The detection of electronic components plays an important role in improving the intelligence level of the manufacturing industry, but there is a problem of poor detection accuracy. Neural network algorithms cannot improve the detection accuracy and detection speed of electronic components. Therefore, this paper proposes a deep learning algorithm to detect electronic components. Firstly, deep separable convolution is introduced to reduce the overall complexity of the model. Then, abstract features are extracted through the efficient feature extraction network, and the pre-selection box is obtained by using the regional proposal network to complete the detection of electronic components. /b11>The MATLAB simulation results show that the algorithm proposed in this paper can effectively improve the accuracy and efficiency of electronic component detection.