| 1. |
- Kristan, Matej, et al.
(författare)
-
The Sixth Visual Object Tracking VOT2018 Challenge Results
- 2019
-
Ingår i: Computer Vision – ECCV 2018 Workshops. - Cham : Springer Publishing Company. - 9783030110086 - 9783030110093 ; , s. 3-53
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative. Results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis and a “real-time” experiment simulating a situation where a tracker processes images as if provided by a continuously running sensor. A long-term tracking subchallenge has been introduced to the set of standard VOT sub-challenges. The new subchallenge focuses on long-term tracking properties, namely coping with target disappearance and reappearance. A new dataset has been compiled and a performance evaluation methodology that focuses on long-term tracking capabilities has been adopted. The VOT toolkit has been updated to support both standard short-term and the new long-term tracking subchallenges. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website (http://votchallenge.net).
|
|
| 2. |
- Costa, Sergio, 1987, et al.
(författare)
-
Validation and improvements of a mesoscale finite element constitutive model for fibre kinking growth
- 2019
-
Ingår i: ECCM 2018 - 18th European Conference on Composite Materials. - : European Society for Composite Materials. - 9781510896932
-
Konferensbidrag (refereegranskat)abstract
- The present work is focused on the computational challenges and further verification and validation of an advanced fibre kinking model. This model was previously developed by the authors and implemented in a Finite Element (FE) code with a mesh objective formulation. The previous validation in terms of comparison with an analytical and a micromechanical model is herein extended to also encompass FE simulations of longitudinal compression in multiaxial stress states. In addition, numerical improvements have been added to the model targeting its computational efficiency and stability in order to handle multiaxial stress states and large structures.
|
|
| 3. |
- del Campo, Sergio Martin, et al.
(författare)
-
FPGA prototype of machine learning analog-to-feature converter for event-based succinct representation of signals
- 2013
-
Ingår i: IEEE International Workshop on Machine Learning for Signal Processing. - Piscataway, NJ : IEEE Signal Processing Society.
-
Konferensbidrag (refereegranskat)abstract
- Sparse signal models with learned dictionaries of morphological features provide efficient codes in a variety of applications. Such models can be useful to reduce sensor data rates and simplify the communication, processing and analysis of information, provided that the algorithm can be realized in an efficient way and that the signal allows for sparse coding. In this paper we outline an FPGA prototype of a general purpose "analog-to-feature converter", which learns an overcomplete dictionary of features from the input signal using matching pursuit and a form of Hebbian learning. The resulting code is sparse, event-based and suitable for analysis with parallel and neuromorphic processors. We present results of two case studies. The first case is a blind source separation problem where features are learned from an artificial signal with known features. We demonstrate that the learned features are qualitatively consistent with the true features. In the second case, features are learned from ball-bearing vibration data. We find that vibration signals from bearings with faults have characteristic features and codes, and that the event-based code enable a reduction of the data rate by at least one order of magnitude.
|
|
| 4. |
- España, Sergio, et al.
(författare)
-
Strategies for Capability Modelling : Analysis Based on Initial Experiences
- 2015
-
Ingår i: Advanced Information Systems Engineering Workshops. - Cham : Springer. - 9783319192420 - 9783319192437 ; , s. 40-52
-
Konferensbidrag (refereegranskat)abstract
- Competitiveness and growth on an international market is for many businesses tightly coupled to their ability of quickly implementing new company strategies, business services and products or market entries. Capability management is among the approaches proposed to tackle these challenges. A feature is capturing the context of capability delivery and providing mechanisms for configuring the delivery. Among the work on capability management is the capability-driven design and delivery (CDD) approach that has been proposed by the EU-FP7 project CaaS. The aim of this paper is to contribute to CDD by (i) introducing different strategies for capability modelling, (ii) elaborating on the differences between these strategies, and (iii) contributing to an understanding of what strategy should be used under what preconditions. The paper addresses these aspects by describing the strategies and initial experiences gathered with them.
|
|
| 5. |
- Fagerström, Martin, 1979, et al.
(författare)
-
MODELLING AND TESTING THE CRASH BEHAVIOUR OF COMPOSITE VEHICLES COMPONENTS
- 2019
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- In the current contribution we will present the latest developments in the project “Modelling crash behaviour in future lightweight composite vehicles – Step 2”, involving 11 Swedish partners. On the material modelling side, a fully three-dimensional model to describe fibre kinking has recently been developed. The model is physically based and considers the fibre rotation during kink-band formation under large deformations. The FE implementation of the model is straightforward which allows for easy implementation. The validation of the model for stiffness and strength shows good correlation with the experiments. The influence of initial misalignments on the stiffness is well captured, the strength defined at the onset of unstable fibre rotation, is well predicted, and, in addition, the crushing response shows very good agreement with experimental results in terms of morphology in the crushing zone, as well as in the load response. To allow for computational efficiency, we have also developed and implemented (as a user element in LS-DYNA) an adaptive modelling strategy which allows for laminates to be initially modelled with only one element over the thickness.The user element kinematics can be adaptively enriched by introducing new degrees of freedom during the simulation to allow for more accurate stress predictions in critical regions by introducing discrete material interfaces, and for the modelling of delamination crack growth by introducing discrete crack surfaces interconnected with a cohesive zone law. In this work, special care has been taken to develop a robust method for explicit crash analysis. In the element, we also able to consider the correct intralaminar fracture toughness regularisation for various spatial discretisations. To assess and validate the models developed in the project, we have also conducted a series of bending and crushing experiments on component level. Three-point bending tests (in total 45 beams) have been conducted for three different carbon-epoxy material systems (pre-preg and vacuum infused), two different span lengths and two different lay-ups at several impact speeds. Similarly, crushing tests have been conducted for the same material systems by crushing tubes (in total 35 tubes) at various angles, with two different lay-ups and at two different loading speeds (quasi-static and dynamic). We believe that these tests serve as a very strong basis for any crash model validation.
|
|
| 6. |
- Javed, Saleha, 1990-, et al.
(författare)
-
Cloud-based Collaborative Learning (CCL) for the Automated Condition Monitoring of Wind Farms
- 2022
-
Ingår i: Proceedings 2022 IEEE 5th International Conference on Industrial Cyber-Physical Systems (ICPS). - : Institute of Electrical and Electronics Engineers (IEEE).
-
Konferensbidrag (refereegranskat)abstract
- Modeling Industrial Internet of Things (IIoT) architectures for the automation of wind turbines and farms(WT/F), as well as their condition monitoring (CM) is a growing concept among researchers. Several end-to-end automated cloud-based solutions that digitize CM operations intelligently to reduce manual efforts and costs are being developed. However, establishing robust and secure communication across WT/F is still difficult for the wind energy industry. We propose a fully automated cloud-based collaborative learning (CCL) architecture using the Eclipse Arrowhead Framework and an unsupervised dictionary learning (USDL) CM approach. The scalability of the framework enabled digitization and collaboration across the WT/Fs. Collaborative learning is a novel approach that allows all WT/Fs to learn from each other in real-time. Each turbine has CCL based CM using USDL as micro-services that autonomously perform feature selection and failure prediction to optimize cost, computation, and resources. The fundamental essence of the USDA approach is to enhance the WT/F’s learning and accuracy. We use dictionary distances as a metric for analyzing the CM of WT in our proposed USDL approach. A dictionary indicates an anomaly if its distances increased from the dictionary computed at a healthy state of that WT. Using CCL, a WT/F learns all types of failures that could occur in a similar WT/F, predicts any machinery failure, and sends alerts to the technicians to ensure guaranteed proactive maintenance. The results of our research support the notion that when testing a turbine with dictionaries of all the other turbines, every dictionary converges to similar behavior and captures the fault that occurs in that turbine.
|
|
| 7. |
|
|
| 8. |
- Martin del Campo Barraza, Sergio, 1983-, et al.
(författare)
-
Kinematic Frequencies of Rotating Equipment Identified with Sparse Coding and Dictionary Learning
- 2019
-
Ingår i: Proceedings of the Annual Conference of the Prognostics and Health Management Society 2019. - Scottsdale, AZ, USA : Prognostics and Health Management Society.
-
Konferensbidrag (refereegranskat)abstract
- The detection of faults and operational abnormalities in rotating machine elements like rolling element bearings and gears requires information about kinematic properties, such as ball-pass and gear mesh frequencies. Typically, condition monitoring experts obtain such information from the manufacturers for diagnostics purposes. However, the reliability of such information can be compromised during installation and maintenance, for example, if components are replaced and do not match the documented specifications. Thus, methods enabling verification and online extraction of such kinematic properties are needed to improve diagnostic reliability. Unsupervised machine learning methods, like sparse coding with dictionary learning, enable automatic modeling and characterization of repeating signal structures in the time domain, which are naturally generated by rotating equipment. Sparse coding with dictionary learning represents a vibration signal as a linear superposition of noise and atomic waveforms. The activation rate of the atomic waveforms typically possesses a cyclic nature in rotating environments, similar to how bearing kinematic frequencies correlate with faults in a rolling element bearing. However, there is no explicit relationship between the activation rates of the atoms and the bearing kinematic frequencies. This motivates this investigation of the possibility to extract bearing kinematic frequencies from sparse representations. Former work describes the use of dictionary learning for the detection of anomalies in rolling element bearings. In this paper, we describe how a similar unsupervised machine learning method can be used to extract kinematic frequencies of bearings and gears, for example for anomaly detection purposes and comparisons with an expected signature. We study the activation rates and changes of atoms learned from vibration signals in two case studies. The first case is based on data from a well-known controlled experiment with faults seeded in the bearings. The second case is based on a public dataset recorded from the high-speed shaft of a wind turbine with a bearing failure. Furthermore, we compare the activation rates and weights of the atoms to the bearing kinematic frequencies and harmonics. Sparse coding with dictionary learning offers a possibility for self-learningof the kinematic frequencies of a bearing, which can be useful for the further improvement of automated anomaly detection methods in condition monitoring.
|
|
| 9. |
- Martin-del-Campo, Sergio, 1983-, et al.
(författare)
-
Exploratory Analysis of Acoustic Emissions in Steel using Dictionary Learning
- 2016
-
Ingår i: IEEE Ultrasonics Symposium 2016, Tours France, September 18-21, 2016. - Piscataway, NJ : IEEE conference proceedings. - 9781467398978 - 9781467398985
-
Konferensbidrag (refereegranskat)abstract
- Analysis of acoustic emissions (AE) from steel deformation is a challenging condition monitoring problem due to the high frequencies and data rates involved, and the difficulty to separate signals from noise. The problem to characterize and identify different AE sources calls for methods that goes beyond conventional time and frequency domain analysis. Feature learning is common in the field of machine learning and is successfully used to approximate and classify other kinds of complex signals. Former studies show that AE classification results depend on the choice of predefined features that are extracted from the raw AE signal, but little is known about feature learning in this context. Here we use dictionary learning and sparse coding to optimize a set of shift-invariant features to the AE signal measured in a steel tensile strength test. The specimen undergoes elastic and plastic deformation and eventually cracks. We investigate the learned features and their repetition rates and use principal component analysis (PCA) to illustrate that the resulting sparse AE code is useful for classification of the three strain stages, without reference to the signal amplitude. Therefore, feature learning is a potentially useful approach to the AE analysis problem, which also opens up for further studies of automated methods for anomaly detection in AE.
|
|
| 10. |
|
|
