Hardware Guide
Nordic Semiconductor's nRF52840 excels at anomaly detection via TFLite Micro. The 1-core cortex-m4f at 64 MHz with 256 KB SRAM handles 15 KB quantized models with 8.0x RAM headroom. Built-in Bluetooth 5.0 LE enables wireless result reporting.
| Spec | nRF52840 |
|---|---|
| Processor | ARM Cortex-M4F @ 64 MHz |
| SRAM | 256 KB |
| Flash | 1 MB |
| Key Features | Built-in 9-axis IMU (LSM9DS1) on Arduino Nano 33 BLE, Arduino ecosystem, Ultra-low-power BLE, Built-in microphone (Sense variant) |
| Connectivity | Bluetooth 5.0 LE, 802.15.4 (Thread/Zigbee), NFC, USB 2.0 |
| Price Range | $5 - $8 (chip), $20 - $35 (dev board) |
The nRF52840's 256 KB SRAM provides 8.0x the 32 KB minimum for anomaly detection. This generous headroom means the 15 KB model tensor arena, sensor input buffers, and application logic (vibration/current/temperature polling, Bluetooth 5.0 LE stack, state management) all fit without contention. The remaining 218 KB after model allocation supports complex application features. The nRF52840 provides 1 MB of flash memory, which comfortably houses the TFLite Micro runtime, the 15 KB model binary, application firmware, and basic configuration data. Flash usage is well within budget for this configuration. The nRF52840 is widely used for BLE-connected ML applications. Its 256 KB SRAM handles keyword spotting, gesture recognition, and sensor anomaly detection models. Zephyr RTOS support and Edge Impulse's first-class nRF integration streamline the development workflow. For anomaly detection, connect a vibration sensor (e.g., ADXL345 accelerometer via I2C/SPI) via SPI and a current sensor (e.g., ACS712 via ADC) via ADC and a temperature sensor (e.g., DS18B20 or TMP36 via ADC) via ADC to the nRF52840. Sample at 50-200 Hz and collect windows of 64-256 samples as model input. The DSP extensions efficiently compute FFT features from raw sensor data. TFLite Micro's static memory allocation model maps well to the nRF52840's memory architecture — define a fixed tensor arena at compile time with no runtime heap fragmentation risk. The framework's operator coverage supports dense and convolutional layers needed for anomaly detection. Model conversion uses the standard TFLite converter with int8 post-training quantization. At $5-8 per chip ($20-35 for dev boards), the nRF52840 offers strong value for anomaly detection deployments. 22 PlatformIO-listed boards provide decent hardware selection. Key nRF52840 features for this workload: Built-in 9-axis IMU (LSM9DS1) on Arduino Nano 33 BLE, Arduino ecosystem, Ultra-low-power BLE, Built-in microphone (Sense variant).
Set up nRF52840 development environment
Install nRF Connect SDK (Zephyr-based) or Arduino via PlatformIO. Create a project targeting the nRF52840 and verify basic functionality (blink LED, serial output). For TFLite Micro, clone the framework repository and add it as a library dependency. Ensure the toolchain supports C++11 or later for the ML runtime.
Collect vibration training data
Connect a vibration sensor (e.g., ADXL345 accelerometer via I2C/SPI) and current sensor (e.g., ACS712 via ADC) and temperature sensor (e.g., DS18B20 or TMP36 via ADC) to the nRF52840 via I2C. Write a data logging sketch that captures vibration readings at the target sample rate and outputs via serial/SD card. Collect 500+ labeled samples across all classes. Include normal operating conditions and edge cases in your dataset.
Train and quantize model for TFLite Micro
Build an autoencoder (3-4 dense layers) in TensorFlow or PyTorch. Apply int8 post-training quantization — this typically reduces model size by 4x with minimal accuracy loss. Convert to .tflite and generate a C array (xxd -i model.tflite > model_data.h). Target model size: under 15 KB to fit the nRF52840's 256 KB SRAM with room for application code.
Deploy and validate on nRF52840
Include the TFLite Micro runtime and compiled model in your Nordic Semiconductor project. Allocate a tensor arena of 23-38 KB in a static buffer. Run inference on live vibration data and compare predictions against your test set. Log results to serial for desktop validation. Measure inference latency and peak RAM usage to verify they meet application requirements.
NXP cortex-m7 at 600 MHz with 1024 KB SRAM. $6-12 per chip. Compared to nRF52840: more RAM, faster clock. Excellent rated.
STMicroelectronics cortex-m7 at 480 MHz with 1024 KB SRAM. $8-20 per chip. Compared to nRF52840: more RAM, faster clock. Excellent rated.
Espressif xtensa-lx7 at 240 MHz with 512 KB SRAM. $3-8 per chip. Compared to nRF52840: more RAM, faster clock, cheaper. Excellent rated.
Connect sensors to AI inference — design monitoring workflows visually and compile to firmware for continuous edge detection.
Get Started Free