Optimization Strategy Research Articles

Comparative dynamic optimization study of batch hydrothermal liquefaction of two microalgal strains for economic bio-oil production

This work presents dynamic optimization strategies of batch hydrothermal liquefaction of two microalgal species, Aurantiochytrium sp. KRS101 and Nannochloropsis sp. to optimize the reactor temperature profiles. Three dynamic optimization problems are solved to maximize the endpoint biocrude yield, minimize the final time, and minimize the reactor thermal energy. The biocrude maximization and time minimization problems demonstrated 11% and 6.18% increment in the optimal biocrude yields and reduction of 78.2% and 61.66% in batch times compared to the base cases for the microalgae with higher lipid and protein fractions, respectively. The energy minimization problem revealed a significant reduction in the reactor thermal energies to generate the targeted biocrude yields compared to the biocrude maximization. Therefore, the identified optimal temperature trajectories outperformed the conventional fixed temperature profiles and could improve the overall economics of the batch bio-oil production from the algal-based biorefineries by significantly enhancing the reactor performance.

Large-scale sandwich structures optimization using Bayesian method

Benefiting from advanced features like high stiffness-to-weight ratios, sandwich structures are widely used in aerospace for primary and secondary structures. As tasks grow more complex and structures increase in scale, high-dimensional design spaces inevitably arise. Optimizing large-scale sandwich structures efficiently and intelligently presents certain challenges. Additionally, functional requirements and constraints, such as thermal deformation, should be fully considered in the design of practical structures like solar arrays, which involve a large expensive analysis and make the problem more complicated. This paper proposes to use efficient Bayesian optimization with the active subspace (AC) method to address this type of problem. The active subspace method, combined with the adaptive kriging and global sensitivity analysis (GSA), is employed for dimension reduction and reconstructing the design space. Then the structure is optimized within the reconstructed design space using the efficient Bayesian method. The proposed optimization strategy is applied to a case study of solar array with sandwich panels, demonstrating that the developed framework is feasible and effective for structural optimization of large-scale sandwich structures.

Deep convolutional neural network framework with multi-modal fusion for Alzheimer’s detection

The biomedical profession has gained importance due to the rapid and accurate diagnosis of clinical patients using computer-aided diagnosis (CAD) tools. The diagnosis and treatment of Alzheimer’s disease (AD) using complementary multimodalities can improve the quality of life and mental state of patients. In this study, we integrated a lightweight custom convolutional neural network (CNN) model and nature-inspired optimization techniques to enhance the performance, robustness, and stability of progress detection in AD. A multi-modal fusion database approach was implemented, including positron emission tomography (PET) and magnetic resonance imaging (MRI) datasets, to create a fused database. We compared the performance of custom and pre-trained deep learning models with and without optimization and found that employing natureinspired algorithms like the particle swarm optimization algorithm (PSO) algorithm significantly improved system performance. The proposed methodology, which includes a fused multimodality database and optimization strategy, improved performance metrics such as training, validation, test accuracy, precision, and recall. Furthermore, PSO was found to improve the performance of pre-trained models by 3-5% and custom models by up to 22%. Combining different medical imaging modalities improved the overall model performance by 2-5%. In conclusion, a customized lightweight CNN model and nature-inspired optimization techniques can significantly enhance progress detection, leading to better biomedical research and patient care.

Survey on Stock Price Forecasting

This research project delves into the challenging domain of stock price prediction by harnessing the capabilities of neural networks. In an ever-evolving financial landscape, the project seeks to develop a robust model that can analyze historical stock data, identifying intricate patterns and trends to inform future price movements. Through the convergence of data science and financial analysis, this endeavor aims to provide investors with valuable insights, aiding them in navigating the complexities of the stock market. Employing machine learning algorithms, particularly neural networks, the model scrutinizes extensive sets of historical stock data, considering factors such as past price trends, trading volumes, and relevant financial indicators. Techniques such as regression, time-series analysis, and neural networks are leveraged to unveil complex relationships within the data, enhancing the model's predictive capabilities. The model undergoes meticulous training on historical data to glean insights from past market behaviors. Subsequently, it undergoes rigorous testing on unseen data to evaluate its predictive accuracy. Continuous refinement and optimization strategies are implemented to ensure the model's adaptability to the ever-changing dynamics of the market. Ultimately, this project aspires to furnish investors with a powerful tool for making informed decisions in the face of the unpredictable nature of financial markets. By integrating the precision of neural networks with the intricacies of stock market analysis, the research aims to contribute to the advancement of stock price forecasting methodologies.

A hybrid criterion-based sample infilling strategy for surrogate-assisted multi-objective optimization

A hybrid criterion-based sample infilling strategy for surrogate-assisted multi-objective optimization

Age-appropriate design of domestic intelligent medical products: An example of smart blood glucose detector for the elderly with AHP-QFD Joint KE

BackgroundIn response to the rise of intelligent products and the increasing prevalence of urban "empty nesters," we have developed a product specifically tailored for elderly diabetic patients. This product fulfils functional requirements and addresses stylistic preferences, contributing to the age-friendly evolution of home intelligent medical devices, particularly in intelligent blood glucose monitoring. MethodsOur approach commenced with a comprehensive user experience analysis to ascertain the needs of elderly users regarding home blood glucose meters. This involved constructing a hierarchy of user demands, followed by analysing and prioritising these needs. Utilizing Quality Function Deployment (QFD), we aligned user requirements with design specifications, identifying specific product functionalities and service design elements. Further, we employed Kansei Engineering (KE) to select sample designs that resonate with the concept of sensual imagery, leading to the derivation of specific modelling intentions. Combining these design elements, we proposed product design strategies and conducted practical case studies. The effectiveness of these designs was then assessed through fuzzy evaluation methods, allowing for user feedback. ResultsEmploying the Analytic Hierarchy Process for goal analysis, along with Quality Function Deployment theory and Kansei Engineering, we developed a home intelligent blood glucose meter catered to the elderly. This device not only meets its users' physiological and psychological needs but also provides an operationally convenient, health-conscious, and aesthetically pleasing experience. ConclusionsThis methodology enhances the age-appropriate design of home-based smart glucose monitors for the elderly, offering innovative insights and optimization strategies for designing elderly-centric smart medical products.

An intelligent optimization strategy for nurse-patient scheduling in the Internet of Medical Things applications

In the last years, the world has witnessed a potential increasing in the patient number resulted from the increasing number of aged persons along with the emergence of new virus and diseases. This imposes a high pressure on hospitals that suffer from a shortage of medical staff, personal equipment and adequate interventions to overcome such a challenge. Particularly, nurse scheduling is becoming a crucial operation to hospitals in order to efficiently handing the patents and increasing the performance of health system. In this paper, we present an efficient Nurse-Patient Scheduling (NPS) mechanism that is based on the patient classification according to the severity levels of their vital signs. The main goal of NPS is to balance the workload of nurses and it consists of three phases: patient monitoring, patient classification, and nurse scheduling. The first phase aims to periodically monitor the patients using a configurable window time and collect their vital signals through a set of biomedical sensors. The second phase allows for the extraction of prospective features among the collected data then to classify them according to a set of predefined criteria such as patient criticality level, patient age, and the allocated treatment time of each patient. In the last phase, we propose a novel scheduling algorithm that combines both genetic and particle swarm optimization methods in order to find the best scheduling assignment of nurses over patients. We performed simulations based on real health data and we demonstrated the performance of NPS mechanism in terms of obtaining optimal of nurses to patients according to the predefined criteria.

Optimization strategy of Co3O4 nanoparticles in biomethane production from seaweeds and its potential role in direct electron transfer and reactive oxygen species formation

In the present study, three process parameters optimization were assessed as controlling factors for the biogas and biomethane generation from brown algae Cystoceira myrica as the substrate using RSM for the first time. The biomass amount, Co3O4NPs dosage, and digestion time were assessed and optimized by RSM using Box-Behnken design (BBD) to determine their optimum level. BET, FTIR, TGA, XRD, SEM, XPS, and TEM were applied to illustrate the Co3O4NPs. FTIR and XRD analysis established the formation of Co3O4NPs. The kinetic investigation confirmed that the modified model of Gompertz fit the research results satisfactorily, with R2 ranging between 0.989–0.998 and 0.879–0.979 for biogas and biomethane production, respectively. The results recommended that adding Co3O4NPs at doses of 5 mg/L to C. myrica (1.5 g) significantly increases biogas yield (462 mL/g VS) compared to all other treatments. The maximum biomethane generation (96.85 mL/g VS) was obtained with C. myrica at (0 mg/L) of Co3O4NPs. The impacts of Co3O4NPs dosages on biomethane production, direct electron transfer (DIET) and reactive oxygen species (ROS) were also investigated in detail. The techno-economic study results demonstrate the financial benefits of this strategy for the biogas with the greatest net energy content, which was 2.82 kWh with a net profit of 0.60 USD/m3 of the substrate and was produced using Co3O4NPs (5 mg/L).

ASXC$^{2}$ Approach: A Service-X Cost Optimization Strategy Based on Edge Orchestration for IIoT

ASXC$^{2}$ Approach: A Service-X Cost Optimization Strategy Based on Edge Orchestration for IIoT

Design Principle Considering Structural Mutual Effects of Double-Stator V-Shape-PM Vernier Machines for Electric Ship Propulsion

This paper proposes the design principle considering structural mutual effects of double-stator V-shape permanent-magnet (DS-V-PM) vernier machines for electric ship propulsion (ESP). Due to the flux concentration effect of the V-PM configuration, the double stators can be divided as a major and a minor stator, considering the different torque generation capability. Cooperation mutual effects between the double stators, V-PM arrangement and vernier machine topology are specifically included in the machine design principle exploration. To illustrate the design principle, first, a unified design principle is deduced, fit for general PM vernier machines. Then, a multi-step optimization strategy with auxiliary of sizing equations is presented, focusing on the parameter cooperation with flux modulation effect. Furthermore, through electromagnetic performance comparison, specific mutual effects of the DS configuration, DS angle shift, V-PMs and barrier structure are clearly summarized. Based on the DS machine design, the multi-mode operation for ESP system is introduced and analyzed. The normal/faulty cruise mode and charging mode are included to realize bi-directional operation. Prototype experiments are carried out for verification of the proposed machine design and operating strategy.

Stochastic Resource Optimization for Wireless Powered Hybrid Coded Edge Computing Networks

With the ubiquitous sensing enabled by the Internet-of-Things (IoT), massive amount of data is generated every second, transforming the way we interact with the world. To manage big data and enable analytics at the edge of the network, large amount of computation power is required to perform the computation intensive tasks. However, the energy-constrained IoT devices are not able to perform the computation tasks without compromising the quality-of-service of the applications. In this paper, we propose a hybrid network in which users can fully offload their computation tasks to edge servers through coded edge offloading or perform local computation with the wireless power transfer derived from coalitions of unmanned aerial vehicles (UAVs) serving as mobile charging stations. To minimize the cost of the network, we consider a two-level optimization approach. At the lower level, an optimal UAV coalition that minimizes the network cost is formed. At the upper level, the computation approach for each user is decided while taking into account the stochastic nature of wireless charging efficiency. Given the interrelation between the two levels, we adopt the backward induction optimization strategy to jointly derive the optimal coalition structure and computation approach for each user. In the performance evaluation, we provide extensive sensitivity analyses to study the performance of the cost minimization approaches amid varying network parameters. Moreover, we show that our approach outperforms deterministic optimization approaches in network cost minimization.

Optimization of RST Controller for Speed Control of Linear Induction Motor Using Genetic Algorithm

Background: In this study, a new model of linear induction motor, along with the impact of end-effect on motor performance, is proposed. Moreover, a new strategy of control approach based on the polynomial RST controller is suggested and investigated. Objective: The proposed approach can provide a robust control strategy and overcome the limitations imposed by the proportional-integral (PI) regulator in the FOC technique. RST controller has a two-degree of freedom structure and consists of three polynomials, namely R, S and T, which are determined by the pole placement method and resolving of a Diophantine equation. Despite this, the implementation of this method is usually difficult and becomes more complicated with the complexity of the controlled plants. Methods: This study proposes the genetic algorithm (GA) optimization strategy for tuning RST controller parameters (adjust the controller coefficients) in order to achieve an adequate response time by minimizing the different objective functions, such as steady-state error, settling time, and rise time. Results: The accuracy and control performance of the proposed technique are checked and validated using Matlab /Simulink environment software tool. Simulation results reported that the proposed method (RST-GA) could provide robust solutions with perfect reference tracking and efficient disturbance rejection. Conclusion: These significant results make the proposed approach a promising technique for the design of a high-performance controller, which is highly suitable for industrial and electrical applications.

A Unified Framework Based on Graph Consensus Term for Multiview Learning.

In recent years, multiview learning technologies have attracted a surge of interest in the machine learning domain. However, when facing complex and diverse applications, most multiview learning methods mainly focus on specific fields rather than provide a scalable and robust proposal for different tasks. Moreover, most conventional methods used in these tasks are based on single view, which cannot be readily extended into the multiview scenario. Therefore, how to provide an efficient and scalable multiview framework is very necessary yet full of challenges. Inspired by the fact that most of the existing single view algorithms are graph-based ones to learn the complex structures within given data, this article aims at leveraging most existing graph embedding works into one formula via introducing the graph consensus term and proposes a unified and scalable multiview learning framework, termed graph consensus multiview framework (GCMF). GCMF attempts to make full advantage of graph-based works and rich information in the multiview data at the same time. On one hand, the proposed method explores the graph structure in each view independently to preserve the diversity property of graph embedding methods; on the other hand, learned graphs can be flexibly chosen to construct the graph consensus term, which can more stably explore the correlations among multiple views. To this end, GCMF can simultaneously take the diversity and complementary information among different views into consideration. To further facilitate related research, we provide an implementation of the multiview extension for locality linear embedding (LLE), named GCMF-LLE, which can be efficiently solved by applying the alternating optimization strategy. Empirical validations conducted on six benchmark datasets can show the effectiveness of our proposed method.

Task Scheduling Optimization for UAV Electrical Image Fault Detection with Wireless Power Transfer

The smooth operation of the power system is of significant importance for ensuring societal stability. Therefore, regular inspections of the power system are necessary. The most efficient method for power inspection is to utilize Unmanned Aerial Vehicles (UAVs) to assist inspection. However, the UAV inspection still needs human resources to operate and manage the UAVs effectively. This paper proposes a UAV-airport power inspection system, where the airport can operate and manage UAVs instead of humans. The key contribution of the system is the computation offloading technology and the Wireless Power Transfer (WPT) capability. In other words, the airport can help UAVs execute electrical image fault detection and the UAVs can be charged by the airport. We propose a joint optimization strategy for UAV flight speed, local execution frequency for fault detection, and WPT time to maximize the number of images in the electrical dataset captured by the UAV that have undergone power fault detection within the inspection time. Comprehensive experiments are conducted to verify the performance of the UAV-airport power inspection system and our optimization strategy.

Static and free vibration analysis of delaminated composite plates using secant function based shear deformation theory

In this work, the static and free vibration analysis of delaminated composite plates are studied. The secant function based shear deformation theory (SFSDT), is used for the analysis of multiple delaminated models. This theory exhibits a non-linear shear stress distribution and fulfills the traction-free boundary conditions at the top and bottom surfaces of the plates, hence there is no need for a shear correction factor. The finite element method, a numerical solution-based approach is used here considering an eight-noded isoparametric quadratic element. The investigation explores the effects of delamination size, position and stacking sequence on the flexural and dynamic characteristics of the composite plates. Additionally, other geometric factors such as delamination thickness and shape are investigated to understand their impact. The study aims to identify the optimal configurations that minimize the detrimental effects of delaminations. The results provide valuable insights into the static and free vibration behaviour of delaminated composite plates, contributing to design guidelines and optimization strategies for structurally sound and efficient composite structures. Overall, this research offers a comprehensive investigation of the static and free vibration analysis of delaminated composite plates, advancing knowledge in the field and facilitating improved design practices.

An Investigation of the Energy-Saving Optimization Design of the Enclosure Structure in High-Altitude Office Buildings

Concerning the double carbon national strategy, the energy-saving renovation of old buildings has become one of the most important tasks of energy conservation and emission reduction in construction in China. There are many problems, such as high energy consumption, thermal environment, and poor thermal comfort. Taking Lhasa as an example, this study adopts field research, questionnaire interviews, on-site measurements, numerical simulations, and other methods to propose suitable energy-saving potential excavation points and thermal optimization strategies for office building envelopes in Lhasa through software simulation. Additionally, typical office buildings are selected to carry out the energy-saving renovation of envelopes with the goal of improving indoor thermal comfort to validate the feasibility of the energy-saving renovation strategies. The results show the following: (1) The measured and predicted thermal neutral temperatures of the office population in Lhasa are 16.5 °C and 18.9 °C, respectively. The 90% acceptable temperature range is from 16.10 °C to 21.77 °C, and the occupants of the office buildings in Lhasa have a higher tolerance for cold than predicted. (2) The passive measures adapted to Lhasa are prioritized in the order of passive solar energy, high-heat-capacity materials, and nighttime ventilation. (3) Through the optimization of the enclosure structure of existing office buildings, the improvement of the heat storage capacity of the outer enclosure structure, and the increase in the window opening area to increase natural ventilation, the indoor thermal comfort of the renovated buildings is effectively improved.

High-Precision Localization of Passive Intermodulation Source in Radio Frequency Transmission Lines Based on Dual-Frequency Signals

With the development of communication technology, the interference from passive intermodulation to the communication system has become increasingly severe. Locating the source of passive intermodulation and then repairing or replacing the device experiencing passive intermodulation is a reliable method. Therefore, this paper proposes a dual-frequency signal localization method based on the principle of phase ranging to accurately locate the passive intermodulation sources in RF cables. This method switches the test signal frequency to obtain the phase of passive intermodulation signals at different frequencies to localize the passive intermodulation source. This paper analyzes the principle of the passive intermodulation localization method based on dual-frequency signals, establishes a localization system for experiments, and finally, analyzes the experimental error to propose an optimization strategy. Through experimental verification, this method can stabilize the positioning error of a passive intermodulation source in a transmission line less than 0.06 m. Meanwhile, this method has high positioning accuracy and the advantages of slight computational complexity, fast positioning speed, and only a small number of requirements on hardware resources. It can work in communication scenarios like satellite and base stations, providing a new technical solution for localizing passive intermodulation interference sources in 5G and 6G communication systems.

Optimization Strategies for Literacy Teaching in the Lower Primary Language Segment under the Background of Core Literacy

Literacy and writing are the foundation of reading and writing, which is the teaching focus of the first school period and an important teaching content throughout the whole compulsory education stage. This paper mainly discusses the current situation of literacy teaching in elementary school language in the context of core literacy, identifies the problems in literacy teaching, and proposes strategies to optimize literacy teaching in combination with the Compulsory Education Language Curriculum Standards (2022 Edition), to stimulate students' interest in literacy, improve literacy skills, and develop students' core literacy.

Green Building: Energy Efficiency Optimisation Strategies using MATLAB

Abstract: This research paper explores the integration of optimization techniques in the realm of green building construction, aiming to minimize environmental impact while maximizing resource efficiency. With the pressing need to mitigate climate change and reduce the carbon footprint of the construction industry, the study investigates various methodologies for optimizing the design, materials, and processes involved in sustainable building practices. The paper delves into the core principles of green building, emphasizing the importance of energy efficiency, renewable resources, and innovative construction techniques. It analyzes the application of optimization models, such as life cycle assessment (LCA), Building Information Modeling (BIM), and parametric design, in streamlining decision- making processes throughout the building life cycle. Moreover, the research assesses case studies and real-world implementations of optimization strategies in green building projects across different geographical locations and scales. It examines the economic feasibility, environmental benefits, and social impacts of these strategies, emphasizing the need for a holistic approach to sustainable construction. By synthesizing existing knowledge and exploring novel approaches, this paper aims to provide insights into the role of optimization in advancing the goals of green building, ultimately contributing to the creation of more ecofriendly and resilient built environments

A Novel Fault Diagnosis Strategy for Diaphragm Pumps Based on Signal Demodulation and PCA-ResNet.

The efficient and accurate identification of diaphragm pump faults is crucial for ensuring smooth system operation and reducing energy consumption. The structure of diaphragm pumps is complex and using traditional fault diagnosis strategies to extract typical fault characteristics is difficult, facing the risk of model overfitting and high diagnostic costs. In response to the shortcomings of traditional methods, this study innovatively combines signal demodulation methods with residual networks (ResNet) to propose an efficient fault diagnosis strategy for diaphragm pumps. By using a demodulation method based on principal component analysis (PCA), the vibration signal demodulation spectrum of the fault condition is obtained, the typical fault characteristics of the diaphragm pump are accurately extracted, and the sample features are enhanced, reducing the cost of fault diagnosis. Afterward, the PCA-ResNet model is applied to the fault diagnosis of diaphragm pumps. A reasonable model structure and advanced residual block design can effectively reduce the risk of model overfitting and improve the accuracy of fault diagnosis. Compared with the visual geometry group (VGG) 16, VGG19, ResNet50, and autoencoder models, the proposed model has improved accuracy by 35.89%, 80.27%, 2.72%, and 6.12%. Simultaneously, it has higher operational efficiency and lower loss rate, solving the problem of diagnostic lag in practical engineering. Finally, a model optimization strategy is proposed through model evaluation metrics and testing. The reasonable parameter range of the model is obtained, providing a reference and guarantee for further optimization of the model.