The rapid and accurate measurement of biochemical oxygen demand (BOD) is very important for the regulation of wastewater treatment process. Aiming at the problems of lower timeliness of BOD concentration measurement in the wastewater treatment process, the least squares support vector machine (LSSVM) is selected as the BOD prediction model and the particle swarm optimization (PSO) algorithm is selected to optimize the regression performance parameters. At the same time, the adaptive inertia weight calculation method is used to improve the PSO algorithm. After establishing the IPSO-LSSVM prediction model, the model is used to simulate and study the data of a wastewater treatment plant (WWTP). Finally, three types of errors are selected to calculate and analyze the prediction accuracy. The prediction results show that the model has the good prediction accuracy.