Fault detection and diagnosis to enhance safety in digitalized process system

Kopbayev, Alibek; Khan, Faisal; Yang, Ming; Halim, Syeda Zohra

doi:10.1016/j.compchemeng.2021.107609

Cited by 20 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the variation of each band signal, the regular characteristics of the signal are determined and analyzed [7], and the characteristic values of different bands are calculated, as shown in Formula (1):…”

Section: Feature Extraction Of Discharge Faults In Switchgearmentioning

confidence: 99%

Partial discharge fault detection method of switchgear based on signal aliasing spectrum separation model

Zhao,

Zhang,

Zhu

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

At present, the detection nodes of partial discharge fault in switchgear are generally set in one direction, and the fault detection range is small, which leads to an increase in the false recognition rate of partial discharge fault detection. Therefore, the design and verification analysis of the detection method of partial discharge fault in switchgear is proposed. According to the current measurement requirements and standards, firstly, the characteristics of switchgear discharge faults are extracted, and the fault detection range is expanded by the multi-step method. Multi-step partial discharge fault detection nodes are deployed, and the partial discharge fault detection model with signal aliasing and spectrum separation is constructed. The fault detection is completed by hierarchical fuzzy automatic identification. The test results show that the final detection error rate of partial discharge fault is well controlled below 20% by comparing the seven selected test cycles and combining the signal aliasing spectrum separation model, which shows that the designed detection method of partial discharge fault is more flexible and changeable, and has strong pertinence and reliability. Facing the complex switchgear operating environment, it can also mark the fault position in the shortest time, strengthen the detection results and ensure the detection accuracy.

show abstract

Section: Feature Extraction Of Discharge Faults In Switchgearmentioning

confidence: 99%

Partial discharge fault detection method of switchgear based on signal aliasing spectrum separation model

Zhao,

Zhang,

Zhu

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…14). 150 The degradation model is then converted into a state-space model using a suitable filtering algorithm to estimate and predict state variables. To predict RUL, then the model is extrapolated till the predicted states reach the allowable threshold (usually 80% of its rated capacity or 160% of its initial internal resistance).…”

Section: 114-118mentioning

confidence: 99%

Electrochemical models: methods and applications for safer lithium-ion battery operation

Sarkar

Halim

El‐Halwagi

et al. 2022

J. Electrochem. Soc.

View full text Add to dashboard Cite

Emphasis on clean energy has led to a widespread focus on lithium-ion batteries. However, a major obstacle is their degradation with several cycles or calendar aging. Battery management systems rely on an essential model-based algorithm to protect the battery from operating outside the safety limit. Thus, this work attempts to answer important research questions on battery models: Are physics-based electrochemical models (EM) robust enough to identify internal cell degradation and abnormal battery behavior? How are the structural simplifications and mathematical order reductions imposed on the EMs and what are their trade-offs? How to apply simplified EM for safer and more efficient battery operation? What are the prospects and obstacles to employing EM-based algorithms in the future? This paper presents a detailed analysis of EM from a modeling and application perspective and introduces battery operating mechanisms, typical failures, and their effects. Followed by an analysis of full order EM (Pseudo 2-Dimensional), and further classification into simpler and advanced reduced order models. The study demonstrates the gaps in theoretical understanding and their implementation for real-time battery operations such as in thermal management, energy utilization, and fault diagnosis and prognosis.

show abstract

“…Recent developments in the field of process monitoring have led to a renewed interest in ensuring operation safety in the process industry. − Model-based and data-driven methods are the two sorts of process monitoring strategies in general. Accurate process models, which are typically difficult to generate for complicated industrial processes, are required for model-based techniques.…”

Section: Introductionmentioning

confidence: 99%

Nonlinear Dynamic Process Monitoring Based on Ensemble Kernel Canonical Variate Analysis and Bayesian Inference

Wang

2022

ACS Omega

View full text Add to dashboard Cite

By considering autocorrelation among process data, canonical variate analysis (CVA) can noticeably enhance fault detection performance. To monitor nonlinear dynamic processes, a kernel CVA (KCVA) model was developed by performing CVA in the kernel space generated by kernel principal component analysis (KPCA). The Gaussian kernel is widely adopted in KPCA for nonlinear process monitoring. In Gaussian kernel-based process monitoring, a single learner is represented by a certain selected kernel bandwidth. However, the selection of kernel bandwidth plays a pivotal role in the performance of process monitoring. Usually, the kernel bandwidth is determined manually. In this paper, a novel ensemble kernel canonical variate analysis (EKCVA) method is developed by integrating ensemble learning and kernel canonical variate analysis. Compared to a single learner, the ensemble learning method usually achieves greatly superior generalization performance through the combination of multiple base learners. Inspired by the ensemble learning method, KCVA models are established by using different kernel bandwidths. Further, two widely used T 2 and Q monitoring statistics are constructed for each model. To improve process monitoring performance, these statistics are combined through Bayesian inference. A numerical example and two industrial benchmarks, the continuous stirred-tank reactor process and the Tennessee Eastman process, are carried out to demonstrate the superiority of the proposed method.

show abstract

Fault detection and diagnosis to enhance safety in digitalized process system

Cited by 20 publications

References 30 publications

Partial discharge fault detection method of switchgear based on signal aliasing spectrum separation model

Partial discharge fault detection method of switchgear based on signal aliasing spectrum separation model

Electrochemical models: methods and applications for safer lithium-ion battery operation

Nonlinear Dynamic Process Monitoring Based on Ensemble Kernel Canonical Variate Analysis and Bayesian Inference

Contact Info

Product

Resources

About