Laser generated metal droplets are basis for many novel production technolgies. Knowing the dynamics of droplet generation is crucial for its optimization and control. The process dynamics is described by time series extracted out of high-speed infrared camera records of the wire end and the pendant droplets. By nonlinear time series analysis, the process was tested against determinism, stationarity and chaotic properties. Positive largest Lyapunov exponent and a negative sum of Lyapunov spectra, indicate that the process dynamics is chaotic with an attractor as solution in the phase space.
COBISS.SI-ID: 14076182
Specimens of AISI 304 stainless steel were subjected to stress corosion test. Intergranular stress-corrosion cracking was monitored simultaneously for electrochemical noise (EN), acoustic emission (AE), and specimen elongation. A section of the gauge length was monitored optically with subsequent analysis of craks digital image. Correlations between the results were observed and analysed. Based on EN, elongation and corelation analysis of cracks digital images, crack propagation from its early stages is possible to detect, whereas AE is associated with the final stages of fracture.
COBISS.SI-ID: 1618535
A method for forecasting lead times of production orders is proposed. The method is based on analysis and statistical evaluation of past lead time data. The result of the proposed procedure is an empirical distribution of possible lead times for a production order. Based on this distribution, it is possible to forecast the most probable lead time of a particular production order, taking into account a confidence interval. Using the proposed procedure, the sales department can make a delivery time forecast for the customer of the planned production order.
COBISS.SI-ID: 11657243
Natural gas consumption forecasting is required to balance the supply and consumption of natural gas. In this chapter, some practical forecasting results for the Slovenia natural gas market are presented. In 2007, an online forecasting system was developed and installed for a larger gas distributing company in Slovenia. The chapter presents the development of the forecasting models for both daily and hourly forecasting and summarizes the practical forecasting results, obtained during the last three years of online operation (winter seasons 2007/2008, 2008/2009, and 2009/2010).
COBISS.SI-ID: 11644955
There is an ever-increasing need for automated solutions to organize the huge amount of digital texts. Ensemble systems are becoming an important resource, since they permit the use of simpler classifiers and the integration of different knowledge in the learning process. Many state-of-the-art classifiers, such as kernel-based ones (SVM, RVM), demand large resources. A new distributed framework on the basis of computing clusters is presented. It employs a combination of both task and data decomposition. Experimental results show that performance of the framework outperforms standard methods.
COBISS.SI-ID: 7683668