The invention provides an electrified railway operation condition identification method based on wavelet transform. The method comprises the following steps: (1) acquiring recording data of an electrified railway traction network, preprocessing the same to form a waveform training sample base; (2) generating current testing waveform in the electrified railway operation; (3) performing five-layer decomposition reconstruction on the training sample by using the wavelet transform to acquire an energy feature value at each layer and each band; (4) learning the training sample by using a genetic algorithm, and computing the weight on the classification contribution by decomposition at each layer; (5) performing five-layer decomposition on the current testing waveform by using the wavelet transform to acquire the energy feature value of each layer and each band; and (6) performing affiliation degree comparison computing on the testing waveform and the training sample by using a final classification model to finish the classification on the testing waveform. Through the identification method provided by the invention, the actual operation condition of the electrified railway can be identified through the optimizing computation, so that the user can understand the electrified railway operation condition in the power supply zone in real time.