The invention belongs to the technical field of wear monitoring of numerical control machining tools, and discloses a numerical control machine tool wear data processing method based on a PCA and a self-encoder. The numerical control machine tool wear data processing method comprises the steps that data collected by a tool sensor on a numerical control machine tool is normalized to obtain trainingdata with tool wear extent labels and data to be tested; data fusion is carried out on the obtained training data with the tool wear extent labels; the fused data is input into the stack self-encoderfor training to obtain a tool wear influencing characteristic data set; and a tool wear prediction model is constructed based on a BP neural network and is trained, and the trained BP neural networkmodel is predicted. According to the numerical control machine tool wear data processing method, the important characteristics in the input data can be fully excavated, the obtained data characteristics are input into the BP neural network, the extracted features are mapped to a prediction result through utilizing the fitting ability of the BP neural network, the prediction of the numerical control machine tool wear is achieved, and the effect that a single neural network cannot achieve is achieved.