留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于改进粒子群算法优化BP神经网络的废水处理软测量模型

何丹 林来鹏 李小勇 牛国强 易晓辉 黄明智

何丹, 林来鹏, 李小勇, 牛国强, 易晓辉, 黄明智. 基于改进粒子群算法优化BP神经网络的废水处理软测量模型[J]. 华南师范大学学报(自然科学版), 2021, 53(2): 114-120. doi: 10.6054/j.jscnun.2021034
引用本文: 何丹, 林来鹏, 李小勇, 牛国强, 易晓辉, 黄明智. 基于改进粒子群算法优化BP神经网络的废水处理软测量模型[J]. 华南师范大学学报(自然科学版), 2021, 53(2): 114-120. doi: 10.6054/j.jscnun.2021034
HE Dan, LIN Laipeng, LI Xiaoyong, NIU Guoqiang, YI Xiaohui, HUANG Mingzhi. A Soft Measurement Model of Wastewater Treatment Process Based on BP Neural Network with Improved Particle Swarm Optimization Algorithms[J]. Journal of South China normal University (Natural Science Edition), 2021, 53(2): 114-120. doi: 10.6054/j.jscnun.2021034
Citation: HE Dan, LIN Laipeng, LI Xiaoyong, NIU Guoqiang, YI Xiaohui, HUANG Mingzhi. A Soft Measurement Model of Wastewater Treatment Process Based on BP Neural Network with Improved Particle Swarm Optimization Algorithms[J]. Journal of South China normal University (Natural Science Edition), 2021, 53(2): 114-120. doi: 10.6054/j.jscnun.2021034

基于改进粒子群算法优化BP神经网络的废水处理软测量模型

doi: 10.6054/j.jscnun.2021034
基金项目: 

国家自然科学基金项目 41977300

广东省自然科学基金项目 2016A030306033

广东省科技计划项目 2017B030314057

福建省科技计划项目 2020I1001

广州市民生计划项目 202002020055

详细信息
    通讯作者:

    黄明智,Email:mingzhi.huang@m.scnu.edu.cn

  • 中图分类号: X703;TP183

A Soft Measurement Model of Wastewater Treatment Process Based on BP Neural Network with Improved Particle Swarm Optimization Algorithms

  • 摘要: 针对废水处理过程BP神经网络软测量模型受处理过程非线性特征影响,存在收敛速度慢、陷入局部极小点等问题,用改进的粒子群算法(PSO)优化BP神经网络,建立废水处理过程中出水化学需氧量(CODeff)与出水固体悬浮物(SSeff)的软测量模型(PSO-BP模型),并与基于遗传算法-BP神经网络算法的模型(GA-BP模型)及BP模型的预测效果进行对比. 研究结果表明:采用PSO-BP模型预测CODeff时,均方根误差(RMSE)、决定系数(R2)分别为3.995 5、0.640 1,而用于预测SSeff时,RMSE、R2分别为0.650 3、0.681 1;相比BP模型和GA-BP模型,PSO-BP模型对CODeff的预测性能分别提高了4.49%、0.44%,对SSeff的预测性能分别提高了40.11%、24.77%.
  • 图  1  三层BP神经网络结构

    Figure  1.  The structure of three-layer BP neural network

    图  2  粒子群改进算法优化BP神经网络的基本流程

    Figure  2.  The BP neural network optimized using improved PSO

    图  3  PSO-BP模型的适应度函数曲线

    Figure  3.  The fitness curve of the PSO-BP prediction model

    图  4  PSO-BP模型的预测结果

    Figure  4.  The prediction results with the PSO-BP model

    图  5  BP模型的预测结果

    Figure  5.  The prediction results with the BP model

    图  6  GA-BP模型的预测结果

    Figure  6.  The prediction results with the GA-BP model

    表  1  3种模型性能指标比较

    Table  1.   The comparison of performance between the three models

    性能指标 CODeff预测 SSeff预测
    PSO-BP模型 GA-BP模型 BP模型 PSO-BP模型 GA-BP模型 BP模型
    RMSE 3.995 5 4.059 9 4.369 0 0.650 3 0.642 8 0.709 8
    R2 0.640 1 0.637 3 0.612 6 0.681 1 0.545 9 0.486 1
    下载: 导出CSV
  • [1] 蒙西, 乔俊飞, 韩红桂. 基于类脑模块化神经网络的污水处理过程关键出水参数软测量[J]. 自动化学报, 2019, 45(5): 906-919. https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201905008.htm

    MENG X, QIAO J F, HAN H G. Soft measurement of key effluent parameters in wastewater treatment process using brain-like modular neural networks[J]. ACTA Automatica Sinica, 2019, 45(5): 906-919. https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201905008.htm
    [2] HUANG M Z, MA Y W, WAN J Q, et al. A sensor-software based on a genetic algorithm-based neural fuzzy system for modeling and simulating a wastewater treatment process[J]. Applied Soft Computing, 2015, 27: 1-10. doi: 10.1016/j.asoc.2014.10.034
    [3] 严玉洁. AMBR工艺畜禽养殖污水处理及BP神经网络水质预测研究[D]. 银川: 宁夏大学, 2017.

    YAN Y J. Study on dairy wastewater treatment by AMBR and effluent quality forecast by BP neural network[D]. Yinchuan: Ningxia University, 2017.
    [4] CANETE J F D, SAZ-OROZCO P D, BARATTI R, et al. Soft-sensing estimation of plant effluent concentrations in a biological wastewater treatment plant using an optimal neural network[J]. Expert Systems with Applications, 2016, 63: 8-19. doi: 10.1016/j.eswa.2016.06.028
    [5] 韩广, 乔俊飞, 韩红桂, 等. 基于Hopfield神经网络的污水处理过程优化控制[J]. 控制与决策, 2014, 29(11): 2085-2088. https://www.cnki.com.cn/Article/CJFDTOTAL-KZYC201411029.htm

    HAN G, QIAO J F, HAN H G, et al. Optimal control for wastewater treatment process based on Hopfied neural network[J]. Control and Decision, 2014, 29(11): 2085-2088. https://www.cnki.com.cn/Article/CJFDTOTAL-KZYC201411029.htm
    [6] WANG J, WEN Y, YE Z, et al. Convergence analysis of BP neural networks via sparse response regularization[J]. Applied Soft Computing, 2017, 61: 354-363. doi: 10.1016/j.asoc.2017.07.059
    [7] SRIDEVI K, SIVARAMAN E, MULLAI P. Back propagation neural network modelling of biodegradation and fermentative biohydrogen production using distillery waste-water in a hybrid upflow anaerobic sludge blanket reactor[J]. Bioresource Technology, 2014, 165: 233-240. doi: 10.1016/j.biortech.2014.03.074
    [8] ZAGHLOUL M S, HAMZA R A, IORHEMEN O T, et al. Performance prediction of an aerobic granular SBR using modular multilayer artificial neural networks[J]. Science of the Total Environment, 2018, 645: 449-459. doi: 10.1016/j.scitotenv.2018.07.140
    [9] 刘亚丽, 李英娜, 李川. 基于遗传算法优化BP神经网络的线损计算研究[J]. 计算机应用与软件, 2019, 36(3): 72-75. https://www.cnki.com.cn/Article/CJFDTOTAL-JYRJ201903015.htm

    LIU Y L, LI Y N, LI C. Line loss calculation of optimized BP neural network based on genetic algorithm[J]. Computer Applications and Software, 2019, 36(3): 72-75. https://www.cnki.com.cn/Article/CJFDTOTAL-JYRJ201903015.htm
    [10] 谢武明, 李俊, 周峰平, 等. 基于BP神经网络和遗传算法的污水处理厂电耗预测[J]. 水电能源科学, 2018, 36(8): 202-204. https://www.cnki.com.cn/Article/CJFDTOTAL-SDNY201808050.htm

    XIE W M, LI J, ZHOU F P, et al. Prediction of power consumption of wastewater treatment plant using BP neural network and genetic algorithm[J]. Water Resources and Power, 2018, 36(8): 202-204. https://www.cnki.com.cn/Article/CJFDTOTAL-SDNY201808050.htm
    [11] ABUALIGAH L M, KHADER A T, HANANDEH E S. A new feature selection method to improve the document clustering using particle swarm optimization algorithm[J]. Journal of Computational Science, 2017, 25: 456-466. http://www.sciencedirect.com/science/article/pii/S1877750316305002
    [12] 叶永伟, 葛沈浩, 任设东, 等. 基于PSO-DE算法的污水处理优化控制研究[J]. 计算机测量与控制, 2016, 24(2): 68-70;76. https://www.cnki.com.cn/Article/CJFDTOTAL-JZCK201602020.htm

    YE Y W, GE S H, REN S D, et al. Optimal control for wastewater treatment process based on mixed POS-DE algorithm[J]. Computer Measurement and Control, 2016, 24(2): 68-70;76. https://www.cnki.com.cn/Article/CJFDTOTAL-JZCK201602020.htm
    [13] 乔俊飞, 逄泽芳, 韩红桂. 基于改进粒子群算法的污水处理过程神经网络优化控制[J]. 智能系统学报, 2012, 7(5): 429-436. doi: 10.3969/j.issn.1673-4785.201205034

    QIAO J F, PANG Z F, HAN H G. Neural network optimal control for wastewater treatment process based on APSO[J]. CAAI Transactions on Intelligent Systems, 2012, 7(5): 429-436. doi: 10.3969/j.issn.1673-4785.201205034
    [14] 徐建栋. 遗传算法和神经网络在污水处理控制及监测系统中的应用研究[D]. 重庆: 重庆大学, 2007.

    XU J D. Application research of genetic algorithms and artificial neural network in control and monitoring system of waste water treatment[D]. Chongqing: Chongqing University, 2007.
    [15] JAMALIPOUR M, SAVAREH R, GHARIB M, et al. Quantum behaved particle swarm optimization with differential mutation operator applied to WWER-1000 in-core fuel management optimization[J]. Annals of Nuclear Energy, 2013, 54: 134-140. doi: 10.1016/j.anucene.2012.11.008
    [16] CHEN Y, LI L, HAIPENG P, et al. Particle swarm optimizer with two differential mutation[J]. Applied Soft Computing, 2017, 61: 314-330. doi: 10.1016/j.asoc.2017.07.020
    [17] 吕振肃, 侯志荣. 自适应变异的粒子群优化算法[J]. 电子学报, 2004(3): 416-420. doi: 10.3321/j.issn:0372-2112.2004.03.016

    LV Z S, HOU Z R. Particle swarm optimization with adaptive mutation[J]. Acta Electronica Sinica, 2004(3): 416-420. doi: 10.3321/j.issn:0372-2112.2004.03.016
    [18] 孙湘, 周大为, 张希望. 惯性权重粒子群算法模型收敛性分析及参数选择[J]. 计算机工程与设计, 2010, 31(18): 4068-4071. https://www.cnki.com.cn/Article/CJFDTOTAL-SJSJ201018037.htm

    SUN X, ZHOU D W, ZHANF X W. Convergence analysis and parameter selection of PSO model with inertia weight[J]. Computer Engineering and Design, 2010, 31(18): 4068-4071. https://www.cnki.com.cn/Article/CJFDTOTAL-SJSJ201018037.htm
    [19] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323: 533-536. doi: 10.1038/323533a0
    [20] PARK J B, LEE K S, SHIN J R, et al. A particle swarm optimization for economic dispatch with nonsmooth cost functions[J]. IEEE Transactions on Power Systems, 2005, 20(1): 34-42. doi: 10.1109/TPWRS.2004.831275
    [21] NEYESTANI M, FARSANGI M M, NEZAMABADI-POUR H, et al. A modified particle swarm optimization for economic dispatch with nonsmooth cost functions[J]. IFAC Proceedings Volumes, 2009, 42: 267-272. http://www.emeraldinsight.com/servlet/linkout?suffix=frd3&dbid=16&doi=10.1108%2F03321640710823046&key=10.1109%2FTPWRS.2004.831275
    [22] NIU G Q, YI X H, CHEN C, et al. A novel effluent quality predicting model based on genetic-deep belief network algorithm for cleaner production in a full-scale paper-ma-king wastewater treatment[J]. Journal of Cleaner Production, 2020, 265: 433-441. http://www.sciencedirect.com/science/article/pii/S0959652620318345
  • 加载中
图(6) / 表(1)
计量
  • 文章访问数:  38
  • HTML全文浏览量:  8
  • PDF下载量:  6
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-11-09
  • 网络出版日期:  2021-04-29
  • 刊出日期:  2021-04-25

目录

    /

    返回文章
    返回