The invention relates to a convolutional neural network electronic component quality detection method based on deep learning, and belongs to the technical field of fault diagnosis and signal processing and analysis. The method comprises the following steps: firstly, searching images of unqualified electronic components, such as component missing and wrong marking, dividing the collected images into a training set, a verification set and a test set, and carrying out unqualified region marking on the images in a data set, including coordinate information and classification information; secondly,constructing a convolutional neural network model for electronic component quality detection; training a convolutional neural network model for detecting the images of the unqualified components by utilizing the images in the training data set; performing quality detection on the unqualified component images in the test data set by using the trained convolutional neural network model for crack image detection. According to the method disclosed in the invention, the network model can effectively increase the selection of unqualified components, the speed is faster than that of a traditional multi-step image detection method, and more images can be processed in a short time; the network model can obtain finer local details; therefore, the whole network can realize effective progressive feature transmission, and the quality detection precision of the electronic components of the network model is improved.