Combining Deep Learning with Knowledge Graph for Design Knowledge Acquisition in Conceptual Product Design

The acquisition of valuable design knowledge from massive fragmentary data is challenging for designers in conceptual product design.This study proposes a novel method for acquiring design knowledge by combining deep learning with knowledge graph.Specifically,the design knowledge acquisition method utilises the knowledge extraction model to extract design-related entities and relations from fragmentary data,and further constructs the knowledge graph to support design knowledge acquisition for conceptual product design.Moreover,the knowledge extraction model introduces ALBERT to solve memory limitation and communication overhead in the entity extraction module,and uses multi-granularity information to overcome segmentation errors and polysemy ambiguity in the relation extraction module.Experimental comparison verified the effectiveness and accuracy of the proposed knowledge extraction model.The case study demonstrated the feasibility of the knowledge graph construction with real fragmentary porcelain data and showed the capability to provide designers with interconnected and visualised design knowledge.

Logical-Structure Modeling for Conceptual Design

Based on the definition of a logic structure feature to relate logically functional requirements to geometric representation independent upon detailed geometric representation, this paper presents an idea of logical structure modeling for computer aided conceptual design and makes attempt to establish a representation formalism of logic structure modeling. The definition and representation of logical structure feature are given and an assembly module definition for supporting top down conceptual design is also proposed. The proposed scheme contributes to several aspects of conceptual design research, especially to provide elementarily a formal methodology for computer aided conceptual design system development and operation.

Web Layout Design of Large Cavity Structures Based on Topology Optimization

Large cavity structures are widely employed in aerospace engineering, such as thin-walled cylinders, blades andwings. Enhancing performance of aerial vehicles while reducing manufacturing costs and fuel consumptionhas become a focal point for contemporary researchers. Therefore, this paper aims to investigate the topologyoptimization of large cavity structures as a means to enhance their performance, safety, and efficiency. By usingthe variable density method, lightweight design is achieved without compromising structural strength. Theoptimization model considers both concentrated and distributed loads, and utilizes techniques like sensitivityfiltering and projection to obtain a robust optimized configuration. The mechanical properties are checked bycomparing the stress distribution and displacement of the unoptimized and optimized structures under the sameload. The results confirm that the optimized structures exhibit improved mechanical properties, thus offering keyinsights for engineering lightweight, high-strength large cavity structures.

Extractive distillation: Advances in conceptual design, solvent selection,and separation strategies

Extractive distillation(ED) is one of the most promising approaches for the separation of the azeotropic or closeboiling mixtures in the chemical industry. The purpose of this paper is to provide a broad overview of the recent development of key aspects in the ED process involving conceptual design, solvent selection, and separation strategies. To obtain the minimum entrainer feed flow rate and reflux ratio for the ED process, the conceptual design of azeotropic mixture separation based on a topological analysis via thermodynamic feasibility insights involving residue curve maps, univolatility lines, and unidistribution curves is presented. The method is applicable to arbitrary multicomponent mixtures and allows direct screening of design alternatives. The determination of a suitable solvent is one of the key steps to ensure an effective and economical ED process. Candidate entrainers can be obtained from heuristics or literature studies while computer aided molecular design(CAMD) has superiority in efficiency and reliability. To achieve optimized extractive distillation systems, a brief review of evaluation method for both entrainer design and selection through CAMD is presented. Extractive distillation can be operated either in continuous extractive distillation(CED) or batch extractive distillation(BED), and both modes have been well-studied depending on the advantages in flexibility and low capital costs. To improve the energy efficiency, several configurations and technological alternatives can be used for both CED and BED depending on strategies and main azeotropic feeds. The challenge and chance of the further ED development involving screening the best potential solvents and exploring the energy-intensive separation strategies are discussed aiming at promoting the industrial application of this environmentally friendly separation technique.

Lessons learned from the “5.12” Wenchuan Earthquake:evaluation of earthquake performance objectives and the importance of seismic conceptual design principles

Many different types of buildings were severely damaged or collapsed during the May 12, 2008 Great Wenchuan Earthquake. Based on survey data collected in regions that were subjected to moderate to severe earthquake intensities, a comparison between the observed building damage, and the three earthquake performance objectives and seismic conceptual design principles specified by the national ＂Code for Seismic Design of Buildings GB50011-2001,＂ was carried out. Actual damage and predicted damage for a given earthquake level for different types of structures is compared. Discussions on seismic conceptual design principles, with respect to multiple defense lines, strong column-weak beam, link beam of shear walls, ductility detailing of masonry structures, exits and staircases, and nonstructural elements, etc. are carried out. Suggestions for improving the seismic design of structures are also proposed. It is concluded that the seismic performance objectives for three earthquake levels, i.e., ＂no failure under minor earthquake level, ＂＂repairable damage under moderate earthquake level＂ and ＂no collapse under major earthquake level＂ can be achieved if seismic design principles are carried out by strictly following the code requirements and ensuring construction quality.

Implementation of a Sketch Based Approach to Conceptual Aircraft Design Synthesis and Modeling

In the context of applying computer aided design tools to aircraft conceptualdesign, a sketch based approach is proposed to help designers turn their original concepts intocomplex numerical models that are usable for further analysis and optimization. This approachemphasizes the integration of general configuration and the layout of such components as engines,payloads, fuel tanks and landing gears, and the representation of a design scheme as uniform planesketches and three dimensional models. This paper presents the measures adopted to implement theapproach in a prototype system, including the object-oriented data structure, friendly graphicaluser interfaces and basic features of relevant modules. Several examples generated in the prototypeand applications of the results are finally outlined to illustrate the effectiveness of theapproach.

Computer-based Creativity Enhanced Conceptual Design Model for Non-routine Design of Mechanical Systems

Computer-based conceptual design for routine design has made great strides, yet non-routine design has not been given due attention, and it is still poorly automated. Considering that the function-behavior-structure（FBS） model is widely used for modeling the conceptual design process, a computer-based creativity enhanced conceptual design model（CECD） for non-routine design of mechanical systems is presented. In the model, the leaf functions in the FBS model are decomposed into and represented with fine-grain basic operation actions（BOA）, and the corresponding BOA set in the function domain is then constructed. Choosing building blocks from the database, and expressing their multiple functions with BOAs, the BOA set in the structure domain is formed. Through rule-based dynamic partition of the BOA set in the function domain, many variants of regenerated functional schemes are generated. For enhancing the capability to introduce new design variables into the conceptual design process, and dig out more innovative physical structure schemes, the indirect function-structure matching strategy based on reconstructing the combined structure schemes is adopted. By adjusting the tightness of the partition rules and the granularity of the divided BOA subsets, and making full use of the main function and secondary functions of each basic structure in the process of reconstructing of the physical structures, new design variables and variants are introduced into the physical structure scheme reconstructing process, and a great number of simpler physical structure schemes to accomplish the overall function organically are figured out. The creativity enhanced conceptual design model presented has a dominant capability in introducing new deign variables in function domain and digging out simpler physical structures to accomplish the overall function, therefore it can be utilized to solve non-routine conceptual design problem.

Multi-objective Optimization Conceptual Design of Product Structure Based on Variable Length Gene Expression

It is a complicated problem for the bottom-to-top adaptive conceptual design of complicated products between structure and function. Reliable theories demand to be found in order to determine whether the structure accords with the requirement of design. For the requirement generally is dynamic variety as time passes, new requirements will come, and some initial requirements can no longer be used. The number of product requirements, the gene length expressing requirements, the structure of the product, and the correlation matrix are varied with individuation of customer requirements of the product. By researching on the calculation mechanisms of dynamic variety, the approaches of gene expression and variable length gene expression are proposed. According to the diversity of structure selection in conceptual design and mutual relations between structure and function as well as structure and structure, the correlation matrixes between structure and function as well as structure and structure are defined. By the approach of making the sum of the elements of correlation matrix maximum, the mathematical models of multi-object optimization for structure design are provided based on variable requirements. An improved genetic algorithm called segment genetic algorithm is proposed based on optimization preservation simple genetic algorithm. The models of multi-object optimization are calculated by the segment genetic algorithm and hybrid genetic algorithm. An example for the conceptual design of a washing machine is given to show that the proposed method is able to realize the optimization structure design fitting for variable requirements. In addition, the proposed approach can provide good Pareto optimization solutions, and the individuation customer requirements for structures of products are able to be resolved effectively.

Conceptual design and RCS performance research of shipborne early warning aircraft

In order to improve the survivability of the aircraft,conceptual design and radar cross section（RCS） performance research are done. The CATIA software is used to design the 3D digital model of the shipborne early warning aircraft, and some measures are taken to reduce the RCS characteristics of the early warning aircraft at the same time. Based on the physical optics method and the equivalent electromagnetic flow method,the aircraft＇s RCS characteristics and strength distribution characteristics are simulated numerically, and compared with the foreign advanced shipborne early warning aircraft. The simulation results show that under the X radar band, when the incident wave pitching angle is 0？, compared with the foreign advanced shipborne early warning aircraft, the forward RCS average value of the conceptual shipborne early warning aircraft is reduced to 24.49%, the lateral RCS average value is reduced to 5.04%, and the backward RCS average value is reduced to 39.26%. The research results of this paper are expected to provide theoretical basis and technical support for the conceptual design and the stealth design of the shipborne early warning aircraft.

CONCEPTUAL MECHANICAL DESIGN METHOD BASED ON QUALITATIVE SIMULATION

A model for conceptual design of mechanical devices is studied based onqualitative simulation. In this model, the desired functions are expressed bystate-transit-diagrams(ST-diagrams) and design space is represented byqualitative-state-curves(QS-curves). The first design idea, called seeds idea, is proposed by thedesigner and then is abstracted into QS-curves. The qualitative simulation is implemented based onthe QS-curves. By changing the motion of acting parts, the connection of parts and the motion ofdriving part, new design ideas are generated. With this model, a series of new design ideas derivedfrom the seeds idea can be achieved.

CASE-BASED CONCEPTUAL DESIGN

The current method of case-based design (CBD) can be well practiced forconfiguration design in which design experience knowledge is involved. However, since the designcase is confined to a certain application domain, it is difficult for CBD to be applied toconceptual design process that develops concepts to meet design specifications. Firstly, a functionfactor description space is erected to provide an exhibition room for all functions of design cases.Next, the approach for identifying the space state of function factor in description space isproposed, including the determination of the similarities between function factors of design case.And then a general object-oriented representation for design case is presented by bringing the classof function and in-out flow into the current case representation. Finally, a living example forelectro-pet design that illustrates the implementation of the method for case-based conceptualdesign based on distributed design case repositories is described.

The Conceptual Design Method for a Pumping Unit Based on QFD and TRIZ

Quality function deployment （QFD） is a quality system, that can help to design novel products that meet customers＇ needs. Theory of inventive problem solving （TRIZ） is a very powerful tool in helping to solve difficult technical problems encountered in the design process. Introducing QFD and TRIZ into the conceptual design of the pumping unit combines advantages of these two theories, therefore meeting different demands of different users. It can tell us “What should we do it” with QFD and “How should we do it” with TRIZ. The conceptual design method, which is based on QFD and TRIZ, is introduced andused to analyze and evaluate the conceptual design project of a pumping unit.

DEFICIENT INFORMATION MODELING OF MECHANICAL PRODUCTS FOR CONCEPTUAL SHAPE DESIGN

In allusion to the deficient feature of product information in conceptualdesign, a framework of deficient information modeling for conceptual shape design is put forward,which includes qualitative shape modeling (a qualitative solid model), uncertain shape modeling (anuncertain relation model) and imprecise shape modeling (an imprecise region model). In theframework, the qualitative solid model is the core, which represents qualitatively (using symbols)the conceptual shapes of mechanical products. The uncertain relation model regarding domainrelations as objects and the imprecise region model regarding domains as objects are used to dealwith the uncertain and imprecise issues respectively, which arise from qualitative shape modeling orexist in product information itself.

Conceptual design of an extractive distillation process for the separation of azeotropic mixture of n-butanol-isobutanol-water

In many chemical processes, large amounts of wastewater containing butanol and isobutanol are produced.Given that n-butanol-isobutanol-water can form triple azeotrope, high-purity butanol cannot be recovered from the wastewater by ordinary distillation. To economically and effectively recover butanol from this kind of wastewater, 1,4-butanediol is selected as an extractant to break the formation of the azeotropes, and a doubleeffect extractive distillation process is proposed. The conceptual design of the proposed process is accomplished based on process simulation. With the proposed process, the purity of recovered butanol and water is greater than 99.99 wt%. In comparison with the conventional azeotropic distillation process, economic analysis shows that the operating cost of the proposed process is lower: when the capacity of wastewater treatment is 100 t·h^(-1), the total operating cost decreases by 5.385 ×10~6 USD per year, and the total annual cost of the new process decreases by 5.249 ×10~6 USD per year. In addition, in the extractive distillation system, variable effects on separation purities and cost are more complex than those in the ordinary distillation system. The method and steps to optimize the key variables of the extractive distillation system are also discussed in this paper and can provide reference for similar studies.

MECHANICAL PRODUCT EXTENSIVE INTELLIGENT CONCEPTUAL DESIGN

Based on extenics, an extensive functional information model(function-behavioral action-structure-environmental constraint) of the mechanical productintelligent conceptual design is developed, and the mechanism of theoretic structure solutions isproduced, the mapping relations between function-behavior and behavior-structure are analyzed. Themodel is applied to the filling material system's conceptual design to verify validity.

Conceptual design of oil palm fibre reinforced polymer hybrid composite automotive crash box using integrated approach

A hybrid conceptual design approach was introduced in this study to develop a conceptual design of oil palm polymer composite automotive crash box(ACB). A combination of theory of inventive problem solving(TRIZ), morphological charts and biomimetics was applied where the foremost requirements in terms of the material characteristics, function specifications, force identification, root cause analysis, geometry profile and design selection criteria were considered. The strategy was to use creations of nature to inspire five innovative conceptual designs of the ACB structure and the AHP method was applied to perform the pairwise analysis of selecting the best ACB conceptual design. A new conceptual design for a composite ACB was conceived bearing in mind the properties of natural fibre, unlike those of conventional materials such as steel alloys and aluminium alloys. The design with the highest ranking(26.6 %) was chosen as the final conceptual design, which was the one with a honeycomb structure for the outermost profile, reinforced with a spider web structure inside the part, supported by fibre foam structure extracted from the woodpecker sponge tissue at the centre to maximize the energy absorption capability. The new design could solve the problem of bending collapse which is a major cause of failure to absorb maximum impact energy for ACB during collision. However, the final conceptual design will still need several modifications for production and assembly purposes, which will be completed in a further study.

Conceptual design of a 15-TW pulsed-power accelerator for high-energy-densityephysics experiments

We have developed a conceptual design of a 15-TW pulsed-power accelerator based on the linear-transformer-driver(LTD)architecture described by Stygar[W.A.Stygar et al.,Phys.Rev.ST Accel.Beams 18,110401(2015)].The driver will allow multiple,high-energy-density experiments per day in a university environment and,at the same time,will enable both fundamental and integrated experiments that are scalable to larger facilities.In this design,many individual energy storage units(bricks),each composed of two capacitors and one switch,directly drive the target load without additional pulse compression.Ten LTD modules in parallel drive the load.Each module consists of 16 LTD cavities connected in series,where each cavity is powered by 22 bricks connected in parallel.This design stores up to 2.75 MJ and delivers up to 15 TW in 100 ns to the constant-impedance,water-insulated radial transmission lines.The transmission lines in turn deliver a peak current as high as 12.5 MA to the physics load.To maximize its experimental value and flexibility,the accelerator is coupled to a modern,multibeam laser facility(four beams with up to 5 kJ in 10 ns and one beam with up to 2.6 kJ in 100 ps or less)that can provide auxiliary heating of the physics load.The lasers also enable advanced diagnostic techniques such as X-ray Thomson scattering and multiframe and three-dimensional radiography.The coupled accelerator-laser facility will be the first of its kind and be capable of conducting unprecedented high-energy-densityephysics experiments.

A Signed Digraphs Based Method for Detecting Inherently Unsafe Factors of Chemical Process at Conceptual Design Stage

Digraph-based causal models have been widely used to model the cause and effect behavior of process systems. Signed digraphs （SDG） capture the direction of the effect. It should be mentioned that there are loops in SDG generated from chemical process. From the point of the inherent operability, the worst unsafe factor is the SDG having positive loops that means any disturbance occurring within the loop will propagate through the nodes one by one and are amplified gradually, so the system may lose control, which may lead to an accident. So finding the positive loops in a SDG and treating these unsafe factors in a proper manner can improve the inherent safety of a chemical process. This article proposed a method that can detect the above-mentioned unsafe factors in the proc- ess conceptual design stage automatically through the analysis of the SDG generated from the chemical process. A case study is illustrated to show the working of the algorithm, and then a complicated case from industry is studied to depict the effectiveness of the proposed algorithm.

A Computational Synthesis Approach of Mechanical Conceptual Design Based on Graph Theory and Polynomial Operation

The design synthesis is the key issue in the mechanical conceptual design to generate the design candidates that meet the design requirements.This paper devotes to propose a novel and computable synthesis approach of mechanisms based on graph theory and polynomial operation.The graph framework of the synthesis approach is built firstly,and it involves:(1)the kinematic function units extracted from mechanisms;(2)the kinematic link graph that transforms the synthesis problem from mechanical domain into graph domain;(3)two graph representations,i.e.,walk representation and path representation,of design candidates;(4)a weighted matrix theorem that transforms the synthesis process into polynomial operation.Then,the formulas and algorithm to the polynomial operation are presented.Based on them,the computational flowchart to the synthesis approach is summarized.A design example is used to validate and illustrate the synthesis approach in detail.The proposed synthesis approach is not only supportive to enumerate the design candidates to the conceptual design of a mechanical system exhaustively and automatically,but also helpful to make that enumeration process computable.

A New Method for Optimum Allocation of Design Requirements in Aircraft Conceptual Design

A new method, Collaborative Allocation （CA）, is proposed to solve the large-scale optimum allocation problem in aircraft conceptual design. According to the characteristics of optimum allocation in aircraft conceptual design. The principle and mathematical model of CA are established. The optimum allocation problem is decomposed into one main optimization problem and several sub-optimization problems. A group of design requirements for subsystems are provided by the main system respectively, and the subsystems execute their own optimizations or further provide the detailed design requirements to the bottom components of aircraft, such as spars, ribs and skins, etc. The subsystems minimize the discrepancy between their own local variables and the corresponding allocated values, and then return the optimization results to main optimization. The main optimization is performed to reallocate the design requirements for improving the integration performance and progressing toward the compatibilities among subsystems. CA provides the general optimum allocation architecture and is easy to be carried out. Furthermore, the concurrent computation can also be realized. Two examples of optimum reliability allocation are used to describe the implementation procedure of CA for two-level allocation and three-level allocation respectively, and to validate preliminarily its correctness and effectiveness. It is shown that the developed method can be successfully used in optimum allocation of design requirements. Then taking weight requirement allocation as example, the mathematical model and solution procedure for collaborative allocation of design requirements in aircraft conceptual design are briefly depicted.