In this paper, a Transformer-based fast Monte Carlo reliability evaluation method for integrated energy systems is proposed. First, the faults of the system components are sampled and the corresponding minimum cut load amounts are calculated to obtain the sample data for training the machine learning model. Then, Transformer is used as a machine learning algorithm for mining the nonlinear mapping relationship between system component faults and the minimum cut load, and the estimation model of the minimum cut load under different faults is trained. Finally, the model is combined with Monte Carlo simulation method to randomly sample component states, and for each state, the minimum cut load amount is directly given by the trained estimation model, thus realizing fast evaluation of integrated energy system fast reliability. The proposed method is applied to the integrated energy system test case, which verifies its effectiveness.

Polyion complex (PIC) materials have been widely used in biosensors due to their molecular selectivity. However, achieving both widely controllable molecular selectivity and long-term solution stability with traditional PIC materials has been challenging due to the different molecular structures of polycations (poly-C) and polyanions (poly-A). To address this issue, we propose a novel polyurethane (PU)-based PIC material in which the main chains of both poly-A and poly-C are composed of PU structures. In this study, we electrochemically detect dopamine (DA) as the analyte and L-ascorbic acid (AA) and uric acid (UA) as the interferents to evaluate the selective property of our material. The results show that AA and UA are significantly eliminated, while DA can be detected with a high sensitivity and selectivity. Moreover, we successfully tune the sensitivity and selectivity by changing the poly-A and poly-C ratios and adding nonionic polyurethane. These excellent results were employed in the development of a highly selective DA biosensor with a detection range from 500 nM to 100 μM and a 3.4 μM detection limit. Overall, our novel PIC-modified electrode has the potential to advance biosensing technologies for molecular detection.