Thermal behavior and fire reaction properties of aerial glass fiber (GF)/bismaleimide (BMI) composites were tested using thermogravimetric analysis (TGA), thermogravimetric coupled with Fourier transform infrared spectroscopy (TG-FTIR), cone calorimeter, limiting oxygen index, and smoke density chamber. The results showed that the pyrolysis process was one stage in a nitrogen atmosphere with the prominent volatile components of CO₂, H₂O, CH₄, NO_x, and SO₂. The release of heat and smoke increased with the increase in heat flux, while the time required to reach hazardous conditions decreased. The limiting oxygen index decreased monotonically from 47.8% to 39.0% with increasing experimental temperature. The maximum specific optical density within 20 min in the non-flaming mode was greater than that in the flaming mode. According to the four kinds of fire hazard assessment indicators, the greater the heat flux, the higher the fire hazard, for the contribution of more decomposed components. The calculations of two indices confirmed that the smoke release in the early stage of fire was more negative under flaming mode. This work can provide a comprehensive understanding of the thermal and fire characteristics of GF/BMI composites used for aircraft.

This paper discusses the predictive maintenance (PM) problem of a single equipment system. It is assumed that the equipment has deteriorating quality states as it operates, resulting in multiple yield levels represented as system observation states. We cast the equipment deterioration as discrete-state and continuous-time semi-Markov decision process (SMDP) model and solve the SMDP problem in reinforcement learning (RL) framework using the strategy-based method. In doing so, the goal is to maximize the system average reward rate (SARR) and generate the optimal maintenance strategy for given observation states. Further, the PM time is capable of being produced by a simulation method. In order to prove the advantage of our proposed method, we introduce the standard sequential preventive maintenance algorithm with unequal time interval. Our proposed method is compared with the sequential preventive maintenance algorithm in a test objective of SARR, and the results tell us that our proposed method can outperform the sequential preventive maintenance algorithm. In the end, the sensitivity analysis of some parameters on the PM time is given.