针对检测生化需氧量(BOD)的传统五日培养法(BOD5)操作复杂、时效性差的不足,以及水质中复杂环境因素干扰检测过程等问题,提出了基于微生物膜法的快速检测系统,进而以粒子群算法(PSO)优化的极限学习机(ELM)算法来实现BOD检测。检测系统以溶解氧传感器和微生物膜反应器为核心,能够在35min内完成检测,其中微生物反应器使用功能化的螺旋玻璃管制成,但微生物膜易受水质复杂环境的影响。为此,运用PSO-ELM算法消除水质中浊度(SS)、pH值、氧化还原电位(ORP)对检测结果的干扰,与BP神经网络和ELM算法相比,运行时间分别缩短0.92s和0.24s,测试误差分别减小5.3%和4.0%。在实际海水水样的测试结果中,该方法与BOD5法相对误差保持在2.69%~3.86%内。
Abstract
In order to overcome the shortcoming of complex operation, poor time-efficiency of traditional five-day culture method (BOD5), and the influence of complex environmental factors on the detection process in actual water quality, a detection method of BOD combining the rapid detection system and the extreme learning machine (ELM) algorithm optimized by particle swarm optimization (PSO) was proposed. The detection system was centered on a dissolved oxygen sensor and a microbial membrane reactor, which can perform the test within 35 minutes. The microbial reactor was made of functionalized spiral glass tubes, but the microbial membrane was affected by the environment of water quality. For this reason, PSO-ELM algorithm was used to eliminate the influence of turbidity (SS), pH and REDOX potential (ORP). Compared with BP neural network and ELM algorithm, the running time is shortened by 0.92 s and 0.24 s respectively, and the test error is reduced by 5.3% and 4.0% respectively. In the test of actual seawater samples, the relative error varies from 2.69% to 3.86%.
关键词
计量学 /
生化需氧量 /
快速检测 /
粒子群算法 /
极限学习机
Key words
metrology /
biochemical oxygen demand /
rapid measurement /
PSO /
ELM
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
［1］Jordan M A, Welsh D T, John R, et al. A sensitive ferricyanide-mediated biochemical oxygen demand assay for analysis of wastewater treatment plant influents and treated effluents［J］. Water Research, 2013, 47(2): 841-849.
［2］王燕, 张志锋, 姚伟, 等. 我国海洋环境保护标准化的现状、需求和建议［J］. 海洋开发与管理, 2018, 35(4): 36-39.
Wang Y, Zhang Z F, Yao W, et al. Current status requirement analysis and suggestion on marine environment protection standard［J］. Marine development management, 2018, 35(4): 36-39.
［3］Liu L, Bai L, Yu D B, et al. Biochemical oxygen demand measurement by mediator method in flow system［J］. Talanta, 2015, 138: 36-39.
［4］肖峻, 杨孟孟, 缪震华, 等. 嵌入式污水COD在线监测仪的研制与应用［J］. 环境工程学报, 2017,11(5):3312-3319.
Xiao J, Yang M M, Liao Z H, et al. Development and application of embedded COD on-line monitoring instrument for wastewater［J］. Chinese Journal of Environmental Engineering, 2017,11(5):3312-3319.
［5］郑璇, 李莉. 生化需氧量快速测定法的研究进展［J］. 福建分析测试, 2015,(1): 47-50.
Zheng X, Li L. Advances in rapid determination of biochemical oxygen demand［J］. Chemical Enterprise Management, 2015,(1): 47-50.
［6］胡敬芳, 李玥琪, 高国伟, 等. 基于电聚合技术的微生物膜制备方法［J］. 仪表技术与传感器, 2017,(9): 13-16.
Hu J F, Li Y Q, Gao G W. Method of microbial biofilm preparation based on electropolymerization technology［J］. Instrument Technique and Sensor, 2017,(9): 13-16.
［7］Commault A S, Lear G, Solene B, et al. Geobacter dominated biofilms used as amperometric BOD sensors［J］. Biochemical Engineering Journal, 2016, 109: 88-95.
［8］Liu C Y, Zhao H, Zhong L, et al. A biofilm reactor based approach for rapid on-line determination of biodegradable organic pollutants［J］. Biosensors & Bioelectronics, 2012, 34(1): 77-82.
［9］Khor B H, Iamail A K, Ahamad R, et al. A redox mediated UME biosensor using immobilized Chromobacterium violaceum strain R1 for rapid biochemical oxygen demand measurement［J］. Electrochimica Acta, 2015, 176: 777-783.
［10］Zaitseva A S, Arlyapov V A, Yudina N Y, et al. A novel Bod-mediator biosensor based on Ferrocene and Debaryomyces Hansenii yeast cells［J］. Applied Biochemistry & Microbiology, 2017, 53(3): 381-387.
［11］乔俊飞, 鞠岩, 韩红桂. 基于自组织随机权神经网络的BOD软测量［J］. 北京工业大学学报, 2016, 42(10): 1451-1460.
Qiao J F, Ju Y, Han H G. BOD soft-sensing based on SONNRW［J］. Journal of Beijing University of Technology, 2016, 42(10): 1451-1460.
［12］乔俊飞, 李瑞祥, 柴伟, 等. 基于PSO-ESN神经网络的污水BOD预测［J］. 控制工程, 2016, 23(4): 463-467.
Qiao J F, Li R X, Chai W, et al. Prediction of BOD based on PSO-ESN neural network［J］. Control Engineering of China, 2016, 23(4): 463-467.
［13］Heddam S, Lamda H, Filali S. Predicting effluent biochemical oxygen demand in a wastewater treatment plant using generalized regression neural network based approach: a comparative study［J］. Environmental Processes, 2016, 3(1): 153-165.
［14］牛培峰,丁翔,刘楠, 等.基于混合鸡群算法和核极端学习机的锅炉NOx排放的预测［J］. 计量学报, 2019, 40(5): 929-936.
Niu P F, Ding X, Liu N,et al.Prediction of Boiler NOx Emission Based on Mixed Chicken Swarm Algorithm and Kernel Extreme Learning Machine［J］. Acta Metrologica Sinica, 2019, 40(5): 929-936.
［15］刘彬,刘泽仁,赵志彪, 等. 基于速度交流的多种群多目标粒子群算法研究［J］. 计量学报, 2020, 41(8): 1002-1011.
Liu B, Liu Z R, Zhao Z B,et al. Research on Multi-population Multi-objective Particle Swarm Optimization Algorithm Based on Velocity Communication［J］. Acta Metrologica Sinica, 2020, 41(8): 1002-1011.
基金
国家自然科学基金(61201112,61475133);河北省自然科学基金(F2016203188,F2016203245);中国博士后基金项目(2018M630279);河北省博士后择优资助项目(B2018003028);河北省高等学校科学技术研究项目(ZD2018243)国家重点研发计划(2016YFC1400601-3);河北省重点研发计划(19273901D, 20373301D);河北省自然科学基金(F2020203066);中国博士后基金(2018M630279);河北省博士后择优资助项目(D2018003028);河北省高等学校科学技术研究项目(ZD2018243)
PDF(1213 KB)
