星期一, 6月 30, 2025

AI在PCB Design的應用

Overview of Circuit Design


From Circuit to Board, Optimized, Circuit Fundamentals Review


PCB

    AI 在PCB設計的應用 KiCad, Zener by Diode Computers


    PCB trace routing by A*
    • ATmega328P the heart of the Arduino Uno (by Black Hunter), A* for trace routing, parameter opt, cosmetic credic: ATmega328P — A* Trace Routing (student project showcase: Black Hunter)


    鑽孔路徑演算法 by A*











    Reference

    AI Assisted PCB Pipeline Process (share)

    TSP 優化推進 PCB 製造業發展研究報告 (英文版含文獻 )


    Course strcture

    From Circuit to Board, Optimized
    ├── 1. PCB Fundamentals
    │     ├── AI 在PCB設計的應用 (KiCad, Zener/Diode Computers)
    │     ├── AI Assisted PCB Pipeline Process
    │     └── [Bridge Unit] Circuit Fundamentals Review ← restore this
    ├── 2. A* Trace Routing
    │     ├── ATmega328P: A* routing, parameter opt, cosmetic
    │     │     └── Crystal 石英振盪電路 (slides) ✓
    │     └── Differential Pair: A* routing, parameter tune-up
    ├── 3. A* Drill Path
    │     ├── 鑽孔路徑演算法 by A*
    │     └── 電路板鑽孔程序模擬
    ├── 4. TSP Optimization
    │     └── Research Report (英文版含文獻)
    └── 5. RL Optimization
          ├── PCB Layout Optimization using RL
          └── Advanced with stopping criteria, optimized


    星期三, 6月 11, 2025

    Syllabus 科技英文與科普傳播 2025 秋天

    上課方式: 使用科技英文學習掌握AI運用技巧,從實做中學習AI領域的技術應用能力與未來科學工程素養。

    講授,工作坊,作業

    學生請自行攜帶手機,平板或筆電。

    本課程特色


    9/17/2025 - Week 2: Boosting human brains with AI

    增強AI的能力

    9/24/2025 - Week 3: Reasoning with AI for Complex Constrained Problems

    推理模式 special topic: Smart Dog Ball Retrieval

    極紫外光(EUV)光源, IEEE Spectrum: The Tiny Star Explosions Powering Moore’s Law

    AI半導體廠製程優化

    10/1/2025 - Week 4

    Timeline for dinner scheduling

    Generate programs for dinner schedule (AI半導體廠製程優化)

    River Puzzles (半導體晶圓廠情境 Part 1)

    10/8/2025 - Week 5

    AI Helper

    Follow up

    River Puzzles Part 2

    10/15/2025 - Week 6

    Follow up

    Make AI smarter

    11/5 - 期中考不上課

    11/12/2025 - Week 9: Visualization

    工程動畫 Pt 1,精選


    11/19/2025 - Week 10

    工程動畫 Pt 2

    AI 互動的基礎:如何與 AI 有效溝通 (Prompt 基礎篇) Pt 2


    11/26/2025 Scientific Animation

    Blue LED

    12/3/2025 - Week 12 High Complexity Animation

    Follow up #11

    Enhance visualization (Mul. Iter. Merg.)

    12/17/2025 - Week 14: Reinforcement Learning



    聖誕節放假


    12/31/2025 - Special Topics





    Backup

    Fractals: 美麗碎形世界



    Further Materials

    星期三, 6月 04, 2025

    EX#15 Capstone test

     1. solve the strategic thinking problem


    2. Visualize one of the scientific problems.


    3. Visualize one of the mathematical programming problems


    4.  Choose one of the following problems.

     You must implement the system from scratch based on the paper.











    Agility Training (artifact, 2d version), paper





    Agility Training (share, 3d version), paper








    EX#14 Fractals in real worlds



    4. identify hazards in a fractal 3d assessment display, first person perspective, according to a real world photo. 

    Choose any photo to proceed with.

    依據照片重建三維場景,越自然越好(例如樹木,雲層等自然物件),需考慮視角與觀測位置轉換以便可以瀏覽各處細節,至少提供三個觀察點

    至少選取一張照片(可使用自選)





    artifact (non Fractal version)



    artifact (fractal version)




















    artifact (first person perspective)









    artifact (non Fractal version)



    artifact (fractal version)





    Photo Galleries






















    Strategic thinking

      Devise a strategy for the dog in the picture to retrieve its ball that fell into the pond without getting its body wet, with no humans nearby to help."

    This is a problem-solving or creative thinking exercise asking someone to come up with a plan for how a dog could get its ball back from water without getting wet and without human assistance.

    Animate your strategy in svg or in 3d.








    Solution 1


    3D use of float bridge (thought out by Claude itself) Veo 2 (video w/ base image)

    float bridge Imagen 4, anotherVeo 2 (video)


    Solution 

    float + paddling inspired by student


    Solution 3

    3D, base 2D float push, wave making, another 2D


    solution 4

    Noodle Nudge Veo2 imagen 4






    original video on social media

    星期一, 6月 02, 2025

    Algorithms

    QuickSort  是常用的數字排序演算法,我們使用AI來視覺化它的排序過程,可以清楚看到數字如何逐漸由小排到大。 

    QuickSort 演算過程視覺化。 







    汽車導航常常需要計算兩地之間最短路徑。我們用AI視覺化一個有名的最短路徑演算法(Dijkstra's Algorithm),你可輸入網路節點數,或是你希望的視覺化方式。












    Traveling Salesman Problem 簡稱TSP

     (一個推銷員要拜訪所有客戶城市,每個城市只能拜訪一次,最後要回到出發城市,請為他/她計算最短的拜訪路徑)

    TSP在工業界有重要應用,包括物流(UPS/Amazon配送路線優化)、製造業(電路板鑽孔、機器人組裝路徑)、電信(網路路由、線路安裝)和能源(電網維護、管線檢查)。凡是需要造訪多個地點同時最小化成本、時間或距離的場合都適用。現代變體能處理容量限制、時間窗口等實際約束。企業使用OR-Tools、Gurobi等專業軟體解決這些問題,透過優化倉儲揀貨、切割模式、3D列印路徑和車隊管理等作業,往往能節省數百萬成本。


    (樸素) Visualize TSP (Traveling Salesman Problem) by A* search 使其可以改變網路節點個數

    (美學) 視覺化 A* for Traveling Salesman Problem 使其可以改變網路節點個數







    給定一個電路板,進行鑽孔程序模擬的優化 (建議 AI 一個演算法,例如A*, Greedy Method...)









    A* 演算法


    以下迷宮問題,比較 A* search 與 Dijkstra 求解過程










    Amplifier Gain and Frequency Response Using AI


    standard strategy


    solve for gain

    do not ignore bias current


    calculate miller effect

    calculate poles for lower cut off

    calculate poles for higher cut off

    plot bode plot gain vs. Hz

    plot bode plot phase vs. Hz


    lab share slides

    Make Bode plot:

    step-by-step prompt share slides

    single prompt share slides