热压混合材料板力学特性PSO-SVR模型预测
|
摘要
精确、快速预测热压过程混合材料板力学特性,可降低生产成本,提高资源利用率。文章以热压过程为研究对象,提出基于粒子群算法(Particle Swarm Optimization,PSO)优化支持向量机回归(Support Vector Regression,SVR)模型。通过正交试验设计,结合混合材料板性能测试数据,以热压压力、热压温度、含水率、热压时间为自变量,预测混合材料板静曲强度、弹性模量、内结合强度。对比分析PSO-SVR与SVR预测结果,结果表明,PSO-SVR预测模型可明确热压参数与混合材料板力学特性间非线性关系,根据自变量预测混合材料板力学特性。与SVR相比,PSO-SVR算法模型具有鲁棒性强、精确度高、泛化能力强等优点。研究结果可为混合材料板力学特性预测及热压控制参数选择提供参考。
In this paper, in order to predict the mechanical properties of the mixed material board accurately and quickly, reduce production costs and improve resource utilization, taking the process of hot-pressing control as the research object, a support vector machine regression(SVR) model based on particle swarm optimization(PSO) optimization was proposed. Based on the performance test data of finished board and orthogonal experimental design, built the predictive model which took the hot-pressing pressure, hot-pressing temperature, hot-pressing time and moisture content of slab as the argument variables, and the modulus of rupture(MOR), modulus of elasticity(MOE) and internal bonding strength(IB) as the dependent variables. Comparison and analysis of PSO-SVR and SVR prediction results showed that PSO-SVR model could well describe the nonlinear relationship between the hot-pressing control parameters and the mechanical properties of the mixed material board and achieved rapid and accurate prediction according to the independent variables. Compared with SVR, PSO-SVR algorithm model had the advantages of strong robustness, high precision and fast learning speed, which could provide reference for the prediction of mechanical properties of mixed material under different process parameters in hot-pressing process.
In this paper, in order to predict the mechanical properties of the mixed material board accurately and quickly, reduce production costs and improve resource utilization, taking the process of hot-pressing control as the research object, a support vector machine regression(SVR) model based on particle swarm optimization(PSO) optimization was proposed. Based on the performance test data of finished board and orthogonal experimental design, built the predictive model which took the hot-pressing pressure, hot-pressing temperature, hot-pressing time and moisture content of slab as the argument variables, and the modulus of rupture(MOR), modulus of elasticity(MOE) and internal bonding strength(IB) as the dependent variables. Comparison and analysis of PSO-SVR and SVR prediction results showed that PSO-SVR model could well describe the nonlinear relationship between the hot-pressing control parameters and the mechanical properties of the mixed material board and achieved rapid and accurate prediction according to the independent variables. Compared with SVR, PSO-SVR algorithm model had the advantages of strong robustness, high precision and fast learning speed, which could provide reference for the prediction of mechanical properties of mixed material under different process parameters in hot-pressing process.
引文
[1]傅万四,王晓军,南生春,等.发展人造板产业,产促进林业建设[J].木材工业2004,18(1):12-15.
[2]孙红敏,吴静婷,李晓明.基于改进BP神经网络的价格预测模型研究[J].东北农业大学学报,2013,44(8):133-137.
[3]Steve K,Bruce M A.Press monitoring system for panel industry[C].26th International Particleboard/Composite Materials Symposium,1992.
[4]陈天全.大片刨花板热压过程温度、气压和含水率变化规律研究[D].北京:北京林业大学,2006.
[5]王东林,俞国胜,杨桦.基于Win CC的中密度纤维板热压工段监控软件的设计[J].林产工业,2009,36(6):37-39.
[6]王宁,孙丽萍.中密度纤维板热机压力模糊控制研究[J].机电产品开发与创新,2010,23(1):129-131.
[7]Harless T,Wagner E,Short P,et al.Heat and moisture movement in wood composite material during the pressing operation[J].Wood and Fiber Science,1987,19:81-92.
[8]Humphrey P,Bolton A.The hot pressing of dry formed based composite.Part li.A simulation model for heat and moisture transfer and typical results[J].Holzforschung,1989,43(3):199-206.
[9]Zombori B,Kamke F,Watson L.Simulation of the internal conditions during the Hot-pressing process[J].Wood and Fiber Science,2003,35(1):20-23.
[10]谢力生,李翠翠.纤维板热压中心层温度与力学性能的关系[J].中南林业科技大学学报,2009,29(5):82-86.
[11]刘亚秋,王春晓,武曲,等.基于Burgers模型的MDF连续平压质量控制计算方法研究[J].安徽农业科学,2014,42(16):5088-5091.
[12]田燕青.中密度纤维板热压控制参数优化系统的研究[D].哈尔滨:东北林业大学,2011.
[13]盖玲,宋孝周.基于BP神经网络的棉秆重组方材性能预测研究[J].木材加工机械,2014,43(4):115-119.
[14]孙建飞,肖生苓,王昊宇,等.工艺类参数对稻壳—木刨花复合包装板力学性能的影响[J].东北林业大学学报,2015,43(2):91-97.
[15]符彬,郑霞,潘亚鸽,等.无胶蔗渣纤维板制备及性能[J].林产工业,2015,42(6):14-17.
[16]Tiryaki S,Aras U,Kalayc?oglu H,et al.Predictive models for modulus of rupture and modulus of elasticity of particleboard manufactured in different pressing conditions[J].High Temperature Materials&Processes,2016,36:1-12.
[17]潘亚鸽,朱凌波,唐钱,等.麦秸/木材均质复合无机碎料板的制备及其性能[J].材料导报,2017,31(4):25-29.
[18]彭顺,桂成胜,林新青,等.大豆胶制备竹刨花板的工艺参数探究[J].林产工业,2017,44(9):19-23.
[19]孙建平,王逢瑚,胡英成,等.基于遗传神经网络的农作物秸秆板材优化设计[J].农业工程学报,2010,26(1):319-323.
[20]孙建平,王逢瑚,李鹏,等.遗传神经网络在木塑复合材料力学性能预测中的应用[J].高分子材料科学与工程,2012,28(1):117-120.
[21]于海英.MDF热压过程多传感器数据融合模型建立与仿真研究[D].哈尔滨:东北林业大学,2013.
[22]Li Q F,Liu Y Q,Zhu L K.Model building and optimization analysis of MDF continuous Hot-pressing by neural network[J].Mathematical Problems in Engineering,2016:1-16.
[23]Vapnik V N.The nature of statistical learning theory[J].IEEE Transactions on Neural Networks,1997,8(6):153-168.
[24]赵开才,石凤梅,孟庆林,等.基于SVM的水稻稻瘟病识别方法[J].东北农业大学学报,2013,44(11):118-126.
[25]Smola A J,Sch?lkopf B.A tutorial on support vector regression[J].Statistics and Computing,2004,14(3):199-222.
[26]Zhang Y T,Liu C Y,Wei S S.ECG quality assessment based on a kernel support vector machine[J].Computers&Electronics,2014,15(7):564-573.
[27]王德福,王沫,李利桥.锤片式粉碎机粉碎玉米秸秆机理分析与参数优化[J].农业机械学报,2017,48(11):165-171.
[28]李珂,邰能灵,张沈习.基于改进粒子群算法的配电网综合运行优化[J].上海交通大学学报,2017,51(8):43-45.
[29]刘环宇,陈海涛,闵诗尧,等.基于PSO-SVR的植物纤维地膜抗张强度预测研究[J].农业机械学报,2017:48(4):30-35.
[30]谷文成,柴宝仁,滕艳平.基于粒子群优化算法的支持向量机研究[J].北京理工大学学报,2014,34(7):68-73.
[31]李静,王京,杨磊,等.热处理炉钢板温度的自适应混沌粒子群算法-最小二乘支持向量机优化预报算[J].控制理论与应用,2011:28(12):12-20.
[2]孙红敏,吴静婷,李晓明.基于改进BP神经网络的价格预测模型研究[J].东北农业大学学报,2013,44(8):133-137.
[3]Steve K,Bruce M A.Press monitoring system for panel industry[C].26th International Particleboard/Composite Materials Symposium,1992.
[4]陈天全.大片刨花板热压过程温度、气压和含水率变化规律研究[D].北京:北京林业大学,2006.
[5]王东林,俞国胜,杨桦.基于Win CC的中密度纤维板热压工段监控软件的设计[J].林产工业,2009,36(6):37-39.
[6]王宁,孙丽萍.中密度纤维板热机压力模糊控制研究[J].机电产品开发与创新,2010,23(1):129-131.
[7]Harless T,Wagner E,Short P,et al.Heat and moisture movement in wood composite material during the pressing operation[J].Wood and Fiber Science,1987,19:81-92.
[8]Humphrey P,Bolton A.The hot pressing of dry formed based composite.Part li.A simulation model for heat and moisture transfer and typical results[J].Holzforschung,1989,43(3):199-206.
[9]Zombori B,Kamke F,Watson L.Simulation of the internal conditions during the Hot-pressing process[J].Wood and Fiber Science,2003,35(1):20-23.
[10]谢力生,李翠翠.纤维板热压中心层温度与力学性能的关系[J].中南林业科技大学学报,2009,29(5):82-86.
[11]刘亚秋,王春晓,武曲,等.基于Burgers模型的MDF连续平压质量控制计算方法研究[J].安徽农业科学,2014,42(16):5088-5091.
[12]田燕青.中密度纤维板热压控制参数优化系统的研究[D].哈尔滨:东北林业大学,2011.
[13]盖玲,宋孝周.基于BP神经网络的棉秆重组方材性能预测研究[J].木材加工机械,2014,43(4):115-119.
[14]孙建飞,肖生苓,王昊宇,等.工艺类参数对稻壳—木刨花复合包装板力学性能的影响[J].东北林业大学学报,2015,43(2):91-97.
[15]符彬,郑霞,潘亚鸽,等.无胶蔗渣纤维板制备及性能[J].林产工业,2015,42(6):14-17.
[16]Tiryaki S,Aras U,Kalayc?oglu H,et al.Predictive models for modulus of rupture and modulus of elasticity of particleboard manufactured in different pressing conditions[J].High Temperature Materials&Processes,2016,36:1-12.
[17]潘亚鸽,朱凌波,唐钱,等.麦秸/木材均质复合无机碎料板的制备及其性能[J].材料导报,2017,31(4):25-29.
[18]彭顺,桂成胜,林新青,等.大豆胶制备竹刨花板的工艺参数探究[J].林产工业,2017,44(9):19-23.
[19]孙建平,王逢瑚,胡英成,等.基于遗传神经网络的农作物秸秆板材优化设计[J].农业工程学报,2010,26(1):319-323.
[20]孙建平,王逢瑚,李鹏,等.遗传神经网络在木塑复合材料力学性能预测中的应用[J].高分子材料科学与工程,2012,28(1):117-120.
[21]于海英.MDF热压过程多传感器数据融合模型建立与仿真研究[D].哈尔滨:东北林业大学,2013.
[22]Li Q F,Liu Y Q,Zhu L K.Model building and optimization analysis of MDF continuous Hot-pressing by neural network[J].Mathematical Problems in Engineering,2016:1-16.
[23]Vapnik V N.The nature of statistical learning theory[J].IEEE Transactions on Neural Networks,1997,8(6):153-168.
[24]赵开才,石凤梅,孟庆林,等.基于SVM的水稻稻瘟病识别方法[J].东北农业大学学报,2013,44(11):118-126.
[25]Smola A J,Sch?lkopf B.A tutorial on support vector regression[J].Statistics and Computing,2004,14(3):199-222.
[26]Zhang Y T,Liu C Y,Wei S S.ECG quality assessment based on a kernel support vector machine[J].Computers&Electronics,2014,15(7):564-573.
[27]王德福,王沫,李利桥.锤片式粉碎机粉碎玉米秸秆机理分析与参数优化[J].农业机械学报,2017,48(11):165-171.
[28]李珂,邰能灵,张沈习.基于改进粒子群算法的配电网综合运行优化[J].上海交通大学学报,2017,51(8):43-45.
[29]刘环宇,陈海涛,闵诗尧,等.基于PSO-SVR的植物纤维地膜抗张强度预测研究[J].农业机械学报,2017:48(4):30-35.
[30]谷文成,柴宝仁,滕艳平.基于粒子群优化算法的支持向量机研究[J].北京理工大学学报,2014,34(7):68-73.
[31]李静,王京,杨磊,等.热处理炉钢板温度的自适应混沌粒子群算法-最小二乘支持向量机优化预报算[J].控制理论与应用,2011:28(12):12-20.