<p>This article extensively compares two distinct artificial intelligence methods: Deep Learning (Long Short-Term Memory-LSTM) and Machine Learning (Piecewise ARX model-PWARX). The focus is on their effectiveness in understanding operational modes and how identify the discrete states within heating systems, particularly in solar and geothermal applications. PWARX proves adept at recognizing and comprehending various operational modes (discrete states), providing a detailed insight into system functionality and aiding in anomaly detection. In contrast, LSTM primarily serves as a validation tool, confirming established patterns within the data but lacking the deep physical understanding of operational modes. The article underscores PWARX’s strengths in system analysis and anomaly detection, highlighting its applicability in solar and geothermal heating systems.</p>

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Comparing AI methods: PWARX and LSTM models in solar and geothermal heating analysis

  • M. H. Benzaama,
  • A. M. Mokhtari,
  • L. Rajaoarisoa,
  • S. Menhoudj,
  • A. Lapertot,
  • I. Chriaa,
  • R. Mege,
  • R. Mishra

摘要

This article extensively compares two distinct artificial intelligence methods: Deep Learning (Long Short-Term Memory-LSTM) and Machine Learning (Piecewise ARX model-PWARX). The focus is on their effectiveness in understanding operational modes and how identify the discrete states within heating systems, particularly in solar and geothermal applications. PWARX proves adept at recognizing and comprehending various operational modes (discrete states), providing a detailed insight into system functionality and aiding in anomaly detection. In contrast, LSTM primarily serves as a validation tool, confirming established patterns within the data but lacking the deep physical understanding of operational modes. The article underscores PWARX’s strengths in system analysis and anomaly detection, highlighting its applicability in solar and geothermal heating systems.