Modern automotive petrol engine performance is significantly affected by effective tune-up. Current practice of engine tune-up relies on the experience of the automotive engineer, and tune-up is usually done by trial-...Modern automotive petrol engine performance is significantly affected by effective tune-up. Current practice of engine tune-up relies on the experience of the automotive engineer, and tune-up is usually done by trial-and-error method and then the vehicle engine is run on the dynamometer to show the actual engine performance. Obviously the current practice involves a large amount of time and money, and then may even fail to tune up the engine optimally because a formal performance model of the engine has not been determined yet. With an emerging technique, Support Vector Machines (SVM), the approximate per- formance model of a petrol vehicle engine can be determined by training the sample engine performance data acquired from the dynamometer. The number of dynamometer tests for an engine tune-up can therefore be reduced because the estimated engine performance model can replace the dynamometer tests to a certain extent. In this paper, the construction, validation and accuracy of the model are discussed. The study showed that the predicted results agree well with the actual test results. To illustrate the significance of the SVM methodology, the results were also compared with that regressed using multilayer feedforward neural networks.展开更多
Electrical discharge machining (EDM) process, at present is still an experience process, wherein selected parameters are often far from the optimum, and at the same time selecting optimization parameters is costly and...Electrical discharge machining (EDM) process, at present is still an experience process, wherein selected parameters are often far from the optimum, and at the same time selecting optimization parameters is costly and time consuming. In this paper, artificial neural network (ANN) and genetic algorithm (GA) are used together to establish the parameter optimization model. An ANN model which adapts Levenberg-Marquardt algorithm has been set up to represent the relationship between material removal rate (MRR) and input parameters, and GA is used to optimize parameters, so that optimization results are obtained. The model is shown to be effective, and MRR is improved using optimized machining parameters.展开更多
This paper has analyzed merits and demerits of both neural network technique and of the information fusion methods based on the D-S (dempster-shafer evidence) Theory as well as their complementarity, proposed the hier...This paper has analyzed merits and demerits of both neural network technique and of the information fusion methods based on the D-S (dempster-shafer evidence) Theory as well as their complementarity, proposed the hierarchical information fusion fault diagnosis strategy by combining the neural network technique and the fused decision diagnosis based on D-S Theory, and established a corresponding functional model. Thus, we can not only solve a series of problems caused by rapid growth in size and complexity of neural network structure with diagnosis parameters increasing, but also can provide effective method for basic probability assignment in D-S Theory. The application of the strategy to diagnosing faults of motor bearings has proved that this method is of fairly high accuracy and reliability in fault diagnosis.展开更多
The development of offshore wind farms was originally carried out in shallow water areas with fixed （seabed mounted） structures. However, countries with limited shallow water areas require innovative floating platfo...The development of offshore wind farms was originally carried out in shallow water areas with fixed （seabed mounted） structures. However, countries with limited shallow water areas require innovative floating platforms to deploy wind turbines offshore in order to harness wind energy to generate electricity in deep seas. The performances of motion and mooring system dynamics are vital to designing a cost effective and durable floating platform. This paper describes a numerical model to simulate dynamic behavior of a new semi-submersible type floating offshore wind turbine （FOWT） system. The wind turbine was modeled as a wind block with a certain thrust coefficient, and the hydrodynamics and mooting system dynamics of the platform were calculated by SESAM soRware. The effect of change in environmental conditions on the dynamic response of the system under wave and wind loading was examined. The results indicate that the semi-submersible concept has excellent performance and SESAM could be an effective tool for floating wind turbine design and analysis.展开更多
One of the key features of Laplace＇s Equation is the property that allows the equation governing the flow field to be converted from a 3D problem throughout the field to a 2D problem for finding the potential on the ...One of the key features of Laplace＇s Equation is the property that allows the equation governing the flow field to be converted from a 3D problem throughout the field to a 2D problem for finding the potential on the surface. The solution is then found using this property by distributing ＂singularities＂ of unknown strength over discretized portions of the surface： panels. Hence the flow field solution is found by representing the surface by a number of panels, and solving a linear set of algebraic equations to determine the unknown strengths of the singularities. In this paper a Hess-Smith Panel Method is then used to examine the aerodynamics of NACA 4412 and NACA 23015 wind turbine airfoils. The lift coefficient and the pressure distribution are predicted and compared with experimental result for low Reynolds number. Results show a good agreement with experimental data.展开更多
The performance of the power assist, global optimization solved by dynamic programming （DP） method, Chery and Insight control strategies are analyzed using the mild parallel hybrid electric vehicle （PHEV） model ba...The performance of the power assist, global optimization solved by dynamic programming （DP） method, Chery and Insight control strategies are analyzed using the mild parallel hybrid electric vehicle （PHEV） model based on Insight structure. The influence of the four control strategies to the load power of the electric motor system used on parallel hybrid electric vehicle is studied. It is found that 80 percent of the motor load power points are under 1/5 of the electric peak power. The motor load power of the power assist control strategy is distributed in the widest range during generating operation, and the motor load power of the global optimization control strategy has the smallest one.展开更多
文摘Modern automotive petrol engine performance is significantly affected by effective tune-up. Current practice of engine tune-up relies on the experience of the automotive engineer, and tune-up is usually done by trial-and-error method and then the vehicle engine is run on the dynamometer to show the actual engine performance. Obviously the current practice involves a large amount of time and money, and then may even fail to tune up the engine optimally because a formal performance model of the engine has not been determined yet. With an emerging technique, Support Vector Machines (SVM), the approximate per- formance model of a petrol vehicle engine can be determined by training the sample engine performance data acquired from the dynamometer. The number of dynamometer tests for an engine tune-up can therefore be reduced because the estimated engine performance model can replace the dynamometer tests to a certain extent. In this paper, the construction, validation and accuracy of the model are discussed. The study showed that the predicted results agree well with the actual test results. To illustrate the significance of the SVM methodology, the results were also compared with that regressed using multilayer feedforward neural networks.
基金Project supported by the National Natural Science Foundation of China (Nos. 50575128 and 50775128)the Outstanding Young Scientist Foundation of Shandong Province (No. 2005BS05004), China
文摘Electrical discharge machining (EDM) process, at present is still an experience process, wherein selected parameters are often far from the optimum, and at the same time selecting optimization parameters is costly and time consuming. In this paper, artificial neural network (ANN) and genetic algorithm (GA) are used together to establish the parameter optimization model. An ANN model which adapts Levenberg-Marquardt algorithm has been set up to represent the relationship between material removal rate (MRR) and input parameters, and GA is used to optimize parameters, so that optimization results are obtained. The model is shown to be effective, and MRR is improved using optimized machining parameters.
文摘This paper has analyzed merits and demerits of both neural network technique and of the information fusion methods based on the D-S (dempster-shafer evidence) Theory as well as their complementarity, proposed the hierarchical information fusion fault diagnosis strategy by combining the neural network technique and the fused decision diagnosis based on D-S Theory, and established a corresponding functional model. Thus, we can not only solve a series of problems caused by rapid growth in size and complexity of neural network structure with diagnosis parameters increasing, but also can provide effective method for basic probability assignment in D-S Theory. The application of the strategy to diagnosing faults of motor bearings has proved that this method is of fairly high accuracy and reliability in fault diagnosis.
基金Foundation item： Supported by the 111 Project under Grant No.B07019, and the National Natural Science Foundation of China under Grant No.50979020.
文摘The development of offshore wind farms was originally carried out in shallow water areas with fixed （seabed mounted） structures. However, countries with limited shallow water areas require innovative floating platforms to deploy wind turbines offshore in order to harness wind energy to generate electricity in deep seas. The performances of motion and mooring system dynamics are vital to designing a cost effective and durable floating platform. This paper describes a numerical model to simulate dynamic behavior of a new semi-submersible type floating offshore wind turbine （FOWT） system. The wind turbine was modeled as a wind block with a certain thrust coefficient, and the hydrodynamics and mooting system dynamics of the platform were calculated by SESAM soRware. The effect of change in environmental conditions on the dynamic response of the system under wave and wind loading was examined. The results indicate that the semi-submersible concept has excellent performance and SESAM could be an effective tool for floating wind turbine design and analysis.
文摘One of the key features of Laplace＇s Equation is the property that allows the equation governing the flow field to be converted from a 3D problem throughout the field to a 2D problem for finding the potential on the surface. The solution is then found using this property by distributing ＂singularities＂ of unknown strength over discretized portions of the surface： panels. Hence the flow field solution is found by representing the surface by a number of panels, and solving a linear set of algebraic equations to determine the unknown strengths of the singularities. In this paper a Hess-Smith Panel Method is then used to examine the aerodynamics of NACA 4412 and NACA 23015 wind turbine airfoils. The lift coefficient and the pressure distribution are predicted and compared with experimental result for low Reynolds number. Results show a good agreement with experimental data.
文摘The performance of the power assist, global optimization solved by dynamic programming （DP） method, Chery and Insight control strategies are analyzed using the mild parallel hybrid electric vehicle （PHEV） model based on Insight structure. The influence of the four control strategies to the load power of the electric motor system used on parallel hybrid electric vehicle is studied. It is found that 80 percent of the motor load power points are under 1/5 of the electric peak power. The motor load power of the power assist control strategy is distributed in the widest range during generating operation, and the motor load power of the global optimization control strategy has the smallest one.
