Prediction of structural mechanical properties of energy-saving materials for solar photovoltaic photo-thermal system based on deep learning

In order to study the annual operating efficiency of solar photovoltaic/photo-thermal collectors, this paper proposes a prediction of structural mechanical properties of energy-saving materials for solar photovoltaic photo-thermal systems based on deep learning. Based on the test data of a solar photovoltaic module, the performance of photovoltaic photo-thermal module is evaluated from the perspectives of the First law of thermodynamics, the Second law of thermodynamics, power generation efficiency and heat collection efficiency. The experimental results show that the working temperature difference increases from 6.8 K to 45.3 K, the normalized temperature difference increases from to, and the power generation efficiency decreases from 0.105 to 0.095 by 0.010, the percentage of change is 9.4%, the heat collection efficiency is reduced from 0.4534 to 0.2120 by 0.2414, and the reduction rate is 53%, compared with the generation efficiency and heat collection efficiency, the efficiency changes during the test period are relatively small. In conclusion for photovoltaic/photo-thermal components, environmental parameters have a greater impact on the heat collection efficiency.