Bearing fault diagnosis remains challenging when models trained on one set of machines are applied to equipment with different bearing geometries, operating speeds, and vibration characteristics. Conventional evaluation protocols often overestimate cross-machine performance, while prediction uncertainty becomes difficult to calibrate under machine-level distribution shift. This study investigates whether geometry-anchored fault features and machine-level conformal calibration can jointly improve diagnostic accuracy and prediction-set reliability on previously unseen machines. A structured review was conducted to identify methodological gaps, followed by controlled simulations involving eight machines with different bearing geometries, shaft speeds, sampling rates, structural resonances, and noise conditions. Three feature representations and four calibration schemes were evaluated using a leave-one-machine-out protocol. The geometry-anchored representation achieved a mean classification accuracy of 0.908 $\pm$ 0.014, compared with 0.585 $\pm$ 0.016 and 0.575 $\pm$ 0.023 for frequency-domain and order-domain features, respectively. Random window splitting overestimated the accuracy of these baselines by 0.25 and 0.29. At a nominal coverage level of 90%, machine-level conformal calibration achieved mean coverage between 0.903 and 0.931, compared with 0.642–0.879 for conventional split calibration. With geometry-anchored features, the calibrated prediction sets contained 0.99 classes on average, whereas the other representations required 2.77–2.96 classes. Conservative calibration increased worst-machine coverage from 0.751 to 0.866, although individual-machine coverage remained variable. The results indicate that physically indexed fault features and machine-level calibration address complementary aspects of cross-machine diagnosis: the former improves fault discrimination, while the latter supports more reliable marginal coverage under machine shift. The study establishes a controlled evaluation framework for examining diagnostic generalization and uncertainty calibration at the machine level, providing a methodological basis for subsequent validation using experimental and industrial bearing data.

Industrial intelligence relies on the integration of industrial software, interconnected production systems, digital twins, and artificial intelligence (AI) to support data-driven monitoring, predictive analysis, and operational decision-making. Despite advances in these technologies, differences in technological maturity, system interoperability, and engineering trustworthiness remain obstacles to their coordinated deployment. This study investigates the relationships among the principal technologies underlying industrial intelligence, with particular attention to their functional dependencies, implementation constraints, and capacity to support reliable industrial operations. A structured literature review was conducted using a corpus comprising 55 peer-reviewed publications and 29 supplementary technical and institutional sources. Industrial software, the industrial Internet, digital twins and digital threads, and industrial AI were examined through a common framework covering seven dimensions of technological and engineering readiness. The comparative analysis identified two recurring categories of deployment constraints. Industrial software and the industrial Internet were primarily constrained by the accumulation of domain-specific knowledge, legacy-system compatibility, and heterogeneous data interoperability. For digital twins and industrial AI, the review identified additional challenges concerning model verification, uncertainty assessment, and the integration of intelligent decisions into industrial processes. The analysis further identified interdependent requirements for data consistency, mechanism-based modeling, computational resources, and closed-loop decision execution. These findings indicate that the engineering readiness of industrial intelligence depends not only on the maturity of individual technologies but also on the reliability of their interactions within integrated production systems. The study establishes a system-level perspective for assessing industrial intelligence technologies and provides a structured basis for identifying integration bottlenecks, evaluating engineering trustworthiness, and directing research toward verifiable industrial decision-making.

Accurate remaining useful life (RUL) prediction of rolling bearings is essential for predictive maintenance and reliable operation of industrial rotating machinery. However, variations in operating conditions introduce substantial differences in vibration characteristics and degradation patterns, limiting the applicability of models trained under individual operating conditions. This study investigates a multi-source transfer learning approach for bearing RUL prediction across different operating conditions. A framework termed deep residual shrinkage network with multi-source weighted screening (DRSN-MW) was developed by integrating a deep residual shrinkage network with multi-source domain screening, subdomain alignment, and physical monotonicity constraints. An adaptive feature extraction module was constructed to capture degradation characteristics from vibration signals, while weighted extension correlation and dynamic time warping (DTW) were combined to identify source domains with similar degradation patterns. Degradation-stage partitioning and entropy-weighted local maximum mean discrepancy (LMMD) were employed to align source and target features within corresponding degradation stages. Physical monotonicity and decision consistency constraints were further incorporated to regulate the predicted RUL trajectories. The framework was evaluated using the 2012 Prognostics and Health Management (PHM2012) bearing dataset and Xi’an Jiaotong University–Sumyoung (XJTU-SY) bearing dataset under single-source and multi-source transfer scenarios. Average mean absolute errors (MAEs) of 0.126 and 0.129 and root mean square errors (RMSEs) of 0.150 and 0.156 were obtained on the two datasets, respectively. On the PHM2012 dataset, the proposed method reduced the average root mean square error by 33.6% compared with the strongest baseline in the reported comparison. The results indicate that combining source-domain screening with degradation-stage alignment and physical constraints can improve RUL prediction across operating conditions. The proposed framework provides a data-driven approach to bearing health prognostics and predictive maintenance in industrial rotating machinery.

Human-robot interaction has become a fundamental component of Industry 5.0. Although recent advances in generative artificial intelligence have substantially improved contextual reasoning and interactive capabilities, existing human-robot interaction decision-making frameworks remain predominantly task-oriented and rarely account for human emotional responses during collaborative decision processes. To address this limitation, a regret-based human-robot interaction framework driven by generative artificial intelligence was proposed for adaptive decision-making in Industry 5.0 environments. A dual-regret mechanism was introduced by jointly modeling human regret $\left(R_h\right)$ and robot task regret $\left(R_{t r}\right)$. Contextual knowledge was dynamically retrieved through a retrieval-augmented generation architecture, enabling interaction strategies to be generated according to task conditions, historical user preferences, and evolving human emotional states. Personalized regret profiles were constructed, while explainable counterfactual action generation was incorporated. Furthermore, real-time reinforcement learning was employed to continuously minimize cumulative regret. Experimental evaluations conducted under multiple interaction scenarios demonstrated that the proposed framework effectively improved decision quality, enhanced user satisfaction, and increased task execution efficiency. Compared with conventional human-robot interaction decision-making approaches, cumulative interaction regret was reduced by approximately 20%, while greater robustness and adaptability were achieved under dynamically changing operational conditions. These findings suggest that the proposed framework provides an effective paradigm for integrating emotional intelligence, generative reasoning, and adaptive optimization into human-centered robotic systems, thereby offering a promising decision-making architecture for next-generation collaborative robotics in Industry 5.0.

Prediction of product life cycle (PLC) at the early stage is important to support the planning of production, inventory control, launch timing, and decisions of product renewal. However, newly introduced batik products often have little historical sales data; therefore, it is difficult to apply conventional forecasting methods. This study introduced the Diffusion Bubble Model for Product Diffusion (DBM-PD) as a low-data diffusion model for predicting cumulative product adoption in batik fashion small and medium enterprises (SMEs). The DBM-PD adapts the bubble-decomposition logic into a product diffusion context, where each adoption bubble represents a possible market response at a specific stage of the PLC. To assess the model performance, this study compared the DBM-PD with three benchmark models: the Bass Diffusion Model, Triangle Model, and Circle Model. Four datasets of PLC from batik fashion products were used as empirical cases. Each dataset was transformed into a cumulative adoption ratio to ensure comparable model evaluation. The results showed that the DBM-PD achieved the lowest prediction error across all four datasets. The Bass Diffusion Model ranked second, indicating that innovation and imitation effects remain relevant in batik product adoption. The Triangle and Circle Models were useful as simple geometric benchmarks, but their assumptions were less able to capture irregular adoption patterns. These findings revealed that the DBM-PD could establish a more flexible prediction structure for estimating PLC at the early stage when only limited data were available. A parameter sensitivity check discovered that the number and width of bubbles affected in-sample accuracy: additional bubbles could reduce errors but also increased model complexity, while the seven-bubble, $\sigma=0.08$ configuration offered a transparent balance between accuracy and parsimony. The root mean square error (RMSE) rankings were identical across the four datasets, and a Friedman test indicated a significant overall difference among the models $\left(\chi^2(3)=12.00, p=0.007\right)$. This study contributes to the management of technology-based PLC by offering a practical framework of diffusion modelling for batik fashion SMEs.

Traditional public health disinfection tasks relying on fixed-area coverage often suffer from resource waste, delayed intervention, and low response efficiency. This study proposes a case-density-driven closed-loop intelligent strategy for air-ground-human collaborative disinfection, establishing an end-to-end framework from case perception to task scheduling. Firstly, a spatiotemporal risk field is constructed based on reported case data and population mobility information, and high-risk areas are adaptively identified and prioritized through dynamic evaluation. Secondly, for coordinated execution by unmanned aerial vehicles (UAVs), ground vehicles, and personnel, a multi-objective coupled optimization model is designed, targeting coverage efficiency, suppression timeliness, path conflicts, and resource cost to generate executable collaborative schedules. Furthermore, a closed-loop execution mechanism is developed, enabling real-time rolling re-planning and adaptive strategy correction in response to task feedback, unexpected disturbances (area lockdown, equipment failure, chemical shortage), and risk field updates. Experimental results demonstrate that the proposed closed-loop approach significantly improves coverage, suppression time, and resource utilization compared with traditional static scheduling and single-entity planning methods across multiple scenarios, and exhibits robustness against environmental uncertainties and resource disturbances. This framework provides a feasible theoretical and methodological foundation for intelligent, precise, and resilient public health disinfection operations.