Expert System for BMW 3-Series Fault Diagnosis Using Forward Chaining

Ahmad Baihaqi

doi:10.69693/jesa.v3i2.100

Authors

Ahmad Baihaqi Universitas Pamulang

DOI:

https://doi.org/10.69693/jesa.v3i2.100

Keywords:

Expert System, Forward Chaining, Fault Diagnosis, BMW 3-Series, Certainty Factor, Rule-Based System

Abstract

Modern automotive technology in premium vehicles, particularly the BMW 3-Series produced between 1990 and 2006, contains interdependent mechanical components, sensors, actuators, and electronic control units. These relationships make fault diagnosis challenging because different failures can produce similar symptoms. At CV. Ryuga Spareparts, initial fault identification depends substantially on the experience and memory of technicians. This condition can create variation in diagnostic decisions, extend troubleshooting time, and make junior technicians dependent on senior personnel. This study develops a web-based expert system to support the initial diagnosis of BMW 3-Series faults using Forward Chaining and Certainty Factor. Research activities include knowledge acquisition, symptom and fault modeling, production-rule formulation, web application development, and functional testing. The knowledge base contains ten symptom indicators, ten fault classifications, and ten IF–THEN rules. The inference engine treats selected symptoms as initial facts and evaluates rule premises to infer a possible fault. Certainty Factor weighting represents confidence associated with user-observed symptoms and expert knowledge. The application is implemented using Laravel and PHP with a MySQL relational database following an MVC architecture. Black Box Testing was conducted on six core modules: authentication, symptom management, fault management, rule configuration, diagnosis, and report export. The source study reports that all tested functions passed, giving 100% functional validity for the tested scenarios. This result indicates functional conformity, not a measured 100% mechanical diagnostic accuracy. The application can support a more systematic preliminary diagnosis and preserve workshop knowledge in a structured form.

Downloads

Download data is not yet available.

References

[1] K. Alomari and N. Jamil, “Expert system applications in diagnostic processes,” J. Intell. Syst., vol. 15, no. 3, pp. 245–259, 2021, doi: 10.1515/jis-2021-0024.

[2] R. Harahap, “Implementation of forward chaining for damage detection systems,” Int. J. Comput. Appl., vol. 179, no. 52, pp. 10–16, 2021, doi: 10.5120/ijca2021921400.

[3] B. Prasetyo, “Optimization of forward chaining for automotive damage identification,” Indones. J. Informatics, vol. 7, no. 1, pp. 33–41, 2022.

[4] Y. Putra, “Forward chaining method in mechanical damage diagnosis,” J. Mech. Intell., vol. 5, no. 1, pp. 21–29, 2022.

[5] A. Lestari and D. Kurniawan, “Rule-based inference for machine fault diagnosis,” J. Appl. Eng. Res., vol. 8, no. 2, pp. 112–120, 2023.

[6] A. Rahman and M. Ghani, “Data-driven reasoning approaches in expert systems,” Expert Syst. Rev., vol. 9, no. 4, pp. 201–215, 2021.

[7] K. Safitri and R. Gunawan, “Perancangan aplikasi sistem pakar menggunakan metode forward chaining berbasis web,” J. Teknol. Sist. Inf. dan Apl., vol. 7, no. 2, pp. 145–152, 2024.

[8] S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed. Englewood Cliffs, NJ, USA: Prentice Hall, 2020.

[9] E. Turban, J. E. Aronson, and T.-P. Liang, Decision Support Systems and Intelligent Systems, 9th ed. Upper Saddle River, NJ, USA: Pearson, 2011.

[10] M. A. Hasan and S. B. Ahmed, “Automotive fault diagnosis using rule-based expert system,” IEEE Access, vol. 9, pp. 102450–102462, 2021, doi: 10.1109/ACCESS.2021.3098120.

[11] C. P. Tan and L. H. Wong, “Vehicle diagnostic trouble code analysis using forward chaining,” Int. J. Automot. Technol., vol. 22, no. 4, pp. 915–925, 2021.

[12] J. Smith and R. Davies, “Engine management system troubleshooting via expert systems,” SAE Tech. Pap., Art. no. 2022-01-0512, 2022, doi: 10.4271/2022-01-0512.

[13] R. S. Pressman and B. R. Maxim, Software Engineering: A Practitioner's Approach, 9th ed. New York, NY, USA: McGraw-Hill, 2020.

[14] I. Sommerville, Software Engineering, 10th ed. Boston, MA, USA: Pearson, 2016.

[15] A. Firmansyah, M. R. Siregar, and Z. Hasibuan, “Pembuatan aplikasi pembelajaran berbasis web,” J. Mhs. Pengabdian, vol. 4, no. 1, pp. 2555–2562, 2025.

[16] R. Kaban and D. J. Sembiring, HTML: Pengantar Pemrograman Berbasis Web, 1st ed. Sumatra Barat, Indonesia: CV Insan Cendekia Mandiri, 2021.

[17] G. F. Luger, Artificial Intelligence: Structures and Strategies for Complex Problem Solving, 6th ed. Boston, MA, USA: Addison-Wesley, 2009.

[18] F. Giarratano and G. Riley, Expert Systems: Principles and Programming, 4th ed. Boston, MA, USA: Thomson Course Technology, 2005.

[19] E. H. Shortliffe and B. G. Buchanan, “A model of inexact reasoning in medicine,” Math. Biosci., vol. 23, no. 3-4, pp. 351–379, 1975, doi: 10.1016/0025-5564(75)90047-4.

[20] M. Stauffer, Laravel: Up & Running, 2nd ed. Sebastopol, CA, USA: O'Reilly Media, 2019.

[21] U. K. Siregar, T. A. Sitakar, S. Haramain, Z. N. S. Lubis, U. Nadhirah, and Y. Yahfizham, “Pengembangan database management system menggunakan MySQL,” J. Sains, Teknol. & Komput., vol. 1, no. 1, pp. 8–12, 2024.

[22] A. Lestari and S. Wibowo, “Pengembangan sistem informasi pelayanan publik berbasis web,” J. Rekayasa Perangkat Lunak, vol. 10, no. 1, pp. 45–52, 2022.

[23] H. Bosch GmbH, Bosch Automotive Electrics and Automotive Electronics, 5th ed. Wiesbaden, Germany: Springer Vieweg, 2014.

[24] G. J. Myers, C. Sandler, and T. Badgett, The Art of Software Testing, 3rd ed. Hoboken, NJ, USA: John Wiley & Sons, 2011.

[25] W. E. Perry, Effective Methods for Software Testing, 3rd ed. Indianapolis, IN, USA: Wiley Publishing, 2006.