Prediction of moisture content in municipal sludge drying process based on GA-BP-Garson model
-
摘要:
市政污泥干燥过程中内部水分检测困难，为准确预测市政污泥热风干燥过程中内部水分的变化规律，将干燥时间、干燥温度、泥层厚度、流量压差作为输入变量，含水率作为输出变量，采用BP神经网络以及GA-BP神经网络分别建立市政污泥热风干燥过程的水分预测模型；对GA-BP神经网络进行敏感性分析，研究了4个输入变量对预测结果的影响。结果表明，BP和GA-BP 2种水分预测模型测试集的决定系数（R2）分别为0.999 55和0.999 64，均方根误差（RMSE）分别为0.513 17和0.455 23，即GA-BP预测模型的预测效果更佳，能更准确地预测市政污泥干燥过程中含水率的动态变化。敏感性分析表明，干燥时间对GA-BP含水率预测模型的影响最为显著。研究结果可为污泥干燥工艺和过程的优化提供理论依据，为污泥资源化利用提供参考。
Abstract:During the municipal sludge drying process, the detection of internal moisture poses challenges. To accurately predict the variation pattern of internal moisture during the hot air drying process of municipal sludge, Back Propagation (BP) neural network and GA-BP (Genetic Algorithm Back Propagation) neural network algorithms were utilized to establish moisture prediction models for the municipal sludge hot air drying process, with drying time, drying temperature, sludge layer thickness, and flow differential pressure as input variables, and moisture content as the output variable. Moreover, a sensitivity analysis was conducted on the GA-BP neural network to investigate the impact of the four input variables on the prediction outcomes. The results indicated that the coefficients of determination (R2) for the BP and GA-BP moisture prediction models on the test set were 0.999 55 and 0.999 64, with root mean square errors (RMSE) of 0.513 17 and 0.455 23, respectively, demonstrating that the GA-BP algorithm-based prediction model achieved better performance, accurately predicting the dynamic changes of moisture during the municipal sludge drying process. The sensitivity analysis revealed that drying time had the most significant impact on the GA-BP moisture prediction model. These findings could provide a theoretical basis for optimising sludge drying processes and procedures and offer a reference for the resource utilization of sludge.
-
Key words:
- municipal sludge /
- drying /
- genetic algorithm /
- BP neural network /
- moisture prediction /
- sensitivity analysis
-
图 1 试验装置示意
1—风机；2—压力变送器；3—电加热器；4—阀门；5—电源控制柜；6—电子天平；7—计算机；8—温度传感器。
Figure 1. Experimental apparatus schematic diagram
表 1 市政污泥的组分特性
Table 1. Component characteristics of municipal sludge
污泥组分 质量分数（干基）/% 有机组分 挥发分 30.6~71.8 固定碳 0.6~9.3 灰分 20.0~70.0 元素分析 C 15.8~48.7 H 2.0~9.0 O 10.7~25.3 N 1.0~6.0 S 0.2~3.6 
下载: 导出CSV
表 2 污泥热风干燥试验方案
Table 2. Experimental scheme of sludge hot air drying
试验分组 干燥温度/℃ 泥层厚度/mm 流量压差/kPa 50 10 1 1 60 10 1 70 10 1 60 5 1 2 60 10 1 60 15 1 60 10 0.61 3 60 10 0.85 60 10 1
下载: 导出CSV
表 3 遗传算法的参数
Table 3. Parameters of genetic algorithm
参数 数值 个体范围 (−3，3) 种群规模 60 迭代次数 400 交叉概率 0.4 变异概率 0.015
下载: 导出CSV
-
[1] ZHOU A, WANG X B, YU S L, et al. Process design and optimization on self-sustaining pyrolysis and carbonization of municipal sewage sludge[J]. Waste Management,2023,159:125-133. doi: 10.1016/j.wasman.2023.01.035 [2] SYED-HASSAN S S A, WANG Y, HU S, et al. Thermochemical processing of sewage sludge to energy and fuel: fundamentals, challenges and considerations[J]. Renewable and Sustainable Energy Reviews,2017,80:888-913. doi: 10.1016/j.rser.2017.05.262 [3] 张钧羿, 魏建兵, 韩冬, 等. 沈阳市政污泥制备烧结砖的试验探究[J]. 环境工程技术学报,2023,13(3):1187-1193. doi: 10.12153/j.issn.1674-991X.20220469ZHANG J Y, WEI J B, HAN D, et al. Experimental study on the making of sintered brick using municipal sludge in Shenyang City[J]. Journal of Environmental Engineering Technology,2023,13(3):1187-1193. doi: 10.12153/j.issn.1674-991X.20220469 [4] 王毅斌, 冯敬武, 谭厚章, 等. 市政污泥热化学处置中磷元素形态转变与回收利用研究进展[J]. 化工进展,2023,42(2):985-999.WANG Y B, FENG J W, TAN H Z, et al. Research progress on phosphorus speciation transformation and recovery during thermal chemical conversion of municipal sewage sludge[J]. Fine Chemicals,2023,42(2):985-999. [5] ZHU Q X, SUN X F, GE S F, et al. Insights into the characteristics and mechanism of vacuum drying technology for municipal sludge processing[J]. Chemosphere,2023,310:136729. doi: 10.1016/j.chemosphere.2022.136729 [6] ZHANG T, YAN Z W, WANG L Y, et al. Theoretical analysis and experimental study on a low-temperature heat pump sludge drying system[J]. Energy,2021,214:118985. doi: 10.1016/j.energy.2020.118985 [7] 周印羲, 石万, 李晓姣, 等. 污泥低温余热干化的模拟研究及参数优化[J]. 中国环境科学,2023,43(8):4099-4105. doi: 10.3969/j.issn.1000-6923.2023.08.026ZHOU Y X, SHI W, LI X J, et al. Simulation study and optimization of parameters for low temperature drying of sludge using waste heat[J]. China Environmental Science,2023,43(8):4099-4105. doi: 10.3969/j.issn.1000-6923.2023.08.026 [8] 吴文庆. 污泥低温干化技术与模型模拟研究进展[J]. 环境工程,2023,41(增刊2):644-650.WU W Q. The research progress of sludge low temperature drying technology and model simulation[J]. Environmental Engineering,2023,41(Suppl 2):644-650. [9] 辛旺, 宋永会, 张亚迪, 等. 污泥基碳吸附材料的制备及其吸附性能研究进展[J]. 环境工程技术学报,2017,7(3):306-317. doi: 10.3969/j.issn.1674-991X.2017.03.044XIN W, SONG Y H, ZHANG Y D, et al. Research progress of preparation of sewage sludge-based carbonaceous adsorbents and their adsorption characteristics[J]. Journal of Environmental Engineering Technology,2017,7(3):306-317. doi: 10.3969/j.issn.1674-991X.2017.03.044 [10] BHAGYA RAJ G V S, DASH K K. Comprehensive study on applications of artificial neural network in food process modeling[J]. Critical Reviews in Food Science and Nutrition,2022,62(10):2756-2783. doi: 10.1080/10408398.2020.1858398 [11] HUANG Y W, CHEN M Q. Artificial neural network modeling of thin layer drying behavior of municipal sewage sludge[J]. Measurement,2015,73:640-648. doi: 10.1016/j.measurement.2015.06.014 [12] ZHANG Y G, PAN G F, CHEN B, et al. Short-term wind speed prediction model based on GA-ANN improved by VMD[J]. Renewable Energy,2020,156:1373-1388. doi: 10.1016/j.renene.2019.12.047 [13] SUN T S, LING F. Prediction method of wheat moisture content in the hot air drying process based on backpropagation neural network optimized by genetic algorithms[J]. Journal of Food Processing and Preservation,2022,46(6):e16565. [14] FABANI M P, CAPOSSIO J P, ROMÁN M C, et al. Producing non-traditional flour from watermelon rind pomace: artificial neural network (ANN) modeling of the drying process[J]. Journal of Environmental Management,2021,281:111915. doi: 10.1016/j.jenvman.2020.111915 [15] YANG T Q, ZHENG X, VIDYARTHI S K, et al. Artificial neural network modeling and genetic algorithm multiobjective optimization of process of drying-assisted walnut breaking[J]. Foods,2023,12(9):1897. doi: 10.3390/foods12091897 [16] BHAGYA RAJ G V S, DASH K K. Microwave vacuum drying of dragon fruit slice: artificial neural network modelling, genetic algorithm optimization, and kinetics study[J]. Computers and Electronics in Agriculture,2020,178:105814. doi: 10.1016/j.compag.2020.105814 [17] 黄艳琴, 甄宇航, 王晨州, 等. “双碳”背景下市政污泥热解资源化利用研究进展[J]. 材料导报,2023,37(10):29-34.HUANG Y Q, ZHEN Y H, WANG C Z, et al. Research progress on pyrolysis and resource utilization of municipal sewage sludge in context of 'peak carbon dioxide emissions and carbon neutrality'[J]. Materials Reports,2023,37(10):29-34. [18] 杨俊祺, 范晓军, 赵跃华, 等. 基于PSO-BP神经网络的山西省碳排放预测[J]. 环境工程技术学报,2023,13(6):2016-2024. doi: 10.12153/j.issn.1674-991X.20230190YANG J Q, FAN X J, ZHAO Y H, et al. Prediction of carbon emissions in Shanxi Province based on PSO-BP neural network[J]. Journal of Environmental Engineering Technology,2023,13(6):2016-2024. doi: 10.12153/j.issn.1674-991X.20230190 [19] SATORABI M, SALEHI F, RASOULI M. The influence of xanthan and balangu seed gums Coats on the kinetics of infrared drying of apricot slices: GA-ANN and ANFIS modeling[J]. International Journal of Fruit Science,2021,21(1):468-480. doi: 10.1080/15538362.2021.1898520 [20] MING J L K, ANUAR M S, HOW M S, et al. Development of an artificial neural network utilizing particle swarm optimization for modeling the spray drying of coconut milk[J]. Foods,2021,10(11):2708. □ doi: 10.3390/foods10112708 -
下载:
点击查看大图
计量
- 文章访问数: 77
- HTML全文浏览量: 57
- PDF下载量: 12
- 被引次数: 0
