Operation Of Chemical Processes Research Articles

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.

Computationally efficient solution of mixed integer model predictive control problems via machine learning aided Benders Decomposition

Mixed integer Model Predictive Control (MPC) problems arise in the operation of systems where discrete and continuous decisions must be taken simultaneously to compensate for disturbances. The efficient solution of mixed integer MPC problems requires the computationally efficient online solution of mixed integer optimization problems, which are generally difficult to solve. In this paper, we propose a machine learning-based branch and check Generalized Benders Decomposition algorithm for the efficient solution of such problems. We use machine learning to approximate the effect of the complicating variables on the subproblem by approximating the Benders cuts without solving the subproblem, therefore, alleviating the need to solve the subproblem multiple times. The proposed approach is applied to a mixed integer economic MPC case study on the operation of chemical processes. We show that the proposed algorithm always finds feasible solutions to the optimization problem, given that the mixed integer MPC problem is feasible, and leads to a significant reduction in solution time (up to 97% or 50×) while incurring small error (in the order of 1%) compared to the application of standard and accelerated Generalized Benders Decomposition.

Integration of chemical process operation with energy, global market, and plant systems infrastructure

Increased globalization, deregulation of energy markets, and environmental constraints, together with associated uncertainty, have created a highly dynamic and uncertain process manufacturing environment. Responding effectively to this increased variation and uncertainty is critical for a company to remain competitive. In this paper, we consider the plant infrastructure in relation to the energy and global market infrastructures. We describe changes to the plant infrastructure system in order to function more effectively in the current manufacturing environment, as well as key research advances that are aligned to addressing challenges faced by present day plant operation.

OPTIMIZATION OF OPERATING PARAMETERS OF OPEN COOLING TOWERS OF THE DOUBLE-CIRCUIT COOLING SYSTEM

The operation of most chemical processes is accompanied by the cooling of various production streams over a wide temperature range using various refrigerants. At cooling temperatures of process streams up to 25 °C, the most common refrigerant is water prepared in circulating water supply systems of petrochemical plants equipped with fan cooling towers, the work of which is considered in the article. Operation of open cooling towers in single-circuit cooling systems is characterized by high economic efficiency with a wide range of thermal capacities. However, drip entrainment of circulating water, entry of production products into the atmosphere, enrichment of circulating water with oxygen followed by growth of microorganisms in water requires a transition to two-circuit systems in which cooling is carried out by a closed-cycle refrigerant cooled by open-cycle water passing through cooling towers. But such changes in cooling systems reduce the economic efficiency of these systems. The analysis of the equipment operation in the open and closed circuits of the cooling system, provided that a number of system parameters are constant (heat load, quality of purification of recuperation heat exchangers of the cooling system, etc.), made it possible to formulate optimization (minimization) of operating costs for water cooling. Taking into account the previously obtained models of pollution growth in recuperation heat exchangers and considering the vector of control parameters of the optimization problem, the main parameter of optimization (mimimization) of operating costs for cooling, which is the cooling temperature of cooling water, was identified. The results of the analysis of the influence of ambient air parameters on the temperature of the produced cooling water in the open cooling towers are also presented, and the calculation of the economic efficiency of the cooling system operation is carried out taking into account seasonal changes in ambient air parameters.

SFILES 2.0: an extended text-based flowsheet representation

SFILES are a text-based notation for chemical process flowsheets. They were originally proposed by d’Anterroches (Process flow sheet generation & design through a group contribution approach) who was inspired by the text-based SMILES notation for molecules. The text-based format has several advantages compared to flowsheet images regarding the storage format, computational accessibility, and eventually for data analysis and processing. However, the original SFILES version cannot describe essential flowsheet configurations unambiguously, such as the distinction between top and bottom products. Neither is it capable of describing the control structure required for the safe and reliable operation of chemical processes. Also, there is no publicly available software for decoding or encoding chemical process topologies to SFILES. We propose the SFILES 2.0 with a complete description of the extended notation and naming conventions. Additionally, we provide open-source software for the automated conversion between flowsheet graphs and SFILES 2.0 strings. This way, we hope to encourage researchers and engineers to publish their flowsheet topologies as SFILES 2.0 strings. The ultimate goal is to set the standards for creating a FAIR database of chemical process flowsheets, which would be of great value for future data analysis and processing.

A reachable set-based scheme for the detection of false data injection cyberattacks on dynamic processes

Recent cyberattacks targeting process control systems have demonstrated that reliance on information technology-based approaches alone to address cybersecurity needs is insufficient and that operational technology-based solutions are needed. An attack detection scheme that monitors process operation and determines the presence of an attack represents an operational technology-based approach. Attack detection schemes may be designed to monitor a process operated at or near its steady–state to account for the typical operation of chemical processes. However, transient operation may occur; for example, during process start-up and set–point changes. Detection schemes designed or tuned for steady-state operation may raise false alarms during transient process operation. In this work, we present a reachable set-based cyberattack detection scheme for monitoring processes during transient operation. Both additive and multiplicative false data injection attacks (FDIAs) that alter data communicated over the sensor–controller and controller–actuator communication links are considered. For the class of attacks considered, the detection scheme does not raise false alarms during transient operations. Conditions for classifying attacks based on the ability of the detection scheme to detect the attacks are presented. The application of the reachable set-based detection scheme is demonstrated using two illustrative processes under different FDIAs. For the FDIAs considered, their detectability with respect to the reachable set-based detection scheme is analyzed.

Galerkin finite element analysis of heat and mass transfer of Jeffrey, Maxwell and Oldroyd-B nanofluids in a vertical annulus with an induced magnetic field and a non–uniform heat source/sink

ABSTRACT The Maxwell, Jeffrey and Oldroyd-B nanofluid models are important for characterising fluid flow, heat and mass transfer in industrial chemical process systems and operations. Consequently, this study focuses on investigating thermophoresis, Brownian motion, a non-uniform heat source/sink and suction influence on Maxwell, Jeffrey and Oldroyd-B nanofluids towards a stretching cylindrical annular surface with an induced magnetic field (IMF). The non-linear ODEs are solved numerically by opting for GFEM for the transformed system. The obtained GFEM results are compared and are in exceptional agreement with existing results, in the limiting sense. The boundary layer of the velocity and IMF are reduced by the Lorentz force, and also in the vertical annulus the IMF is independent of magnetic parameter ( 1 ≤ β ≤ 5 ) and is reliant on the size of the radius ratio. For higher values of Nb ( 0.1 ≤ N b ≤ 0.5 ) the temperature distribution in the annulus accelerates, whereas the concentration profile decelerates. Additionally, heat and mass transfer characteristics are analysed in the annulus through ANN – BLMN. The important outcome of this study is that the Jeffrey model outperforms the Maxwell and Oldroyd-B nanofluid models in terms of heat and mass transfer rates.

A novel dynamic distance coding identification method for oil–gas gathering and transportation process

Deep learning (DL) has become a mainstream method for fault identification in petrochemical processes. However, the high noise and nonlinear coupling of complex data samples have led to different degrees of low accuracy and robustness problems in the method. Meanwhile, the fault cause is difficult to capture due to the complex chemical process operation mechanism. To address this challenge, a novel dynamic distance coding method incorporating DL is proposed to identify anomalies in real time. First, the collected normal process data are smoothed by the Savitzky–Golay filter to build a normal sample set. Then, dynamic coding based on the distance metric is introduced to compute the distribution of normal and real-time samples for extracting the spatial domain features. By a sliding window, dynamic coded maps are generated and analyzed for fault causes. Finally, the time-domain information is extracted by long short-term memory (LSTM) to learn the deep features of the encoded graph for fault identification. The proposed method was applied to an oil–gas gathering and transportation process, which proves its feasibility and effectiveness. Compared with the conventional LSTM, the F1 score of the method is improved by 0.193, reaching 0.986. The obtained visualization information enables explaining the causes and supplements the fault database, providing a valuable reference for workers’ feedback operations.

Safety education 4.0 – A critical review and a response to the process industry 4.0 need in chemical engineering curriculum

Safety education has found a place in the chemical engineering curriculum. However, its complete impact is yet to be realized. A part of this delay may be attributed to the gap between the concepts traditionally taught in engineering education and the tools required for the practice of engineering in the process industry. This gulf is only exacerbated by the advent of Industry 4.0, which relies heavily on emerging technologies, such as big data, automation, and machine learning. Therefore, a fundamental aspect that educators of process safety need to readdress is the following: “How can safety knowledge and competence among engineering graduates be enhanced for them to have a sustained impact on the safe design and operation of chemical processes during industrial practice?” In this context, the present work investigates the status of safety knowledge development and transfer from education to practice. A detailed analysis of demographic and temporal evaluation of safety education in specific engineering disciplines, and the shortcomings of the current curricula in imparting safety concepts to the students, are also discussed in detail. This perspective attempts to bridge the gap between academic training and the job requirements of process safety engineers through a concept titled ‘Safety Education 4.0’. In the proposed Safety Education 4.0 methodology, academics and industry personnel collaborate in teaching students safety principles through project-based learning (PBL). The compact modular format of PBL makes it flexible to be updatable on-demand process safety education.

Impact of nickel–titanium super-elastic material properties on the mechanical performance of self-expandable transcatheter aortic valves

Self-expandable transcatheter aortic valves (TAVs) elastically resume their initial shape when implanted without the need for balloon inflation by virtue of the nickel–titanium (NiTi) frame super-elastic properties. Experimental findings suggest that NiTi mechanical properties can vary markedly because of a strong dependence on the chemical composition and processing operations. In this context, this study presents a computational framework to investigate the impact of the NiTi super-elastic material properties on the TAV mechanical performance. Finite element (FE) analyses of TAV implantation were performed considering two different TAV frames and three idealized aortic root anatomies, evaluating the device mechanical response in terms of pullout force magnitude exerted by the TAV frame and peak maximum principal stress within the aortic root. The widely adopted NiTi constitute model by Auricchio and Taylor (1997) was used. A multi-parametric sensitivity analysis and a multi-objective optimization of the TAV mechanical performance were conducted in relation to the parameters of the NiTi constitutive model. The results highlighted that: five NiTi material model parameters (EA, σtLS, σtUS, σtUE and σcLS) are significantly correlated with the FE outputs; the TAV frame geometry and aortic root anatomy have a marginal effect on the level of influence of each NiTi material parameter; NiTi alloy candidates with pareto-optimal characteristics in terms of TAV mechanical performance can be successfully identified. In conclusion, the proposed computational framework supports the TAV design phase, providing information on the relationship between the super-elastic behavior of the supplied NiTi alloys and the device mechanical response.

Cybersecurity and dynamic operation in practice: Equipment impacts and safety guarantees

Though dynamic operation of chemical processes has been extensively explored theoretically in contexts such as economic model predictive control or even considering the potential for cyberattacks on control systems creating non-standard operating policies, important practical questions remain regarding dynamic operation. In this work, we look at two of these with particular relevance to process safety: (1) evaluating dynamic operating policies with respect to process equipment fidelity and (2) evaluating procedures for determining the parameters of an advanced control law that can promote both dynamic operation as well as safety if appropriately designed. Regarding the first topic, we utilize computational fluid dynamics and finite element analysis simulations to analyze how cyberattacks on control systems could impact a metric for stress in equipment (maximum Von Mises stress) over time. Subsequently, we develop reduced-order models showing how both a process variable and maximum Von Mises stress vary over time in response to temperature variations at the boundary of the equipment, to use in evaluating how advanced control frameworks might impact and consider the stress. We close by investigating options for obtaining parameters of an economic model predictive control design that would need to meet a variety of theoretical requirements for safety guarantees to hold. This provides insights on practical safety aspects of control theory, and also indicates relationships between control and design from a safety perspective that highlight further relationships between design and control under dynamic operation to deepen perspectives from the computational fluid dynamics and finite element analysis discussions.

A modified electrolyte non‐random two‐liquid model with analytical expression for excess enthalpy: Application to theMEA‐H2O‐CO2system

AbstractAccurate thermodynamic properties of electrolyte systems are critical for the design and operation of many chemical processes. A comprehensive description of the thermodynamic framework for multielectrolyte mixed solvent systems is presented, where the parameter structure of the symmetric electrolyte‐non‐random two liquid (e‐NRTL) model is reformulated and a thermodynamically consistent and analytically derived formulation for the excess enthalpy is developed from the e‐NRTL model. The refined parameter structure of the e‐NRTL model avoids numerical singularities of the analytical formulation for the excess enthalpy in the absence of ionic species and extends the derived excess enthalpy formulation to non‐electrolyte systems. The thermodynamic framework is demonstrated for the MEA‐H2O‐CO2case study using experimental data on thermodynamic quantities for the binary MEA‐H2O system and the ternary MEA‐H2O‐CO2system. The model is implemented in Pyomo and will be available for release in the Institute for the Design of Advanced Energy Systems (IDAES) computational platform.

Machine learning aided multi-objective optimization and multi-criteria decision making: Framework and two applications in chemical engineering

To accelerate data-driven studies for various optimization applications in chemical engineering, a comprehensive machine learning aided multi-objective optimization and multi-criteria decision making (abbreviated as ML aided MOO-MCDM) framework is proposed in the present paper. The framework comprises a total of seven steps; firstly, study the application and its input-output datasets to identify objectives, constraints and required ML models; secondly, select ML model(s) for some or all objectives and constraints; thirdly, train the chosen ML model(s), including finding optimal hyperparameter values in each of them using an advanced/global optimization algorithm; fourthly, formulate the MOO problem for the application; fifthly, select a MOO method and develop/test the program; sixthly, solve the formulated MOO problem with the developed/tested MOO program many times and review the Pareto-optimal solutions obtained; lastly, perform MCDM using several methods and choose one Pareto-optimal solution for implementation. The proposed ML aided MOO-MCDM framework is useful for process design and operation of chemical and related processes. It is shown to be beneficial for the optimization of two complex chemical processes, which are supercritical water gasification process aiming for H2-rich syngas with lower greenhouse gas emissions, and combustion process in a power plant targeting for higher energy output and lower pollution of the environment.

Microscopic principles of chemical engineering after fossil fuels

Chemical engineering is a broad field in terms of the scope of practice but the discipline has been united by a few intellectually coherent principles. Among them, thermodynamics, reaction kinetics and transport phenomena are often considered as the cornerstones, providing support for the design and operation of diverse chemical processes for power generation and production of industrial goods such as plastics, gasoline and ammonia. Traditionally, these industrial processes use fossil fuels as the raw materials and are responsible for significant greenhouse gas emissions. As fossil-energy-based processes are deemed phasing out , development of alternative routes with renewable energy and sustainable feedstock is calling for the expansion of the knowledge base such that eco-friendly chemical processes can be quantified, controlled and optimized with high precision. This article offers some perspectives on possible engineering developments to accelerate the paradigm shift from fossil fuels to renewable energy.

Carbon dioxide splitting and hydrogen production using a chemical looping concept: A review

The gradually increasing atmospheric concentration of greenhouse gases has caused global climate change and subsequent environmental problems. To negate the emission of greenhouse gases from human activities, converting captured carbon into value-added products and changing our energy paradigm from fossil fuels to hydrogen both are significantly investigated. Chemical looping technology can offer several advantages since CO/H2 production efficiency can be enhanced due to the inherent product separation and autothermal operation. This report presents a brief review of the chemical looping process combined with CO2 or H2O splitting to provide CO or H2, respectively. Thermodynamic analysis was carried out to determine viable transition metal oxides. Various oxygen carriers for the chemical looping CO2/H2O splitting were categorized according to their structural characteristics. In addition, studies on different reactors, including fluidized-, moving bed-, and fixed bed-types which have proven their potential for realizing large-scale operation of chemical looping processes were summarized. Based on past advances and additional aspects of chemical looping, the authors strongly believe that this process offers a promising commercial technology that will contribute to carbon neutrality.

Group Contribution-Based Graph Convolution Network: Pure Property Estimation Model

Properties data for chemical compounds are essential information for the design and operation of chemical processes. Experimental values are reported in the literature, but that are too scarce compared with exploding demand for data. When the data are not available, various estimation methods are employed. The group contribution method is one of the standards and simple techniques used today. However, these methods have inherent inaccuracy due to the simplified representation of the molecular structure. More advanced methods are emerging, including improved molecular representations and handling experimental data. However, such processes also suffer from a lack of valid data for adjusting many parameters. We suggest a compromise between a complex machine learning algorithm and a linear group contribution method in this contribution. Instead of representing a molecule using a graph of atoms, we employed bulkier blocks—a graph of functional groups. The new approach dramatically reduced the number of adjustable parameters for machine learning. The result shows higher accuracy than the conventional methods. The whole process was also examined in various aspects—incorporating uncertainties in the data, the robustness of the fitting process, and detecting outlier data.

Integrating stochastic programming and reliability in the optimal synthesis of chemical processes

Plant availability and operating uncertainties are critical considerations for the design and operation of chemical processes as they directly impact service level and economic performance. This paper proposes a two-stage stochastic programming GDP (Generalized Disjunctive Programming) model with reliability constraints to deal with both the exogenous and endogenous uncertainties in process synthesis, where the reliability model is incorporated into the flowsheet superstructure optimization. The proposed stochastic programming model anticipates the market uncertainties through scenarios for selecting the optimal flowsheet topology, equipment sizes and operating conditions, while considering the impact of selecting parallel units for improving plant availability. An improved logic-based outer approximation algorithm is applied to solve the resulting hybrid GDP model, which effectively avoids numerical difficulties with zero flows and provides high quality design solutions. The applicability of the proposed modeling framework and the efficiency of solution strategy are illustrated with two well-known conceptual design case studies: methanol synthesis process and toluene hydrodealkylation process. The model, which integrates reliability (endogenous uncertainty) and exogenous uncertainty, shows the best economic performance with the increasing operational flexibility and plant availability.

Approaches to deep learning based manipulating strategy reconstructions for complex chemical processes

Modern complex chemical process operations produce a large amount of process monitoring and control time series data, which are potentially useful to extract valuable operating experiences and manipulating rules to improve the intelligence of process operations. Previous researches show that time series clustering is an effective method to mine historical control sequences. However, the actual working conditions often deviate from the historical data, making it difficult to reconstruct accurate process regulation manipulating strategies. In response to this problem, this paper proposes a manipulation strategies reconstruction method using a convolutional neural network model (MSR-CNN). Therein, the time series are hierarchically clustered according to the Levenshtein distance to obtain different classes of process disturbance states, and the corresponding manipulated sequences fragments obtained are treated with a symbolic aggregation approximation. Then the improved convolutional neural network is used for deep learning and manipulation strategies reconstruction of the process disturbance states and the corresponding manipulating sequences strings. Finally, applying to a numerical example and an ethanol–water distillation tower unit, the proposed method is proved to be effective. Compared with traditional supervisory control methods, our contributions can help well construct complex chemical process control strategies less dependent on human operators’ operating experiences.

A machine learning-based methodology for multi-parametric solution of chemical processes operation optimization under uncertainty

Chemical process operation optimization aims at obtaining the optimal operating set-points by real-time solution of an optimization problem that embeds a steady-state model of the process. This task is challenged by unavoidable Uncertain Parameters (UPs) variations. MultiParametric Programming (MPP) is an approach for solving this challenge, where the optimal set-points must be updated online, reacting to sudden changes in the UPs. MPP provides algebraic functions describing the optimal solution as a function of the UPs, which allows alleviating large computational cost required for solving the optimization problem each time the UPs values vary. However, MPP applicability requires a well-constructed mathematical model of the process, which is not suited for process operation optimization, where complex, highly nonlinear and/or black-box models are usually used. To tackle this issue, this paper proposes a machine learning-based methodology for multiparametric solution of continuous optimization problems. The methodology relies on the offline development of data-driven models that accurately approximate the multiparametric behavior of the optimal solution over the UPs space. The models are developed using data generated by running the optimization using the original complex process model under different UPs values. The models are, then, used online to, quickly, predict the optimal solutions in response to UPs variation. The methodology is applied to benchmark examples and two case studies of process operation optimization. The results demonstrate the methodology effectiveness in terms of high prediction accuracy (less than 1% of NRMSE, in most cases), robustness to deal with problems of different natures (linear, bilinear, quadratic, nonlinear and/or black boxes) and significant reduction in the complexity of the solution procedure compared to traditional approaches (a minimum of 67% reduction in the optimization time).

An integrated dimensionality reduction and surrogate optimization approach for plant‐wide chemical process operation

AbstractWith liquefied natural gas becoming increasingly prevalent as a flexible source of energy, the design and optimization of industrial refrigeration cycles becomes even more important. In this article, we propose an integrated surrogate modeling and optimization framework to model and optimize the complex CryoMan Cascade refrigeration cycle. Dimensionality reduction techniques are used to reduce the large number of process decision variables which are subsequently supplied to an array of Gaussian processes, modeling both the process objective as well as feasibility constraints. Through iterative resampling of the rigorous model, this data‐driven surrogate is continually refined and subsequently optimized. This approach was not only able to improve on the results of directly optimizing the process flow sheet but also located the set of optimal operating conditions in only 2 h as opposed to the original 3 weeks, facilitating its use in the operational optimization and enhanced process design of large‐scale industrial chemical systems.