**5. Conclusions**

By combining the improved EWT algorithm, MFE feature extraction, and AEPSO\_PNN clustering, a load identification model of a ball mill is constructed. The main contributions to this work are as follows:


In future research, the algorithm, structure, and parameter setting process of the proposed model will be optimized and improved to enhance the ability of the model to identify the ball mill load state.

**Author Contributions:** Conceptualization, G.C., X.L. (Xin Liu) and C.D.; methodology, G.C. and X.L. (Xin Liu); software, X.L. (Xin Liu) and C.D.; validation, G.C., X.L. (Xin Liu), and X.L. (Xiaoyan Luo); formal analysis, G.C. and X.L. (Xin Liu); investigation, G.C. and X.L. (Xiaoyan Luo); resources, X.L. (Xin Liu) and C.D.; data curation, G.C. and X.L. (Xin Liu); writing—original draft preparation, G.C. and X.L. (Xin Liu); writing—review and editing, G.C., X.L. (Xin Liu), and X.L. (Xiaoyan Luo); visualization, X.L. (Xin Liu) and C.D.; supervision, G.C.; project administration, G.C.; funding acquisition, G.C.

**Funding:** This research was supported by the National Natural Science Foundation of China (No. 51464017) and by a project of the Jiangxi Key Research and Development Plan, China (20181ACE50034).

**Conflicts of Interest:** The authors declare no conflicts of interest.
