Efficient Optimization Research Articles

Predicting biomass conversion and COD removal in wastewater treatment by phototrophic bacteria with interpretable machine learning.

Photosynthetic bacteria (PSB) excel in wastewater treatment by removing pollutants and generating biomass but are challenging to optimize due to complex operational and environmental interactions. Neural Ordinary Differential Equations, Elastic Net, Stacking, and Categorical Boosting were applied as artificial intelligence methods to predict chemical oxygen demand (COD) removal efficiency, biomass productivity, biomass yield, and energy yield. Among these, the Stacking model demonstrated superior predictive performance across all targets. Interpretable machine learning methods were employed to identify key features and establish their workable ranges, which included dissolved oxygen (0.3-2.8mgL⁻1), illuminance (2995.3-6000.0 lux), and light energy (20.0-40.0 kWh) for COD removal efficiency; organic loading rate (OLR, 5.7-7.5g COD L⁻1d⁻1), hydraulic retention time (HRT, 0.2-3.2d), and COD concentration (5.3-10.1gL⁻1) for biomass productivity; COD/N ratio (609.0-800.0), OLR (0.1-2.4g COD L⁻1d⁻1), and illuminance (2661-6000 lux) for biomass yield; and pH (6.5-7.9) and HRT (1.2-2.6d) for energy yield. The two-dimensional partial dependence plots revealed that optimal interactions between two key input features resulted in COD removal efficiency >72%, biomass productivity >28gL⁻1d⁻1, biomass yield> 0.96g CODbiomass g CODremoved⁻1, energy yield> 0.49g kWh⁻1. This work advances the understanding of PSB optimization in wastewater treatment through a combination of advanced machine learning and interpretability analysis, offering potential for more efficient resource recovery and process optimization.

An integrated energy efficiency optimization method of the wind-assisted hybrid ship for the shipping decarbonization.

The utilization of wind energy can provide auxiliary thrust and hence reduce the fuel consumption as well as carbon dioxide (CO2) emissions of wind-assisted ship. However, the use of sails would deviate main engine (ME) from its optimal operating point, which would reduce the engine fuel efficiency. The adoption of the shaft generator (SG) can maintain the ME running at the optimal fuel efficiency point in this condition. However, it is crucial to achieve the integrated optimization of the sailing speed, route, sails' angle of attack, and SG output power (SG-OP) to enhance the wind-assisted ship energy efficiency. Therefore, an integrated energy efficiency optimization method is proposed for reducing the ship fuel consumption. The results reveal that this method can effectively increase the energy efficiency of the wind-assisted hybrid ship, decreasing fuel consumption and energy efficiency operational index (EEOI) by about 5.25% and 7.36%, respectively.

Ultrasmooth Micromilling of Stainless Steel by Ultrashort Pulsed Laser Ablation Using MHz Bursts.

Ultrashort pulsed (USP) laser burst ablation has attracted numerous interests for its great potential in enhancing ablation efficiency and reducing the heat-affected zone. However, little attention has been paid to the influence of burst ablation on the processed surface quality. To fill this research gap, the present study conducts a comprehensive investigation on the surface processing of stainless steel using ultrashort pulsed laser burst ablation. Systematic experiments have been carried out to investigate influences of pulse number per burst (PpB), pulse fluence, and burst overlap ratio on surface quality and ablation efficiency. A two-dimensional model has been developed to unveil the fundamental thermodynamic process and evolution of ablation and melting in material during USP laser burst ablation. Compared to single-pulse ablation, the optimum ablation efficiency decreases with increasing PpB by less than 30% in burst ablation. Despite reduced ablation efficiency, burst-mode ablation can generate much better surface quality, achieving an ultrasmooth surface with an Sa roughness as low as 0.13 μm. Burst ablation generates distinctive surface structures compared to single-pulse ablation, and their formation mechanisms are scrutinized. The thickness of the surface melting layer is unveiled to determine surface morphology. Based on transmission electron microscopy (TEM) analysis and numerical simulation, a melting layer thickness between 100 and 320 nm is found to result in smooth surfaces. This work highlights the advantage of burst-mode ablation in achieving ultrasmooth surfaces on stainless steel and unveils the fundamental mechanisms of surface structures formation in USP laser burst ablation.

Transforming vessel and fleet operations in oil and gas: A framework for integrated operations planning and efficiency optimization

Transforming vessel and fleet operations in oil and gas: A framework for integrated operations planning and efficiency optimization

Efficient Modeling and Optimization Approach for Grating-Based Flow Cytometers

Efficient Modeling and Optimization Approach for Grating-Based Flow Cytometers

A Hybrid Biologically-Inspired Optimization Algorithm for Data Gathering in IoT Sensor Networks

The wireless sensor networks are autonomous Ad hoc Networks that form the backbone of IoT technology. Their vital role is to collect data from their physical environments and transfer these data to the Base Station (BS). This task implies high energy consumption when a suitable data routing policy is not applied. Then, the data collection method determines the efficiency of WSNs. Moreover, the IoT-based applications that require the mobility of the IoT sensor nodes introduce a new challenge regarding network connectivity. The IoT sensor node’s mobility leads to regular changes in the network topology, resulting in high packet loss during communication. The management of network energy use in order to prolong the battery life of IoT sensor nodes is a crucial issue, as IoT sensor nodes possess limited battery capacity. This paper addresses these issues by proposing an efficient Hybrid Biologically-Inspired Optimization Algorithm, named HBIP, for Data Gathering in IoT Sensor Networks. The flagship idea of the HBIP algorithm is to incorporate the swarming stage of the Bacterial Foraging Optimization (BFO) into the Artificial Bee Colony (ABC) Optimization’s exploitation phase. Simulation results show that the HBIP protocol outperforms the LEACH protocol and ABC and BFO metaheuristics regarding network energy consumption, lifetime, and data packets received at the BS. In practice, we demonstrated that the HBIP protocol increases the data collection by 84.40% over LEACH, 19.43% over BFO, and 7.26% over ABC in the network scenario considered. Further on, we extend the study of the HBIP algorithm on Mobile IoT Sensor Networks by proposing a Multi-Objective Optimization-based Data Gathering Protocol (MOO-DGP). The MOO-DGP protocol employs the HBIP algorithm to determine the best solution that balances Velocity, Cluster Stability, Link Quality, and Energy Consumption. An extensive evaluation of the MOO-DGP protocol shows it outperforms the existing Mobility-Based Clustering (MBC) protocol regarding effective data packet delivery rate, average control overhead, network lifespan, and energy consumption.

Unlocking the potential of CRISPR-Cas9 for cystic fibrosis: A systematic literature review.

CRISPR-Cas9 technology has revolutionized genetic engineering, offering precise and efficient genome editing capabilities. This review explores the application of CRISPR-Cas9 for cystic fibrosis (CF), particularly targeting mutations in the CFTR gene. CF is a multiorgan disease primarily affecting the lungs, gastrointestinal system (e.g., CF-related diabetes (CFRD), CF-associated liver disease (CFLD)), bones (CF-bone disease), and the reproductive system. CF, a genetic disorder characterized by defective ion transport leading to thick mucus accumulation, is often caused by mutations like ΔF508 in the CFTR gene. This review employs a systematic methodology, incorporating an extensive literature search across multiple academic databases, including PubMed, Web of Science, and ScienceDirect, to identify 40 high-quality studies focused on CRISPR-Cas9 applications for CFTR gene editing. The data collection process involved predefined inclusion criteria targeting experimental approaches, gene-editing outcomes, delivery methods, and verification techniques. Data analysis synthesized findings on editing efficiency, off-target effects, and delivery system optimization to present a comprehensive overview of the field. The review highlights the historical development of CRISPR-Cas9, its mechanism, and its transformative role in genetic engineering and medicine. A detailed examination of CRISPR-Cas9's application in CFTR gene correction emphasizes the potential for therapeutic interventions while addressing challenges such as off-target effects, delivery efficiency, and ethical considerations. Future directions include optimizing delivery systems, integrating advanced editing tools like prime and base editing, and expanding personalized medicine approaches to improve treatment outcomes. By systematically analyzing the current landscape, this review provides a foundation for advancing CRISPR-Cas9 technologies for cystic fibrosis treatment and related disorders.

Advanced microgrid optimization using price-elastic demand response and greedy rat swarm optimization for economic and environmental efficiency

In this paper, a comprehensive energy management framework for microgrids that incorporates price-based demand response programs (DRPs) and leverages an advanced optimization method—Greedy Rat Swarm Optimizer (GRSO) is proposed. The primary objective is to minimize the generation cost and environmental impact of microgrid systems by effectively scheduling distributed energy resources (DERs), including renewable energy sources (RES) such as solar and wind, alongside fossil-fuel-based generators. Four distinct demand response models—exponential, hyperbolic, logarithmic, and critical peak pricing (CPP)—are developed, each reflecting a different price elasticity of demand. These models are integrated with a flexible elasticity matrix to assess the dynamic consumer response to fluctuating electricity prices. The study evaluates four operational scenarios, focusing on grid participation, DER utilization, and the impact of real-time pricing (RTP), time of use (TOU), and critical peak pricing strategies. Quantitative results demonstrate the significant cost-saving potential of integrating DRPs with microgrid operations. In the optimal scenario, the GRSO achieved a minimum generation cost of 882¥ for the base load profile. Further, when critical peak pricing (CPP) was applied, the generation cost was reduced to 746¥, representing a 15.4% reduction. For a scenario where the grid’s participation was limited, the logarithmic-based demand response model decreased the generation cost to 817¥, while full grid interaction led to higher cost reductions. Additionally, our results show a significant reduction in peak load, with load factor improvements of up to 87.7% across the studied demand profiles. Furthermore, limiting the grid’s upstream power capacity to 30 kW resulted in a 7% increase in generation cost across all cases, confirming the importance of grid participation in reducing operational costs. The GRSO algorithm outperformed traditional metaheuristics in terms of both execution time and convergence, making it a viable solution for real-time microgrid optimization. In conclusion, the proposed GRSO-based framework provides an efficient approach for microgrid cost minimization, achieving up to a 15.4% reduction in operational costs and notable environmental benefits by reducing emissions. This study highlights the importance of dynamic demand response strategies and grid participation for sustainable and cost-effective microgrid management.

Simultaneous Optimization of Hydrogen Network with Pressure Swing Absorption Based on Evolutionary Response Surface Method

The simultaneous optimization of complex process units and hydrogen networks is a significant challenge in refinery hydrogen network integration. To address this, an evolutionary response surface-based collaborative optimization method is proposed, enabling the concurrent optimization of pressure swing adsorption (PSA) and the hydrogen network. This method develops a mechanistic model for PSA and alternates between random sampling and evolutionary response surface-based hydrogen network optimization to obtain diverse sampling points and potential optimal solutions. The PSA mechanistic model is then used to compute the accurate output parameters for the sampled points, and these parameters are incorporated into the hydrogen network optimization to obtain precise objective function values. An efficient optimization framework is presented to streamline the process. The proposed method is applied to a refinery hydrogen network integration case study, comprehensively considering both PSA costs and hydrogen utility costs. The results demonstrate that the method is computationally efficient and effectively reduces the refinery’s total annual costs. The accuracy of the optimization results is significantly improved compared to traditional methods, providing an effective solution for the collaborative optimization of the refinery hydrogen network and PSA.

Resource Assignment Algorithms for Autonomous Mobile Robots with Task Offloading

This paper deals with the optimization of the operational efficiency of a fleet of mobile robots, assigned with delivery-like missions in complex outdoor scenarios. The robots, due to limited onboard computation resources, need to offload some complex computing tasks to an edge/cloud server, requiring artificial intelligence and high computation loads. The mobile robots also need reliable and efficient radio communication with the network hosting edge/cloud servers. The resource assignment aims at minimizing the total latency and delay caused by the use of radio links and computation nodes. This minimization is a nonlinear integer programming problem, with high complexity. In this paper, we present reduced-complexity algorithms that allow to jointly optimize the available radio and computation resources. The original problem is reformulated and simplified, so that it can be solved by also selfish and greedy algorithms. For comparison purposes, a genetic algorithm (GA) is used as the baseline for the proposed optimization techniques. Simulation results in several scenarios show that the proposed sequential minimization (SM) algorithm achieves an almost optimal solution with significantly reduced complexity with respect to GA.

A State-of-the-Art Fractional Order-Driven Differential Evolution for Wind Farm Layout Optimization

The wind farm layout optimization problem (WFLOP) aims to maximize wind energy utilization efficiency and mitigate energy losses caused by wake effects by optimizing the spatial layout of wind turbines. Although Genetic Algorithms (GAs) and Particle Swarm Optimization (PSO) have been widely used in WFLOP due to their discrete optimization characteristics, they still have limitations in global exploration capability and optimization depth. Meanwhile, the Differential Evolution algorithm (DE), known for its strong global optimization ability and excellent performance in handling complex nonlinear problems, is well recognized in continuous optimization issues. However, since DE was originally designed for continuous optimization scenarios, it shows insufficient adaptability under the discrete nature of WFLOP, limiting its potential advantages. In this paper, we propose a Fractional-Order Difference-driven DE Optimization Algorithm called FODE. By introducing the memory and non-local properties of fractional-order differences, FODE effectively overcomes the adaptability issues of advanced DE variants in WFLOP’s discreteness while organically applying their global optimization capabilities for complex nonlinear problems to WFLOP to achieve more efficient overall optimization performance. Experimental results show that under 10 complex wind farm conditions, FODE significantly outperforms various current state-of-the-art WFLOP algorithms including GA, PSO, and DE variants in terms of optimization performance, robustness, and applicability. Incorporating more realistic wind speed distribution and wind condition data into modeling and experiments, further enhancing the realism of WFLOP studies presented here, provides a new technical pathway for optimizing wind farm layouts.

Dynamic configuration optimization of FPGA accelerators through reinforcement learning for enhanced performance and resource utilization

Abstract Deploying Sparse Ternary Neural Networks on edge devices is in the areas of computational efficiency and energy optimization is a challenging task. This work presents a new FPGA-based accelerator integrating reinforcement learning and neural architecture search to dynamically optimize Sparse Ternary Neural Networks (Sparse TNN) for real-time applications. The design adopts adaptive pruning and quantization techniques for computational complexity and power consumption with the desired accuracy. Experimental evaluation on the Xilinx ZCU102 platform achieves up to 16.46× speedup compared to dense models at less than 1% accuracy loss and achieves state-of-the-art performance on benchmarks such as Google Net and MobileNetV2. This work holds promise for resource-constrained high-throughput applications, bringing FPGA-based deep learning closer to efficiency and scalability.

A Paradigm of Computer Vision and Deep Learning Empowers the Strain Screening and Bioprocess Detection.

High-performance strain and corresponding fermentation process are essential for achieving efficient biomanufacturing. However, conventional offline detection methods for products are cumbersome and less stable, hindering the "Test" module in the operation of "Design-Build-Test-Learn" cycle for strain screening and fermentation process optimization. This study proposed and validated an innovative research paradigm combining computer vision with deep learning to facilitate efficient strain selection and effective fermentation process optimization. A practical framework was developed for gentamicin C1a titer as a proof-of-concept, using computer vision to extract different color space components across various cultivation systems. Subsequently, by integrating data preprocessing with algorithm design, a prediction model was developed using 1D-CNN model with Z-score preprocessing, achieving a correlation coefficient (R2) of 0.9862 for gentamicin C1a. Furthermore, this model was successfully applied for high-yield strain screening and real-time monitoring of the fermentation process and extended to rapid detection of fluorescent protein expression in promoter library construction. The visual sensing research paradigm proposed in this study provides a theoretical framework and data support for the standardization and digital monitoring of color-changing bioprocesses.

Efficient Distributed Sparse Relative Similarity Learning

Learning a good similarity measure for large-scale high-dimensional data is a crucial task in machine learning applications, yet it poses a significant challenge. Distributed minibatch stochastic gradient descent (SGD) serves as an efficient optimization method in large-scale distributed training, allowing linear speedup in proportion to the number of workers. However, communication efficiency in distributed SGD requires a sufficiently large minibatch size, presenting two distinct challenges. Firstly, a large minibatch size leads to high memory usage and computational complexity during parallel training of high-dimensional models. Second, a larger batch size of data reduces the convergence rate. To overcome these challenges, we propose an efficient distributed sparse relative similarity learning framework EDSRSL . This framework integrates two strategies: local minibatch SGD and sparse relative similarity learning. By effectively reducing the number of updates through synchronous delay while maintaining a large batch size, we address the issue of high computational cost. Additionally, we incorporate sparse model learning into the training process, significantly reducing computational cost. This paper also provides theoretical proof that the convergence rate does not decrease significantly with increasing batch size. Various experiments on six high-dimensional real-world datasets demonstrate the efficacy and efficiency of the proposed algorithms, with a communication cost reduction of up to \(90.89\%\) and a maximum wall time speedup of \(5.66\times\) compared to the baseline methods.

Advancing Mathematical Optimization Methods: Applications, Challenges, and Future Directions

Mathematical optimization methods have seen substantial advancements and applications in diverse fields, including industry, agriculture, commerce, and scientific research, due to advances in computer science and artificial intelligence. These methods improve production efficiency, resource allocation, and structural optimization. This paper reviews key optimization techniques such as gradient descent, Newtons method, and heuristic algorithms, discussing their advantages, limitations, and applicability. Although optimization methods offer powerful tools for solving complex equations and optimizing solutions, real-world scenarios often introduce challenges such as computational errors and model idealizations. The future of mathematical optimization lies in improving algorithm speed, usability, and accuracy, allowing broader accessibility and aligning solutions with practical realities. This exploration highlights both the current utility and the evolving potential of optimization techniques in addressing global challenges

Tomato Stem and Leaf Segmentation and Phenotype Parameter Extraction Based on Improved Red Billed Blue Magpie Optimization Algorithm

In response to the structural changes of tomato seedlings, traditional image techniques are difficult to accurately quantify key morphological parameters, such as leaf area, internode length, and mutual occlusion between organs. Therefore, this paper proposes a tomato point cloud stem and leaf segmentation framework based on Elite Strategy-based Improved Red-billed Blue Magpie Optimization (ES-RBMO) Algorithm. The framework uses a four-layer Convolutional Neural Network (CNN) for stem and leaf segmentation by incorporating an improved swarm intelligence algorithm with an accuracy of 0.965. Four key phenotypic parameters of the plant were extracted. The phenotypic parameters of plant height, stem thickness, leaf area and leaf inclination were analyzed by comparing the values extracted by manual measurements with the values extracted by the 3D point cloud technique. The results showed that the coefficients of determination (R2) for these parameters were 0.932, 0.741, 0.938 and 0.935, respectively, indicating high correlation. The root mean square error (RMSE) was 0.511, 0.135, 0.989 and 3.628, reflecting the level of error between the measured and extracted values. The absolute percentage errors (APE) were 1.970, 4.299, 4.365 and 5.531, which further quantified the measurement accuracy. In this study, an efficient and adaptive intelligent optimization framework was constructed, which is capable of optimizing data processing strategies to achieve efficient and accurate processing of tomato point cloud data. This study provides a new technical tool for plant phenotyping and helps to improve the intelligent management in agricultural production.

Enhancing fine-tuning efficiency and design optimization of an eight-channel 3T transmit array via equivalent circuit modeling and Eigenmode analysis.

Radiofrequency (RF) transmit arrays play a crucial role in various MRI applications, offering enhanced field control and improved imaging capabilities. Designing and optimizing these arrays, particularly in high-field MRI settings, poses challenges related to coupling, resonance, and construction imperfections. Numerical electromagnetic simulation methods effectively aid in the initial design, but discrepancies between simulated and fabricated arrays often necessitate fine-tuning. Fine-tuning involves iteratively adjusting the array's lumped elements, a complex and time-consuming process that demands expertise and substantial experience. This process is particularly required for high-Q-factor arrays or those with decoupling circuitries, where the impact of construction variations and coupling between elements is more pronounced. In this context, our study introduces and validates an accelerated fine-tuning approach custom RF transmit arrays, leveraging the arrays equivalent circuit modeling and eigenmode analysis of the scattering (S) parameters. This study aims to streamline the fine-tuning process of lab-fabricated RF transmit arrays, specifically targeting an eight-channel degenerate birdcage coil designed for 3T MRI. The objective is to minimize the array's modal reflected power values and address challenges related to coupling and resonance. An eight-channel 3T transmit array is designed and simulated, optimizing capacitor values via the co-simulation strategy and eigenmode analysis. The resulting values are used in constructing a prototype. Experimental measurements of the fabricated coil's S-parameters and fitting them into an equivalent circuit model, enabling estimation of self/mutual-inductances and self/mutual-resistances of the fabricated coil. Capacitor adjustments in the equivalent circuit model minimize mismatches between experimental and simulated results. The simulated eight-channel array, optimized for minimal normalized reflected power, exhibits excellent tuning and matching and an acceptable level of decoupling (|Snn|≤-23dB and |Smn|≤-11dB). However, the fabricated array displays deviations, including resonances at different frequencies and increased reflections. The proposed fine-tuning approach yields an updated set of capacitor values, improving resonance frequencies and reducing reflections. The fine-tuned array demonstrates comparable performance to the simulation (|Snn|≤-15dB and |Smn|≤-9dB), mitigating disparities caused by construction imperfections. The maximum error between the calculated and measured S-parameters is -7dB. This accelerated fine-tuning approach, integrating equivalent circuit modeling and eigenmode analysis, effectively optimizes the performance of fabricated transmit arrays. Demonstrated through the design and refinement of an eight-channel array, the method addresses construction-related disparities, showcasing its potential to enhance overall array performance. The approach holds promise for streamlining the design and optimization of complex RF coil systems, particularly for high Q-factor arrays and/or arrays with decoupling circuitry.

Chitosan-Based Bioactivator Mitigates Water Deficit Stress and Enhances Soybean Productivity

The chitosan-based bioactivator FF-BR (Patent Nº: US 9,868,677 B2) represents a cutting-edge solution within green chemistry, designed to enhance plant stresses tolerance. Upon application, FF-BR forms a protective film on the plant surface, triggering defense mechanisms. This study evaluated FF-BR’s capacity to mitigate the effects of water deficit in soybean plants under both greenhouse and field conditions, focusing on its impact on grain yield and physiological performance. Our results demonstrate that FF-BR significantly improved intrinsic water use efficiency (iWUE) in both greenhouse (66.70%) and field environments (35%). The net photosynthetic rate increased (8.12%-greenhouse; 12%-field), while stomatal conductance (20.21%-greenhouse; 15%-field) and leaf transpiration (14.30%-greenhouse; 10%-field) were reduced, reflecting enhanced water use efficiency. Additionally, under greenhouse conditions, FF-BR optimized energy dissipation via non-photochemical quenching (NPQ), potentially improving carbon assimilation during sun-shade transitions in crop canopies. Field experiments indicated cultivar-specific responses to FF-BR application. Early-cycle cultivar BMX 51X51 I2X-Trovão exhibited yield increases of 651 kg ha-1, 515 kg ha-1, and 667 kg ha-1 at concentrations of 0.75%, 1.0%, and 1.25% (v.v), respectively. By contrast, mid-cycle Soytech ST 641-I2X showed lower yield improvements of 278 kg ha-1, 216 kg ha-1, and 187 kg ha-1 at the same concentrations, compared to untreated controls. FF-BR also modulated root architecture by reducing growth rates in total root length (16.09%), root volume (41.11%), and surface area (26.04%) under well-watered conditions, while stabilizing root volume growth under drought, suggesting optimized water acquisition and minimized metabolic costs. This suggests that FF-BR enhances root water acquisition efficiency, while minimizing the metabolic costs of root plasticity—an essential adaptation in fluctuating environments. FF-BR offers a sustainable, innovative tool for improving soybean performance under water deficit conditions, enhancing water use efficiency and photosynthetic optimization while reducing ecological impacts. This bioactivator has promising applications for climate-resilient agriculture and long-term crop productivity.

Fault Diagnosis and Optimized Operation and Maintenance of Drop-out Fuses in Alpine Regions Using MKL-SVM and GRU

Extreme climate in alpine regions leads to frequent failures of drop-out fuses, but existing methods have low detection accuracy and response speed. This article combines MKL-SVM (Multiple Kernel Learning-Support Vector Machine) and GRU (Gated Recurrent Unit) model to achieve precise fault diagnosis of drop-out fuses, leveraging their efficient processing of high-dimensional time series data. Sensors are used to collect data such as voltage, current, temperature, and wind speed. Based on GRU, global trends, temporal hidden states, and dynamic nonlinear features of the data are extracted as inputs for subsequent MKL-SVM. In MKL-SVM, a linear kernel function is used to simplify the linear relationship between static features; targeting temporal features, RBF (Radial Basis Function) kernel effectively captures dynamic trends, fluctuations, and periodic changes in temporal features. To further enhance the classification ability of the model, the kernel function parameters, including linear kernel weights and RBF kernel widths, are adjusted through cross-validation. Finally, based on the model diagnosis results and predicted data, an optimized operation and maintenance plan is formulated to reduce maintenance costs and improve equipment operating efficiency. The results show that the fusion model can significantly improve the reliability of fault detection and adapt to the unique environmental challenges of alpine regions. The accuracy of fault diagnosis for drop-out fuses is 95%, with an MSE (mean square error) value of about 0.15 and a maintenance cost reduction of about 21.89%. This method can achieve accurate fault diagnosis and efficient optimization of operation and maintenance under extreme weather conditions.

Critical success factors for rail infrastructure joint ventures

Due to their myriad socioeconomic and environmental benefits, Joint Ventures (JVs) between construction contractors are considered a highly effective commercial strategy for delivering construction projects. This is especially true in the rail infrastructure industry. While rail infrastructure JVs (RIJVs) between several contractors may not always run smoothly, there have also been cases of successful implementation; nevertheless, the factors contributing to their success have not been comprehensively explored. It is crucial to thoroughly understand the critical success factors (CSFs) for RIJVs, as their success depends on the combination of various key factors during their implementation. This study aims to evaluate the CSFs for RIJVs. Through a comprehensive literature review, 20 CSFs for RIJVs were identified, and an expert survey was conducted with 40 UK-based RIJV professionals. The data were analysed using the relative importance index and Spearman’s rank correlation analysis. The top five perceived CSFs were communication, compatibility of partner objectives, suitable JV partner selection, trust, and effective planning. This suggests the level of importance attached to these CSFs by the professionals working in and managing RIJVs. Spearman’s rank correlation analysis revealed significant interdependencies among CSFs, such as the combination of trust with communication and the intent to learn with the level of participation and involvement, suggesting that these CSFs often go hand in hand. Further analysis of challenges encountered on RIJVs revealed four key themes: information management and IT systems integration, alignment, congruency and synergy, inter-organisational dynamics, and strategic management. Solutions proposed for these challenges also fell into four primary themes: strategic management and leadership, collaboration and communication, risk management and conflict resolution, and operational efficiency and resource optimisation. The findings showed a comprehensive evaluation of CSFs for RIJVs, highlighting pathways to effective JV execution. This study makes a valuable contribution to the existing body of knowledge on RIJV by analysing the CSFs. It also offers practical insights that can enhance the successful implementation of RIJV projects and provide guidance for top team managers in allocating strategic resources to key areas.