Computer-aided Design Design Research Articles

Effect of wound dressing porosity and exudate viscosity on the exudate absorption: In vitro and in silico tests with 3D printed hydrogels

Exudate absorption is a key parameter for proper wound dressing performance. Unlike standardized tests that consider exudate viscosity close to that of water, patients' exudates vary greatly in composition and, therefore, viscosity. This work aimed to investigate the effects of exudate viscosity and pore size of hydrogel-like dressings on the exudate absorption rate to establish rational criteria for the design of dressings that can meet the personalized needs of wound treatment. Computer-aided design (CAD) was used for Digital Light Processing (DLP) 3D printing of hydrogels with 0%, 30% and 60% porosity. The hydrogels were characterized in detail, and the absorption of two simulated exudate fluids (SEFs) was video-recorded. The same CAD files were used to develop in silico models to simulate exudate uptake rate. Both in vitro data and in silico modeling revealed that low-viscosity SEF penetrates faster through relatively small hydrogel pores (approx. 400 μm) compared to larger pores (approx. 1100 μm) due to capillary forces. However, in vitro vertical uptake took longer than when simulated using CAD design due to lateral fluid absorption through the pore walls in the hydrogel bulk. Distortions of hydrogel channels (micro-CT images) and lateral fluid absorption should be both considered for in silico simulation of SEF penetration. Overall, the results evidenced that porous hydrogel dressings allow rapid penetration (within a few seconds) and hosting of exudates, especially for pore size <1 mm. This information may be useful for design criteria of wound dressings with adequate fluid handling and drug release rate.

Sketching Versus Digital Design Tools in Architectural Design

Sketching is a design tool that can be assumed to be ill-structured, does not offer exact solutions, is intuitive, and is open-ended in the initial stages of architectural design. Sketching creates an opportunity for architects to release their creativity and intuition, giving rise to spontaneous ideas and concepts in an organic and natural way. During the initial design phases, like in the conceptual stage of the design, designers receive aid from conventional sketching as their concepts and ideas can easily transform into tangible, real-world forms. With the development of digital design methods like CAD (computer-aided design) in pursuit of AI (artificial intelligence), it has been accepted that manual sketches are no longer the only method used in the design process, and the trend toward using new methods has begun. The diversity and evolution of tools used in architectural design, together with the integration of CAD, AI, and traditional sketching techniques, have contributed to the development of architectural design and facilitated enhanced collaboration, visualization, and efficiency across the design process. As a result, it has evolved to embrace the use of CAD, which was the first method adopted from these developments, as a basic skill in the field of architectural design education. This shift places a strong emphasis on the professional field of architectural design while also encouraging students to explore the innovative potential of CAD for design purposes. CAD presents architects with a robust platform that facilitates the creation of intricate designs and precise measurements during the initial stages of the design process. Following CAD, the development of AI-driven design tools motivates architecture students and designers to transform their concepts into concrete designs. Although it is known that each method mentioned has its own positive or negative aspects, it is not possible to say that any of them is used alone in architectural design processes. At this point, combining the design process with CAD and AI-supported design tools, as well as traditional manual sketching in architecture, helps develop a diverse and adaptable skill set in design. Integrating digital design tools into the architectural field emphasizes the enduring importance of traditional sketches, especially in terms of inspiration and conceptualization in architectural design, while also updating the design process. This document aims to explore the progression of employing diverse design tools, namely manual sketching, CAD, and AI-driven design tools, throughout the architectural design process. This paper undertakes a comparative analysis of using computational design tools instead of traditional sketching with pen and pencil, aiming to juxtapose their respective benefits and drawbacks. In conclusion, although it is not yet possible to assert the superiority of one method over the other, it is evident that traditional sketching continues to hold significant relevance and effectiveness in the design process despite its long-term use.

ERCAD: A Parametric Reactor Design Tool That Enables Rapid Prototyping and Optimization of Electrochemical Reactors through 3D Printing.

The reactors are an essential component of electrosynthetic reactions. As the electron transfer processes are heterogeneous, the reactors have a significant impact on reaction outcomes. This has resulted in reaction reproducibility being problematic, which commercial reactors alleviate somewhat but are expensive and cannot be optimized or iterated upon. Using 3D printing, rapid prototyping of bespoke reactors should facilitate investigation of the sensitivity of key reactor parameters, enable reactor optimization, and improved reproducibility through sharing of the print files. However, the bottleneck to this approach is the Computer Aided Design (CAD) of the reactors, which typically requires specialist knowledge and training to do. This has resulted in 3D printing not being typically used in the field of electrosynthesis. Herein, we showcase the development and application of a user-friendly, open-source software tool that can be used to produce Electrochemical Reactor CAD (ERCAD) designs simply and easily by nonexperts. We demonstrate its use to design and print reactors for the analysis, optimization, screening, and scaleup of electrosynthetic reactions. Using this parametric design tool, chemists with no design experience or skills can now easily create, print, test, and share their reactors.

BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometry

This paper presents BrepGen , a diffusion-based generative approach that directly outputs a Boundary representation (B-rep) Computer-Aided Design (CAD) model. BrepGen represents a B-rep model as a novel structured latent geometry in a hierarchical tree. With the root node representing a whole CAD solid, each element of a B-rep model (i.e., a face, an edge, or a vertex) progressively turns into a child-node from top to bottom. B-rep geometry information goes into the nodes as the global bounding box of each primitive along with a latent code describing the local geometric shape. The B-rep topology information is implicitly represented by node duplication. When two faces share an edge, the edge curve will appear twice in the tree, and a T-junction vertex with three incident edges appears six times in the tree with identical node features. Starting from the root and progressing to the leaf, BrepGen employs Transformer-based diffusion models to sequentially denoise node features while duplicated nodes are detected and merged, recovering the B-Rep topology information. Extensive experiments show that BrepGen advances the task of CAD B-rep generation, surpassing existing methods on various benchmarks. Results on our newly collected furniture dataset further showcase its exceptional capability in generating complicated geometry. While previous methods were limited to generating simple prismatic shapes, BrepGen incorporates free-form and doubly-curved surfaces for the first time. Additional applications of BrepGen include CAD autocomplete and design interpolation. The code, pretrained models, and dataset are available at https://github.com/samxuxiang/BrepGen.

3D printed stents using Fused deposition modelling

3D printing has emerged as an appealing technology for designing and manufacturing bioresorbable stents. This innovative technology enables the creation of a diverse range of stent structures with specific features and intricate geometries, significantly impacting their mechanical properties and potentially affect clinical performance. In this study, we investigated the influence of various processing parameters during the 3D printing process and assess their effects on stent quality. Fused Deposition Modelling (FDM) was chosen as the 3D printing technology, with a focus on optimizing the printing of a novel chevron-strut stent design. Printing parameters were systematically investigated to understand their individual contributions to overall stent quality. The findings reveal the significance of print speed (6.5 mm/s) as a pivotal factor, influencing strut width and the difference between the Computer Aided Design (CAD) volume to calculated volume of stent. Furthermore, the optimization of printing parameters such as travel speed (200 mm/s), and line width (0.2 mm) led to the fabrication of stent with strut widths of 400 μm. However, it is important to also consider other parameters for comprehensive print optimization. In conclusion, by exercising control over the print process parameters, it becomes feasible to produce stents that closely align with the original CAD designs.

Harnessing CFD simulations and CAD design to optimize hydropower efficiency of a propeller turbine in the Maliringan River: acase study

This research focuses on improving hydropower production by designing a turbine for the MaliringanRiver in Kalimantan Selatan. The rotational speed and torque will be the focus of maximizing power generation. This research used Computational Fluid Dynamics (CFD) to understand how the fluid flows and how efficiently the turbine works. The simulations helped us see how the fluid flowed, the pressure differences, and the speed of the water inside the turbine. The software COMSOL Multiphysics imitates how the fluid behaves and interacts in real-life situations. The utilization of SOLIDWORKS played a crucial role in the turbine's design process, facilitating an accurate representation of the turbine's geometry and the subsequent fabrication of a prototype propeller turbine, featuring an outer diameter measuring 0.27 meters and an inner diameter measuring 0.113 meters. The methodology resulted in a power efficiency of 76.45%, showcasing the possibility of significant enhancements in the efficiency of hydropower generation. The broader ramifications of this study emphasize the feasibility of tailor-made turbines for local hydropower initiatives, thereby supporting Indonesia's renewable energy plan by providing sustainable and efficient energy alternatives. This study emphasizes the collaborative utilization of Computer-Aided Design (CAD) and CFD technologies in the progression of turbine technology, thereby establishing a basis for future investigations in hydropower optimization.

3D printing, modelling and simulation for dental implant: A comprehensive review

The implementation of three-dimensional printing technology has revolutionised dentistry over the past decade. The desired object is scanned by a 3D scanner or built using computer-aided design (CAD)/computer-aided manufacturing (CAM) software. CAD designs of dental implants can be analysed by the finite element method (FEM). Finite element analysis (FEA) is done by discretising the geometrically developed model into smaller and simpler elements and analysing the 3D model using different boundary conditions on different nodes. Depending on the materials of choice, various printing methods are available, such as selective laser sintering (SLS), stereolithography, fused deposition modelling, and laminated object manufacturing. Dental implants are designed with the help of different biomaterials, such as polymers, metals, and ceramics. Clinicians should know the latest implant materials for successful implant therapy. This review article investigates 3D printing on various dental implants, designs, simulations, and limitations. The last part of the article discusses different properties of the implant materials used in the designs.

Brep2Seq: a dataset and hierarchical deep learning network for reconstruction and generation of computer-aided design models

Abstract Three-dimensional (3D) reconstruction is a significant research topic in the field of computer-aided design (CAD), which is used to recover editable CAD models from original shapes, including point clouds, voxels, meshes, and boundary representations (B-rep). Recently, there has been considerable research interest in deep model generation due to the increasing potential of deep learning methods. To address the challenges of 3D reconstruction and generation, we propose Brep2Seq, a novel deep neural network designed to transform the B-rep model into a sequence of editable parametrized feature-based modeling operations comprising principal primitives and detailed features. Brep2Seq employs an encoder-decoder architecture based on the transformer, leveraging geometry and topological information within B-rep models to extract the feature representation of the original 3D shape. Due to its hierarchical network architecture and training strategy, Brep2Seq achieved improved model reconstruction and controllable model generation by distinguishing between the primary shape and detailed features of CAD models. To train Brep2Seq, a large-scale dataset comprising 1 million CAD designs is established through an automatic geometry synthesis method. Extensive experiments on both DeepCAD and Fusion 360 datasets demonstrate the effectiveness of Brep2Seq, and show its applicability to simple mechanical components in real-world scenarios. We further apply Brep2Seq to various downstream applications, including point cloud reconstruction, model interpolation, shape constraint generation, and CAD feature recognition.

Optimizing the Gating System for Rapid Investment Casting of Shape Memory Alloys: Computational Numerical Analysis for Defect Minimization in a Simple-Cubic Cell Structure

With the aid of virtual prototyping and casting numerical simulation, this work presents the optimization of an injection system used in a non-traditional investment casting process that applies perpendicular centrifugal force to inject the molten metal into refractory plaster molds. In this study, advanced techniques of simulation and production of complex geometries in Computer-Aided Design CAD (Computer-Aided Design) are used in the design of the casting system of a miniaturized simple-cubic cell structure. The cast part has a complex shape profile and needs a high surface finish with strict dimensional tolerance. The alloy used to fill the mold is an aluminum bronze shape memory alloy (SMA). CAD was used to model the part and the proposed models for casting optimization. ProCAST software was used for the numerical simulation of the casting process. Experimental parameters were used as input data for the numerical simulation. The simulation results were analyzed focusing on the identification of defects in the Cu–Al–Mn SMA simple-cubic structures. Different feeding systems have been designed to eliminate the identified defects. Concerning the molten recirculation, the optimal nozzle model has a truncated cone profile, with a larger radius of 6.5 mm, a smaller radius of 2.0 mm and a height of 8.0 mm (called here model 3). Experimental observations from cast SMA parts agree with the simulated results of the optimized nozzle model 3. In addition to the elimination of alloy recirculation with the nozzle optimization in this work, the shrinkage porosity at the upper base of the part was eliminated with the addition of a compensation volume close to the region where porosity is more intense. By exploring the possibilities offered by commercial software, the work contributes to advance the knowledge and application of the non-traditional investment casting process, highlighting its advantages and potential applications.

An automated topology optimization interpreter that generates space frames

This paper presents the methodology and theoretical foundation of topology optimization (TO) Results Spaceframe Interpreter, an automatic TO results interpreter that generates a closely associated space frame consisting of welded structural tubing or rectangular bars. TO is a computational technique that uses a finite element (FE) formulation to identify the most weight-efficient structure within a design domain. Density-based TO results in structures that take organic forms and is usually a tedious and cumbersome process to generate a computer-aided-design (CAD) model to manufacture through conventional techniques. The optimal topology frequently resembles a space frame, which is well-known as being a rigid, lightweight structure. The methodology of the TO results interpreter leverages several techniques from volumetric image processing and has four primary processes. First, the results are obtained from commercial FE/TO software and mapped into a cubic grid of voxels. Second, junction locations are extracted and member connectivity that represents a frame is identified. Third, a sizing optimization is incorporated to determine appropriate sectional dimensions of the circular or rectangular space frame members. Fourth, the optimized space frame geometry is imported into a CAD design tool to automatically create a design model. The logic and are implemented within the frame extraction processes. The automated TO interpreter is designed to interact with commercial FE analysis and CAD systems. The interpreter is demonstrated on various spatial examples including aerospace and automotive applications. In each case, the welded space frame closely resembles the TO result, with nearly equivalent stiffness and mass.

Towards Machine Learning-Based FPGA Backend Flow: Challenges and Opportunities

Field-Programmable Gate Array (FPGA) is at the core of System on Chip (SoC) design across various Industry 5.0 digital systems—healthcare devices, farming equipment, autonomous vehicles and aerospace gear to name a few. Given that pre-silicon verification using Computer Aided Design (CAD) accounts for about 70% of the time and money spent on the design of modern digital systems, this paper summarizes the machine learning (ML)-oriented efforts in different FPGA CAD design steps. With the recent breakthrough of machine learning, FPGA CAD tasks—high-level synthesis (HLS), logic synthesis, placement and routing—are seeing a renewed interest in their respective decision-making steps. We focus on machine learning-based CAD tasks to suggest some pertinent research areas requiring more focus in CAD design. The development of open-source benchmarks optimized for an end-to-end machine learning experience, intra-FPGA optimization, domain-specific accelerators, lack of explainability and federated learning are the issues reviewed to identify important research spots requiring significant focus. The potential of the new cloud-based architectures to understand the application of the right ML algorithms in FPGA CAD decision-making steps is discussed, together with visualizing the scenario of incorporating more intelligence in the cloud platform, with the help of relatively newer technologies such as CAD as Adaptive OpenPlatform Service (CAOS). Altogether, this research explores several research opportunities linked with modern FPGA CAD flow design, which will serve as a single point of reference for modern FPGA CAD flow design.

Three-Dimensional Printing and the Art of Making Small Working Prototype Spectrometers

In the past, moving from a concept for an analytical instrument to actually producing a functioning instrument was a relatively tedious and lengthy process. The traditional approach was to draft a design and then go through a number of iterations, along with design reviews and sign-offs. Today, if one has a good designer who is well-versed in computer-aided design (CAD) engineering software, then it is possible to significantly reduce the time to develop a good-looking functional design. However, the time to go from the CAD design to a complete piece of hardware is typically the longest part of the process. It is not unusual for machine shop delays to be up to 6–8 weeks. Today, such delays can be eliminated by producing the designed parts on a desktop with a three-dimensional (3D) printer. This article shows, by example, how a 3D printer can speed up the process of making prototype hardware for a spectral measurement system, shortening the time to produce functional hardware from weeks to days—or less.

Utilizing ChatGPT to assist CAD design for microfluidic devices.

ChatGPT is a generative AI model that has garnered tremendous public interest due to its ability to solve diverse problems through high-level reasoning and analysis. Among its features is an ability to create and debug code. While this capability has been explored with conventional programming languages such as Python, it has yet to be applied to computer-aided design (CAD). In this work, we utilized GPT-4 to create functional microfluidic components using OpenSCAD, an open-source CAD software package. Through an iterative dialogue, GPT-4 created functional designs for a helix/spiral, a valve, a t-junction, and a serpentine channel. This concept could facilitate CAD in the future for both technical and non-technical users and can be reasonably extended to other fields.

Effect of Horizontal Resolution of Printer on Trueness of 3D-Printed Provisional Crown: An In Vitro Study

Abstract Objectives Provisional crowns play an integral role in prosthodontic therapy and need to be fabricated with high accuracy to ensure good marginal fit and proper contour. The aim of this study is to evaluate the effect of 3D printer's horizontal pixel resolution on trueness of the intaglio surface, external surface, and marginal area and the actual marginal adaptation of the interim crowns. Materials and Methods A gypsum reference model of mandible with a prepared right first molar was scanned with a dental laboratory scanner (AutoScan-DS-MIX, Shining 3D) and a digital provisional crown was design using the computer-aided design (CAD) software (Exocad). The provisional crown was manufactured by two printers with different horizontal resolutions (Sonic Mini 4K Printer and Sonic Mini 8K Printer). The printed crowns were scanned using the aforementioned scanner. The trueness of the external surface, internal surface, and marginal area of the provisional crowns was evaluated by comparing the scanned data with the reference CAD design data using a 3D inspection software (Geomagic Control X, 3D systems). The trueness of the crown manufactured by two printers was compared by a two-sided test (α = 0.05). Finally, the marginal adaptation of the provisional crowns was evaluated on the printed removable dies and compared. Results The results revealed that there was a significant difference in the trueness of the marginal area and the marginal adaptation (p &lt; 0.05). Conclusions It can be concluded that the trueness of provisional crown marginal area and the marginal adaptation was affected by the horizontal resolution of the 3D printer.

A cognitive design assistant for context-aware computer-aided design

Computer-Aided Design (CAD) plays a crucial role throughout a product's life cycle, especially regarding detecting design errors early on. To date, for complex engineered systems, the detection of design errors in a digital mock-up. It is a reactive and laborious activity that requires a complete CAD design before searching for applicable design rules in a set of large and unstructured design guidelines containing hundreds or thousands of design rules and making sure that the design complies with the applicable rules. This paper will illustrate how a context-aware cognitive design assistant, a seamless, ubiquitous and intelligent computer program, can sense relevant data of a CAD context to provide, without explicit user intervention, proactive and on-the-fly recommendations of relevant design rules, where relevancy depends on the designer's task. To illustrate the feasibility of the proposal, the cognitive design assistant will be integrated with the 3DExperience CAD software. The functional demonstrator shows that this proactive approach will not only reduce design iterations usually due to a-posteriori checks but also deal with any kind of design rules rather than a specific set of geometry and topology constraints verified by design checkers based on IF-ELSE instructions.

Design and Development of Sugarcane Leaf Stripper

Background: India is the second largest producer of sugarcane in the world. Uttar Pradesh, Maharashtra, Punjab and Bihar are Indian states have maximum production of sugarcane. During 2019, approximately 307 lakh tonnes of sugarcane was produced in India, which is nearly 11.8 per cent of the global sugarcane production. Sugarcane crop has very long leaves. Stripping of sugarcane leaves is a major problem, which requires labor-intensive effort. Therefore, to resolve this problem, a tractor operated sugarcane stripper machine was designed using the computer aided design (CAD) software. Methods: In main frame of CAD design, a power transmission system, transportation system, feed hopper conveyer, sugarcane de-topper and a stripper system were designed. This machine will reduce human drudgery. Currently, this sugarcane stripper machine is getting very good acceptance nationwide. Further research has been undertaken at Department of Farm Machinery and Power Engineering, Sam Higginbottom University of Agriculture Technology and Sciences, Prayagraj, Uttar Pradesh, India. This machine was designed. Result: Use of this machine will also help in reducing the cost and time of operation. In future, this machine will help in improving quality of stripping as well as ensuring effective utilization of the resources. The Design and development of sugarcane leaf stripper machine will play a significant role.

Machine learning-enabled optimization of extrusion-based 3D printing.

Machine learning (ML) and three-dimensional (3D) printing are among the fastest-growing branches of science. While ML can enable computers to independently learn from available data to make decisions with minimal human intervention, 3D printing has opened up an avenue for modern, multi-material, manufacture of complex 3D structures with a rapid turn-around ability for users with limited manufacturing experience. However, the determination of optimum printing parameters is still a challenge, increasing pre-printing process time and material wastage. Here, we present the first integration of ML and 3D printing through an easy-to-use graphical user interface (GUI) for printing parameter optimization. Unlike the widely held orthogonal design used in most of the 3D printing research, we, for the first time, used nine different computer-aided design (CAD) images and in order to enable ML algorithms to distinguish the difference between designs, we devised a self-designed method to calculate the "complexity index" of CAD designs. In addition, for the first time, the similarity of the print outcomes and CAD images are measured using four different self-designed labeling methods (both manually and automatically) to figure out the best labeling method for ML purposes. Subsequently, we trained eight ML algorithms on 224 datapoints to identify the best ML model for 3D printing applications. The "gradient boosting regression" model yields the best prediction performance with an R-2 score of 0.954. The ML-embedded GUI developed in this study enables users (either skilled or unskilled in 3D printing and/or ML) to simply upload a design (desired to print) to the GUI along with desired printing temperature and pressure to obtain the approximate similarity in the case of actual 3D printing of the uploaded design. This ultimately can prevent error-and-trial steps prior to printing which in return can speed up overall design-to-end-product time with less material waste and more cost-efficiency.

3D printed superhydrophobic structures for sustainable manufacturing benefits: An overview

Superhydrophobic properties have been present in nature for many millennia before human beings discovered their true capabilities and utilized them to revolutionize modern societies. The most familiar form of hydrophobicity found in nature is that of the lotus leaf, where its ultra-low water adhesion and self-cleaning properties make it one of the best hydrophobic elements formed naturally. Since its discovery, artificially created superhydrophobic elements have been used in many industries --maritime, automobile, and medical -- due to their self-cleaning, antibacterial, and corrosion-prevention properties. However, for a surface to become superhydrophobic, it must possess a greater roughness. To achieve this, microscopic- or nanoscopic-level modifications must be made to the surface through various experimentations. For a surface to be considered superhydrophobic, it must have a water contact angle greater than 150°. One cost-effective method of manufacturing superhydrophobic materials is three-dimensional (3D) printing (additive manufacturing), which has been gaining popularity in the recent past. A 3D printing design is initially created using computer-aided design (CAD) software. Then, the design information is transferred to a 3D printer through digital slicing of the CAD design. 3D printing allows the printing of objects with various functionalities at pre-designed locations in the object, so it is important to investigate these phenomena. This paper provides an overview of several studies that were conducted to achieve superhydrophobicity through the 3D printing process. The following section of the manuscript includes an introduction, literature review, methods of increasing surface roughness for superhydrophobicity, market-available 3D printing materials, and their applications, discussion on 3D printing technologies and concluding remarks.

SOFAR and Auto-link: software tools that bridge the gap between multirotor drone design optimization and CAD

Several types of tools are used to develop drones. Computer-aided design (CAD) is used for developing the drone geometry, and software such as ComQuest Venture’s Typhon UDX is used for aerodynamic analysis. Presently, both are used independently, and a user then manually bridges the gap between the analysis and the CAD to create a final aerostructure. This manual process can lead to long design times and information transfer errors. An automated design process that automatically selects parts from a database optimizes drone parts cost, while meeting key performance requirements could shorten the design time. This paper presents the Sensible Optimization for Aerial Robots tool for automatically minimizing drone systems’ cost using a commercial component database and linking it directly to CAD software. As drones become increasingly popular, this streamlining of the drone development process will reduce both the time and cost required to develop an optimal structure.

The multi-user computer-aided design collaborative learning framework

New developments to computer-aided design (CAD) software transform a once solitary modelling task into a collaborative one. The emerging multi-user CAD (MUCAD) systems allow virtual, real-time collaboration, with the potential to expand the learning outcomes and teaching methods of CAD. This paper proposes a MUCAD collaborative learning framework (MUCAD-CLF) to interpret backend analytic data from commercially available MUCAD software. The framework builds on several existing metrics from the literature and introduces newly developed methods to classify CAD actions collected from users’ analytic data. The framework contains two different classification approaches of user actions, categorizing actions by action type (e.g., creating, revising, viewing) and by design space (e.g., constructive, organizing), for comparative analysis. Next, the analytical framework is applied via a collaborative design challenge, corresponding to over 20,000 actions collected from 31 participants. Illustrative analyses utilizing the MUCAD-CLF are presented to demonstrate the resulting insight. Differences in CAD behaviour, indicating differences in learning, are observed between teams made up entirely of novices, entirely of experienced users, or a mix. In pairs of experts and novices, we see both a perceived high-satisfaction apprenticeship experience for the novices and preliminary evidence of an increase in expert design behaviours for the novices. The proposed framework is critical for MUCAD systems to make the most of the educational possibility of combining technical skill-building with team collaboration. Preliminary evidence collected in a fully-virtual design learning activity, and analyzed using the proposed MUCAD-CLF, shows that novice students gain advanced CAD design knowledge when collaborating with experienced teammates. With the user data captured by modern MUCAD software and the MUCAD-CLF presented herein, instructors and researchers can more efficiently assess and visualize students’ performance over the design learning process.