Optimization Model Of Process Research Articles

Optimizing Hydrogen Production in the Co-Gasification Process: Comparison of Explainable Regression Models Using Shapley Additive Explanations.

The co-gasification of biomass and plastic waste offers a promising solution for producing hydrogen-rich syngas, addressing the rising demand for cleaner energy. However, optimizing this complex process to maximize hydrogen yield remains challenging, particularly when balancing diverse feedstocks and improving process efficiency. While machine learning (ML) has shown significant potential in simulating and optimizing such processes, there is no clear consensus on the most effective regression models for co-gasification, especially with limited experimental data. Additionally, the interpretability of these models is a key concern. This study aims to bridge these gaps through two primary objectives: (1) modeling the co-gasification process using seven different ML algorithms, and (2) developing a framework for evaluating model interpretability, ultimately identifying the most suitable model for process optimization. A comprehensive set of experiments was conducted across three key dimensions, generalization ability, predictive accuracy, and interpretability, to thoroughly assess the models. Support Vector Regression (SVR) exhibited superior performance, achieving the highest coefficient of determination (R2) of 0.86. SVR outperformed other models in capturing non-linear dependencies and demonstrated effective overfitting mitigation. This study further highlights the limitations of other ML models, emphasizing the importance of regularization and hyperparameter tuning in improving model stability. By integrating Shapley Additive Explanations (SHAP) into model evaluation, this work is the first to provide detailed insights into feature importance and demonstrate the operational feasibility of ML models for industrial-scale hydrogen production in the co-gasification process. The findings contribute to the development of a robust framework for optimizing co-gasification, supporting the advancement of sustainable energy technologies and the reduction of greenhouse gas (GHG) emissions.

Hybrid MCDM-FMEA Model for Process Optimization: A Case Study in Furniture Manufacturing

The furniture-manufacturing industry is pressured to improve quality, productivity, and profitability, particularly within increasingly volatile market conditions. This study is focused on the development of methods for optimizing production processes in a furniture-manufacturing company through the application of an integrated risk management framework. By integrating Failure Mode and Effects Analysis (FMEA) with advanced multi-criteria decision-making (MCDM) techniques, specifically fuzzy AHP, fuzzy TOPSIS, and fuzzy WINGS, a hybrid model is developed to identify, prioritize, and address critical failure points while accounting for complex interdependencies. Significant failure modes, such as order inaccuracies and delivery delays, are revealed as key findings and are found to notably affect productivity and customer satisfaction. The proposed model’s ability to capture cascading effects and a nuanced prioritization enables a more precise risk assessment, thereby supporting resilience and process efficiency in the furniture-manufacturing sector. This approach is shown to not only optimize production but also provide a foundation for applying such hybrid models in other industries to manage sector-specific interdependencies effectively.

Numerical Design Structure Matrix–Genetic Algorithm-Based Optimization Method for Design Process of Complex Civil Aircraft Systems

In the requirement-driven forward design process of civil aircraft, the large number of design tasks of complex systems with varying difficulty and the complex relationships between design tasks lead to unnecessary repetitive design iterations. In order to solve the above problems, the concept of overlap coefficient is proposed to further sort out the forward and backward logical relationships between design tasks and the civil aircraft system design process optimization model based on a numerical design structure matrix. The algorithm NSGA-II is improved and verified with the flight control system design as a case study. The results show that the proposed method can effectively improve the efficiency of complex system design and provide technical support for the optimization of the design process of complex civil aircraft systems.

Application of flotation kinetics models to chalcopyrite flotation: determination of optimum flotation times

This study advances the field of flotation kinetics by deriving and comparing optimum flotation time equations for eight different kinetic models in chalcopyrite beneficiation. While Agar (1985) established the method for finding the optimum flotation time for his specific model, this research extends the application to multiple established flotation kinetic models, a calculation largely unexplored in flotation literature since Agar’s work. Selective flotation data from ore samples (Gümüşhane, Türkiye) were fitted to eight kinetic models, all showing high correlation (R2 > 0.97) with experimental results. The optimum flotation times were calculated by equating each model’s recovery rate derivatives for valuable minerals and gangue. This method revealed that most models predicted optimal times between 0.8 and 1.0 min, with one model diverging at 3.1 min. The Agar kinetic model (Model 7) demonstrated a superior fit for both chalcopyrite and gangue recovery curves. By deriving equations for multiple models, the study provides a comprehensive framework for comparing and selecting appropriate kinetic models in flotation circuit design. These equations offer valuable insights into the critical nature of precise timing in chalcopyrite flotation and highlight the importance of considering multiple kinetic models for process optimization. The derived equations contribute to more efficient and sustainable chalcopyrite beneficiation techniques, which are particularly relevant for processing lower-grade copper ores in industrial applications and expanding the toolkit available for researchers and practitioners in flotation kinetics optimization.

Hybrid manufacturing thermal environment cycle and industrial economic transformation based on artificial intelligence

With the continuous development of global manufacturing, hybrid manufacturing has become an important way to improve production efficiency and respond to market demand. However, traditional manufacturing enterprises face many challenges in thermal environment management and energy consumption, and urgently need to achieve transformation and upgrading through artificial intelligence technology. This article aims to explore the thermal environment cycle of hybrid manufacturing based on artificial intelligence and its impact on industrial economic transformation, in order to provide theoretical support and practical guidance for manufacturing enterprises in intelligent manufacturing and energy management. We have researched and designed an intelligent manufacturing system, clarified the design principles and requirements of the system, constructed the system architecture, and designed the functional modules in detail. By collecting and processing data, using intelligent scheduling prediction technology to simulate the thermal environment of the manufacturing workshop, and then simulate the energy consumption situation. Finally, a manufacturing workshop scheduling model was constructed, process optimization strategies were proposed, and the transformation path of industrial economy was explored. Research has shown that through the implementation of intelligent manufacturing systems, the energy consumption of manufacturing workshops is significantly reduced, the thermal environment is effectively improved, and the application of process optimization and scheduling models greatly improves production efficiency. The exploration of the path of industrial economic transformation provides new ideas for the sustainable development of enterprises in the new situation.

Process optimization and finite element modeling in magnetorheological abrasive finishing of SS-316L with surface characterization

This study explores the potential of Magnetorheological Abrasive Finishing (MRAF) for ultra-precision finishing of SS-316L using a high-performance Nd-Fe-B (N-35 grade) magnetic tool. Key parameters, including the relationship between normal force (Fn) and working gap, magnetic flux distribution, and finishing spot area, were analyzed using ANSYS 2020 R1® Magnetostatic module simulations. Material removal rate (MRR) and surface roughness (Ra) were optimized through response surface methodology (RSM) using a central composite design (CCD) with two primary input factors: SiC abrasive volume fraction (5%, 10%, 15%) and abrasive mesh size (800, 1000, 1200). Statistical analysis via ANOVA revealed a significant influence of process variables, achieving a remarkable surface finish with a minimum Ra of 52 nm in just 60 min, utilizing an MR fluid with 10% SiC abrasives. Microscopic and spectroscopic evaluations confirmed enhanced surface morphology and microstructural refinement. Moreover, bioactivity studies in simulated body fluid highlighted improved hydroxyapatite layer formation on the finished SS-316L samples, underscoring the process’s potential for biomedical applications.

Attention-based CNN model for motor imagery classification from nonlinear EEG signals

Motor imagery (MI)-based brain–computer interface (BCI) provides a promising solution for the limb rehabilitation of stroke patients. For better rehabilitation performance, high-precision classification of MI-related EEG signals plays a critical role. However, this is still a challenging problem for multi-category MI signals. In this paper, we focus on four commonly used stroke rehabilitation actions, and propose a modular temporal–spatial attention-based CNN (MTSACNN) model for MI classification. In detail, we carry out the MI experiments and acquire the EEG signals related to imagining left/right fist clenching and left/right wrist dorsiflexion. MTSACNN model firstly extracts the low-order MI features through the temporal–spatial feature extraction module (TSFE module). Especially, a group attention mechanism is proposed for intra-group information interaction. Secondly, considering the short- and long-term working characteristics of brain, high-order temporal features are further extracted and fused by the multi-level feature fusion module (MLFF module). Finally, four auxiliary losses are arranged in the classification module (C module) to speed up the model optimization process. The experimental results show that MTSACNN model can achieve good performance in decoding rehabilitation-related MI brain intentions, achieving an average classification accuracy of 72.05% for fourteen subjects. This work is beneficial to promote the construction of high-performance stroke rehabilitation BCI system.

Digital Transformation Strategy of Macys: Addressing Challenges and Achieving Revival

Abstract: This study explores the challenges faced by Macys in the United States and its strategy for digital transformation. Firstly, it introduces the rise and fall of the U.S. department store industry and the challenges Macys faces as a representative of the traditional department store industry, such as the rise of e-commerce and changes in consumer shopping habits. Then, taking Macys as a case study, it describes its digital transformation strategy, Polaris, including cost reduction, accelerated digitization, reshaping the supply chain and other initiatives and the results achieved. It then proposes specific plans for staffing adjustments, enterprise transaction process optimization and online business model modifications. Finally, the challenges that may be faced in implementing digital transformation programs, such as data silos, change management and financial overheads, are analyzed, and solutions are proposed. By summarizing and learning from the successful experiences of modern enterprises, this study proposes a series of feasible digital transformation plans for Macy's to emerge from the predicament of the traditional department store industry, meet the challenges of the digital era, and achieve a renaissance.

Mitigating social bias in sentiment classification via ethnicity-aware algorithmic design

Sentiment analysis tools are frequently employed to analyze large amounts of natural language data gathered from social networks and generate valuable insights on public opinion. Research has discovered that these tools tend to be biased against some demographic groups, based on social attributes such as gender, age, and ethnicity. Sentiment classification works dealt with this issue by means of data balancing and algorithmic approaches. However, one crucial limitation of existing methods is the inability to tackle social bias while maintaining satisfactory model performance. In this paper, we aim to fill this gap by proposing a sentiment classification method that entails ethnicity-aware algorithmic design. Specifically, our method involves balanced training and a custom ethnicity-aware loss function that leverages ethnicity group information to foster a fair model optimization process. The proposed loss incentivizes the model to iteratively improve accuracy for currently underperforming demographic or social groups, therefore simultaneously decreasing social bias and boosting overall performance. Our extensive qualitative and quantitative experimental evaluation involving a large corpus of user reviews demonstrated the effectiveness of the proposed method, also when compared to popular baselines for sentiment classification.

Prediction of mechanical properties of manufactured sand polymer-modified mortar based on swarm intelligence algorithm

Because polymer-modified mortar (PMM) exhibits a complex and diverse composition, there is a complex nonlinear relationship between its mechanical properties and mix proportions that is challenging for conventional mechanical performance prediction methods to accurately predict. Consequently, in this study, a predictive model utilizing a backpropagation neural network (BPNN) was formulated, featuring a structure of 6–14-2. Simultaneously, three swarm intelligence algorithms were integrated—the ant colony optimization algorithm, grey wolf optimization algorithm, and bat optimization algorithm (BAT)—to collectively refine the optimization process of the BPNN prediction model. The model's input layer included cement (OPC), cellulose ether (CE), dispersible polymer powder (DPP), antifoam (AF), fly ash (FA), and tuff stone powder (SP), and the output layer consisted of the compressive and bond strengths. The model dataset comprised 520 samples (260 × 2), with 60 % (312) used for model establishment and 40 % (208) used for validation. Correlation matrix and principal component analyses were conducted on the dataset, along with a comparative analysis of the factors influencing the mechanical performance evaluation indicators. The results indicate that at 7 and 28 d, there was a positive correlation between the DPP and AF with the development of PMM mechanical properties. At 7 d, the SP and FA were negatively correlated with the compressive and flexural strength, whereas the CE was positively correlated with the bond strength. At 28 d, the OPC was negatively correlated with the compressive, bond, and flexural strengths, and positively correlated with the SP and FA. C3 represents the optimal mix proportion for the PMM, and considering the influence of all raw materials, F3 was identified as the comprehensive optimal mix proportion. The predictive performance evaluation indicators of the BAT–BPNN for the compressive and bond strengths were R2 = 0.980 and 0.942, MAE = 5.967 and 1.958, MAPE = 0.071 and 0.041, and RMSE = 4.686 and 1.594, respectively. BAT significantly improves the predictive accuracy of the BPNN model, enabling the prediction of PMM mechanical properties and providing a scientific basis for its mix proportion design.

Integrating different fidelity models for process optimization: A case of equilibrium and rate-based extractive distillation using ionic liquids

We integrate equilibrium and rate-based models to formulate a hybrid optimization scheme for designing an ionic liquid-based extractive distillation process for mixed-refrigerant separation. The equilibrium model assumes vapor–liquid equilibrium at each stage but challenges arise with low-volatility, high-viscosity solvents, which drive the system away from equilibrium. The rate-based approach considers mass and heat transfer rates, giving more accurate representation. We compare the two models for separating R-410A, an azeotropic mixture of R-32 and R-125, using [EMIM][SCN] ionic liquid as entrainer. Analyzing over 4300 simulations with various dimensionality reduction and topological analysis techniques, we find that predictions from the two models exhibit similar trends, but the overestimation in equilibrium-based purities sometimes leads to infeasible process designs. The proposed optimization algorithm thus combines the strengths of the two models to locate feasible and optimal designs.

Supercritical CO2 as a green technology for carotenoids-rich virgin palm oil production: Process optimization, kinetics and thermodynamics modeling

The experimental conditions of supercritical carbon dioxide (scCO2) extraction of virgin palm oil (VPO) from oil palm mesocarp fiber (OPMF) were optimized using the Response Surface Methodology (RSM). Results showed that a maximum of 28.68 % of VPO extraction was obtained at the optimal experimental conditions of scCO2 extraction: pressure of 31 MPa, temperature of 340 K, and extraction time of 80 min. The second-order rate equation, Arrhenius equation and Eyring theory were employed to assess the kinetics behaviour, activation energy and thermodynamics behaviour of scCO2 extraction of VPO from oil palm mesocarp fiber. The lower activation energy value (12.17 kJ/mol) of scCO2 for the extraction of VPO from OPMF indicates that the scCO2 extraction technology is less dependent on temperature during the extraction of VPO from OPMF. The physicochemical properties and fatty acids compositions analyses reveal that the scCO2 extracted VPO contains high carotenoids content (982 μg/g), low free fatty acids content (0.31 wt%), higher oxidative stability and higher unsaturated fatty acids content.

The Evolution of Dilatant Shear Bands in High-Pressure Die Casting for Al-Si Alloys

Bands of interdendritic porosity and positive macrosegregation are commonly observed in pressure die castings, with previous studies demonstrating their close relation to dilatant shear bands in granular materials. Despite recent technological developments, the micromechanism governing dilatancy in the high-pressure die casting (HPDC) process for alloys between liquid and solid temperature regions is still not fully understood. To investigate the influence of fluid flow and the size of externally solidified crystals (ESCs) on the evolution of dilatant shear bands in HPDC, various filling velocities were trialled to produce HPDC samples of Al8SiMnMg alloys. This study demonstrates that crystal fragmentation is accompanied by a decrease in dilatational concentration, producing an indistinct shear band. Once crystal fragmentation stagnates, the enhanced deformation rate associated with a further increase in filling velocity (from 2.2 ms−1 to 4.6 ms−1) localizes dilatancy into a highly concentrated shear band. The optimal piston velocity is 3.6 ms−1, under which the average ESC size reaches the minimum, and the average yield stress and overall product of strength and elongation reach the maximum values of 144.6 MPa and 3.664 GPa%, respectively. By adopting the concept of force chain buckling in granular media, the evolution of dilatant shear bands in equiaxed solidifying alloys can be adequately explained based on further verification with DEM-type modeling in OpenFOAM. Three mechanisms for ESC-enhanced dilation are presented, elucidating previous reports relating the presence of ESCs to the subsequent shear band characteristics. By applying the physics of granular materials to equiaxed solidifying alloys, unique opportunities are presented for process optimization and microstructural modeling in HPDC.

Edge-assisted U-shaped split federated learning with privacy-preserving for Internet of Things

In the realm of the Internet of Things (IoT), deploying deep learning models to process data generated or collected by IoT devices is a critical challenge. However, direct data transmission can cause network congestion and inefficient execution, given that IoT devices typically lack computation and communication capabilities. Centralized data processing in data centers is also no longer feasible due to concerns over data privacy and security. To address these challenges, we present an innovative Edge-assisted U-Shaped Split Federated Learning (EUSFL) framework, which harnesses the high-performance capabilities of edge servers to assist IoT devices in model training and optimization process. In this framework, we leverage Federated Learning (FL) to enable data holders to collaboratively train models without sharing their data, thereby enhancing data privacy protection by transmitting only model parameters. Additionally, inspired by Split Learning (SL), we split the neural network into three parts using U-shaped splitting for local training on IoT devices. By exploiting the greater computation capability of edge servers, our framework effectively reduces overall training time and allows IoT devices with varying capabilities to perform training tasks efficiently. Furthermore, we proposed a novel noise mechanism called LabelDP to ensure that data features and labels can securely resist reconstruction attacks, eliminating the risk of privacy leakage. Our theoretical analysis and experimental results demonstrate that EUSFL can be integrated with various aggregation algorithms, maintaining good performance across different computing capabilities of IoT devices, and significantly reducing training time and local computation overhead.

Health state assessment model for complex systems: Trade-off accuracy and robustness in belief rule base

In complex system, health state assessment can determine the state of the system and identify potential system problems. However, due to the numerous uncertainties and variations present in complex systems, it is difficult to effectively construct assessment models. Belief rule base (BRB) can use data-driven and knowledge-driven methods to effectively address uncertain information, and is widely used for modeling health state assessments of complex systems. The primary modeling and optimization goals of BRB is currently at accuracy, ignoring the impact of robustness on complex systems, and the reliability of the model is reduced. Therefore, this article introduces a novel method to balance the accuracy and robustness of BRB models. This method enhances the performance of the BRB model in assessing complex system health and provides valuable guidance for engineering applications. Firstly, the guidelines for BRB modeling are systematically summarized to address the trade-off between accuracy and robustness. This provides essential guidance for constructing BRB models during the model-building process. Secondly, four feasible domain criteria are proposed to enhance the reliability of the BRB during the model optimization process. A modified multi-objective optimization algorithm is proposed based on the feasible domain criteria. Finally, in the case studies of aerospace relay and lithium-ion battery health assessments, the MSE of the proposed model for aerospace relay health assessment is 0.0015 with a Lipschitz constant of 6.73, while for lithium-ion battery health assessment, the MSE is 0.0013 with a Lipschitz constant of 24.17. The experimental results demonstrate that the proposed model has an advantage in terms of the trade-offs between both robustness and accuracy.

Optimized energy efficient reactive distillation for octane upgrading with economic and environmental considerations

Advancing fuel efficiency and production technologies can significantly reduce “Well to Wheels” and “Octane on Demand” emissions. This has been accomplished by integrating intensified technologies in fuel refineries. However, maintaining low energy consumption and high octane number while considering the impact of operating conditions under uncertainty on the process feasibility remains a challenge. Therefore, this article proposes a novel absorption heat pump reactive distillation (AHPRD). Aiming to maximize the economic potential of the AHPRD, an optimization framework that considers operating conditions under uncertainty (i.e. temperature (T), pressure (P), reflux ratio (RR), and feed stage (FS)) is developed. The optimization framework synchronizes Monte Carlo simulation and particle swarm optimization (PSO) to maximize the net present value (NPV). The framework used a hybrid Python-DWSim interface platform. The AHPRD was further investigated and compared against existing processes, namely, a conventional process refinery (CP) and reactive distillation (RD), to improve energy saving, increase financial return, and cut CO2 emissions. Attractively, the AHPRD outperforms existing processes, both economically and environmentally, doubling profit values and avoiding 52.2% − 77.4% of CO2 emissions. This study believes that the future direction will be to build an artificial intelligence model for process optimization and economic prediction.

Building information modeling-based production process optimization model

In the current manufacturing process of enterprises, there are some problems such as poor predictability and low level of intelligence, which lead to high product error rate and affect production efficiency. Therefore, this paper introduces the building information model in the field of engineering construction, and proposes a big data predictive manufacturing model based on the building information model, which divides the production process into production service system, resource planning system, production control system and after-sales service system, and realizes the overall process optimization of planning-production-sales on the basis of the close combination of each system and virtual model system. Finally, the application of error correction process in production line is verified from an empirical point of view, which provides a reference method and path for reducing production error rate and improving work efficiency.

Surrogate gradient methods for data-driven foundry energy consumption optimization

In many industrial applications, data-driven models are more and more commonly employed as an alternative to classical analytical descriptions or simulations. In particular, such models are often used to predict the outcome of an industrial process with respect to specific quality characteristics from both observed process parameters and control variables. A major step in proceeding from purely predictive to prescriptive analytics, i.e., towards leveraging data-driven models for process optimization, consists of, for given process parameters, determining control variable values such that the output quality improves according to the process model. This task naturally leads to a constrained optimization problem for data-driven prediction algorithms. In many cases, however, the best available models suffer from a lack of regularity: methods such as gradient boosting or random forests are generally non-differentiable and might even exhibit discontinuities. The optimization of these models would therefore require the use of derivative-free techniques. Here, we discuss the use of alternative, independently trained differentiable machine learning models as a surrogate during the optimization procedure. While these alternatives are generally less accurate representations of the actual process, the possibility of employing derivative-based optimization methods provides major advantages in terms of computational performance. Using classical benchmarks as well as a real-world dataset obtained from an industrial environment, we demonstrate that these advantages can outweigh the additional model error, especially in real-time applications.

Process optimization and kinetic modeling of ultrasound assisted lactic acid production

AbstractThe impact of ultrasound‐assisted fermentation using Lactobacillus species was investigated, for enhanced lactic acid production. The different ultrasound frequencies of 20, 30, and 40 Hz, with time intervals of 3, 4, and 5 min, and with corn steep liquor concentrations of 1%–3% were examined using response surface methodology‐Box–Behnken design. The growth of lactic acid production was modeled by Contois model (linear) and Baranyi–Roberts model (nonlinear), assessing the suitability of Lactobacillus paracasei, Lactobacillus plantarum, and Lactobacillus acidophilus for industrial processes. At 34 h, the maximal lactic acid generation of L. paracasei, L. plantarum, and L. acidophilus was 85.2%, 82.1%, and 79.4%, respectively. The R2, μmax, and Ks values for L. paracasei and L. plantarum were found to be 0.9158, 0.574 h−1, 54.27 g/L and 0.9426, 0.294 h−1, 22.66 g/L, respectively, using Contois model. The observed R2 values of Baranyi–Roberts model for the strains L. acidophilus, L. paracasei, and L. plantarum were 0.9947, 0.9954, and 0.9998, respectively.Practical ApplicationsLactic acid is crucial in the fermentation process for products like yogurt, sauerkraut, kimchi, and pickles, enhancing flavor, texture, and shelf life. As a precursor to biodegradable plastics, lactic acid contributes to the development of sustainable packaging materials and environmentally friendly alternatives to traditional plastics. Utilizing waste corn steep liquor (CSL) as a growth medium presents a sustainable and cost‐effective solution for lactic acid production, capitalizing on its rich nutrient profile to enhance microbial growth. As a byproduct of corn wet milling, using CSL for fermentation processes promotes waste valorization and contributes to a circular economy. The optimization of fermentation conditions using the Box–Behnken design ensures maximum yield and efficiency by systematically evaluating the effects of key process variables. Integrating advanced growth curve models like the Contois and Baranyi models further refines the understanding and prediction of microbial dynamics, enabling precise control over the fermentation process. This comprehensive approach not only promotes the efficient use of industrial by‐products but also advances the development of environmentally friendly and economically viable bioprocesses.

Continuous-flow synthesis of di-(2-ethylhexyl) peroxydicarbonate in a packed-bed microreactor: Process optimization and kinetic modeling

Di-(2-ethylhexyl) peroxydicarbonate (EHP) is a low-temperature liquid organic peroxide commonly used as an initiator for polymerization of vinyl chloride and ethylene. The exothermic nature of peroxidation and the instability of this peroxide product pose safety challenges during synthesis. Therefore, batch reaction processes for synthesizing such products often prioritize safety over efficiency. In this work, an efficient and safe protocol was proposed for EHP production with the use of a packed-bed microreactor. Response surface methodology was applied to optimize critical process parameters, resulting in a remarkable yield of 95.48% in a residence time of 23.8 min. It proves that the efficiency was significantly improved by the packed-bed microreactor compared with batch reactors. Additionally, an operational window was established to guide the process development for synthesizing EHP in flow. Finally, a kinetic model was established, which was of crucial theoretical significance and practical value for better understanding peroxidation processes and parameter optimization.