BLOG
BLOG
2021. 12. 8. | Time to read: 2 min
Drishti 이사회의 설립자이자 회장인 Prasad Akella박사는 기술을 사용하여 인간의 능력을 확장하는 세 번째 거대한 시장 카테고리를 만들고 있습니다. 1990년대에 프라사드는 세계 최초의 협동 로봇 (‘cobots’, 2025년까지 120억 달러의 시장이 될 것으로 예상되는 예상됨 코봇)을 개발한 제너럴 모터스 팀을 이끌었습니다. 2000년대 초, 소셜 네트워킹의 선구자인 Spoke의 공동 설립자로서, 현재 수조 달러의 가치를 가진 거대한 소셜 그래프를 구상하고 그 구축을 지원했습니다. 현재는 Drishti에서 AI 기반 생산이라는 형태로, AI의 인식력과 공장에서의 인간의 유연성을 조합하는 것에 임하고 있습니다. Prasad는 캘리포니아 마운틴 뷰에 기반을 두고 있습니다.
Digital twins combine all the best elements of a simulation, 3D CAD model, bill of materials and data from connected devices to produce a system of systems that interoperates between different technology platforms. By spanning the entire engineering lifecycle, a digital twin allows for continuous improvements to be tested and implemented at any stage of the manufacturing process in a digital environment that is much cheaper to operate compared to the physical world.
By making product modeling much easier, faster and more accurate, how goods are produced is drastically changed. In the future, with the help of digital twins, manufacturers will be able to produce customized goods at a similar price point to mass manufactured goods.
There is only one issue with this future: When it comes to taking advantage of digital twin technology, assembly operations will be left behind. Factories that still rely on 100-year-old time and motion studies vis-a-vis the traditional pen, paper and stopwatch approach are not prepared to digitally transform their lines and extend this Industry 4.0 technology to their assembly operations. The data modality that manufacturers are using to measure their team’s success needs to change, and the data needs to be scaled and shared across systems. Executing on such an initiative takes Drishti.
Drishti is the execution element of digital twins
By using Drishti’s AI and computer vision to capture metrics on things like cycle times, defect rates and standardized work adherence, a physical assembly line can be paired with its digital counterpart. That data can then be analyzed and shared across teams using Drishti’s platform to pull out insights and decide which stations need to be optimized.
Take line balancing for example. Since industrial engineers can’t run kaizens on a continuous basis, and coupled with the frequency of market demand changes and process changes, manufacturers need a more optimal starting point. Drishti’s platform makes it easy for anyone, not just industrial engineers, to see where changes need to be made.
No longer does a line supervisor’s time need to be wasted gathering data; it can now be applied to taking action. Industrial engineers can save time and use the data to actually address line issues. With Drishti, everyone can conduct mini-kaizens at any time – this is the Drishti-driven world of continuous improvement.
Bringing it all together
This digital lean approach arms the management team with data that is now more easily quantifiable and gives them a visual representation of how their line is functioning. When paired with Drishti, digital twin technology no longer has to omit human activities from its simulations. AI-powered assembly production creates the data sets that have been missing from digital twins to generate a digital assembly line.
As products continue to get more complex, technological convergence will be imperative. Platforms will need to cooperate with each other to provide more in-depth capabilities, so the best decision can always be made. As information inefficiencies are solved, assembly operations will be able to receive more value.
