Figure - available from: Measurement Science and Technology
This content is subject to copyright. Terms and conditions apply.
Source publication
Batch process is often characterized by multiphase and different batch durations, which varies from phase to phase presenting multiple local neighborhood features. In this paper, a sequential phase division - multiway sparse weighted neighborhood preserving embedding (SPD-MSWNPE) method is proposed for monitoring batch processes more sensitively. F...
Citations
... The paper by Zhang et al [32] proposed a batch process monitoring method based on sequential phase division multiway sparse weighted neighborhood preserving embedding (SPD-MSNPE). This method is designed to sensitively monitor batch processes characterized by multiphase and varying batch durations. ...
... The NPE algorithm, serving as a linear approximation of local linear embedding , is employed for dimensionality reduction [20,21]. Notably, recent studies have emerged focusing on enhancing the NPE algorithm, offering fresh insights and inspirations for further developments in this area [22,23]. Ai-Min Miao introduced the non-local structure neighborhood preserving embedding (NSC-NPE) algorithm with the aim of preserving both refined local variance information and meaningful non-local variance information [24]. ...
Fault detection in industrial processes is essential for enhancing production safety. Despite the application of the neighborhood preserving embedding (NPE) algorithm in fault detection as a manifold learning technique, a notable limitation exists-NPE overlooks local geometric structure, leading to suboptimal fault detection and occasional false alarms. This paper introduces the Gaussian kernel weighted NPE (KW-NPE) algorithm to address this challenge. Specifically designed for precise weight assignment in local structures, KW-NPE strategically employs the Gaussian kernel method to project the spatial neighborhood set and capture comprehensive local structural characteristics. The weight assignment, dependent on feature values, enhances the retention of intrinsic structure during dimensionality reduction. A novel objective function further augments this process.To assess performance, a comprehensive composite index is introduced in a case study, amalgamating the false alarm rate and fault detection rate. The effectiveness of the KW-NPE algorithm is demonstrated through extensive simulations and its application to the Tennessee Eastman process dataset, highlighting its superiority over conventional approaches.
Because of increasing demand and strict regulations, pharmaceutical manufacturers encounter significant hurdles in achieving high productivity while ensuring normal process states. Variability in raw materials and operational disturbances can lead to deviations from normal operating conditions that result in decreased productivity. The implementation of smart fault detection and diagnosis (FDD) techniques is crucial for attaining acceptable productivity and ensuring process safety. In this review, we identify the major challenges of smart FDD in pharmaceutical processes, and we discuss future opportunities and new perspectives.
Because of increasing demand and strict regulations, pharmaceutical manufacturers encounter significant hurdles in achieving high productivity while ensuring normal process states. Variability in raw materials and operational disturbances can lead to deviations from normal operating conditions that result in decreased productivity. The implementation of smart fault detection and diagnosis (FDD) techniques is crucial for attaining acceptable productivity and ensuring process safety. In this review, we identify the major challenges of smart FDD in pharmaceutical processes, and we discuss future opportunities and new perspectives.