An effective strategy for online safety assessment is the guarantee and fundamental to ensuring the safe and stable operation of industrial systems. However, in increasingly dynamic and complex industrial systems, operational condition transitions and production state changes may cause the probability density function (PDF) to exhibit notable irregularities or even severe collapse. This renders the conventional methods for process safety index calculation no longer applicable, let alone conducting online safety assessments based on the process safety index. To solve the problem, a modified process safety index calculation method based on the Gaussian mixture variational autoencoder (GMVAE) is proposed in this article. This method, through the nonlinear capability of GMVAE, transforms the irregular PDFs into Gaussian-distributed PDFs in the latent space, and then denotes the probability within the safety region determined by the PDFs as the process safety index. Afterward, the process safety index calculated in the latent space is mapped back to the original feature space for safety assessment in real-world scenarios. Finally, the experimental case is designed on the actual industrial process to verify and validate the effectiveness and superiority of the proposed method.

PanTS is a large-scale, multi-institutional dataset curated to advance research in pancreatic CT analysis. It contains 36,390 CT scans from 145 medical centers, with expert-validated, voxel-wise annotations of over 993,000 anatomical structures, covering pancreatic tumors, pancreas head, body, and tail, and 24 surrounding anatomical structures such as vascular/skeletal structures and abdominal/thoracic organs. Each scan includes metadata such as patient age, sex, diagnosis, contrast phase, in-plane spacing, slice thickness, etc. AI models trained on PanTS achieve significantly better performance in pancreatic tumor detection, localization, and segmentation than those trained on existing public datasets. Our analysis indicates that these gains are directly attributable to the 16× larger-scale tumor annotations and indirectly supported by the 24 additional surrounding anatomical structures. As the largest and most comprehensive resource of its kind, PanTS offers a new benchmark for developing and evaluating AI models in pancreatic CT analysis.

Multi variables, complex correlation and nonlinear characteristic bring challenge to plant-wide process monitoring. In this study, a distributed kernel-global and local preserving projection (distributed KGLPP) algorithm is proposed for distributed process monitoring. First, large-scale process variables are decomposed into different blocks with mutual information. Secondly, the kernel global and local preserving projection (KGLPP) algorithm is applied into every block to detect the fault. Third, support vector data description (SVDD) is introduced to integrate the local detection results of every block and provide the global detection result. The proposed method considers nonlinear relationship of variables and simplified the calculation of fault detection. The feasibility and performance of proposed method are verified with Tennessee Eastman benchmark.

The applications of barrier functions to safety analysis, diagnosis, and control have become a popular re-search direction. Barrier functions have been widely applied to solve the safety problems for different types of integer-order systems. This paper starts to discuss the relationship between barrier function and system state-safety for fractional-order nonlinear dynamical systems. First, by using Caputos fractional derivative, this paper revisits the safety theories via barrier functions (BFs). And based on less-zero barrier function, reciprocal barrier function and zeroing barrier function, three extended BFs under the Caputo fractional-order descriptions are designed. Then it establishes a framework by proposing the definitions and criteria of safety, safety-and-stability for a class of fractional-order nonlinear dynamical systems.