) a) Objectives b) Explaining variability c) SVD 3. Related approaches a) ICA b) Autoencoders 2 Example 1: Sportsball

More information

Identification of a Chemical Process for Fault Detection Application

Identification of a Chemical Process for Fault Detection Application Identification of a Chemical Process for Fault Detection Application Silvio Simani Abstract The paper presents the application results concerning the fault detection of a dynamic process using linear system

More information

Nonlinear Stochastic Modeling and State Estimation of Weakly Observable Systems: Application to Industrial Polymerization Processes

Nonlinear Stochastic Modeling and State Estimation of Weakly Observable Systems: Application to Industrial Polymerization Processes Nonlinear Stochastic Modeling and State Estimation of Weakly Observable Systems: Application to Industrial Polymerization Processes Fernando V. Lima, James B. Rawlings and Tyler A. Soderstrom Department

More information

Neural-based Monitoring of a Debutanizer. Distillation Column

Neural-based Monitoring of a Debutanizer. Distillation Column Neural-based Monitoring of a Debutanizer Distillation Column L. Fortuna*, S. Licitra, M. Sinatra, M. G. Xibiliaº ERG Petroli ISAB Refinery, 96100 Siracusa, Italy e-mail: slicitra@ergpetroli.it *University

More information

Forecasting River Flow in the USA: A Comparison between Auto-Regression and Neural Network Non-Parametric Models

Forecasting River Flow in the USA: A Comparison between Auto-Regression and Neural Network Non-Parametric Models Journal of Computer Science 2 (10): 775-780, 2006 ISSN 1549-3644 2006 Science Publications Forecasting River Flow in the USA: A Comparison between Auto-Regression and Neural Network Non-Parametric Models

More information

Chap.11 Nonlinear principal component analysis [Book, Chap. 10]

Chap.11 Nonlinear principal component analysis [Book, Chap. 10] Chap.11 Nonlinear principal component analysis [Book, Chap. 1] We have seen machine learning methods nonlinearly generalizing the linear regression method. Now we will examine ways to nonlinearly generalize

More information

Reprinted from February Hydrocarbon

Reprinted from February Hydrocarbon February2012 When speed matters Loek van Eijck, Yokogawa, The Netherlands, questions whether rapid analysis of gases and liquids can be better achieved through use of a gas chromatograph or near infrared

More information

BATCH PROCESS MONITORING THROUGH THE INTEGRATION OF SPECTRAL AND PROCESS DATA. Julian Morris, Elaine Martin and David Stewart

BATCH PROCESS MONITORING THROUGH THE INTEGRATION OF SPECTRAL AND PROCESS DATA. Julian Morris, Elaine Martin and David Stewart BATCH PROCESS MONITORING THROUGH THE INTEGRATION OF SPECTRAL AND PROCESS DATA Julian Morris, Elaine Martin and David Stewart Centre for Process Analytics and Control Technology School of Chemical Engineering

More information

Process modeling and optimization of mono ethylene glycol quality in commercial plant integrating artificial neural network and differential evolution

Process modeling and optimization of mono ethylene glycol quality in commercial plant integrating artificial neural network and differential evolution From the SelectedWorks of adeem Khalfe Winter December 7, 2008 Process modeling and optimization of mono ethylene glycol quality in commercial plant integrating artificial neural network and differential

More information

2 D wavelet analysis , 487

2 D wavelet analysis , 487 Index 2 2 D wavelet analysis... 263, 487 A Absolute distance to the model... 452 Aligned Vectors... 446 All data are needed... 19, 32 Alternating conditional expectations (ACE)... 375 Alternative to block

More information

Overview of Control System Design

Overview of Control System Design Overview of Control System Design General Requirements 1. Safety. It is imperative that industrial plants operate safely so as to promote the well-being of people and equipment within the plant and in

More information

Dimensionality Reduction and Principle Components Analysis

Dimensionality Reduction and Principle Components Analysis Dimensionality Reduction and Principle Components Analysis 1 Outline What is dimensionality reduction? Principle Components Analysis (PCA) Example (Bishop, ch 12) PCA vs linear regression PCA as a mixture

More information

Comparison of linear and nonlinear system identification approaches to misfire detection for a V8 SI engine

Comparison of linear and nonlinear system identification approaches to misfire detection for a V8 SI engine AVEC 6 Comparison of linear and nonlinear system identification approaches to misfire detection for a V8 SI engine David Antory *, Yingping Huang, Paul J. King, R. Peter Jones 3, Craig Groom, Ross McMurran,

More information

EE04 804(B) Soft Computing Ver. 1.2 Class 2. Neural Networks - I Feb 23, Sasidharan Sreedharan

EE04 804(B) Soft Computing Ver. 1.2 Class 2. Neural Networks - I Feb 23, Sasidharan Sreedharan EE04 804(B) Soft Computing Ver. 1.2 Class 2. Neural Networks - I Feb 23, 2012 Sasidharan Sreedharan www.sasidharan.webs.com 3/1/2012 1 Syllabus Artificial Intelligence Systems- Neural Networks, fuzzy logic,

More information

Stochastic optimization - how to improve computational efficiency?

Stochastic optimization - how to improve computational efficiency? Stochastic optimization - how to improve computational efficiency? Christian Bucher Center of Mechanics and Structural Dynamics Vienna University of Technology & DYNARDO GmbH, Vienna Presentation at Czech

More information

ARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD

ARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD ARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD WHAT IS A NEURAL NETWORK? The simplest definition of a neural network, more properly referred to as an 'artificial' neural network (ANN), is provided

More information

ABSTRACT INTRODUCTION

ABSTRACT INTRODUCTION ABSTRACT Presented in this paper is an approach to fault diagnosis based on a unifying review of linear Gaussian models. The unifying review draws together different algorithms such as PCA, factor analysis,

More information

CONTROL OF MULTIVARIABLE PROCESSES

CONTROL OF MULTIVARIABLE PROCESSES Process plants ( or complex experiments) have many variables that must be controlled. The engineer must. Provide the needed sensors 2. Provide adequate manipulated variables 3. Decide how the CVs and MVs

More information

Cheng Soon Ong & Christian Walder. Canberra February June 2018

Cheng Soon Ong & Christian Walder. Canberra February June 2018 Cheng Soon Ong & Christian Walder Research Group and College of Engineering and Computer Science Canberra February June 2018 Outlines Overview Introduction Linear Algebra Probability Linear Regression

More information

Deep Feedforward Networks. Han Shao, Hou Pong Chan, and Hongyi Zhang

Deep Feedforward Networks. Han Shao, Hou Pong Chan, and Hongyi Zhang Deep Feedforward Networks Han Shao, Hou Pong Chan, and Hongyi Zhang Deep Feedforward Networks Goal: approximate some function f e.g., a classifier, maps input to a class y = f (x) x y Defines a mapping

More information

Comparison of statistical process monitoring methods: application to the Eastman challenge problem

Comparison of statistical process monitoring methods: application to the Eastman challenge problem Computers and Chemical Engineering 24 (2000) 175 181 www.elsevier.com/locate/compchemeng Comparison of statistical process monitoring methods: application to the Eastman challenge problem Manabu Kano a,

More information

Address for Correspondence

Address for Correspondence Research Article APPLICATION OF ARTIFICIAL NEURAL NETWORK FOR INTERFERENCE STUDIES OF LOW-RISE BUILDINGS 1 Narayan K*, 2 Gairola A Address for Correspondence 1 Associate Professor, Department of Civil

More information

Supply chain monitoring: a statistical approach

Supply chain monitoring: a statistical approach European Symposium on Computer Arded Aided Process Engineering 15 L. Puigjaner and A. Espuña (Editors) 2005 Elsevier Science B.V. All rights reserved. Supply chain monitoring: a statistical approach Fernando

More information

Speaker Representation and Verification Part II. by Vasileios Vasilakakis

Speaker Representation and Verification Part II. by Vasileios Vasilakakis Speaker Representation and Verification Part II by Vasileios Vasilakakis Outline -Approaches of Neural Networks in Speaker/Speech Recognition -Feed-Forward Neural Networks -Training with Back-propagation

More information

Introduction to. Process Control. Ahmet Palazoglu. Second Edition. Jose A. Romagnoli. CRC Press. Taylor & Francis Group. Taylor & Francis Group,

Introduction to. Process Control. Ahmet Palazoglu. Second Edition. Jose A. Romagnoli. CRC Press. Taylor & Francis Group. Taylor & Francis Group, Introduction to Process Control Second Edition Jose A. Romagnoli Ahmet Palazoglu CRC Press Taylor & Francis Group Boca Raton London NewYork CRC Press is an imprint of the Taylor & Francis Group, an informa

More information

Nonlinear singular spectrum analysis by neural networks. William W. Hsieh and Aiming Wu. Oceanography/EOS, University of British Columbia,

Nonlinear singular spectrum analysis by neural networks. William W. Hsieh and Aiming Wu. Oceanography/EOS, University of British Columbia, Nonlinear singular spectrum analysis by neural networks William W. Hsieh and Aiming Wu Oceanography/EOS, University of British Columbia, Vancouver, B.C. V6T 1Z4, Canada tel: (64) 822-2821, fax: (64) 822-691

More information

Functional Preprocessing for Multilayer Perceptrons

Functional Preprocessing for Multilayer Perceptrons Functional Preprocessing for Multilayer Perceptrons Fabrice Rossi and Brieuc Conan-Guez Projet AxIS, INRIA, Domaine de Voluceau, Rocquencourt, B.P. 105 78153 Le Chesnay Cedex, France CEREMADE, UMR CNRS

More information

SOFT SENSOR AS COMPOSITION ESTIMATOR IN MULTICOMPONENT DISTILLATION COLUMN

SOFT SENSOR AS COMPOSITION ESTIMATOR IN MULTICOMPONENT DISTILLATION COLUMN SOFT SENSOR AS COMPOSITION ESTIMATOR IN MULTICOMPONENT DISTILLATION COLUMN Claudio Garcia, Diogo R. P. Zanata Department of Telecommunications and Control, University of Sao Paulo, Brazil Av. Luciano Gualberto,

More information

MODELING OF A HOT AIR DRYING PROCESS BY USING ARTIFICIAL NEURAL NETWORK METHOD

MODELING OF A HOT AIR DRYING PROCESS BY USING ARTIFICIAL NEURAL NETWORK METHOD MODELING OF A HOT AIR DRYING PROCESS BY USING ARTIFICIAL NEURAL NETWORK METHOD Ahmet DURAK +, Ugur AKYOL ++ + NAMIK KEMAL UNIVERSITY, Hayrabolu, Tekirdag, Turkey. + NAMIK KEMAL UNIVERSITY, Çorlu, Tekirdag,

More information

CHAPTER 3 SHELL AND TUBE HEAT EXCHANGER

CHAPTER 3 SHELL AND TUBE HEAT EXCHANGER 20 CHAPTER 3 SHELL AND TUBE HEAT EXCHANGER 3.1 INTRODUCTION A Shell and Tube Heat Exchanger is usually used for higher pressure applications, which consists of a series of tubes, through which one of the

More information

Independent Component Analysis for Redundant Sensor Validation

Independent Component Analysis for Redundant Sensor Validation Independent Component Analysis for Redundant Sensor Validation Jun Ding, J. Wesley Hines, Brandon Rasmussen The University of Tennessee Nuclear Engineering Department Knoxville, TN 37996-2300 E-mail: hines2@utk.edu

More information

Wavelet Neural Networks for Nonlinear Time Series Analysis

Wavelet Neural Networks for Nonlinear Time Series Analysis Applied Mathematical Sciences, Vol. 4, 2010, no. 50, 2485-2495 Wavelet Neural Networks for Nonlinear Time Series Analysis K. K. Minu, M. C. Lineesh and C. Jessy John Department of Mathematics National

More information

Modeling of Liquid-Liquid Extraction in Spray Column Using Artificial Neural Network

Modeling of Liquid-Liquid Extraction in Spray Column Using Artificial Neural Network International Journal of Scientific and Research Publications, Volume 2, Issue 6, June 2012 1 Modeling of Liquid-Liquid Extraction in Spray Column Using Artificial Neural Network S.L. Pandharipande, Aashish

More information

Neural Networks and Ensemble Methods for Classification

Neural Networks and Ensemble Methods for Classification Neural Networks and Ensemble Methods for Classification NEURAL NETWORKS 2 Neural Networks A neural network is a set of connected input/output units (neurons) where each connection has a weight associated

More information

A Model-Based Fault Detection and Diagnostic Methodology for Secondary HVAC Systems

A Model-Based Fault Detection and Diagnostic Methodology for Secondary HVAC Systems A Model-Based Fault Detection and Diagnostic Methodology for Secondary HVAC Systems A Thesis Submitted to the Faculty of Drexel University by Shun Li in partial fulfillment of the requirements for the

More information

Impeller Fault Detection for a Centrifugal Pump Using Principal Component Analysis of Time Domain Vibration Features

Impeller Fault Detection for a Centrifugal Pump Using Principal Component Analysis of Time Domain Vibration Features Impeller Fault Detection for a Centrifugal Pump Using Principal Component Analysis of Time Domain Vibration Features Berli Kamiel 1,2, Gareth Forbes 2, Rodney Entwistle 2, Ilyas Mazhar 2 and Ian Howard

More information

Neural Networks biological neuron artificial neuron 1

Neural Networks biological neuron artificial neuron 1 Neural Networks biological neuron artificial neuron 1 A two-layer neural network Output layer (activation represents classification) Weighted connections Hidden layer ( internal representation ) Input

More information

A summary of Deep Learning without Poor Local Minima

A summary of Deep Learning without Poor Local Minima A summary of Deep Learning without Poor Local Minima by Kenji Kawaguchi MIT oral presentation at NIPS 2016 Learning Supervised (or Predictive) learning Learn a mapping from inputs x to outputs y, given

More information

An Intelligent Nonlinear System Identification Method with an Application to Condition Monitoring

An Intelligent Nonlinear System Identification Method with an Application to Condition Monitoring Rochester Institute of Technology RIT Scholar Works Theses Thesis/Dissertation Collections 4-215 An Intelligent Nonlinear System Identification Method with an Application to Condition Monitoring Clara

More information

Direct Method for Training Feed-forward Neural Networks using Batch Extended Kalman Filter for Multi- Step-Ahead Predictions

Direct Method for Training Feed-forward Neural Networks using Batch Extended Kalman Filter for Multi- Step-Ahead Predictions Direct Method for Training Feed-forward Neural Networks using Batch Extended Kalman Filter for Multi- Step-Ahead Predictions Artem Chernodub, Institute of Mathematical Machines and Systems NASU, Neurotechnologies

More information

Enhanced Single-Loop Control Strategies (Advanced Control) Cascade Control Time-Delay Compensation Inferential Control Selective and Override Control

Enhanced Single-Loop Control Strategies (Advanced Control) Cascade Control Time-Delay Compensation Inferential Control Selective and Override Control Enhanced Single-Loop Control Strategies (Advanced Control) Cascade Control Time-Delay Compensation Inferential Control Selective and Override Control 1 Cascade Control A disadvantage of conventional feedback

More information

Keywords- Source coding, Huffman encoding, Artificial neural network, Multilayer perceptron, Backpropagation algorithm

Keywords- Source coding, Huffman encoding, Artificial neural network, Multilayer perceptron, Backpropagation algorithm Volume 4, Issue 5, May 2014 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Huffman Encoding

More information

CS281 Section 4: Factor Analysis and PCA

CS281 Section 4: Factor Analysis and PCA CS81 Section 4: Factor Analysis and PCA Scott Linderman At this point we have seen a variety of machine learning models, with a particular emphasis on models for supervised learning. In particular, we

More information

Multivariable and Multiaxial Fatigue Life Assessment of Composite Materials using Neural Networks

Multivariable and Multiaxial Fatigue Life Assessment of Composite Materials using Neural Networks Multivariable and Multiaxial Fatigue Life Assessment of Composite Materials using Neural Networks Mas Irfan P. Hidayat Abstract In the present paper, multivariable and multiaxial fatigue life assessment

More information

ARTIFICIAL NEURAL NETWORK WITH HYBRID TAGUCHI-GENETIC ALGORITHM FOR NONLINEAR MIMO MODEL OF MACHINING PROCESSES

ARTIFICIAL NEURAL NETWORK WITH HYBRID TAGUCHI-GENETIC ALGORITHM FOR NONLINEAR MIMO MODEL OF MACHINING PROCESSES International Journal of Innovative Computing, Information and Control ICIC International c 2013 ISSN 1349-4198 Volume 9, Number 4, April 2013 pp. 1455 1475 ARTIFICIAL NEURAL NETWORK WITH HYBRID TAGUCHI-GENETIC

More information