Competitive Solution Research Articles

New Hybrid Approaches Based on Swarm-Based Metaheuristic Algorithms and Applications to Optimization Problems

Metaheuristic algorithms are favored for solving a variety of problems due to their inherent simplicity, ease of implementation, and effective problem-solving capabilities. This study proposes four new hybrid approaches using swarm-based metaheuristic algorithms. Two of these new approaches are HHHOWOA1 and HHHOWOA2, based on the hybridization of Harris Hawks Optimization (HHO) with the Whale Optimization Algorithm (WOA), and the others are HHHOWOA1PSO and HHHOWOA2PSO, based on the hybridization of HHHOWOA1 and HHHOWOA2 with particle swarm optimization (PSO). An evaluation of these four innovative approaches is conducted on 23 benchmark functions, and their results are compared to those reported in the literature under equivalent parameter settings. Among the four approaches, HHHOWOA1 and HHHOWOA2PSO have demonstrated more favorable results. According to the literature, the HHHOWOA1 and HHHOWOA2PSO approaches achieve the most optimal results, either better or with the same average fitness values in 15 of the 23 functions and in 18 of the 23 functions, respectively. Moreover, the proposed approaches have been applied to three engineering problems, and the optimum values obtained are compared to the literature. Ultimately, the proposed approaches have proven effective in providing competitive solutions for the majority of optimization problems.

3D printing fiber-tip integrated Fabry-Perot interferometers for ultrasensitive RI sensing with an enhanced Vernier effect.

An ultrasensitive refractive index (RI) sensing technology based on an enhanced Vernier effect is proposed, which integrates a polymer Fabry-Perot interferometer (FPI) with an open cavity FPI on the tip of a seven-core optical fiber. Interference spectra of the polymer FPI and the open cavity FPI shift to opposite directions as the ambient RI changes, thus leading to the enhanced Vernier effect. Investigations of RI sensitivity and temperature dependence of the proposed fiber sensors are carried out. Taking advantage of the enhanced Vernier effect, we demonstrate a remarkable sensitivity of 19742.86 nm/RIU within the RI range from 1.39 to 1.395. The sensor exhibits substantial advantages such as ease of fabrication, compact structure, high sensitivity, and good repeatability, providing a practical and competitive solution for RI sensing.

A Robust and Efficient Representation‐based DNA Storage Architecture by Deep Learning

AbstractAs one main form of multimedia data, images play a critical role in various applications. In this paper, a representation‐based architecture is proposed which takes advantage of the outstanding representation and image‐generation abilities of deep learning (DL). This architecture includes two DL models: an autoencoder and a U‐Net network which achieve the representation, construction, and refinement of images from the noisy reads in DNA storage. Simulation experiments demonstrate that it can reconstruct images of moderate quality in scenarios where insertion‐deletion‐substitution (IDS) errors are less than 6%. Combined with the feature quantization, it also offers a flexible way to achieve a balanced trade‐off between compression ratio and image quality by selecting an approximate representation channel number. Additionally, the quality of images can be boosted by using multiple reads which are a common situation in DNA storage. A wet lab practice that successfully reconstructs an image stored in 14 plasmids further proves the feasibility of the proposed architecture. Instead of storing the original image information, the representation‐based architecture provides a competitive solution which achieves robust and efficient DNA storage for large‐scale image applications.

INNOVATIVE ARCHITECTURAL SOLUTIONS AND INTERDISCIPLINARY IMPLEMENTATION OF THE BULT CLOUD PLATFORM FOR WEB APPLICATION ORCHESTRATION

The article is devoted to the creation of the BULT cloud platform, which implements an interdisciplinary approach to the development and orchestration of web applications. The main goal of this work is to develop a platform that provides flexibility, scalability and integration of various technologies. Architectural solutions including microservice architecture and containerization are described, which simplifies the deployment and management of applications. HashiCorp's Nomad is used as the basis for container orchestration, which allows you to dynamically manage the distribution of tasks and resources, ensuring the efficiency and stability of applications. The data management system is implemented on the basis of PostgreSQL and JuiceFS, which ensures high performance and reliability of data storage. To ensure security, Wireguard and Let's Encrypt are used, which provide encryption of network traffic and automatic updating of SSL certificates. Monitoring and analysis of the system are carried out using Grafana and Loki, which allow you to visualize metrics and logs in real time. The implementation of DevOps principles and automation of development, testing and deployment processes are achieved using CI/CD tools, which allows you to quickly and safely implement changes and new features. The application of an interdisciplinary approach allows us to take into account various aspects of system development and operation, which makes the BULT platform a competitive solution in the modern cloud technology market, providing high performance, reliability and ease of use of web applications. Examples of the practical application of the platform and its advantages in comparison with traditional approaches are given.

ENSEMBLE OF SIMPLE SPIKING NEURAL NETWORKS AS A CONCEPT DRIFT DETECTOR

Context. This paper provides a new approach in concept drift detection using an ensemble of simple spiking neural networks. Such approach utilizes an event-based nature and built-in ability to learn spatio-temporal patterns of spiking neurons, while ensemble provides additional robustness and scalability. This can help solve an active problem of limited time and processing resources in tasks of online machine learning, especially in very strict environments like IoT which also benefit in other ways from the use of spiking computations. Objective. The aim of the work is the creation of an ensemble of simple spiking neural networks to act as a concept drift detector in the tasks of online data stream mining. Method. The proposed approach is primary based on the accumulative nature of spiking neural networks, especially Leaky Integrate-and-Fire neurons can be viewed as gated memory units, where membrane time constant Гm is a balance constant between remembering and forgetting information. A training algorithm is implemented that utilizes a shallow two-layer SNN, which takes features and labels of the data as an input layer and the second layer consists of a single neuron. This neuron’s activation implies that an abrupt drift has occurred. In addition to that, such model is used as a base model within the ensemble to improve robustness, accuracy and scalability. Results. An ensemble of shallow two-layer SNNs was implemented and trained to detect abrupt concept drift in the SEA data stream. The ensemble managed to improve accuracy significantly compared to a base model and achieved competitive results to modern state-of-the-art models. Conclusions. Results showcased the viability of the proposed solution, which not only provides a cheap and competitive solution for resource-restricted environments, but also open doors for further research of SNN’s ability to learn spatio-temporal patters in the data streams and other fields.

Comparative Analysis of the Biochemical and Molecular Responses of Nannochloropsis gaditana to Nitrogen and Phosphorus Limitation: Phosphorus Limitation Enhances Carotenogenesis.

Nannochloropsis gaditana is well known for its potential for biofuel production due to its high lipid content. Numerous omics and biochemical studies have explored the overall molecular mechanisms underlying the responses of Nannochloropsis sp. to nutrient availability, primarily focusing on lipid metabolism. However, N. gaditana is able to synthesize other valuable products such as carotenoids, including violaxanthin, which has various biological functions and applications. In this study, we comparatively investigated the physiological, biochemical, and molecular responses of N. gaditana to nitrogen and phosphorus limitation, examining biomass production, photosynthetic activity, lipid, chlorophyll, and carotenoids content, and RNA-seq data. Nitrogen limitation decreased photosynthetic activity, chlorophyll content, and biomass production but increased lipid content. Phosphorus limitation substantially increased carotenoids content, with violaxanthin productivity of 10.24 mg/L, 3.38-fold greater than under the control condition, with little effect on biomass production or photosynthetic function. These results were generally consistent with the gene expression pattern observed in transcriptomic analysis. This integrated analysis shows that phosphorus limitation can be an economically competitive solution by enhancing valuable carotenoids while maintaining lipid and biomass production in N. gaditana.

Inhibition of sulfated glycans on the binding of dengue virus envelope protein to heparin.

Dengue viruses (DENV) are transmitted to humans through mosquito bites and infect millions globally. DENV uses heparan sulfate (HS) for attachment and cell entry by binding the envelope protein to highly sulfated HS on target cells. Therefore, inhibiting the binding between DENV and HS could be a promising strategy for preventing DENV infection. In the current study, the interactions between DENV envelope protein (from Type 2 DENV) and heparin (a surrogate for HS) were analyzed using competition solution SPR. Results demonstrate that heparin binds to DENV envelope protein with high affinity (KD = 8.83 nM). Competitive Solution SPR assays using surface-immobilized heparin and a series of naturally-sourced and semi-synthetic sulfated glycans demonstrated significant inhibitory activity against the binding of DENV envelope proteins to heparin. This study of molecular interactions could provide insights into the development of therapeutics for DENV infection.

Model Predictive Control for Six-Phase Induction Machines with Insight into Past Current Errors

Multi-phase electric drives can act as a competitive solution for high-power applications. To take advantage of the multi-phase benefits, the design of high-performance control techniques is a crucial task. In this regard, the inherent features of model predictive control (MPC) have aroused the interest of the scientific community in the last decade. This control solution, based on the usage of a cost function, provides notable flexibility to the control designer to select diverse regulation goals. Although the use of some weighting factors is a common trend to prioritize control purposes, the internal behavior of each term of the cost function is commonly ignored since the cost function is only focused on minimizing the total error. With this issue in mind, this work firstly performs a detailed analysis about the behavior of each cost function term in a standard MPC. The mentioned study permits identifying a certain pattern of the internal mechanics of the cost function that can disturb the current quality. To solve this limitation, the cost function of the MPC scheme is redefined. The proposed strategy permits improving current quality without increasing the number of switching states applied per control period, as it is validated with experimental results in six-phase electric drives.

DIAFM: An Improved and Novel Approach for Incremental Frequent Itemset Mining

Traditional approaches to data mining are generally designed for small, centralized, and static datasets. However, when a dataset grows at an enormous rate, the algorithms become infeasible in terms of huge consumption of computational and I/O resources. Frequent itemset mining (FIM) is one of the key algorithms in data mining and finds applications in a variety of domains; however, traditional algorithms do face problems in efficiently processing large and dynamic datasets. This research introduces a distributed incremental approximation frequent itemset mining (DIAFM) algorithm that tackles the mentioned challenges using shard-based approximation within the MapReduce framework. DIAFM minimizes the computational overhead of a program by reducing dataset scans, bypassing exact support checks, and incorporating shard-level error thresholds for an appropriate trade-off between efficiency and accuracy. Extensive experiments have demonstrated that DIAFM reduces runtime by 40–60% compared to traditional methods with losses in accuracy within 1–5%, even for datasets over 500,000 transactions. Its incremental nature ensures that new data increments are handled efficiently without needing to reprocess the entire dataset, making it particularly suitable for real-time, large-scale applications such as transaction analysis and IoT data streams. These results demonstrate the scalability, robustness, and practical applicability of DIAFM and establish it as a competitive and efficient solution for mining frequent itemsets in distributed, dynamic environments.

Design Concept of the Virtual Showroom for the Lighting Equipment Sale

In the 2020s, consumer behaviour in the field of lighting design and lighting systems evolved under the influence of various factors, such as technological innovations, changes in the economy, new socio-cultural tasks, and environmental requirements. Lighting design must not only respond to current challenges, but also anticipate future opportunities and threats, creating sustainable and competitive solutions. The outdated user scenario, which exists and is often used in the marketing of lighting systems, includes a list of lighting equipment limited by retail space, offered to the buyer in analogue format, leaving a huge layer of products sold outside the showroom. The market needs new human-centred design products, including interactive media forms of commerce. The article aims to uncover the potential of interdisciplinary experience in integrating the engineering approach of light and engineering and the artistic and aesthetic approach of multimedia design to solve new commercial problems. A scientific approach based on the achievements of circadian photobiology, the method of semantic differential and the theory of colour science allowed Environmental Design Department of Russian State Stroganov University of Design and Applied Arts (Stroganov University) to develop a conceptual design of a showroom for the sale of lighting in virtual reality (VR) format for the L1 Group company as the final project. The creation of a virtual (or virtual reality, VR) lighting showroom is designed to change the user experience in the field of sales of lighting equipment. The product introduces the customer to the concept of light as a form and a fundamental unit for creating a unique atmosphere, as well as captures the emotions that arise when viewing scenes with different lighting. From a business point of view, such a solution can optimize the budget, attract new customers, and improve communication between the seller and the client.

Optimization of Abrasive Wear Parameters and Thermo-Mechanical Properties of Bauhinia Vahlii and Grewia Optiva Fiber Reinforced Hybrid Polymer Composites

Natural fiber-reinforced polymer composite offers competitive solutions for lightweight applications but faces significant abrasive wear challenges in many industrial and automobile applications. The current study aims to conduct mechanical, physical, and dynamic mechanical analyses, as well as three body abrasion examinations, on grewia-optiva (GO) and bauhinia-vahlii (BV) natural fiber-reinforced epoxy-based hybrid polymer composites containing marble dust as filler. Initially, the woven mat was knitted with an equal amount of grewia-optiva and bauhinia-vahlii natural fibers. Three weight percentages of the woven mat i.e. 10, 20, and 30wt.% were used as reinforcement, and industrial waste marble dust with a fixed amount of 5wt.% was also used as a filler material. GO, and BV fiber mats were chemically treated with 10wt—% NaOH for the cleaning and surface modification of fibers before their use as reinforcement. The fabricated composites' physical and mechanical characteristics, i.e., density, water absorption, hardness, impact, flexural, and tensile strength were examined experimentally. The value of the damping factor (tan δ), storage modulus (Eʹ), and loss modulus (Eʹʹ) of the developed composites were analyzed by a dynamic mechanical analyzer (DMA). The fabricated composites' three-body abrasive wear characteristics were also examined with varying parameters i.e. A: fiber loading, B: sliding distance, and C: normal load. The results show that increasing the fiber loading and using a constant amount of discarded marble dust improves all mechanical characteristics. The tensile strength, flexural strength, impact strength, and hardness improves by 15.99%, 26.30%, 24.40%, and 30.39% respectively for 10wt.% to 30wt.% fiber loading. The composites exhibit significant improvements in damping properties with fiber loading. Moreover, parameters i.e. normal load, speed, and fiber loading have contributed to abrasive wear of composites at 29.70%, 24.81%, and 19.07% respectively. This study will aid in the analysis of the morphological, mechanical, and thermo-mechanical properties of a new class of composite material that might be used for producing natural polymeric roofing systems, boats, and floors, as well as for the automobile industry.

Simulation of the process of transverse-forward extrusion with expansion

Levchenko V. M., Aliiev I. S., Chepelenko O. Yu., Kartamyshev D. O., Malii O. G. Simulation of the process of transverse-forward extrusion with expansion Combined extrusion methods are a competitive solution for the production of complex-profiled and hollow parts in optimal power mode. By simulation of the combined transverse-forward extrusion process with using the energy method of kinematic modules, calculated correlations were obtained and an assessment of the influence of technological parameters on the deformation pressure was given. The possibility of considering the process of combined extrusion as sequentially composed one of two plane modules with the addition of normalized pressures of transverse and forward extrusion with expansion has been confirmed. For the transverse extrusion module the correlations obtained by the upper bound method and showing results close to experimental data and similar solutions for problems of plane upsetting (final stage of die forming) and differing in two types of discontinuous velocity field were used. For a rectangular module of forward extrusion with expansion, a discontinuous velocity field was constructed and the correlation for calculating the pressure components on the velocity discontinuity lines was obtained. It has been found that there is an optimal value for the angle of the triangular module in the range of 42–45°, according to which it is recommended to tilt the semi-die wall. A graphical analysis of the dependence of the normalized combined extrusion pressure has allowed to identify that the relative parameters have the greatest influence on the pressure level: the height of the transverse extrusion deformation zone h/R0 and the thickness of the ledge h/s, which characterize the degree of metal deformation. The correlations that make it possible to evaluate the influence of the relative wall thickness of a hollow product h/s on the normalized deformation pressure were experimentally confirmed on workpieces made of aluminum alloy AA1135.

Preventive Planning of ‘Product-as-a-Service’ Offers Using Genetic Population-Driven Stepping Crawl Threads

Unlike the precise methods implemented in constrained programming environments, the proposed approach to preventive planning of Product-as-a-Service offers implements a competitive solution based on Genetic Population Stepping Crawl Threads (GPSCT).GPSCT techniques are used to determine the so-called stepping crawl threads (SCT) that recreate, in subsequent steps, variants of the allocation of sets of leased devices with parameters that meet the expectations of the customers ordering them by means of genetic algorithms. SCTs initiated at a selected point of the Cartesian product space of the functional repertoire of the equipment offered penetrate it in search of offer variants that meet the constraints imposed by the size of the budget and the risk level (i.e., expressed as the likelihood of damaging the device or losing part of its functionality) of individual customers. Two approaches of implementation techniques were used to determine the initial SCT population for the genetic algorithm—branch and bound (BBA) and linear programming (LPA). Many experiments assessed their impact on the computation time and the quality of the obtained solution. The performed computational experiments indicate that the effectiveness of both approaches depends on the specificity of the problem considered each time. Interestingly, for different instances of the problem, an alternative solution can always be selected that is competitive with the exact methods, allowing for a 10-fold increase in scalability.

Tower Crane Layout Planning: Multi-Optimal Solutions Algorithm

Effective tower crane layout planning is essential for the success of construction projects. Traditional optimization algorithms, which often provide a single optimal solution, may not always reveal the global optimum, leaving room for doubt. This paper introduces the competitor algorithm, a novel multi-optimal solution approach inspired by the competitive learning paradigm within classroom settings. This algorithm is designed to provide users with a diverse set of competitive solutions, while avoiding falling into local optima. This strategic diversification ensures that users are equipped with a comprehensive range of options, empowering them to make confident, informed decisions. Furthermore, we have streamlined the positioning range for tower cranes, transitioning from a two-dimensional plane to a one-dimensional segmented line, thus eliminating the need to explore extensive, non-competitive regions. The competitor algorithm’s performance was validated through practical application, showcasing both its stability and optimization prowess, thereby confirming its reliable utility in real-world scenarios.

Alamouti coding enabled polarization insensitive simplified self-homodyne coherent system for short-reach optical interconnects

Coherent technology inherent with more available degrees of freedom is deemed as a competitive solution for next-generation ultra-high-speed short-reach optical interconnects. However, the high system cost, elevated power consumption, and large footprint size pose formidable barriers to the application of conventional coherent systems in short-reach scenarios. Self-homodyne coherent detection exhibits its potential for short-reach applications due to the sharing of the signal carrier and the local oscillator (LO), which not only reduces the system cost but also eliminates the frequency offset. Nevertheless, the self-homodyne coherent technique suffers from the polarization fading issue due to the random polarization states of the remote LO. In this paper, an Alamouti coding enabled simplified self-homodyne coherent detection technique is proposed to solve the polarization fading issue, resulting in a polarization-insensitive receiver. Besides, to further reduce the computational complexity of the system, the digital subcarrier multiplexing (DSCM) technique is discussed to alleviate the complexity of chromatic dispersion compensation (CDC), which is another dominant power consumption module of the receiver-side digital signal processing. The performance of the proposed scheme is demonstrated with a 50Gbaud 4-subcarrier 16/32QAM DSCM signal. The results show that polarization-insensitive self-homodyne detection is achieved by the transmitter-side Alamouti coding technique, circumventing the sophisticated automatic polarization controller for the polarization state tracking of the remote LO. In addition, by applying the joint dispersion compensation and equalization (JDCE) method for the DSCM signal, the CD-induced penalty can be fully addressed by increasing 4 taps in the equalizer for an 80 km single-mode fiber transmission without an individual CDC module, reducing the computational complexity of the system significantly.

An integrated BLS-Net optimized with dual PCA and improved PSO-CARS variable selection strategy to determine heavy metals in soil by XRF

Combining machine learning with X-ray fluorescence (XRF) spectroscopy is a promising solution for quantitatively analyzing heavy metal elements in soil. However, the implied linear and nonlinear interferences between spectral intensities and elemental concentrations are difficult to quantify by a single model, thus degrading the prediction performance for low-concentration elements. This paper presents a novel combined spectral variable selection and fusion modeling framework for quantitative analysis of heavy metal elements in soil XRF, which consists of the proposed Particle Swarm Optimization-based Competitive Adaptive Re-weighted Sampling (PSO-CARS) by adaptive decay strategy and Dual Principal Component Analysis-based broad learning system (BLS-Net). The proposed method is compared with advanced machine learning methods by predicting the concentrations of Cr, Cd, Cu, and Pb. The results show that PSO-CARS provides more efficient characteristic and auxiliary spectral variables for BLS-Net. BLS-Net precisely quantified concentrations of heavy metal elements by distinguishing between linear and nonlinear responses in spectra, resulting in average predictive coefficients of determination (R2) exceeding 0.995 of the different elements. The proposed method is a competitive spectral quantitative fusion modeling solution, offering a more precise and reliable analysis of heavy metal elements.

Multicolor Gold Clusterzyme-Enabled Construction of Ratiometric Fluorescent Sensor Array for Visual Biosensing.

The simultaneous detection of multiple bioanalytes with similar structures has been a long-standing challenge for biological research and disease diagnosis. Bioreceptor-inspired sensor arrays provide an attractive and competitive solution for addressing this challenge, but applying this technique to biosensing in practical application scenarios is complicated by many factors such as the lack of robust probes, interference from the biological matrix, and difficulty for on-site analysis. In this work, by taking advantage of the intrinsic fluorescence and enzyme-mimic properties of gold nanoclusters (AuNCs), we report the design of an innovative ratiometric sensor array toward enhanced fluorescent visual biosensing. With biologically important phosphates as an example, we show that the present fluorescent clusterzyme-based ratiometric sensor array could effectively discriminate and detect eight types of phosphates. In particular, AuNCs with three different emission colors (blue, green, and red) and good peroxidase-mimic properties were employed as the sensing units, and the presence of phosphates affected both the intrinsic fluorescence and the enzymatic activity of these AuNCs, yielding distinct optical responses in a ratiometric manner. Moreover, a portable sensor array was established by further integrating these fluorescent clusterzymes into a hydrogel matrix, which could visually identify different phosphates based on their distinct fluorescence color changes. Consequently, the point-of-care diagnosis of urinary tract infections at different levels was achieved by analyzing urinary microbial ATP via the present strategy. This study illustrates the great potential of clusterzyme-based fluorescent sensor arrays as a promising biosensing platform for disease diagnosis.

Optimized Graph Sample and Aggregate‐Attention Network‐Based High Gain Meta Surface Antenna Design for IoT Application

ABSTRACTThis paper presents a High Gain Metasurface (HGM) antenna design optimized for IoT applications. The antenna operates at a 5.8 GHz frequency and utilizes a quarter‐wavelength unit cell structure. The design employs a Graph Sample and Aggregate‐Attention Network (GSAAN) to enhance the transmission characteristics of the metasurface. To optimize the performance of GSAAN, the Giza Pyramids Construction Algorithm (GPCN) is applied to adjust the weight parameters, leading to significant improvements in radiation efficiency, bandwidth, gain, directivity, and return loss. The proposed HGM antenna is simulated in MATLAB 2023b, where it demonstrates substantial performance gains over existing methods. Specifically, the proposed design achieves 28.34% higher gain compared to the MSA‐RHCOA method, 24.47% improvement over HGM‐AD‐MATCS, 26.34% better gain than BR‐HGA‐PGM, and a 32.12% gain increase relative to MSA‐Hyb‐ADSA‐HMSOA. These enhancements make the proposed antenna design a competitive solution for high‐gain applications in wireless communication, satellite communication, and radar systems. The integration of GSAAN with GPCN optimization in the HGM antenna design enables the creation of highly directive radiation patterns, making it well‐suited for IoT applications that require high performance and reliability. The results of this study demonstrate the effectiveness of the proposed approach in achieving superior antenna performance, positioning it as a strong alternative to existing metasurface antenna designs.

Analysis of order-of-addition experiments

The order-of-addition (OofA) experiment involves arranging components in a specific order to optimize a certain objective, which is attracting a great deal of attention in many disciplines, especially in the areas of biochemistry, scheduling, and engineering. Recent studies have highlighted its significance, and notable works have aimed to address NP-hard OofA problems from a statistical perspective. However, solving OofA problems presents challenges due to their complex nature and the presence of uncertainty, such as scheduling problems with uncertain processing times. These uncertainties affect processing times, which are not known with certainty in advance. They introduce heteroscedasticity into OofA experiments, where different orders result in varying dispersions. To address these challenges, a unified framework is proposed to analyze scheduling problems without making specific assumptions about the distribution of these certainties. It encompasses model development and optimization, encapsulating existing homoscedastic studies (where different orders produce the same dispersion value) as a specific instance. For heteroscedastic cases, a dual response optimization within an uncertainty set is proposed, aiming to minimize the dispersion of response while keeping the location of response with a predefined target value. However, solving the proposed non-linear minimax optimization is rather challenging. An equivalent optimization formulation with low computational cost is proposed for solving such a challenging problem. Theoretical supports are established to ensure the tractability of the proposed method. Simulation studies are conducted to demonstrate the effectiveness of the proposed approach. With its solid theoretical support, ease of implementation, and ability to find an optimal order, the proposed approach offers a practical and competitive solution to solving general order-of-addition problems.

Physics-Informed Neural Networks for Modeling Li-ion Batteries: Solving the Single Particle Model Without Labeled Data

Abstract Li-ion batteries are garnering significant attention due to the electrification of critical sectors. High-fidelity battery cell models have proven effective in assessing performance and optimizing design, alleviating the financial burden associated with extensive experimental procedures. However, the computational costs associated with such simulations can become prohibitive, particularly when numerous iterations are required or when integration into small devices, such as battery management systems, is necessary. To address these challenges and provide an alternative to traditional methods such as finite element and finite volume solvers, we propose the development of an algorithm that utilizes Physics-Informed Neural Networks (PINNs) to solve the Single Particle Model across multiple parameter ranges. A notable advantage of this machine learning approach is its capacity to generate competitive solutions post-training by relying solely on the governing equations, without the necessity for experimental or simulation data. Additionally, the lightweight nature of the model indicates its potential for embedding within small-scale devices.