Rodriguez-Roda I, Sànchez-Marrè M, Comas J, Baeza J, Colprim J, Lafuente J, Cortés U, Poch M
Laboratori d'Enginyeria Química i Ambiental, Universitat de Girona, Catalonia, Spain.
Water Sci Technol. 2002;45(4-5):289-97.
Integrated operation of Wastewater Treatment Plants is still far from being solved. A reasonable proposal should link advanced and robust control algorithms to some knowledge-based techniques, allocating the detailed engineering to numerical computations, while delegating the logical analysis and reasoning to supervisory intelligent systems. This paper describes the development and implementation of a knowledge-based Hybrid Supervisory System to support the operation of a real Wastewater Treatment Plant. The system integrates different reasoning modules, overcoming the limitations in the use of each single technique, while providing an agent based architecture with additional modularity and independence. It is structured into three separated levels: data gathering, diagnosis, and decision support. The different tasks of the system are performed in a seven-step cycle: data gathering and update, diagnosis, supervision, prediction, communication, actuation, and evaluation phase. In spite of certain reservations of the scientific community about the use of these techniques, the system is successfully performing real-time support to the operation of the Granollers facility since September 1999. Results of the first four-month validation period are shown and discussed. An example of the system behavior is also shown in the paper. The conclusions indicate the key steps which are necessary to transfer the system to another facility.
污水处理厂的综合运营问题仍远未得到解决。一个合理的方案应该将先进且稳健的控制算法与一些基于知识的技术相结合，把详细的工程计算分配给数值计算，同时将逻辑分析和推理交给监控智能系统。本文描述了一个基于知识的混合监控系统的开发与实施，以支持实际污水处理厂的运营。该系统整合了不同的推理模块，克服了单一技术使用中的局限性，同时提供了具有额外模块化和独立性的基于代理的架构。它分为三个独立层次：数据收集、诊断和决策支持。系统的不同任务按七个步骤循环执行：数据收集与更新、诊断、监控、预测、通信、驱动和评估阶段。尽管科学界对这些技术的使用存在一定保留意见，但自1999年9月以来，该系统已成功为格拉诺列尔斯污水处理厂的运营提供实时支持。文中展示并讨论了前四个月验证期的结果。本文还给出了系统运行情况的一个示例。结论指出了将该系统转移到其他污水处理厂所需的关键步骤。
