SLUUDB7 August   2025 TMS320F28P550SJ

 

  1.   1
  2.   Abstract
  3.   Trademarks
  4. 1Introduction
  5. 2TMS320F28P55x
  6. 3Edge AI Studio
  7. 4Out-of-the-Box Demo (Smart Signal Classifier)
    1. 4.1 Dataset
      1. 4.1.1 Methods for Data Collection
        1. 4.1.1.1 Collection Process
      2. 4.1.2 Data Formats
    2. 4.2 Model Training
      1. 4.2.1 Preprocessing Options
    3. 4.3 Deploying to TI's Hardware
      1. 4.3.1 TVM Compiler
      2. 4.3.2 Model Execution
  8. 5Summary

TMS320F28P55x

The TMS320F28P550SJ is the first in the C2000™ family to integrate a hardware Neural Processing Unit (NPU), positioning it as cutting-edge platform for Edge AI in real-time control systems. Built on the robust C28x DSP core, this MCU blends deterministic control, advanced signal processing, and on-chip machine learning inference, enabling smarter, more autonomous embedded applications in power, motion, and industrial systems. The integrated NPU is designed to accelerate inference of quantized neural networks, dramatically reducing CPU overhead and enabling real-time AI use cases such as predictive maintenance, motor fault detection, sensor classification, and fault detection. While the TMS320F28P550SJ includes a dedicated NPU for acceleration, it is important to note that all Edge AI models can still be compiled and run entirely in software on the C2000 MCU, without requiring any dedicated NPU hardware.

The following resources are available for customers to start evaluating arc fault detection, system fault and motor fault detection: