为准确预测大中型沼气工程的日产气量,提出一种利用基于PSO-BP模型的软测量方法。首先,依托软测量技术选取参数;其次,以进料量、发酵温度、液位、罐内液压等参数作为输入量,沼气日产量为输出量进行模型建立。在此基础上,使用线性降低权重系数法和引入变异算子对粒子群算法进行改进,并对BP神经网络进行初始化来提高模型性能。通过实验比较改进PSO-BP模型、传统BP神经网络以及遗传算法优化的BP神经网络在预测沼气日产量方面的性能,采用改进的PSO-BP模型进行预测时,均方根误差（RMSE）、决定系数（R2）和平均绝对误差（MAE）分别为1.38440、0.84011和1.00910,证明改进PSO-BP模型结合软测量技术对进行复杂非线性牛粪高温厌氧发酵过程预测的可行性,同时可保证预测结果的精准性。
Abstract
The high-temperature anaerobic fermentation system of cow dung involves complex dynamics, with serious nonlinearity and time-varying, which makes it difficult to construct an accurate prediction model of biogas production. In order to accurately predict the daily gas production of large and medium-sized biogas projects, a new method of using improved particle swarm optimization algorithm to optimize traditional BP neural network was proposed, and an improved PSO-BP model was established. Firstly, the parameters are selected by soft measurement technology. Secondly, the model was established by taking the parameters such as feed rate, fermentation temperature, liquid level and hydraulic pressure in the tank as input and the daily biogas production as output. On this basis, the particle swarm optimization algorithm is improved by using the linear reduction weight coefficient method and introducing the mutation operator, and the BP neural network is initialized to improve the performance of the model. The performance of the improved PSO-BP model, the traditional BP neural network and the BP neural network optimized by genetic algorithm in predicting the daily biogas production was compared through experiments. When the improved PSO-BP model was used for prediction, the root mean square error （RMSE）, the coefficient of determination （R2） and the mean absolute error （MAE） were 1.38440,0.84011 and 1.00910, respectively. It is proved that the improved PSO-BP model combined with soft measurement technology is feasible to predict the complex nonlinear high temperature anaerobic fermentation process of cow dung, and the accuracy of the prediction results is ensured.
关键词
生物质能 /
沼气 /
粒子群优化算法 /
BP神经网络 /
软测量技术
Key words
biomass energy /
biogas /
particle swarm optimization algorithm /
BP neural network /
soft-sensing technique
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] SEO K W, SEO J, KIM K, et al.Prediction of biogas production rate from dry anaerobic digestion of food waste: process-based approach vs. recurrent neural network black-box model[J]. Bioresource technology, 2021, 341: 125829.
[2] 费凡, 高立艾, 张瑞强, 等. 基于供需协调特性的养殖场沼气热电联供系统优化研究[J]. 太阳能学报, 2023, 44(4): 231-237.
FEI F, GAO L A, ZHANG R Q, et al.Research on optimization of biogas cogeneration system for farms based on characteristics of supply and demand coordination[J]. Acta energiae solaris sinica, 2023, 44(4): 231-237.
[3] PALMA-HEREDIA D, VERDAGUER M, MOLINOS-SENANTE M, et al.Optimised blending for anaerobic co-digestion using ant colony approach: Besòs River Basin case study[J]. Renewable energy, 2021, 168: 141-150.
[4] ABDEL DAIEM M M, HATATA A, GALAL O H, et al. Prediction of biogas production from anaerobic co-digestion of waste activated sludge and wheat straw using two-dimensional mathematical models and an artificial neural network[J]. Renewable energy, 2021, 178: 226-240.
[5] MOGODINIYAI KASMAEI K, RUSTAS B O, SPÖRNDLY R, et al. Prediction models of silage fermentation products on crop composition under strict anaerobic conditions: a meta-analysis[J]. Journal of dairy science, 2013, 96(10): 6644-6649.
[6] 蒋滔, 王冰, 韦秀丽, 等. 川渝养殖场沼气工程运行状况与沼液生物学特性研究[J]. 太阳能学报, 2021, 42(2): 239-246.
JIANG T, WANG B, WEI X L, et al.Study on operation status of biogas plants and biological characteristics of biogas slurry in livestock farms of Chongqing and Sichuan Province[J]. Acta energiae solaris sinica, 2021, 42(2): 239-246.
[7] 崔琳琳, 沈冰冰, 葛志强. 基于混合变分自编码器回归模型的软测量建模方法[J]. 自动化学报, 2022, 48(2): 398-407.
CUI L L, SHEN B B, GE Z Q.A mixture variational autoencoder regression model for soft sensor application[J]. Acta automatica sinica, 2022, 48(2): 398-407.
[8] 赵孝文, 蒋继成. 厌氧发酵工艺的BP神经网络建模与粒子群算法优化[J]. 应用能源技术, 2015(3): 8-12.
ZHAO X W, JIANG J C.BP neural network modeling and particle swarm algorithm optimization of anaerobic fermentation process[J]. Applied energy technology, 2015(3): 8-12.
[9] 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, 2018, 25: 456-466.
[10] 鲍敏, 杨世品, 李丽娟. 基于新型BP神经网络的沼气生产预测[J]. 计算机与应用化学, 2019, 36(4): 308-311.
BAO M, YANG S P, LI L J.Biogas production prediction method based on novel BP neural network modeling[J]. Computers and applied chemistry, 2019, 36(4): 308-311.
[11] 祁翔, 张心光. 基于遗传算法优化BP神经网络的预测建模[J]. 智能计算机与应用, 2021, 11(5): 160-162, 169.
QI X, ZHANG X G.Prediction modeling of BP neural network optimized by genetic algorithm[J]. Intelligent computer and applications, 2021, 11(5): 160-162, 169.
[12] 何丹, 林来鹏, 李小勇, 等. 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.
HE D, LIN L P, LI X Y, et al.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.
[13] 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-making wastewater treatment[J]. Journal of cleaner production, 2020, 265: 121787.
[14] 胡兵, 王小娟, 徐立军, 等. 基于KMO-PCA-BP的燃料电池堆输出电压预测方法[J]. 太阳能学报, 2022, 43(3): 12-19.
HU B, WANG X J, XU L J, et al.Output voltage prediction method of fuel cell stack based on KMO-PCA-BP[J]. Acta energiae solaris sinica, 2022, 43(3): 12-19.
[15] 曾庆扬, 丁楚衡, 谷战英, 等. 基于BP神经网络的油茶产量预测模型构建[J]. 经济林研究, 2022, 40(3): 87-95.
ZENG Q Y, DING C H, GU Z Y, et al.Building camellia oleifera yield prediction model based on BP neural network[J]. Non-wood forest research, 2022, 40(3): 87-95.
[16] KUMAR S, SINGH A K, PATHAK V K, et al.Modelling and optimization of injection molding process for PBT/PET parts using modified particle swarm algorithm[J]. Indian journal of engineering and materials sciences, 2020, 27(3): 603-615.
[17] 陈际, 袁守利, 刘志恩. 基于BAS改进PSO算法对PEMFC温度的控制[J]. 太阳能学报, 2023, 44(5): 67-73.
CHEN J, YUAN S L, LIU Z E.Temperature control of PEMFC based on BAS improved PSO algorithm[J]. Acta energiae solaris sinica, 2023, 44(5): 67-73.
[18] 秦国辉, 刘伟, 刘旭丹. 基于最小二乘向量机的厌氧发酵沼气产量建模研究[J]. 黑龙江科学, 2013, 4(2): 40-42.
QIN G H, LIU W, LIU X D.Modeling anaerobic fermentation biogas output based on least squares support vector machines[J]. Heilongjiang science, 2013, 4(2): 40-42.
[19] HEYDARI B, ABDOLLAHZADEH SHARGHI E, RAFIEE S, et al.Use of artificial neural network and adaptive neuro-fuzzy inference system for prediction of biogas production from spearmint essential oil wastewater treatment in up-flow anaerobic sludge blanket reactor[J]. Fuel, 2021, 306: 121734.
[20] 朱昶胜, 李岁寒. 基于改进果蝇优化算法的随机森林回归模型及其在风速预测中的应用[J]. 兰州理工大学学报, 2021, 47(4): 83-90.
ZHU C S, LI S H.Random forest regression model based on improved fruit fly optimization algorithm and its application in wind speed forecasting[J]. Journal of Lanzhou University of Technology, 2021, 47(4): 83-90.
[21] ALMOMANI F.Prediction of biogas production from chemically treated co-digested agricultural waste using artificial neural network[J]. Fuel, 2020, 280: 118573.
[22] 苏攀, 张伟. 混沌映射的禁忌同步随机学习因子粒子群算法[J]. 小型微型计算机系统, 2022, 43(8): 1675-1680.
SU P, ZHANG W.Tabu synchronization stochastic learning factor particle swarm optimization based on chaotic mapping[J]. Journal of Chinese computer systems, 2022, 43(8): 1675-1680.
PDF(1201 KB)
