DC arc detection in solar applications with 10 times lower latency and 98% plus accuracy
Cost-effective arc protection meeting global safety standards (UL1699B and IEC63027).
Application overview
Solar systems need protection from dangerous electrical arcs that can cause fires and damage property. Unlike basic detection methods that often trigger false alarms, our solution uses advanced pattern recognition to accurately identify real threats while ignoring harmless electrical activity. Powered by TI's TinyEngine? NPU, it monitors multiple channels simultaneously and runs up to 10 times faster than traditional CPU processing. With no connectivity requirements, our edge AI detects arcs locally in milliseconds, far faster than cloud processing. While keeping data private & continuously learning (adapting) to reduce false alarms.
Starting evaluation
Data collection
?
The Capture & Display Data tab in CCStudio? EdgeAI Studio is used to command the TIDA-010955 hardware and complete the data acquisition. This reference design enables quick acquisition of the current monitored cable along with DC string and arc-gap voltage measurements. The acquired current data is used for model training. The DC string voltage and arc-gap voltage can be leveraged to auto-label the current data.
?
Data quality assessment
?
Acquired current data can be displayed and plotted in CCStudio Edge AI Studio in both time and frequency domain to ensure arc and normal data sets are separable in features.
Figure 1.1 - Arc fault present
Figure 1.2 - No arc fault
Build and train your model
EdgeAI Studio allows model training, assessment and deployment to be completed within a intuitive GUI user interface.
- Explore and train multiple model choices through an easy-to-use GUI based workflow
- Start fast with the motor bearing fault example project, featuring a preloaded dataset
- Use your own data with integrated capture and hosting tools
Model Flexibility to support your application needs based on the memory constraints and outlier detection requirements.
Deploying your model
Edge AI Studio provides a start to finish workflow for deploying trained models directly to embedded targets.
For developers seeking deeper customization and control, the C2000WARE-DIGITALPOWER-SDK?offers a comprehensive framework for building and integrating edge AI functionality into your own embedded applications.
Choosing the right device for you
TI's?c28 DSPs and Arm? Cortex?-M33 based MCUs deliver scalable performance for executing and accelerating arc fault detection models, along with key SoC features critical to your application.
Data below is taken into consideration 250KHz sampling frequency and 1024 samples
?
| Product number | Processing core | NPU available | Clock frequency (MHz) | Arc detection benchmark metrics | ||
|---|---|---|---|---|---|---|
| Latency (ms) | Flash (kB) | SRAM (kB) | ||||
| TMS320F28P550x | C28x DSP core | Yes | 150 | 1.04 | 3 | 8 |
| TMS320F2800137 | C28x DSP core | No | 120 | 2.5 | 2 | 8 |
| TMS320F28P650 | C28x DSP core | No | 200 | 1.5 | 2 | 8 |
| AM13E23019 | Cortex-M33 core | Yes | 200 | 1.2 | 4 | 9 |
All the hardware, software and resources you’ll need to get started
Hardware
C2000 TMS320F28P550x SOM board. Bundle with TIEVM-ARC-AFE?(sold separately) for complete AI arc fault detection solution.
Start your evaluation with DC arc detection hardware with TIDA-010955 reference that features an analog front end for DC arc detection.
Software & development tools
CCStudio? Edge AI Studio
A fully integrated no-code solution for training and compiling PIR Motion detection models, to deploy onto TI embedded microcontroller devices.?
CLI tools
A command line interface for advanced users, who want to develop their own model.?Use this end-to-end model development tool that contains dataset handling, model training and compilation.
AM13E230-SDK
Is a unified software platform for TI's AM13E23x MCU family providing easy setup and fast out-of-the-box access to benchmarks and demos.?
Supporting resources
Reference design for AI based arc detection in solar applications.
Industrial automation | Motor diagnostics & monitoring
Protect AC motor drive designs with high-accuracy AI based motor fault classification.