Artificial neural network has been widely used at present to solve many engineering problems. However, simple neural network model is hard to get the desired result. This paper proposes one combined model of AHP (Anal...
详细信息
Artificial neural network has been widely used at present to solve many engineering problems. However, simple neural network model is hard to get the desired result. This paper proposes one combined model of AHP (Analytic Hierarchy Process) and BPNN (Back Propagation Neuron Network) based on data mining. This model can improve the rate of convergence and the reliability of results. The validity of this method has been demonstrated with data from an existing oilfield in north-west China for predicting the rate of penetration (ROP). Furthermore, the model can be used in post-well analysis to identify areas where potential drilling performance was not achieved, and help in identifying improvements for future projects.
This paper deals with the development of feed back controller design for a voltage controlled induction motor drive employing an enhanceda* optimization algorithm derived from the principles of foraging of natural ants....
详细信息
This paper deals with the development of feed back controller design for a voltage controlled induction motor drive employing an enhanceda* optimization algorithm derived from the principles of foraging of natural ants. A linearized incremental model of a voltage controlled induction motor drive is shown to exhibit parameter variation at different operating points of the drive system. A PI-controller derived at a typical operating point using traditional methods does not give satisfactory performance for a wide bandwidth of load and reference speed changes. The newly developed Ant Colony optimization technique enforces continuous exploration of the solution space and identifies optimal controller structure. The development ofa* optimization algorithm and its application to feed back controller design for a variable voltage induction motor drive is well documented in this paper. Experimental and simulation results are presented to validate the efficacy of the optimized controller. (C) 2012 Elsevier B.V. All rights reserved.
A new version of progressive resolution optimizer (PRO) with an option of air cavity correction has been implemented for RapidArc volumetric-modulated arc therapy (RA). The purpose of this study was to compare the per...
详细信息
A new version of progressive resolution optimizer (PRO) with an option of air cavity correction has been implemented for RapidArc volumetric-modulated arc therapy (RA). The purpose of this study was to compare the performance of this new PRO with the use of air cavity correction option (PRO10_air) against the one without the use of the air cavity correction option (PRO10_no-air) for RapidArc planning in targets with low-density media of different sizes and complexities. The performance of PRO10_no-air and PRO10_air was initially compared using single-arc plans created for four different simple heterogeneous phantoms with virtual targets and organs at risk. Multiple-arc planning of 12 real patients having nasopharyngeal carcinomas (NPC) and ten patients having non-small cell lung cancer (NSCLC) were then performed using the above two options for further comparison. Dose calculations were performed using both the Acuros XB (AXB) algorithm with the dose to medium option and the analytical anisotropic algorithm (AAA). The effect of using intermediate dose option after the first optimization cycle in PRO10_air and PRO10_no-air was also investigated and compared. Plans were evaluated and compared using target dose coverage, critical organ sparing, conformity index, and dose homogeneity index. For NSCLC cases or cases for which large volumes of low-density media were present in or adjacent to the target volume, the use of the air cavity correction option in PRO10 was shown to be beneficial. For NPC cases or cases for which small volumes of both low-and high-density media existed in the target volume, the use of air cavity correction in PRO10 did not improve the plan quality. Based on the AXB dose calculation results, the use of PRO10_air could produce up to 18% less coverage to the bony structures of the planning target volumes for NPC cases. When the intermediate dose option in PRO10 was used, there was negligible difference observed in plan quality between optimizations
A numerical solution algorithm has been developed to solve a generalization of Wahba's attitude determination problem in the case of unknown attitude and attitude rate. It provides a robust global solution to nonl...
详细信息
A numerical solution algorithm has been developed to solve a generalization of Wahba's attitude determination problem in the case of unknown attitude and attitude rate. It provides a robust global solution to nonlinear batch attitude and rate estimation problems for spinning spacecraft. The original Wahba problem seeks the attitude that fits a set of unit-normalized direction vector measurements. The generalized problem seeks an initial attitude and rate that, when combined with a torque-free rigid-body attitude dynamics model, tit a time series of direction vector measurements. The new algorithm combines an inner analytic solution for the unknown initial attitude quaternion with an outer numerical solution for the unknown initial rate. The inner problem can be cast in a standard Wahba form, and it is solved in closed form using an adaptation of the q method. The outer problem relies on a trust-region implementation of Newton's method to ensure global convergence. The global solution is determined by re-solving starting from a random set of first guesses of the attitude rate that cover the space of nonaliasing rates. Tests on truth-model simulation data for minor-axis and major-axis spinning spacecraft confirm the new algorithm's ability to achieve global convergence and its estimation accuracy's consistency with its computed estimation error covariance matrix.
Advances in autonomy have made it possible to invert the typical operator-to-unmanned-vehicle ratio so that a single operator can now control multiple heterogeneous unmanned vehicles. algorithms used in unmanned-vehic...
详细信息
Advances in autonomy have made it possible to invert the typical operator-to-unmanned-vehicle ratio so that a single operator can now control multiple heterogeneous unmanned vehicles. algorithms used in unmanned-vehicle path planning and task allocation typically have an objective function that only takes into account variables initially identified by designers with set weightings. This can make the algorithm seemingly opaque to an operator and brittle under changing mission priorities. To address these issues, it is proposed that allowing operators to dynamically modify objective function weightings of an automated planner during a mission can have performance benefits. A multiple-unmanned-vehicle simulation test bed was modified so that operators could either choose one variable or choose any combination of equally weighted variables for the automated planner to use in evaluating mission plans. Results from a human-participant experiment showed that operators rated their performance and confidence highest when using the dynamic objective function with multiple objectives. Allowing operators to adjust multiple objectives resulted in enhanced situational awareness, increased spare mental capacity, fewer interventions to modify the objective function, and no significant differences in mission performance. Adding this form of flexibility and transparency to automation in future unmanned vehicle systems could improve performance, engender operator trust, and reduce errors.
In this study, we developed the Allometric Scaling and Resource Limitations (ASRL) model by using the best GLAS tree heights to optimize the ASRL. At first, we obtained the best metric of GLAS tree heights by comparin...
详细信息
ISBN:
(纸本)9781467311595
In this study, we developed the Allometric Scaling and Resource Limitations (ASRL) model by using the best GLAS tree heights to optimize the ASRL. At first, we obtained the best metric of GLAS tree heights by comparing with LVIS tree heights in six sites. Then, the best metric GLAS tree heights were separately used to optimize ASRL model and test the accuracy of prediction heights from optimized ASRL model in sites scale and country scale. Validation result showed that predicted tree heights from optimized ASRL model had high accuracy.
Spatial information of crop area statistics is of great significance for study of global change, population, resources, environment, ecology and food security. In this paper, based on MODIS NDVI time series data and g...
详细信息
ISBN:
(纸本)9781467324946
Spatial information of crop area statistics is of great significance for study of global change, population, resources, environment, ecology and food security. In this paper, based on MODIS NDVI time series data and globala* optimization algorithm SCE-UA (Shuffled Complex Evolution-University of Arizona), the research of spatialization of crop area statistical data was carried out in 13 counties which were located in Shijiazhuang City of Huanghuaihai Plain. The research crop was winter wheat. At last, the accuracy of the result of spatialization of crop area statistical data crop was validated. The final results showed that the regional accuracy of optimal winter wheat distribution map was 99.71% and pixel accuracy kappa coefficient was 0.898. It proved that the method of spatialization of crop area statistical data using the NDVI time-series data and globala* optimization algorithm SCE-UA was reasonable and feasible. The spatial crop map with higher accuracy could be gotten using this method which was more significant to solve the spatialization of crop area statistical data.
Computational optimization is becoming a standard tool that is widely used in engineering design and industrial applications. Products and services are often concerned with the maximization of profits and reduction of...
详细信息
Computational optimization is becoming a standard tool that is widely used in engineering design and industrial applications. Products and services are often concerned with the maximization of profits and reduction of cost, but also aim at being more energy-efficient, environment-friendly and safety-ensured; at the same time they are limited by resources, time and money. Despite of increasing computer power and availability of better simulation packages, there are a number of challenges remaining when applying numerical optimization methods for real-world engineering problems. Also, new challenges emerge when attempting to attack problems whose solution by means of simulation-based optimization was not even possible in the past. This third workshop on Computational optimization, Modelling and Simulation (COMS 2012) at ICCS 2012 will further summarize the latest developments of optimization and modelling and their applications in science, engineering and industry.
Currently, when calculating the magnetic field generated by the solenoid coil of the superconducting wire wound, we assume that the coil cross section with a uniform current density, but actual current in superconduct...
详细信息
Currently, when calculating the magnetic field generated by the solenoid coil of the superconducting wire wound, we assume that the coil cross section with a uniform current density, but actual current in superconducting wires (NbTi) in the form of a wire in channel is not evenly distributed, the current distribution only in the superconducting core, i.e., there is no current in copper, insulation, and filler, and this method of calculation will result in errors. In this paper, we model the superconducting cores of the 1.5-T superconducting magnetic resonance imaging (MRI) magnet to calculate accurate magnetic field intensity and inhomogeneity by helicoidal method in the diameter of spherical volume and find that inhomogeneity is eight times bigger than that calculated by spherical harmonic expansions, which cannot be accepted in design. Hence, in order to design a high-homogeneity MRI magnet, we amend the 1.5-T MRI magnet's original parameters by ana* optimization algorithm through an original interface between OPERA-3D and MATLAB according to the accurate results.
Design for assembly (DFA) has proved its success in manufacturing to face the market challenge. But the assembly process parameters were rarely concerned in the design for assembly. Aimed at this problem, an algorithm...
详细信息
ISBN:
(纸本)9780878494705
Design for assembly (DFA) has proved its success in manufacturing to face the market challenge. But the assembly process parameters were rarely concerned in the design for assembly. Aimed at this problem, an algorithm for design for automated assembly of circular parts was proposed. This algorithm can help designer to select the optimal process parameters, such as dimension tolerance of mating parts, location precision of assembly device and so on, subject to budgetary constraints. Finally a case is employed to explain the optimal course.
暂无评论