赵一帆

A novel aircraft wing inspection framework based on multiple view geometry and convolutional neural network

To achieve greener and safer aeronautical operations, this paper considers the problem of reconstructing the three-dimensional (3D) geometric structure of aeronautical components. A novel framework that recovers the 3D shapes by means of convolutional neural network (ConvNets) and multiple view geometry (MVG) operating on Mask-R-CNN-segmented two-dimensional images is proposed. To achieve more accurate 3D aircraft’s surface and exclude the invalid background structures, this paper innovatively integrates the environmental robustness of ConvNets and geometric adaptation of Mask-R-CNN into the MVG theory. The preliminary experiments show that the proposed framework is visual-comfortable, and it also accurately reconstructs the regions with damage to catch up with the inspection purpose.

A miniaturised active thermography system for in-situ inspections

With the increase of the functionalisation, integration and complexity of industrial components and systems, deploying Non-Destructive Testing (NDT) devices for ‘in-situ’ inspection has become a major challenge for high-value assets. Due to the mismatching of size and volume between the existing inspection unit and the targeted complex object, inaccessibility and inapplicability have limited the applicability of NDT techniques. To address this challenge, this paper introduces a novel miniaturised active thermography system based on a commercial thermal imaging sensor featured with small size and low cost. Combining with different excitation sources, its detection performance on different types of defect of carbon fibre reinforced polymer (CFRP) is investigated and compared with an existing system. The results show that the proposed system can work with laser and flash effectively for degradation assessment although the detectability is compromised. Such a technique will play a unique role in the in-situ inspection where the space to deploy the device is limited.

A clustering approach to detect faults with multi-component degradations in aircraft fuel systems

Accurate fault diagnosis and prognosis can significantly increase the safety and reliability of engineering systems and also reduce the maintenance costs. There is very limited relative research reported on the fault diagnosis of a complex system with multi-component degradation. The Complex Systems (CS) problem, which features multiple components simultaneously and nonlinearly interacting with each other and corresponding environment on multiple levels, has become an essential challenge in system engineering. In CS, even a single component degradation could cause misidentification of the fault severity level and lead to serious consequences. This paper introduces a new test rig to simulate multi-component degradations of the aircraft fuel system. A data analysis approach based on machine learning classification of both the time and frequency domain features is then proposed to detect and identify the fault severity level of CS with multi-component degradation. Results show that a) the fault can be sensitively detected with an accuracy > 99

A Dementia Classification Framework Using Frequency and Time-Frequency Features Based on EEG Signals

Tremor after long term lithium treatment; is it cortical myoclonus?

Tremor is a common side effect of treatment with lithium. Its characteristics can vary and when less rhythmical, distinction from myoclonus can be difficult.

Topology reconstruction of tree-like structure in images via structural similarity measure and dominant set clustering

The reconstruction and analysis of tree-like topological structures in the biomedical images is crucial for biologists and surgeons to understand biomedical conditions and plan surgical procedures. The underlying tree-structure topology reveals how different curvilinear components are anatomically connected to each other. Existing automated topology reconstruction methods have great difficulty in identifying the connectivity when two or more curvilinear components cross or bifurcate, due to their projection ambiguity, imaging noise and low contrast. In this paper, we propose a novel curvilinear structural similarity measure to guide a dominant-set clustering approach to address this indispensable issue. The novel similarity measure takes into account both intensity and geometric properties in representing the curvilinear structure locally and globally, and group curvilinear objects at crossover points into different connected branches by dominant-set clustering. The proposed method is applicable to different imaging modalities, and quantitative and qualitative results on retinal vessel, plant root, and neuronal network datasets show that our methodology is capable of advancing the current state-of-the-art techniques.

Non-destructive evaluation of localised heat damage occurring in carbon composites using thermography and thermal diffusivity measurement

Filter-generating system of Zernike polynomials

This work proposes a new approach to find the generating function (GF) of the Zernike polynomials in two dimensional form. Combining the methods of GFs and discrete-time systems, we can develop two dimensional digital systems for systematic generation of entire orders of Zernike polynomials. We establish two different formulas for the GF of the radial Zernike polynomials based on both the degree and the azimuthal order of the radial polynomials. In this paper, we use four terms recurrence relation instead of the ordinary three terms recursion to calculate the radial Zernike polynomials and their GFs using unilateral 2D Z-transform. A spatio-temporal implementation scheme is developed for generation of the radial Zernike polynomials. The case study shows a reliable way to evaluate Zernike polynomials with arbitrary degrees and azimuthal orders.

Estimation of Damage Thickness in Fiber-Reinforced Composites using Pulsed Thermography

Distractor-Aware Deep Regression for Visual Tracking