A novel long-term water absorption and thickness swelling deep learning forecast method for corn husk fiber-polypropylene composite
Source abstract
Abstract
Investigating long-term water absorption (WA) and thickness swelling (TS) behaviors of wood plastic composites demand long working hours and high laboratory costs. However, using artificial intelligence methods, these behaviors can be predicted in far less time and with a low degree of error. This paper aims to predict the long-term WA and TS behaviors of a cornhusk fiber (CHF) propylene (PP) composite using the deep learning field’s long short-term memory (LSTM) method. We assessed the network LSTM performance based on mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The experimental tests of WA and TS behaviors were performed on a CHF/PP composite using three different filler percentages over a period of 0–1500 h. The predictions were carried out for 200, 400, 600, 800, and 1000 h to construct a database to identify how many hours of training data are required to meet a MAPE criterion of 2% between the actual and predicted data. The results show that 200 h of training data is adequate for the LSTM method to achieve this MAPE metric. Furthermore, the metrics results validate the applicability of the proposed method. All the manufacturing metrics and codes are attached.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Textile materials and evaluations · Infrastructure Maintenance and Monitoring · Wind and Air Flow Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (47)
Show source-provided references
1. Liu Xin, Su Tian, Fei Tao, Haodong Du, Wenbin Yu, Machine learning-assisted modeling of composite materials and structures: a review, 2021. doi: 10.2514/6.2021-2023.10.1115/1.0004762V ↗
2. Prediction of two-phase composite microstructure properties through deep learning of reduced dimensional structure-response data
3. Predicting student performance in an educational game using a hidden Markov model
4. Comparison of ARIMA and artificial neural networks models for stock price prediction
5. Machine learning for composite materials10.1557/mrc.2019.32 ↗
6. Analysis of lumber prices time series using long short-term memory artificial neural networks10.3390/f12040428 ↗
7. Artificial neural network evaluation of cement-bonded particle board produced from red iron wood (Lophira alata) sawdust and palm kernel shell residues
8. Predicting the effective thermal conductivities of composite materials and porous media by machine learning methods10.1016/j.ijheatmasstransfer.2018.08.082 ↗
9. Machine learning prediction of thermal transport in porous media with physics-based descriptors10.1016/j.ijheatmasstransfer.2020.120176 ↗
10. Open set recognition of timber species using deep learning for embedded systems10.1109/TLA.2019.9011545 ↗
11. Machine learning for composite materials10.1557/mrc.2019.32 ↗
12. An artificial neural network model for predicting compression strength of heat treated woods and comparison with a multiple linear regression model10.1016/j.conbuildmat.2014.03.041 ↗
13. Multiple linear regression, artificial neural network, and fuzzy logic prediction of 28 days compressive strength of concrete
14. Can the compressive strength of concrete be estimated from knowledge of the mixture proportions?: new insights from statistical analysis and machine learning methods
15. Descriptor selection for predicting interfacial thermal resistance by machine learning methods
16. Machine learning applications in polymer composites
17. Ageing of autoclaved epoxy/flax composites: effects on water absorption, porosity and flexural behaviour
18. Moisture sorption and swelling of flax fibre and flax fibre composites
19. The influence of water absorption on unidirectional and 2D woven CFRP composites and their mechanical performance
20. The effect of water immersion and fibre content on properties of corn husk fibres reinforced thermoset polyester composite
21. Long-term water absorption and dimensional stability of composites from recycled polypropylene and rubberwood flour
22. Long-term water absorption behavior of thermoplastic composites produced with thermally treated wood10.1016/j.measurement.2016.02.058 ↗
23. The changes on morphological and absorption ability of treated corn stalk fiber10.1088/1742-6596/1529/5/052009 ↗
24. A machine learning framework for real-time inverse modeling and multi-objective process optimization of composites for active manufacturing control10.1016/j.compositesb.2021.109150 ↗
25. Yamak, Peter & Yujian, Li & Gadosey, Pius., 2019. A Comparison between ARIMA, LSTM, and GRU for Time Series Forecasting. 49–55. 10.1145/3377713.3377722.10.1145/3377713.3377722 ↗
26. Forecasting across time series databases using recurrent neural networks on groups of similar series: a clustering approach
27. Pedro Lara-Benítez, Manuel Carranza-García, José Riquelme, An Experimental Review on Deep Learning Architectures for Time Series Forecasting, 2021.10.1142/S0129065721300011 ↗
28. Short-term photovoltaic power forecasting using an LSTM neural network and synthetic weather forecast10.1109/ACCESS.2020.3024901 ↗
29. A simplified LSTM neural networks for one day-ahead solar power forecasting
30. Short-term residential load forecasting based on LSTM recurrent neural network
31. Predicting the number of customer transactions using stacked LSTM recurrent neural networks10.1007/s13278-021-00805-4 ↗
32. High granular and short term time series forecasting of $$\hbox {PM}2.5$$ air pollutant - a comparative review10.1007/s10462-021-09991-1 ↗
33. Masum, Mohammad & Shahriar, Hossain & Haddad, Hisham & Alam, Md. (2020). r-LSTM: Time Series Forecasting for COVID-19 Confirmed Cases with LSTMbased Framework. 1374–1379. 10.1109/BigData50022.2020.9378276.10.1109/BigData50022.2020.9378276 ↗
34. Standard test methods of evaluating properties of wood-based fiber and particle panel materials. Annual Book of ASTM Standards, vol. 04–09. Philadelphia: American Society for Testing and Materials––ASTM, ASTM D 1037–96a, 1998.
35. Ben Adcock, Anders Hansen, 18 - Neural Networks and Deep Learning, 2021. Doi: 10.1017/9781108377447.024.10.1017/9781108377447.024 ↗
36. Leveraging long short-term memory (LSTM)-based neural networks for modeling structure–property relationships of metamaterials from electromagnetic responses10.1038/s41598-021-97999-6 ↗
37. Deep convolutional and LSTM recurrent neural networks for rolling bearing fault diagnosis under strong noises and variable loads10.1109/ACCESS.2020.2985617 ↗
38. Effective neural network training with a new weighting mechanism-based optimization algorithm10.1109/ACCESS.2019.2919987 ↗
39. Machine learning: algorithms, real-world applications and research directions10.1007/s42979-021-00592-x ↗
40. Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM10.1016/j.chaos.2020.110212 ↗
41. A novel genetic LSTM model for wind power forecast10.1016/j.energy.2021.120069 ↗
42. A novel wavenets long short term memory paradigm for wind power prediction10.1016/j.apenergy.2020.115098 ↗
43. Physico-mechanical properties and long-term creep behavior of wood-plastic composites for construction materials: effect of water immersion times
44. Effects of water absorption on the mechanical properties of hybrid natural fibre/phenol formaldehyde composites10.1038/s41598-021-92457-9 ↗
45. Development and characterization of wood-polypropylene plastic-cement composite board
46. Melih Şahinöz, Hüseyin Aruntaş, Metin Gürü, Processing of polymer wood composite material from pine cone and the binder of phenol formaldehyde/PVAc/molasses and improvement of its properties, 2021. doi: 10.21203/rs.3.rs-1211662/v1.10.21203/rs.3.rs-1211662/v1 ↗
47. Comparative study on artificial and natural weathering of wood-polymer compounds: a comprehensive literature review