MOPSO-Based Research on Manufacturing Process Optimization in Process Industry
To deal with the conflict between multiple targets involved in the manufacturing process of the process industry, multi-objective particle swarm optimization (MOPSO) is used to solve the optimization problem among multiple objectives. Basing on the manufacturing process analysis of the process industry and with the background of the cement manufacturing process of a process industry, two objective functions, which are the total processing cost and the integrated error of the mineral content in the cement compared to the standard, are established, and the concrete realization process of algorithm is given. The results of the example analysis show that when using the results by means of MOPSO algorithm to guide the production, it not only can improve the product performance index, but also can reduce the cost required as much as possible with the same performance indicators. Therefore, it is feasible to use the MOPSO algorithm to optimize the multi-objectives involved in the manufacturing process.
KeywordsProcess industry Particle swarm optimization Manufacturing process optimization
This work was supported by Key Research and Development Plan Project of Shandong Province, China (No. 2017GGX201001).
- 1.Pang, Q., Wan, M., Wu, X.G., Wang, J.Y.: Multi-objective optimization design method based neural network for raw meal proportioning of cement. J. Southeast Univ. 39, 76–81 (2009)Google Scholar
- 2.Gong, W., Jiang, Z.H., Zheng, W., Chen, N.Z.: Component controlling model in BOF steelmaking process. J. Northeast. Univ. 23(12), 1155–1157 (2002). (in Chinese)Google Scholar
- 3.Lv, X.W., Bai, C.G., Qiu, G.B., Ouyang, Q., Huang, Y.M.: Research on sintering burdening optimization based on genetic algorithm. Iron Steel 46(4), 12–15 (2007). (in Chinese)Google Scholar
- 5.Bian, P.Y., Li, D., Bao, B.J., Lu, Y.: Application of particle swarm optimization in production logistics scheduling. Comput. Eng. Appl. 46(17), 220–223 (2010). (in Chinese)Google Scholar
- 6.Xing, X.H., Lu, J.G., Xie, J.C.: Reservoir flood control operation based on improved multi-objective particle swarm optimization algorithm. Comput. Eng. Appl. 48(30), 33–39 (2012). (in Chinese)Google Scholar
- 7.Zhang, J., Cheng, C.T., Liao, S.L., Zhang, S.Q.: Application of improved particle swarm optimization in the optimal scheduling of hydropower stations. J. Hydraul. Eng. 40(4), 435–441 (2004). (in Chinese)Google Scholar
- 8.Mostaghim, S., Teich, J.: Strategies for finding good local guides in multi-objective particle swarm optimization (MOPSO). In: IEEE 2003 Swarm Intelligence Symposium, pp. 26–33 (2003)Google Scholar
- 9.Huang, N., Liu, B.: An overview of multi-agent technology. Microprocessors 31(2), 1–4 (2010). (in Chinese)Google Scholar
- 10.Zhao, X.Z., Song, B., Yu, C.M.: Multi-agent complex system modeling method based on BDI. Inf. Technol. 10, 121–123 (2015). (in Chinese)Google Scholar
- 11.Ni, J.J.: Theory and Application of Multi-agent Modeling and Control for Complex Systems. Publishing House of Electronics Industry, Beijing (2011). (in Chinese)Google Scholar