Influence of neural network training parameters on short-term wind forecasting

This paper investigates factors which can affect the accuracy of short-term wind speed prediction when done over long periods spanning different seasons. Two types of neural networks (NNs) are used to forecast power generated via specific horizontal axis wind turbines. Meteorological data used are for a specific Western Australian location. Results reveal that seasonal variations affect the prediction accuracy of the wind resource, but the magnitude of this influence strongly depends on the details of the NN deployed. Factors investigated include the span of the time series needed to initially train the networks, the temporal resolution of these data, the length of training pattern within the overall span which is used to implement the predictions and whether the inclusion of solar irradiance data can appreciably affect wind speed prediction accuracy. There appears to be a relatively complex relationship between these factors and the accuracy of wind speed prediction via NNs. Predicting wind speed based on NNs trained using wind speed and solar irradiance data also increases the prediction accuracy of wind power generated, as can the type of network selected.     

Multi-response optimization of mechanical and comfort properties of bi-stretch woven fabrics using grey relational analysis in Taguchi method

The present paper envisages the multi-response optimization of certain factors like elastane linear density, fabric thread density and weave float on some mechanical, (i.e. stretch %, recovery %) and comfort (i.e. air permeability) properties of bi-stretch woven fabrics, under L₁₈ orthogonal array in Taguchi design. Fabric samples were produced using elastane core-spun cotton yarns both in the warp and weft. The elastane linear density, fabric thread density and weave float size were used as predictor variables, while fabric air permeability, stretch and recovery were taken as response variables. Two different elastane linear densities, i.e. 44 dtex and 78 dtex, 3 different thread densities and 3 different weave designs, i.e. 1/1 plain, 2/2 z-twill and 3/3 z-twill were used. The results have been analysed using grey relational analysis for the identification of an optimum level of process factors. Furthermore, using analysis of variance method, significant contributions of predictor variables were determined.     

The development of novel auxetic woven structure for impact applications

Nowadays, the auxetic materials, auxetic reinforcement as well as auxetic composite are under the great attention of scientific research due to having excellent mechanical properties. In the current research work, the impact resistance of composite was improved by modifying the four layer through the thickness woven structure, that was used as reinforcement. A comparison was made between the standard four layer through the thickness and modified four layer through the thickness woven structure in terms of auxeticity and penetration. The modified four layer through the thickness woven structure showed auxetic behavior in both warp and weft direction having less penetration resistance as compared to standard sample. The four layer through the thickness non-auxetic woven structures and modified auxetic four layer thorough the thickness woven structures were used as reinforcements to develop composite for impact resistance comparison. The result showed that impact resistance of auxetic composite was 6.7% greater as compared to the non-auxetic composite. It was concluded that the greater value of impact resistance was due to the auxetic behavior of modified four layer through the thickness woven structure.     

Influence of powder loading on densification and microstructure of injection molded Fe‐50Ni soft magnetic alloys

Metal injection molding (MIM) is a well‐known technique capable to produce micro size electromagnetic components with intricate shape features. Powder loading is a crucial parameter in the metal injection molding process which controls the densification and microstructure of the sintered parts. The lower powder loading leads to various defects and lower densification whereas higher loading results in failure of parts during injection molding. Therefore, it is important to engineer an appropriate powder loading to achieve defect‐free parts along with higher densification and improved microstructure. In this contest, three feedstocks of Fe‐50Ni alloys are prepared with powder loadings of 52 vol.%, 54 vol.% and 57 vol.% and injection molded. After debinding, the parts are sintered at 1325 °C for 2 h. The main objective of this study is to investigate the effect of powder loading on injection molding, densification, and microstructure. In addition, scanning electron microscopy and x‐ray diffraction analysis are performed during the study. The defect‐free green parts are produced successfully from the 52 % and 54 % loading. It has been found that the optimal powder loading of 54 % is the best from the perspective of enhanced densification and improved microstructure to assure the quality parts of Fe‐50Ni alloys via metal injection molding.     

Herausforderungen & Wichtigkeit der Korrosionsprüfung an automobilen Abgassystemanlagen

Standard corrosion test methods are largely known in the automotive supplier industry and are among the common tests. Different tests, like salt spray testing as well as combined-alternating tests in climatic chambers, are commonly used to evaluate the corrosion behavior of stainless steels. Corrosion effects like uniform and pitting corrosion can be simulated and quantified, and thus base materials can be separated according to their corrosion performance. Still, the correlation to reality and the behavior in the field are still an open question. Respecting the wide range of exhaust applications, especially the influence of temperature, the technical requirements have been greatly increased in the last years and the corrosion effects are difficult to replicate. In addition, the target lifetime for exhaust systems are increasing more and more.Within the scope of a project group at FAURECIA CLEAN MOBILITY, a concept has been developed with the target to combine the common corrosion testing with application oriented component tests. The objective is to cover the time-temperature influence on the corrosion behavior of a component in one test. A testing device has been developed which combines all the technical requirements in one test under elevated temperature influence to make estimations about lifetime, design, and material selections.     

Output Linearization of Single-Input Single-Output Fuzzy System to Improve Accuracy and Performance

For fuzzy systems to be implemented effectively, the fuzzy membership function (MF) is essential. A fuzzy system (FS) that implements precise input and output MFs is presented to enhance the performance and accuracy of single-input single-output (SISO) FSs and introduce the most applicable input and output MFs protocol to linearize the fuzzy system’s output. Utilizing a variety of non-linear techniques, a SISO FS is simulated. The results of FS experiments conducted in comparable conditions are then compared. The simulated results and the results of the experimental setup agree fairly well. The findings of the suggested model demonstrate that the relative error is abated to a sufficient range (≤ ± 10%) and that the mean absolute percentage error (MPAE) is reduced by around 66.2%. The proposed strategy to reduce MAPE using an FS improves the system’s performance and control accuracy. By using the best input and output MFs protocol, the energy and financial efficiency of every SISO FS can be improved with very little tuning of MFs. The proposed fuzzy system performed far better than other modern days approaches available in the literature.     

Investigation of Gate Material Engineering in Junctionless Transistor for Digital and Analog Applications

Silicon - In this paper, we propose dual material gate with dual-k dielectric gate oxide double gate junctionless transistor ‘DMG-DK-JLT’ for significant enhancement of performance. We...