Radar assessment of structural concrete using neural networks

Radar assessment of structural concrete using neural networks

N DT Abstracts location on samples of various geometrical properties and with various SN configurations. 59323 Heiler, M.; McNed, S.; Garrett, J. Gro...

147KB Sizes 0 Downloads 48 Views

N DT Abstracts location on samples of various geometrical properties and with various SN configurations.

59323 Heiler, M.; McNed, S.; Garrett, J. Ground penetrating radar for highway and bridge deck condition assessment and inventory

59214 Pham, D.T.; Jennings, N.R.; Ross, I. Intelligent visual inspection of valve-stem seals

Nondestructive Evaluation of Aging Bridges and Highways, Oakland California (United States), 6-7 June. 1995. pp. 195-206 Edited by S. Chase. SPIE Vol. 2456 (1995) ISBN 0-8194-1809-9 Ground penetrating radix (GPR) has been developed and used successfully for bridge deck and roadway condition assessment. Parallel processing in the form of artificial neural networks (ANN's) has been applied to the interpretation of GPR condition assessment data from highways. This paper introduces a general strategy for using ANN's for the interpretation of GPR data. Results of applying this strategy to bridge deck condition assessment data are also given.

Control Engineering Practice, Vol. 3, No. 9, pp. 1237-1245 (Sep. 1995) This paper discussed how rules and neural networks have been applied in an automated visual inspection system for the rejection of faulty components, and more importantly, to provide information about the faults that may be used by an on-line quality improvement system. Rules have been used to implement an attentional mechanism which detects discontinuities on the sealing lip contour, and neural networks have been employed to classify surface defects by their geometrical outline features. The paper describes - the types of faults to be discriminated by the system, the optical and mechanical hardware employed, the different algorithms developed and their practical validation.

59315 Molyneaux, T.C.K.; Millard, S.G.; Bungey, J.H.; Zhou, J.Q. Radar assessment of structural concrete using neural networks

59211 Kim, J.H.; Cho, H.S. Neural network-based inspection of solder joints using a c i r c u l a r illumination

NDT&E International, Vo]i. 28, No. 5, pp. 281-288 (Oct. 1995) An assessment of the capability of artificial neural networks to interpret radar images of reinforced concrete is presented. The capability of three-layer, fully connected networks to detect the presence of a bar, the size of a bar, and the depth of a bar is examined. The study demonstrates that the use of a neural network app]roach to interpret complex sub-surface radar results of embedded reinforcing bars is promising. The neural network approach is successful in locating reinforcing bars over a range of embedment depths on almos~Lall occasions. In addition it is shown to be possible to place each bar into a depth category with a high degree of

Image and Vision Computing, Vol. 13, No. 6, pp. 479-490 (Aug. 1995) We describe an approach to inspection of solder joints on printed circuit boards by using a circular illumination technique and a neural network classifier. The illumination technique gives good visual clues to infer 3D shape of the solder joint surface. The practical feasibility of the proposed approach is demonstrated by building a prototype inspection machine and testing its performance.

Success.

59210 Anon Fiber-optic sensors in s m a r t civil s t r u c t u r e s Sensors, Vol. 12, No. 8, pp. 18-25 (Aug. 1995) Smart civil structures incorporate sensors and actuators into buildings. bridges, and dams to measure and monitor their structural integrity and to take remedial actions.

59313 Araki, K.; Yoshida, K. Expert system for evaluation of material degradation in a nuclear power plant with the data of material condition monitoring Proceedings of the 13th International Conference on NDE in the Nuclear and Pressure Ves:sel Industries, Kyoto (Japan), 22-25 May 1995. pp. 369- 380. AS M International (1995) ISBN 0-87170-548-6 We are developing a computer system to read data obtained from the devices and to assess the mal:erial degradation. This computer system is to assess material degradation with its mode and level using the MCM data and plant information such as operating record. This paper describes an outline of the evaluation system of material degradation, and shows some evaluation results using the neural network inference, which is adopted in the system as a tool to evaluate the degradation quantitatively.

Kaseko, M.S.; Ritchie, S.G.; Lo, Z.P. Evaluation of two automated thresholding techniques for pavement images 59193

Infrastructure Planning and Management Conference Proceedings, Denver, Colorado (United States), 21-23 Jun. 1993. pp. 277-281. Edited by J.L. Gifford, D.R. Vzarski and S. McNeil. American Society of Civil Engineers (1993). ISBN 0-87262-917-1 Thresholding of pavement images is an important step towards the design of an automated pavement crack detection system. However, traditional automated thresholding techniques generally do not perform well on pavement images. Recently, a number of studies have been conducted proposing different approaches for this thresholding problem. This paper presents a comparative analysis and evaluation of the performance of one of the most promising of these approaches, the regression analysis approach, and a new approach based on artificial neural networks.

59308 Wilkie, B.A.; Gr~jTi'ths,B.J.; Wang, Y.S.; Norgate, P.; Silverwood, P.A. An AI vision system for the inspection of complex coloured objects International Journal of Production Research, Vol. 33, No. 9, pp. 2633- 2647 (Sep. 1995) This paper outlines an AI technique which involves the use of artificial neural networks. WISE, which incorporates algorithms for both conventional image processing used for position and rotation normalisation, and n-tube processing for subsequent pattern classification. WISE is implemented in software (C++)

Guralnick, S.A.; Suen, E.S.; Gu, J. Neural network system for automated highway pavement 59192

inspection Infrastructure Planning and Management Conference Proceedings, Denver, Colorado (United States), 21-23 Jun. 1993. pp. 272-276. Edited by J.L. Gifford, D.R. Vzarski and S. McNeil. American Society of Civil Engineers (1993). ISBN 0-87262-917-1 A Multi-layer Perception back-propagation neural network based methodology has been developed to process and analyze moire fringes obtained with an automated highway pavement inspection system developed in our laboratory. The sensitivity, accuracy, and efficiency of the model is compared with benchmark results obtained by means of traditional techniques to evaluate the overall system performance.

Milne, R. Continuous expert diagnosis: is the future so far away? 59287

Modern Power Systems, Vol. 15, No. 10, pp. 19-22 (Oct. 1995) Condition based maintenance is a practice that can bring benefits in cost and efficiency. For the best return, however, it requires accurate condition monitoring and diagnosis, in order to carry out this function, the TIGER programme has been deveh)ped to integrate an expert system with data acquisition to provide advan,2ed monitoring and diagnosis of problems. 59239 Grabec, I.; Anto[ovic, B. Intelligent Iocator of A E sources Progress in Acoustic Emission VIi. Proceedings of 12th International Acoustic Emission Symposium, Sapporo (Japan), 17-20 Oct. 1994. pp. 565- 570. Edited by T. Kishi Y, Mori and M. Enoki. The Japanese Society for Non-Destructive Inspection (1994) This article describes an information processing system (ILAES) which is capable of locating sources of acoustic emission bursts based on learning from examples. The system includes a network of AE sensors (SN), a triggered clock, and a neural network (NN) simulated on a PC. For the operation of ILAES a learni]3g and an analysis phase are characteristic. It is shown in the article that the same system is applicable for AE source

333

Workman, G.L.; Walker, J.; Lansing, M. Acoustic method of damage sensing in composite materials

59101

Alabama Univ., Huntsville (United States), N95-18135/0/GAR, 39pp. (20 Oct. 1994) The use of acoustic emission and acousto-uitrasonics to characterize impact damage in composite structures is being performed on both graphite epoxy and kevlar bottles. Further development of the acoustic emission methodology to include neural net analysis and/or other multivariate techniques will enhance the capability of the technique to identify failure mechanisms during fracture. The acousto-ultrasonics technique will be investigated to determine its ability to predict regions prone to failure prior to the burst tests.