Due to ever-increasing number and scale of substations, traditional inspection methods for infrared image acquisition are often hindered by factors such as light changes, noise, or other interferences, resulting in varying degrees of recognition bias in the detection effect, leading to a significant decrease in the overall detection efficiency and safety. To enhance inspection efficiency and accuracy, the infrared image target detection method for substation multi-rotor unmanned aerial vehicle inspection is proposed based on PCA technology. Inspection infrared images are captured within the determined coverage range of multi rotor unmanned aerial vehicles in substations, and the pixel information of the collected images is converted into a pixel matrix. The pulse amplitude and waveform envelope area UI signal power in the target inspection image features are calculated and combined with pixel filtering method to obtain the accurate target edges. On this basis, infrared image target detection of multi rotor unmanned aerial vehicle inspection in substations is achieved by adjusting the PCA parameters. The experimental results show that the proposed method boasts a recognition rate of up to 98.5% and an accuracy of 96%, indicating that it meets the expected design effects. This method effectively improves target detection accuracy and safety, enhances detection efficiency, and overall reliability. It exhibits excellent performance and holds high promotional value.