Process Operation Research Articles

One-Class Classification-Based Monitoring of Mineral Processing Operations with Hyperensemble Tree-Models

Reliable monitoring of mineral process systems is key to more efficient plant operation. Multivariate statistical process control based on principal component analysis is well-established in industry, but may not be effective when dealing with nonlinear or transient processes, where process behaviour can change rapidly over time. Although many advances have been made in unsupervised process monitoring, the detection of incipient process drift or nascent abnormal process conditions remains an open research problem.In this investigation, monitoring of mineral process operations based on the use of random forest classifiers is considered. When the random forests are used, data representing normal operating conditions are split into subclasses with K-means clustering, after which an ensemble of random forests is trained as binary classifiers on the subclasses in a one-against-the-rest approach. These hyperensemble models are subsequently used to classify new operational data as in-control or out-of-control.One simulated and one real world case study are considered. In each case, the models were trained on data representing normal operating conditions and then tested on new process data that were generally different from the training data to test their ability to identify these data as out-of-control. In the real-world case study, the approach is compared with traditional multivariate statistical process monitoring based on a principal component model, as well as a recently proposed isolation forest model. The random forest-based models performed markedly better than the principal component model and slightly better than the isolation forest model as far as identification of out-of-control data were concerned, but this came at the expensive of a significantly larger false positive rate than these two models.

Fault Current Unified Calculation Method for Whole Process Fault Ride-Through of DFIG-Based Wind Farms

The present inaccurate fault current calculation, due to the incomplete consideration of whole process operation stages of fault ride-through (FRT) of DFIG-based wind farms (WFs), has a distinct impact on the safe operation of local power grid. To tackle this challenge, a fault current unified calculation (FCUC) method is proposed to achieve high-accuracy and high-speed mathematical analytical calculations of DFIGs output fault current during FRT. The proposed FCUC method mainly includes: 1) Whole process unified state space model, which contains transition stage, crowbar protection stage, demagnetization stage, reactive current compensation stage, and dc-chopper protection stage, is established to thoroughly consider FRTs different internal protection circuits and control strategies; 2) Stator output fault current is conducted by the unified state space model based on the stator residual voltage and the stator flux linkage; 3) Grid side converter (GSC) output fault current, which considers both injection mode and absorption mode, is developed based on the grid residual voltage and the unified state space model; 4) Fault current contribution mechanism, which is aggregated from both stator and grid side converter, is revealed based on Laplace transform from time-frequency-time domain, and is first expressed as an unified fault current expression. Extensive simulation/experimental/calculation results under different voltage sags have validated the correctness and effectiveness of the proposed FCUC method.

Environmental requirements in the standard for acceptance of petroleum products

The article discusses the current state of the process of receiving petroleum products at a gas station in order to eliminate and reduce losses and cycle time. A methodology for preparing a standard for obtaining petroleum products is presented and the effectiveness of its use at a gas station is determined. A standardized sequence of actions made it possible to detect problems and losses and reliably evaluate the efficiency of production processes. Based on the established sequence of operations for the process of receiving petroleum products, the standard work instructions (SWI) indicate the time for performing a separate process operation, the total time of the production cycle, the trajectory of movement through the facility between workplaces, and the classification of work taking into account compliance with safety and environmental requirements. As a result of the redistribution of all operations in order to eliminate and reduce losses and process cycle time, the best sequence of actions was established, which ensured the efficiency of the process of receiving petroleum products and environmental safety during the operation of gas stations.

Implementing virtuality in Social Network based Education

Virtuality, and its implementation process virtualization, is one of the most important concepts in Industry 4.0. Students of the engineering courses should adopt the related skills, i.e., to design different architectures and tools for virtuality implementation in organizations and develop skills for working within virtual environments. In Social Network based Education (SNE), virtuality is implemented in both dimensions in a “coupled” way, i.e., through the virtual architecture for the teaching process operation itself and as learning objects through experiential learning. This paper presents how the virtuality concept, i.e. the virtuality implementation model, is implemented in SNE process and methodology in the context of students’ effective learning of Industry 4.0 skills, and its evaluation based on a questionnaire. The results show that the majority of the students do not have problems with work within virtual environments, which, on the other hand, could be interpreted as an indicator for acceptance of fully virtual environments in professional work.

Hybrid prognosis of drill-bits based on direct inspection

Within the paradigm of industry 5.0, manufacturing systems are seeking for human-centred production, where the operator finds high-level supervision tasks. In this context, low-level decision making should be performed by machines themselves. In this paper, a hybrid prognosis algorithm is developed to automatically inspect the cutting edges of drill-bits and to predict their Remaining Useful Life (RUL) and the associated probability density function. The solution relies on the automatic measurement of flank wear through convolutional filtering and edge detection. Prognosis exploits particle filter, which updates multi-layer perceptron with online data, to adaptively predict drill-bits RUL. The solution reduces the experimental preliminary run-to-failures needed for training standard machine learning algorithms, exploiting them in a real-time adaptive scenario, while predicting tool RUL under untested and variable cutting process operations. The algorithm uses direct wear observations, taken during set-up times (e.g., tool changes, workpiece change), thus not interfering with the process.

Further study on particle size, stability, and complexation of silver nanoparticles under the composite effect of bovine serum protein and humic acid.

Silver nanoparticles (AgNPs) are widely used due to their unique antibacterial properties and excellent photoelectric properties. Wastewater treatment plants form a pool of AgNPs due to the social cycle of wastewater. During biological treatment processes, the particle size and stability of AgNPs change. We studied the particle size changes and stability of silver nanoparticles in the presence of bovine serum albumin (BSA) and humic acid (HA). The experimental results indicated that silver nanoparticles can complex with the functional groups in BSA. For AgNP-BSA composites, as the BSA concentration increases, the size of the silver nanoparticles first decreases and then increases. AgNPs can combine with the amide, amino, and carboxyl groups in HA. As the concentration of HA increases, the particle size and large particle size distribution of AgNPs increase. This increasing trend is more obvious when the HA concentration is lower than 20 mg L-1. When HA and BSA exist at the same time, HA will occupy the adsorption sites of BSA on the surface of AgNPs, and the AgNP-HA complex will dominate the system. This study aims to provide key operational control strategies for the process operation of wastewater treatment plants containing AgNPs and theoretical support for promoting water environment improvement and economic development such as tourism.

Creasing and folding of paper-based sandwich material–Phenomena and modelling

Creasing and folding are fundamental steps in many manufacturing processes of multi-material paperboard packaging. The complex structure of these materials, which comprise layers of cellulose fibres, aluminium, and polyethylene, coupled with the growing complexity of packaging designs, make these process operations essential to ensure the required structural integrity for packaging as well as their functionality in daily life. This paper introduces an approach for modelling damage in paper-based sandwich materials by integrating fibre-based and cohesive numerical modelling techniques. The results prove the effectiveness of the proposed methodology, opening new possibilities for process design and optimization in packaging manufacturing.

Machine Learning models to forecast defects occurrence on foundry products

Manufacturing defects negatively affect production cost and environmental impact. This impact is even heavier for production processes that are particularly energy intensive, such as in the metallurgical industry. In the cast iron foundry sector, components manufacturing can be affected by various defects that depend on quality of raw materials fed to the melting process, process parameters, cast iron final temperature, ferroalloys additions and final composition. Defects formation is a multifactorial phenomenon, for which relevant factors are not easy to identify, as it is also a rare event. This paper presents a set of models based on machine learning methodologies for predicting and classifying defects on foundry production lines to assist process operators in managing the process and, eventually, stop production when it is not possible to adjust process parameters. The modelling phase exploits decision trees methodologies enhanced with algorithms for augmenting unbalanced datasets related to defects occurrences. The combination of these methodologies produces efficient models showing very encouraging results.

Process Operating Performance Assessment for Plant-Wide Froth Flotation via Distributed Multigraph Deep Embedding Graph Clustering Network

Process Operating Performance Assessment for Plant-Wide Froth Flotation via Distributed Multigraph Deep Embedding Graph Clustering Network

Software Bug Prediction Using Machine Learning Approach

Abstract: Software defect prophecy work focuses on the number of faults remaining in a software system. A prophecy of the number of remaining scars in an audited artefact can be used for decision timber. An accurate prophecy of the number of scars in a software product during system testing contributes not only to the operation of the system testing process but also to the estimation of the product’s demanded conservation. amiss software modules beget software failures, increase development and conservation costs, and drop customer satisfaction. It strives to meliorate software quality and testing effectiveness by constructing predictive models from law attributes to enable a timely identification of fault-prone modules. In this design, we will explore machine knowledge ways for software defect prophecy . This helps the formulators to descry software scars and correct them. Unsupervised ways may be used for defect prophecy in software modules, more so in those cases where defect labels are not available.

Анализ грейферной выемки волокнистого торфяного сырья

The purpose of the study was to confirm the possibility of implementing the operations of the working cycle of mining equipment with the determination of the range of forces required to introduce the elements of the grab into the deposit and close the jaws in the massif, taking into account the design features of the grab. Research methodology. A series of field studies was carried out using full-scale models of the working bodies of a fork grab in the conditions of a peat deposit to confirm the possibility of implementing the process of extracting raw materials of a low degree of decomposition. Results. It has been established that the average value of the force required overcoming the resistance to the introduction of the grab model: on the site with magellanicum peat – 44.4 kN, with fuscum-peat – 61.5 kN. The average value of the normal stress when immersed in an array of a clamshell equipment element, taking into account the end surface area, is 89 kPa for: magellanicum peat, 123 kPa for fuscum-peat. The average value of the total deformation modulus in the natural occurrence of a peat deposit is 116 kPa for magellanicum peat and 126 kPa for fuscum-peat. The rational distance between the teeth of the jaw model of the fork grab has been determined. With a distance between the teeth of the grab jaw model l=0.25 m, a single drawing body is formed when the captured area of the material is shifted. Conclusion. With the determination of the effort ranges for the implementation of the two main operations of the excavation process, as well as the establishment of the design features of the grab for surface excavation, it was concluded that it is possible to use grab equipment for the surface extraction of fibrous peat raw materials.

Optimization approach of berth-quay crane-truck allocation by the tide, environment and uncertainty factors based on chaos quantum adaptive seagull optimization algorithm

The post-epidemic era has led to the accumulation of cargo, which has brought greater pressure to container ports. Since traditional methods cannot simultaneously consider the effect of tidal, uncertain, and environmental factors on the allocation plan. To relieve this pressure, firstly, considering tidal factors, formulating time window rules, thinking out uncertain factors, and determining constraints from three perspectives of vessel berthing process, quay crane and container truck operation, a new berth-quay crane-truck joint scheduling model is constructed by minimizing three aspects of vessels turnaround time, the carbon emissions of quay cranes and trucks, namely TEU-BQCT model. Then, aiming at obtaining a relatively high-quality solution, combining chaotic mapping and quantum entanglement, a new chaotic quantum adaptive seagull optimization algorithm is proposed, namely CQASOA, exclusive coding rules suitable for the TEU-BQCT model is formulated, a feasible integer algorithm is developed, the external penalty function is constructed to limit constraints, and a novel joint scheduling solution method of berth-quay crane-truck is proposed, namely TEU-BQCT_CQASOA. Subsequently, two ports of different scales in South China are used to test the constructed solution method feasibility. The simulation results indicate that the constructed TEU-BQCT model can obtain a more suitable scheduling scheme. The proposed CQASOA has better performance than other comparison algorithms selected in this paper, which can obtain a better solution when solving the TEU-BQCT model.

INVESTIGATION OF THE WEAR PROCESS OF MIXER ELEMENTS USING INFORMATION TECHNOLOGY

Today, mechanical engineering is one of the dynamically developing sectors of the economy of Kazakhstan. Any production process involving machines imposes requirements for reliability and durability to ensure stable and trouble-free operation of technological processes. In this regard, ensuring the operational characteristics of machines for a long time is a key factor when choosing a manufacturer. The quality of the materials used in the production of machines significantly affects the service life and operational characteristics of machines. The wear of machine parts is one of the main causes of breakdowns and accidents. The financial costs of car repair items are quite large. To date, the wear control of the mixer elements, removable elements of the blades is carried out only visually and replacement occurs without a system, after complete abrasion or breakage. Since these elements are not always available in the warehouse of the enterprise, downtime of equipment can take a considerable time. Modeling of the wear process of mixer elements in the matlab program allowed us to develop a simulation model using the vibroacoustic control method. Analysis and processing of vibration signals is carried out using standard programs. The developed algorithm of the process of monitoring the wear of the mixer elements allows you to form a library of signals and noises, comparing them with the reference values of the signals, to determine the degree of wear of the mixer elements. The algorithm can be implemented on standard hardware and software devices. Keywords: Mixer, wear, model, control, matlab, management.

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.

An integrated accounting system of the economic-social-ecological framework for assessing the value of intensive land use: A case study of the Taihu Lake governance project

Assessing the value of land resources is a prerequisite for resource management, as well as for resolving the conflict between supply and demand. In the realm of intensive land use (ILU), a standardized framework for accounting methods from a project perspective has yet to be established. Therefore, taking the Taihu Lake governance project (TLGP) (which includes the Xingou River project, Xinmeng River project and Zoumatang River project) as a case study, this paper firstly constructs an integrated value accounting system based on economic, social and ecological frameworks. Furthermore, with consideration of physical parameters, we incorporated the integrated land section price method, income reduction method, alternative market method, and equivalent factor method are all incorporated to assess the value of ILU at distinct stages within the research area. This approach serves to elucidate the evolving dynamics of ILU valuation. The results showed that: (1) There were significant differences in the values generated by the ILU in different projects. The integrated value of the TLGP brought about by ILU was 177,189,300 yuan, and the ILU of the Xinmeng River project was significantly higher than the Zoumatang River project and the Xingou River project. (2) The ILU at different stages basically displayed the law of diminishing marginal utility. Consistent with changes in the different stages of the TLGP, the value of ILU in Stage I of the Zoumatang River project and the Xingou River project was significantly higher than that in Stage II. Additionally, the accounting system proposed in this study has the advantages of reasonable index setting and simple process operability. This helps to realize the comparison of ILU values across projects and stages. The results of this study can provide a reference for the management and sustainable use of land resources during the construction of water conservancy and other projects.

Predicting the multispecies solid-state vinegar fermentation process using single-cell Raman spectroscopy combined with machine learning

Microbial community is a key contributing factor for flavor formation in natural food fermentation. However, it is a challenge to maintain batch-to-batch uniformity during the fermentation process due to the diversity and variability of microbial community. A rapid detection of the structure and function of the microbial community in the whole fermentation process is of great importance for quality control of the final fermentation products. Firstly, we employed amplicon sequencing to target the dominant operational taxonomic units in the microbial community of Zhenjiang aromatic vinegar, a traditional cereal vinegar. Secondly, we isolated and created a Raman database for 13 dominant bacterial species from vinegar culture, enabling us to establish a logistic regression model with 96.4% accuracy in species classification. Finally, a Raman-fermentation phase regression model was established, achieving an R2 of 0.952, accurately determining the actual fermentation phase of vinegar. This study offers a new method for dynamics monitoring of microbial community, prediction of fermentation state, and decision of subsequent production operations in multi-species fermentation processes.

Molecular Design of Functional Polymers for Silica Scale Inhibition.

Silica polymerization, which involves the condensation reaction of silicic acid, is a fundamental process with wide-ranging implications in biological systems, material synthesis, and scale formation. The formation of a silica-based scale poses significant technological challenges to energy-efficient operations in various industrial processes, including heat exchangers and water treatment membranes. Despite the common strategy of applying functional polymers for inhibiting silica polymerization, the underlying mechanisms of inhibition remain elusive. In this study, we synthesized a series of nitrogen-containing polymers as silica inhibitors and elucidated the role of their molecular structures in stabilizing silicic acids. Polymers with both charged amine and uncharged amide groups in their backbones exhibit superior inhibition performance, retaining up to 430 ppm of reactive silica intact for 8 h under neutral pH conditions. In contrast, monomers of these amine/amide-containing polymers as well as polymers containing only amine or amide functionalities present insignificant inhibition. Molecular dynamics simulations reveal strong binding between the deprotonated silicic acid and a polymer when the amine groups in the polymer are protonated. Notably, an extended chain conformation of the polymer is crucial to prevent proximity between the interacting monomeric silica species, thereby facilitating effective silica inhibition. Furthermore, the hydrophobic nature of alkyl segments in polymer chains disrupts the hydration shell around the polymer, resulting in enhanced binding with ionized silicic acid precursors compared to monomers. Our findings provide novel mechanistic insights into the stabilization of silicic acids with functional polymers, highlighting the molecular design principles of effective inhibitors for silica polymerization.

Near-infrared reflectance spectroscopy for rapid prediction of biochemical methane potential of wastewater wasted sludge

The information of biochemical methane potential (BMP) of wasted sludge is essential to ensure the stable operation of sludge management processes. However, conventional anaerobic digestion (AD) approach for BMP test is time-consuming and labour-intensive. Currently, the technique of Near Infrared Spectroscopy (NIRS) is gaining prominence in the biogas production within AD process. Previous studies mostly focused on predicting BMP values for fibrous plant biomass and solid waste, with only a limited number of studies attempting to apply NIRS to obtain BMP values across a wide array of wasted sludge types. To obtain BMP values for this diverse range of wasted sludge efficiently and accurately, it is imperative to develop precise models for assessing BMP values using NIRS. In this study, the possibility of using NIRS to predict the BMP values of wasted sludge was evaluated. A total of 70 sludge samples from different sources were investigated to develop a BMP-prediction model by correlating the measured BMP values with the obtained NIR spectra. As a result, a reliable and successful BMP-prediction model was established with the determination coefficient of 0.90, residual prediction deviation of 3.50 and low root mean square error of prediction of 36.8 mL CH4/g VS. This BMP-prediction model is satisfactory for predicting BMP values of various types of sludge. It could provide support for plant operators to make decisions rapidly, thereby improving the process efficiency and optimizing sludge management procedures.

UV-Crosslinked Poly(N-isopropylacrylamide) Interpenetrated into Chitosan Structure with Enhancement of Mechanical Properties Implemented as Anti-Fouling Materials.

High-performance properties of interpenetration polymer network (IPN) hydrogels, based on physically crosslinked chitosan (CS) and chemically crosslinked poly(N-isopropylacrylamide) (PNiPAM), were successfully developed. The IPN of CS/PNiPAM is proposed to overcome the limited mechanical properties of the single CS network. In this study, the viscoelastic behaviors of prepared materials in both solution and gel states were extensively examined, considering the UV exposure time and crosslinker concentration as key factors. The effect of these factors on gel formation, hydrogel structures, thermal stabilities of networks, and HeLa cell adhesion were studied sequentially. The sol-gel transition was effectively demonstrated through the scaling law, which agrees well with Winter and Chambon's theory. By subjecting the CS hydrogel to the process operation in an ethanol solution, its properties can be significantly enhanced with increased crosslinker concentration, including the shear modulus, crosslinking degree, gel strength, and thermal stability in its swollen state. The IPN samples exhibit a smooth and dense surface with irregular pores, allowing for much water absorption. The HeLa cells were adhered to and killed using the CS surface cationic charges and then released through hydrolysis by utilizing the hydrophilic/hydrophobic switchable property or thermo-reversible gelation of the PNiPAM network. The results demonstrated that IPN is a highly attractive candidate for anti-fouling materials.

Process Intensification of Electrodialysis through the Investigation and Elimination of Maldistribution

Often, advancements in electrochemical engineering processes stem from improvements at the microscale and in fundamental understanding. However, there is often much insight to be gained from identifying engineering challenges associated with process operation. Electrodialysis (ED) is an emerging electro separation technology which utilises a stack of ion selective membranes and an electric field to drive salt transfer between streams. Industrial implementation and intensification of ED is currently hindered by operational efficiencies being far from ideal. In this work, we explore a system-wide approach to investigate operational inefficiencies resulting from maldistribution in the flow between ED channels.Through computational fluid dynamics (CFD) simulations, it was shown that maldistribution is prevalent in ED. Further, a simplified analytical model demonstrated that the degree of maldistribution will be far more severe upon scale-up. In order to examine the effects of maldistribution on ED performance, transport models were built. These demonstrated that the limiting current density, and thus the maximum salt flux, was reduced by as much as 23% for a standard lab-scale stack. This will be much more significant upon scaleup, and therefore, overcoming maldistribution in ED can have significant benefits for process intensification. Validation of this was conducted through particle image velocimetry (PIV) and desalination experiments.A glass cell was constructed for PIV experiments with an identical geometry to that used for CFD simulations. A camera and telecentric lens was focussed on the channel centreline, and red and blue LEDs were sequentially pulsed. This light was scattered off particles in water flowing through the cell and collected by a single exposure image. The particle velocities were calculated from the superimposed red and blue images and a flow field was constructed. The experimentally determined flow field had excellent agreement with that found from CFD simulations, validating the existence of maldistribution in ED.Desalination experiments were conducted on a PC64004 ED stack operating in a steady state mode. The degree of maldistribution was independently altered by changing the flow rate while ensuring that the overall salt convective flux was constant. The LCD was subsequently measured by collecting current-voltage curves. results showed excellent consistency with the transport model, thereby validating the relationship between increased maldistribution and a lower LCD.In summary, in this work we have demonstrated and validated the presence of maldistribution in ED, as well as the significant detrimental effect it has on the upper limits of process intensification. Further, we have demonstrated the benefits of investigating system-wide inefficiencies in addition to fundamental phenomena. Future research will focus on developing methods to overcome maldistribution in ED. Figure 1