İçeriğe geç
KAMPANYA

Logo Tasarım + Web Tasarım + 1 Yıl Domain + E-posta + Hosting — $299 +KDV

AIOR

Search results

Sektör topluluğu — sorularınız, deneyimleriniz ve duyurularınız için.

Search results

  1. Aior

    SCADA in 2026: Ignition, WinCC, or a custom stack — and where each one belongs

    The SCADA conversation has changed Five years ago, SCADA picks were Siemens WinCC vs Wonderware vs Ignition vs "the thing my system integrator already knows". The technical lines between options were genuinely meaningful. In 2026, the gap has narrowed for most use cases — the picks are now...
  2. Aior

    LoRa, NB-IoT, Wi-Fi, BLE: which IoT radio for which factory problem

    The radio decision is upstream of the device decision Picking a radio technology before you've sized the project's data, range, and power constraints is the source of most failed IoT pilots. Each of the major options below wins in a band and loses outside of it. Here's the practical framing...
  3. Aior

    HMI design that operators actually trust: less screen real estate, more decision support

    Why most HMIs are bad The default HMI in most factories looks like a 1998 P&ID diagram with thirty motor symbols, twelve numeric readouts, and a pop-up alarm window that the operator dismisses without reading. It's not bad because the engineers were lazy — it's bad because the priorities at...
  4. Aior

    Industrial sensors: how to specify them so the data you log is actually useful

    The sensor dataset that ruins a project Here's a pattern we see often: a customer adds a hundred sensors to their line, logs everything, and a year later asks why the data isn't useful for predictive maintenance. The answer, in almost every case: the sensors weren't specified for the question...
  5. Aior

    Siemens TIA, Beckhoff TwinCAT, Codesys: a PLC platform pick that survives a decade

    The decision you live with for ten years A PLC choice on a new line is not a one-year decision. The customer's maintenance team will live with the IDE, the comms libraries, and the spare-parts supply chain for the lifetime of the cell. Picking by feature checklist alone misses the point — the...
  6. Aior

    ESP32 vs STM32 vs Raspberry Pi vs RP2040: picking a board for the actual project

    Four families, four shapes of project The "what board should I use" question is a beginner question with an experienced answer: it depends on the project's electrical, software, and operational shape. Below is the framework we use, with the reasons each family wins or loses in a given context...
  7. Aior

    Shipping an anomaly model: latency, drift, and the operator UI nobody plans for

    The deployment is 70 % of the project The model is the part of the project everyone wants to talk about. The deployment is the part that determines whether the project survives. Below is the runbook we've converged on after a few dozen anomaly stations. Latency budgets that actually exist on a...
  8. Aior

    Edge AI deployment patterns: from a working kit to a working factory

    The gap between a demo and a deployment Every edge AI project we've inherited had the same problem: the demo on the engineer's bench worked beautifully. The deployment on the factory floor failed in interesting and expensive ways. The patterns below are what we apply to close that gap...
  9. Aior

    Three industrial anomaly detection deployments and what each one taught us

    Case 1 — PCB inspection, 250 good samples, no anomalies The brief: inspect populated PCBs at end-of-line for solder bridges, missing components, and tombstones. Customer had 250 known-good boards and effectively zero confirmed defects in the historical archive (defective boards were destroyed...
  10. Aior

    DeepStream vs GStreamer vs custom: picking a video pipeline for edge AI

    The thing nobody warns you about Edge AI tutorials show "load image, run model, draw box". Production edge AI is "decode an RTSP stream from a camera that drops frames every fourteen minutes, run inference at variable framerate without skipping the trigger frame, push results to a PLC over...
  11. Aior

    AUROC is misleading: how to actually evaluate an anomaly detector

    The number that fooled everyone Anomaly detection papers report image-level AUROC. Production anomaly detection lives or dies on per-image false-reject rate at a fixed threshold. These are not the same number, and confusing them is the #1 reason a "99 % accurate" model gets unplugged on day...
  12. Aior

    Jetson, Hailo, Coral, RK3588 — when each one is the right answer

    Four platforms, four different shapes of project We get asked this every other RFP: "should we use Jetson, Hailo, Coral, or RK3588?". The honest answer is "depends on the project shape", and the project shape questions matter more than the chip's TOPS rating. Here's the framework. NVIDIA Jetson...
  13. Aior

    Beyond MVTec AD: collecting your own anomaly dataset that survives reality

    MVTec AD is a benchmark, not a dataset Every anomaly detection paper tops out near 99 % image-AUROC on MVTec AD. That number is the reason teams confidently deploy a model and then watch it fail in production. MVTec AD is small (~5k images), pristine (lab lighting, clean backgrounds, single...
  14. Aior

    ONNX, INT8, QAT: what actually breaks when you quantize a model

    The conversion pipeline, in three steps that always go wrong Going from a research-trained PyTorch model to an INT8 binary running on edge hardware looks simple in the docs. In practice, every step has its own failure modes. Here's the version with the warnings included. Step 1 — PyTorch → ONNX...
  15. Aior

    Anomalib in production: what works, what we end up rewriting

    Why Anomalib is our default Intel's Anomalib has, over the last two years, become the de-facto framework for unsupervised anomaly detection. We default to it on new projects because: Most published architectures (PatchCore, EfficientAD, FastFlow, PaDiM, ReverseDistillation) are implemented and...
  16. Aior

    Jetson Orin Nano vs AGX vs Xavier: a 2026 decision guide

    The Jetson lineup, demystified NVIDIA's Jetson family has been an industrial-AI staple for a decade. The 2026 picture: Xavier is end-of-life-ish for new designs, Orin is the active line, and choices come down to Nano / NX / AGX. Here's how we actually pick between them. Orin Nano (8 GB)...
  17. Aior

    PaDiM, PatchCore, EfficientAD: which anomaly model actually wins on your line

    Three families, three tradeoffs The unsupervised anomaly detection space has more or less converged on three architectural families. Picking between them is less about which one tops the MVTec leaderboard and more about which one fits the constraints of your cell — memory budget, retrain...
  18. Aior

    Hailo-8 in production: lessons from shipping eight stations on the same platform

    Why Hailo We started shipping Hailo-8 accelerators about two years ago, after testing it head-to-head with Jetson Xavier NX on a vision inspection workload. The headline numbers were clear: comparable inference performance at roughly a quarter of the power, with a much smaller thermal envelope...
  19. Aior

    From PoC to production: a six-stage vision project rollout

    The shape of every vision project we've shipped After a few dozen vision projects across automotive, packaging, white goods, and metal, we've converged on a six-stage rollout. It's not a Gantt chart and it's not Agile theatre — it's the order in which questions actually need to be answered to...
  20. Aior

    Designing a 24/7 surface defect inspection station — from the ground up

    Why most defect stations underperform The pattern we keep seeing on existing inspection cells: a good camera, a decent model, no thinking about the 23.5 hours a day when nobody is watching. Defect inspection is a 24/7 problem with a 9-to-5 design budget, and that's why so many of these stations...
Back
Top