Detecting Multidimensional Pareto Fronts during the Optimization of a Return Channel within a Centrifugal Compressor

2021 ◽  
pp. 1-24
Author(s):  
Jan Bisping ◽  
Peter Jeschke
Keyword(s):  
Big Data ◽  
Numerical Optimization ◽  
Pareto Front ◽  
Three Dimensional ◽  
Design Guidelines ◽  
Optimized Design ◽  
Performance Potential ◽  
Reference Design ◽  
Return Channel ◽  
Pareto Fronts

Abstract This paper explains the advantages of using big-data methods for evaluating numerical optimization. The investigation focuses on the performance potential of three-dimensional return channel vanes under realistic manufacturing constraints. Based on an analysis of an optimization database, the paper presents a systematic approach for analysis and setting up design guidelines. To this end, a validated numerical setup was developed on the basis of experiments, followed by a numerical optimization using genetic algorithms and artificial neural networks. The optimization database was analyzed with a dimension reduction method called t-SNE. This method enabled linking geometric design features with physical correlations and, finally, with the objective functions of the optimization. With the help of the detected correlations within the database, it has been possible to work out a method for deciding on the selection of a design on the Pareto front and to draw new relevant conclusions. The systematic use of big-data methods proposed enables a more penetrating insight to be gained into numerical optimization, which is more general and relevant than those gained by simply comparing a single optimized design with a reference design. An analysis of the Pareto front reveals that 0.6% efficiency can be exchanged for 20% more homogeneous outflow. The design of the vane profiles at hub and shroud works best using a front-loaded design for the hub side and an aft-loaded design for the shroud side, since this minimizes the blade-to-blade pressure gradient and, in turn, the secondary flow.

Extension of the Stator Vane Upstream Across the 180° Bend for a Multistage Radial Compressor Stage

2009 ◽  
Author(s):  
Christian Aalburg ◽  
Alexander Simpson ◽  
Jorge Carretero ◽  
Tue Nguyen ◽  
Vittorio Michelassi
Keyword(s):  
Three Dimensional ◽  
Design Procedure ◽  
Design Parameters ◽  
Optimized Design ◽  
Angle Distribution ◽  
Conventional Design ◽  
Stator Vane ◽  
Limited Applicability ◽  
Return Channel ◽  
Vane Angle

The design, analysis and optimization of a new stator concept for multistage centrifugal compressors using numerical methods is presented. The first objective was to further improve the performance of a well-optimized stage with a short vaneless diffuser, see Aalburg et al [1]. The second objective was to achieve a significant increase in the flow turning in the stator part. In order to achieve these goals an extension of the return channel vane upstream, over the U-turn bend, was considered. This design poses challenges that are quite different from those encountered for a conventional design. For example, a conventional vane angle distribution leads to lean angles across the bend that are not feasible from a manufacturing and aerodynamic perspective. In addition, conventional design tools for geometry generation were found to have limited applicability for this concept. To address these issues a geometry generator was developed that facilitated the design of three-dimensional across-the-bend type vanes with unconventional vane angle distributions. The geometry generator was based on an analytical design procedure similar to that outlined by Veress and Braembussche [2]. This procedure allows a desired loading distribution to be specified. In this paper the vane concept will be introduced, the development of the geometry generator will be outlined and the effect of varying design parameters will be considered. An optimized design will then be presented that outperformed the reference conventional design in terms of efficiency by up to one point across the operating range. This improvement was achieved despite a significantly higher vane loading.

Research on the university intelligent learning analysis system based on AI

2021 ◽  
pp. 1-10
Author(s):  
Meng Huang ◽  
Shuai Liu ◽  
Yahao Zhang ◽  
Kewei Cui ◽  
Yana Wen
Keyword(s):  
Artificial Intelligence ◽  
Big Data ◽  
Academic Performance ◽  
Clustering Algorithm ◽  
Back Propagation ◽  
Three Dimensional ◽  
Training Model ◽  
Future Trend ◽  
Artificial Intelligence Technology ◽  
Visualization Technology

The integration of Artificial Intelligence technology and school education had become a future trend, and became an important driving force for the development of education. With the advent of the era of big data, although the relationship between students’ learning status data was closer to nonlinear relationship, combined with the application analysis of artificial intelligence technology, it could be found that students’ living habits were closely related to their academic performance. In this paper, through the investigation and analysis of the living habits and learning conditions of more than 2000 students in the past 10 grades in Information College of Institute of Disaster Prevention, we used the hierarchical clustering algorithm to classify the nearly 180000 records collected, and used the big data visualization technology of Echarts + iView + GIS and the JavaScript development method to dynamically display the students’ life track and learning information based on the map, then apply Three Dimensional ArcGIS for JS API technology showed the network infrastructure of the campus. Finally, a training model was established based on the historical learning achievements, life trajectory, graduates’ salary, school infrastructure and other information combined with the artificial intelligence Back Propagation neural network algorithm. Through the analysis of the training resulted, it was found that the students’ academic performance was related to the reasonable laboratory study time, dormitory stay time, physical exercise time and social entertainment time. Finally, the system could intelligently predict students’ academic performance and give reasonable suggestions according to the established prediction model. The realization of this project could provide technical support for university educators.

scholarly journals Gynecology Meets Big Data in the Disruptive Innovation Medical Era: State-of-Art and Future Prospects

2021 ◽  
Vol 18 (10) ◽  
pp. 5058
Author(s):  
Rola Khamisy-Farah ◽  
Leonardo B. Furstenau ◽  
Jude Dzevela Kong ◽  
Jianhong Wu ◽  
Nicola Luigi Bragazzi
Keyword(s):  
Big Data ◽  
Information And Communication Technologies ◽  
Imaging Techniques ◽  
Treatment Options ◽  
Wearable Sensors ◽  
Three Dimensional ◽  
Disruptive Innovation ◽  
Healthcare Management ◽  
The Internet ◽  
Big Data Visualization

Tremendous scientific and technological achievements have been revolutionizing the current medical era, changing the way in which physicians practice their profession and deliver healthcare provisions. This is due to the convergence of various advancements related to digitalization and the use of information and communication technologies (ICTs)—ranging from the internet of things (IoT) and the internet of medical things (IoMT) to the fields of robotics, virtual and augmented reality, and massively parallel and cloud computing. Further progress has been made in the fields of addictive manufacturing and three-dimensional (3D) printing, sophisticated statistical tools such as big data visualization and analytics (BDVA) and artificial intelligence (AI), the use of mobile and smartphone applications (apps), remote monitoring and wearable sensors, and e-learning, among others. Within this new conceptual framework, big data represents a massive set of data characterized by different properties and features. These can be categorized both from a quantitative and qualitative standpoint, and include data generated from wet-lab and microarrays (molecular big data), databases and registries (clinical/computational big data), imaging techniques (such as radiomics, imaging big data) and web searches (the so-called infodemiology, digital big data). The present review aims to show how big and smart data can revolutionize gynecology by shedding light on female reproductive health, both in terms of physiology and pathophysiology. More specifically, they appear to have potential uses in the field of gynecology to increase its accuracy and precision, stratify patients, provide opportunities for personalized treatment options rather than delivering a package of “one-size-fits-it-all” healthcare management provisions, and enhance its effectiveness at each stage (health promotion, prevention, diagnosis, prognosis, and therapeutics).

Numerical and Experimental Investigation of Return Channel Vane Aerodynamics With Two-Dimensional and Three-Dimensional Vanes

2016 ◽  
Vol 139 (1) ◽  
Author(s):  
A. Hildebrandt ◽  
F. Schilling
Keyword(s):  
Experimental Investigation ◽  
Flow Field ◽  
Static Pressure ◽  
Three Dimensional ◽  
Pressure Rise ◽  
Field Performance ◽  
Two Dimensional ◽  
Flow Angle ◽  
Overall Performance ◽  
Return Channel

The present paper deals with the numerical and experimental investigation of the effect of return channel (RCH) dimensions of a centrifugal compressor stage on the aerodynamic performance. Three different return channel stages were investigated, two stages comprising three-dimensional (3D) return channel blades and one stage comprising two-dimensional (2D) RCH vanes. The analysis was performed regarding both the investigation of overall performance (stage efficiency, RCH total pressure loss coefficient) and detailed flow-field performance. For detailed experimental flow-field investigation at the stage exit, six circumferentially traversed three-hole probes were positioned downstream the return channel exit in order to get two-dimensional flow-field information. Additionally, static pressure wall measurements were taken at the hub and shroud pressure and suction side (SS) of the 2D and 3D return channel blades. The return channel system overall performance was calculated by measurements of the circumferentially averaged 1D flow field downstream the diffuser exit and downstream the stage exit. Dependent on the type of return channel blade, the numerical and experimental results show a significant effect on the flow field overall and detail performance. In general, satisfactory agreement between computational fluid dynamics (CFD)-prediction and test-rig measurements was achieved regarding overall and flow-field performance. In comparison with the measurements, the CFD-calculated stage performance (efficiency and pressure rise coefficient) of all the 3D-RCH stages was slightly overpredicted. Very good agreement between CFD and measurement results was found for the static pressure distribution on the RCH wall surfaces while small CFD-deviations occur in the measured flow angle at the stage exit, dependent on the turbulence model selected.

scholarly journals The dilemma between eliminating dominance-resistant solutions and preserving boundary solutions of extremely convex Pareto fronts

2021 ◽  
Author(s):  
Zhenkun Wang ◽  
Qingyan Li ◽  
Qite Yang ◽  
Hisao Ishibuchi
Keyword(s):  
Evolutionary Algorithms ◽  
Coping Strategies ◽  
Test Problem ◽  
Pareto Front ◽  
Optimization Problems ◽  
Feasible Region ◽  
Multi Objective Optimization ◽  
Multi Objective ◽  
Pareto Fronts ◽  
Boundary Solutions

AbstractIt has been acknowledged that dominance-resistant solutions (DRSs) extensively exist in the feasible region of multi-objective optimization problems. Recent studies show that DRSs can cause serious performance degradation of many multi-objective evolutionary algorithms (MOEAs). Thereafter, various strategies (e.g., the $$\epsilon $$ ϵ -dominance and the modified objective calculation) to eliminate DRSs have been proposed. However, these strategies may in turn cause algorithm inefficiency in other aspects. We argue that these coping strategies prevent the algorithm from obtaining some boundary solutions of an extremely convex Pareto front (ECPF). That is, there is a dilemma between eliminating DRSs and preserving boundary solutions of the ECPF. To illustrate such a dilemma, we propose a new multi-objective optimization test problem with the ECPF as well as DRSs. Using this test problem, we investigate the performance of six representative MOEAs in terms of boundary solutions preservation and DRS elimination. The results reveal that it is quite challenging to distinguish between DRSs and boundary solutions of the ECPF.

Efficient Gradient-Based Algorithms for the Construction of Pareto Fronts

2011 ◽  
Author(s):  
Sriram Shankaran ◽  
Brian Barr
Keyword(s):  
Pareto Front ◽  
Computational Cost ◽  
High Fidelity ◽  
Simulation Tools ◽  
Pareto Points ◽  
Uniform Spacing ◽  
Design Variables ◽  
Gradient Based ◽  
Pareto Fronts ◽  
Sampling Approach

The objective of this study is to develop and assess a gradient-based algorithm that efficiently traverses the Pareto front for multi-objective problems. We use high-fidelity, computationally intensive simulation tools (for eg: Computational Fluid Dynamics (CFD) and Finite Element (FE) structural analysis) for function and gradient evaluations. The use of evolutionary algorithms with these high-fidelity simulation tools results in prohibitive computational costs. Hence, in this study we use an alternate gradient-based approach. We first outline an algorithm that can be proven to recover Pareto fronts. The performance of this algorithm is then tested on three academic problems: a convex front with uniform spacing of Pareto points, a convex front with non-uniform spacing and a concave front. The algorithm is shown to be able to retrieve the Pareto front in all three cases hence overcoming a common deficiency in gradient-based methods that use the idea of scalarization. Then the algorithm is applied to a practical problem in concurrent design for aerodynamic and structural performance of an axial turbine blade. For this problem, with 5 design variables, and for 10 points to approximate the front, the computational cost of the gradient-based method was roughly the same as that of a method that builds the front from a sampling approach. However, as the sampling approach involves building a surrogate model to identify the Pareto front, there is the possibility that validation of this predicted front with CFD and FE analysis results in a different location of the “Pareto” points. This can be avoided with the gradient-based method. Additionally, as the number of design variables increases and/or the number of required points on the Pareto front is reduced, the computational cost favors the gradient-based approach.

Large-scale three-dimensional anisotropic topology optimization of variable-axial lightweight composite structures

2021 ◽  
pp. 1-15
Author(s):  
Yuqing Zhou ◽  
Tsuyoshi Nomura ◽  
Enpei Zhao ◽  
Kazuhiro Saitou
Keyword(s):  
Topology Optimization ◽  
Composite Structures ◽  
Large Scale ◽  
Volume Fraction ◽  
Three Dimensional ◽  
Optimization Method ◽  
Optimized Design ◽  
Adaptive Meshing ◽  
Design Synthesis ◽  
Fiber Placement

Abstract Variable-axial fiber-reinforced composites allow for local customization of fiber orientation and thicknesses. Despite their significant potential for performance improvement over the conventional multiaxial composites and metals, they pose challenges in design optimization due to the vastly increased design freedom in material orientations. This paper presents an anisotropic topology optimization method for designing large-scale, 3D variable-axial lightweight composite structures subject to multiple load cases. The computational challenges associated with large-scale 3D anisotropic topology optimization with extremely low volume fraction are addressed by a tensor-based representation of 3D orientation that would avoid the 2π periodicity of angular representations such as Euler angles, and an adaptive meshing scheme, which, in conjunction with PDE regularization of the density variables, refines the mesh where structural members appear and coarsens where there is void. The proposed method is applied to designing a heavy-duty drone frame subject to complex multi-loading conditions. Finally, the manufacturability gaps between the optimized design and the fabrication-ready design for Tailored Fiber Placement (TFP) is discussed, which motivates future work toward a fully-automated design synthesis.

Sign in / Sign up

Export Citation Format

Share Document