Rapid measurement of sludge sedimentation ratio based on polarization information

Xinqiang WANG; Shan QIN; Xiaobing SUN; Wei XIONG; Song YE; Fangyuan WANG; Xuanke TONG

doi:10.5768/JAO202546.0103001

Journal of Applied Optics, Volume. 46, Issue 1, 121(2025)

Rapid measurement of sludge sedimentation ratio based on polarization information

Xinqiang WANG^1,3, Shan QIN^1,3, Xiaobing SUN^2,4, Wei XIONG^2,4, Song YE^1,3, Fangyuan WANG^1,3, and Xuanke TONG^1,3、*

Author Affiliations

¹School of Optoelectronic Engineering, Guilin University of Electronic Technology, Guilin 541004, China

²Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China

³Guangxi Key Laboratory of Optoelectronic Information Processing, Guilin 541004, China

⁴Key Laboratory of General Optical Calibration and Characterization of Chinese Academy of Sciences, Hefei 230031, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(12)

Fig. 1. Structure diagram of BP neural network

Download full size

View in Article

Fig. 2. Structure diagram of detection system for rapid measurement of sludge sedimentation ratio

Download full size

View in Article

$Detection schematic of three-fractional beam polarization camera$

Fig. 3. Detection schematic of three-fractional beam polarization camera

Download full size

View in Article

Fig. 4. Actual experimental environment

Download full size

View in Article

Fig. 5. Original images of I, Q, U, P and $θ$ of selected water samples

Download full size

View in Article

Fig. 6. MSE curves of sludge settling ratio BP neural network with node number from 8 to 13 based on polarization information

Download full size

View in Article

Fig. 7. Correlation diagrams of each sample set and population in BP network training model for temporal sludge sedimentation ratio based on I single input

Download full size

View in Article

Fig. 8. Correlation diagrams of each sample set and population in BP network training model for sludge sedimentation ratio based on polarization information

Download full size

View in Article

Fig. 9. Comparison curves of relative errors of sludge sedimentation ratio prediction at different inputs

Download full size

View in Article

Table 1. Algorithm steps

View table

View in Article

Table 1. Algorithm steps

内容：基于偏振信息的污泥沉降比BP神经网络模型构建及验证
输入：污泥水样的 I、Q、U、P、 $θ$ 偏振信息
输出：污泥沉降比
步骤1：读取所有沉降比实验数据及对应的偏振信息数据
步骤2：将数据分为训练集以及预测集，将训练集数据归一化
步骤3：设置训练次数、学习速率以及目标最小误差
步骤4：用训练集进行BP神经网络模型的构建
步骤5：预测集数据归一化，使用预测集数据进行模型的验证，预测结果反归一化，并计算真实值与预测值之间的误差

Table 2. Parameters list of three-fractional beam polarization camera
View table
View in Article
Table 2. Parameters list of three-fractional beam polarization camera
参数指标
分辨率/pixel 1392×1040
CCD尺寸/mm 24 ×36
像元尺寸/μm 6.45 ×6.45
偏振探测波段/nm 500～1000
镜头焦距/mm 51.7
偏振片角度/(°) 0、45、90

Table 3. Model prediction errors at different inputs
View table
View in Article
Table 3. Model prediction errors at different inputs
输入类型平均相对误差/% 均方误差均方根误差
偏振信息共同作为输入 4.361 0.00014 0.01213
光强I单独作为输入 9.789 0.00032 0.01790

Tools

Get Citation

Copy Citation Text

Xinqiang WANG, Shan QIN, Xiaobing SUN, Wei XIONG, Song YE, Fangyuan WANG, Xuanke TONG. Rapid measurement of sludge sedimentation ratio based on polarization information[J]. Journal of Applied Optics, 2025, 46(1): 121

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites