Ensure Process Safety Research Articles

Enhancing predictive monitoring of ethylene oxychlorination reactor states through spatiotemporal coupling analysis

The production of polyvinyl chloride (PVC) encounters challenges stemming from the temporal and spatial coupling characteristics inherent in the fixed bed ethylene oxychlorination process. Consequently, the implementation of enhanced safety measures and risk reduction strategies becomes imperative. This study introduces a pioneering methodology leveraging a spectral temporal graph neural network. By leveraging reactor temperature data, spatial variable decoupling facilitated by the Fourier transform, and a self-attentive mechanism within graph neural networks, the proposed approach adeptly forecasts future reactor states. The model's seamless alignment with the physical knowledge of reaction processes, validated through the adjacency matrix and hotspot region identification, underscores its efficacy in ensuring process safety and mitigating operational risks in PVC production. Empirical findings further validate the effectiveness of the approach, with predictions demonstrating an error margin of less than 0.5°C in forecasting future reactor temperatures.

Cross-domain fault diagnosis for multimode green ammonia synthesis process based on DA-CycleGAN

Green ammonia is a crucial strategy for reducing carbon emissions and promoting sustainable development. However, in industrial applications, the production load of the ammonia synthesis section must be adjusted to accommodate fluctuations in renewable energy generation and hydrogen production. Consequently, the green ammonia synthesis process operates under multiple conditions with varying production loads. The operations of this multimode process introduce new challenges for process safety. Traditional fault diagnosis methods experience significant performance degradation when production conditions change. In new conditions, only a small number of normal samples can be obtained, and no fault samples are available. To address this issue, a novel transfer learning method named DA-CycleGAN is proposed for the multimode green ammonia synthesis process. This method combines a two-dimensional generation model based on CycleGAN (Cycle-Consistent Generative Adversarial Networks) with domain adaptation to enhance model performance in cross-domain tasks. The feasibility of the proposed method was initially validated using the benchmark Tennessee-Eastman process for fault diagnosis. Subsequently, a case study of the green ammonia synthesis process demonstrated that it significantly enhances performance in multimode processes, ensuring process safety and reducing losses for industrial applications.

Distributed monitoring of nonlinear plant-wide processes based on GA-regularized kernel canonical correlation analysis

Fault detection and diagnosis is important for ensuring process safety and is gaining increasing attention in the system safety field. A regularized kernel canonical correlation analysis (RKCCA) approach is proposed for monitoring nonlinear plantwide processes. For each local unit, genetic algorithm (GA)-based regularization is performed to determine the communication variables from neighboring units, which preserves the maximum correlations and eliminates the irrelevant variables. Then variables from a local unit and the communication variables are mapped into high-dimensional feature spaces, and the feature space of the local unit is decomposed into three orthogonal subspaces, namely the residual subspace, the inner subspace, and the outer-related subspace. Monitoring statistics to identify both the process status and the characteristic of a detected fault are constructed. The proposed RKCCA-based monitoring method considers both the information of a local unit and the beneficial information of related units to facilitate fault detection, thereby exhibiting superior performance to some state-of-the-arts methods. Applications on the Tennessee Eastman benchmark process and an industrial tail gas treatment process demonstrate the superiority of RKCCA monitoring.

Study on thermal runaway propagation characteristics of the lithium-ion battery module by two-phase flow of nitrogen and water mist in longitudinal ventilation environment

To prevent and control the thermal runaway (TR) and its propagation of lithium-ion batteries (LIBs) is a key problem for its sustainable development and wide application. However, there is still a gap in the research on the characteristics of two-phase flow of nitrogen(N2) and water mist (NWM) controlling TR and its propagation in different longitudinal ventilation environments. In this study, the influence of wind velocity on 0.5 MPa NWM to control TR and its propagation characteristic parameters of LIB module was studied experimentally. The results show that with the increase of wind velocities, the opening time of the safety valve and TR trigger temperature of the LIB module gradually increased. At the same wind velocity, TR trigger temperature of cell 1 to cell 5 was successively reduced after 0.5 MPa NWM was applied. The cooling and asphyxiation effect of 0.5 MPa NWM is the best in natural ventilation environment, but the suppression effect of 0.5 MPa NWM on TR propagation of the LIB module is weakened under the influence of forced ventilation. However, different wind velocities have little effect on TR trigger temperature of the blocked LIB module. At the same time, a quasi-steady state thermal equilibrium of the NWM in a ventilation environment was established for the LIB module, and the influence of the coupling effect of different longitudinal ventilation environments and 0.5 MPa NWM on TR propagation characteristic parameters of the LIB module and the heat transfer mechanism in the thermal runaway propagation process were compared under the two conditions of within or without battery case. It is found that the convection effect of the wind plays a leading role in the heat dissipation of the blocked LIB module when the wind velocity is less than 4.5 m/s. The heat conduction of the battery case plays a leading role when the wind velocity is greater than 4.5 m/s. Moreover, in any ventilation environments, TR propagation time of the blocked LIB module is smaller than that of the unblocked LIB module. Under the same wind velocity, TR trigger temperature of the blocked LIB module and the maximum temperature of each cell are higher than that without battery case. This work provides a new perspective for controlling TR propagation of the LIBs. At the same time, it can provide theoretical guidance for ensuring process safety and firefighters to fight LIB fire accidents.

Toward understandable semi-supervised learning fault diagnosis of chemical processes based on long short-term memory ladder autoencoder (LSTM-LAE) and self-attention (SA)

Fault diagnosis and localization play vital role in chemical process monitoring. Finding the root cause of fault accurately and timely is the key to avoid serious accidents and ensure process safety. Unfortunately, most deep learning-based models only involves in predicting fault state and interpretability is still not fully explored. Besides, lack of labeled samples in practical situations makes supervised learning difficult to implement. To circumvent the obstacle, semi-supervised learning based on long short-term memory ladder autoencoder is combined with self-attention mechanism, which is intended to establish interpretable model by explicitly clarifying the corresponding relationship between abnormal variables and faults. Using Tennessee Eastman process and practical high-purity carbonate production process as benchmark, fault diagnosis and identification performance of proposed LSTM-LAE-SA is validated, and interpretability analysis is performed to demonstrate its capabilities in abnormal variable locations. The developed understandable model could improve operator's trust and industrial application in fault diagnosis system.

Optimized data driven fault detection and diagnosis in chemical processes

Fault detection and diagnosis (FDD) is crucial for ensuring process safety and product quality in the chemical industry. Despite the large amounts of process data recorded and stored in chemical plants, most of them are not well-labeled, and their conditions are not adequately specified. In this study, an optimized data-driven FDD model was developed for a chemical process based on automatic clustering algorithms. Due to data preprocessing importance, feature selection was performed by a non-dominated sorting genetic algorithm (NSGAII) based on k-means clustering. The optimal subset of features is selected by comparing clustering results for each subset. The performance of the proposed feature selection method was compared with the Fisher discriminant ratio (FDR), and XGBoost methods. The t-distributed stochastic neighbor embedding (t-SNE), Isomap, and KPCA dimension reduction methods were also employed for feature extraction. Finally, automatic clustering was performed based on metaheuristic algorithms for fault detection and diagnosis. Results were compared with non-automatic clustering methods. The performance of the proposed method was evaluated by examining the Tennessee Eastman and four water tank processes as case studies. The results showed that the proposed method is reliable and capable of online and offline chemical process fault detection and diagnosis. As a result, the findings of this study can be used to stabilize the operation of chemical processes.

Thermal runaway propagation behavior and cooling effect of water mist within a 18650-type LiFePO4 battery module under different conditions

The thermal runaway (TR) propagation behavior of lithium-ion batteries (LIBs) and mitigation strategies to suppress TR of LIBs have gained significant attention. This study conducted a series of tests to investigate the TR propagation behavior of LiFePO4 battery modules arranged in a one-dimensional linear arrangement and a square configuration. The influence of flames on the TR propagation was analyzed. Furthermore, the cooling effects of water mist (WM) on single cells and battery modules at different stages of TR were explored. Flaming combustion could induced more cells to TR and significantly accelerate the propagation speed of TR. The mitigation effect of WM on the TR propagation is notable, however, as TR progresses, the duration of WM required to prevent TR or completely cool the cells increases. Under the same water usage conditions, intermittent WM releases significantly extend the low-temperature duration of the cells, enhancing the cooling effectiveness. This work provides essential guidance for ensuring process safety and designing fire protection measures for 18650-type LiFePO4 battery systems.

A novel gel dry water: Preparation and application in methane-air explosion

To weaken the adverse effects of methane-air explosions on industrial processes and the environment, the development of highly effective explosion inhibitors is imperative. In this study, a novel ammonium polyphosphate gel dry water (AGDW) powder was synthesized by incorporating superabsorbent polymer (SAP) and ammonium polyphosphate (APP) as additives. The addition of SAP significantly enhanced the physical properties such as stability and water retention of AGDW powder, while APP improved its suppression effects. The suppression effect of AGDW powder on methane-air explosions was investigated in a square explosion pipeline. Experimental results revealed that 4 g AGDW powder with 15 wt% APP completely hindered the propagation of the explosion flame, resulting in a 91.2% reduction in peak temperature and completed elimination of the pressure reflection wave. Increasing the spraying pressure from 0.2 MPa to 0.4 MPa, 2 g AGDW powder with 5 wt% APP was sufficient to suppress the explosion completely. The suppression mechanism of AGDW powder on methane-air explosions was comprehensively elucidated from the cooling effect, diluting effect, and interrupting the chain reaction. This work sheds light on the preparation and application of novel dry water powders and provides a feasible solution for ensuring process safety and controlling gas explosions.

A review of Faisal Khan's contribution to process monitoring

AbstractProcess monitoring is pivotal in process system engineering for abnormal situation management and ensuring process safety. This paper presents a review of Professor Khan's works on process monitoring. It examines (i) the number of publications, (ii) the type of publications, (iii) key sources, (iv) focused areas and their evolvement, and (v) the research impact by Professor Khan in process monitoring. The results suggest that journals are the primary sources he has used to disseminate research results. Over the years, his research focus evolved from detection to root cause diagnosis, fault propagation pathway analysis, and failure prognosis. Professor Khan has immensely impacted his peers, evidenced by his theoretical contributions, a higher number of recognitions by other researchers, and diversified workforce development.

Knowledge-Enhanced Distributed Graph Autoencoder for Multiunit Industrial Plant-Wide Process Monitoring

In multiunit industrial plant-wide processes (MIPPs), data-driven distributed process monitoring methods have played an important role in ensuring process safety and reliability. However, the existing studies fail to leverage the relational knowledge about the underlying process structure of MIPPs, which may lead to inaccurate process modeling and degradation of the monitoring performance. To tackle these issues, this work proposes a novel knowledge-enhanced distributed graph autoencoder (KDGAE) for plant-wide process monitoring. Firstly, a posterior graph structure learning module (PGSL) is designed for relational knowledge discovery, which explicitly characterizes the dependencies between operation units in MIPPs into a directed graph. Prior knowledge is introduced into PGSL as a learning bias that steers the posterior graph to adhere to the underlying physics. Then, a novel distributed graph autoencoder (DGAE) is developed to encode both the local information within each unit and the global information between units for distributed process monitoring. The discovered posterior knowledge is embedded as a relational inductive bias in DGAE to enhance the capability of unsupervised representation learning, thereby improving the monitoring performance. Finally, the effectiveness of the proposed method is demonstrated through the Tennessee Eastman process and a real-world air separation process.

A multi-feature-based fault diagnosis method based on the weighted timeliness broad learning system

Accurate and timely fault diagnosis is a vital task to ensure process safety of modern industrial facilities. Motivated by the complex variations of process signals and mutual coupling of faults, this paper presents a multi-feature-based fault diagnosis method based on the weighted timeliness Broad Learning System (BLS). The proposed method fuses multiple features extracted from the original process data to improve the fault diagnosis performance, and makes the diagnosis model suitable for dynamic fault diagnosis problems by incorporating the BLS. The major contributions of this study are twofolds: 1) A systematic multi-feature extraction method is proposed to extract long-term trend features, short-term trend features, and binary alarm signals, which reflect the direction and amplitude changes of process signals under faulty conditions; 2) a weighted timeliness BLS structure with multiple fault-sensitive features as the input is proposed to ensure the dynamic characteristics of the fault diagnosis model. The designed fault diagnosis model can be updated in an incremental manner, and thus can improve the model updating efficiency while ensuring accuracy. The effectiveness and superiority of the proposed method is demonstrated by a case study based on the Tennessee Eastman benchmark process.

Early Warning of Loss and Kick for Drilling Process Based on Sparse Autoencoder With Multivariate Time Series

Complicated geological environments lead to a high risk of drilling incidents. Early warning of loss and kick for the drilling process is essential to ensure process safety. On account of the nonlinear and temporal correlation of drilling parameters, an early warning method for loss and kick based on sparse autoencoder with multivariate time series is proposed. The sparse autoencoder is utilized for multivariate time series abnormality detection of the drilling process. Abnormal drilling parameter isolation is performed through contribution analysis. Reconstruction analysis and time series segmentation approaches are integrated for abnormal time series trend evaluation. The characteristic of drilling parameters under normal operation learned by the sparse autoencoder and the property of the original time series are taken into account. The final early warning result can be obtained through expert rules based on the trend evaluation result. Case studies are presented based on the data from an actual drilling project. The experiment result shows the effectiveness of the proposed method.

Predictive control scheme by integrating event-triggered mechanism and disturbance observer under actuator failure and sensor fault

Liquid-level control in an interacting storage-tank system exhibits major challenges due to the effect of interaction and the presence of combustible/flammable liquid as it faces huge threats from the unmeasurable disturbances, irregular geometry and unmodelled dynamics of the process plant. A combination of tanks with multiple geometries may be preferred for storing liquids using common pumps for energy conservation. Continuous improvement of risk assessment, predicting hazardous scenarios and implementation of inherently-safer-control systems ensure process safety and, as a result, ease out the safe operation. From the process analysis, it was observed that the dynamics of the interacting tank are very sensitive to effective parameters like valve coefficient and pump gain. To overcome the loss of inventory or production, we investigate the synthesis of a non-linear model predictive control scheme with an outline of simultaneous state and parameter estimation strategies. This mechanism deals with a stochastic event-trigger cubature Kalman filter scheme to estimate process states while performing servo operations. To mitigate plant uncertainty, reduce the impact of large disturbances and nullify the effect of actuator failure/sensor fault, influential model parameters are estimated simultaneously with the model state(s). Predicted values of the model states/parameters/faults are used to derive an effective control effort. An inferential non-linear model predictive control paradigm is proposed, where the primary variable(s) is (are) measured with the help of measurable secondary state(s). To demonstrate the practical utility and effectiveness of the control framework for safe operation and loss prevention, a complex industrial process (quadrupled tank) is considered for control, where the system dynamics have been structured newly. Realistic simulations such as servo-regulatory compliance and elimination of measurement noise with a state-of-the-art simulator ensures the efficacy of the proposed scheme. The results are analysed further for a comparative study with traditional non-linear model predictive control law. To guarantee convergence of the estimator and stability of the closed-loop controller, the Lyapunov theorem is well blended.

Flame evolution and pressure dynamics of methane-hydrogen-air explosion in a horizontal rectangular duct

This work is aimed at exploring flame evolution and pressure dynamics of methane-hydrogen-air explosion experimentally and numerically by changing equivalence ratio and hydrogen content. For the flame evolution, the smooth distortion vanishes at equivalence ratio of Ф = 1.4, the prominent cellular structure and distorted tulip flame start to form with increasing hydrogen content. For the pressure dynamics, as the equivalence ratio increases, both maximum explosion overpressure and maximum pressure rise rate increase and then decrease, and both of them continue to increase with increasing hydrogen content. H + O2 = O + OH is the main elementary reaction with positive effect on the laminar burning velocity. The main elementary reactions with negative effects are H + O2(+M) = HO2(+M) and CH3 + H(+M) = CH4(+M). H radical always dominates on the rich side or the lean, stoichiometric side with high hydrogen content. As the hydrogen content increases, the main oxidation pathways of CH4 undergoes the transfer from CH4 → CH2(S) → CH2 → CO to CH4 → CH2(S) → CH2 → CH → CO → CO2. The research results are helpful to improve combustion efficiency of internal combustion engine and ensure process safety of hydrogen doped natural gas pipeline transportation.

Robust fault detection for chemical processes based on dynamic low-rank matrix and optimized LSTM

The data collected by sensors in modern chemical process systems are always contaminated by industrial noise, so robust fault detection is an important technology to ensure process safety. However, the existing robust detection techniques have limitations in extracting dynamic and time series features of chemical process data. In this paper, a robust fault detection method based on dynamic low-rank matrix and optimized LSTM is proposed for dynamic chemical processes under noise background. First, a new low-rank matrix decomposition method, dynamic principal component pursuit (DPCP), is proposed for the dynamic characteristics of process data containing noise. The PCP is improved using the time delay excursion method, i.e., the DPCP is constructed by embedding an augmented dynamic matrix with a time lag factor on the PCP and solved using the alternating direction multiplier method. The purpose is to strip the useless noise from the useful detection information and extract the dynamic low-rank matrix. Second, an optimized LSTM (OPLSTM) is proposed for the time series features of dynamic low-rank matrix. vector factors for feature selection of memory cells in the LSTM are reweighted to balance the time series features of industrial processes and avoid heavy reliance on erroneous fault information. In addition, support vector data description (SVDD) is used to describe the hypersphere with clear boundary, and distance-based statistic is constructed to achieve fault detection with high fault detection rate and low false alarm rate. Finally, to assess the effectiveness of the proposed method, we performed extensive experiments on the Tennessee Eastman Process and the electrolytic aluminum process, and compared them with multiple methods. The experimental results show that the proposed method is effective and robust for chemical processes fault detection in the background of industrial noise.

Multiscale Bayesian PCA for robust process modeling of a Fischer–Tropsch bench scale process

Building a good process model is critical for process monitoring technologies which ensure process safety, reliability, and profitability. In this work, we develop a Multiscale Bayesian PCA (MS-BPCA) algorithm and use it to model a real Fischer–Tropsch (FT) pilot plant. We demonstrate the algorithm’s superior and robust performance in dealing with autocorrelation and noise contamination compared to BPCA and Multiscale PCA. The modeling performance of BPCA depends on the accuracy of the likelihood and prior parameters. Therefore, we explore various techniques (multiscale filtering, polynomial approximation, and PCA) to empirically estimate these parameters. Furthermore, we study the limitations of the BPCA modeling algorithm when its assumptions of gaussian data and independent noise are violated. Finally, this work will compare the modeling performance of all techniques (PCA, Bayesian PCA, Multiscale PCA, and Multiscale Bayesian PCA) with real data collected from a state-of-the-art bench-scale Fischer–Tropsch (FT) process.

Development of Hydrogen Oxidation Reaction Catalysts to Overcome CO Poisoning and Elucidation of Reaction Mechanism

Passive autocatalytic recombiner (PAR) represents a potential technology for ensuring process safety in the hydrogen society. PARs function through the catalytic oxidation of generated or leaked hydrogen, facilitating its conversion into water and effectively mitigating the risk of hydrogen explosions. CO is recognized as a catalyst poison that hampers surface catalytic reactions. To investigate the negative effects of CO on the local structure of platinum metal nanoparticle catalysts during water formation, in situ and time-resolved X-ray absorption spectroscopy analyses were conducted. The results revealed that the Pt–Fe/CZY catalyst exhibited notable hydrogen oxidation activity even in the presence of CO. The enhanced performance can be attributed to the combined effects of Pt–Fe alloy composition and CZY support materials.

Process Modeling and Simulation of Ammonia Production from Natural Gas: Control and Response Analysis

Optimal production of ammonia (NH3) using natural gas is necessary in order to make it available for wide range of applications including the manufacture of fertilizers, fuel for transportation and during synthesis of some chemicals. Achieving this would require strategic implementation of a control scheme to simulated ammonia production, capable of ensuring adequate realization of production targets. The work involves ASPEN Plus modeling, simulation, sensitivity analysis and control of NH3 production process. Steam/carbon ratio, conversion of CH4, removal of carbon dioxide (CO2) and carbon monoxide (CO), hydrogen/nitrogen ratio and heat exchanger and separator temperatures were identified as requiring control in units any of these specifically impacts. As a result, approximately 176 tons of NH3 was realized daily based on the simulation results and can be scaled-up using a calculated factor equivalent to 1.1375 to 200 tons/day capacity, in this design. Sensitivity analysis resulting in control of certain unit parameters is effective in ensuring process safety, maximum yield of important end-products and reduction in the cost of operation

Automation and control of the thermal mixing process

In this research, the automation and control of an industrial mixing process were developed. Process safety was established through pipeline maintenance, plant instrumentation repair, and the addition of required instrumentation to ensure process safety. The process operation was divided into the industrial operation stages A1,F1, F2, F3, F5, and D1 of the GEMMA guide, designed in the GRAFCET methodology. The design of the temperature and level controllers was carried out using the approximation technique of each closed-loop system to a second order system with zero, based on the pole approximation technique. The industrial process was carried out with the DCS Honeywell HC900, integrating the automation of the system and the temperature and level controllers designed. A real-time SCADA supervision system was implemented to visualize the process and report alarms caused by failures in sensors or actuators. The mixing process was carried out in real-time, evidencing the settling times and overshoot values under the desired conditions.

A weighted k-nearest neighbor process monitoring method based on statistical volume pattern analysis

Process monitoring technology has developed rapidly in response to the increasing demand for safer and more reliable systems in modern process operations. Online process monitoring plays an important role not only in ensuring process safety through the timely detection of process faults but also in improving process productivity and product quality. One of the outstanding features of modern manufacturing facilities, which are large in scale and highly complex, is that the processes contain numerous variables operating under closed-loop control. Fully exploiting and utilizing the valuable information in these variables will benefit early and accurate fault detection and diagnosis of processes, minimizing downtime, increasing plant operational safety, and reducing manufacturing costs. The development of process monitoring technology is of great importance to ensure the operational safety, reliability, and economy of complex industrial processes. With the continuous development of industrial processes, the collection and use of process data are gradually increasing, and data-driven multivariate statistical process monitoring methods have developed significantly. A weighted k-nearest neighbor process monitoring method based on SPA is proposed for the problem of multimodal properties of process statistics. When the covariance difference between different modes is large, the multimodal characteristics of the original variable space are retained in the statistic feature space. By introducing weights and assigning weights to the distances between statistic samples, the proposed method can regulate the distances between statistic samples in modes with larger covariance and those with smaller covariance to the same scale, overcoming the limitations of the SPA-based process monitoring method in multimodal fault detection.