Detection of Geothermal Operational Asset Anomalies Using the Locality-Sensitive Hashing (LSH) Algorithm Muhammad Vito Hamza (a*), Fransisco T.P. Simamora (a), Efrata Pratenta Meliala (a), R. Fuad Satrio Ajie (a), Hanifah Nur Azizah (a), Fajar Khamim Mustofa (a), Adi Suparyanto (a)
a) PT Geo Dipa Energi (Persero),
Jl. Buncit Raya No.75, RW.7, Pejaten Bar., Kec. Pancoran, Kota Jakarta Selatan, Daerah Khusus Ibukota Jakarta 12510
Abstract
Geothermal power plants are crucial for sustainable energy generation, necessitating the reliable maintenance of their operating assets. This research proposes an approach for asset maintenance through anomaly detection using the Locality-Sensitive Hashing (LSH) algorithm.
The accuracy and coverage of traditional anomaly detection approaches in geothermal power plants may be constrained by sensor monitoring systems. The LSH algorithm is used to improve detection skills and get a full understanding of the state of important assets.
The proposed method utilizes historical sensor data collected during geothermal power plant operations. This data is transformed into hash codes using LSH, effectively capturing similarities between various operational states and asset conditions.
By comparing the hash codes of the current operational state with a library of precomputed hash codes representing typical operating conditions, the LSH algorithm can identify deviations indicating potential irregularities. This facilitates early detection of anomalies, even in large-scale databases, enabling prompt maintenance interventions.
The application of anomaly detection using the LSH algorithm provides benefits such as improved asset maintenance planning, reduced downtime, and increased operational safety. By leveraging data-driven analysis and the effectiveness of LSH, geothermal operators can detect faults early, enabling prompt interventions and optimizing reliability and efficiency.
In conclusion, this paper presents an approach for detecting anomalies in geothermal power plant operating assets using the LSH algorithm. By leveraging historical sensor data and the efficient similarity approximation capabilities of LSH, the proposed approach enables early diagnosis of problems, improving maintenance planning and optimizing geothermal operations.
