Mohammed Y. Hassan

Comparison between Neural Network based PI and PID controllers

The Pneumatic actuation systems are widely used in industrial automation, such as drilling, sawing, squeezing, gripping, and spraying. Also, they are used in motion control of materials and parts handling, packing machines, machine tools, and in robotics; e.g. two-legged robot. In this paper, a Neural Network based PI controller and Neural Network based PID controller are designed and simulated to increase the position accuracy in a pneumatic servo actuator. In these designs, a well-trained Neural Network provides these controllers with suitable gains depending on feedback representing changes in position error and changes in external load force. These gains should keep the positional response within minimum overshoot, minimum rise time and minimum steady state error. A comparison between Neural Network based PI controller and Neural Network based PID controller was made to find the best controller that can be generated with simple structure according to the number of hidden layers and the number of neurons per layer. It was concluded that the Neural Network based PID controller was trained and generated with simpler structure and minimum Mean Square Error compared with the trained and generated one used with PI controller.

Tribological Features of Refined, Deodorized, and Bleached Palm Olein with Mineral Oil Blend

ABSTRACT Vegetable oils have been investigated to replace petroleum-based lubricants due to their environmentally friendly characteristics, and these oils have become an important source of biolubricants. For the purpose of ensuring the ability of vegetable oils as a neat or partial biolubricants, image processing techniques were employed to explore the tribological characteristics of vegetable oil with a mineral oil blend. Refined, bleached, and deodorized palm olein blended with mineral oils was investigated using a four-ball tribotester and design of experiments with volumetric blend ratios of 20 to 80%. An optimized value E53.11/RB46.89 was obtained from the investigation, in compliance with ASTM D4172 standard. From the results, the E53.11/RB46.89 blend reduces the friction coefficient and wear scar diameter as well as the material lost in comparison with neat mineral oil. It is concluded that the E53.11/RB46.89 blend could be a potential partial biolubricant due to its negligible negative impact on wear and it provides satisfactory performance as a lubricant.

The Tribological Characteristics of RBD Palm Olein with Jatropha Oil Blend Using Four-Ball Tribotester with Different Normal Loads

Vegetable oils are bio-fluids that could replace petroleum-based products due to its environment friendly characteristics and becoming an important source of bio-lubricants. The great advantage of vegetable oils is that they are widely available, renewable source of bio-lubricants. Moreover, vegetable oil based lubricant have shown the potential to reduce carbon dioxide and hydrocarbon emissions when operated in engines. There are two ways to use vegetable oil as a bio-lubricant, either use directly the neat vegetable oil without any additives or use with certain blending ratio of the vegetable oil with mineral lubricant. In this paper, the influences of the normal load on the tribological characteristics for the blending of two types of vegetable oils were investigated and compared with commercial lubricant oil by the use of the four ball tribotester. The vegetable blends are RBD palm olein and Jatropha oil ratio of RBD40/J60. All experimental works were conforming to ASTM D4172. The results exhibited that the both blending of RBD palm olein and Jatropha oil has lower the wear scar of ball bearings and coefficient of friction compared to commercial lubricant oil. As a conclusion, the blending of RBD palm olein and Jatropha oil has better performance compared to commercial lubricant oil or neat RBD palm olein.