Our experts at TÜV Rheinland have many years of experience and practice in NDT techniques and strive to provide clients with the most fitted and tailored nondestructive method for their pressure equipment while offering reliable, timeand cost-efficient solutions. Acoustic emission testing is one of the most comprehensive and adapted proceduresto detect defects and flaws in your pressure equipment because it can be conducted during operation and does not require any interruption of activity. It also allows for global monitoring of the complete pressure equipment asset and is the best solution for vessels with complex geometries.

Acoustic Emission 방법의 공학적 응용

White blood cells identification system based on convolutional deep neural learning networks.

The detection and classification of white blood cells (WBCs, also known as Leukocytes) is a hot issue because of its important applications in disease diagnosis. Nowadays the morphological analysis of blood cells is operated manually by skilled operators, which results in some drawbacks such as slowness of the analysis, a non-standard accuracy, and the dependence on the operator’s skills. Although there have been many papers studying the detection of WBCs or classification of WBCs independently, few papers consider them together. This paper proposes an automatic detection and classification system for WBCs from peripheral blood images. It firstly proposes an algorithm to detect WBCs from the microscope images based on the simple relation of colors R, B and morphological operation. Then a granularity feature (pairwise rotation invariant co-occurrence local binary pattern, PRICoLBP feature) and SVM are applied to classify eosinophil and basophil from other WBCs firstly. Lastly, convolution neural networks are used to extract features in high level from WBCs automatically, and a random forest is applied to these features to recognize the other three kinds of WBCs: neutrophil, monocyte and lymphocyte. Some detection experiments on Cellavison database and ALL-IDB database show that our proposed detection method has better effect almost than iterative threshold method with less cost time, and some classification experiments show that our proposed classification method has better accuracy almost than some other methods.

Automatic detection and classification of leukocytes using convolutional neural networks

White blood cells detection and classification based on regional convolutional neural networks.

Automatic segmentation, counting, size determination and classification of white blood cells

Discontinuity inspection in pipelines: A comparison review

A new measurement system using magnetic flux leakage method in pipeline inspection

In this study, the variation of the magnetic flux distribution in a magnetised ferromagnetic material which has inhomogeneity as a crack is studied using giant magnetoimpedance, GMI, sensor. The sensor was moved by a specially designed moving system. The amorphous (Co0.94Fe0.06)72.5Si12.5B15 wire was used as a GMI sensor and 1 MHz with 5 mA ac current applied to the GMI sensor. A large decrease in the output voltage of the sensor circuit was observed when the sensor was moved on the top of the crack, after the further movement of the sensor the output voltage came back to the nearly previous value. (© 2004 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim)

Non-destructive Crack detection using GMI sensor

In this paper, a new method is proposed to identify and classify the data obtained by the sensor network (SN) for the detection of mines. This method is used for the identification of antitank and antipersonnel mines and classification of buried objects within a target region. In this paper, a mobile SN is used to detect mines and some other objects buried and creating magnetic anomaly in and around the region where they are found, with the behavior of the individual sensors swarming onto the area under which a mine or any other object is buried. The process of collecting data by the SN and modeling it mathematically are explained in detail. The SN is modeled as a fictitious two-dimensional spatial impulse sampler. This paper is motivated by clearing the territories of mine fields to open them to agriculture. It is very important because, currently, in some countries, very fertile territories around the borders are covered by buried mines. The approach is basically based on magnetic anomaly measurements, which directly tackles the subregions corresponding to buried objects whether they represent objects that are separately located or occluded by other objects. It is based on a new developed method that is called “the back-most object detection and identification algorithm.” This method is fully automatic, and there is no human intervention throughout the process. In this paper, classification of objects is based on their well-known shapes and dimensions. Therefore, there is no need for sophisticated learning algorithms to achieve classification. The experimental results are given both for detection and identification of a single mine and classification of a number of mines and any other objects that have a potential of giving false alarms in a target region.

Yavuz Ege

Papers

Automatic segmentation, counting, size determination and classification of white blood cells

Discontinuity inspection in pipelines: A comparison review

A new measurement system using magnetic flux leakage method in pipeline inspection

Non-destructive Crack detection using GMI sensor

Mine Identification and Classification by Mobile Sensor Network Using Magnetic Anomaly