Optimization of production parameters of particle gluing on internal bonding strength of particleboards using machine learning technology

Zhang, Beilong; Hua, Jun; Cai, Liping; Gao, Yunbo; Li, Yilin

doi:10.1186/s10086-022-02029-2

Cited by 6 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…By using the algorithm of TF-IDF, we can obtain the importance of the target words in the document [16] and then complete the screening of words, so as to obtain the representative text feature items, which lays a foundation for the subsequent classification and prediction.…”

Section: Methodsmentioning

confidence: 99%

Census and Inventory Method of Pollution Sources Based on Big Data Technology under Machine Learning

Liu

Sun

Jing

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In order to strengthen the supervision and management of environmental pollution and timely understand and record the basic information of potential environmental pollution of enterprises and institutions, this paper proposes a general survey and inventory method of pollution sources based on big data technology under machine learning. Firstly, this paper evaluates and screens the data provided by government departments, constructs a machine learning classification model, and uses a variety of classification algorithms to compare and analyze according to the basic idea of machine learning to deal with practical problems. Then, the calibration data set constructed is used as the training set to predict and classify the national industrial and commercial data, provincial industrial and commercial data, and municipal industrial and commercial data provided by government departments. The experimental results show that the naive Bayesian classification algorithm is the best algorithm, and the F1 values of each data set are increased by 32.92%, 21.42%, and 14.91%, respectively. The classified prediction of the screened Internet data shows that the accuracy of the final Internet supplementary data is 17.26%, which is similar to the industrial and commercial data of the city. The availability of the machine learning model established in this paper is proven.

show abstract

Section: Methodsmentioning

confidence: 99%

Census and Inventory Method of Pollution Sources Based on Big Data Technology under Machine Learning

Liu

Sun

Jing

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Glue stick diatas blog dilelehkan menggunakan hot plate yang kemudian blog dan board direkatkan dengan proses cooling pada water bath agar blog dan sampel board tersebut merekat dengan baik. Kemudian baru dilakukan penarikan oleh alat Zwick/Roell Z005, dengan hasil uji IB tersebut didapat HDF paling tinggi nilainya dibandingkan dengan MDF, dan MLDF [18].…”

Section: Density Profileunclassified

Analisis Sifat Fisis dan Mekanik Fiberboard Pada HDF, MDF, dan MLDF dengan Variasi Density Profile Menggunakan Alat Density Profile Analyzer Meter DPX200 IMAL

Rahmawati

Lafira

Sari³

et al. 2022

JPS

View full text Add to dashboard Cite

Telah dilakukan penelitian analisis sifat fisis dan mekanik tentang perbandingan produk HDF, MDF, dan, MLDF yang ditinjau dari density profile. Tujuan penelitian ini untuk mengetahui pengaruh densitas pada sifat fisis dan mekanik fibreboard. Produk yang digunakan sebagai bahan perbandingan adalah HDF, MDF, dan MLDF sesuai dengan tingkat densitasnya. Penelitian ini dimulai dengan melihat density profile menggunakan alat density profile meter analyzer DPX200 IMAL yang menggunakan sinar X-Ray. Sampel diurutkan sesuai dengan posisi saat board dipotong di line pabrik. left, center left, center, center right, dan right dengan diberi plat aluminium antar sampel baru dimasukkan ke dalam alat density profile meter analyzer dengan hasil pada MLDF, puncak maksimum encapai 908 kg/m 3 dan 881 kg/m 3 . Pada MDF, puncak maksimum mencapai 935 kg/m 3 dan 946 kg/m 3 , serta HDF puncak maksimum mencapai 1085 kg/m 3 dan 1032 kg/m 3 . Sampel yang telah diuji density profile kemudian dilakukan pengujian Internal boanding, MOE/MOR, dan surface weight. Hasil dari pengukuran densitas diperoleh bahwa semakin tinggi densitas yang diperoleh, maka semakin besar pula nilai dari internal boanding, MOE/MOR, dan surface weight. Hal ini berarti, densitas berbanding lurus dengan ketiga pengujian mekanik yang telah dilakukan.

show abstract

“…They also determined the relationship between production process parameters and mechanical properties of particleboard. Beilong Zhang [14] divided particleboard into three layers and used parameters such as particle discharge speed, flow rate of particle glue, and pressure on particle gluing to establish a nonlinear regression prediction model based on GRA-SVR. The prediction results showed that 91.16% of the test data had a deviation of 0-10% between the predicted values and the true values, while 28.28% of the test data had a relative deviation of 10-20%.…”

Section: Introductionmentioning

confidence: 99%

Investigation of Bonding Strength of Medium Density Fiberboard by Using Ultrasonic Testing

Xu,

Zhang,

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

Medium density fiberboard (MDF) is a widely used wood-based material, where the internal bond strength is a crucial mechanical performance index. Currently, the measurement of internal bond strength is achieved through destructive testing, which has the disadvantages of a complex procedure and a long testing time. This article proposes a model for measuring the dynamic compression modulus of elasticity (DCME) based on elastic dynamics. The model involves attaching a piezoelectric ceramic sheet to each side of the board, one for excitation and the other for response. By measuring the resonance frequency based on the response amplitude change, the DCME can be determined using the proposed model. Results indicated that there is a highly linear correlation between DCME and internal bond strength, with an r-squared value above 0.96. As the DCME increases, the internal bond strength improves, and the internal bond strength can be predicted based on the DCME. The article analyzes the model from the perspectives of acoustic transmission and ultrasonic directional analysis and verifies the correctness of the model through acoustic theory.

show abstract

Optimization of production parameters of particle gluing on internal bonding strength of particleboards using machine learning technology

Cited by 6 publications

References 26 publications

Census and Inventory Method of Pollution Sources Based on Big Data Technology under Machine Learning

Census and Inventory Method of Pollution Sources Based on Big Data Technology under Machine Learning

Analisis Sifat Fisis dan Mekanik Fiberboard Pada HDF, MDF, dan MLDF dengan Variasi Density Profile Menggunakan Alat Density Profile Analyzer Meter DPX200 IMAL

Investigation of Bonding Strength of Medium Density Fiberboard by Using Ultrasonic Testing

Contact Info

Product

Resources

About