Global Journal of Computer Science and Technology, C: Software & Data Engineering, Volume 22 Issue 2

The mean deviation error of the proposed system running on manual mode is computed using the formula below: The Mean Deviation Error = (∑ | x - µ | )/n, ,,,,, The mean (µ) of the errors for the proposed system running on manual mode is computed as follows: Mean (µ) Error Therefore, the mean (µ) error of the proposed system running on manual mode is 7.8 The mean deviation error of the proposed system running on manual mode is computed using the formula below: The Mean Deviation Error = (∑ | x - µ | )/n, The Mean Deviation Error (MAD) = (∑ | x - µ | )/n = 24/10 = 2.4 In computing the standard deviation of the proposed system error on auto run, we must take the square root of the mean absolute deviation error (MADE) squares it, divide by the total number of system errors (n) in auto run. Standard Déviation = √((∑ 〖 | x - µ | 〗 ^2)/n) = √( 〖 24 〗 ^2/10) = √(576/10) = 57.6 Therefore, the SD of proposed system error is 57.6 VII. C onclusion This paper is focused on expert system for control and maintaining steam package boiler parameters of the feed water and boiler drum recommended qualities using a hybrid technology of rule-base system and fuzzy logic. The dynamics simulation performs showed relatively high performance of consistency, correctness, and its precision of the system. The system can be modified, used as a platform by boiler trainers, especially for new intakes in all boilers operated allied industries. The design system will prevent damaged and malfunctioning as control the alkalinity, prevent scaling, both mechanical & chemical corrosion, forming, correct pH values and then the conductivity which deals with the feed boiler water. Acceptable error margined were not considered during this research work. Furthermore, we discovered in this paper that from 1 to 10minutesrun time for AUTO RUN form figure17 gives 2.8% errors as compared to the 1 to 10 minutes time interval on MANUAL RUN that gives 80.2% error. This speaks more for users less effort in user interface application usage on AUTO operations better than MANUAL operations, leading with a recommendation that AUTOMATION in industrial plant processes (fertilizer plant) for control and maintenance make it more consistence, correct and precise than MANUAL process of operations. R eferences R éférences R eferencias 1. Amit, K. J. (2012). An Approach towards Efficient Operation of Boilers. International Journal of Scientific & Engineering Research, 3(6). 2. Adetokunbo et al, (2012), Software Engineering Methodologies: A Review of the Waterfall Model and Object-Oriented Approach, International Journal of Scientific & Engineering Research, 4(7). 3. American Trainco Inc. (2006). Boiler Operation Maintenance & Safety Study Guide American Trainco Real World Training, American Trainco, In. www. AmericanTrainco.com 4. Anne Håkansson (2013), Portal of Research Methods and Methodologies for Research Projects and Degree Projects, WORLDCOMP'13 - The 2013 World Congress in Computer Science, Computer Engineering, and Applied Computing, 22-25 July Steam Package Boiler Expert System for Control and Maintenance of Fertilizer Plants Using Rule-Base Fuzzy Logic Global Journal of Computer Science and Technology Volume XXII Issue II Version I 38 Year 2022 ( ) C © 2022 Global Journals Figure 17: System Error Graphical Analysis on Manual and Auto Run 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% 0 2 4 6 8 10 12 1 2 3 4 5 6 7 8 9 10 SYSTEM ERRORS ANALYSIS ON AUTO ANDMANUAL RUN SYSTEMRUNNING IN AUTO (ERRORS) TIME IN MINUTES SYSTEMRUNNING IN MANUAL (ERRORS) = (∑x)/n = (3+6+6+6+6+8+9+11+11+12)/10 = 7.8 where x is the true mean error, µ is the mean error and n the sum of system errors in auto run of the proposed system. where x is the true mean error, µ is the mean error and n, the sum of system errors in manual run of the proposed system.