How does it work? One new application integrates machine learning into computer aided design (CAD). This process has been coined generative design<\/em>. The application GM is experimenting with: Autodesk\u2019s Dreamcatcher<\/em>, procedurally generates dozens of plausible designs of a given part based on a series of inputs such as required weight, strength, size, material, cost, or other performance requirements.[4] These plausible designs can be sent directly to machining to generate test parts. Real performance data of the parts can be fed back into Dreamcatcher to optimize the program\u2019s understanding of the performance implications of its design choices. What would normally take a designer several days to create a single design, can now be done in hours with multiple viable alternatives. The more parts that are designed and analyzed with dreamcatcher, the larger its knowledge base of performance outcomes \u2013 allowing it to cross-leverage knowledge from multiple different classes of parts.[1][4]<\/p>\n Currently, GM has only experimented with simple, non-drivetrain related applications. GM recently completed a pilot project to redesign a seatbelt bracket. The original part consisted of eight separate pieces. The dreamcatcher program generated 150 alternatives that were all a single piece, one of which proved to be 40% lighter and 20% stronger than the original eight-component design.[1][2][3]<\/p>\n Sample design iterations <\/em>[9]<\/p>\n GM is currently using this technology to drive two design initiatives: lightweighting<\/em>, and part consolidation. These two initiatives serve a strategy of improving fuel efficiency (lightweighting) and supply chain simplification (parts consolidation). In the near term, GM will use Dreamcather to drive these two strategies across all vehicles as part of a multiyear partnership.[5][3][1][2]<\/p>\n Unfortunately, the barrier to entry in lightweighting and parts consolidation in non-drivetrain componentry is low. To sustain its edge, GM has to shift into using machine learning to power generative design and rapid prototyping in higher value components. Naturally, drivetrain components have more performance variables and integrating performance results back into dreamcatcher as part of supervised learning <\/em>is more difficult. Undertaking this task would however allow GM to develop a real asset \u2013 a bank of performance data attached to drivetrain-specific variables that is very difficult for other companies to replicate. Early targets could include relatively simple components such as valve covers and engine blocks while the long term could shift to moving parts such as crankshafts, pistons, and transmission componentry.<\/p>\n Given the proliferation of in-vehicle data generation, GM should focus on integrating live performance monitoring of higher-value componentry into its generative design process. Sensors could understand how engine componentry is performing under various situations. Data could also be generated as part of procedure during regular maintenance at dealerships \u2013 understanding how design choices on habitually maintained parts impact long-term reliability.<\/p>\n Overall, further investment in machine learning amplified design will help give GM the cost advantage needed to sustain real incremental innovation in a highly uncertain environment. It will do this not only by compressing the design lifecycle, but by de-risking experimentation in higher value componentry.<\/p>\n Finally, I question whether the insights produced by machine learning augmented design will be limited by traditional manufacturing techniques. Will the prototypes suggested by Dreamcatcher be too complex for mass production? (See photo above).[9]<\/p>\n Words: (809)<\/p>\n Sources:<\/p>\n [1] “Project Dreamcatcher | Autodesk Research”. 2018. Autodeskresearch.Com<\/i>. https:\/\/autodeskresearch.com\/projects\/dreamcatcher.<\/span><\/p>\n [2] “Advanced Software Design Technology Leads GM To Lighter, More Efficient Vehicles”. 2018. Generalmotors.Green<\/i>. https:\/\/www.generalmotors.green\/product\/public\/us\/en\/GMGreen\/home.detail.html\/content\/Pages\/news\/us\/en\/gm_green\/2018\/0518-more-efficient-vehicles.html.<\/span><\/p>\n [3] 2018.\u00a0Gmsustainability.Com<\/i>. https:\/\/www.gmsustainability.com\/_pdf\/downloads\/GM_2017_SR.pdf.<\/p>\n [4]”Driving A Lighter, More Efficient Future Of Automotive Part Design”. 2018.\u00a0Autodesk.Com<\/i>. https:\/\/www.autodesk.com\/customer-stories\/general-motors-generative-design.<\/p>\n [5] Kvernvik, Marthe, and Marthe Kvernvik. 2018. “General Motors Applies Autodesk Generative Design Software To Develop Future Vehicles”.\u00a0TCT Magazine<\/i>. https:\/\/www.tctmagazine.com\/3d-software-news\/gm-teams-up-autodesk-generative-design-vehicle\/.<\/p>\n [6]\u00a0“How Humans And AI Are Working Together In 1,500 Companies”. 2018.\u00a0性视界 Business Review<\/i>. https:\/\/hbr.org\/2018\/07\/collaborative-intelligence-humans-and-ai-are-joining-forces.<\/p>\n [7] 2018.\u00a0Mckinsey.Com<\/i>. https:\/\/www.mckinsey.com\/~\/media\/mckinsey\/dotcom\/client_service\/%20Automotive%20and%20Assembly\/PDFs\/McK_The_road_to_2020_and_beyond.%20ashx.<\/p>\n [8]”Where To Profit As Tech Transforms Mobility”. 2018.\u00a0Https:\/\/Www.Bcg.Com<\/i>. https:\/\/www.bcg.com\/en-us\/publications\/2018\/profit-tech-transforms-mobility.aspx.<\/p>\n [9]”Generative Design: The Road To Production”. 2018.\u00a0Engineering.Com<\/i>. https:\/\/www.engineering.com\/DesignSoftware\/DesignSoftwareArticles\/ArticleID\/16973\/Generative-Design-The-Road-to-Production.aspx.<\/p>\n <\/p>\n","protected":false},"excerpt":{"rendered":" AI-driven product development may help GM find an edge in an industry that has increasingly trended towards conformity in the face of uncertainty. Can GM use machine learning to transform from a company hedging its risk by dabbling in everything new \u2013 to a company that thrives on compressed, cost effective design cycles with measurable results?<\/p>\n","protected":false},"author":11794,"featured_media":28601,"comment_status":"open","ping_status":"closed","template":"","categories":[4336,1255,346],"class_list":["post-28600","hck-submission","type-hck-submission","status-publish","has-post-thumbnail","hentry","category-generative-design","category-gm","category-machine-learning","hck-taxonomy-organization-gm","hck-taxonomy-industry-auto","hck-taxonomy-country-united-states"],"connected_submission_link":"https:\/\/d3.harvard.edu\/platform-rctom\/assignment\/rc-tom-challenge-2018\/","yoast_head":"\n![](\"https:\/\/res.cloudinary.com\/engineering-com\/image\/upload\/w_1000,c_fit,q_auto,f_auto\/image008_vb4flj.jpg\")
<\/p>\n