The invention discloses a method for the online monitoring of a fault of an insulator based on the thermal infrared imaging technology, and the method comprises the steps: employing a rectangular frame point selection method for a steel cap part, and employing line point selection for an insulator string part for coordinate and temperature conversion; obtaining four types of temperature parameter characteristic quantities through employing an insulator fault detection algorithm: a low-value insulator characteristic quantity, a zero-value insulator characteristic quantity, an insulator pollution accumulation characteristic quantity and an insulator damage characteristic quantity; selecting two three-layer PNN probability neural networks for the feature level fusion of the steel cap part and the insulator string part through combining with environment temperature, humidity and pollution conditions; giving a local information fusion judgment result; and submitting the result to a decision-making level for global decision marking. The method improves the precision of an information fusion model, clearly divides a fault and a non-fault, reduces the misjudgment rate, employs the plurality of characteristic quantities for monitoring, and combines the data of the plurality of characteristic quantities and the insulator fault judgment model to carry out the fault discrimination. Therefore, the method improves the reliability of the monitoring data.