In actual production processes, the feed mass of a dewatering process is uncertain and a future production state cannot be predicted. This results in improper operation, a substandard production index, and a high energy economic index (EEI). To solve these problems, the authors propose a two‐step coordinated optimization model for the dewatering process based on production data. The prediction model of the dewatering process is first established using the data accumulated during production. A two‐step optimization model is then established to solve the problems existing in the dewatering process. The objective of the optimization is to minimize the EEI in the dewatering process, and the constraints are the ladder electricity price, operation safety, and production index. The genetic algorithm (GA) and gravitational search algorithm‐genetic algorithm (GSA‐GA) are used to solve the two‐step coordinated optimization model, and the computational time can meet the application demand. An offline simulation and a field application showed that the optimization model can be used to improve the production index and reduce the EEI, loss due to the filter cloth, and the frequency of abnormal production.

中文翻译：

---

脱水过程的两步协调优化模型

在实际生产过程中，脱水过程的进料质量是不确定的，并且无法预测未来的生产状态。这会导致操作不当，生产指标不合格以及能源经济指标（EEI）高。为解决这些问题，作者提出了基于生产数据的脱水过程的两步协调优化模型。首先使用在生产过程中积累的数据来建立脱水过程的预测模型。然后建立一个两步优化模型来解决脱水过程中存在的问题。优化的目的是使脱水过程中的EEI最小化，并且约束条件包括阶梯电价，操作安全性和生产指标。采用遗传算法（GA）和重力搜索遗传算法（GSA-GA）求解两步协调优化模型，计算时间可以满足应用需求。离线仿真和现场应用表明，该优化模型可用于提高生产指标，减少EEI，滤布损耗和异常生产频率。