基于bp神经网络的sbr污水测控技术研究-测试计量技术及仪器专业论文.docxVIP

摘 摘 要 万方数据 万方数据 摘 要 随着计算机和自动控制技术的发展，SBR 工艺在城市污水、工业废水中的 应用越加广泛，已经成为中小城镇污水及工业废水处理的首选。SBR 工艺仍属 于发展中的污水处理技术。在硬件设备满足需求的条件下，控制策略开发成为 SBR 节能控耗的关键。智能控制是 SBR 控制策略的发展方向。神经网络为具有 高度复杂、多变量、非线性特点的污水处理实时控制创造了条件。现今我国大 部分的污废水处理系统采用 DCS 及 PLC 的计算机控制技术，有学者开始研究基 于嵌入式系统方案的污水测控系统。 本文针对嵌入式 Linux 开发复杂、缺少强大技术支持等缺点，选用了和桌面 Windows 系统开发相似的 Windows 7 组件化嵌入式操作系统 Windows Embedded Standard 7，为 SBR 工艺神经网络控制建立一个操作系统平台。研究 WES7 的定 制过程，对 WES7 的功能模块进行详细分析。 本文以训练算法为重点，介绍反向传播 (back-propagation, BP) 神经网络。 在 Windows Embedded Standard 7 操作系统基础上，利用 Matlab 2013a 神经网络 工具箱，建立三层结构为 3-8-2 的 BP 神经网络。该网络能通过 SBR 工艺中的进 水 COD、初始 DO、初始 MLSS，实现曝气工段的曝气量和曝气时间预测。在 Dev c++ 集成开发环境中，通过分析并改写 C 语言程序，实现 SBR 工艺 pH 值 时间变化序列的 BP 神经网络预测。 关键词：SBR 工艺；Windows Embedded Standard 7；BP 神经网络；Matlab 神经 网络工具箱 I AB ABSTRACT ABSTRACT With the development of computer and automatic control technology, the application of SBR process is more widely used in the treatment of urban sewage and industrial wastewater. It has become the best choice of the treatment of small-medium urban sewage and industrial wastewater. SBR process is still a developing sewage treatment technology. The development of control strategy is the key of the SBR energy consumption under the conditions that the reasonable hardware equipment is provided. Intelligent Control determines the development direction for SBR control strategy. Moreover, sewage treatment of highly complexity, multi variable, and nonlinear, neural network has created the conditions for real-time control, also it manifests high potential in energy saving system. Today, the wastewater treatment system is mostly adopting Computer Control Technique of the DCS and PLC. Many scholars set up to studying sewage treatment control system based on embedded system. Embedded Linux has some shortcoming—development complexity, lack of strong technical support. Therefore the paper presents Windows 7 componentized embedded operating system which is similar to desktop Windows systems--Windows Embedded Standard 7 instead. The