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

Automotive

Industrial

Consumer

Technologies

Application Software Pack: ML-Based System State Monitor

APP-SW-PACK-ML-STATE-MONITOR

Roll over image to zoom in

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.

Diagram

Choose a diagram:

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
Get diagram 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

Supported Devices

  • i.MX-RT1170: i.MX RT1170: 1 GHz Crossover MCU with Arm® Cortex® Cores
  • 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, Low-Power 12-Bit Digital IoT Accelerometer
  • MCX-N94X-N54X: MCX N94x/54x Highly Integrated Multicore MCUs with On-Chip Accelerators, Intelligent Peripherals and Advanced Security

Downloads

Quick reference to our software types.
Filters

1 download

  • Application Example Software

    Application Software Pack - ML State Monitor

    EXTERNALRev 0Jan 18, 2022APPLICATION-SW-PACK-ML-STATE-MONITOR
    Download

Note: For better experience, software downloads are recommended on desktop.

Y true 0 SSPAPP-SW-PACK-ML-STATE-MONITORen 1 Application Note Application Note t789 1 en_US en_US en Application Note 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 en true 1 Y SSP Application Note 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

Documentation

Quick reference to our documentation types.

Filters

1 document

Compact List

Hardware

Quick reference to our board types.
Filters

5 hardware offerings

Training

Filters

2 trainings

Support

What do you need help with?

  • Narrow your search
Search