Combination of probability approach and support vector machine towards machine health prognostics

This study presents a combined method of the probability approach and support vector machine (SVM) to predict failure degradation based on simulated and experimental failure bearing data. The failure rate as a degradation parameter is calculated using the Cox-proportional hazard model and the reliability theory based on simulated and experimental data. Kurtosis is used to show the bearing condition under specified operating conditions up to final failure occurrence. For simulated data, a failure degradation is calculated using the Cox model, where the baseline hazard is assumed having Weibull probability. In the case of experimental data, a reliability formula is employed to estimate the failure degradation of the bearing based on run-to-failure datasets. Both failure degradations are regarded as target vectors which indicate the bearing health to failure condition. Moreover, an SVM is employed as an artificial intelligence prognostics method and trained by kurtosis and the target vector to build the prediction model. The trained SVM is then utilized to predict the final failure time of individual bearing data. The result shows that the proposed method has the potential to be a machine health prognostics framework.     

Optimization of SC–CO2 extraction of zerumbone from Zingiber zerumbet (L) Smith

Response surface methodology (RSM) was applied to optimize the variables affecting the Supercritical carbon dioxide (SC–CO₂) extraction of non-polar compounds from Zingiber zerumbet using the Box-Behnken design (BBD). Dependent variables were the percentage of the chemical components in the ginger vis a vis α-caryophyllene (y₁), camphene (y₂), and zerumbone (2,6,10-cycloundecatrien-1-one, 2,6,9,9-tetramethyl-) (y₃). Pressure was the most significant parameter affecting the amount of each compound extracted. When temperature was kept constant and pressure was increased, all of the dependent variables increased concomitantly. Since pressure and temperature are two of the major influential factors in the extraction using SC–CO₂, any combination of these two parameters could be selected to ascertain the optimum combination for a particular compound in the extract. Extraction at 30 °C and 55 MPa with total amount of 30 g of CO₂ used was found to maximize all the responses.     

Dynamic Characteristics and Effective Stiffness Properties of Honeycomb Composite Sandwich Structures for Highway Bridge Applications

In this paper, a combined analytical and experimental study of dynamic characteristics of honeycomb composite sandwich structures in bridge systems is presented, and a relatively simple and reliable dynamic experimental procedure to estimate the beam bending and transverse shear stiffness is proposed. This procedure is especially practicable for estimating the beam transverse shear stiffness, which is primarily contributed by the core and is usually difficult to measure. The composite sandwich beams are made of E-glass fiber and polyester resins, and the core consists of the corrugated cells in a sinusoidal configuration. Based on the modeling of equivalent properties for the face laminates and core elements, analytical predictions of effective flexural and transverse shear stiffness properties of sandwich beams along the longitudinal and transverse to the sinusoidal core wave directions are first obtained. Using piezoelectric sensors, the dynamic response data are collected, and the dynamic characteristics of the sandwich structures are analyzed, from which the flexural and transverse shear stiffness properties are reduced. The experimental stiffness results are then compared to the analytical stiffness properties, and relatively good correlations are obtained. The proposed dynamic tests using piezoelectric sensors can be used effectively to evaluate the dynamic characteristics and stiffness properties of large sandwich structures suitable for highway bridge applications.     

The 10 years operation of a PV-micro-hydro hybrid system in Taratak, Indonesia

A 48–71.1 kWp photovoltaic-micro-hydro system has been installed at Taratak, Indonesia since June 10, 1989. The system is being developed in Indonesia to obtain optimal result by combining the advantages of both energy conversion systems. The photovoltaic works as a dominant part in this hybrid system. However, the micro-hydro sub-system works to compensate the inconvenience found in the photovoltaic. It will anticipate the weather uncertainty and fulfill the need during the peak load. In this paper we analyze and evaluate the performance of a PV-micro-hydro (PV-MH) system in Taratak. We find the difference between the initial design and the actual system operation. Results of the evaluation show that the performance of PV-MH system operation is still optimal.