Interpretation and explanation of convolutional neural network-based fault diagnosis model at the feature-level for building energy systems

作者：Li, Guannan; Chen, Liang; Fan, Cheng^*; Li, Tao; Xu, Chengliang; Fang, Xi

来源：ENERGY AND BUILDINGS, 2023, 295: 113326.

DOI：10.1016/j.enbuild.2023.113326

• Building energy system
• Deep learning
• Fault diagnosis
• Model interpretation and explanation
• Shapley additive explanations (SHAP)
• Layer-wise relevance propagation (LRP)

electrolyte membrane electrolysis. to one based on clean energy requires implementing policies, stakeholders, technological adchallenges. While the UAE is clean energy, the contribution energy mix remains relatively Barakah plant) and solar (2000 constitute steps toward clean contribution to the 37 GW More support is critical to a at 8% share in 2021) under an more ambitious approach is needed to eliminate the reliance on coal, which has a 12% target by 2050. Hydrogen energy can significantly promote renewable energy adoption in hard-to-decarbonize sectors like energy-intensive industries, and utilizing solar energy for green hydrogen production can decarbonize industries such as aluminum, steel, and cement. A national hydrogen strategy is necessary to drive hydrogen energy applications and accelerate the deployment of clean hydrogen projects domestically and internationally. Credit author statement

• 单位
  重庆大学