This article proposes an effective evolutionary hybrid optimization method for identifying unknown parameters in photovoltaic (PV) models based on the northern goshawk optimization algorithm (NGO) and pattern search (PS). The chaotic sequence is used to improve the exploration capability of the NGO algorithm technique while evading premature convergence. The suggested hybrid algorithm, chaotic northern goshawk, and pattern search (CNGPS), takes advantage of the chaotic NGO algorithm’s effective global search capability as well as the pattern search method’s powerful local search capability. The effectiveness of the recommended CNGPS algorithm is verified through the use of mathematical test functions, and its results are contrasted with those of a conventional NGO and other effective optimization methods. The CNGPS is then used to extract the PV parameters, and the parameter identification is defined as an objective function to be minimized based on the difference between the estimated and experimental data. The usefulness of the CNGPS for extraction parameters is evaluated using three distinct PV models: SDM, DDM, and TDM. The numerical investigates illustrate that the new algorithm may produce better optimum solutions and outperform previous approaches in the literature. The simulation results display that the novel optimization method achieves the lowest root mean square error and obtains better optima than existing methods in various solar cells.

Mathematical optimization can be a useful strategy for minimizing energy usage while designing low-energy buildings. To handle building energy optimization challenges, this study provides an effective hybrid technique based on the pelican optimization algorithm (POA) and the single candidate optimizer (SCO). The suggested hybrid algorithm (POSCO) benefits from both the robust local search power of the single candidate method and the efficient global search capabilities of the pelican optimization. To conduct the building optimization task, the optimization method was developed and integrated with the EnergyPlus codes. The effectiveness of the proposed POSCO method was verified using mathematical test functions, and the outcomes were contrasted with those of conventional POA and other effective optimization techniques. Application of POSCO for global function optimization reveals that, among the thirteen considered functions, the proposed method was best at finding the global solution for seven functions, while providing superior results for the other functions when compared with competitive techniques. The suggested POSCO is applied for reducing an office buildings’ annual energy use. Comparing POSCO to POA procedures, the building energy usage is reduced. Furthermore, POSCO is compared to simple POA and other algorithms, with the results showing that, at specific temperatures and lighting conditions, the POSCO approach outperforms selected state-of-the-art methods and reduces building energy usage. As a result, all data suggests that POSCO is a very promising, dependable, and feasible optimization strategy for dealing with building energy optimization models. Finally, the building energy optimization findings for various climatic conditions demonstrate that the changes to the weather dataset had limited effect on the efficiency of the optimization procedure.

Accurately determining phase fractions in two-phase flows is among the most significant issues in Industries related to the production and processing of petroleum and petrochemicals. There are numerous sensor types and configurations for measuring the void fraction. In this respect, the capacitance-based sensor is commonly recognized as one of the most precise and widely utilized sensors. In this essay, COMSOL Multiphysics software, which has been benchmarked, was used for simulations with various electrode architectures for measuring oil-air two-phase flow in an annular pattern. The initial electrode configurations were helix, double ring, concave and parallel plates. Finite element analysis utilizing COMSOL Multiphysics was executed to compare the electrode configurations. Results exposed disparate sensitivities for different electrode geometries. To get better results, a new electrode geometry called arrow-shaped which was optimized with Artificial intelligence (AI) was proposed and compared with the others. The sensor responses presented demonstrated that the proposed arrow-shaped capacitance-based sensor had 21% higher sensitivity than the best-performing sensor among four other existing sensor designs, including concave, helix, double ring, and parallel plates. These results indicate the superior performance of the arrow-shaped sensor and its potential for use in high-sensitivity applications.

This research was conducted to forecast the uniaxial compressive strength (UCS) of rocks via the random forest, artificial neural network, Gaussian process regression, support vector machine, K-nearest neighbor, adaptive neuro-fuzzy inference system, simple regression, and multiple linear regression approaches. For this purpose, geo-mechanical and petrographic characteristics of sedimentary rocks in southern Iran were measured. The effect of petrography on geo-mechanical characteristics was assessed. The carbonate and sandstone samples were classified as mudstone to grainstone and calc-litharenite, respectively. Due to the shallow depth of the studied mines and the low amount of quartz minerals in the samples, the rock bursting phenomenon does not occur in these mines. To develop UCS predictor models, porosity, point load index, water absorption, P-wave velocity, and density were considered as inputs. Using variance accounted for, mean absolute percentage error, root-mean-square-error, determination coefficient (R²), and performance index (PI), the efficiency of the methods was evaluated. Analysis of model criteria using multiple linear regression allowed for the development of a user-friendly equation, which proved to have adequate accuracy. All intelligent methods (with R² > 90%) had excellent accuracy for estimating UCS. The percentage difference of the average of all six intelligent methods with the measured value was equal to +0.28%. By comparing the methods, the accuracy of the support vector machine with radial basis function in predicting UCS was (R² = 0.99 and PI = 1.92) and outperformed all the other methods investigated.