PREDICTION OF POLYHYDROXYALKANOATE (PHA) PRODUCTION UTILIZING FOOD WASTE BASED ON GA-BP NEURAL NETWORK METHOD
-
摘要: 为了预估混合底物碳源条件下活性污泥PHA合成产量预测的准确度,通过引入遗传算法对BP人工神经网络的权值和阈值进行优选,建立基于GA-BP神经网络的餐厨垃圾合成PHA工艺产量预测模型。以餐厨垃圾发酵液为底物碳源,利用活性污泥在ADD模式下进行PHA合成。以实验数据为基础训练神经网络模型,通过实测数据与模型预测数据之间的对比,验证了人工神经网络预测模型的精确度,并对长期PHA合成能力进行了预测。结论表明:基于遗传算法改进的GA-BP网络模型表现出比传统BP神经网络模型更佳的预测准确度,为评估混合菌群PHA最大合成产量的长期发展趋势,确定合理富集时长探索了可行方法。Abstract: To evaluate the activated sludge PHA synthesis yield prediction under the condition of mixed carbon sources, genetic algorithms were proposed to optimize the weights and thresholds of the BP artificial neural network, and the research established the prediction model based on the GA-BP network. Food waste fermentation liquid was applied as the substrate and activated sludge was used to synthesize PHA under the ADD mode. Based on experimental data, the comparison between the measured data and the model predictions was carried out, to verify the accuracy of the network prediction model and the prediction of the long-term PHA synthesis ability. Results showed that the GA-BP network model improved based on the genetic algorithm had high prediction accuracy than the traditional BP neural network model, and the model explored a feasible method to evaluate the long-term variation of the maximum PHA production yield in mixed microbial cultures and determined the reasonable enrichment time.
-
Key words:
- food waste fermentation liquid /
- ADD process /
- PHA yield /
- GA-BP neural network
-
[1] 徐彦芹,杨锡智,罗若诗,等.合成生物学在生物基塑料制造中的应用[J].化工学报, 2020, 71(10):4520-4531. [2] 季业,温沁雪,郝亚茹,等.盐度对模拟餐厨垃圾发酵液产聚羟基脂肪酸酯工艺的影响[J].环境工程学报, 2020, 14(1):236-243. [3] 郝亚茹.氯化钠对混合菌群利用餐厨垃圾产酸液合成PHA的影响研究[D].哈尔滨:哈尔滨工业大学, 2017. [4] 王攀,邱银权,陈锡腾,等.利用餐厨垃圾水解酸化液合成PHA——耐盐菌的筛选及其产PHA特性[J].环境工程, 2018, 36(4):78-82,116. [5] WANG K, ZHANG R H. Production of polyhydroxyalkanoates (PHA) by haloferax mediterranei from food waste derived nutrients for biodegradable plastic applications[J]. Journal of Microbiology and Biotechnology, 2021,31(2):338-347. [6] 李鑫鑫,郑丹,杨建喜,等.基于GA-BP神经网络的施工区域水质预测及预警模型研究[J].重庆交通大学学报(自然科学版), 2020, 39(12):106-110. [7] 胡程鹏,薛涛.基于遗传算法的Kubernetes资源调度算法[J].计算机系统应用, 2021, 30(9):152-160. [8] 王佳君,陆洪宇,陈志强,等.接种量对餐厨垃圾中温厌氧产甲烷潜能的影响[J].环境科学学报, 2016,已录用. [9] 国家环境保护总局.水和废水监测分析方法[M]. 4版.北京:中国环境科学出版社, 2002. [10] WEN Q X, CHEN Z Q, WANG C Y, et al. Bulking sludge for PHA production:energy saving and comparative storage capacity with well-settled sludge[J]. Journal of Environmental Sciences, 2012, 24(10):1744-1752. [11] SUN W, HUANG C C. A carbon price prediction model based on secondary decomposition algorithm and optimized back propagation neural network[J]. Journal of Cleaner Production, 2020, 243:118671. [12] CHEN Z Q, GUO Z R, WEN Q X, et al. A new method for polyhydroxyalkanoate (PHA) accumulating bacteria selection under physical selective pressure[J]. International Journal of Biological Macromolecules, 2015, 72:1329-1334. [13] 郭子瑞.基于动态间歇排水瞬时补料的活性污泥合成PHA新工艺研究[J].哈尔滨工业大学, 2016. [14] GUO Z R, CHEN Z Q, WEN Q X, et al. Strategy to reduce the acclimation period for enrichment of PHA accumulating cultures[J]. Desalination and Water Treatment, 2016,57:29286-29294. [15] SERAFIM LEMOS, OLIVEIRA REIS. Optimization of polyhydroxybutyrate production by mixed cultures submitted to aerobic dynamic feeding conditions[J]. Biotechnology and Bioengineering, 2004, 87(2):145-160. [16] 蔡萌萌.剩余活性污泥中的微生物利用实际废液合成聚羟基烷酸酯[D].哈尔滨:哈尔滨工业大学, 2009.
点击查看大图
计量
- 文章访问数: 177
- HTML全文浏览量: 15
- PDF下载量: 2
- 被引次数: 0