Quality risks in digitalized equipment manufacturing processes are increasingly characterized by multi-source coupling, chain-like transmission, and latent evolution, making it difficult for single-method approaches alone to fully reveal their transmission mechanisms and key driving factors. This study proposes a mixed-methods framework integrating grounded theory, covariance-based structural equation modeling (CB-SEM), and XGBoost-SHAP. First, grounded theory was applied to in-depth interview data to develop a five-dimensional quality risk framework covering process design and transformation, data flow and collaboration, production execution and process control, quality inspection and data traceability, and personnel capability matching. Second, based on 420 valid questionnaire responses, CB-SEM was used to validate the chain transmission path of risks along “process design–data collaboration–production execution–inspection and traceability” and to reveal the pervasive effect of personnel capability matching risk, with indirect effects accounting for 43.5%. Finally, the XGBoost-SHAP framework was introduced to capture nonlinear and item-level effects, identifying risk items with high predictive contributions, such as the absence of pre-job certification, underlying control failures, and distorted simulation boundary conditions. By integrating qualitative construction, linear validation, and nonlinear attribution, this study provides cross-method evidence for identifying the driving factors and transmission mechanisms of quality risks in equipment digital manufacturing processes. The findings deepen the understanding of how quality risks are formed and transmitted across equipment digital manufacturing processes and provide decision support for agile and targeted digital quality control in equipment manufacturing enterprises.

Ignoring real decision contexts in linguistic multi-criteria classification (MCC) causes unreasonable weights, rank reversal and unreliable classification. This paper develops a context-constrained MCC framework integrating case-based reasoning, grey target theory and cloud model. Unlike conventional data-only grey target methods, three practical contextual features structurally reshape all algorithm modules: linguistic dual fuzziness-randomness, labeled benchmark cases and expert weight preferences. First, cloud Hamming distance and cloud-based dual target centers are constructed to eliminate rank reversal, a property invalid without linguistic uncertainty. Second, benchmark case constraints build a target-score classification mechanism with case-calibrated grading thresholds. Third, expert weight bounds form a bi-objective optimization model fusing multi-source information to avoid data-biased weights. A riparian wetland ecological grading case validates the method. A rigorous mathematical proof, counterexample contrast and large-scale random simulation are further supplemented to verify that the proposed fixed dual cloud target center rule significantly mitigates rank-reversal phenomena triggered by adding new alternatives under the designed experimental settings. Comparisons show our framework yields domain-consistent weights, grading outputs with perfect agreement with independent blind expert judgments, and stable monotonic scoring performance (where larger target scores correspond to worse ecological conditions), which achieves more consistent grading results compared with cloud entropy weighting and virtual linguistic approaches in the tested wetland case.

Faults in aero-engine rotating components account for more than 60% of total failures, and their early features are easily masked by noise under complex conditions. Traditional single-sensor diagnosis suffers from low feature utilization, poor interpretability, and weak cross-condition generalization. This paper proposes a multi-source fault diagnosis method for aero-engines based on an explainable boosted tree, integrating spatiotemporal attention (STA) and adaptive feature selection (AFS). We collect multi-domain data from four standard core sensors widely used in existing engine health management systems and extract multi-dimensional features to build a heterogeneous feature set. Adaptive feature selection is implemented using mutual information and a variance inflation factor. A spatiotemporal attention mechanism is introduced to weight and fuse features effectively. The fused features are used to train an XGBoost classifier, and SHAP values are adopted to quantify feature contributions and improve model interpretability. Uncertainty sources and sensitivity boundaries are quantitatively analyzed to support engineering acceptance. The method achieves high sensitivity to early weak faults and stable uncertainty under complex operating conditions. Tests on a fault simulation test rig show that the proposed method achieves 99.2% diagnosis accuracy and 97.5% cross-condition generalization accuracy, outperforming conventional models. It can identify early weak fault signatures, clarify key fault indicators, and provide a quantitative basis for fault tracing and maintenance decision-making. The method employs a standard sensor suite without additional hardware costs, features lightweight computation and low inference overhead, and delivers clear economic benefits by reducing false alarms, avoiding unplanned downtime, and optimizing maintenance resources. It offers a reliable, cost-effective solution for aero-engine fault diagnosis under complex operating conditions.

Quality risks in digitalized equipment manufacturing processes are increasingly characterized by multi-source coupling, chain-like transmission, and latent evolution, making it difficult for single-method approaches alone to fully reveal their transmission mechanisms and key driving factors. This study proposes a mixed-methods framework integrating grounded theory, covariance-based structural equation modeling (CB-SEM), and XGBoost-SHAP. First, grounded theory was applied to in-depth interview data to develop a five-dimensional quality risk framework covering process design and transformation, data flow and collaboration, production execution and process control, quality inspection and data traceability, and personnel capability matching. Second, based on 420 valid questionnaire responses, CB-SEM was used to validate the chain transmission path of risks along “process design–data collaboration–production execution–inspection and traceability” and to reveal the pervasive effect of personnel capability matching risk, with indirect effects accounting for 43.5%. Finally, the XGBoost-SHAP framework was introduced to capture nonlinear and item-level effects, identifying key risk drivers such as the absence of pre-job certification, underlying control failures, and distorted simulation boundary conditions. By integrating qualitative construction, linear validation, and nonlinear attribution, this study provides cross-method evidence for identifying the driving factors and transmission mechanisms of quality risks in equipment digital manufacturing processes. The findings deepen the understanding of how quality risks are formed and transmitted across equipment digital manufacturing processes and provide decision support for agile and targeted digital quality control in equipment manufacturing enterprises.