Biomass is a key factor in fermentation process, directly influencing the performance of the fermenta- tion system as well as the quality and yield of the targeted product. Therefore, the on-line estimation of biomass...Biomass is a key factor in fermentation process, directly influencing the performance of the fermenta- tion system as well as the quality and yield of the targeted product. Therefore, the on-line estimation of biomass is indispensable. The soft-sensor based on support vector machine (SVM) for an on-line biomass estimation was ana- lyzed in detail, and the improved SVM called the weighted least squares support vector machine was presented to follow the dynamic feature of fermentation process. The model based on the modified SVM was developed and demonstrated using simulation experiments.展开更多
This paper presents presents a new analytical solution of transverse vibration ofrectangular plaies simply supported at two opposite edges with arbitrary number ofelastic line supports in one way. The reaction forces ...This paper presents presents a new analytical solution of transverse vibration ofrectangular plaies simply supported at two opposite edges with arbitrary number ofelastic line supports in one way. The reaction forces of the elastic line supports areregarded as foe unknown external forces acted on the plate. The analytical solution ofthe differential equation of motion of the rectangular plate, which includes theunknown reaction forces. is gained. The frequency' equation is derived by using thelinear relationships between the reaction forces of the elastic line supports and thetransverse displacements of the plale along the elastic line supports. Therepresentations of foe frequency equation and the mode shape functions are differentfrom those obtained by other methods.展开更多
On-line chatter detection can avoid unstable cutting through monitoring the machining process.In order to identify chatter in a timely manner,an improved Support Vector Machine(SVM)is developed in this paper,based on ...On-line chatter detection can avoid unstable cutting through monitoring the machining process.In order to identify chatter in a timely manner,an improved Support Vector Machine(SVM)is developed in this paper,based on extracted features.In the SVM model,the penalty factor(e)and the core parameter(g)have important influence on the classification,more than from Kernel Functions(KFs).Hence,first the classification results are conducted using different KFs.Then two methods are presented for exploring the best parameters.The chatter identification results show that the Genetic Algorithm(GA)approach is more suitable for deciding the parameters than the Grid Explore(GE)approach.展开更多
The benchmark of a simply supported beam with damage and bending fuzzy stiffness consideration is established to be utilized for damage detection. The explicit expression describing the Rotational Angle Influence Line...The benchmark of a simply supported beam with damage and bending fuzzy stiffness consideration is established to be utilized for damage detection. The explicit expression describing the Rotational Angle Influence Lines(RAIL) of the arbitrary section in the benchmark is presented as the nonlinear relation between the moving load and the RAIL appeared, when the moving load is located on the damage area. The damage detection method is derived based on the Difference of the RAIL Curvature(DRAIL-C) prior to and following arbitrarily section damage in a simply supported beam with bending fuzzy stiffness consideration. The results demonstrate that the damage position can be located by the DRAIL-C graph and the damage extent can be calculated by the DRAIL-C curve peak. The simply supported box girder as a one-dimensional model and the simply supported truss bridge as a three-dimensional model with the bending fuzzy stiffness are simulated for the validity of the proposed method to be verified. The measuring point position and noise intensity effects are discussed in the simply supported box girder example. This paper provides a new consideration and technique for the damage detection of a simply supported bridge with bending fuzzy stiffness consideration.展开更多
A new kind of tunnel support was put forward on the basis of the anchor spraysupport principle. The mechanics of the new three-dimensional steel bar shotcrete liningsupport was studied and the structure's internal...A new kind of tunnel support was put forward on the basis of the anchor spraysupport principle. The mechanics of the new three-dimensional steel bar shotcrete liningsupport was studied and the structure's internal forces were analyzed. The model experiment was done relying on the industrial test. The conclusion of numerical calculationsproved that the ANSYS program is reasonable and creditable. It was compared to otherkinds of support that are commonly used in soft rock tunnels. The technique and economiccontrasts of the typical tunnel with support three-dimensional steel bar were completed.展开更多
In order to study the stress characteristics of the initial support and secondary lining of the large section tunnel and to solve the problem of secondary lining cracking during operation. Taking the large section tun...In order to study the stress characteristics of the initial support and secondary lining of the large section tunnel and to solve the problem of secondary lining cracking during operation. Taking the large section tunnel in Zihong village, Qi County as the research object, a numerical simulation method was used to establish a finite element model of the large section tunnel. So as to simulate and analyze the stress characteristics of the support structure of this tunnel. Through the simulation of the initial support and second lining of this large section tunnel in terms of displacement, stress, plastic zone damage and anchor shaft force, the results show that as the excavation progresses, the stress and displacement on the surface of the newly excavated tunnel profile is faster, especially at the side walls and arch footings, the stress and displacement values are slightly larger than other characteristic points, but the final values are stable and converge, and are basically consistent with the field monitoring results, which indicates that this support system is basically in stable state. Therefore, during the tunnel excavation and support process, special attention should be paid to the stability of the sidewalls and footings, and the results of this study will be of great practical significance for tunnel construction and maintenance.展开更多
The solutions of Linear Programming Problems by the segmentation of the cuboidal response surface through the Super Convergent Line Series methodologies were obtained. The cuboidal response surface was segmented up to...The solutions of Linear Programming Problems by the segmentation of the cuboidal response surface through the Super Convergent Line Series methodologies were obtained. The cuboidal response surface was segmented up to four segments, and explored. It was verified that the number of segments, S, for which optimal solutions are obtained is two (S = 2). Illustrative examples and a real-life problem were also given and solved.展开更多
针对室内可见光定位中非视距信道(Non Line of Sight,NLOS)导致定位精度不足的问题,提出了一种基于动态高斯加权(Dynamic Gaussian Weighted,DGW)接收信号强度指示(Received Signal Strength Indicator,RSSI)和遗传算法(Genetic Algorit...针对室内可见光定位中非视距信道(Non Line of Sight,NLOS)导致定位精度不足的问题,提出了一种基于动态高斯加权(Dynamic Gaussian Weighted,DGW)接收信号强度指示(Received Signal Strength Indicator,RSSI)和遗传算法(Genetic Algorithm,GA)改进支持向量回归(Support Vector Regression,SVR)的室内可见光定位算法。首先,构建指纹库并划分数据集,计算接收器与光源之间的距离动态调整高斯函数的标准差,再结合RSSI信号的波动性进行自适应加权,以减少NLOS对定位的影响。然后,使用GA优化SVR模型的参数,得到最佳定位模型。最后,使用最佳定位模型对加权后的指纹数据进行定位预测。实验结果表明:本算法的平均定位误差为7.1 cm,相较于SVR、SVR-GA等算法降低了21.1%~42.3%,并且能有效降低NLOS的影响、提高室内定位的精度,具有较强的应用前景。展开更多
基金National Natural Science Foundation of China (No.20476007).
文摘Biomass is a key factor in fermentation process, directly influencing the performance of the fermenta- tion system as well as the quality and yield of the targeted product. Therefore, the on-line estimation of biomass is indispensable. The soft-sensor based on support vector machine (SVM) for an on-line biomass estimation was ana- lyzed in detail, and the improved SVM called the weighted least squares support vector machine was presented to follow the dynamic feature of fermentation process. The model based on the modified SVM was developed and demonstrated using simulation experiments.
文摘This paper presents presents a new analytical solution of transverse vibration ofrectangular plaies simply supported at two opposite edges with arbitrary number ofelastic line supports in one way. The reaction forces of the elastic line supports areregarded as foe unknown external forces acted on the plate. The analytical solution ofthe differential equation of motion of the rectangular plate, which includes theunknown reaction forces. is gained. The frequency' equation is derived by using thelinear relationships between the reaction forces of the elastic line supports and thetransverse displacements of the plale along the elastic line supports. Therepresentations of foe frequency equation and the mode shape functions are differentfrom those obtained by other methods.
文摘On-line chatter detection can avoid unstable cutting through monitoring the machining process.In order to identify chatter in a timely manner,an improved Support Vector Machine(SVM)is developed in this paper,based on extracted features.In the SVM model,the penalty factor(e)and the core parameter(g)have important influence on the classification,more than from Kernel Functions(KFs).Hence,first the classification results are conducted using different KFs.Then two methods are presented for exploring the best parameters.The chatter identification results show that the Genetic Algorithm(GA)approach is more suitable for deciding the parameters than the Grid Explore(GE)approach.
基金the National Natural Science Foundation of China(Nos.51608245 and 51568041)the Natural Science Foundation of Gansu Province(No.148RJZA026)
文摘The benchmark of a simply supported beam with damage and bending fuzzy stiffness consideration is established to be utilized for damage detection. The explicit expression describing the Rotational Angle Influence Lines(RAIL) of the arbitrary section in the benchmark is presented as the nonlinear relation between the moving load and the RAIL appeared, when the moving load is located on the damage area. The damage detection method is derived based on the Difference of the RAIL Curvature(DRAIL-C) prior to and following arbitrarily section damage in a simply supported beam with bending fuzzy stiffness consideration. The results demonstrate that the damage position can be located by the DRAIL-C graph and the damage extent can be calculated by the DRAIL-C curve peak. The simply supported box girder as a one-dimensional model and the simply supported truss bridge as a three-dimensional model with the bending fuzzy stiffness are simulated for the validity of the proposed method to be verified. The measuring point position and noise intensity effects are discussed in the simply supported box girder example. This paper provides a new consideration and technique for the damage detection of a simply supported bridge with bending fuzzy stiffness consideration.
文摘A new kind of tunnel support was put forward on the basis of the anchor spraysupport principle. The mechanics of the new three-dimensional steel bar shotcrete liningsupport was studied and the structure's internal forces were analyzed. The model experiment was done relying on the industrial test. The conclusion of numerical calculationsproved that the ANSYS program is reasonable and creditable. It was compared to otherkinds of support that are commonly used in soft rock tunnels. The technique and economiccontrasts of the typical tunnel with support three-dimensional steel bar were completed.
文摘In order to study the stress characteristics of the initial support and secondary lining of the large section tunnel and to solve the problem of secondary lining cracking during operation. Taking the large section tunnel in Zihong village, Qi County as the research object, a numerical simulation method was used to establish a finite element model of the large section tunnel. So as to simulate and analyze the stress characteristics of the support structure of this tunnel. Through the simulation of the initial support and second lining of this large section tunnel in terms of displacement, stress, plastic zone damage and anchor shaft force, the results show that as the excavation progresses, the stress and displacement on the surface of the newly excavated tunnel profile is faster, especially at the side walls and arch footings, the stress and displacement values are slightly larger than other characteristic points, but the final values are stable and converge, and are basically consistent with the field monitoring results, which indicates that this support system is basically in stable state. Therefore, during the tunnel excavation and support process, special attention should be paid to the stability of the sidewalls and footings, and the results of this study will be of great practical significance for tunnel construction and maintenance.
文摘The solutions of Linear Programming Problems by the segmentation of the cuboidal response surface through the Super Convergent Line Series methodologies were obtained. The cuboidal response surface was segmented up to four segments, and explored. It was verified that the number of segments, S, for which optimal solutions are obtained is two (S = 2). Illustrative examples and a real-life problem were also given and solved.
文摘针对室内可见光定位中非视距信道(Non Line of Sight,NLOS)导致定位精度不足的问题,提出了一种基于动态高斯加权(Dynamic Gaussian Weighted,DGW)接收信号强度指示(Received Signal Strength Indicator,RSSI)和遗传算法(Genetic Algorithm,GA)改进支持向量回归(Support Vector Regression,SVR)的室内可见光定位算法。首先,构建指纹库并划分数据集,计算接收器与光源之间的距离动态调整高斯函数的标准差,再结合RSSI信号的波动性进行自适应加权,以减少NLOS对定位的影响。然后,使用GA优化SVR模型的参数,得到最佳定位模型。最后,使用最佳定位模型对加权后的指纹数据进行定位预测。实验结果表明:本算法的平均定位误差为7.1 cm,相较于SVR、SVR-GA等算法降低了21.1%~42.3%,并且能有效降低NLOS的影响、提高室内定位的精度,具有较强的应用前景。
