Automation interpretation

The effectiveness of the approach is demonstrated on two rqjresentative NDT techniques intapretation of data acquired with an ultrasonic rail inspection system and interpretation of eddy-current data from heat exchangers in (petro-)chemical industry. The results show that it is possible to provide a high level of automation in combination with efficient operator support for highly variable NDT measurements where up to now use of automated interpretation was only limited. 

For homogeneous NDT data and repeatable inspection conditions successful automated interpretation systems can relatively easily be developed. They usually use standard techniques from statistical classification or artificial intelligence. Design of successful automated interpretation systems for heterogeneous data coming form non-repeatable, small volume inspections with little a-priori information about the pieces or constructions to be inspected is far more difficult. This paper presents an approach which can be used to develop such systems. 

To simplify further discussion we would like to present in this section the four characteristics of NDT inspection which we think are of the most influence on the (options for) choice of any technique for automated interpretation of the data. 

Examples of automated interpretation systems for heterogeneous NDT data... 

Woodruff and co-workers introduced the expert system PAIRS [67], a program that is able to analyze IR spectra in the same manner as a spectroscopist would. Chalmers and co-workers [68] used an approach for automated interpretation of Fourier Transform Raman spectra of complex polymers. Andreev and Argirov developed the expert system EXPIRS [69] for the interpretation of IR spectra. EXPIRS provides a hierarchical organization of the characteristic groups that are recognized by peak detection in discrete ames. Penchev et al. [70] recently introduced a computer system that performs searches in spectral libraries and systematic analysis of mixture spectra. It is able to classify IR spectra with the aid of linear discriminant analysis, artificial neural networks, and the method of fe-nearest neighbors. 

Greer J. Three dimensional pattern recognition an approach to automated interpretation of electron density maps of proteins. / Mol Biol 1974 82 279-301. 

Leherte, L., Fortier, S., Glasgow, J. and Allen, F.H. (1994) Molecular scene analysis application of a topological approach to the automated interpretation of protein electron-density maps, Acta Cryst., D50, 155-166 and references therein. 

Data Reduction and Automated Interpretation of CPC Spin Column/ESI-MS Data... 

Fernandez-De-Cossio, J., Gonzalez, J., Satomi, Y. et al. (2001) Automated interpretation of low-energy collision induced dissociation spectra by SeqMS, a software aid for de novo sequencing by tandem mass spectrometry. Electrophoresis, 21, 1694-9. 

Huang, K., Lin, J., Gajnak, J.A. and Murphy, R.F. (2002) Image content-based retrieval and automated interpretation of fluorescence microscope images via the protein subcellular location image database. Proc 2002 IEEE Inti Symp Biomedl Imag 325-328. 

Murphy, R.F. (2004) Automated interpretation of subcellular location patterns. 2004 IEEE International Symposium on Biomedical Imaging (ISBl-2004),... 

Josh HJ, Harrison Ml, Schulz BL, Cooper CA, Packer NH, Karlsson NG. Development of a mass fingerprinting tool for automated interpretation of oligosaccharide fragmentation data. Proteomics 2004 4 1650-64. 

Tang H, Mechref Y, Novotny MV. Automated interpretation of MS/MS spectra of oligosaccharides. Bioinformatics 2005 21(Suppl 1) i431-i439. 

Luinge, H.J. Automated interpretation of vibrational spectra. Vibr. Spectrosc. 1990, 1, 3-18. 

Klagkou, K. Pullen, E. Harrison, M. Organ, A. Firth, A. Langley, G.J. Approaches Towards the Automated Interpretation and Prediction of Electrospray TandemMass Spectra of Non-peptidic Combinatorial Compounds, Rapid Commun. Mass Spectrom. 17, 1163-1168 (2003). 

Alford-Stevens AL, Bellar TA, Eichelberger JW, et al. 1986. Accuracy and precision of determinations of chlorinated pesticides and polychlorinated biphenyls with automated interpretation of mass spectrometric data. Anal Chem 58 2022-2029. 

PAIRS is a program that analyzes infrared spectra in a similar manner as a spectros-copist does and was designed for automated interpretation of Eourier transform Raman spectra of complex polymers. 

Claybourn, M., Luinge, H. J., and Chalmers, J.M., Automated Interpretation of Eourier Transform Raman Spectra of Complex Polymers Using an Expert System, J. Raman Spectrosc., 25, 115, 1994. 

Culvenor DS, Coops N, Preston R, Tolhurst K (1999) A spatial clustering approach to automated tree crown delineation. Proceedings of the international forum on automated interpretation of high spatial resolution digital imagery for forestry, 10-12 February, Victoria, BC, Canada, Natural Resources Canada, pp 67—80... 

Nuclear magnetic resonance (NMR) spectroscopy is the most informative analytical technique and is widely applied in combinatorial chemistry. However, an automated interpretation of the NMR spectral results is difficult (3,4). Usually the interpretation can be supported by use of spectrum calculation (5-18) and structure generator programs (8,12,18-21). Automated structure validation methods rely on NMR signal comparison using substructure/ subspectra correlated databases or shift prediction methods (8,15,22,23). We have recently introduced a novel NMR method called AutoDROP (Automated Definition and Recognition of Patterns) to rapidly analyze compounds libraries (24-29). The method is based on experimental data obtained from the measured ID or 2D iH,i C correlated (HSQC) spectra. 

M Clayboum, HJ Luinga, JM Chalmers. Automated interpretation of Fourier transform Raman spectra of complex polymers using an expert system. J Raman Spectrosc 25 115-122, 1994. 

The approach used here for connection table interpretation assumes that there are limited numbers of kinds of information which exist in the desired formats, and that it is known how to convert the information from each of these to a suitable internal form. The interpretation of any instance of a connection table can then be divided into two completely independent parts extracting the information from the table and converting it to internal form. This allows automated interpretation, given the meaning (representation and encoding) of each field of a connection table format. 

Mizuno, Y. Sasagawa, T Dohmae, N. Taho, K. An automated interpretation of MALDl/TOF postsource decay spectra of ohgosaccharides. 1. Automated peak assignment Anal. Chem. 1999, 71, 4764—4771. 

Classification tools are widely used in both 3D and 4D reservoir characterization, for example in mapping 3D structures, lithological properties and production effects [8]. In this work we extend the area of application of the classification methodology into automated interpretation of seismic horizons... 

---