Laser additive manufacturing technology has been applied in many fields, but due to the lack of corresponding monitoring and diagnosis of the manufacturing process, it hinders the development and application of this technology in the highly sophisticated field where the quality of products is strictly required. In this paper, the laser induced plasma method is used to monitor the composition of Cr in the laser additive manufacturing process. Firstly, the spectral data is collected by experiment. Secondly, the spectral characteristics affecting the Cr concentration are found. Finally, the Cr concentration monitoring model is established according to the relevant spectral characteristics. The model used in this paper is the support vector machine model. The experimental results show that the model can accurately predict the Cr concentration in the laser additive manufacturing process. When the Cr concentration is 11.9%, the absolute error of calibration of the whole process is 0.67%, the relative error of calibration is 5.04%, and the relative standard error is 4.23%. When the model was applied to component monitoring, it was found that the predicted value fluctuated around the actual Cr concentration value with a small amplitude.