Deep Learning Automated System for Thermal Defectometry of Multilayer Materials

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 %.

Study of multilayer material deformation conditions by method of finite element analysis

The finite element analysis method of multilayer materials deformation during hot rolling is studied. Physical conditions, on which the model is based, is described. Calculation results showed the multilayer materials center of deformation singularity and difference from condition of blank edge. It is shown that uniform deformation of multilayer material during hot rolling is possible due to formation of layer bonding. Described results are useful for multilayer materials on the base of different metals.

Wireless Network Enhancement in the Arctic by Selection of Dielectric Materials of Rooms

The Arctic is of fundamental military-strategic importance for Russia. The development of the Arctic without an advanced telecommunication infrastructure is very difficult. To supply working in the Arctic employees with universal means of communication, it is the most efficient to use wireless communication band between 2.4 GHz and 5 GHz. Facilities, where radio telecommunication equipment in the Arctic works, have walls consisting of a multilayer structure. There is the problem of organizing communication of good quality. In such rooms, the best method is to use wireless networks using MIMO technology. We have developed a theory that allows us to determine the time Interflection T based on the determination of the dielectric constant of multilayer materials. In this case, problems arise in determining this coefficient. We propose to use the well-known method of short circuit and idling. We conducted a large number of measurements to determine the dielectric constant of various materials. We used this value to calculate the time T. In the future, we made adjustments to the premises by changing the size and amount of multilayer materials. Experimental results in the range from 2.4 GHz to 5 GHz showed that the data transfer rate increased by 5-10% when we performed the calculation of time Interflection and processed the room with multilayer materials. The proposed method is applicable indoors to build a wireless LAN standard IEEE 802.11 n.