The fault diagnosis of rolling bearing acoustic radiation signals holds significant importance in industrial equipment maintenance. It effectively prevents equipment failures and downtime, ensuring the smooth operation of the production process. Compared with traditional vibration signals, acoustic radiation signals have the advantage of non-contact measurement. They can diagnose faults in special conditions where sensors cannot be installed and provide more comprehensive equipment status information. Therefore, to extract the fault characteristic information of rolling bearings from complex acoustic signals, this paper proposes an advanced deep learning model combining Gramian Angular Field (GAF), ResNet1D, ResNet2D, and multi-head attention mechanism, named CRAMNet (Combined ResNet Attention Multi-Head Net), to diagnose the faults of rolling bearing acoustic radiation signals. Firstly, this method includes converting one-dimensional signals into GAF images and performing data standardization and segmentation. Then, the method utilizes ResNet1D to extract features from one-dimensional signals and ResNet2D to extract features from GAF images. Further, it combines the multi-head attention mechanism to enhance feature representation and capture dependencies between different channels. Finally, this paper compares the proposed method with several traditional models (including CNN, LSTM, DenseNet, and CNN-Transformers). Experimental results show that the proposed method performs outstandingly in terms of accuracy and robustness. The combination of residual networks and multi-head attention mechanism in the model significantly enhances its ability to accurately diagnose rolling bearing faults, proving the superiority of the algorithm.

Urban regeneration of industrial heritage increasingly depends not only on physical conservation and functional redevelopment but also on the creation of experiential and affective value. Drawing on the stimulus–organism–response (SOR) framework, this study examines the relationships among multisensory experience (MSE), place attachment (PA), and district-level branding-related outcomes (DBROs), including the mediating role of PA and potential differences between tourists and residents. The analysis included 653 valid responses from tourists and residents who had visited Zhengzhou Ersha Cultural and Creative Park in Henan, China. We analyzed the data using confirmatory factor analysis, structural equation modeling, bootstrapped mediation analysis, and multi-group analysis in IBM SPSS Amos 24. The results showed that MSE was positively associated with both PA and DBROs, while PA was positively associated with DBROs and partially mediated the relationship between MSE and DBROs. The direct relationship between MSE and DBROs was stronger among tourists, whereas the relationship between PA and DBROs was stronger among residents. These findings extend the SOR framework to adaptively reused industrial heritage districts and highlight the mediating role of PA in the relationship between sensory experience and branding-related responses. They further indicate that differentiated experience-management approaches may be appropriate for tourists and residents.

Against the backdrop of the digital economy, the deep integration of artificial intelligence and Internet of Things technologies has driven the rapid adoption of smart home appliances, providing new pathways for energy conservation, emissions reduction, and sustainable consumption in households. However, the psychological mechanisms underlying the transformation of smart home appliance technology perceptions into sustainable consumption behaviors—particularly the serial mediating roles of perceived value and perceived consumer effectiveness—remain to be thoroughly investigated. Based on the SOR theory, a research model was constructed with perceived usefulness and perceived ease of use as stimulus variables, perceived value and perceived consumer effectiveness as organism variables, and sustainable consumption behavior as the response variable. Empirical analysis was conducted using SmartPLS based on 508 valid questionnaires. The results indicate that the model exhibits good explanatory power (R² = 50.4%), with significant positive relationships among all variables. Among these, perceived usefulness has a positive association with perceived value; perceived value is significantly associated with perceived consumer effectiveness; and perceived consumer effectiveness has a significant direct association with sustainable consumption behavior. Furthermore, perceived value and perceived consumer effectiveness play significant mediating and serial mediating roles. This study reveals the psychological transmission mechanism through which the perceived technology of smart home appliances influences sustainable consumption behavior, expands the application of SOR theory, and provides a theoretical basis and practical guidance for smart home appliance companies to formulate green marketing strategies oriented toward value enhancement and efficacy strengthening.

Cultural heritage preservation is essential to sustainable development, yet fragmentary remains at archaeological sites limit visitors’ understanding of their significance. Augmented reality (AR) can enrich heritage interpretation and visitor experience. However, the psychological pathways linking visitors’ evaluations of the physical environment and AR content to heritage conservation intention remain insufficiently understood. Based on stimulus–organism–response theory, Tangibles and AR content quality are modeled as external stimuli in this study, with experiential authenticity and place attachment as mediators and heritage conservation intention as the outcome. Survey data from 635 visitors who used the Mojiaoshan Pilgrimage Route AR Experience at Liangzhu Ancient City Ruins Park were analyzed using partial least squares structural equation modeling (PLS-SEM). Tangibles and AR content quality were positively associated with experiential authenticity. In the baseline model, Tangibles also showed a weak direct association with place attachment, whereas AR content quality showed no significant direct association with attachment and was related to it mainly through experiential authenticity. Both stimuli showed significant indirect associations with heritage conservation intention through experiential authenticity and place attachment, consistent with the proposed theoretical pathway. Place attachment showed a stronger direct association with heritage conservation intention than experiential authenticity. The hypothesized moderating effect of Tangibles on the relationship between AR content quality and experiential authenticity was nonsignificant. These findings highlight the positive associations of both physical and digital quality evaluations with experiential authenticity, underscoring the roles of experiential authenticity and place attachment in understanding heritage conservation intention. The findings also inform site maintenance and AR content design; whether these associations translate into actual conservation behavior remains to be validated.