Process Industries Research Articles

Fault diagnostic method based on transfer dynamic deep learning for few shot temporal–spatial correlation industry process

AbstractData‐based fault diagnosis plays a crucial role in ensuring the safety of industrial processes. However, the complex industry process often has temporal–spatial correlation with insufficient labelled fault data. To settle these problems, a new transfer dynamic deep learning strategy that combines autoencoder (AE) with gate recurrent unit (GRU) is proposed. First, dynamic AE networks are introduced to extract the single‐attribute time series features, and the dynamic GRU is employed to extract the spatial correlation features among multiple feature dimensions and temporal correlation among samples. Then, to solve the problem of insufficiently labelled industrial data, the model‐based transfer learning between the sufficient laboratory data and insufficient labelled industrial data is executed. Experimental results based on the Tennessee Eastman (TE) process and the benchmark simulation model 1 (BSM1) process show that the proposed approach has excellent performance.

Digital twins: Transforming the chemical process industry—A review

AbstractDigital twin (DT) technology represents a significant advancement in the digital transformation of the chemical process industry (CPI), offering innovative capabilities for real‐time monitoring, predictive maintenance, and process optimization. This review investigates the current deployment status, frameworks, architectures, and applications of DTs within CPI, highlighting their transformative potential in improving operational efficiency, enhancing safety, and promoting sustainability. By examining case studies from industry leaders and analyzing recent advancements, this study elucidates the critical roles of DTs in asset health monitoring, process optimization, and environmental performance. The review identifies key components of DT frameworks, including data integration, hybrid modelling, and real‐time analytics, which are essential for effective implementation. It further explores challenges such as high computational requirements, integration with legacy systems, cybersecurity risks, and the lack of standardization, which impede widespread adoption. Despite these challenges, the paper emphasizes opportunities for leveraging advanced technologies such as artificial intelligence, edge computing, and 5G connectivity to enhance DT capabilities and scalability. In addition, this review underscores the importance of DTs in addressing global sustainability goals, mainly through their ability to optimize energy consumption, reduce emissions, and facilitate circular economy practices. By synthesizing insights from academia and industry, this study provides a comprehensive understanding of DTs' current state and future potential in CPI, offering strategic directions for research and development. The findings contribute to advancing the deployment of DTs as a cornerstone technology in achieving operational excellence, safety, and sustainability in the chemical process industry.

Penerapan Teknologi Ramah Lingkungan untuk Mengurangi Limbah pada Industri Pengolahan Kayu

The wood processing industry is a crucial sector that utilizes forest resources to produce various value-added products. In Pontianak City, wood processing industries produce items such as door and window frames, doors, windows, and cabinets. The aim of this study is to identify clean production alternatives for the wood processing industry. The research methods include field studies and descriptive analysis of the production process and the potential waste generated. The production process in Pontianak's wood processing industry includes several stages: receiving and unloading raw materials, cutting wood to the required size, profiling products, smoothing wood surfaces, and final assembly of finished products. Each of these stages has the potential to generate waste, including unused wood scraps, wood dust, and shavings from the smoothing process. This study offers recommendations for clean technologies that can be applied to reduce this waste. These clean technologies include the production of active carbon, using wood dust waste as partition material, producing bio briquettes and wood pellets as alternative fuels, and using wood waste as a growing medium for oyster mushroom cultivation. Additionally, wood waste can be used to create creative products, such as entertainment and educational games.

A Novel Machine Learning Technique for Fault Detection of Pressure Sensor

Pressure transmitters are widely used in the process industry for pressure measurement. The sensing line, a core component of the pressure sensor in the pressure transmitter, significantly impacts the accuracy of the pressure transmitter’s output. The reliability of pressure transmitters is critical in the nuclear power industry. Blockage is recognized as a common failure in pressure sensing lines; therefore, a novel detection method based on Trend Features in Time–Frequency domain characteristics (TFTF) is proposed in this paper. The dataset of pressure transmitters comprises both fault and normal data. This method innovatively integrates multi-scale time series decomposition algorithms with time-domain and frequency-domain feature extraction techniques. Initially, this dataset is decomposed into multi-scale time series to mitigate periodic component interference in diagnosis. Subsequently, via the sliding window algorithm, both the time-domain features and frequency-domain features of the trend components are extracted, and finally, the XGBoost algorithm is used to detect faults. The experimental results demonstrate that the proposed TFTF algorithm achieves superior fault detection accuracy for diagnosing sensing line blockage faults compared with traditional machine learning classification algorithms.

AGTM Optimization Technique for Multi-Model Fractional-Order Controls of Spherical Tanks

Spherical tanks are widely utilized in process industries due to their substantial storage capacity. These industries’ inherent challenges necessitate using highly efficient controllers to manage various process parameters, especially given their nonlinear behavior. This paper proposes the Approximate Generalized Time Moments (AGTM) optimization technique for designing the parameters of multi-model fractional-order controllers for regulating the output (liquid level) of a real-time nonlinear spherical tank. System identification for different regions of the nonlinear process is here innovatively conducted using a black-box model, which is determined to be nonlinear and approximated as a First Order Plus Dead Time (FOPDT) system over each region. Both model identification and controller design are performed in simulation and real-time using a National Instruments NI DAQmx 6211 Data Acquisition (DAQ) card (NI SYSTEMS INDIA PVT. LTD., Bangalore Karnataka, India) and MATLAB/SIMULINK software (MATLAB R2021a). The performance of the overall algorithm is evaluated through simulation and experimental testing, with several setpoints and load changes, and is compared to the performance of other algorithms tuned within the same framework. While traditional approaches, such as integer-order controllers or linear approximations, often struggle to provide consistent performance across the operating range of spherical tanks, it is originally shown how the combination of multi-model fractional-order controller design—AGTM optimization method—GA for expansion point selection and index minimization has benefits in specifically controlling a (difficult to be controlled) nonlinear process.

Simulation Model Exchange in Process Industry: Requirements, Solutions, and Open Challenges

AbstractSimulation models are crucial for various applications across the lifecycle of process plants, such as plant engineering. As the industry moves toward modularization, plant components are increasingly supplied by manufacturers who design these modular units, often called package units or process equipment assemblies. Consequently, critical knowledge about their behavior resides with the manufacturers. This paper outlines the requirements for simulation model exchange to share this behavioral knowledge. It reviews solutions and highlights challenges based on literature and case studies. Key elements include metadata, open standards, IP protection, and quality assurance. Solutions, like the asset administration shell (AAS), CAPE‐OPEN, the Functional Mock‐up Interface (FMI), encrypted models, and quality models, are discussed. Remaining gaps are highlighted.

Automatic Production Planning and Scheduling of Size

Automatic production planning and scheduling are critical for optimizing manufacturing processes in modern industries. This approach integrates advanced algorithms, machine learning, and real-time data analysis to streamline resource allocation, minimize production bottlenecks, and enhance overall efficiency. By automating traditionally manual planning tasks, the system improves accuracy and responsiveness to dynamic production demands. Challenges such as implementation costs, integration with existing systems, and data reliability are addressed through scalable architectures and robust predictive models. This study investigates innovative methodologies to achieve seamless coordination, examining their impact on productivity, cost reduction, and adaptability in competitive markets Key Words: optics, photonics, light, lasers, templates, journals

Solvometallurgical Properties of Choline Chloride-Based Deep Eutectic Solvents for Copper Extraction from Chalcopyrite: Optimization and Analysis

This paper focuses on the solvometallurgical properties of choline chloride-based deep eutectic solvents for copper extraction from chalcopyrite concentrate. The study, conducted with scientific rigor, utilized the response surface methodology to optimize the extraction process and investigate the effects of the temperature and contact time on the copper recovery efficiency. The results showed that the ChCl-EG-Ox solvent at 80 °C and 48 h produced the highest copper recovery rate, exceeding 76%. This underscores the potential of deep eutectic solvents for sustainable metal extraction. Kinetic studies revealed the influence of temperature on dissolution kinetics, with higher temperatures leading to faster reaction rates. The mineralogical analysis demonstrated the changes in the chalcopyrite concentrate after dissolution, while spectroscopy and mass spectrometry highlighted the esterification reactions in the solvent. The study also examined the effects of adding water and heating on the solvent’s behavior, providing insights into the chemical interactions and structural changes. Ultimately, the research demonstrated that ChCl-based deep eutectic solvents present a promising avenue for environmentally friendly and efficient copper extraction processes in the metallurgical industry.

Industry 4.0 and the Importance of an Ecosystem‐Based Approach: An Empirical Investigation Based on a Mixed‐Method Analysis

ABSTRACTThis paper will analyze the role of the innovation ecosystem (IES) in the industry implementation process of Industry 4.0 (I4.0) at company level. Based on a mixed‐method analysis using econometric models and content analysis, we have investigated the implementation process of industry 4.0‐enabling technologies of 123 manufacturing companies in the Hauts‐de‐France region of France. We have showed that the implementation process of industry 4.0‐enabling technologies is facilitated by the complexities of relationships between actors, complementarities among actors, particularly between start‐ups and others ecosystem stakeholders, and the role of regional policies (innovation support). Our quantitative results confirm that complex relationships with heterogenous actors within an IES positively affect the implementation process of Industry 4.0 at company level. While our qualitative analysis has showed that business‐to‐business relationships were decisive, our quantitative analysis has gone further and has showed that the more a given company develops diverse forms of relationships with other companies within the IES, the higher the level of I4.0 implementation‐enabling technologies there are in the company. Both qualitative and quantitative results demonstrate the importance of university‐industry linkage and of business incubators for the I4.0 implementation process, in enabling technologies at company level. A further result that completes our econometric study is the clear identification by company managers of the key role played by collaborative innovation projects and by start‐ups as providers of new solutions in fostering their I4.0 technological development. Therefore, our research calls for an ecosystem‐based approach to fostering I4.0 implementation at company level.

Water Treatment Technologies: Development of a Test Bench for Optimizing Flocculation-Thickening Processes in Laboratory Applications

This study introduces an automated test bench designed to optimize flocculation-thickening processes in the wastewater treatment industry. Addressing current challenges in operational efficiency and cost reduction, the test bench employs Model-Based Systems Engineering (MBSE) principles, leveraging SysML modeling within the CESAM framework. By integrating advanced technologies, including PLC programming and a closed-loop control system, this bench provides precise and efficient testing under varying operational conditions. Economic implications are explored, demonstrating the cost-effectiveness of optimized flocculation processes, which reduce chemical use and operational expenditures while enhancing water clarity and sludge management. The system’s 3D modeling enables detailed simulations, aiding in both research and pedagogical applications. This platform highlights the potential of MBSE in creating scalable, robust solutions that contribute to sustainable water management.

Tailoring Metal-Organic Frameworks for One-Step Separation of Alkane/Alkene/Alkyne Mixtures.

The purification of polymer-grade (>99.9%) olefins (mostly C2 and C3) represents a significant yet challenging process in petrochemical industry. The commonly employed method for hydrocarbon separation involves heat-driven distillations. Adsorptive separation based on porous solids offer the potential to purify olefins under ambient conditions, rendering considerable energy and environmental benefits. In particular, one-step purification of alkenes through selective adsorption of their corresponding alkanes and alkynes stands out as a promising technique. Notably, metal-organic frameworks (MOFs), possessing finely tunable pore structures (pore size/shape/internal chemical environment), hold great potential in this regard. In this review article, we outline recent progresses in the development of MOFs for one-step adsorptive purification of alkenes from alkane/alkene/alkyne ternary mixtures, with an emphasis on the rational regulation of pore structures for desired separation.

Integrated Risk Framework (IRF)—Interconnection of the Ishikawa Diagram with the Enhanced HACCP System in Risk Assessment for the Sustainable Food Industry

This paper presents a new risk assessment methodology called the Integrated Risk Framework (IRF) through the application of Ishikawa diagrams combined with the enhanced Hazard Analysis and Critical Control Point (HACCP) system. This risk investigation technique aims to ensure a significantly higher level of quality, safety, and sustainability in food products by using improved classical methods with strong intercorrelation capabilities. The methodology proposes expanding the typology of basic physical, chemical, and biological risks outlined by the ISO 22000 Food Safety Management System standard, adding other auxiliary risks such as allergens, fraud/sabotage, Kosher/Halal compliance, Rapid Alert System for Food and Feed notification, or additional specific risks such as irradiation, radioactivity, genetically modified organisms, polycyclic aromatic hydrocarbons, African swine fever, peste of small ruminants, etc. depending on the specific technological process or ingredients. Simultaneously, it identifies causes for each operation in the technological flow based on the 5M diagram: Man, Method, Material, Machine, and Environment. For each identified risk and cause, its impact was determined according to its severity and likelihood of occurrence. The final effect is defined as the risk class, calculated as the arithmetic mean of the impact derived at each process stage based on the identified risks and causes. Within the study, the methodology was applied to the spring water bottling process. This provided a new perspective on analyzing the risk factors during the bottling operations by concurrently using Ishikawa diagrams and HACCP principles throughout the product’s technological flow. The results of the study can form new methodologies aimed at enhancing sustainable food safety management strategy. In risk assessment using these two tools, the possibility of cumulative or synergistic effects is considered, resulting in better control of all factors that may affect the manufacturing process. This new perspective on studying the dynamics of risk factor analysis through the simultaneous use of the fishbone diagram and the classical HACCP system can be extrapolated and applied to any manufacturing process in the food industry and beyond.

Identification and Prioritization of Criteria Affecting the Location of Safe Assembly Points Using the Best-Worst Method

Introduction: Identifying secure gathering spots during emergencies is a crucial step in emergency management across multiple industries, particularly in oil, gas, and petrochemical fields. This study was designed to identify and rank the factors affecting the placement of safe assembly points for implementation in the country’s process industries. Materials and Methods: This descriptive-exploratory study was conducted at the National Petrochemical Company. During the initial phase, criteria affecting the selection of safe assembly points were determined by examining scientific literature, standards, guidelines, along with national and international directives. A Delphi study involving 15 experts in emergency management experts was subsequently conducted to finalize the criteria list . During the second phase, these criteria were prioritized and ranked through a multi-criteria decision-making method utilizing and the Best-Worst Method. Results: The Delphi study was completed after two rounds, revealing 10 internal and 7 external criteria, amounting to 17 criteria that affect the determination of safe assembly points during emergencies in processing industries. Within the internal criteria, accessibility was the highest rated (weight: 0.1948), vulnerability to incidents was second (weight: 0.1543), and travel time was third (weight: 0.1109). Among the external criteria, the distance from nearby hazardous centres was the highest (weight: 0.2181), the type of potential scenarios was second (weight: 0.2081), and nearby emergency facilities placed third (weight: 0.1462). Conclusion: In process industries, the placement of safe assembly points during emergencies must take into account factors like the distance from surrounding hazardous areas, the type of possible incidents, ease of access, vulnerability to incidents, nearby emergency services, and wind patterns to guarantee optimal personnel protection.

Modeling and Evaluation of Attention Mechanism Neural Network Based on Industrial Time Series Data

Chemical process control systems are complex, and modeling the controlled object is the first task in automatic control and optimal design. Most chemical process modeling experiments require test signals to be applied to the process, which may lead to production interruptions or cause safety accidents. Therefore, this paper proposes an improved transformer model based on a self-attention mechanism for modeling industrial processes. Then, an evaluation mechanism based on root mean square error (RMSE) and Kullback–Leibler divergence (KLD) metrics is designed to obtain more appropriate model parameters. The Variational Auto-Encoder (VAE) network is used to compute the associated KLD. Finally, a real nonlinear dynamic process in the petrochemical industry is modeled and evaluated using the proposed methodology to predict the time series data of the process. This study demonstrates the validity of the proposed transformer model and illustrates the versatility of using an integrated modeling, evaluation, and prediction scheme for nonlinear dynamic processes in process industries. The scheme is of great importance for the field of industrial soft measurements as well as for deep learning-based time series prediction. In addition, the issue of a suitable time domain for the prediction is discussed.

Surface-Enhanced Raman Spectroscopy for the Detection of Reactive Oxygen Species.

Reactive oxygen species (ROS) play fundamental roles in various biological and chemical processes in nature and industries, including cell signaling, disease development and aging, immune defenses, environmental remediation, pharmaceutical syntheses, metal corrosion, energy production, etc. As such, their detection is of paramount importance, but their accurate identification and quantification are technically challenging due to their transient nature with short lifetimes and low steady-state concentrations. As a highly sensitive and selective analytical technique, surface-enhanced Raman spectroscopy (SERS) is promising for detecting ROS in real-time, enabling in situ monitoring of ROS-involved electrochemical and biochemical events with exceptional resolution. This review provides a comprehensive analysis of the state-of-the-art in the SERS-based detection of ROS. Herein, the principles and ROS sensing mechanisms of SERS have been critically evaluated, highlighting their emerging applications in direct and indirect ROS monitoring in electrochemical and biological systems. The developments and reaction schemes of selective SERS probes for superoxide (•O2-), hydroxyl radicals (•OH), nitric oxide (•NO), peroxynitrite (ONOO-), and hypochlorite (OCl-) are presented. Finally, technical challenges and future research directions are discussed to guide the design of SERS for ROS analysis.

MISMS: a multistep-ahead and interpretable sequential modelling scheme for the long-term dynamic forecasting in process industries

This paper introduces Multistep-ahead and Interpretable Sequential Modeling Scheme (MISMS), a pioneering approach for long-term dynamic forecasting that enhances model interpretability in process industries. MISMS is distinguished by its innovative integration of multivariate analysis, multistep-ahead forecasting, and sequential model interpretability. The scheme incorporates knowledge embedding and Exploratory Data Analysis (EDA) to structure multiple variables and extract their temporal attributes. Based on this groundwork, sequence-to-sequence (Seq2Seq) submodels are developed to capture domain-wide dynamics rather than one single value. Crucially, MISMS has pioneered the application of sequence interpretation for model decomposition and transparency, improving interpretability. The proposed scheme employs different temporal models in practical scenarios and can ensure a better prediction with long-term accuracy and stability. Additionally, discussions on the model explainer's expected and unexpected outcomes are conducted, providing potential avenues for future research in process industries.

Reaction Engineering for Asymmetric R‐/S‐PAC Synthesis With Ephedrine or Pseudoephedrine Dehydrogenase in Pickering Emulsion

ABSTRACTThe synthesis of enantiopure α‐hydroxy ketones, particularly R‐ and S‐phenylacetylcarbinol (PAC), represents an important process in the pharmaceutical industry, serving as a pivotal step in the production of drugs. Recently, two novel enzymes, ephedrine dehydrogenase (EDH) and pseudoephedrine dehydrogenase (PseDH), have been described. These enzymes enable the specific reduction of 1‐phenyl‐1,2‐propanedione (PPD) to R‐PAC and S‐PAC, respectively. In this study, we transferred these enzymes into Pickering emulsions, which is an attractive reaction set‐up for large‐scale synthesis. The bioactive w/o Pickering emulsion (bioactive Pickering emulsion [BioPE]), in which methyl tert‐butyl ether served as the continuous phase, was stabilized by silica nanoparticles. Formate dehydrogenase from Rhodococcus jostii was utilized for cofactor regeneration. Given the considerable complexity of the BioPE, this reaction system underwent a first‐time application of design of experiment (DOE) for systematic engineering. A definitive screening design was employed to identify significant factors affecting space‐time yield (STY) and conversion. Response surface methodology was used to optimize the conditions, resulting in the observation of a high STY of 4.2 g L⁻¹ h⁻¹ and a conversion of 83.2% for BioPE with EDH, and an STY of 4.4 g L⁻¹ h⁻¹ and a conversion of 64.5% for BioPE with PseDH.

Surface characteristics and molecular interactions of thin films between bubbles by molecular simulations.

Whether in industrial production or daily life, froth plays an important role in many processes. Sometimes, froth exists as a necessity and is also regarded as the typical characteristic of products, e.g., froth on shampoo. Froth often makes an important contribution to product performance, such as in cleaning operations. On the other hand, froth may destroy the production process, such as in the textile and paper industry. Another example, ultra-stable froth accumulates on the thickener from flotation brings a series of difficulties to pumping, settling and dewatering operations, and would lead to pollution to the industrial circulating water treatment, thus it must be prevented. In this work, the factors affecting the stability of froth, and relationship of bubble coalescence and film rupture was investigated, and molecular simulations (MD) were performed to study the aqueous molecular formation and surface characteristics of thin films between bubbles that contribute to the froth stability. The detailed interfacial structure, molecular formation along Z-axis, angle distribution within the first and second layer, and also critical thickness were studied and discussed. The film rupture was validated and interpreted by the water-water interactions within the thin film, and these surface interactions were also examined using binding energy, dipole autocorrelation function (DAF). These simulations explicitly utilize polarizable potential model, incorporating many-body interactions, in which induced polarization plays a critical role in reproducing experimental observables and understanding physical behavior. The results provide beneficial insight for ultra-stable removal from microscopic view, and have direct benefits in dissolved air flotation used in mining industry, to develop efficient and sustainable processes for industries to minimize water and chemical usage.

Quality control and safety of raw materials for the compound feed industry

The volume of feed production in our country in terms of feed units in 2021 amounted to 105.8 million tons. The quality of feed directly depends on the quality and safety of raw materials. If all requirements for the quality and safety of raw materials are met, the nutritional properties of feed will be preserved, which will ensure livestock growth, and the consumer will receive high-quality dairy and meat products. The purpose of the research was to substantiate the importance of incoming quality control and safety of raw materials and documentary registration of this process in the compound feed industry. The work summarized the requirements for the safety of feed production, which includes incoming quality control of raw materials. Three hazards associated with incoming raw material control have been identifi ed, critical control points have been established, controlled parameters, monitoring procedures and controlled actions in the HACCP worksheet have been determined. The quality of incoming control depends on the implementation of procedures regulating the incoming control process. In quality management, a process map is often used to document processes. A process map has been developed that describes the incoming control of raw materials of suppliers and consumers, types of activities within the process, regulatory documentation, records, and the necessary resources. Process indicators and control results are also recommended. The documents were tested using the example of incoming control of soybean oil cake. The obtained results of testing raw materials for contamination, toxicity, humidity and protein met the requirements of State National Standard R 53799–2010 for feed soybean meal. Conducting incoming control in accordance with the process map will ensure compliance with the technology of incoming control of raw materials and minimize the risks associated with three hazardous factors.

Separation effectiveness of ideal ion exchange membranes: Application of the Gibbs-Donnan theory.

Ion exchange membranes (IEMs) are permselective membranes that, in principle, only allow the flow of ions with a specific charge sign, opposite to that of the fixed membrane ionic groups (counter-ions). This charge-based selectivity, like the size-based selectivity of classic semipermeable membranes, leads to an uneven distribution of permeating ions on the two sides of the membrane, which allows for ion separation or recovery in various processes in industry or environmental protection. Here, we apply the principles of mass balance, charge neutrality, and equality of electrochemical potentials in the state of thermodynamic equilibrium to provide a simple method for estimating the Gibbs-Donnan factors and the equilibrium concentrations of permeating ions in two compartments separated by an ideal IEM, i.e. an IEM that is not permeable to co-ions. We present the method for the case when the equilibrium concentrations are known in one compartment and need to be estimated in the other compartment as well as for the case when the total masses of ions in both compartments are known and their equilibrium concentrations need to be predicted. For both cases, the presented nonlinear algebraic equations require in general the use of numerical methods to approximate their mathematical solutions, although we present as well some closed solutions for simple cases with ideal ionic mixtures. Based on the extended Debye-Hückel theory, we also provide analogous equations (general and for specific cases) for systems with non-ideal ionic mixtures. The presented method can provide the expected ideal separation effectiveness of an IEM, which can then be used to assess the relative separation effectiveness of a real membrane.