The rapid development of big data technology and machine learning has increasingly focused attention on fault diagnosis in complex chemical processes. However, data-driven approaches often overlook the inherent physical correlations within the system and lack a robust mechanism for providing trusted explanations for fault diagnosis. To address this challenge, a graph-based fault diagnosis model framework is proposed along with a dependable fault node diagnosis analysis method. In order to enhance the extraction of chemical process features from a spatial perspective, a graph convolution network (GCN)-based node spatial encoding module is integrated. The construction of the adjacency matrix involves combining a priori knowledge of chemical processes with Pearson correlation, thereby incorporating the physical correlations between nodes. Simultaneously, to capture temporal dependencies in fault data, a spatiotemporal feature fusion module based on the long short-term memory network (LSTM) is employed. In terms of model training, a dual-supervision strategy is adopted to ensure stable convergence of the multiclass fault diagnosis model. For model inference, a multi-model voting strategy is designed to mitigate accuracy degradation resulting from model prediction bias. To tackle the interpretability challenge, a fault diagnosis analysis method based on node masking is designed, effectively identifying critical nodes contributing to system faults. Experimental validation on the Tennessee Eastman process demonstrates the effectiveness of the proposed model, achieving high accuracy in fault diagnosis. The average fault diagnosis rate for all fault types reaches 0.9844, showcasing state-of-the-art performance in fault diagnosis.

Molecular dynamics (MD) simulations are invoked to simulate the diffusion process and microstructural evolution at the solid–liquid, cast-rolled Al–Cu interfaces. K-Means clustering algorithm is used to identify the formation and composition of two types of nanostructural features in the Al-rich and Cu-rich regions of the interface (i.e., the intermetallic Al₂Cu near the Al-rich interface and the intermetallic Al₄Cu₉ near the Cu-rich interface). MD simulations are also used to assess the effects of annealing temperature on the evolution of the compositionally graded microstructural features at the Al–Cu interfaces and to characterize the mechanical strength of the Al–Cu interfaces. It is found that the failure of the Al–Cu interface takes place at the Al-rich side of the interface (Al₂Cu–Al) which is mechanically weaker than the Cu-rich side of the interface (Cu–Al₄Cu₉), which is also verified by the nanoindentation studies of the interfaces. Centrosymmetry parameter analyses and dislocation analyses are used to understand the microstructural features that influence deformation behavior leading to the failure of the Al–Cu interfaces. Increasing the annealing temperature reduces the stacking fault density at the Al–Cu interface, suppresses the generation of nanovoids which are precursors for the initiation of fracture at the Al-rich interface, and increases the strength of the interface.

In order to improve the flow state of the heater shell side and enhance the performance evaluation of the heater, this paper proposes a perforated plate-type heater model. Based on Fluent, numerical studies are conducted on the heat transfer performance and shell-side fluid flow characteristics of a perforated plate-type heater. The variations of the heat transfer factor Nu, friction factor f, and evaluation parameter Nu/f(1/3) are analyzed for different helix angles ss and ratios of the long and short semiaxes of the circular holes on the heating plate under different Reynolds numbers Re. The results reveal that under the same shell-side Reynolds number Re, the heat transfer factor Nu shows an increasing trend with the increase in the proportion of the helix angle ss. The heat transfer factor Nu for the heating plate with the hole shape ratio a/b = 1 does not exhibit significant improvement compared to hole shape ratios a/b = 0.8 and a/b = 0.6, but it increases by 4.87 to 7.07% compared to the hole shape ratio a/b = 0.4 in the perforated plate-type heater. On the other hand, the friction factor f decreases as the helix angle ss and the ratio of hole shapes on the heating plate increase. The lowest friction factor f is observed for the helix angle ss of 25 degrees and the hole shape ratio a/b = 1 in the perforated plate-type heater. When the helix angle ss is 25 degrees and the hole shape ratio is a/b = 1, the evaluation parameter Nu/f(1/3) reaches its highest value, indicating the optimal overall performance of the perforated plate-type heater.

Aiming at the problems of low precision, low search efficiency, and being easy to fall into local optimization of the multi-objective harris hawk optimization algorithm (MOHHO) based on grid method, a MOHHO based on blank angle region enhanced search (BARESMOHHO) is proposed. The main changes of the algorithm are as follows: firstly, chaotic mapping is used to initialize the population, which is beneficial to speed up the search. Then, in order to find low-density regions faster, the algorithm adjusts the classification level according to the number of individuals in the external archive. In order to make the distribution of individuals in the target space more uniform, inspired by the idea of symmetrical segmentation, the number of archives at different levels are symmetrically distributed. Finally, it strengthens the search for the non-individual region (blank angle region) in the process of division. The effectiveness of the proposed algorithm is verified by comparing it with some known classical functions on test functions.