A Deep-Learning-Based Bearing Fault Diagnosis Using Defect Signature Wavelet Image Visualization

A new method is established to construct the 2-D fault diagnosis representation of multiple bearing defects from 1-D acoustic emission signals. This technique starts by applying envelope analysis to extract the envelope signal. A novel strategy is propounded for the deployment of the continuous wavelet transform with damage frequency band information to generate the defect signature wavelet image (DSWI), which describes the acoustic emission signal in time-frequency-domain, reduces the nonstationary effect in the signal, shows discriminate pattern visualization for different types of faults, and associates with the defect signature of bearing faults. Using the resultant DSWI, the deep convolution neural network (DCNN) architecture is designed to identify the fault in the bearing. To evaluate the proposed algorithm, the performance of this technique is scrutinized by a series of experimental tests acquired from a self-designed testbed and corresponding to different bearing conditions. The performance from the experimental dataset demonstrates that the suggested methodology outperforms conventional approaches in terms of classification accuracy. The result of combining the DCNN with DSWI input yields an accuracy of 98.79% for classifying multiple bearing defects.

SPARQLGPViz: SPARQL Graph Pattern Visualization

We present SPARQLGPViz, a tool to visualize graph pat-terns in a SPARQL Query. The initial implementation of this tool dis-plays exemplary SPARQL query using visual representation to identifythe variables and their relationship for didactic purposes (i.e. teachinghow to query using SPARQL).

Visualization of path patterns in semantic graphs

Graphs with a large number of nodes and edges are difficult to visualize. Semantic graphs add to the challenge since their nodes and edges have types and this information must be mirrored in the visualization. A common approach to cope with this difficulty is to omit certain nodes and edges, displaying sub-graphs of smaller size. However, other transformations can be used to summarize semantic graphs and this research explores a particular one, both to reduce the graph?s size and to focus on its path patterns. A-graphs are a novel kind of graph designed to highlight path patterns using this kind of summarization. They are composed of a-nodes connected by a-edges, and these reflect respectively edges and nodes of the semantic graph. A-graphs trade the visualization of nodes and edges by the visualization of graph path patterns involving typed edges. Thus, they are targeted to users that require a deep understanding of the semantic graph it represents, in particular of its path patterns, rather than to users wanting to browse the semantic graph?s content. A-graphs help programmers querying the semantic graph or designers of semantic measures interested in using it as a semantic proxy. Hence, a-graphs are not expected to compete with other forms of semantic graph visualization but rather to be used as a complementary tool. This paper provides a precise definition both of a-graphs and of the mapping of semantic graphs into a-graphs. Their visualization is obtained with a-graphs diagrams. A web application to visualize and interact with these diagrams was implemented to validate the proposed approach. Diagrams of well-known semantic graphs are presented to illustrate the use of agraphs for discovering path patterns in different settings, such as the visualization of massive semantic graphs, the codification of SPARQL or the definition of semantic measures. The validation with large semantic graphs is the basis for a discussion on the insights provided by a-graphs on large semantic graphs: the difference between a-graphs and ontologies, path pattern visualization using a-graphs and the challenges posed by large semantic graphs.

Influence of Particle on Gas Detonation by Shock

There exist evidence, that the gaseous detonation passing through a cloud of solid particles could be attenuated or even suppressed. Contrary to these known works, in the present article, we have found that just one single 160-micron particle can serve as a trigger for the detonation onset. By numerical simulation, we have obtained that there are the concentration ratio limits, in which single particle is enough to initiate gaseous detonation, although without particle the detonation is not ignited in the same conditions in a tube of restricted size. In other words, the presence of a solid particle in the combustible mixture could decrease significantly the ignition delay time. Using of temperature pattern visualization, we have demonstrated that the ignition arises in the subsonic region located between the particle and the bow shock front. The approximations of the used model are discussed. It is shown that used assumptions are valid within investigated time intervals. The work performed with use of the supercomputer resources Interdepartmental Supercomputer Center Russian Academy of Sciences (ISC RAS)