The concentration of hydrate inorganic salt inhibitors is closely related to inhibition efficiency, production cost, and equipment corrosion. Therefore, predicting the concentration of hydrate inorganic salt inhibitors is great significance. Taking the prediction of NaCl concentration as an example, the temperature, pressure, and gas components processed by Kernel Principal Component Analysis (KPCA) were used as input parameters. The Wavelet Neural Network (WNN) was utilized to predict the NaCl concentration, and the WNN was optimized by the Genetic algorithm (GA), Simulated annealing algorithm (SA), and AdaBoost algorithm. The AdaBoost-GASA-WNN prediction model for the concentration of the hydrate inhibitor NaCl was established, addressing the current lack of methods for predicting the concentration of inorganic salt inhibitors for hydrates. The results show that the model"s Mean Square Error (MSE) decreased by 3.8658 after KPCA processing, and the MSE of the optimized model was further reduced to 9.5062. Compared with the ELM, KNN, RF, and data fitting methods, the MSE declined by 5.7994, 17.7416, 2.912, and 8.8105, respectively. This indicates the best prediction performance of the AdaBoost-GASA-WNN prediction model, providing a reference for determining the concentration of inorganic salts in hydrate prevention and control.