scholarly journals Establishing a dynamic elastic modulus prediction model of larch based on nondestructive testing data

BioResources ◽  
2020 ◽  
Vol 15 (3) ◽  
pp. 4835-4850
Author(s):  
Liting Cheng ◽  
Wei Wang ◽  
Zhiguo Yang ◽  
Jian Dai
Keyword(s):  
Elastic Modulus ◽  
Nondestructive Testing ◽  
Prediction Model ◽  
Information Diffusion ◽  
Dynamic Elastic Modulus ◽  
Coefficient Of Determination ◽  
Diffusion Method ◽  
Strong Basis ◽  
Evaluation Indexes ◽  
Testing Data

To accurately evaluate the dynamic elastic modulus (Ed) of wood in ancient timberwork buildings, the new materials of larch were used as the research object, and the stress wave nondestructive testing method was used to determine it. Based on nondestructive testing data, this paper proposed a method for predicting the Ed of larch using the principle of information diffusion. It selected the distance (D) from the bark to the pith in the cross-section of the wood and the height (H) from the base to the top in the radial section of the wood. The fuzzy diffusion relationships between the two evaluation indexes and the Ed were established using the information diffusion principle and the first- and second-order fuzzy approximate inferences in the fuzzy information optimization process. The calculation results showed that the dynamic elastic modulus model constructed by the information diffusion method can better predict the Ed of larch. The coefficient of determination between the measured value and the predicted value of the Ed was 0.861, they were in good agreement. The weights of the two influencing factors were 0.7 and 0.3, respectively, the average relative error of the fitted sample data was the minimum, which was 8.55%. This prediction model provided a strong basis for field inspection.

scholarly journals Predicting Ink Transfer Rate of 3D Additive Printing Using EGBO Optimized Least Squares Support Vector Machine Model

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Shengpu Li ◽  
Yize Sun
Keyword(s):  
Support Vector Machine ◽  
Prediction Model ◽  
Least Squares ◽  
Transfer Rate ◽  
Coefficient Of Determination ◽  
Percentage Error ◽  
Support Vector ◽  
Experimental Sample ◽  
Machine Model ◽  
Ink Transfer

Ink transfer rate (ITR) is a reference index to measure the quality of 3D additive printing. In this study, an ink transfer rate prediction model is proposed by applying the least squares support vector machine (LSSVM). In addition, enhanced garden balsam optimization (EGBO) is used for selection and optimization of hyperparameters that are embedded in the LSSVM model. 102 sets of experimental sample data have been collected from the production line to train and test the hybrid prediction model. Experimental results show that the coefficient of determination (R2) for the introduced model is equal to 0.8476, the root-mean-square error (RMSE) is 6.6 × 10 (−3), and the mean absolute percentage error (MAPE) is 1.6502 × 10 (−3) for the ink transfer rate of 3D additive printing.

Studies the Properties of Polyaspartic Polyurea Coated Concrete under Coaction of Salt Fog and Freeze-Thaw

2012 ◽  
Vol 455-456 ◽  
pp. 781-785
Author(s):  
Ping Lu ◽  
Xin Mao Li ◽  
Xue Qiang Ma ◽  
Wei Bo Huang
Keyword(s):  
Elastic Modulus ◽  
Frost Resistance ◽  
Dynamic Elastic Modulus ◽  
Freeze Thaw ◽  
Decrease Rate ◽  
Thaw Cycle ◽  
Freeze Thaw Cycle ◽  
Salt Fog

. This paper mainly studied the properties of PAE polyurea coated concrete under coactions of salt fog and freeze-thaw. After exposed salt fog conditions for 200d, T3, B2, F2 and TM four coated concrete relative dynamic elastic modulus have small changes, but different coated concrete variation amplitude is different. T3 coated concrete after 100 times of freeze-thaw cycle the relative dynamic elastic modulus began to drop, 200 times freeze-thaw cycle ends, relative dynamic elastic modulus variation is the largest, decrease rate is 95%, TM concrete during 200 times freeze-thaw cycle, relative dynamic elastic modulus almost no change, B2 concrete and F2 concrete the extent of change between coating T3 and TM. After 300 times the freeze-thaw cycle coated concrete didn't appear freeze-thaw damage phenomenon. Four kinds of coating concrete relative dynamic elastic modulus variation by large to small order: T3 coated concrete > B2 coated concrete >F2 coated concrete > TM coated concrete, concrete with the same 200d rule. Frost resistance order, by contrast, TM coated concrete > B2 coated concrete > F2 coated concrete > T3 coated concrete.

scholarly journals Use of Silica Fume and GGBS to Improve Frost Resistance of ECC with High-Volume Fly Ash

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Yushi Liu ◽  
Xiaoming Zhou ◽  
Chengbo Lv ◽  
Yingzi Yang ◽  
Tianan Liu
Keyword(s):  
Elastic Modulus ◽  
Sodium Chloride ◽  
Mass Loss ◽  
Frost Resistance ◽  
Chloride Solution ◽  
Sodium Chloride Solution ◽  
Tap Water ◽  
High Volume ◽  
Dynamic Elastic Modulus ◽  
Freeze Thaw

Fly ash (FA) has been an important ingredient for engineered cementitious composite (ECC) with excellent tensile strain capacity and multiple cracking. Unfortunately, the frost resistance of ECC with high-volume FA has always been a problem. This paper discusses the influence of silica fume (SF) and ground-granulated blast-furnace slag (GGBS) on the frost resistance of ECC with high volume of FA. Four ECC mixtures, ECC (50% FA), ECC (70% FA), ECC (30% FA + 40% SL), and ECC (65% FA + 5% SF), are evaluated by freezing-thawing cycles up to 200 cycles in tap water and sodium chloride solution. The result shows the relative dynamic elastic modulus and mass loss of ECC in sodium chloride solution by freeze-thaw cycles are larger than those in tap water by freeze-thaw cycles. Moreover, the relative dynamic elastic modulus and mass loss of ECC by freeze-thaw cycles increase with FA content increasing. However, the ECC (30% FA + 40% SL) shows a lower relative dynamic elastic modulus and mass loss, but its deflection upon four-point bending test is relatively smaller before and after freeze-thaw cycles. By contrast, the ECC (65% FA + 5% SF) exhibits a significant deflection increase with higher first cracking load, and the toughness increases sharply after freeze-thaw cycles, meaning ECC has good toughness property.

scholarly journals Study on the Mechanical Properties of Chlorine Saline Soil under the Interaction of Multiple Factors

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Anhua Xu ◽  
Pengcheng Wang ◽  
Jianhong Fang
Keyword(s):  
Elastic Modulus ◽  
Moisture Content ◽  
Mechanical Characteristics ◽  
External Environment ◽  
Confining Pressure ◽  
Dynamic Elastic Modulus ◽  
Dynamic Strain ◽  
Saline Soils ◽  
Loading Frequency ◽  
Failure Strength

The distribution of chlorine saline soils is extensive in Haixi region of Qinghai Province in Northwest China. Its natural and geographical conditions are unique, and the external environment varies greatly. To study the effects of variable external environment on the mechanical characteristics of chlorine saline soils, a number of unconsolidated undrained (UU) dynamic triaxial tests under different confining pressure, moisture content, and loading frequency were carried out. The dynamic stress–dynamic strain, failure strength, dynamic elastic modulus, and parameter of shear strength were analyzed. The triaxial test results demonstrated that the stress–strain curves of the soil were strain-hardening. The failure strength and dynamic elastic modulus increased with the increasing of confining pressure; the law with moisture content and loading frequency were inconsistent. The dynamic cohesion and dynamic friction angle increased with the increasing of loading frequency, but decreased with the increasing of moisture content. Besides, the significance analysis theory was used to analyze the effect degree of different factors. It found that the effects of confining pressure, loading frequency, and the interaction between confining pressure and frequency on mechanical characteristics were significant, but the moisture content had less effect.

scholarly journals Retweet Prediction Based on User Behavior

2021 ◽  
Author(s):  
Syeda Nadia Firdaus
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Network ◽  
Prediction Model ◽  
Matrix Factorization ◽  
Information Diffusion ◽  
User Behavior ◽  
Past Research ◽  
The Difference ◽  
The Impact

Social network is a hot topic of interest for researchers in the field of computer science in recent years. These social networks such as Facebook, Twitter, Instagram play an important role in information diffusion. Social network data are created by its users. Users’ online activities and behavior have been studied in various past research efforts in order to get a better understanding on how information is diffused on social networks. In this study, we focus on Twitter and we explore the impact of user behavior on their retweet activity. To represent a user’s behavior for predicting their retweet decision, we introduce 10-dimentional emotion and 35-dimensional personality related features. We consider the difference of a user being an author and a retweeter in terms of their behaviors, and propose a machine learning based retweet prediction model considering this difference. We also propose two approaches for matrix factorization retweet prediction model which learns the latent relation between users and tweets to predict the user’s retweet decision. In the experiment, we have tested our proposed models. We find that models based on user behavior related features provide good improvement (3% - 6% in terms of F1- score) over baseline models. By only considering user’s behavior as a retweeter, the data processing time is reduced while the prediction accuracy is comparable to the case when both retweeting and posting behaviors are considered. In the proposed matrix factorization models, we include tweet features into the basic factorization model through newly defined regularization terms and improve the performance by 3% - 4% in terms of F1-score. Finally, we compare the performance of machine learning and matrix factorization models for retweet prediction and find that none of the models is superior to the other in all occasions. Therefore, different models should be used depending on how prediction results will be used. Machine learning model is preferable when a model’s performance quality is important such as for tweet re-ranking and tweet recommendation. Matrix factorization is a preferred option when model’s positive retweet prediction capability is more important such as for marketing campaign and finding potential retweeters.

scholarly journals Retweet Prediction Based on User Behavior

2021 ◽  
Author(s):  
Syeda Nadia Firdaus
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Network ◽  
Prediction Model ◽  
Matrix Factorization ◽  
Information Diffusion ◽  
User Behavior ◽  
Past Research ◽  
The Difference ◽  
The Impact

Social network is a hot topic of interest for researchers in the field of computer science in recent years. These social networks such as Facebook, Twitter, Instagram play an important role in information diffusion. Social network data are created by its users. Users’ online activities and behavior have been studied in various past research efforts in order to get a better understanding on how information is diffused on social networks. In this study, we focus on Twitter and we explore the impact of user behavior on their retweet activity. To represent a user’s behavior for predicting their retweet decision, we introduce 10-dimentional emotion and 35-dimensional personality related features. We consider the difference of a user being an author and a retweeter in terms of their behaviors, and propose a machine learning based retweet prediction model considering this difference. We also propose two approaches for matrix factorization retweet prediction model which learns the latent relation between users and tweets to predict the user’s retweet decision. In the experiment, we have tested our proposed models. We find that models based on user behavior related features provide good improvement (3% - 6% in terms of F1- score) over baseline models. By only considering user’s behavior as a retweeter, the data processing time is reduced while the prediction accuracy is comparable to the case when both retweeting and posting behaviors are considered. In the proposed matrix factorization models, we include tweet features into the basic factorization model through newly defined regularization terms and improve the performance by 3% - 4% in terms of F1-score. Finally, we compare the performance of machine learning and matrix factorization models for retweet prediction and find that none of the models is superior to the other in all occasions. Therefore, different models should be used depending on how prediction results will be used. Machine learning model is preferable when a model’s performance quality is important such as for tweet re-ranking and tweet recommendation. Matrix factorization is a preferred option when model’s positive retweet prediction capability is more important such as for marketing campaign and finding potential retweeters.

Sign in / Sign up

Export Citation Format

Share Document