Discrete power devices are used in a wide range of applications some of which would benefit from device condition monitoring (CM). This article presents a data-driven method to online evaluate the health status of discrete devices. It is based on the detection of mold temperature by only one thermocouple, offering low-cost and nonintrusive features. The approach looks into five electrical stressors and uses existing sensors to track the load variation, enabling adaptation to both linear or nonlinear load conditions of the inverter system; no additional sampling of electrical signal is required. Under the tracked electrical stresses, a backpropagation neural network (BPNN) is employed to establish the correlation between mold temperature and aging status. The overall design and implementation process, including the hardware design, model training, and CM integration, are demonstrated on a 7.5-kW T-type neutral-point-clamped (TNPC) uninterruptible power supply (UPS) inverter.

中文翻译：

---

分立功率器件的状态监测：具有应力量化和模具温度传感的数据驱动方法


分立功率器件有着广泛的应用，其中一些应用将受益于器件状态监测 (CM)。本文提出了一种数据驱动的方法来在线评估分立设备的健康状态。它仅通过一根热电偶检测模具温度，具有低成本和非侵入性的特点。该方法研究了五个电应力源，并使用现有传感器来跟踪负载变化，从而能够适应逆变器系统的线性或非线性负载条件；不需要额外的电信号采样。在跟踪电应力下，采用反向传播神经网络（BPNN）建立模具温度和老化状态之间的相关性。整体设计和实现过程，包括硬件设计、模型训练和CM集成，在7.5kW T型中性点钳位（TNPC）不间断电源（UPS）逆变器上进行了演示。