Search Results (47)

The rapid growth of electric vehicles (EVs) has created an urgent need for sustainable end-of-life battery management systems. This paper presents a novel AI-driven framework for designing resilient reverse logistics networks that optimize the collection, testing, repurposing, and recycling of EV batteries within a circular economy context. We develop a bi-level optimization model in which the upper level determines strategic facility location decisions under disruption uncertainty, and the lower level employs deep reinforcement learning (DRL) to make dynamic operational decisions including battery routing, State-of-Health (SoH)-based sorting, and inventory management. The model simultaneously optimizes three objectives: total supply chain cost minimization, carbon emission reduction, and resilience maximization. A novel Fuzzy-Robust Stochastic programming approach with Conditional Value-at-Risk (FRS-CVaR) handles hybrid uncertainty from demand variability, supply disruptions, and material price volatility. We propose an enhanced Non-dominated Sorting Genetic Algorithm III (NSGA-III) integrated with Proximal Policy Optimization (PPO) for an efficient solution. The framework is validated through a comprehensive case study of the Gulf Cooperation Council (GCC) region, demonstrating that the AI-driven approach reduces total costs by 18.7%, decreases carbon emissions by 23.4%, and improves supply chain resilience by 31.2% compared to traditional optimization methods. Ablation studies across 10 independent runs with different random seeds confirm the robustness of these findings (95% confidence intervals within ±2.3% for all metrics). Sensitivity analysis reveals that battery SoH prediction accuracy and facility redundancy levels significantly impact network performance. This research contributes to both methodology and practice by providing decision-makers with an intelligent, adaptive tool for sustainable EV battery lifecycle management. Full article

Autonomous vehicles (AVs) promise improved safety and sustainability, yet their sophisticated sensing, computing, and communication systems impose auxiliary power loads of 1.5–3.2 kW, risking an increase of up to 45% in global transport energy demand by 2040 if left unaddressed. Existing energy management strategies fail to jointly optimize propulsion and autonomy subsystems under real-world dynamic traffic, treat ADAS loads as static, and lack statistically rigorous validation. This paper proposes a novel Adaptive Neuro-Fuzzy Inference System (ANFIS)-PID framework that integrates (i) 5 s V2X traffic preview, (ii) online PID gain scheduling, and (iii) energy-aware rule pruning for real-time energy allocation. Validated on a real-world trajectory dataset, the approach consistently reduces fuel consumption by up to 4.4% over pure fuzzy logic, 0.05% over FL-RWOA, 1.16% over FL-GWO, and 2.39% over FL-PSO across 25–100 km segments (paired t-test, p ≤ 0.001 on 50 random segments). Additional benefits include 18% faster transient response and 18% lower inference computational load compared to metaheuristic baselines. Scaled to fleet level, the 0.51 L/100 km average saving equates to over CAD 100 million annual savings in Canada. The hybrid neuro-fuzzy architecture offers a deployable, adaptive solution for sustainable autonomous transportation. Full article

This study presents a practical framework for the maximal covering location problem (MCLP) under uncertainty. The approach combines possibility theory with chance-constrained programming to represent both imprecision and randomness in demand. Demand is modeled as fuzzy random variables. Using the Zadeh extension principle, both the fuzzy and fuzzy random formulations are transformed into equivalent deterministic mixed-integer programs. Clear linearization steps are provided for the objective function and constraints. Two specifications are examined to reflect different attitudes toward risk. The first specification uses possibility measures, reflecting an optimistic stance, while the second uses necessity measures and represents a conservative approach. Computational experiments conducted in an urban facility context show that increasing the possibility or probability level results in more conservative solutions and a smaller amount of covered demand. In contrast, lower thresholds lead to more exhaustive coverage with greater exposure to uncertainty. In the deterministic scenario, full coverage becomes attainable as the number of facilities increases. Under uncertainty, the models balance coverage with robustness based on the chosen risk tolerance levels. The proposed framework serves as a flexible decision support tool, enabling planners to align facility location choices with their risk tolerance while maintaining tractability with standard optimization solvers. Full article

The growing demand for energy and the environmental impacts of fossil fuels have driven the search for sustainable alternatives such as biodiesel. Castor oil stands out as a promising non-edible feedstock but requires optimization strategies to overcome challenges in its conversion to biodiesel. This study developed a predictive model to determine the optimal parameters for homogeneous alkaline or acid transesterification of castor oil, aiming to maximize fatty acid methyl ester (FAME) yield. A dataset of 406 operating conditions from the literature was used to train and evaluate six models: Multilayer Perceptron with logistic sigmoid activation (MLP-logsig), hyperbolic tangent activation (MLP-tansig), Radial Basis Function network (RBF), hybrid RBF + MLP, Random Forest (RF), and Adaptive Neuro-Fuzzy Inference System (ANFIS). The MLP-tansig achieved the best performance in training, validation, and testing (R > 0.98). However, when combined with a Genetic Algorithm (GA), it generated infeasible parameters. Conversely, the RBF + GA combination yielded results consistent with the literature: molar ratio 19.35:1, alkaline catalyst 1.13% w/w, temperature 50 °C, reaction time 70 min, and stirring speed 548.32 rpm, achieving 100% FAME yield. This approach reduces the need for extensive experimental testing, offering a cost- and time-efficient solution for optimizing biodiesel production. Full article

This paper introduces an innovative methodology for optimizing recommendation strategies across different populations within the food industry. While previous approaches to recommending courses have overlooked cultural and age-based preferences, our work demonstrates how understanding these differences can significantly enhance the attractiveness for consumers and create new opportunities for marketing. By simulating diverse populations using a fuzzy logic approach, based on individual characteristics such as age, gender, geographical area, and city size, the study evaluates how recommendation algorithms perform within a generated menu database. Results show that algorithms like State–Action–Reward–State–Action (SARSA), multi-armed bandit (MAB), and Deep-Q Network (DQN) exhibit varying levels of efficiency depending on the population. Notably, the DQN improves accumulated reward over a random recommender by 71.60% for “Foodies”, 65.02% for “Veggies”, 63.46% for “Spanish”, and 8.89% for “Seniors”, while MAB achieves similar performance with fewer resources. Statistically significant differences (p < 0.005) are found in the performance of the DQN between populations, with large effect sizes according to Cliff’s delta. These findings highlight recommender systems as an opportunity to navigate market demand, optimize supply chains, and reduce food waste. A better understanding of public preferences enables more effective alignment of supply and demand across the entire food supply chain. As a conclusion, while the DQN effectively captures target group preferences, the optimum recommendation strategy should be chosen by balancing algorithmic performance, computational efficiency, and the specific requirements of the food sector. Full article

Aiming at the problems that the random probability characteristics of large-scale source and load resources lead to the ineffectiveness of deterministic planning methods, the standard grid structure is difficult to adapt to the demands of diversified scenarios. This paper proposes a grid-based scenario delineation method for distribution networks based on fuzzy comprehensive evaluation and SNN-DPC (density peak clustering based on shared-nearest-neighbors). First, analyze the response characteristics of various types of flexible resources, and establish a multi-dimensional comprehensive assessment index system that integrates operational characteristics and structural features. Second, the comprehensive weights of each index in the index layer are calculated based on the DEMATEL-ANP method and the CRITIC method, and the assessment value of the intermediate layer is calculated by the fuzzy comprehensive evaluation method. Finally, the assessment value of the intermediate layer is clustered based on the improved SNN-DPC algorithm, so as to classify the distribution grid scenarios. The results indicate that the proposed method can effectively and accurately classify distribution network scenarios. Full article

Driven by the demand for cost-effective vehicle access, enhanced flexibility, and sustainable transportation practices, smart car-sharing has emerged as a prominent alternative to traditional vehicle rental systems. Leveraging the Internet of Vehicles (IoV) and wireless communication, these systems feature dynamic renter-vehicle mappings, enabling users to access any available vehicle rather than being restricted to a specific one pre-assigned by the service provider. However, many existing schemes in the IoV field conflate users and vehicles, complicating the identification and tracking of the vehicle’s actual driver. Moreover, most current authentication protocols rely on a strict, initial binding between a user and a vehicle, rendering them unsuitable for the dynamic nature of car-sharing environments. To address these challenges, we propose an enhanced certificateless signature scheme tailored for smart car-sharing. By employing a biometric fuzzy extractor and the Chinese Remainder Theorem, our scheme provides a fine-grained authentication mechanism that eliminates the need for local computations on the user’s side, meaning users do not require a smartphone or other digital device. Furthermore, our scheme introduces category identifiers to facilitate vehicle selection based on specific classes within car-sharing contexts. A formal security analysis demonstrates that our scheme is existentially unforgeable against adversaries under the random oracle model. Finally, a comprehensive evaluation shows that our proposed scheme achieves competitive performance in terms of computational and communication overhead while offering enhanced practical functionalities. Full article

Electric vehicles (EVs) are gradually gaining high penetration in transportation due to their low carbon emissions and high power conversion efficiency. However, the large-scale charging demand poses significant challenges to grid stability, particularly the risk of transformer overload caused by random charging. It is necessary that a coordinated charging strategy be carried out to alleviate this challenge. We propose a hierarchical charging scheduling framework to optimize EV charging consisting of demand prediction and hierarchical scheduling. Fuzzy reasoning is introduced to predict EV charging demand, better modeling the relationship between travel distance and charging demand. A hierarchical model was developed based on NSGA-II, where the upper layer generates Pareto-optimal power allocations and then the lower layer dispatches individual vehicles under these allocations. A simulation under this strategy was conducted in a residential scenario. The results revealed that the coordinated strategy reduced the user costs by 21% and the grid load variance by 64% compared with uncoordinated charging. Additionally, the Pareto front could serve as a decision-making tool for balancing user economic interest and grid stability objectives. Full article

This study examines reinforcement learning (RL) and fuzzy logic control (FLC) for optimizing battery energy storage in residential systems with photovoltaic (PV) power, grid interconnection, and dynamic or fixed electricity pricing. Effective management strategies are crucial for reducing costs, extending battery lifespan, and ensuring reliability under fluctuating demand and tariffs. A 24 h simulation with minute-level resolution modeled diverse conditions, including random household demand and ten initial state of charge (SOC) levels from 0% to 100%. RL employed proximal policy optimization (PPO) for adaptive energy scheduling, while FLC used rule-based logic for charge–discharge cycles. Results showed that FLC rapidly restored SOC at low levels, ensuring immediate availability but causing cost fluctuations and increased cycling, particularly under stable pricing or low demand. RL dynamically adjusted charging and discharging, reducing costs and smoothing energy flows while limiting battery cycling. Feature importance analysis using multiple linear regression (MLR) and random forest regression (RFR) confirmed SOC and time as key performance determinants. The findings highlight a trade-off between FLC’s rapid response and RL’s sustained cost efficiency, providing insights for optimizing residential energy management to enhance economic and operational performance. Full article

With the rapid growth of the electric vehicle market, the importance of the user experience and product sustainability requirements for intelligent charging stations has become increasingly significant. However, accurately capturing the complex associations between design features and sustainability elements remains challenging. Therefore, this study aims to balance user needs and environmental standards in designing smart charging piles, ensuring adherence to symmetry principles. This balance addresses the growing demand for personalization and ensures sustainability. In this paper, the semiotic approach to product construction (SAPAD) model is introduced to analyze the user behavioral process in depth and clarify the core needs of users. Subsequently, these core needs are translated into specific technical requirements for products, and a correlation matrix linking user needs with product technical requirements is constructed using fuzzy quality function deployment (FQFD) to identify design features that fulfill the user requirements. The sustainability factors are then comprehensively evaluated and prioritized based on three dimensions: economic, environmental, and social, i.e., the triple bottom line (TBL). Furthermore, a mapping matrix is developed to connect the design features and sustainability factors, which is combined with the particle swarm optimization–random forest (PSO-RF) algorithm to predict the sustainability factors associated with design features that meet users’ needs. The number of branches m and the maximum depth d of the random forest (RF) algorithm are optimized using the particle swarm optimization (PSO) method. The results indicate that the SAPAD-FQFD model effectively identifies the user needs and relevant product design features. In contrast, the PSO-RF model adeptly manages the nonlinear relationships between charging pile design features and various sustainability factors, e.g., aesthetics and material selection, ensuring that the intelligent charging pile meets users’ core needs in terms of form and function, while embodying the principles of design symmetry. This integrated approach effectively bridges the gap between user needs analysis and product functional design, ensuring the sustainability of the design solution. This study contributes a sustainable framework for the development and design of smart charging piles and related products, further promoting the adoption of green design principles and symmetry design concepts within the supporting infrastructure of new energy vehicles. Full article

In the present paper, a sustainable supply chain model is investigated with a variable production rate and remanufacturing for the production of defective items under the effect of learning fuzzy theory, where the lower and upper variations in fuzzy demand rate are affected by learning parameters and backorders are also allowed. Our proposed model reveals a springy manufacturing inventory organization that makes various types of items, and imperfect items can be created through the method of manufacturing things in a fuzzy environment. When the screening process is completed, defective items are remanufactured immediately, and a limited financial plan and space limitations are assumed concerning the product assembly. We minimized the total fuzzy inventory cost with different distributions (beta, triangular, double triangular, uniform, and χ² (chi−square)) concerning the production rate, lot size, and backorder under learning in a fuzzy environment where the costs of screening, manufacturing, carrying, carbon emissions, backorders, and remanufacturing are included. The Kuhn–Tucker optimization technique is applied to solve non-linear equations that are based on some distributions. Numerical examples, sensitivity analysis, managerial insights and observations, limitations, future work, and applications are provided for the validation of our proposed model, and the industrial scope of this proposed work is included. Full article

Modern marine ranching construction has drawn growing attention of relevant planning authorities and enterprises with the potential value of oceans becoming apparent. To satisfy the demand for a successful marine ranching construction, site selection is considered as the first and fundamental procedure. This work aims to help planning authorities find the optimal marine ranching site by introducing a methodological evaluation framework for solving this critical problem. Firstly, the advanced CRiteria Importance Through Inter-criteria Correlation (CRITIC) method is extended by using a cloud model to determine the relative importance of attributes in marine ranching site selection problems. Secondly, the Evaluation based on Distance from Average Solution (EDAS) method is developed by integration with the cloud model to obtain the ranks of alternative sites for marine ranching construction. The proposed cloud model-based CRITIC-EDAS method considers the fuzziness and randomness of the linguistic terms given by experts simultaneously to ensure the scientificity and rationality of decision making. Finally, a real-world marine ranching site selection problem is solved by using the proposed model, where the efficiency and reliability of the proposed model are verified according to the comparison with other traditional multi-attribute decision-making methods. Full article

Chaotic maps have been widely studied in the field of cryptography for their complex dynamics. However, chaos-based cryptosystems have not been widely used in practice. One important reason is that the following requirements of practical engineering applications are not taken into account: computational complexity and difficulty of hardware implementation. In this paper, based on the demand for information security applications, we modify the local structure of the three-dimensional Intertwining Logistic chaotic map to improve the efficiency of software calculation and reduce the cost of hardware implementation while maintaining the complex dynamic behavior of the original map. To achieve the goal by reducing the number of floating point operations, we design a mechanism that can be decomposed into two processes. One process is that the input parameters value of the original system is fixed to $2^k$ by Scale index analysis. The other process is that the transcendental function of the original system is replaced by a nonlinear polynomial. We named the new map as “Simple intertwining logistic”. The basic chaotic dynamic behavior of the new system for controlling parameter is qualitatively analyzed by bifurcation diagram and Lyapunov exponent; the non-periodicity of the sequence generated by the new system is quantitatively evaluated by using Scale index technique based on continuous wavelet change. Fuzzy entropy (FuzzyEn) is used to evaluate the randomness of the new system in different finite precision digital systems. The analysis and evaluation results show that the optimized map could achieve the designed target. Then, a novel scheme for generating pseudo-random numbers is proposed based on new map. To ensure its usability in cryptographic applications, a series of analysis are carried out. They mainly include key space analysis, recurrence plots analysis, correlation analysis, information entropy, statistical complexity measure, and performance speed. The statistical properties of the proposed pseudo random number generator (PRNG) are tested with NIST SP800-22 and DIEHARD. The obtained results of analyzing and statistical software testing shows that, the proposed PRNG passed all these tests and have good randomness. In particular, the speed of generating random numbers is extremely rapid compared with existing chaotic PRNGs. Compared to the original chaotic map (using the same scheme of random number generation), the speed is increased by 1.5 times. Thus, the proposed PRNG can be used in the information security. Full article

Photovoltaic (PV) arrays have a considerably lower output when exposed to partial shadowing (PS). Whilst adding bypass diodes to the output reduces PS’s impact, this adjustment causes many output power peaks. Because of their tendency to converge to local maxima, traditional algorithms like perturb and observe and hill-climbing should not be used to track the optimal peak. The tracking of the optimal peak is achieved by employing a range of artificial intelligence methodologies, such as utilizing an artificial neural network and implementing control based on fuzzy logic principles. These algorithms perform satisfactorily under PS conditions but their training method necessitates a sizable quantity of data which result in placing an unnecessary demand on CPU memory. In order to achieve maximum power point tracking (MPPT) with fast convergence, minimal power fluctuations, and excellent stability, this paper introduces a novel optimization algorithm named PSO-AWDV (particle swarm optimization–adaptive weighted delay velocity). This algorithm employs a stochastic search approach, which involves the random exploration of the search space, to accomplish these goals. The efficacy of the proposed algorithm is demonstrated by conducting experiments on a series-connected configuration of four modules, under different levels of solar radiation. The algorithm successfully gets rid of the problems brought on by current traditional and AI-based methods. The PSO-AWDV algorithm stands out for its simplicity and reduced computational complexity when compared to traditional PSO and its variant PSO-VC, while excelling in locating the maximum power point (MPP) even in intricate shading scenarios, encompassing partial shading conditions and notable insolation fluctuations. Furthermore, its tracking efficiency surpasses that of both conventional PSO and PSO-VC. To further validate our results, we conducted a real-time hardware-in-the-loop (HIL) emulation, which confirmed the superiority of the PSO-AWDV algorithm over traditional and AI-based methods. Overall, the proposed algorithm offers a practical solution to the challenges of MPPT under PS conditions, with promising outcomes for real-world PV applications. Full article

The concept of using wastewater as a substitute for limited water resources and environmental protection has enabled this sector to make major technological advancements and, as a result, has given us an abundance of physical data, including chemical, biological, and microbiological information. It is easier to comprehend wastewater treatment systems after studying this data. In order to achieve this, a number of studies use machine learning (ML) algorithms as a proactive approach to solving issues and modeling the functionalities of these processing systems while utilizing the experimental data gathered. The goal of this article is to use textual analysis techniques to extract the most popular machine learning models from scientific documents in the “Web of Science” database and analyze their relevance and historical development. This will help provide a general overview and global scientific follow-up of publications dealing with the application of artificial intelligence (AI) to overcome the challenges faced in wastewater treatment technologies. The findings suggest that developed countries are the major publishers of articles on this research topic, and an analysis of the publication trend reveals an exponential rise in numbers, reflecting the scientific community’s interest in the subject. As well, the results indicate that supervised learning is popular among researchers, with the Artificial Neural Network (ANN), Random Forest (RF), Support Vector Machine (SVM), Linear Regression (LR), Adaptive Neuro-Fuzzy Inference System (ANFIS), Decision Tree (DT), and Gradient Boosting (GB) being the machine learning models most frequently employed in the wastewater treatment domain. Research on optimization methods reveals that the most well-known method for calibrating models is genetic algorithms (GA). Finally, machine learning benefits wastewater treatment by enhancing data analysis accuracy and efficiency. Yet challenges arise as model training demands ample, high-quality data. Moreover, the limited interpretability of machine learning models complicates comprehension of the underlying mechanisms and decisions in wastewater treatment. Full article