IoT

Renesas Electronics introduces its Failure Detection e-AI Solution for motor-equipped home appliances, featuring the Renesas RX66T 32-bit microcontroller. It simplifies home appliance maintenance and makes it easy to add abnormality-detection AI to the microcontroller for failure detection and predictive maintenance.

Embedded AI (e-AI) enables failure detection of home appliances, such as refrigerators, air conditioners, and washing machines, due to motor abnormality. Property data showing the motor’s current or rotation rate status can be used directly for abnormality detection, making it possible to implement both motor control and e-AI–based abnormality detection with a single microcontroller, says Renesas. Using the RX66T eliminates the need for additional sensors, and reduces the bill of materials cost.

When a home appliance malfunctions, the motor operation typically appears abnormal when running and being monitored for fault detection in real-time. Implementing e-AI-based motor control-based detection means that failure detection results can be applied not only to trigger alarms when a fault occurs, but also for preventive maintenance. e-AI can estimate when repairs and maintenance should be performed, and it can identify the fault locations to boost maintenance efficiency and improve product safety by adding functionality that predicts faults before they occur.

The Renesas Failure Detection e-AI Solution for motor-equipped home appliances can control up to four motors by virtue of using the RX66T. Today’s washing machines typically incorporate three motors, one to rotate the washing tub, one to drive the water circulation pump, and one to drive the drying fan. The Renesas Failure Detection e-AI Solution can be used to control these three motors with a single RX66T chip while at the same time monitoring all three motors for faults.

The e-AI solution uses the Renesas Motor Control Evaluation System and an RX66T CPU card. This hardware is combined with a set of sample program files that run on the RX66T as well as a GUI tool that enables collecting and analysing property data indicating motor states. To detect faults, it is necessary to learn the characteristics of the normal state. System engineers can use the GUI tool to begin developing AI learning and optimised fault detection functionality. Once the AI models are developed, the e-AI Translator, e-AI Checker, and e-AI Importer which make up the e-AI solution, can be used to import the learned AI models into the RX66T.

http://www.renesas.com

Support for concurrent communication over Bluetooth Low Energy and Sub-1GHz wireless allows users of the STEVAL-FKI001V1 dual-radio development kit to build and connect IoT devices like smart sensors, finders and trackers. These devices can be configured, updated, remotely monitored and tracked using various network topologies, protocols and services, confirms STMicroelectronics.

The development kit is for use by IoT developers in projects from smart homes and smart buildings to asset tracking, energy management, smart farming and industrial monitoring and control use.

The kit includes ST’s BlueNRG-1 Bluetooth system on chip and S2-LP sub-1GHz transceiver. The dual-radio architecture enables simultaneous operations on a variety of radio-frequency bands and protocols such as Bluetooth Low Energy or proprietary 2.4GHz, Sub-1GHz, and Sigfox.

According to ST, users can create smart objects that connect to each other locally through mesh or point-to-point connections and support flexible ways of connecting to the Cloud. For instance, a sensor ecosystem for a smart home could be created with local sensor networking leveraging either Bluetooth Low Energy or Sub-1GHz wireless link and the whole system is then connected to the Cloud through a local gateway or directly via a seamless Sigfox ubiquitous link, for surveillance or remote monitoring purposes.

The BlueNRG-1 Bluetooth 5.0 certified kit allows configuration or modification of device settings during installation or maintenance and permits monitoring of networked node sensors through an app running on any Android or iOS device.

The sub-1GHz S2-LP transceiver allows local networking as well as LPWAN installations including global Sigfox connectivity, which allows capabilities such as real-time notification of events. Sigfox-ready networking can be used to track and remotely localise devices or assets.

The kit can be expanded through its Arduino Uno V3 connectors with ST’s X-Nucleo offering, including expansion boards with MEMS sensors, motor control, GNSS receivers or industrial I/O and power drivers.

The STEVAL-FKI001V1 development kit is interoperable with the recently announced BlueNRG-Tile board. This combination can allow users to build end-to-end smart-sensor networks, including the sensor node, local gateways and Cloud connectivity.

Leveraging the BlueNRG-1 SoC’s versatile interfaces and low-power Arm Cortex-M0 core with 256kbyte of embedded program memory, users can connect their own choice of external sensors and process the data acquired locally in real time. The STEVAL-FKI001V1 has a software development kit (SDK) that simplifies development to reduce time to market, yet preserves the flexible, scalable nature of the design. It could also be used in conjunction with the ST BlueNRG-Mesh software package to create extensive networking on a large-scale installation, advises ST. Over the air (OTA) firmware updates are possible via the Bluetooth Low Energy connection.

Based on a ready-to-use WS2118 RF dual-radio module from Jorjin, the STEVAL-FKI001V1 provides a pre-certified solution for developers to quickly move from early concept-feasibility phase to prototyping, field trials and volume production. The programmable low-power radio module has flexible power management and wake-on-event capability that allows multi-year lifetime from a small primary battery, says ST.

http://www.st.com