A correcting nonlinear errors of the thermocouple sensor based on Radial Basis Function Neural Network using particle swarm optimization are introduced. It solves t he shortcoming of Thermocouple Sensor’s application on large data. The result of experiment shows that the nonlinear calibration based on APSO-RBF has higher precision than the method based on RBF and ANFIS. Then, APSO-RBF is used to test fire path temperature in the anode baking. It is proved that the method is effective. DOI: http://dx.doi.org/10.11591/telkomnika.v11i5.2463