论文部分内容阅读
为了对水处理过程中水质浊度进行实时、准确检测,设计了基于红外光的散射浊度检测系统,并提出一种聚类灰色融合的预测模型对水质浊度的变化趋势进行有效预测。利用890 nm波长的红外发光二极管作为发光器件,光敏二极管作为接收器,检测装置响应时间短,零点误差小。采用灰色预测算法和聚类融合的方法对传感器所采集的数据进行处理,将聚类融合处理后的数据作为灰色预测控制的输入数据,灰色预测控制的输出数据与融合数据进行对比分析,确定预测浊度值。通过实际项目进行了数据跟踪和运算,聚类灰色融合算法的浊度预测输出值和实测值的平均误差值为0.008 7 NTU,聚类灰色融合算法预测性能优于单一的灰色预测算法,能够保证水质浊度参数的平稳,满足了水质的要求。
In order to detect the turbidity of water during the water treatment in real time and accurately, a scattering turbidity detection system based on infrared light was designed and a clustering gray fusion prediction model was proposed to predict the trend of water turbidity effectively. The infrared light-emitting diode with 890 nm wavelength is used as a light-emitting device and the photodiode is used as a receiver. The response time of the detection device is short and the zero point error is small. The gray prediction algorithm and clustering fusion method are used to process the data collected by the sensor. The clustering fusion data is used as the gray prediction control input data. The gray prediction control output data and the fusion data are compared to determine the prediction Turbidity value. The data tracking and computing are carried out through the actual project. The average error between the gray prediction and output of the clustering gray fusion algorithm is 0.008 7 NTU. The prediction performance of clustering gray fusion algorithm is better than the single gray prediction algorithm Turbidity of water quality parameters of a smooth, to meet the water quality requirements.