A unified causation prediction model for aboveground onshore oil and refined product pipeline incidents using artificial neural network

Kumari, Pallavi; Wang, Qingsheng; Khan, Faisal; Kwon, Joseph

doi:10.1016/j.cherd.2022.09.022

Cited by 10 publications

(11 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each cause, another ANN model was developed to predict the sub-cause of the incident. The integration of cause and sub-cause prediction models enabled the efficient causation prediction of incidents …”

Section: Introductionmentioning

confidence: 99%

“…The integration of cause and sub-cause prediction models enabled the efficient causation prediction of incidents. 12 Some models solve industrial production problems by combining multiple data-driven approaches, such as a realtime hybrid method based on PCA and Bayesian belief network, 13 and limited diagnostic information from kernel PCA, other online fault detection and diagnostic tools, and process knowledge combined through Bayesian belief network. 14 Amin proposed an integrated method for process fault detection and diagnosis and propagation pathway identification, which can detect the fault earlier and ensure the correctness of the diagnosis.…”

Section: Introductionmentioning

confidence: 99%

“…The integration of cause and sub-cause prediction models enabled the efficient causation prediction of incidents. 12 …”

Section: Introductionmentioning

confidence: 99%

“…12) where σ() is the sigmoid activation function; tanh() is the hyperbolic tangent function; w i , w f , w g , and w o are the weights of each gating unit; b i , b f , b g , and b o are the bias of each gating unit; and ⊙ is the Hadamard product. Additional LSTM details are in Piyush Agarwal et al37 2.5.2.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Yield and Properties Prediction Based on the Multicondition LSTM Model for the Solvent Deasphalting Process

et al. 2023

View full text Add to dashboard Cite

Solvent deasphalting (SDA) is a complex multiscale continuous process. The operation mode of the SDA process is not considered in the related data-driven model. Therefore, this paper proposes a time lag process prediction model with multiple operation modes to solve the above problem. First, based on random forests, the relative importance of initial input variables in the SDA process on DAO yield and Conradson carbon residual are studied and features are selected according to the results. Then, the stack denoising autoencoder (SDAE) is used to reconstruct the data and obtain the nonlinear mapping information of hidden layers of SDAE and achieve feature dimension reduction. SDAE can improve clustering accuracy of fuzzy c-means, and the operation mode of SDA process is accurately divided. Long short-term memory (LSTM) is used to establish a multicondition LSTM model. Compared with the traditional LSTM model, the multicondition LSTM model has a higher prediction accuracy with R 2 > 0.95. The sensitivity analyses of the properties of feed and operating conditions on DAO yield are consistent with the principle of two-phase countercurrent extraction in the SDA process. In addition, the benchmark test of the Tennessee Eastman process shows that the proposed method is also effective in the fault detection of other processes. Because the multicondition LSTM can predict the future process measurement data according to operating mode, it can better avoid the false alarm problem and predict the fault earlier.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…The integration of cause and sub-cause prediction models enabled the efficient causation prediction of incidents. 12 …”

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Yield and Properties Prediction Based on the Multicondition LSTM Model for the Solvent Deasphalting Process

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Rare events are low-frequency events such as toxic release, explosions, and oil spills. , Rare events have been explored in various fields, including aviation, pipelines, nuclear power, and the chemical process industry (CPI), due to their high monetary, environmental, and societal implications. , In the CPI, the U.S. Chemical Safety Board reports more than 130 rare events with severe consequences in the last two decades . Rare events in the CPI results from poorly managed process faults, which are defined as deviations of observed process variables from their normal operating conditions (NOCs) .…”

Section: Introductionmentioning

confidence: 99%

A Direct Transfer Entropy-Based Multiblock Bayesian Network for Root Cause Diagnosis of Process Faults

Kumari

Wang

Khan

et al. 2022

Ind. Eng. Chem. Res.

Self Cite

View full text Add to dashboard Cite

In chemical processes, Bayesian network (BN)-based approaches have been extensively applied for process fault diagnosis. Generally, BN is learned using score and search algorithms where search algorithms create candidate networks whose fitness to data is measured by scores. However, existing approaches cannot utilize cyclic loop knowledge while learning BN. Since cyclic loops are prevalent in chemical processes, their unaccountability results in inaccurate BN and reduces diagnosis accuracy. Therefore, for accurate diagnosis, we propose direct transfer entropy (DTE)-based multiblock BN to discover cyclic loops while learning BN. First, the process is segmented into multiple blocks. Next, block-level BNs are learned using DTE-based score and Greedy search. By eliminating the common source variable effect, DTE finds correct causality between process variables and obtains accurate block-level BNs, which are fused to discover significant cyclic loops that were otherwise unachievable when finding BN. The performance of the developed methodology is demonstrated through a benchmark process.

show abstract

Application of machine learning methods for process safety assessments

Bengherbia,

Syed,

Chew

et al. 2023

Process Safety Progress

View full text Add to dashboard Cite

The accurate prediction of gas dispersion and the potential consequences of gas explosions hold a pivotal role in the assessment of explosion design loads for oil and gas processing facilities. This often involves the use of computational fluid dynamics (CFD) simulations, a widely adopted practice in the field. The extent of CFD simulations required depends on the specific characteristics and size of the facility. In many cases, a substantial number of simulations, often in the thousands, are needed to comprehensively assess the potential outcomes in the event of a hydrocarbon loss of containment. These simulations account for the complex three‐dimensional nature of the facility, the surrounding environmental conditions, and the properties of the leaking hydrocarbon fluids. Although unquestionably invaluable, CFD simulations impose significant temporal constraints upon their execution and necessitate the allocation of substantial efforts and Central Processing Unit (CPU) time. In this paper we develop a neural model tailored specifically for the analysis of CFD gas dispersion and gas explosion scenarios. This model leverages the capabilities of machine learning algorithms to expedite the execution of these complex studies. The proposed neural network model has the advantage of being able to handle a wide range of scenarios in a fraction of time it takes to perform the CFD simulations, making it particularly useful for large‐scale processes facilities. The accuracy of the predictions is remarkably high, providing a high level of confidence in the predictions of the flammable gas clouds sizes across various scenarios, as well as the resulting explosion overpressures.

show abstract

A unified causation prediction model for aboveground onshore oil and refined product pipeline incidents using artificial neural network

Cited by 10 publications

References 38 publications

Yield and Properties Prediction Based on the Multicondition LSTM Model for the Solvent Deasphalting Process

Yield and Properties Prediction Based on the Multicondition LSTM Model for the Solvent Deasphalting Process

A Direct Transfer Entropy-Based Multiblock Bayesian Network for Root Cause Diagnosis of Process Faults

Application of machine learning methods for process safety assessments

Contact Info

Product

Resources

About