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

Figure 1: The Expert System Architecture 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 28 Year 2022 ( ) C © 2022 Global Journals Domain Expert: The domain expert is the personnel either designing the ES shell or putting in his/her knowledge into the system. It has a ready and mostly accurate knowledge and experience on the proposed system shell to be designed. The expert then encodes their knowledge into the system, by making it understandable for the machine to read by fuzzification. Knowledge Base (KB): The KB is the part of the ES shell which holds the encoded expert knowledge where the inference engine gets its own knowledge. It is knowledge warehouse or library of the entire ES shell. Datasets/Software Mechanism (Rule of Engine): This is the process of converting a fuzzy system statement or expression into a software usable or understandable language. The fuzzified expression or language is in the form of a fuzzy system membership form. This is the process where the software makes use of the datasets in the system as encoded by the domain expert. Plant Datasets: The plant datasets are then extracted from the inference engine (core of the fuzzy system) to be used for proper working of the plant. This process is bi-directional where the plant gets its datasets from the inference engine and gives its current datasets working condition to the inference engine for control. User interface : this is the part of expert system architecture that helps the user to be in contact with the system so we can consider it as the main engine of expert system. The User (Field Operators/Panel Engineers): The user on operations logs into the main system with an authenticated username and password. Users carried out required corrections of errors on the UI when the system is running on MOM and monitor and maintained the progress of the system on AMOs. a) Steam Package Boiler Rule-Base Fuzzy Logic The system has a inference kernel and a knowledge-based linked. The inference kernel (engine) is executed periodically to determine system output based on current system input. The knowledge-based contains membership functions and rules. Fuzzification: The current input values are compared against stored input membership functions, usually in a program loop structure to determine the degree to which each linguistic variable of each system is true. Defuzzification: Dissolves multiple degree ambiguous by putting raw fuzzy outputs into a composite numerical output. Rule-Base Evaluation: on the rule-base evaluation, this processes a list of rules from the knowledge-based using current fuzzy input values to produce a list of fuzzy output linguistic variable. Therefore, the system has the processes of both fuzzification and defuzzification, which plays major role in the proposed system architecture. The fuzzy logic is found in the part of the inference engine, where the software system converts rules to code and codes back to rules. V. S team P ackage B oiler E xpert S ystem D esign a) Datasets The datasets used are extracted from Section C, Boiler Manual (2020). Boiler drum water and Feed water recommended qualities datasets are used for the design of the fuzzy logic system. According to Amit (2012), the impurities found in boiler water depend on the untreated feed water quality, the treatment process used and the boiler operating procedures. As a rule, the