Ensure Process Safety Research Articles

Enhanced Dynamic Dual-Latent Variable Model for Multirate Process Monitoring and Its Industrial Application

Quality-related process monitoring is an important tool to ensure process safety and product quality. However, the existence of process dynamics and multirate sampling makes it difficult to construct an efficient monitoring model. In order to handle process dynamics and multirate sampling, a multirate process monitoring method based on a dynamic dual-latent variable model is proposed. The model involves two sets of latent variables modeled as first-order Markov chains, which are used to capture both quality-related and quality-unrelated dynamic information. In addition, to deal with multiple sampling rates in the process data, the proposed model is combined with a multirate Kalman filtering technique. An expectation-maximization (EM) algorithm is used to estimate the unknown parameters, and a fault detection strategy is developed. The higher fault detection rate of the proposed method is verified by two application studies including a real industrial experiment and the Tennessee Eastman (TE) process.

Process hazard and decomposition mechanism of benzoyl peroxide in the presence of incompatible substances

Benzoyl peroxide (BPO) is a hazardous chemical, which is incompatible with many substances. Due to its high thermal sensitivity, it reacts violently with organic chemicals and can cause serious explosions when heated. Toluene and sodium hydroxide (NaOH) are incompatible substances frequently encountered in the production and utilization of BPO. Therefore, it is necessary to investigate the thermal decomposition behavior of BPO and its reaction mechanism under the effect of impurities. In this paper, thermal decomposition behavior of BPO, the mixture of BPO and toluene, and the mixture of BPO and NaOH were studied using differential scanning calorimetry and adiabatic calorimetry under different conditions. The decomposition kinetic models were obtained to simulate thermal runaway behavior in actual package. Chromatography-Mass Spectrometry experiments were performed to examine the composition of thermal decomposition products in different systems. The results show that NaOH improves the thermal stability of BPO and toluene makes it easier for BPO decomposition. Both NaOH and toluene change the decomposition path of BPO. The consumption of benzoic acid radicals is accelerated by NaOH. Toluene makes the decomposition of BPO follow an n-order reaction by consuming phenyl radicals generated by the decomposition of BPO. This study is important for understanding thermal hazards of BPO at the reaction mechanism level and ensuring process safety in industrial processes.

Progress of Process Monitoring for the Multi-Mode Process: A Review

Multi-mode processing is a central feature of modern industry. The application of monitoring technology to multi-mode processing is crucial to ensure process safety and to enhance product quality. This paper describes the definition, nature and data characteristics of the multi-mode process. A complete classification framework for multi-mode process monitoring methods is produced, covering steady-state modes and transitional processes. After introducing basic concepts and describing research outcomes obtained for monitoring methods, prospects for multi-mode process monitoring technology are discussed.

Two-dimensional multiphase batch process monitoring based on sparse canonical variate analysis

Most industrial batch processes involve inherent dynamic characteristics in both within-batch time direction and batch-wise direction. In order to ensure process safety and improve process performance, the two-dimensional dynamics should be analyzed during batch process monitoring. In this work, two-dimensional region of support (2D-ROS) is first constructed to select and preserve the relevant samples for the current measured sample by calculating autoregressive orders with Akaike information criterion (AIC) in time direction and measuring the similarity with the weighted Euclidean distance in batch-wise direction. Afterwards, sparse canonical variate analysis (SCVA) algorithm is performed to yield sparse canonical vectors, which is especially advantageous for eliminating the irrelevant variables and facilitating the interpretation of underlying relationships of process variables. Meanwhile, given most measurements are subject to the non-Gaussian distribution, the upper control limits (UCLs) in 2D-SCVA can be estimated using kernel density estimation (KDE). The achieved results obtained from a numerical dynamic example and the benchmark fed-batch penicillin fermentation process clearly verify that the proposed method performs well for detecting abnormal operation for the batch processes.

Heat exchanger network synthesis with process safety compliance under tube rupture scenarios

While there exists considerable research on HEN Synthesis (HENS), little attention has been paid to incorporating process safety of HENS at the conceptual design stage. In this work, we extend the optimization-based HENS to incorporate safety using a Safety Rating (SR) to safely navigate dynamic tube rupture scenarios for all plausible heat exchanger matches. This metric allows one to assess the risk of overpressure resulting in failure of the equipment. To avoid such complexity, we develop a piecewise linear approximation of SR using data obtained from a dynamic tube rupture model. Our approximation is such that it always provides guaranteed and tight underestimation of the SR values, thereby ensuring process safety. Applying the methodology, we obtain HEN configurations with lowest costs that can safely handle overpressure events for the entire network. By rethinking how to mitigate process safety challenges using systems approaches, plants can incorporate safer designs for minimal cost.

An Imbalanced Multifault Diagnosis Method Based on Bias Weights AdaBoost

Fault diagnosis plays an important role in ensuring process safety. It is noted that imbalance between fault data and normal data always exists, and multifault obviously outranges a single fault in common, which leads to more challenges to fault diagnosis. In this article, an imbalanced multifault diagnosis method based on bias weights AdaBoost (BW-AdaBoost) is proposed. First, majority normal samples are under-sampled by K-nearest neighbor (KNN) to collect the boundary samples between majority normal samples and minority fault samples, and then the bias datasets are formed by under-sampled majority samples and minority samples. Second, different weak classifiers with adaptive weights are constructed based on the bias datasets and are integrated into a strong classifier, which is taken as the base classifier. While constructing the weak classifier, higher weights are given to the items corresponding to the minority class in the loss function to enhance the influence of minority class samples. Third, to solve the multifault problem, the base classifiers are integrated into a multiclassification model by the hierarchical structure which needs fewer classifiers and less computational expense. Finally, through simulation experiment, the comparison results show that the proposed imbalanced multifault diagnosis method based on BW-AdaBoost can effectively improve the diagnosis accuracy and F1 score.

Consistency Regularization Auto-Encoder Network for Semi-Supervised Process Fault Diagnosis

Industrial processes are developing towards intelligence and complexity, which brings challenges to intelligent process monitoring. An effective fault diagnosis model plays a vital role in ensuring process safety. However, labeling process samples is time-consuming and costly, which make it hard to obtain enough labeled samples to train an effective diagnostic model. This motivates the development of semi-supervised learning which basic idea is to use unlabeled data to help limited labeled data for model training. In this paper, a consistency regularization auto-encoder (CRAE) framework based on encoder-decoder network is proposed to overcome the problem caused by limited labeled samples. The proposed CRAE captured temporal and spatial correlations from both labeled and unlabeled samples to realize fault diagnosis. Firstly, single process sample is processed as sample matrix using proposed data augmented strategy which can help the proposed method to extract more representative features. Secondly, local encoder and global encoder are proposed to extract local and global temporal and spatial features from sample matrices. Next, the local and global features are fused as the input of decoder network, which improve the ability of reconstruction. Finally, the consistency regularization method is introduced into the encoder-decoder framework to push the decision boundary to the low-density area, which make the distinction among different categories more obvious to help the model better achieve the classification task. Experiments on the Tennessee Eastman process show that the proposed method is effective for process fault diagnosis when labeled samples are limited compared to the other semi-supervised algorithms.

A Novel Safety-Relevant Fault Detection and Assessment Method for Dynamic Process*

Process monitoring and fault diagnosis is the key to ensuring process safety and improving product quality. In traditional studies, process safety indicator related fault detection and evaluation have not been fully resolved. To address this problem, a method of maximum information coefficient and slow feature analysis is presented in this paper. The relevance between process and safety variables is calculated by using the maximum information coefficient, and the process variables are divided into strongly safety-related block, weakly safety-related block and safety-unrelated block. Then, the distributed local monitors are established in each block using slow feature analysis method which can identify the process dynamic anomalies. Meanwhile, a new decision fusion method based on logical analysis is proposed to process monitoring and fault grade assessment. Finally, the proposed method is practiced with the Tennessee Eastman Process, and the effectiveness and superiority are proved by comparing with other methods.

Quality-related monitoring of distributed process systems using dynamic concurrent partial least squares

Process monitoring is critical to ensure process safety and maintain quality stabilization. Currently, a large-scale industrial process commonly consists of multiple operation units or manufacturing plants, and a huge number of variables that reflect operation conditions can be collected easily. The conventional monitoring methods usually utilize all process variables to model, which will submerge the correlation between the process and quality variables. In this paper, a new dynamic concurrent partial least squares (DCPLS) monitoring scheme based on variable importance in the projection (VIP) is proposed for large-scale processes. Firstly, process variables are firstly partitioned into quality-related and weakly quality-related space based on their VIP value. Then, DCPLS model is used to monitor abnormal events in these two spaces, respectively. Finally, fusing the statistics of these two spaces through support vector data description to provide an overall indication. The proposed distributed process monitoring scheme not only automatically realizes the division of variables but also characterizes the dynamic information of data. The monitoring results of the Tennessee Eastman process indicate that the proposed VIP-DCPLS method is more efficient than other monitoring methods.

Research on equipment corrosion diagnosis method and prediction model driven by data

With the rapid development of the oil refining industry, safety problems caused by equipment corrosion have become increasingly important, making equipment corrosion management a key factor to ensure process safety. Corrosion diagnosis, as the first step of equipment corrosion management, is of great significance in not only ensuring the proper corrosion supervision, but also realizing safety protection of equipment. This paper addresses the problems of incompleteness as well as the subjective factors of existing methods in equipment corrosion diagnosis. The proposed solution, based on data-driven corrosion diagnosis, suggests a more comprehensive view. Special focus in this paper is on evaluation and prediction of corrosion safety state, including the identification of corrosion mode and the prediction of corrosion type and degree. This paper brings together large amount of historical data of equipment corrosion detection and solves the problem of unbalanced original data by data wrangling and the application of Borderline-SMOTE algorithm. What’s more, a prediction model that is based on Random Forest (RF) algorithm is constructed, aiming at equipment corrosion mechanism, type and degree. The results show that the model, aiming at critical mechanism identification, performs ideally after evaluation and the accuracy of the results amount to 86%. As for the classification and prediction of corrosion state, the model can be further optimized by Particle Swarm Optimization (PSO) algorithm to reach a better accuracy (92%), which verifies generalization effect compared with traditional prediction models. In addition, this solution improves the functionality and practicability of corrosion diagnosis, which is beneficial to the investigation of hidden dangers. It also can serve as an instruction for equipment safety management to ensure the stable operation for an enterprise.

Cybersecurity of Offshore Oil and Gas Production Assets Under Trending Asset Digitalization Contexts: A Specific Review of Issues and Challenges in Safety Instrumented Systems

Due to the rapid digitalization of offshore oil fields and production platforms, diverse technological solutions, products, and application software have begun to appear both in upstream and midstream processes raising new organizational and operational challenges. The potential effects of these digital technologies driven developments have also been generating concerns, particularly in safety, security, and regulatory terms. Both hardware and software related changes and challenges in sensitive systems such as safety instrumented systems (SIS) can expose a production asset to new forms of risks. Hence, diverse aspects of cybersecurity have gained serious attention from authorities, operators, and service providers, particularly due to increasing general tendencies of major cyber-attacks on high-risk industrial assets, as well as their significant impact on safety, production, and asset economics terms. A SIS in an offshore oil and gas production asset has a critical role towards its safety integrity level (SIL). In general, a SIS consists of specific safety assurance instruments and pre-defined safety functions that are tightly coupled to detect, prevent, or mitigate hazardous situations ensuring process safety. Under the current industrial contexts of major changes within the offshore oil and gas production sector, partly due to unavoidable commercial changes and partly due to rapid technological developments, a better understanding of the cybersecurity exposure potentials of SIS is quite important to mitigate unwanted events and incidents. Under such circumstances, this paper explores critical issues and challenges related to cybersecurity of SIS as an extended step of a research study done in collaboration with industrial partners. It assesses the current actual status, requirements in governing standards and guidelines, and identifies some dangerous failure modes of SISs that need due security-oriented attention in a continuous asset digitalisation process. Towards the end, the paper defines and elaborates in-depth on specific issues and challenges relating to cybersecurity of SIS. Moreover, it identifies and reflects on generic initial steps that can be taken for assurance of cybersecurity of SIS within offshore oil and gas production assets to ensure necessary safety and security integrity levels under rapidly changing industrial contexts.

Metrics for objectively assessing operator training using eye gaze patterns

Process plant operators rely on their knowledge of process cause-and-effect relationships during abnormal situation management. Novice operators develop such process knowledge during training. Hence, holistic assessment of operators’ training is essential to ensure process safety. Currently, during training, operators’ process understanding is evaluated using criteria such as successful completion, task based measures, and operator actions that ignore their cognitive behavior. In this work, we propose an eye-tracking-based approach that uses the operator’s attention allocation during different pre-specified training scenarios along with process data, alarm information, and operator actions. Our approach is based on the precept that an operator would focus their attention on those variables on the human-machine interface that they believe have a direct causal relationship to the situation at hand. Also, expert operators seek time-based information for proactive monitoring. Accordingly, to quantify the progress of a novice operator’s learning, we develop two metrics — association metric and salience metric — using correspondence analysis of operators' eye gaze. To evaluate the applicability of the metrics, we conducted experiments with ten participants who performed 486 tasks. Statistical studies reveal that the proposed metrics can quantify operators’ learning and thus can be used to objectively evaluate training effectiveness.

Effective method of predicting confined pressure behavior under isotropic turbulence

Explosion pressure prediction is indispensable to ensure process safety against accidental gas explosions. This work is aimed at establishing a theoretical method for predicting confined methane-air explosion pressure under isotropic turbulence. The results indicated that the pressure rise rate becomes significantly increased by the existence of isotropic turbulence, which effect on peak value of explosion pressure is negligible. Among various models of turbulent burning velocity, the calculated pressure rise rate using Chiu model, Williams model and Liu model is relatively closer to experimental value. With the increase of turbulent integral length and RMS turbulent fluctuation velocity, the pressure rise rate becomes increased continuously. The influence of adiabatic compression and isothermal compression on pressure rise rate could be ignored. To predict explosion pressure in a more accurate way, the dynamic variation of turbulent integral length and RMS turbulent fluctuation velocity should be considered in the future.

A CFD-based empirical model for hazardous area extent prediction including wind effects

Hazardous extent predictions that ensure process safety while avoiding overestimation have been a challenge for hazardous area classification. Specific leak scenarios can be addressed to build rapid empirical models to accurately determine hazardous extent considering several factors that are not included in general approaches. In view of that, this work aims to propose a novel CFD-based empirical model for gas emissions in open and unobstructed areas. It considers a wide range of variables such as storage temperature and pressure, orifice diameter, molecular weight, gas concentration, and wind velocity. A sensitivity analysis was performed to evaluate each variable's contribution to the gas cloud extent. The linear regression model resulting from the combination of all variables contribution was coupled with Ewan and Moddie's model to minimize the prediction errors due to the non-monotonic wind effects. The suggested algorithm accurately calculates the hazardous extent with a coefficient of determination equals to 0.9842 and a RMSE of 0.0151 for a dataset of 600 cases of generic gases release. The proposed model was also validated for 60 cases of hydrogen releases under different storage conditions, giving a coefficient of determination equal to 0.9829 and a RMSE of 0.0680, indicating a good agreement with the data.

Rebooting kernel CCA method for nonlinear quality-relevant fault detection in process industries

Process monitoring is essential and important strategy for ensuring process safety and product quality. However, due to the nonlinear characteristics and multiple working conditions in process industries, the traditional process monitoring method cannot be effectively applied. Therefore, we propose a novel process monitoring framework, termed as mixture enhanced kernel canonical correlation analysis framework (M-NAKCCA). The innovations and advantages of M-NAKCCA are as follows: 1). The traditional CCA method is re-boosted as a new method, M-NAKCCA, to better nonlinear fault detection. Also, a matter-element model (MEm) is assimilated into M-NAKCCA to make the information more refined. 2). To overcome the curse of dimensionality that usually occurs in the high-dimensional dataset, M-NAKCCA uses the Nyström approximation technology to compress the kernel matrix. Moreover, the T2 control chart is reconstructed and the corresponding control upper limit is re-configured to improve the method sensitivity and to better the fault detection performance. 3). The proposed M-NAKCCA framework is firstly used to monitor a wastewater treatment plant (WWTP) and chemical plant with diverse process behaviors. The experimental results showed that the M-NAKCCA framework achieved the best performance for both of case studies.

Multimodal process monitoring based on transition-constrained Gaussian mixture model

Reliable process monitoring is important for ensuring process safety and product quality. A production process is generally characterized by multiple operation modes, and monitoring these multimodal processes is challenging. Most multimodal monitoring methods rely on the assumption that the modes are independent of each other, which may not be appropriate for practical application. This study proposes a transition-constrained Gaussian mixture model method for efficient multimodal process monitoring. This technique can reduce falsely and frequently occurring mode transitions by considering the time series information in the mode identification of historical and online data. This process enables the identified modes to reflect the stability of actual working conditions, improve mode identification accuracy, and enhance monitoring reliability in cases of mode overlap. Case studies on a numerical simulation example and simulation of the penicillin fermentation process are provided to verify the effectiveness of the proposed approach in multimodal process monitoring with mode overlap.

On the non-monotonic wind influence on flammable gas cloud from CFD simulations for hazardous area classification

Hazardous areas are defined as a result of a variety of variables as storage temperature, pressure, leak orifice size, physical properties of flammable substance, and wind characteristics. The potential formation of an explosive atmosphere must be accurately assessed to ensure process safety. Therefore, computational fluid dynamics (CFD) arises as an important tool for accurate predictions as recommended by the international standard IEC 60079-10-1 (2015). This study aims to analyze the influence of wind velocity magnitude and direction on the hazardous area classification. The authors evaluated the extent and volume for methane, propane, and hydrogen leakages from a CFD model. For each flammable gas, the wind velocity magnitude and direction were regularly varied. The outcomes show that the behavior of the plume size as the wind varies mainly depends on the gas concentration. Counter-flow wind directions lead to zero relative velocity closer to the release point, which concentrates the gas, and wind in the release direction promotes a higher dilution of the gas cloud increasing the hazardous extent while decreases the volume. As a consequence, the wind also influences the zone type, which was accurately predicted from CFD simulations and significant differences were found when compared to the standard analyses. These differences are, to some extent, related to the consideration of wind velocity effects on the gas jet release.

Impact of Organizational Culture and Perceived Process Safety in the UAE Oil and Gas Industry

In the last few decades, there had been a lot of accidents in the oil and gas industry throughout the world. This article reports a qualitative study of 30 employees employed in the United Arab Emirates (UAE) oil and gas industry. Health, Safety, and Environment (HSE) culture is a concept which was studied in many researches. However, this research is set to examine how certain behaviors affect the safety performance in UAE’s oil and gas industry. Four core themes that were drawn from the interviewee discussions of how safety culture, leadership safety behaviors, supervisory safety behaviors, and employee training on safety affect the employee’s performance on safety. The emergent narratives on the safety culture showed that an employee was likely to perceive safety in the organization favorably if s/he believed that his/her role in ensuring process safety was critical. Moreover, results pertaining to supervisory safety culture showed that the safety culture promoted by a supervisor within his/her role often set the standard for his/her subordinates constituted the benchmark against which all his/her subordinates rated their own idea and practice of safety culture. In addition, the findings confirm the important role played by safety leadership, which entails leader-follower interactions where the former influences the achievement of safety goals. Lastly, it was emphasized that safety training stimulated employees with negative or indifferent attitudes towards safety to be more actively engaged in safety matters in the organization.

Performance-Indicator-Oriented Concurrent Subspace Process Monitoring Method

Process monitoring is an effective means to ensure process safety and improve product quality. On the one hand, it is possible that the fault will not affect process safety or product quality. On the other hand, not every fault affects both process safety and product quality simultaneously. To make process monitoring more purposeful and more accurate, a novel performance-indicator-oriented concurrent subspace (PIOCS) process monitoring method containing three subspaces with different degrees of importance is proposed in this paper. The first one is safety-related subspace, the second one is safety-unrelated quality-related subspace, and the third one is safety quality unrelated subspace. Through subspace division and construction, the fault can be categorized as safety-related fault, safety-unrelated quality-related fault, and safety quality unrelated fault. For mining safety and quality related information, both mechanism analysis and data analysis are used. In order to show the effectiveness and superiority, the proposed PIOCS method is tested under a number example and an industrial case study. Compared with traditional process monitoring methods, the proposed PIOCS method can obtain richer information, which is easy to show process operation condition clearly.

A practical approach to improve alarm system performance: Application to power plant

Abstract Process safety in chemical industries is considered to be one of the important goals towards sustainable development. This is due to the fact that, major accidents still occur and continue to exert significant reputational and financial impacts on process industries. Alarm systems constitute an indispensable component of automation as they draw the attention of process operators to any abnormal condition in the plant. Therefore, if deployed properly, alarm systems can play a critical role in helping plant operators ensure process safety and profitability. However, in practice, many process plants suffer from poor alarm system configuration which leads to nuisance alarms and alarm floods that compromise safety. A vast amount of research has primarily focused on developing sophisticated alarm management algorithms to address specific issues. In this article, we provide a simple, practical, systematic approach that can be applied by plant engineers (i.e., non-experts) to improve industrial alarm system performance. The proposed approach is demonstrated using an industrial power plant case study.