The increasing prevalence of digital twins across various industries is attributed to their capacity for enhancing performance, minimizing downtime, and improving efficiency in the manufacturing process. These virtual models enable users to monitor and analyze the real-time behavior of physical assets, systems, or processes. However, the design of digital twins presents several challenges, such as excessive time costs, security risks, data accuracy, privacy concerns, and complexity in chosen components. This research paper introduces a comprehensive framework that effectively and flexibly addresses these challenges in digital twin development by employing S4 features, a Morphological Matrix, and Fuzzy TOPSIS. The proposed framework draws inspiration from methodologies utilized in product design and leverages a morphological matrix to identify and categorize diverse S4 features. These features are crucial in creating smart, sustainable, sensing, and socially impactful digital twins. Additionally, Fuzzy TOPSIS is employed to determine the optimal digital twin structure. The digital twin is divided into a physical and virtual model, interconnected and interactively communicated through a dedicated interface model. Furthermore, the framework integrates human knowledge into the digital twin structure, enhancing its robustness. When combined with a Large Natural Language Processing model, a comparative analysis of the digital twin structure is presented. A reconfigurable micromachine is used as a case study to validate the proposed approach. The results demonstrate the proposed framework’s applicability for developing digital twins within the manufacturing industry. The main contribution of this paper is the innovative integration of human expertise and generative AI in a digital twin design framework. This approach provides a structured method that aligns the solution closely with industry requirements and offers a scalable and adaptable design methodology validated through practical applications. This framework is particularly valuable when dealing with a high number of devices that are challenging for human experts to evaluate rapidly in digital twin design.

The application of fuzzy hybrid methods has significantly increased in recent years across various sectors. However, the application of fuzzy hybrid methods for modeling systems or processes, such as fuzzy machine learning, fuzzy simulation, and fuzzy decision-making, has been relatively limited in the energy sector. Moreover, compared to standard methods, the benefits of fuzzy-hybrid methods for capturing complex problems are not adequately explored for the solar energy sector, which is one of the most important renewable energy sources in electric grids. This paper investigates the application of fuzzy hybrid systems in the solar energy sector compared to other sectors through a systematic review of journal articles published from 2012 to 2022. Selection criteria for choosing an appropriate method in each investigated fuzzy hybrid method are also presented and discussed. This study contributes to the existing literature in the solar energy domain by providing a state-of-the-art review of existing fuzzy hybrid techniques to (1) demonstrate their capability for capturing complex problems while overcoming limitations inherent in standard modeling methods, (2) recommend criteria for selecting an appropriate fuzzy hybrid technique for applications in solar energy research, and (3) assess the applicability of fuzzy hybrid techniques for solving practical problems in the solar energy sector.

The demand for electrical energy has increased since the population of and automation in factories have grown. The manufacturing industry has been growing dramatically due to the fast-changing market, so electrical energy for manufacturing processes has increased. As a result, solar energy has been installed to supply electrical energy. Thus, assessing a solar panel company could be a complex task for manufacturing companies that need to assess, install, and operate solar panels when several criteria with different hierarchies from decision-makers are involved. In addition, the stages of a solar panel system could be divided into analysis, installation, operation, and disposal, and all of them must be considered. Thus, the solar panel company must provide a holistic solution for each stage of the solar panel lifespan. This paper provides a fuzzy decision-making approach (Fuzzy TOPSIS) to deal with the assessment of solar companies using the S4 framework in which the sensing, smart, sustainable, and social features are labeled with linguistic values that allow the evaluation of companies using fuzzy values and linguistic labels, instead of using crisp values that are difficult to define when decision-makers are evaluating a solar company for installation of the solar panels. The S4 features are considered the benefits of the evaluation. In the case study presented, three solar panel companies with different alternatives are evaluated on the basis of three decision-makers from manufacturing companies using the S4 framework. This paper considers the benefits of solar companies in the context of decision-makers participating in a multi-decision selection of such a company to install solar panels, so that the selection process is more effective. Thus, the proposed Fuzzy TOPSIS method proved efficient when selecting a solar panel company from among many options that best meets the needs of manufacturing companies.

Currently, the industrial sector consumes more than 60% of the energy produced in Mexico, mainly from fossil fuels, causing negative impacts on the environment and human beings. Solar energy helps companies diversify their energy sources, generate savings, and reduce dependence on fossil fuels. Moreover, the environmental impact can be reduced when CO₂ emissions are reduced. Nevertheless, in Mexico, less than 3.5% of the electricity comes from solar energy, and along with a lack of information about the technical and social aspects involved in photovoltaic (PV) systems, it is difficult for companies to analyze and evaluate relevant data, and thus make effective decisions based on their needs. As such, companies cannot understand the complete lifecycle of PV systems, and, usually, the economic, environmental, and technical decisions are made only using the installation analysis, which is only one stage in the lifespan of PV systems. This paper proposes an S4 framework with the sensing, smart, sustainable, and social features that small and medium-sized companies must consider to install, operate, and dispose of PV systems, considering the Mexican context. The current literature does not show a complete classification to cover the essential S4 features to describe PV systems, so companies only have partial information when deciding about the installation of PV systems. This framework considers all the needs that may exist during the PV systems’ lifecycle, making a detailed evaluation of each of its elements in each lifecycle stage. Consequently, this S4 framework gives a complete guideline allowing companies to decide on PV systems. Finally, this paper presents a case study about a Mexican company that uses the proposed S4 framework to analyze the PV’s lifespan.

Artificial intelligence (AI) has emerged as a transformative tool for optimizing photovoltaic (PV) systems, enhancing energy efficiency, predictive maintenance, and fault detection. This study presents a systematic literature review and bibliometric analysis to identify the most commonly used AI techniques and their applications in PV systems. The review provides details on the advantages, limitations, and optimal use cases of various review techniques, such as Artificial Neural Networks, Fuzzy Logic, Convolutional Neural Networks, Long-Short Term Memory, Support Vector Machines, Decision Trees, Random Forest, k-Nearest Neighbors, and Particle Swarm Optimization. The findings highlight that maximum power point tracking (MPPT) optimization is the most widely researched AI application, followed by solar power forecasting, parameter estimation, fault detection and classification, and solar radiation forecasting. The bibliometric analysis reveals a growing trend in AI-PV research from 2018 to 2024, with China, the United States, and European countries leading in contributions. Furthermore, a type-2 fuzzy logic system is developed in MATLAB R2023b for automating AI technique selection based on the problem type, offering a practical tool for researchers, industry professionals, and policymakers. The study also discusses the practical implications of adopting AI in PV systems and provides future directions for research. This work serves as a comprehensive reference for advancing AI-driven solar PV technologies, contributing to a more efficient, reliable, and sustainable energy future.