Kentz Wong · Singapore / Shanghai
Wong Chih Chiang (Kentz) · 新加坡 / 上海

Wong Chih Chiang

黄志强

20 years running inspection lines. Now building the AI that assists the inspector.

二十年深耕检测产线,如今打造辅助检测员的 AI。

R&D and technical leader with 20+ years in electronics manufacturing and automated inspection and test (AOI · SPI · AXI · ICT). Former R&D Director and Support Director, PMP®-certified, now applying computer vision and machine learning to real production problems.

研发与技术负责人,在电子制造与自动化检测和测试(AOI · SPI · AXI · ICT)领域拥有 20 多年经验。曾任研发总监与支持总监,持有 PMP® 认证,现将计算机视觉与机器学习应用于真实的生产问题。

Open to roles in R&D and engineering management, project management, technical service leadership and applied AI for manufacturing, in Singapore or the Suzhou–Shanghai region.

开放机会:研发与工程管理、项目管理、技术服务管理,以及面向制造业的应用 AI 相关职位,工作地点为新加坡或苏州—上海地区。

Download Resume (PDF)下载简历(PDF) LinkedIn Email邮件
Wong Chih Chiang (Kentz) speaking at an industry event

I'm Kentz. I build and lead the teams, products and partnerships behind automated inspection and test in electronics manufacturing. Over 20 years, I have moved from field application engineering to R&D Director and Support Director, working across SMT inspection and test (AOI, SPI, AXI, ICT, conformal-coating AOI and machine vision) for EMS, automotive and industrial customers in China, Taiwan and Southeast Asia, with programmes reaching Germany, Malaysia, Vietnam and Mexico. I stay close to the technology (PLC, vision, scripting, data) while managing scope, schedule, cost and stakeholders across cultures and time zones. PMP®-certified and fluent in English and Mandarin, I recently completed NTU's Advanced Professional Certificate in Data Science & AI and the AWS Certified AI Practitioner to bring practical machine learning and data engineering into manufacturing — and Drevoiq is where I build those ideas into working tools.

我是黄志强(Kentz)。我在电子制造领域打造并领导自动化检测与测试背后的团队、产品与合作伙伴关系。20 多年来,我从现场应用工程做起,先后担任研发总监与支持总监,覆盖 SMT 检测与测试(AOI、SPI、AXI、ICT、三防漆 AOI 及机器视觉),服务中国大陆、台湾及东南亚的 EMS、汽车与工业客户,项目延伸至德国、马来西亚、越南与墨西哥。我始终贴近技术(PLC、视觉、脚本、数据),同时跨文化、跨时区地管理范围、进度、成本与干系人。我持有 PMP® 认证,中英文流利,近期完成了南洋理工大学数据科学与人工智能高级专业证书课程及 AWS Certified AI Practitioner 认证,把实用的机器学习与数据工程带入制造业 —— Drevoiq 是我把这些想法做成可用工具的地方。

Drevoiq: dream + evolution + IQ.

Drevoiq:梦想(dream)+ 进化(evolution)+ 智能(IQ)。

Years in electronics manufacturing
电子制造从业年限
20+
Support engineers at Triertech, scaled from a 5-person core
Triertech 支持工程师人数(由 5 人核心团队扩展)
25
Coating-AOI units shipped from a platform my team built
基于我团队打造的平台出货的三防漆 AOI 设备
160+
First-year orders for a new ICT business line
ICT 新业务线首年订单
USD 1M+
Track record 履历

Experience

工作经历

From application engineer to R&D Director and Support Director in automated test and inspection: taking products from concept to commercial sale, then running the organisation that supports them in the field. Customers include EMS, automotive and industrial manufacturers in China, Taiwan and Southeast Asia, with programmes reaching Germany, Malaysia, Vietnam and Mexico.

从应用工程师成长为自动化测试与检测领域的研发总监、支持总监:既把产品从概念推向商业化销售,也管理在现场支持产品的团队。客户包括中国大陆、台湾及东南亚的 EMS、汽车与工业制造商,项目延伸至德国、马来西亚、越南与墨西哥。

Apr 2026 – Present2026年4月 – 至今

Independent Projects – Data Science, AI & Project Management独立项目 —— 数据科学、AI 与项目管理

Singapore · Self-employed
新加坡 · 自雇

Building AI tools that apply 20+ years of automated inspection experience to machine learning, alongside formal training in data science and project management. Built Defect Hunter and CalorieScanner as end-to-end applied-AI products, and completed NTU's Advanced Professional Certificate in Data Science & AI (Apr–Jul 2026), the AWS Certified AI Practitioner (Jul 2026) and PMP® (Sep 2026).

将 20 多年自动化检测经验应用于机器学习,打造 AI 工具,同时系统进修数据科学与项目管理。独立完成 Defect Hunter 与 CalorieScanner 两款端到端应用 AI 产品,并完成南洋理工大学数据科学与人工智能高级专业证书课程(2026年4月 – 7月),取得 AWS Certified AI Practitioner(2026年7月)与 PMP®(2026年9月)认证。

Open to roles in R&D and engineering management, project management, technical service leadership and applied AI for manufacturing, in Singapore or the Suzhou–Shanghai region.

开放机会:研发与工程管理、项目管理、技术服务管理,以及面向制造业的应用 AI 相关职位,工作地点为新加坡或苏州—上海地区。

Aug 2024 – Apr 20262024年8月 – 2026年4月

Support Director支持总监 — Triertech Co., Ltd.

Suzhou, China · ICT · AOI · SPI · AXI · CCAOI
中国苏州 · ICT · AOI · SPI · AXI · CCAOI

Led the after-sales organisation and the Digitaltest ICT business line for a new test-and-inspection equipment company in Suzhou, covering China and Taiwan.

为苏州一家新成立的测试与检测设备公司领导售后服务组织及 Digitaltest ICT 业务线,覆盖中国大陆与台湾。

  • Scaled a multi-product support team from a 5-person core to 25 engineers (AOI/SPI, AXI, conformal-coating AOI, ICT), with structured onboarding qualification and standard field tooling; the team was named in the company's Nepcon 2025 excellent-team commendation.
  • Secured an ICT distribution and service partnership with Digitaltest (Germany) for China, Taiwan and Southeast Asia, from first contact to signed contract in 8 weeks, and grew the line to USD 1M+ in first-year orders.
  • Turned a single service enquiry at a global industrial-drives manufacturer into a repeat key account: 2 ICT systems and 8 test fixtures across 4 orders in 7 months.
  • Closed the first Digitaltest system order under the new agreement and designed the cross-border order-to-install process (customs, terms, delivery scheduling) for imported test systems.
  • Launched an ICT calibration and maintenance service line: earned OEM certification, built the process and certificates, and calibrated 7 systems at automotive and industrial customers.
  • Contributed to development of the T7300 press-fit pin inspection system and led its field support through demos and customer evaluations; the system won Gold at the 19th Step-by-Step Excellence Awards (2025).
  • Led a 2-week OEM certification programme in Germany for 6 engineers and sales staff to launch the new ICT business line.
  • Introduced weekly service-record and labour-hour reporting for the support team.
  • 将多产品支持团队(AOI/SPI、AXI、三防漆 AOI、ICT)从 5 人核心团队扩展至 25 名工程师,建立结构化的入职资质认证与标准化现场工具;团队入选公司 Nepcon 2025 优秀团队表彰。
  • 与德国 Digitaltest 达成覆盖中国大陆、台湾及东南亚的 ICT 分销与服务合作,从首次接触到签约仅用 8 周,并推动该业务线首年订单超过 100 万美元。
  • 将一家全球工业驱动器制造商的一次服务咨询发展为持续复购的重点客户:7 个月内 4 笔订单,共 2 套 ICT 系统与 8 套测试治具。
  • 拿下新协议下的首个 Digitaltest 系统订单,并为进口测试系统设计跨境"订单到安装"流程(报关、贸易条款、交付排期)。
  • 推出 ICT 校准与维护服务线:取得原厂认证,建立流程与证书体系,并为汽车与工业客户完成 7 套系统的校准。
  • 参与 T7300 压接针检测系统的开发,并负责其演示与客户评估阶段的现场支持;该系统荣获第 19 届一步步卓越奖金奖(2025)。
  • 带领 6 名工程师与销售人员赴德国参加为期 2 周的原厂认证培训,为 ICT 新业务线的启动做好准备。
  • 为支持团队建立每周服务记录与工时报告制度。
Jan 2023 – Aug 20242023年1月 – 2024年8月

R&D Director研发总监 — Suzhou LinkWays Tech Co., Ltd.

Suzhou, China · Coating AOI · Hybrid inspection · Product roadmap
中国苏州 · 三防漆 AOI · 混合检测 · 产品路线图

Promoted to lead the R&D department across Suzhou and Taiwan (mechanical, electrical/PLC, software and vision/AI engineers).

晋升后领导苏州与台湾两地的研发部门(机械、电气/PLC、软件及视觉/AI 工程师)。

  • Owned the product roadmap and engineering delivery for the coating-AOI, Pin AOI and Hybrid Inspection System (HIS) lines.
  • Led the R&D department to ISO 9001:2015 certification (2023), working with an external consultant and building mechanical and electrical design-control documentation.
  • Drove design-for-cost and design-for-assembly changes across the range, including 1–2 hours of wiring time saved per coating-AOI unit.
  • Led local engineering of a partner's selective-fluxing system for China, resolving process-capability (CPK) issues and designing new variants, leading to a first EMS customer order.
  • Qualified a new UV coating material for 200 µm thickness inspection with a German partner, and presented inspection solutions to a leading EV maker.
  • Set R&D cost and schedule estimates for new opportunities to support go/no-go and pricing decisions.
  • 负责三防漆 AOI、Pin AOI 及混合检测系统(HIS)产品线的产品路线图与工程交付。
  • 带领研发部门通过 ISO 9001:2015 认证(2023),与外部顾问合作,建立机械与电气设计控制文件。
  • 在全系列产品中推动面向成本与面向装配的设计改进,其中每台三防漆 AOI 节省 1–2 小时接线工时。
  • 主导合作伙伴选择性助焊系统在中国的本地化工程,解决制程能力(CPK)问题并设计新机型,促成首个 EMS 客户订单。
  • 与德国合作伙伴共同验证一种用于 200 µm 厚度检测的新型 UV 三防漆材料,并向一家领先的电动汽车制造商介绍检测方案。
  • 为新商机制定研发成本与进度估算,支持立项(go/no-go)与定价决策。
Jan 2017 – Jan 20232017年1月 – 2023年1月

R&D Manager研发经理 — Suzhou LinkWays Tech Co., Ltd.

Suzhou, China · Machine vision · Test systems · AI deep learning
中国苏州 · 机器视觉 · 测试系统 · AI 深度学习

Built and led a cross-site R&D team (peak 8 engineers) in Suzhou and Taiwan that delivered 5+ inspection and test product lines.

在苏州与台湾组建并领导跨地域研发团队(最多 8 名工程师),交付 5 条以上检测与测试产品线。

  • Coating AOI: led 5 product generations in 18 months from one core platform, including simultaneous dual-side scanning; the family scaled to 160+ units shipped to 15+ EMS/OEM customer groups in China, Taiwan, Mexico and Vietnam.
  • Hybrid Inspection System (HIS-10): led a phased 2D/3D glue and pin inspection platform reaching ±20 µm pin accuracy; a Vision Award winner at the 16th Step-by-Step awards (2022).
  • Pin AOI: created a press-fit pin inspection variant for automotive connectors, with about 30 systems delivered.
  • Automotive radar test system: led a custom end-of-line test system for a global test-and-measurement OEM, from first prototype in 8 months to customer acceptance and a showcase at productronica Munich 2021.
  • AI Assembly System: originated a deep-learning assembly-verification system, from concept to the company's first AI product sales in about 7 months; team shortlisted in Taiwan MOEA's AIGO AI competition.
  • Camera-module inspection: delivered machine-vision inspection for camera-module test and sorting machines at a consumer-electronics customer, with 40 systems delivered.
  • Wrote and delivered MES and traceability integrations (SFIS, TARS, IPC-CFX) and introduced software version control.
  • Co-founded the technical partnership with Modus (Germany) that led to a licensed local-manufacturing agreement.
  • 三防漆 AOI:基于同一核心平台,在 18 个月内主导 5 代产品开发,包括双面同步扫描;该系列累计出货 160+ 台,客户涵盖中国大陆、台湾、墨西哥及越南的 15+ 个 EMS/OEM 客户集团。
  • 混合检测系统(HIS-10):主导分阶段推出的 2D/3D 点胶与插针检测平台,插针检测精度达 ±20 µm;荣获第 16 届一步步奖远见奖(2022)。
  • Pin AOI:为汽车连接器开发压接针检测机型,累计交付约 30 套系统。
  • 汽车雷达测试系统:为一家全球测试测量原厂主导定制下线测试系统,8 个月完成首台原型,最终通过客户验收,并于 2021 年慕尼黑 productronica 展出。
  • AI 装配系统:提出基于深度学习的装配验证系统构想,约 7 个月从概念走到公司首批 AI 产品销售;团队入围台湾经济部 AIGO AI 竞赛。
  • 摄像头模组检测:为一家消费电子客户的摄像头模组测试与分选设备提供机器视觉检测,累计交付 40 套系统。
  • 编写并交付 MES 与追溯系统集成(SFIS、TARS、IPC-CFX),并引入软件版本控制。
  • 共同建立与德国 Modus 的技术合作,并促成授权本地制造协议。
Jan 2015 – Jan 20172015年1月 – 2017年1月

AOI Product ManagerAOI 产品经理 — Suzhou LinkWays Tech Co., Ltd.

Suzhou, China · ViTrox 3D AOI
中国苏州 · ViTrox 3D AOI

Owned market introduction of the ViTrox 3D AOI platform in China, from presales and benchmarking to post-sales service contracts.

负责 ViTrox 3D AOI 平台在中国的市场导入,涵盖售前、对比评测直至售后服务合同。

  • Introduced the 3D AOI platform at three China sites of a global EMS provider, winning 50+ system sales.
  • Converted the installed base into support contracts covering 60+ systems, about RMB 2M a year in recurring revenue.
  • Owned go-to-market across South and East China: marketing material, 4 trade shows including Nepcon, and lead follow-up.
  • Ran user-group meetings and 6 product seminars (about 300 participants in total), after roadmap training at ViTrox in Penang.
  • Fed field benchmark results back to ViTrox R&D, and trained new application engineers.
  • 将 3D AOI 平台引入一家全球 EMS 企业的三个中国工厂,赢得 50+ 套系统销售。
  • 将已装机设备转化为覆盖 60+ 套系统的支持合同,每年带来约 200 万元人民币的经常性收入。
  • 负责华南与华东地区的市场推广:市场资料、包括 Nepcon 在内的 4 场展会以及销售线索跟进。
  • 在槟城 ViTrox 总部接受产品路线图培训后,组织用户交流会及 6 场产品研讨会(累计约 300 人参加)。
  • 将现场对比评测结果反馈给 ViTrox 研发,并培训新入职的应用工程师。
Mar 2005 – Jan 20152005年3月 – 2015年1月

Senior Application Consultant高级应用顾问 — Ellipsiz iNETest (Shanghai) Co. Ltd

Shanghai, China · AOI · SPI · X-ray across Asia and the Americas
中国上海 · 面向亚洲与美洲的 AOI · SPI · X 光检测

Progressed from Application Engineer (2005) to Senior Application Engineer (2011) and Senior Application Consultant (2012–2015) at an Agilent and ViTrox channel partner for AOI, SPI and X-ray inspection, supporting EMS customers in nine countries: China, Malaysia, Vietnam, Taiwan, Thailand, Indonesia, Mexico, Korea and Brazil.

在 Agilent 与 ViTrox 的 AOI、SPI 及 X 光检测渠道合作伙伴任职,从应用工程师(2005)晋升为高级应用工程师(2011)及高级应用顾问(2012–2015),为九个国家和地区的 EMS 客户提供支持:中国大陆、马来西亚、越南、台湾、泰国、印度尼西亚、墨西哥、韩国及巴西。

  • Led competitive benchmarks that helped win a 9-system SPI order, a 13-system AOI order and an approved-vendor-list position at a global EMS provider.
  • Resolved critical escalations, including a 90,000 ppm false-call issue traced to a software bug and fixed with the principal's R&D.
  • Cut cycle time by 2–3 seconds per board across 13 AOI lines through PLC programming, without new hardware.
  • Wrote production Perl tools and two licensed AOI software add-ons (deployed at 8+ EMS sites) linking inspection data to customer shop-floor systems.
  • Installed and brought new AOI systems into production, including a greenfield smartphone plant in Mexico.
  • Supported AOI support contracts reaching a company record of 100+ systems in China (2010); mentored new engineers and delivered on-site customer training programmes.
  • Received 4 company awards in 5 years, including the Ellipsiz Group Outstanding Staff Award 2010.
  • 主导竞争性对比评测,助力赢得一家全球 EMS 企业的 9 套 SPI 订单、13 套 AOI 订单及合格供应商名录资格。
  • 解决重大客户升级问题,包括一起 90,000 ppm 误报问题:追溯为软件缺陷,并与原厂研发共同修复。
  • 通过 PLC 编程,在不增加硬件的情况下,将 13 条 AOI 产线的单板节拍缩短 2–3 秒。
  • 编写生产用 Perl 工具及两款授权 AOI 软件插件(部署于 8 个以上 EMS 工厂),将检测数据与客户车间系统打通。
  • 安装新 AOI 系统并导入量产,包括墨西哥一座全新建设的智能手机工厂。
  • 支持 AOI 售后支持合同,2010 年在中国覆盖系统数达到公司创纪录的 100+ 套;指导新入职工程师,并为客户提供现场培训课程。
  • 5 年内获得 4 项公司奖项,包括 2010 年 Ellipsiz 集团杰出员工奖。
Nov 2003 – Mar 20052003年11月 – 2005年3月

Application Sales Engineer应用销售工程师 — Precicon Distribution & Controls (now LKH Precicon)

Singapore · Earlier career
新加坡 · 早期经历

Combined technical and sales role at an authorised Omron and Schneider Electric distributor: technical support and presales for Omron industrial automation (PLC, HMI, sensors, networks), then field sales for the West industrial zone and ownership of the Schneider / Himel / BlueLine product portfolio.

在欧姆龙(Omron)与施耐德电气(Schneider Electric)授权分销商担任技术兼销售职位:先为欧姆龙工业自动化产品(PLC、HMI、传感器、网络)提供技术支持与售前,后负责西部工业区的现场销售,并主管 Schneider / Himel / BlueLine 产品组合。

Capabilities 能力

Skills

技能

Leadership & Management

领导与管理

Program & project management (PMP®)R&D managementEngineering managementProduct managementAfter-sales & field service leadershipTeam leadership & scalingStrategic partnershipsTechnical sales & pre-salesBusiness development
项目集与项目管理(PMP®)研发管理工程管理产品管理售后与现场服务管理团队建设与扩展战略合作技术销售与售前业务拓展

Domain

行业领域

AOI · SPI · AXI · CCAOIIn-circuit test (ICT)SMT / EMS processMachine vision
AOI · SPI · AXI · CCAOI在线测试(ICT)SMT / EMS 工艺机器视觉

AI / Data

AI / 数据

Computer visionObject detectionModel compression & on-device inference (ONNX)Generative AI integrationData pipelinesPythonMachine learning
计算机视觉目标检测模型压缩与端侧推理(ONNX)生成式 AI 集成数据管道Python机器学习

Product & Delivery

产品与交付

Progressive web appsReact Native · ExpoCloud deployment (AWS Lightsail)Self-hosted infrastructureMES integrationPLC · Perl
渐进式网页应用React Native · Expo云端部署(AWS Lightsail)自建基础设施MES 集成PLC · Perl

Languages

语言

English (fluent)Mandarin 中文 (fluent)
英语(流利)普通话(流利)
Shipped 已交付

Projects

项目

Working, deployed applications. Each starts from a real production or product problem and is designed, built and shipped end-to-end.

已部署、可用的应用。每个项目都源于真实的生产或产品问题,并由我独立完成设计、构建与上线。

Defect Hunter mode-select screen — SPI, AOI, AXI and Benchmark modes, plus an in-app field guide and leaderboard
Mode select
模式选择
Defect Hunter AOI mode — tapping component-placement defects on a populated PCB, level 38, 8 of 10 defects found
AOI mode
AOI 模式
Defect Hunter AXI mode — X-ray view of a bare board, spotting a head-in-pillow solder joint hidden under a BGA package
AXI mode
AXI 模式

Defect Hunter

Live · beta 已上线 · 测试版 Industrial AI 工业 AI Try it live ↗在线体验 ↗

Why it matters: built to test how far a lightweight, on-device object-detection model can go against the same defect taxonomy a real SMT line uses — informed by two decades of running SPI / AOI / AXI stations. The self-labelling board generator doubles as a human-free training-data pipeline.

项目意义:用于验证一个轻量级端侧目标检测模型,在真实 SMT 产线所用的同一套瑕疵分类体系下究竟能走多远 —— 背后是二十年运营 SPI / AOI / AXI 工位的经验。自动标注的电路板生成器同时也是一条无需人工的训练数据管道。

A free PWA that turns real SMT quality-control inspection into a fast, replayable spot-the-defect game. Every board is procedurally generated from a seed — same seed, same board, on every device — and ships with pixel-accurate ground-truth defect labels as a side effect of how it's built, no human annotation required.

一款免费的渐进式网页应用(PWA),将真实的 SMT 品质检测流程转化为快节奏、可反复游玩的"找瑕疵"游戏。每块电路板都由种子(seed)程序化生成 —— 同一种子在任何设备上都生成同一块板 —— 并在生成过程中自动附带像素级精确的瑕疵标注,无需人工标注。

Detector shipped to the browser (int8 ONNX)
随应用下发到浏览器的检测模型(int8 ONNX)
2.7 MB
Self-labelled training boards
自动标注的训练电路板
4,000
Defect classes detected
可检出的瑕疵类别
8
Recall on 500 held-out boards, at 99.6% precision
500 块留出测试板上的召回率(精确率 99.6%)
100%

Measured on generated boards the model never saw in training — the same kind it inspects in the game, not photos from a real line.

以上数据在模型训练中从未见过的生成电路板上测得 —— 与它在游戏中检测的电路板同源,并非真实产线拍摄的图像。

Read moreShow less展开收起

How it's built

构建方式

  1. SeedOne number defines a board
  2. GeneratorDraws the board and injects defects
  3. LabelsExact defect boxes come free
  4. TrainingDetector fine-tuned on 4,000 boards
  5. CompressionQuantised to a 2.7 MB ONNX file
  6. BrowserRuns on-device in Benchmark mode
  1. 种子一个数字确定一块电路板
  2. 生成器绘制电路板并注入瑕疵
  3. 标注精确的瑕疵框随之产生
  4. 训练在 4,000 块板上微调检测模型
  5. 压缩量化为 2.7 MB 的 ONNX 文件
  6. 浏览器在 Benchmark 模式中端侧运行

Play through the three inspection stages a real board actually passes through — SPI (solder-paste print, before parts are placed), AOI (optical inspection of every visible joint), and AXI (X-ray inspection for joints hidden under BGA packages, invisible to any camera). In Benchmark mode, a small object-detection model — trained on the game's own self-labelled boards and compressed to run entirely client-side via ONNX Runtime Web — plays the AOI ladder on its own, live in your browser; you can tap in to catch whatever it misses and see exactly where its detection breaks down.

游戏还原了一块电路板真正会经历的三道检测工序 —— SPI(锡膏印刷检测,元件贴装前进行)、AOI(对每个可见焊点的光学检测),以及 AXI(针对隐藏在 BGA 封装下、任何摄像头都无法看到的焊点的 X 光检测)。在 Benchmark 模式中,一个基于游戏自动生成的标注数据训练、并压缩至可通过 ONNX Runtime Web 在浏览器端完整运行的小型目标检测模型会自行挑战 AOI 关卡 —— 当它漏检时,你可以介入补上,直接看清它的检测极限究竟在哪里。

  • Three real inspection stationsSPI checks the solder-paste print before any part is placed; AOI scans every joint a camera can see; AXI X-rays the joints hidden under BGA packages. Same defect taxonomy a real line runs on.
  • Boards that label themselvesEvery board is generated from a seed and carries pixel-accurate ground-truth boxes as a by-product, so the game doubles as an unlimited, human-free training set.
  • Benchmark mode: ML live in your browserA small object-detection model trained on thousands of self-labelled boards, compressed to a few megabytes and run entirely client-side via ONNX Runtime Web. No server round trip.
  • Honest about the gapDifficulty is one dial — subtlety — and it makes defects harder for the model too. When it misses, you tap in, and see exactly where machine vision breaks down and why a person still stands at a real AOI station.
  • Daily board, leaderboards, field guideSame seed, same board on every device, so everyone can compare scores on the day's challenge. All-time leaderboards per mode, and an in-app field guide with a sample of every defect.
  • Free, installable, offline-firstAdd it to your home screen and play without a connection. The detector runs on-device, so no board images ever leave your browser.
  • 三道真实检测工序SPI 在任何元件贴装前检查锡膏印刷;AOI 扫描摄像头可见的每个焊点;AXI 用 X 光检测隐藏在 BGA 封装下的焊点。采用与真实产线相同的瑕疵分类体系。
  • 自带标注的电路板每块板由种子生成,并作为副产物附带像素级精确的真值标注框,因此游戏本身就是一套无需人工、可无限扩充的训练集。
  • Benchmark 模式:浏览器内实时运行的 ML一个基于数千块自标注电路板训练的小型目标检测模型,压缩至几 MB 并通过 ONNX Runtime Web 完全在客户端运行,无需服务器往返。
  • 坦然面对检测盲区难度只有一个变量 —— 细微程度 —— 它同样会让模型更难检出。当模型漏检时你可以介入,亲眼看到机器视觉在哪里失效,以及为什么真实 AOI 工位仍然需要人。
  • 每日挑战、排行榜与图鉴同一种子在所有设备上生成同一块板,人人都能比较当日成绩;每个模式都有全时段排行榜;内置图鉴为每种瑕疵配有样例。
  • 免费、可安装、离线优先添加到主屏幕后无需网络即可游玩;检测模型在设备端运行,电路板图像不会离开你的浏览器。
Progressive Web App渐进式网页应用 Computer vision / ML计算机视觉 · 机器学习 Procedural generation程序化生成 On-device inference (ONNX)端侧推理(ONNX) SPI · AOI · AXISPI · AOI · AXI
defecthunter.drevoiq.com →
CalorieScanner scan tab — camera and gallery buttons, today's total of 380 out of 2,540 kcal, plus hydration and protein progress bars
Scan
扫描
CalorieScanner meal result — a breakfast of coffee, hard-boiled eggs and toast: 380 kcal, a six-nutrient grid, per-item breakdown, health tip and a Log this meal button
AI result
AI 识别结果
CalorieScanner stats tab — six-week calorie bar chart against a 2,540 kcal goal, and macros as a percentage of daily value with over-limit warnings
Trends & macros
趋势与营养素

CalorieScanner

Live · free tier 已上线 · 免费使用 Range: consumer AI 跨界:消费级 AI Try it live ↗在线体验 ↗

Why it matters: a consumer-facing AI product built end-to-end — vision model integration, multilingual UX, push notifications, PDF reporting and cloud backend — to demonstrate range beyond industrial tooling.

项目意义:一款从头到尾独立完成的消费级 AI 产品 —— 视觉模型集成、多语言体验、推送通知、PDF 报告与云端后台 —— 用以证明工业工具之外的产品能力。

Snap a photo, know your calories instantly — no food search, no barcode scanning. CalorieScanner is an AI-powered nutrition tracker that runs in the browser and installs to your home screen on iOS and Android. Point the camera at a meal and the AI model identifies what's on the plate — restaurant dishes included — and returns calories, protein, carbs, fat, sugar and sodium, an item-by-item breakdown and a short health tip, in seconds. One tap logs it against your daily goal.

拍一张照片,立刻知道卡路里 —— 无需搜索食物,也无需扫描条码。CalorieScanner 是一款 AI 驱动的营养追踪应用,在浏览器中运行,并可安装到 iOS 与 Android 主屏幕。将镜头对准餐点,AI 模型会识别盘中的食物(包括餐厅菜品),并在数秒内给出卡路里、蛋白质、碳水、脂肪、糖与钠的含量、逐项食材明细以及一条简短的健康建议。一键即可记录到当日目标中。

Read moreShow less展开收起

Most trackers fail because logging is a chore; here the whole loop is photo → result → log, so the record actually gets kept. Everything else builds on that record: a calendar of every meal (with retroactive entry for the ones you forgot), one-tap hydration and protein logging, 7-day / 6-week / 6-month trend charts against your goal, a macro view that flags anything over your personal daily-value limits, and an Analyze button where the AI reads your own history and writes plain-language suggestions. Export any date range as a PDF report to share with a coach or doctor.

大多数饮食追踪应用之所以半途而废,是因为记录本身太繁琐;而在这里,整个流程只有"拍照 → 结果 → 记录"三步,记录才真正能坚持下来。其余功能都建立在这份记录之上:按日历回看每一餐(忘了记的可以补录到过去的日期)、一键记录饮水与蛋白质、7 天 / 6 周 / 6 个月的趋势图并对照目标线、以百分比显示各项营养素相对个人每日参考值并标出超标项,以及「分析」按钮 —— 由 AI 阅读你自己的记录,用通俗语言给出总结与建议。还可将任意日期范围导出为 PDF 营养报告,方便分享给教练或医生。

  • AI food scanCamera or gallery, auto-compressed before upload. Calories, six nutrients, a per-item breakdown and a health tip. Recognises when a photo isn't food and says so instead of guessing.
  • Water & protein in one tap150 / 250 / 500 / 750 ml hydration buttons and 1 / 5 / 10 / 20 g protein shortcuts, each with a progress bar toward your daily goal.
  • Trends & AI insightsCalorie and water charts over 7 days, 6 weeks or 6 months with a goal line; macros as % of daily value with over-limit flags; an AI-written review of your own data.
  • History & PDF reportsCalendar with dots on logged days, per-meal detail, retroactive logging, and PDF export for any date range — emailed to you or downloaded directly.
  • Goals that fit youAge, weight, height, sex and activity level produce a suggested calorie goal (Mifflin-St Jeor) — suggested, never forced. Calorie, water and per-macro targets are all editable.
  • Three languages, install anywhereEnglish, 简体中文 and 繁體中文 across the UI and the AI's replies. A progressive web app that installs to the home screen on iOS and Android, with an offline app shell and push reminders for meals, water and a daily summary.
  • AI 食物识别拍照或从相册选取,上传前自动压缩。返回卡路里、六项营养素、逐项食材明细与健康建议;若照片并非食物,会如实说明而不会胡乱猜测。
  • 一键记录饮水与蛋白质150 / 250 / 500 / 750 ml 饮水按钮与 1 / 5 / 10 / 20 g 蛋白质快捷键,各自配有朝向每日目标的进度条。
  • 趋势与 AI 洞察7 天 / 6 周 / 6 个月的卡路里与饮水图表并附目标线;各营养素按每日参考值百分比显示并标出超标项;由 AI 基于你自己的数据撰写分析。
  • 历史记录与 PDF 报告日历上以圆点标记已记录的日子,可查看每餐详情、补录过往日期,并将任意日期范围导出为 PDF —— 发送到邮箱或直接下载。
  • 贴合个人的目标根据年龄、体重、身高、性别与活动量给出建议卡路里目标(Mifflin-St Jeor 公式)—— 仅作建议,绝不强制套用。卡路里、饮水与各营养素目标均可自由修改。
  • 三种语言,随处可安装英文、简体中文、繁體中文覆盖界面与 AI 回复。作为渐进式网页应用,可安装到 iOS 与 Android 主屏幕,支持离线外壳缓存与用餐、饮水、每日总结的推送提醒。

Free accounts include 5 scans a day. Photos are analysed through Drevoiq's own server, so no AI keys ever reach your device. Nutrition values are AI-generated estimates, not medical or dietary advice.

免费账户每天可使用 5 次扫描。照片通过 Drevoiq 自有服务器进行分析,AI 密钥绝不会下发到你的设备。营养数值为 AI 生成的估算,不构成医疗或饮食建议。

PWA · installs on iOS & AndroidPWA · 可安装于 iOS 与 Android React Native · Expo AI food recognitionAI 食物识别 Nutrition tracking营养追踪 Push notifications推送通知 PDF reportsPDF 报告 EN · 简体 · 繁體
cs.drevoiq.com →

More projects will be added as they reach a shareable stage.

后续将持续添加更多项目。

Background 背景

Education & Certifications

教育与认证

Sep 20262026年9月

Project Management Professional (PMP)®项目管理专业人士认证(PMP)®

Project Management Institute (PMI)
美国项目管理协会(PMI)

Issued Sep 2026 · Expires Sep 2029 · Credential ID 45182792026年9月颁发 · 2029年9月到期 · 证书编号 4518279 Show credential →查看证书 →

Jul 20262026年7月

AWS Certified AI PractitionerAWS Certified AI Practitioner(AWS 认证 AI 从业者)

Amazon Web Services
亚马逊云科技(Amazon Web Services)

Issued Jul 2026 · Expires Jul 2029 · Credential ID ad34240536b3440c9825de6536ccbb8e2026年7月颁发 · 2029年7月到期 · 证书编号 ad34240536b3440c9825de6536ccbb8e Show credential →查看证书 →

Apr – Jul 20262026年4月 – 7月

Advanced Professional Certificate in Data Science & AI (SCTP)数据科学与人工智能高级专业证书(SCTP)

Nanyang Technological University · PaCE@NTU, SkillsFuture Career Transition Programme
南洋理工大学 · PaCE@NTU,SkillsFuture 职业转型计划

Python, machine learning, data engineering and AI capstone projects.

涵盖 Python、机器学习、数据工程与 AI 结业项目。

Issued Jul 2026 · Credential ID 79727522026年7月颁发 · 证书编号 7972752 Show credential →查看证书 →

Graduated Jul 20032003年7月毕业

Bachelor of Engineering (Mechatronics)工程学学士(机电一体化)

Nanyang Technological University, Singapore · Second Class Upper Honours
新加坡南洋理工大学 · 二等一级荣誉学位
Recognition 荣誉

Awards & Recognition

荣誉与奖项

Oct 20252025年10月

Gold Award, 19th Step-by-Step Excellence Awards (一步步卓越奖)第 19 届一步步卓越奖 金奖

T7300 press-fit pin inspection system, Triertech; contributed to development and led field support.
Triertech T7300 压接针检测系统;参与开发并负责现场支持。

Awards page →奖项页面 → · Triertech news →Triertech 新闻 →

Apr 20252025年4月

Nepcon 2025 Excellent-Team Commendation (Support Team)Nepcon 2025 优秀团队表彰(支持团队)

Triertech
Dec 20222022年12月

Vision Award (远见奖), 16th Step-by-Step awards第 16 届一步步奖 远见奖

HIS-10 Hybrid Inspection System, developed by my R&D team.
HIS-10 混合检测系统,由我带领的研发团队开发。

Award announcement →获奖报道 →

Jun 20202020年6月

Shortlisted, AIGO AI-Solution Competition入围 AIGO AI 解决方案竞赛

Taiwan Ministry of Economic Affairs (IDB); NTD 150,000 first-stage grant.
台湾经济部工业局;获第一阶段补助 15 万新台币。
Aug 20102010年8月

Outstanding Staff Award 20102010 年杰出员工奖

Ellipsiz Group
Ellipsiz 集团
FY06 · FY07 · FY10

Engineering Excellence Awards FY06, FY07, FY10卓越工程奖(FY06、FY07、FY10)

iNETest Resources
Recent activity 近况

Recent Activity

近期动态

Nov 20262026年11月

Built Pocket Andon at the Claude Singapore Community × Supabase "Build with Claude and Supabase" hackathon — a real-time andon board for an SMT line (printing, SPI, pick & place, reflow, AOI, ICT) showing live station status, downtime and stoppage reasons, built in under an hour with Claude Code and Supabase Realtime.

在 Claude Singapore Community × Supabase "Build with Claude and Supabase" 黑客松上打造 Pocket Andon —— 一款面向 SMT 产线(印刷、SPI、贴片、回流焊、AOI、ICT)的实时安灯看板,实时显示各工站状态、停机时间与停线原因,借助 Claude Code 与 Supabase Realtime 在一小时内完成。

Nov 20262026年11月

Attended AgentCon Singapore (Global AI Community) and the Tencent Cloud Hackathon Singapore 2026 Demo Day, following how AI agents are being applied in industry.

参加 AgentCon Singapore(Global AI Community)及 Tencent Cloud Hackathon Singapore 2026 成果展示日(Demo Day),关注 AI 智能体在产业中的应用。

Oct 20262026年10月

Attended PMI Singapore Chapter's session on Managing AI Risk, Security and Governance in Digital Transformation.

参加 PMI 新加坡分会主办的"数字化转型中的 AI 风险、安全与治理管理"专题活动。

Sep 20262026年9月

Earned the PMP® (Project Management Professional) certification from PMI.

取得美国项目管理协会(PMI)颁发的 PMP®(项目管理专业人士)认证。

Sep 20262026年9月

Graduated from the NTU SCTP Advanced Professional Certificate in Data Science & AI (Cohort 3) at NTU@one-north on 12 September 2026.

于 2026年9月12日在 NTU@one-north 从南洋理工大学 SCTP 数据科学与人工智能高级专业证书课程(第 3 期)毕业。

Sep 20262026年9月

Launched Defect Hunter in public beta — a free PWA that turns real SMT quality-control inspection (SPI, AOI, AXI) into a procedurally generated, spot-the-defect game, plus a Benchmark mode where a live, in-browser ML model plays the AOI ladder itself.

发布 Defect Hunter 公测版 —— 一款免费的渐进式网页应用,将真实的 SMT 品质检测流程(SPI、AOI、AXI)转化为程序化生成的"找瑕疵"游戏;还新增 Benchmark 模式,由一个在浏览器中实时运行的机器学习模型自行挑战 AOI 关卡,当它未能检出瑕疵时,你可以介入协助。

Sep 20262026年9月

CalorieScanner now installs to the home screen on iOS and Android — Simplified and Traditional Chinese, push reminders, PDF nutrition reports, and one-tap hydration/protein logging.

CalorieScanner 现可作为渐进式网页应用(PWA)安装到 iOS 与 Android 主屏幕 —— 新增简体与繁體中文、用餐 / 饮水 / 每日总结推送提醒、任意日期范围的 PDF 营养报告,以及一键记录饮水与蛋白质。

Say hello 联系方式

Contact

联系

Open to roles in R&D and engineering management, project management, technical service leadership and applied AI for manufacturing, in Singapore or the Suzhou–Shanghai region.

开放机会:研发与工程管理、项目管理、技术服务管理,以及面向制造业的应用 AI 相关职位,工作地点为新加坡或苏州—上海地区。

© 2026 Wong Chih Chiang · drevoiq.com