Modeling the Output Power of Direct Methanol Fuel Cells Using SVR

The output power of Direct Methanol Fuel Cells (DMFC) is one of the most important elements which limit the performance of DMFC. In order to enhance performance of DMFC, it is necessary to have model to modeling the output power of DMFC. In this paper, a novel model base on Support Vector Regression (SVR) to modeling the output power of DMFC base on output current (I) and operating temperature (T). The test result is shown that the generalization ability of SVR model is high accuracy. This investigation suggests that SVR is quite satisfied used to developing a DMFC model and can be used for controlling, optimal designing and feasibility study of the DMFC system.

Ventilation Prediction for an Industrial Cement Raw Ball Mill by BNN—A “Conscious Lab” Approach

In cement mills, ventilation is a critical key for maintaining temperature and material transportation. However, relationships between operational variables and ventilation factors for an industrial cement ball mill were not addressed until today. This investigation is going to fill this gap based on a newly developed concept named “conscious laboratory (CL)”. For constructing the CL, a boosted neural network (BNN), as a recently developed comprehensive artificial intelligence model, was applied through over 35 different variables, with more than 2000 records monitored for an industrial cement ball mill. BNN could assess multivariable nonlinear relationships among this vast dataset, and indicated mill outlet pressure and the ampere of the separator fan had the highest rank for the ventilation prediction. BNN could accurately model ventilation factors based on the operational variables with a root mean square error (RMSE) of 0.6. BNN showed a lower error than other traditional machine learning models (RMSE: random forest 0.71, support vector regression: 0.76). Since improving the milling efficiency has an essential role in machine development and energy utilization, these results can open a new window to the optimal designing of comminution units for the material technologies.

Pulp pumping efficiency II – Designing of a pulp pump

Based on the loss model of pulp pump set up in the I part of this research, an efficient designing method is proposed by taking account of the influences of head reduction by small blade number, leakage loss via tip clearance, and erosion-corrosion wears in pumps separately. Further, a two-stage optimal designing approach was proposed to tackle the oversized design. The pump designing was performed by coupling with a CFD-based optimization procedure. An efficiency increase of near 10 % was achieved on the pump model validated in laboratory. It was proved that performance could be improved by increasing the impeller blade width and enlarging the impeller blade outlet angle. It was further shown that the erosion-corrosion wear in pulp pump was relatively lighter when compared to particle-impingement wear in slurry and sewage pump. Adoption of composite material showed potential in energy-saving in the pumping system.

Performance Analysis of Gough Stewart Platform with 6 Limbs

This paper concentrates on widespread study of parallel manipulator. It focuses on optimal designing of manipulator which has a large number of application fields. Optimal design is an important criterion to improve the accuracy of a robot. Through optimal design a robot can achieve isotropic configurations where the condition number of its jacobian matrix equals one. In this we are also concentrating on transmission index and stiffness index along with their plots, which can affect the kinetostatic performance of the robot. In this the singularity of Gough Stewart platform is also studied.