California Scientific      BrainMaker Neural Network Software
Home	Applications	What Are Neural Networks	Products	Ordering Info	Tech Support

Applications Stocks Currency Predictions Corporate Bonds S&P 500 Index Stock Price Prediction Stock Prophet Natural Gas Prices Business Direct Mail Credit Scoring Real Estate Appraisal Bad Cops Finding Gold Jury Summoning Highway Maintenance Medical Breast Cancer Hospital Expenses Functional Recovery Heart Attack Diagnosis ER Test ordering Psychiactric Care Giant Cell Arteritis Sports Thoroughbreds Thoroughbreds 1 Dog Racing Science Solar Flares Protein Sequencing Mosquito Identification Spectroscopy Weather Forecasting Predicting El Nino Air Quality Manufacturing Welding Quality Plastics Testing IC Quality Control Paper Quality Concrete Testing Beer Quality Enzyme Synthesis Steam Quality Pattern Recog. Speech Recognition Article Classification Working with Chaos Chemical Drawings Sequence Prediction

BrainMaker performs non-destructive concrete strength testing. In testing concrete for structural imperfections there are many different methods ranging from the drilling of core samples to the use of radar. The first method is destructive, time consuming, and allows for only a small percentage of the total area, while the second requires expensive equipment and isn't effective when steel reinforcement is present. The National Institute of Standards and Technology (NIST) has developed a non-destructive method for testing the internal structure of concrete. Nondestructive testing (NDT) methods are used to obtain information about the properties or internal condition of an object without damaging it. Steel balls are dropped onto the concrete surface causing soundwaves, which are reflected by cracks and other imperfections in the concrete. These sound waves can then be collected and analyzed by a neural network to determine the probability of a flaw. NIST has developed a system that used the thickness of the concrete as the base measurement and was able to determine the depth of the flaw to 10% accuracy. (The network was able to test a 0.4m thick slab with a 0.2m flaw and determine that the flaw was 40% to 50% the depth of the slab.) They constructed their network in the following manner: Inputs: 1-150. The reflected sound Outputs: 1. The probability that a flaw exists 2-11. The approximate depth of the flaw (in 10% increments) More information can be found at: Impact-echo signal interpretation using artificial intelligence Title: Impact-echo signal interpretation using artificial intelligence Author(s): DONALD PRATT and MARY SANSALONE Publication: Materials Journal Volume: 89 Issue: 2 Keywords: artificial intelligence; concretes; impact tests; slabs; voids; stress waves; Materials Research Date: March 1, 1992 Abstract: Discusses advancements in impact-echo instrumentation and signal processing that have led to the development of an automated field system. The basic principles involved in impact-echo testing and signal analysis are reviewed. An artificial intelligence technique called a neural network, which has been used to automate signal interpretation from platelike concrete structures, is explained, and examples of its use on concrete slabs containing voids and cracks are shown. Impact-echo instrumentation is discussed, and a new, rapid impact-echo field system is presented. This field system can be used independently when testing concrete structures, such as beams or columns, or in conjunction with the automated signal interpretation software when testing plate-like structures, such as bridge decks, parking garage slabs, and walls. The automated field system makes it possible for the impact-echo test method to become a practical nondestructive tool for condition assessment of concrete structures. Reprints available at: http://www.aci-int.org/journals/journals.htm

Home	Applications	What Are Neural Networks	Products	Ordering Info	Tech Support
California Scientific      BrainMaker Neural Network Software