Assessment of Some Basic Engineering Properties of Fibres Extracted from Thaumatococcus danielli Plant
Nurudeen Simbiat Adesola,
Lasisi Kayode Hassan,
Babatola Josiah Oladele,
Lafe Olurinde
Issue:
Volume 5, Issue 1, March 2020
Pages:
1-9
Received:
4 October 2019
Accepted:
31 January 2020
Published:
10 February 2020
Abstract: The use of natural fibres either as reinforcement in polymer composites or as stand-alone material in engineering and construction is continuously gaining more attention. This study assesses some basic engineering properties of fibres extracted from thaumatococcus daniellii plant using topbond and evo-stik as adhesives. A total of 340 individual samples were weaved into sizes of 15 cm by 15 cm and glued together to a thickness of 2.5 cm from two fibre types of different texture and structure derived from thaumatococcus daniellii plant. Some of the samples were selected for alkali and acetylation treatments to improve their strength and were thereafter subjected to basic engineering tests such as water absorption, flexural strength, fire resistance and tensile strength tests. The test results show that the average water absorption rate of the treated materials glued with topbond for Material A possesses a lower percentage of 19.61% than 51.41% for treated materials glued with topbond for Material B. Material with evo-stik as adhesives has an extremely high water absorbing capacity. The average flexural strength of 103.50 Mpa for treated and topbond glued Material A is higher than 73.07 Mpa for treated Material B and other untreated materials. Material A exhibits better fire resistance property than Material B, as it takes the latter longer time for ignition to occur during the test. Although, Material B give higher tensile strength values than Material A but with insignificant difference. The comparison between the two materials given due consideration to the adhesives used shows some correlation in their properties. However, Material A gives more satisfactory results than Material B hence making it the best choice of material from the two fibres extracted from the plant.
Abstract: The use of natural fibres either as reinforcement in polymer composites or as stand-alone material in engineering and construction is continuously gaining more attention. This study assesses some basic engineering properties of fibres extracted from thaumatococcus daniellii plant using topbond and evo-stik as adhesives. A total of 340 individual sa...
Show More
Timing and Parameter Optimization for One-time Motion Problem Based on Reinforcement Learning
Boxuan Fan,
Guiming Chen,
Hongtao Lin
Issue:
Volume 5, Issue 1, March 2020
Pages:
10-17
Received:
17 February 2020
Accepted:
3 March 2020
Published:
24 March 2020
Abstract: Baseball hitting, swatter swing and football catching, there are many tasks can be seen as a one-time action, whose goal is to control the timing and parameters of the action to achieve optimal results. Many one-time motion problems are difficult to obtain the optimal policy through model solving, and model-free reinforcement learning has advantages for such problems. However, although reinforcement learning has developed rapidly, there is currently no universal one-time motion problem algorithm architecture. Decomposing the one-time motion problem into the action timing problem and the action parameter problem, we construct a suitable reinforcement learning method for each of them. We design a combination mechanism that allows the two modules to learn simultaneously by passing the estimated value between the two modules while interacting with the environment. We use REINFORCE + DPG to solve the problem of continuous motion parameter space, and use REINFORCE + Q learning to solve the problem of discrete motion parameter space. To testing the algorithm model, we designed and realized an aircraft bombing simulation environment. The test results show that the algorithm can converge quickly and stably, and is robust to different time step and observation errors.
Abstract: Baseball hitting, swatter swing and football catching, there are many tasks can be seen as a one-time action, whose goal is to control the timing and parameters of the action to achieve optimal results. Many one-time motion problems are difficult to obtain the optimal policy through model solving, and model-free reinforcement learning has advantage...
Show More
