This paper introduces the basic principles of radiation temperature measurement technology and key issues in research. The current application status of temperature measurement methods for engine turbine blades based on infrared radiation at home and abroad is summarized, the errors generated during measurement are analyzed, and the measures to reduce errors are proposed. It is pointed out that in terms of environmental radiation, it is necessary to fully consider the influence of combustion gases and environmental surface radiation, establish accurate reflection models, integrate algorithms, and correct radiation interference errors; In terms of emissivity modelling, emissivity model and non?emissivity model should be established in advance according to specific situations, and machine learning algorithms should be combined to improve measurement accuracy; In terms of optical system design, it is necessary to select appropriate optical materials and coatings to enhance the sensitivity of the system in different environments; In terms of data processing, methods such as neural networks, genetic algorithms, and constraint optimization can be used to minimize errors and improve computational accuracy to the greatest extent possible.