An edge radiation thermometer performs measurements before a semiconductor wafer is transported into a chamber. The edge radiation thermometer performs the measurements while the semiconductor wafer is supported by lift pins and while the semiconductor wafer is placed on a susceptor, after the semiconductor wafer is transported into the chamber. A controller calculates a reflectivity of the semiconductor wafer based on these measurement values. Then, the controller calculates an intensity of an ambient light receive by the edge radiation thermometer, based on the reflectivity and an intensity of synchrotron radiation radiated from a quartz window. Subsequently, the controller subtracts the intensity of the ambient light from an intensity of light received by of the edge radiation thermometer during heat treatment on the semiconductor wafer to calculate the temperature of the semiconductor wafer.

A thermal monitoring system includes thermal monitoring devices that generate sensor data including thermal images depicting monitored elements (e.g. of an electrical switchgear system). The sensor data for all monitoring devices installed at a local deployment is collected by a gateway device, and relevant data from multiple local deployments is further aggregated by a cloud management system for further analysis. New event triggering rules determining how the thermal monitoring devices filter or record the sensor data are generated based on the aggregated data during a continuous learning process. The system detects patterns in the sensor data for the monitoring devices and/or local deployments as a whole and tracks deviations from these patterns, improving the accuracy of the event detection over time.

A system and method for monitoring a switchgear includes an infrared camera, a processing unit, and an output unit. The infrared camera acquires an infrared image of the switchgear, and the processing unit converts it into a binary image. Pixels in the infrared image having a temperature equal to or above a first threshold value are given the same first value. Pixels in the infrared image having a temperature below the first threshold value are given the same second value. The processing unit is configured to implement a Siamese neural network to determine if a hot spot exists in the infrared image.