A new tuning approach of Single Input Fuzzy Logic Controller (SIFLC) for Remotely Operated Vehicle (ROV) Depth Control

The proton exchange membrane fuel cell (PEMFC) has a higher power density, so it is suitable to be utilized for powering electric vehicles (EVs) and supporting the grid's power balance and voltage stability. As its load will vary during operation, the PEMFC system have to manage the fuel feed following load variations. In this study, a dead-end anode-type PEMFC system with a rated power of 1 kW is used to investigate its performance under current loading rates of 0-28 A in steady-state conditions. From the test results, the empirical models were derived and simulated in MATLAB. The test is conducted by measuring the PEMFC stack's current, voltage, hydrogen flow rate, and purging behavior. The experimental results show a nonlinear correlation between stack current and voltage as well as its efficiency of hydrogen consumption to the electricity generated. The hydrogen flow rate exhibits a linear relationship to the generated power output in normal operation, neglecting the purging flow rate. Meanwhile, the total consumed hydrogen, including purging process, performs an exponential result which indicates more hydrogen was consumed for purging. Moreover, the observed purging behavior shows that the load current affects the purging interval time in an exponential decay manner. Some possible control methods are then discussed to control the hydrogen flow that dynamically follow the load variation and enable a not-complete purge; thus, the hydrogen consumption could be optimized and the excess hydrogen during the purging could be minimized.

Section: Discussionmentioning

confidence: 99%

Performance Test of 1 kW PEM Fuel Cell System to Determine Its Empirical Model

Fauziah,

Kurniawan,

Kurniasari

et al. 2023

“…Hence the appropriate controller method is the on/off controller method or Boolean control logic. Other methods, such as fuzzy logic [24][25] , are irrelevant.…”

Section: Study Methodsmentioning

confidence: 99%

A Method to Present the Uniqueness for Uniform Program Applied in Irrigation Telecontrol

Maftukhah,

Wijonarko,

Purwowibowo

et al. 2023

This study aims to show a trick to display the uniqueness of a steady program implied in irrigation telecontrol. The instrument comprises master terminal unit (MTU, master) and remote terminal unit (RTU). The MTU can exhibit the uniqueness of each instrument by inputting the RTU number. Then the program enters an array definition. The array definition makes every RTU seems unique and distinct from the others from the aspects of 1) MTU sim card number, 2) RTU sim card number, 3) background image, 4) farmer group, 5) farmer coordinator, 6) farming area name, and 7) display colour.

“…Some more works carried out by the researchers also showed systematic failure [12][13][14] occurred inside the cutting tools which are taken care for reference in the manuscript. Furthermore, the earlier work [15][16][17][18][19] that motivated the authors to carried out this novel work that cope up with the demand of Industry 4.0.…”

Section: Literature Reviewmentioning

confidence: 99%

Prediction of Tool Wear Using Machine Learning Approaches for Machining on Lathe Machine

Ashish Kumar Srivastava,

Bipin Kumar Singh,

Gupta

2023

In manufacturing industries, removal of material from the workpiece is the prime processes that convert raw material into finished product. During removal processes the cutting tool are incessantly deteriorated in health, which can be stated as perks and drawbacks of process. The precision and roughness of the material are directly related to the condition of the tools during the machining process. Machining analysis depends on numerous of cutting conditions when it is being performed. The likelihood of wearing increases with repeated use. So, by implementing the proposed approach for tool wear prediction can improve the quality as well as reduce the machining time. However, to maintain the healthy tool's conditions for prolong time is a major challenge for the scientific community. Hence, as a component of industry 4.0, this study explored the possibilities to monitor the tool condition using the machine learning techniques. So, an endeavor has been made to present a solution of this problem without hampering the productivity losses in terms of time, material, and tool, consequences in high productivity. For the proposed work, machine learning techniques such as k-NN, Random forest, Adaboost, k-Star, and Decision Tree are implemented and there accuracy of prediction is demonstrated. Furthermore, WEKA, open source software has been used to employ several tool learning algorithms for better understanding. The investigation noticed that the random forest algorithm has a higher accuracy of 97.30% and a root mean square error value of 0.144 among all other algorithm.