An intelligent temperature detection method based on multi-sensor fusion was proposed in order to solve the problem that the precision instrument would generate heat when running in special environment, which would cause the temperature to rise and lead to the life of the precision instrument to be shortened and the original parts to be processed incorrectly. The multi-layer feedforward neural network intelligent detection technology optimized by genetic algorithm is applied to the temperature detection of the incubator. The results show that the predicted temperature value obtained by the multi-layer feedforward neural network optimized by genetic algorithm is basically consistent with the change trend of the actual temperature value, and has high generalization ability and robustness.