Statistical approaches and artificial neural networks for process monitoring

Alauddin, Md.; Arunthavanathan, Rajeevan; Amin, Md. Tanjin; Khan, Faisal

doi:10.1016/bs.mcps.2022.04.003

Cited by 5 publications

(8 citation statements)

References 208 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The aim of using ANN is to mode identification when real-time data come. ANN and its variances have ample applications in process monitoring. ,, Interested readers are referred to refs − to know how they can be applied to solve classification problems (e.g., fault diagnosis and mode identification). For each operating mode, the following substeps are performed.…”

Section: Methodology For Dynamic Process Safety Assessmentmentioning

confidence: 99%

“…Integrating FDD modules with failure prediction models can efficiently measure dynamic risk. Due to its efficacy, multivariate data-driven process monitoring has received much attention compared to its univariate counterparts in the past few decades …”

Section: Introductionmentioning

confidence: 99%

“…Due to its efficacy, multivariate data-driven process monitoring has received much attention compared to its univariate counterparts in the past few decades. 9 The conventional multivariate process monitoring schemes could not show the risk associated with a fault. To address this issue, Zadakbar et al 10 proposed a multivariate data-driven fault detection and DRA method using the principal component analysis (PCA).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dynamic Process Safety Assessment Using Adaptive Bayesian Network with Loss Function

Amin

Khan

2022

Ind. Eng. Chem. Res.

Self Cite

View full text Add to dashboard Cite

Fault detection and diagnosis (FDD) is crucial for dynamic process safety analysis. Integrated with failure prediction models, it enables us to realize how a deviation in process variable(s) can affect system safety (measured as risk). This work aims to overcome the challenges of nonlinear, non-Gaussian, and multimodal behavior of the processing systems to detect abnormal process operations, predict dynamic operational risk, and diagnose root cause of the abnormal situation. A methodology is proposed here by integrating different techniques. The artificial neural network (ANN) is used to identify process modes, while the Bayesian network (BN) is used for fault detection. How a fault will lead to a process failure is modeled using the event tree (ET), whereas time-dependent losses associated with the failure scenarios are assessed using the inverted normal loss function (INLF). A probability adaption mechanism is used to estimate the conditional probabilities in each time slice. The complexity of estimating conditional probabilities is handled using the copula theory. The proposed framework is validated using numerical, simulated, and industrial datasets. The results suggest that the developed framework can provide greater flexibility and wider applications.

show abstract

Section: Methodology For Dynamic Process Safety Assessmentmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Process Safety Assessment Using Adaptive Bayesian Network with Loss Function

Amin

Khan

2022

Ind. Eng. Chem. Res.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Data‐driven models are suitable for large‐scale digitalized process operations and find the hidden features in highly correlated process variables to develop a monitoring model that is used for FDD. Some widely used data‐driven techniques currently being explored are principal component analysis (PCA), artificial neural networks, and Gaussian mixture models 8,9 . Compared to the other models, PCA is mostly used due to lower data requirements to build the monitoring model 10,11 .…”

Section: Introductionmentioning

confidence: 99%

“…Gaussian mixture models. 8,9 Compared to the other models, PCA is mostly used due to lower data requirements to build the monitoring model. 10,11 It is a dimensionality reduction technique used to represent the variance of an entire dataset using only a few variables to reduce computational requirements and demonstrate the correlation among different individual variables.…”

mentioning

confidence: 99%

Process safety analysis using operational data and Bayesian network

Daley

Khan

Amin

2023

Process Safety Progress

Self Cite

View full text Add to dashboard Cite

Fault detection and diagnosis (FDD) methods have recently experienced significant advances. These methods provide valuable information from an abnormal situation management perspective. However, traditional FDD methods do not consider system failure analysis, which is required from the process safety perspective. This work seeks to overcome this barrier and presents a methodology to assess process system failure probability based on process operational data and system knowledge. The methodology is built using the principal component analysis (PCA) and a Bayesian network (BN). The PCA is used for FDD, while the BN determines the probability of system failure once a fault is detected. This portion of the network is based on the logical relationship of the data, operational thresholds, and system failure conditions.The proposed methodology is tested and verified on a level-controlled tank system and the real-life failure scenario of the 2010 Tesoro heat exchanger explosion. The results suggest that the proposed methodology helps to assess process system failure probability based on process operating conditions. The current work is expected to give a stimulus on digital process safety education.

show abstract

Process safety 4.0: Artificial intelligence or intelligence augmentation for safer process operation?

Arunthavanathan,

Sajid,

Amin

et al. 2024

AIChE Journal

Self Cite

View full text Add to dashboard Cite

The growth of artificial intelligence (AI) has allowed industries to automate and improve their efficiency in operations. Especially in process industries, AI helps to develop intelligent models and tools to proactively monitor and predict equipment or system failures, minimize downtime, and optimize maintenance schedules. With the advancements in AI and its ability to perform tasks, there is a growing belief that AI may eventually replace humans. However, the absence of human involvement in operations in the process industry raises safety concerns. Therefore, AI should collaborate with humans rather than replace them in processing facility operations. This technology is referred to as intelligence augmentation (IA). This article (i) presents a detailed comparison between AI and IA's potential in process systems, (ii) identifies the feasibility of using AI and IA in process safety, and (iii) identifies the risk associated with the implementation of AI or IA in process industries.

show abstract

Statistical approaches and artificial neural networks for process monitoring

Cited by 5 publications

References 208 publications

Dynamic Process Safety Assessment Using Adaptive Bayesian Network with Loss Function

Dynamic Process Safety Assessment Using Adaptive Bayesian Network with Loss Function

Process safety analysis using operational data and Bayesian network

Process safety 4.0: Artificial intelligence or intelligence augmentation for safer process operation?

Contact Info

Product

Resources

About