New biofuels, as a sustainable energy alternative to traditional fossil fuels, are attracting global attention. With the increasing awareness of environmental protection and the continuous growth of energy demand, biofuels offer the possibility of reducing greenhouse gas emissions and decreasing dependence on fossil fuels. In this paper, by introducing the Wasserstein distance, which is used to describe the objective function of the GAN model, the self-attention mechanism is applied to improve the discriminator structure of the traditional WGAN-GP to achieve more efficient generation of high-quality data samples. The WGAN-GP model is used to design a new biofuel combustion scenario, and based on the combustion data, the new biofuel is prepared in the scenario. The final data generation results of the model are evaluated based on relevant evaluation indexes. It can be seen that the trend of the generated data set is consistent with the trend of the actual output value of the power station, and the interval range formed by the generated 50 sets of data can include the real data in a more complete way, with a high data coverage, and the error between the generated value and the real value is in the range of ±250-±300. The new biofuel output scenarios generated by the WGAN-GP model were utilized for EMF synthesis experiments. PTFE@ACMS-SO3H samples showed strong absorption peaks at 759cm-1 and 54cm-1 , indicating that the acidic groups-SO3H were successfully loaded on the surface of the material and the preparation of the novel biofuel was successful.