Aircraft design cycle time reduction using artificial intelligence

Oroumieh, Mehran Ali Azizi; Malaek, S.M.; Ashrafizaadeh, Mahmud; Taheri, S. Mahmoud

doi:10.1016/j.ast.2012.05.003

Cited by 27 publications

(11 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results demonstrated the effectiveness of the ANN approach in the preliminary aircraft design process. The error between the ANN models and the actual value was less than 10% for the take-off wing loading and the take-off thrust loading (12) . S. Manoranjan et al presented a method using neural networks to estimate the separation point and stall speed of cascaded fins.…”

Section: Introductionmentioning

confidence: 86%

See 1 more Smart Citation

Repetitively enhanced neural networks method for complex engineering design optimisation problems

et al. 2015

View full text Add to dashboard Cite

A Repetitively Enhanced Neural Networks (RENN) method is developed and presented for complex and implicit engineering design problems. The enhanced neural networks module constructs an accurate surrogate model and avoids over-fitting during neural networks training from supervised learning data. The optimiser is executed by the enhanced neural networks models to seek a tentative optimum point. It is repetitively added into the supervised learning data set to refine the surfaces until the RENN tolerance is reached. The RENN method demonstrates the effectiveness and feasibility for a 2D highly non-linear numerical example and the structure design of a two-member frame reaching a convergent solution at 10 and 15 iterations at the maximum error of 1% when compared with the exact solution. Then, the RENN method is applied for a long endurance unmanned aerial vehicle (UAV) aerofoil design optimisation. A Class/Shape function transformation (CST) geometry parameterisation method represents an accurate UAV aerofoil with ten geometry design variables. The high-fidelity analysis solver with structured mesh is used for

show abstract

Section: Introductionmentioning

confidence: 86%

“…. (12) The specific shape of the aerofoil can be obtained by varying the Ai coefficients. A Bernstein polynomial order (BPO) of four makes it possible to fit the existing aerofoil shapes with an accuracy order of 10 -3 ), as seen in Fig.…”

Section: Design Methodology a Aerofoil Geometry Parameterisationmentioning

confidence: 99%

Repetitively enhanced neural networks method for complex engineering design optimisation problems

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Its implementation relies on a wide variety of techniques such as Expert Systems, Fuzzy Logic or Neural Networks. In fact, it has been used to improve the design process [7], reducing development time and costs. But our vision is also adding AI to the assessment of standard compliance, while also serving as a learning guide for software professionals involved in the development of critical systems.…”

Section: Introductionmentioning

confidence: 99%

A Framework for Evaluating the Standards for the Production of Airborne and Ground Traffic Management Software

et al. 2020

View full text Add to dashboard Cite

The development of Airborne and Ground systems is framed by specific regulations, usually expressed as standards. A disadvantage of those standards is the inherent complexity for its application and the verification of compliance given the high number of requirements to be checked in many different situations of the application and which are highly dependent on the applicable level of criticality. When the development of this type of system requires the incorporation of new personnel without enough knowledge about the standards, risks of mistakes in their application grow exponentially. The objective of this work is to develop an Expert System (ES) that helps to evaluate the application of the standards DO-178C and DO-278A throughout the project life cycle, at the same time it serves to facilitate both its use and the learning of its application to a wide group of professionals. The proposed underlying method for the ES will allow evaluating the set of development processes to check coverage of the standards DO-178C and DO-278A without depending on a specific life cycle model. The method involves a model of the set of processes, so they can be evaluated by the ES. Additionally, the ES will require a minimum configuration to evaluate the development of systems based on these two standards. The main result is a new generic Expert System based on rules capable of being adapted to different environment of evaluation, whichh minor configuration operations thus allowing that a Generic ES can act as a Specific ES for each situation. This configurable ES has been customized to evaluate the software life cycle based on the standards under study.

show abstract

“…Application of artificial intelligence in aircraft design is an emerging field. Oroumieh et al [23] presented a scheme for employing artificial intelligence in preliminary aircraft design to reduce the design cycle time. Two artificial intelligence techniques namely, fuzzy logic and ANN have been utilized.…”

Section: Introductionmentioning

confidence: 99%

Knowledge-Based Aerodynamic Estimation of Airships

Rashid¹,

Ahmad²,

Maqsood³

et al. 2016

IJMERR

View full text Add to dashboard Cite

High fidelity flight modeling and simulation generally involves development of mathematical models based on aerodynamics and flight characteristics derived from experimental or numerical data. The data is generally recorded in look-up tables and called in during simulation. This results in very high computational cost (time & hardware requirements). An alternative, discussed in this paper, is to use a computational and knowledge-based paradigm, called neural networks. The network is presented with the experimental data and learns the relationships between forces and moments in six degrees of freedom. This modeling strategy has important implications for modeling the behavior of novel and complex flying configurations, such as airships that are considered in this paper. The pipeline includes, digitization of wind tunnel data, compatibility of digitized data with neural network (feedforward) followed by development of six degree of freedom aerodynamic model. The preliminary results of using neural networks to model aerodynamic forces & moments look promising. 

show abstract

Aircraft design cycle time reduction using artificial intelligence

Cited by 27 publications

References 46 publications

Repetitively enhanced neural networks method for complex engineering design optimisation problems

Repetitively enhanced neural networks method for complex engineering design optimisation problems

A Framework for Evaluating the Standards for the Production of Airborne and Ground Traffic Management Software

Knowledge-Based Aerodynamic Estimation of Airships

Contact Info

Product

Resources

About