The invention discloses a smelting burdening method based on an optimized ecological niche genetic algorithm, which comprises the following steps: S1, establishing a multi-objective function, proposing indexes of various parameters as multi-constraint conditions, and establishing a burdening optimization mathematical model; S2, performing weighting processing on the multi-objective function basedon a difference particle swarm optimization method, and converting the multi-objective model into a problem of a single-objective function; S3, dividing the population into K clusters according to a K-means clustering algorithm, and determining a clustering center; S4, performing selection, self-adaptive crossover, self-adaptive variation and niche elimination operation; and S5, judging whether atermination condition is met or not to obtain the final addition amount of the ingredients. According to the invention, problems of difficult multi-objective solving and easy falling into a local optimal solution and the like existing in batching optimization are solved; according to the smelting batching method based on the optimized ecological niche genetic algorithm, the three processes of determining the weight of the multi-objective function, the ecological niche radius and crossover and mutation operators are improved, the accuracy of the batching ratio is effectively and remarkably improved, and the cost is saved.