Mobile-Based Expert System for Fault Diagnosis of Air Handling Units

 
Abstract. This study aims to develop and evaluate an artificial intelligence–based expert system to support fault diagnosis in Air Handling Units (AHUs). Early fault identification in AHU systems is often constrained by reliance on technician experience, which may lead to inconsistent diagnostic outcomes. The proposed system is intended to provide a consistent, explainable, and practical decision-support tool to assist maintenance personnel, particularly less-experienced technicians, in identifying AHU faults accurately. Methodology: The research adopts a rule-based expert system approach using forward chaining inference. Knowledge acquisition was conducted through structured interviews with experienced HVAC technicians and supported by technical documentation. The resulting knowledge base consists of observable symptoms, diagnostic rules, and corresponding corrective actions. The system was implemented as an Android-based mobile application to enable direct field usage. System validation was performed using real operational fault scenarios, with expert diagnoses serving as the reference standard. Findings: Evaluation results indicate full agreement between the system-generated diagnoses and expert assessments across all tested scenarios. This demonstrates that the proposed system is capable of producing accurate and consistent diagnostic outcomes within its defined knowledge domain. Implications: The system operates using deterministic rules without incorporating uncertainty modeling or probabilistic reasoning. Additionally, validation was limited to a finite number of real-world scenarios, which may affect generalizability to broader AHU configurations. Practical implications: The expert system can be utilized as a practical diagnostic aid in routine AHU maintenance, improving response time, diagnostic consistency, and technician training effectiveness. Originality: This study contributes a mobile-based, explainable expert system specifically tailored for AHU fault diagnosis, emphasizing practical deployment and rule transparency rather than data-intensive learning models.