<![CDATA[The BMW 3 Series with production code E36, built between 1991 and 1998, remains widely owned in Indonesia, yet its age of more than two decades makes power loss a frequent complaint. Although the E36 engine is partially computerized, owners living far from an authorized or specialist workshop equipped with a diagnostic scanner cannot easily determine the cause of the power loss they experience. This study builds a web-based expert system, “Si Pak-E”, that identifies power loss problems on the BMW 3 Series E36 engine and recommends solutions. Knowledge was acquired through structured interviews with a BMW specialist mechanic and represented as a knowledge base of 22 problems, 33 symptoms, 22 solutions, and 22 production rules derived from a 33 × 22 decision table. Forward chaining was selected as the inference engine because diagnosis proceeds from observed symptoms toward a conclusion, while the waterfall model guided development. The system was implemented in PHP, MySQL, and Bootstrap with three user roles. Evaluation combined functional black-box testing with knowledge-base verification against the expert. Black-box testing executed 95 scenarios across 36 test cases and three roles, and all 95 (100%) produced the expected output. Rule-coverage verification traced all 22 production rules as consultation cases, and the system returned the problem and solution expected by the expert in 22 of 22 cases (100% agreement). The findings show that forward chaining is effective for symptom-driven automotive fault identification and that the system is a practical, transparent, and accessible diagnostic aid for E36 owners. Keywords: BMW E36, expert system, fault diagnosis, forward chaining, power loss, web-based.]]>
Copyrights © 2026
