App SW Pack | ML-Based System State Monitor | NXP Semiconductors

オートモーティブ

インダストリアル

コンスーマ

テクノロジ

Application Software Pack: ML-Based System State Monitor

APP-SW-PACK-ML-STATE-MONITOR

画像にカーソルを合わせると拡大表示されます。

This Machine Learning (ML) application software pack, ML-based System State Monitor, relies on the Deep Learning (DL) subfield of ML and enables developers to develop and deploy neural networks on MCU-based systems for building smart sensing applications. This example software package, designed to show how to create a fan vibration state monitoring solution and also provides details on how to validate and evaluate the performance of a model by running it through different inference engines on an embedded sensing device.

This App SW Pack is available for the MCX N family with dedicated eIQ® Neutron neural processing unit (NPU) for machine learning applications, i.MX RT1170 family of Crossover MCUs, LPC55S6x and K66 families of general purpose MCUs.

To access this software pack, click on the download button here to visit the NXP MCUXpresso SDK github repository and follow the steps found in this App SW Pack ML State Monitor Lab Guide.

ソフトウェア詳細

図

図を選択する。:

ML-based System State Monitor - App SW Pack

ML-based System State Monitor - App SW Pack

ML-based System State Monitor - App SW Pack - Example

ML-Based System State Monitor App SW Pack - Example

ML-based System State Monitor - App SW Pack - Collaterals

ML-Based System State Monitor App SW Pack - Collaterals

ML-based System State Monitor - App SW Pack - SW Stack Block Diagram

ML-Based System State Monitor App SW Pack - SW Stack Block Diagram
図を取得する PDF

Features

  • AI edge Computing
  • eIQ® machine learning (ML) software development and deep learning at the edge on i.MX RT Crossover MCUs
  • Complete and easy ML-based applications development, validation and performance analysis
  • Multiple inference engines usage: TensorFlow™ Lite Micro, DeepViewRT™, Glow
  • Provides examples through an entire workflow of building and deploying on embedded targets with a real use-case
  • Related application spaces: system state monitoring, activity recognition, machine health (preventive maintenance, anomaly detection, failure identification)
  • Low-latency real-time system monitoring and failure identification
  • Applicable to time series real-time data
  • Can be used for other types of sensor data models that detect vibration

対応製品

  • i.MX-RT1170: i.MX RT1170：Arm® Cortex®コア搭載1 GHzクロスオーバーMCU
  • LPC55S6x: High Efficiency Arm® Cortex®-M33-Based Microcontroller Family
  • K66_180: Kinetis® K66-180 MHz, Dual High-Speed and Full-speed USBs, 2MB Flash Microcontrollers (MCUs) based on Arm® Cortex®-M4 Core
  • FXLS8974CF: ±2g/±4g/±8g/±16g、低消費電力の12ビット・デジタルIoT加速度センサ
  • MCX-N94X-N54X: MCX N94x/54x オンチップ・アクセラレータ、インテリジェントなペリフェラル、高度なセキュリティを備えた高集積マルチコアMCU

ダウンロード

クイック・リファレンス ソフトウェア・タイプ.
フィルタ

1 ダウンロード

  • アプリケーション例 ソフトウェア

    Application Software Pack - ML State Monitor

    EXTERNAL改訂 0Jan 18, 2022APPLICATION-SW-PACK-ML-STATE-MONITOR
    ダウンロード

注: より快適にご利用いただくために、ソフトウェアのダウンロードはデスクトップで行うことを推奨します。

Y true 0 SSPAPP-SW-PACK-ML-STATE-MONITORja 1 アプリケーション・ノート Application Note t789 1 ja ja ja アプリケーション・ノート Application Note 1 1 1 Chinese This application note presents the process of building and deploying deep learning models for Smart Sensing Appliances. It also highlights how to validate and evaluate the performance of a model by running it through different inference engines on an Embedded Sensing Device. 1644318754124703028011zh SSP 4.9 MB None None documents None 1644318754124703028011 /docs/zh/application-note/AN13562.pdf 4943726 /docs/zh/application-note/AN13562.pdf AN13562 documents N N 2022-02-08 Building and Benchmarking Deep Learning Models for Smart Sensing Appliances on MCUs /docs/zh/application-note/AN13562.pdf /docs/zh/application-note/AN13562.pdf Application Note N 645036621402383989 2024-07-17 zh Apr 25, 2022 645036621402383989 Application Note Y N Building and Benchmarking Deep Learning Models for Smart Sensing Appliances on MCUs 2 English AN13562: This application note presents the process of building and deploying deep learning models for Smart Sensing Appliances. It also highlights how to validate and evaluate the performance of a model by running it through different inference engines on an Embedded Sensing Device. 1644318754124703028011 SSP 4.9 MB None None documents None 1644318754124703028011 /docs/en/application-note/AN13562.pdf 4943726 /docs/en/application-note/AN13562.pdf AN13562 documents N N 2022-02-08 Building and Benchmarking Deep Learning Models for Smart Sensing Appliances on MCUs /docs/en/application-note/AN13562.pdf /docs/en/application-note/AN13562.pdf Application Note N 645036621402383989 2024-07-17 pdf N en Sep 27, 2023 645036621402383989 Application Note Y N Building and Benchmarking Deep Learning Models for Smart Sensing Appliances on MCUs false 0 APP-SW-PACK-ML-STATE-MONITOR downloads ja true 1 Y SSP アプリケーション・ノート 1 /docs/en/application-note/AN13562.pdf 2022-02-08 1644318754124703028011 SSP 1 Sep 27, 2023 Application Note AN13562: This application note presents the process of building and deploying deep learning models for Smart Sensing Appliances. It also highlights how to validate and evaluate the performance of a model by running it through different inference engines on an Embedded Sensing Device. None /docs/en/application-note/AN13562.pdf English documents 4943726 None 645036621402383989 2024-07-17 N /docs/en/application-note/AN13562.pdf Building and Benchmarking Deep Learning Models for Smart Sensing Appliances on MCUs /docs/en/application-note/AN13562.pdf documents 645036621402383989 Application Note N en None Y pdf 2 N N Building and Benchmarking Deep Learning Models for Smart Sensing Appliances on MCUs 4.9 MB AN13562 N 1644318754124703028011 true Y Softwares

ドキュメント

クイック・リファレンス ドキュメンテーションの種類.

フィルタ

1 ドキュメント

コンパクトリスト

ハードウェア

クイック・リファレンス ボードタイプ.
フィルタ

5 ハードウェア提供

トレーニング

フィルタ

2 トレーニング

サポート

お困りのことは何ですか？?

  • Narrow your search
検索