Search

Currently, along with growth in industrial production, the requirements for product quality testing are also increasing. In the tasks of defectoscopy and defectometry of multilayer materials, the use of thermal nondestructive testing method is promising. At the same time, interpretation of thermal testing data is complicated by a number of factors, which makes the use of traditional methods of data processing ineffective. Therefore, an urgent task is to search for new methods of thermal testing that will automate the diagnostic process and increase information content of obtained results. The purpose of article is to use the advances in deep learning for processing results of active thermal testing of products made of multilayer materials and development of an automated system for thermal defectoscopy and defectometry of such products. The proposed system consists of a heating source, an infrared camera for recording sequences of thermograms and a digital information processing unit. Three neural network modules are used for automated data processing, each of which performs one of the tasks: defects detection and classification, determination of the defect depth and thickness. The software algorithms and user interface for interacting with system are programmed in the NI LabVIEW development environment.Experimental studies on samples made of multilayer fiberglass have shown a significant advantage of the developed system over using traditional methods for analyzing thermal testing data. The defect classification (determining the type) error on the test dataset was 15.7 %. Developed system ensured determination of defect depth with a relative error of 3.2 %, as well as the defect thickness with a relative error of 3.5 %.

Currently, non-destructive testing is an interdisciplinary field of science and technology that serves to ensure the safe functioning of complex technical systems in the face of multifactorial risks. In this regard, there is a need to consider new information technologies based on intellectual perception, recognition technology, and general network integration. The purpose of this work was to develop an ultrasonic flaw detector, which uses a smartphone to process the test results, as well as transfer them directly to an powerful information processing center, or to a cloud storage to share operational information with specialists from anywhere in the world.The proposed flaw detector consists of a sensor unit and a smartphone. The exchange of information between the sensor and the smartphone takes place using wireless networks that use "bluetooth" technology. To ensure the operation of the smartphone in the ultrasonic flaw detector mode, the smartphone has software installed that runs in the Android operating system and implements the proposed algorithm of the device, and can serve as a repeater for processing data over a considerable distance (up to hundreds and thousands of kilometers) if it necessary.The experimental data comparative analysis of the developed device with the Einstein-II flaw detector from Modsonic (India) and the TS-2028H+ flaw detector from Tru-Test (New Zealand) showed that the proposed device is not inferior to them in terms of such characteristics as the range of measured thicknesses, the relative error in determining the depth defect and the object thickness. When measuring small thicknesses from 5 to 10 mm, the proposed device even surpasses them, providing a relative measurement error of the order of 1 %, while analogues give this error within 2–3 %.