Search

Background: Anti-Inflammatory Peptides (AIPs) are potent therapeutic agents for inflammatory and autoimmune disorders due to their high specificity and minimal toxicity under normal conditions. Therefore, it is greatly significant and beneficial to identify AIPs for further discovering novel and efficient AIPs-based therapeutics. Recently, three computational approaches, which can effectively identify potential AIPs, have been developed based on machine learning algorithms. However, there are several challenges with the existing three predictors. Objective: A novel machine learning algorithm needs to be proposed to improve the AIPs prediction accuracy. Methods: This study attempts to improve the recognition of AIPs by employing multiple primary sequence-based feature descriptors and an efficient feature selection strategy. By sorting features through four enhanced minimal redundancy maximal relevance (emRMR) methods, and then attaching seven different classifiers wrapper methods based on the sequential forward selection algorithm (SFS), we proposed a hybrid feature selection technique emRMR-SFS to optimize feature vectors. Furthermore, by evaluating seven classifiers trained with the optimal feature subset, we developed the Extremely Randomized Tree (ERT) based predictor named PREDAIP for identifying AIPs. Results: We systematically compared the performance of PREDAIP with the existing tools on independent test dataset. It demonstrates the effectiveness and power of the PREDAIP. Conclusion: The correlation criteria used in emRMR would affect the selection results of the optimal feature subset at the SFS-wrapper stage, which justifies the necessity for considering different correlation criteria in emRMR.

An engineering thermodynamic model has been developed to study the phenomena that large discrepancies found among the different temperature sensors monitoring the exhaust of the gas turbine designed for syngas. The mathematical model utilized large amounts of industrial operation data at different typical power loads for validation and good agreements were found between the measured and calculated exhaust temperature using input boundary conditions not in the training sets. The reason for the large temperature discrepancies of exhaust corresponding to different combustion chambers has been attributed to the deviation between the flow rates of the compressed air from single compressor to different combustion chambers through analysis with the mathematic model. Finally, a method to reduce the temperature discrepancies has been proposed with the mathematic model using industrial operation data from various power loads. The proposed method can quickly calculate the required syngas flow rates to different combustion chambers based on measured differences of exhaust temperatures. The scheme of varying syngas flow rates to different combustion chambers according to the proposed method has been verified by simulation. The impacts to the stability of combustion and NOx emission by the scheme of varying syngas flow rates to different combustion chambers according to the proposed method have also been studied via computational fluid dynamics (CFD) simulations and found that there is little impact on the stability of combustion and it may lead to slightly lower NOx emission for all power loads.

Integrated Gasification Combined Cycle (IGCC) combines gasifier, gas turbine, and steam turbine to increase the electricity production efficiency while having lower emissions compared to conventional coal fired power plants. The syngas produced from coal gasification differs from natural gas in terms of composition, heating value, as well as combustion characteristics. Typically, syngas has much lower heating value than natural gas, thus the flow rates of the syngas are higher than that of natural gas for a similar size gas turbine. In addition, the hydrogen in the syngas may lead to more rapid combustion and higher flame temperature compared to natural gas, which may result it more NOx emission. Thus, to address these issues, syngas could be diluted with nitrogen, steam or carbon dioxides to lower the flame speed and temperature. The effects of different diluents on the fuel economy and emissions are investigated by a combined thermodynamic and computational fluid dynamics (CFD) model. The thermodynamic model was first established and validated by the industrial operational data. More power output and better fuel economy can be achieved using N2 and CO2 as diluent instead of steam from calculation with the thermodynamic model. A numerical case study was done to estimate the profit using nitrogen instead of the steam considering in industrial operation conditions as well as all other costs. Next, the CFD model was employed to further examine the combustion stability and NOx emissions. The results show that changing diluent from steam to nitrogen will not impact the combustion stability and may lead to slightly lower NOx emissions. Finally, the partial replacement of steam by nitrogen as diluent has been realized and the industrial operational performance has also been reported.

Integrated Gasification Combined Cycle (IGCC) is a technology that integrates the coal gasification and combined cycle to produce electricity efficiently. Due to the fact that the heating value of syngas from coal gasification process is typically lower than that of the natural gas, the conventional gas turbine will have to be adapted for syngas. The nozzle adjustment is the key to the successful transformation since the ignition properties are different between syngas and natural gas which have totally different compositions. The nozzles suitable for natural gas have been prone to partially melting around the flame stabilization holes on sidewalls of the nozzle in real operation. Thus a computational fluid dynamics (CFD) model was constructed for the syngas nozzles as well as combustion chamber of the gas turbine for low heating value syngas to study the thermostability of the nozzle. The detailed structure of the syngas nozzle, the combustion characteristics of syngas, as well as the actual operation condition of the gas turbine were all employed in the CFD model to improve the simulation accuracy. The reason of partially melting of the nozzles suitable for natural gas can be attributed to that the syngas leaked from the flame stabilization holes into the mainstream air can quickly mix with air, adhere to the sidewalls of the nozzles and then ignite around the holes which result in temperatures high enough to melt the material of the nozzle around the holes through CFD simulation. Finally, a new structure of the syngas nozzle was proposed and validated by CFD simulations. The simulation result shows that the flames caused by the syngas leaked from the flame stabilization holes are no longer adhering to the nozzle sidewalls and local high temperature can be lowered by about 30% which will not be able to melt the nozzle material.