ABSTRACT Design of Experiments (DoE) studies generate valuable process knowledge during pharmaceutical development, and aggregating scientifically related studies can make this knowledge more reusable for future experimental planning. However, prior study results are often difficult to reuse because data, metadata, and statistical model outputs are stored in inconsistent formats across studies. This paper describes the development of a centralized experimental database and statistical decision‐support workflow, implemented in a data science workbench, for standardizing and compiling historical process characterization DoE studies in alignment with FAIR principles. The database captures raw data, study metadata, process parameter information, response information, and selected model artifacts, enabling cross‐study comparisons and dashboard‐based review. We demonstrate the value of this framework through a case study in which historical patterns of effect significance and co‐significance were used to inform OMARS design selection and factor‐to‐column assignment for a process characterization study. This work presents a practical statistical knowledge‐management framework that moves beyond ad hoc data reuse to support more transparent, reliable, evidence‐based experimental planning.
ABSTRACT Accurate prediction of the remaining useful life (RUL) of rolling bearings under different operating conditions remains challenging, because variations in operating conditions distort the consistency of degradation representations across domains. Existing transfer learning methods often fail to explicitly separate transferable degradation semantics from residual information associated with specific operating conditions, while insufficiently modeling the dependence of bearing degradation on stage progression. This limitation makes it difficult to preserve the intrinsic temporal structure and may result in negative transfer. Moreover, most existing methods rely on post hoc interpretation strategies that cannot impose physical constraints during forward propagation, thereby limiting model interpretability. To address these issues, this study proposes a physics‐based shared stage‐aware prototype transfer network for cross‐condition bearing RUL prediction. The proposed framework uses separate shared and specific representation branches, applies stage‐aware prototype transfer in the shared space, and performs RUL regression using their gated fusion. By combining physics‐guided representation learning with stage‐aware semantic transfer, the proposed method enhances cross‐domain consistency while improving robustness and interpretability. Experiments conducted on the XJTU‐SY bearing dataset and an accelerated bearing life test platform demonstrate that the proposed method achieves superior prediction performance and satisfactory cross‐platform generalization capability. The results indicate that separating the transfer of shared degradation semantics from the final RUL regression provides an effective and interpretable approach for cross‐condition bearing RUL prediction.
ABSTRACT Gearboxes play a vital role in numerous industrial machines that include wind turbines, automotive transmissions, manufacturing systems, etc. Heavy mechanical and continuous operation result in different types of faults such as cracks, tooth breakage, and gear wear. Early detection of these faults is essential to reduce maintenance costs, machine failures, and production downtime. Hence, reliable gearbox fault diagnosis has become a significant research area in intelligent condition monitoring. To address such shortcomings, this paper proposes a novel graph‐integrated selective state space fault network (GSS‐FaultNet) for gearbox fault diagnosis using vibration signal analysis. The proposed model initially performs signal preprocessing to enhance data quality. The comprehensive fault features generate time domain and frequency domain representations. A graph construction module is introduced to model the structural relationship among gearbox components as well as sensor locations. Simultaneously, a selective state space module effectively captures long‐range temporal dependency from various sequential vibration signals. Finally, the extracted temporal features are fused via a feature integration layer, followed by a fully connected layer for classifying faults. Thus, the hybrid architecture enables the model to capture the temporal dynamics and structural interactions of gearbox behavior. Experimental validation demonstrates that the proposed GSS‐FaultNet framework attains enhanced fault classification accuracy. The results indicate that the proposed model enhances the capability of gearbox health monitoring systems. The proposed model demonstrates an effective capability to learn both temporal and structural features, achieving the highest accuracy of 97.7%.
ABSTRACT This study is devoted to the estimation of the process capability index (PCI), , within the framework of the Fréchet distribution in the purview of modified version of a multiple interval type‐I censoring scheme. The estimation of is approached through three distinct methodologies: maximum likelihood estimation, maximum product spacing estimation, and a Bayesian framework. In the Bayesian paradigm, independent gamma priors are specified, and Bayes estimators of are derived under the squared error loss, general entropy loss and the LINEX loss functions. Inference is further augmented by constructing asymptotic confidence intervals and highest posterior density intervals. A comprehensive simulation study is undertaken to evaluate the finite‐sample performance of the proposed estimators in terms of mean squared error. Moreover, an optimal censoring scheme from a collection of potential schemes under various censoring scenarios has been investigated. The practical efficacy of the proposed methodologies is illustrated through the analysis of a real‐world data set.
ABSTRACT The integration of artificial intelligence into industrial quality control (QC) and management encompassing automated defect detection, real‐time process monitoring, and zero‐defect manufacturing has generated a rapidly expanding yet fragmented research landscape. This study addresses the need for comprehensive mapping of quality and reliability engineering practice through a computational systematic review of 9618 publications spanning the 2020–2025 period. A hybrid natural language processing (NLP) pipeline combining FlashText, Sentence‐BERT, KeyBERT, and spaCy performs semantic extraction of AI architectures, learning paradigms, defect typologies, and deployment contexts. The review pursues three objectives: mapping the architectural evolution of deep learning in industrial inspection, characterizing operational challenges of AI‐driven manufacturing, and identifying methodological frontiers for improving production reliability and supporting intelligent quality assurance (QA) systems. Results reveal that AI‐based quality control advances through coevolution of neural architectures, learning paradigms, and deployment requirements. CNNs remain central to discriminative visual inspection, while Transformers extend capabilities for multimodal reasoning. The field exhibits strong bias toward surface defects while overlooking safety‐critical internal defects. Emerging trends show transition from algorithm‐centric research toward deployment‐oriented paradigms including Uncertainty Quantification, Edge AI, Explainable AI, and Digital Twins. This work provides practitioners with an evidence‐based foundation for developing reliable, scalable AI quality systems aligned with Industry 4.0 principles.
