Detection of dairy fouling: Combining ultrasonic measurements and classification methods

Fouling and cleaning in heat exchangers are severe and costly (up to 0.3% of gross national product) issues in dairy and food processing. Therefore, reducing cleaning time and cost is urgently needed. In this study, two classification methods [artificial neural network (ANN) and support vector machine (SVM)] for detecting protein and mineral fouling presence and absence based on ultrasonic measurements were presented and compared. ANN is based on a multilayer perceptron feed forward neural network, whereas SVM is based on clustering between fouling and no fouling using a hyperplane. When both fouling types (1239 datasets) were combined, ANN showed an accuracy of 71.9% while SVM displayed an accuracy of 97.6%. Separate fouling detection of mineral/protein fouling by ANN/SVM was comparable: dependent on fouling type detection accuracies of 100% (protein fouling, ANN and SVM), and 98.2% (SVM), and 93.5% (ANN) for mineral fouling was reached. It was shown that it was possible to detect fouling presence and absence offline in a static setup using ultrasonic measurements in combination with a classification method. This study proved the applicability of combining classification methods and fouling measurements to take a step toward reducing cleaning costs and time.

[1]  Walid Hussein,et al.  DETECTION OF THE RED PALM WEEVIL RHYNCHOPHORUS FERRUGINEUS USING ITS BIOACOUSTICS FEATURES , 2010 .

[2]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[3]  Xiao Dong Chen,et al.  On-line fouling/cleaning detection by measuring electric resistance-equipment development and application to milk fouling detection and chemical cleaning monitoring , 2004 .

[4]  H. Burton,et al.  Section G. Deposits from whole milk in heat treatment plant—a review and discussion , 1968, Journal of Dairy Research.

[5]  Aparajita Datta,et al.  Milk fouling simulation in helical triple tube heat exchanger , 2005 .

[6]  José Sérgio da Rocha Neto,et al.  Non-Invasive Fast Detection of Internal Fouling Layers in Tubes and Ducts by Acoustic Vibration Analysis , 2009, IEEE Transactions on Instrumentation and Measurement.

[7]  Qi-feng Liu,et al.  Prediction of microfiltration membrane fouling using artificial neural network models , 2009 .

[8]  Inmaculada Arauzo,et al.  Monitoring and prediction of fouling in coal-fired utility boilers using neural networks , 2005 .

[9]  Hans Müller-Steinhagen,et al.  INTELLIGENT DISCRIMINATION MODEL TO IDENTIFY INFLUENTIAL PARAMETERS DURING CRYSTALLISATION FOULING , 2007 .

[10]  George S. K. Wong,et al.  Speed of sound in pure water as a function of temperature , 1993 .

[11]  Bipan Bansal,et al.  A Critical Review of Milk Fouling in Heat Exchangers , 2006 .

[12]  S. Verzakov,et al.  Classification of signatures of Bovine Spongiform Encephalopathy in serum using infrared spectroscopy. , 2004, The Analyst.

[13]  Michael Egmont-Petersen,et al.  Image processing with neural networks - a review , 2002, Pattern Recognit..

[14]  Ulf Schnars,et al.  1 Applications of NDT Methods on Composite Structures in Aerospace Industry , 2006 .

[15]  M. T. Belmar-Beiny,et al.  Fouling of heat exchangers in the food industry: a chemical engineering prespective , 1991 .

[16]  A. Datta,et al.  Improved milk fouling simulation in helical triple tube heat exchanger. , 2006 .

[17]  Peter J. Fryer,et al.  Engineering and chemical factors associated with fouling and cleaning in milk processing , 1997 .

[18]  J. Mendes,et al.  Using nanovibrations to monitor biofouling , 2008, Biotechnology and bioengineering.

[19]  H. Müller-Steinhagen,et al.  Initiation of CASO4 Scale Formation on Heat Transfer Surfaces under Pool Boiling Conditions , 2007 .

[20]  P. J. Goetz,et al.  Use of ultrasound for characterizing dairy products. , 2005, Journal of dairy science.

[21]  David Baker,et al.  Ranking predicted protein structures with support vector regression , 2007, Proteins.

[22]  Shrikanth S. Narayanan,et al.  Support Vector Regression for Automatic Recognition of Spontaneous Emotions in Speech , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[23]  Patrice Tochon,et al.  A new transient thermal fouling probe for cross flow tubular heat exchangers , 2009 .

[24]  T. Jeurnink,et al.  Fouling of heat exchangers in the dairy industry , 1997 .

[25]  J. Hinrichs,et al.  On the usage of acoustic properties combined with an artificial neural network – A new approach of determining presence of dairy fouling , 2011 .

[26]  Laurent Bouvier,et al.  Structure and rate of growth of whey protein deposit from in situ electrical conductivity during fouling in a plate heat exchanger , 2007 .

[27]  Peter J. Fryer,et al.  A prototype cleaning map: A classification of industrial cleaning processes , 2009 .

[28]  A. Law,et al.  Effect of pH on the thermal denaturation of whey proteins in milk. , 2000, Journal of agricultural and food chemistry.

[29]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[30]  Hiroshi Nakamura,et al.  Multidimensional support vector machines for visualization of gene expression data , 2004, SAC '04.

[31]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[32]  Guillaume Delaplace,et al.  Design and performance of a low-frequency non-intrusive acoustic technique for monitoring fouling in plate heat exchangers , 2007 .

[33]  Alexander Gammerman,et al.  Machine learning classification with confidence: Application of transductive conformal predictors to MRI-based diagnostic and prognostic markers in depression , 2011, NeuroImage.

[34]  Peter Withers.  Ultrasonic sensor for the detection of fouling in UHT processing plants , 1994 .

[35]  T. Benezech,et al.  Thermal performance of a flat ohmic cell under non-fouling and whey protein fouling conditions , 2008 .

[36]  Yingying Zhang,et al.  Fouling Prediction of Heat Exchanger Based on Genetic Optimal SVM Algorithm , 2009, 2009 Third International Conference on Genetic and Evolutionary Computing.

[37]  Hans Müller-Steinhagen,et al.  Analysis of Fouling Data Based on Prior Knowledge , 2003 .

[38]  Kazuhiro Hotta.  Robust face recognition under partial occlusion based on support vector machine with local Gaussian summation kernel , 2008, Image Vis. Comput..

[39]  N. Lamberti,et al.  An ultrasound technique for monitoring the alcoholic wine fermentation. , 2009, Ultrasonics.

[40]  Sylvain Lalot,et al.  Detection of fouling in a cross-flow heat exchanger using a neural network based technique , 2010 .

[41]  W. Stark,et al.  Relationship between the Mechanical and Ultrasound Properties of Polymer Materials , 2006 .

[42]  Xiao Dong Chen,et al.  Effect of whey protein concentration on the fouling and cleaning of a heat transfer surface , 2011 .

[43]  J. C. Leuliet,et al.  Continuous ohmic heating unit under whey protein fouling , 2004 .

[44]  T. Truong,et al.  The Use of a Heat Flux Sensor for In-Line Monitoring of Fouling of Non-Heated Surfaces , 2002 .

[45]  CONSTRUCTION OF HIGH PREDICTIVE FOULING MODELS USING STATISTICAL METHODS , 2009 .

[46]  E. Buyruk,et al.  Numerical investigation of fouling on cross-flow heat exchanger tubes with conjugated heat transfer approach , 2008 .

[47]  Sun Lingfang,et al.  Research on the Fouling Prediction of Heat Exchanger Based on Support Vector Machine , 2008, 2008 International Conference on Intelligent Computation Technology and Automation (ICICTA).

[48]  Steven W. Su,et al.  Online Support Vector Machine Applicationfor Model Based Fault Detection and Isolationof HVAC System , 2011 .

[49]  C Riverol,et al.  Estimation of fouling in a plate heat exchanger through the application of neural networks , 2005 .

[50]  William R. Paterson,et al.  The effect of Reynolds number and fluid temperature in whey protein fouling , 1993 .