Mechanical Engineering CAD Models

Engineering will never be the same again. For months, everyone talked about Vibe Coding. Now Vibe Engineering is becoming real. Last weekend, I decided to test something. Instead of opening CAD and clicking through sketches, I built a workflow where I simply described a component and let AI construct it for me. No manual modeling. No GUI-driven feature creation. Just a prompt. I wrote the technical specifications of a CAD part. Seconds later, the geometry appeared in Onshape by PTC, fully parametrized and built step by step. This wasn’t a demo from a big tech lab. It was my weekend project. And it made one thing very clear: We’re shifting from GUI-driven construction to prompt-driven construction. AI is becoming the mediator between engineer and CAD system. Core thesis: The future of CAD is not clicking features, it’s describing intent. Here’s the workflow I built: 1. I write a structured prompt with the technical specifications of the part. 2. Claude Code (embedded in an IDE, in my case Google's Antigravity) calls Claude's Opus 4.6. 3. Opus 4.6 generates parametrized Python code that constructs the part sequentially. 4. Claude Code executes that Python code. 5. The code activates an MCP server and sends REST API calls for every construction step. 6. Onshape by PTC builds the geometry automatically, feature by feature. Intent → code → API → geometry. The consequences are hard to ignore: • Massive acceleration of construction tasks • Near-instant design iterations • Lower barrier to entry for CAD tools • Engineers shift from “modeling operators” to “design architects” Yes, you still need engineering expertise. You still need to understand tolerances, constraints, manufacturability. But execution is no longer limited by tool fluency. The bottleneck is moving. From mouse skills to clarity of thought. From feature clicking to technical articulation. CAD is becoming democratized. If you can clearly formulate what should exist and give technically clean instructions, you can construct. Vibe Engineering isn’t hype. It’s already possible. The question is: Are we ready to train engineers for a world where describing intent matters more than mastering the interface? Vlad Larichev | Timmo Sturm | Dr. Pascalis Trentsios | Rick Bouter | Holger Wienecke

Ever felt like your engineering toolchain is working against you instead of with you? Imagine you’re a designer optimizing a gas turbine blade—but you’re not the top expert in every tool you need. Requirements, CAD, simulation, post-processing… and you’re supposed to bounce between systems, interpret results, and iterate fast. Now imagine having an AI Engineering Orchestrator as your partner in crime. In this video, Julian Waldmann shows how an AI Engineering Orchestrator can jump across NX Modeling, Polarion, Hypermesh, and HyperView—pulling requirements, updating design, running validation, checking performance, nesting, build job preparation and iterating back within minutes. Now imagine handing it 100 or even 1,000 DOE iterations. No sleep needed for the agent. ▶️ Watch the video—this gives you a glimpse of what industrial AI will be able to do for Additive Manufacturing Engineers. Accenture Siemens Digital Industries Software Vivek Kaushik Siemens Industry Mareike Oltmann #AdvancedManufacturing #AI #AdditiveManufacturing

Today, Backflip AI is unveiling a new Foundation model that can build precise, engineering parts in existing 3D design packages. This breakthrough will dramatically accelerate the pace of hardware development and drive down the cost of manufacturing. Our new AI model solves the long-standing pain of converting a 3D scan into a parametric CAD model. In one click. We finally did it. 3D scanners map the surface of an object with incredible precision, quickly generating millions of data points, but they produce micro surface textures that can’t be manufactured with traditional tools. Our technology automatically converts these intricate surfaces into clean geometries designed for existing 3D CAD and manufacturing software. The first model will be available to early users in a month. You can access it online, or through a SOLIDWORKS plugin. After the AI generates a 3D model, it will drive Solidworks to create a native file with a full feature tree you can edit. Here's a cool article from Michael Alba at engineering.com (link in the comments). There are two target users for this new AI model. The obvious one is existing CAD designers who want to save hours of their life by automatically converting a scan to CAD. We're so excited to be done doing that by hand. The second set of users is much bigger. For a given automotive factory, there may be 1-2 CAD engineers, and 2,000-5,000 brilliant, mechanically savvy technicians assembling the cars / keeping the lines running. But many don't know CAD. Our new AI model will flatten the learning curve and help them get all the parts around them into parametric CAD. In the near future, everyone will be able to create the world around them.

I’ve created a step-by-step video course on how to model a Formula 1 car in SOLIDWORKS 🏎️👉 https://lnkd.in/eZbDrbEn This steering wheel is just one piece of the much bigger project. Inside the full course, I guide you through: ✅ Building a complete Formula 1 car from scratch in SOLIDWORKS ✅ Running CFD simulations to analyze aerodynamics ✅ Identifying drag problems and design flaws ✅ Making smart design changes that reduce drag and boost downforce by +236% (!) One comment I often hear is: “In real life you don’t have perfect blueprints available.” I actually think differently. In fact, as a Lead Product Designer myself, I always use underlayers when creating new designs. An underlayer doesn’t have to be a perfect technical line drawing — it can also be a picture of a similar product or even a simple hand sketch. The point is: you don’t have to start from a completely blank sheet in SOLIDWORKS. Having a visual reference accelerates creativity and keeps your design process structured. The course isn’t just about modeling a car — it’s about learning how to think and work like a SOLIDWORKS pro. By the end, you’ll have the skills to design, analyze, and optimize complex products that impress clients, employers, and even yourself. Curious to get started? In the free preview, I’ll kick things off by modeling an F1 driver helmet step by step 🏎️👉 https://lnkd.in/eZbDrbEn #SOLIDWORKS #SolidWorksTutorial #SolidWorksDesign #SurfaceModeling #CAD #3DModeling #3DDesign #EngineeringDesign #MechanicalEngineering #ProductDesign #EngineeringEducation #Innovation #CFD #AutomotiveDesign #Formula1 #CADDesigner #DassaultSystems

𝗩𝗶𝗯𝗲 𝘆𝗼𝘂𝗿 𝗖𝗔𝗗! 𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲 𝗶𝘀 𝗻𝗼 𝗹𝗼𝗻𝗴𝗲𝗿 𝗷𝘂𝘀𝘁 𝘄𝗿𝗶𝘁𝗶𝗻𝗴 𝗰𝗼𝗱𝗲 - 𝗶𝘁’𝘀 𝗺𝗼𝘃𝗶𝗻𝗴 𝗶𝗻𝘁𝗼 𝗶𝗻𝗱𝘂𝘀𝘁𝗿𝗶𝗮𝗹 𝗱𝗼𝗺𝗮𝗶𝗻𝘀🏭 What started as a developer tool is now touching real engineering workflows. With a new plugin, Claude Code can connect directly to Onshape and work with true parametric CAD models Instead of stopping at scripts and code, Claude can now directly: ✏️ Turn sketches or reference images into editable 3D CAD parts 💬 Modify geometry via chat: fillets, holes, gears, patterns, wall thickness 🔁 Iterate without rebuilding models from scratch 🌳 Operate on real feature trees and parameters - not meshes or exports Claude Code is spreading from classical coding tasks into physical-world engineering. What this enables: • Concept-to-CAD cycles measured in hours • Natural-language customization of parts at scale • Faster collaboration between software, mechanical, and manufacturing teams • Lower barrier for non-CAD experts to explore real designs 𝗧𝗵𝗲 𝗯𝗶𝗴𝗴𝗲𝗿 𝘀𝗵𝗶𝗳𝘁 𝗯𝗲𝗵𝗶𝗻𝗱 𝗶𝘁: Classical software tools are moving into the background and AI orchestrators are becoming the only interface experts actually need in 80% of cases. What do you think - will the graphical user interface disappear from industrial workflows? If so, when?

𝗕𝗮𝗹𝗮𝗻𝗰𝗶𝗻𝗴 𝗔𝗰𝗰𝘂𝗿𝗮𝗰𝘆, 𝗦𝗽𝗲𝗲𝗱 & 𝗠𝗲𝗺𝗼𝗿𝘆 𝗶𝗻 𝗙𝗶𝗻𝗶𝘁𝗲 𝗘𝗹𝗲𝗺𝗲𝗻𝘁 𝗔𝗻𝗮𝗹𝘆𝘀𝗶𝘀 I’ve just released a 150-page guide that distills 11 critical trade-offs faced by every FEA analyst when transforming CAD into credible results. Download the PDF below and keep it handy for your next simulation. 𝗪𝗵𝗮𝘁’𝘀 𝗶𝗻𝘀𝗶𝗱𝗲 • The “Accuracy-Speed-Memory” triangle: Understand where higher-order elements or sparse iterative solvers fit on the spectrum and how to achieve a balanced solution.   • Mesh and element strategy: Adaptive refinement checklists, aspect-ratio warning signs, and when quadratic is preferable to linear.   • Dimensional reduction for smart modeling: Make informed choices between 1D, 2D, or 3D; decision tables illustrate the cost of neglecting out-of-plane effects.   • Solver showdown: Direct vs. iterative, modal vs. full frequency response, plus a brief “million-DOF” rule of thumb.   • Contact and nonlinearity playbook: Penalty vs. Lagrange, tiers of friction modeling, and tips for convergence.   • Material-model ladder: From Hooke’s law to coupled viscoplastic-damage, with advice on when “simple” is the smarter choice.   • Hardware and workflow acceleration: CPU, GPU, cloud, and automation scripts that transform late-night meshing into coffee-break tasks. Each section concludes with actionable heuristics and, in some cases, flowcharts (e.g., implicit vs explicit time integration), allowing you to justify your design choices during reviews. Simulation success is no longer limited by compute power alone—it depends on engineering judgment, such as knowing where to invest in fidelity and where to conserve cycles. Master these trade-offs, and you’ll deliver results that are both reliable 𝘢𝘯𝘥 timely. So, read the PDF, and let’s talk about which trade-off trips you up the most often. 1. Which of the 11 trade-offs do you struggle with the most in day-to-day projects, and why?  2. What is your bottleneck in transitioning from CAD to Mesh?  3. What rule of thumb assists you in deciding between direct and iterative solvers for large assemblies?  4. How have cloud or GPU resources influenced the way you mesh or model compared to five years ago?     P.S. What trade-off surprised you? 

⚡ Free n8n Workflow for CAD-BIM 𝗔𝗨𝗧𝗢𝗠𝗔𝗧𝗘𝗗 𝗘𝗟𝗘𝗠𝗘𝗡𝗧 𝗖𝗟𝗔𝗦𝗦𝗜𝗙𝗜𝗖𝗔𝗧𝗜𝗢𝗡 𝗪𝗜𝗧𝗛 𝗟𝗟𝗠 & 𝗥𝗔𝗚 (works with Revit/IFC/DWG/DGN) Today, BIM and CAD specialists still spend significant time manually classifying elements, checking attributes, and aligning models with internal standards. This process is becoming more and more like what we did in the past: ▪️ photos were sorted into albums by hand ▪️ forum posts required careful selection of the “right category” ▪️ finding a video meant endless navigation through folders ML and AI have already freed us from that routine — and the same shift is now happening with CAD-BIM projects. LLMs and RAG will gradually take over the tasks of classification and data validation, while specialists evolve from “operators” to process architects. When trained with RAG on your BIM Execution Plan (BEP) or internal classification rules in XLSX or PDF format, the workflow acts as an intelligent auditor that can: ▪️ detect classification errors ▪️ highlight deviations from corporate naming standards ▪️ suggest corrections based on accumulated knowledge 𝗛𝗼𝘄 𝘁𝗵𝗲 𝗻𝟴𝗻 𝘄𝗼𝗿𝗸𝗳𝗹𝗼𝘄 𝘄𝗼𝗿𝗸𝘀 1️⃣ Conversion — Revit / IFC / DWG / DGN → Open Database 2️⃣ Extraction — clean headers & select grouping parameter 3️⃣ Grouping — count elements & volumes 4️⃣ LLM + RAG — automatic classification by codes & standards 5️⃣ Reporting — Excel & HTML with summaries and charts Processing 1,000 elements with GPT-4.1-mini costs only a few cents. For maximum accuracy, I recommend the most effective models - Opus 4, Grok 4, Gemini 2.5 and ChatGPT5. 𝗣𝗮𝗿𝗮𝗱𝗶𝗴𝗺 𝘀𝗵𝗶𝗳𝘁 We’re moving from manual quality control to probability management. BIM professionals will increasingly act as conductors: defining rules, training models on corporate data, and making decisions in edge cases. This isn’t about replacing expertise - it’s about amplifying it: less routine, more analysis and decision-making. Explore the workflow: 🔗 𝗚𝗶𝘁𝗛𝘂𝗯: https://lnkd.in/eJyaySSR 📄 File: n8n_5_CAD_BIM_Automatic_Classification_with_LLM_and_RAG.json Examples of project classifications according to different classifiers will be posted later in our telegram group (links in messages). Distributed small solutions, simple 𝗻𝟴𝗻 𝘄𝗼𝗿𝗸𝗳𝗹𝗼𝘄 𝗰𝗿𝗲𝗮𝘁𝗲 "𝗮𝗻𝘁𝗶𝗳𝗿𝗮𝗴𝗶𝗹𝗶𝘁𝘆" for business - which is of course extremely boring in calm times, but extremely vital during crises. 𝗧𝗵𝗼𝘀𝗲 𝘄𝗵𝗼 𝗰𝗮𝗻𝗻𝗼𝘁 𝗯𝗲 𝗮𝗻𝘁𝗶𝗳𝗿𝗮𝗴𝗶𝗹𝗲 𝗱𝘂𝗿𝗶𝗻𝗴 𝗽𝗲𝗿𝗶𝗼𝗱𝘀 𝗼𝗳 𝘁𝘂𝗿𝗯𝘂𝗹𝗲𝗻𝗰𝗲 - 𝗹𝗲𝗮𝘃𝗲 𝘁𝗵𝗲 𝗺𝗮𝗿𝗸𝗲𝘁. 👉 If you need help testing n8n solutions with RAG and LLM on your data or adapting the workflow to real project tasks, contact us. ♻️ Share this with colleagues who still believe that manual checking and classification is “normal work.” In reality, these tasks can already be automated with LLMs and n8n workflows.

Not all CAD models are created equal! On the left is a highly detailed CAD model, great for visualization, documentation and manufacturing intent. But when it’s time for numerical simulations, those fine details make the mesh dense, needlessly intricate and the solver unnecessarily heavy. That’s when you can use a CAE optimized CAD model (like on the right): watered down, simplified geometry that still preserves the key stiffness, mass, and load paths. Goes easy on the mesh and solver while still being relevant. It’s not “less detail” (well, kinda it is) but it’s more of a smart simplification, helping simulations run smoother and results stay physically meaningful. Here used the same concept while analyzing the Clarke CDP152B Drill Press using an optimized model ensured realistic mode shapes without overcomplicating the setup. #CAD #CAE #FEA #SolidWorks #Ansys #Simulation #DesignOptimization #VibrationAnalysis #MechanicalDesign #Engineering

A chief engineer reached out to us today & this was top of mind for new capabilities he needs: "Modeling families of air vehicles to varying missions, Automation of performance analysis, trade studies, multi-disciplinary optimizations including cost, Design automation direct from requirements." Here's what's interesting about that list: each item forces a tradeoff: do you go low-fidelity and fast, or high-fidelity and slow. Neither option is good. You can definitely go fast drawing up quick planforms or tubes with wings, but will the design close when trying to integrate all of the real stuff? Usually you need a high-fidelity CAD model to know this, but by the time it's modeled up and nothing fits, it's too late. Higher-fidelity parametric models break when flexed, even undergoing small changes like changing the leading edge angle I've seen cause errors. Faster speed only reinforces the Lock-In Trap. Teams freeze architecture early because exploring alternatives feels too slow, and end up over many month- long cycles trying to close out the design, possibly one that might not close. Next week, he'll sit with an nTop engineer to go through a workflow that shows exactly what he's asking for: 1) UAV family modeling: Fully parametric models that never break when you change parameters. Build once, scale across your entire family. 2) Performance analysis automation: Embedded analysis (LBM, AVL/XFOIL, DATCOM, SUAVE integration) gives instant performance feedback as you modify geometry. No export workflows. 3) Trade studies & MDO: Generate hundreds of variants automatically, all simulation-ready. Zero geometry failures in optimization loops. 4) Requirements to design: Encode mission requirements directly into parametric logic that drives geometry generation. The programs that win will be the ones that stop accepting the speed vs fidelity tradeoff. If you're dealing with the same constraints, DM me.

In CAD, every hinge is perfect. But in reality, nothing ever moves that clean. When I first started designing assemblies, I trusted the geometry with closed eyes. If it rotated in CAD, it would rotate in real life… right? ➥Wrong. That’s where motion simulation in Solid Edge changes the game. Here’s what it shows you before the shop floor does: ➮ Clearances that look fine in 2D — but bind once gravity and real tolerances join the picture ➮ “Ideal” pins or bolts that actually flex, shear, or seize under load ➮ Collisions you’ll never notice in a static model until it’s too late It’s not just about movement. It’s about truth: how parts behave when friction, mass, and gravity step in. CAD doesn’t care if your lever jams or your linkage binds. But the shop floor will. Motion simulation lets you see it and fix it before steel is cut. What’s the biggest surprise you’ve caught in motion simulation before it reached the shop? #engineering #cad #solidworks #solidedge #dfm #designformanufacturability #projektdesign #mechanicalengineering #manufacturing #simulation #stressanalysis