Fan blower imbalance detection in HVAC systems with MCUs and 98% plus accuracy
Reduce noise, improve efficiency, increase reliability of HVAC system by detecting fan-blade imbalance early with TI's MCUs.
Application overview
Detects fan and blower blade wobbles and imbalances in real-time using a current signal based method without sending data to the cloud. Instead of fixed frequency analysis, edge AI detects imbalance across varying speeds and operating conditions without recalibration. Our real-time motor control & automation microcontrollers (MCUs) allow such detection to be done by executing models on main CPU or TinyEngine? NPU in addition to motor control, on a single device.
Starting evaluation
Data collection
?
LAUNCHXL-F2800137 EVM is used to perform the task. A motor drive BoosterPack plugged onto the Launchpad is used to drive the motor of a blower fan. F2800137 on the launchpad is used to control the running of the motor and blower fan and is also used to collect sensor data. The Capture & Display Data tab in CCStudio Edge AI Studio is used to command the Launchpad h/w and complete the data acquisition. The acquired sensor data is used for model trainning.
?
Data quality assessment
?
Acquired vibration data can be displayed and plotted in EdgeAI Studio in both time and frequency domain to ensure vibration data sets are separable in features. Goodness of Fit (GOF) analysis can also be performed in this tool on acquired data to check whether the acquired data has high enough separation in characteristics.
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
Find the right model for your needs
Access TI's library of optimized and configurable motor bearing fault detection models. From Edge AI Studio there is a link to ModelZoo (URL). There a specific application can be picked. A table as the one in below can then be leveraged to decide on the model choice.Four models can be explored in EdgeAI Studio or command line ModelMaker.
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-MOTORCONTROL-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 4K Hz sampling frequency on 256 samples
?
| Product number | Processing core | NPU available | Clock frequency (MHz) | Arc detection benchmark metrics | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Model execution time (ms) | Flash (kB) | SRAM (kB) | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| TMS320F28P550x | C28x DSP core | Yes | 150 | 0.17 | 1.8 | 1.1 | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| TMS320F2800137 | C28x DSP core | No | 120 | 0.42 | 1.2 | 1 | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| TMS320F28P650 | C28x DSP core | Yes | 200 | 0.25 | 1.2 | 1 | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| AM13E23019 | Cortex-M33 core | Yes | 200 | ~0.13* | 3 | 0.9 | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| *AM13E23019 with TinyEngineTM NPU numbers are preliminary | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
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.