Off-design Performance Research Articles

Off-design characteristics and operation strategy analysis of a compressed carbon dioxide energy storage system coupled with a combined heating and power plant

To advance renewable energy development, it is crucial to increase the operational flexibility of power plants to consume renewable energy. Supercritical compressed carbon dioxide energy storage (SC-CCES) system is considered as a promising solution. This paper develops thermodynamic and off-design models for system components to formulate the system off-design model. The round-trip efficiency (RTE), system power efficiency (SPE), total exergy efficiency (TEE), and energy storage density (ESD) are defined to analyze the off-design performance of the system under two operation strategies. The results indicate that the system achieves the RTE of 32.44 %, SPE of 67.58 %, TEE of 43.26 %, and ESD of 1.73 kWh/m3 under the rated operating condition. The input power, output power, heat transfer rate, and mass flow rate during the charging and discharging process are proportional to the load level for both operation strategies. The RTE and TEE of the system vary inversely with the charging load level and directly with the discharging load level. The ESD is independent of the charging load level and increases with the discharging load level. The speed regulation-throttling regulation (SR-TR) operation strategy demonstrates superior system performance and a broader range of operating conditions.

Auxiliary Heat System Design and Off-Design Performance Optimization of OTEC Radial Inflow Turbine

In this paper, solar energy is used as the auxiliary heat source of the ocean thermal energy radial inflow turbine, and the thermodynamic model of the circulation system is established. In addition, the ejector is introduced into the ocean thermal power generation system, and the process simulation is carried out using Aspen Plus V12. To address performance attenuation of the radial turbine under varying working conditions, shape optimization of a 30 kW OTEC radial turbine was conducted. Finally, the off-design performance variation in the radial inflow turbine is analyzed in the presence of a solar auxiliary heat source. The results show that the use of an auxiliary heat source can effectively improve the cycle efficiency of the system and is also conducive to the stable operation of the radial turbine. Under the condition of auxiliary heat source, the system cycle efficiency is increased by 2.269%.

Exergy analysis of off-design performance in solar-aided power generation systems: Evaluating the rationality of using part-load operation solution of coal-fired plants

Solar aided coal-fired power generation (SAPG) technology has been proven to be an effective way of renewable energy utilization. However, the efficiency of coal-fired units declines at partial loads, and solar inputs may further force the system to deviate from its design condition. In particular, part-load operation solutions for coal-fired units (PLOS) are conventionally applied to the SAPG system, a practice whose appropriateness has not yet been thoroughly evaluated. This paper, therefore, selects a 330 MW SAPG plant as a case study to conduct an exhaustive exergy analysis under off-design conditions. The findings indicate that the governing stage of the steam turbine and the slip-pressure operation are the main contributors to the efficiency degradation at partial loads. In addition, solar input resulted in significant changes in key operating parameters, such as exhaust flow rate and the pressure of each turbine stage. Merely adopting the PLOS for SAPG systems results in a marked increase in standard coal consumption by 0.99, 2.82, and 3.63 g/kWh at 50 %, 40 %, and 30 % load, respectively. However, the introduction of solar energy presents the potential to operate the unit more efficiently, particularly when valve point conditions are optimally adjusted. For instance, upon input of 28 MW solar thermal power, the #3 valve point condition shifted from a load of 321 MW–330 MW, achieving a reduction in standard coal consumption by 0.96 g/kWh, compared to the design condition of the original coal-fired unit. This study underscores the irrationality of directly applying PLOS from coal-fired units to SAPG system without tailored adjustments for solar integration.

Hybrid geothermal-fossil power cycle analysis in a Polish setting with a focus on off-design performance and CO2 emissions reductions

Growing demand for electricity due to economic development contributes to increased greenhouse gas production, especially CO2. However, emissions can be limited by enhancing the efficiency of primary energy conversion, such as integrating geothermal energy into coal-fired power plants. Therefore, this paper proposes replacing conventional feed-water heaters with geothermal preheaters to create a hybridized system. This study was based on a numerical model validated at a selected Polish power unit. The model was subsequently calibrated for off-design conditions to facilitate partial load analysis. The obtained characteristics outperformed those of the non-hybrid unit, generating over 18 MW of electric power output. Such an improvement could potentially boost the unit's net efficiency by more than 2.6 %. This enhancement is significant as power units typically operate under part load for approximately 90 % of the time, hence the need to evaluate the performance characteristics of hybridized units in those states. Furthermore, the research outlines the potential decrease in the plant's CO2 emission factor, with reductions reaching up to 6.5 % under off-design conditions. Based on a gap analysis of the existing literature, this paper's comprehensive partial load evaluation serves as a new addition to research on hybridized systems.

Off-design operation of supercritical CO2 Brayton cycle arranged with single and multiple turbomachinery shafts for lead-cooled fast reactor

The lead-cooled fast reactor (LFR) engenders novel requisites for the energy conversion system when applied to maritime ships and distributed energy supply systems. The supercritical carbon dioxide (sCO2) Brayton cycle, with the advantages of high efficiency, space-saving, simplicity, and flexibility, is a promising candidate for LFR. Here, we present the first study on the off-design operation of the sCO2 cycle for LFR, with the turbine and compressor arranged on a single shaft (coaxial-shaft) or two shafts (split-shaft). The off-design performances of the system are investigated using four rotational speed (RS) control-based hybrid control strategies. We showed that the split-shaft system controlled by separate turbine speed and compressor speed has a wider operating space of power load than the coaxial-shaft system. Among the four investigated control strategies, the RS-inventory hybrid control can achieve the best thermal efficiency during load variation by operating at the turbine speed and mass flow rate corresponding to the optimal turbine isentropic efficiency. The maximum operating space of power load (0%–100 %) can be achieved by the RS-turbine inlet pressure hybrid control and the RS-bypass hybrid control. Our study can provide guidance for the flexible and safe part-load operation for small-scale modular Gen-IV nuclear reactors.

Comparative study on the organic rankine cycle off-design performance under different zeotropic mixture flow boiling correlations

Zeotropic mixture utilization enhances the performance of the Organic Rankine cycle (ORC) significantly. For geothermal ORC power plants, the zeotropic mixture flow boiling correlation plays a vital role in both evaporator design and system performance evaluation. Based on the screened zeotropic mixture R1224yd(Z)/R1234ze(E) (0.452/0.548), a comparative analysis of 4 flow boiling correlations is performed to assess their impact on both evaporator design and system performance under off-design conditions. The results underscore a substantial impact of these correlations on determining the plate length, with the largest relative difference being 53.8%, consequently resulting in uncertainties of 31.7% and 23.4% for the evaporator exergy loss and cost, respectively. Under off-design working conditions, the relative difference in net power output varies from 16.43% to 7.67%. The exergy efficiency variation is up to 11.82% and the electricity production cost (EPC) uncertainty is up to 11.2% at the working condition with the maximum difference in net output work. This study provides valuable insights for selecting the appropriate zeotropic mixture flow boiling correlation in practical evaporator design and evaluating the off-design performance of ORC systems.

A comparative performance analysis of sensible thermal energy storage (with concentrated solar field and sCO2 Brayton Cycle) and hydrogen energy storage (with solar PV field)

Utility scale energy storage is an integral part of renewable energy installations to achieve sustainable and reliable transition to a net zero energy economy. There exists a myriad of such storage solutions each having unique characteristics. This paper attempts at a systems level quantitative study and comparison between two different energy storage technologies, Thermal Energy Storage System (TESS) which is already mature, and Hydrogen Energy Storage System (HESS) which gained a lot of momentum recently, with the former coupled with a concentrated parabolic trough solar field using molten salt as heat transfer fluid and a power block running on high efficiency sCO2 Brayton cycle while the latter is coupled with a solar photovoltaic (PV) field. So that comparisons can be made on similar scale, both the systems are normalized on the total equipment area used for capturing incident solar irradiation, i.e., total aperture area for the PTC field and total flat surface area of PV modules. Both the systems are subjected to year-long variations of ambient conditions and solar irradiance and off-design performances are simulated over various seasons. The results show superior performance of TESS in terms of roundtrip efficiency (96% as opposed to 32% with HESS) which also results in superior capacity utilization factor (CUF of 64.5% and 48% for TESS and HESS respectively) and better specific energy and energy density. However, HESS offers virtually infinite idling time where TESS has a shorter self-discharge time (17 h), and better power performance (specific power and power density) in 10MWe output range.

Evaluating the impact of off-design CHP performance on the optimal sizing and dispatch of hybrid renewable-CHP distributed energy resources

The maturation of distributed energy resources (DER) has prompted the exploration of their deployment in commercial building applications due to their potential to supply energy at lower costs and emissions rates compared to centralized generation. While several software tools exist for evaluating the techno-economic potential of integrated renewable energy and combined heat and power (CHP) systems for distributed generation applications, many suffer from poor accuracy in capturing off-design (part load and changes in ambient air temperature and pressure) performance characteristics of microturbines, combustion turbines, or internal combustion engines. Thus, this paper presents a methodology for integrating these off-design characteristics in the mixed-integer linear program within REopt, a hybrid DER screening tool. The economic impact of the CHP off-design performance is observed through several application studies of various hybrid system configurations in different climates. Each study indicates how CHP off-design performance influences optimal sizing and dispatch decisions and therefore overall system economic value. We observe through case studies that modeling without the off-design effects, depending on the CHP prime mover and site, can result in Net Present Value predictions of hybrid systems that can be overoptimistic in frequently hot climates (up to 52 %), too conservative in frequently cold climates (up to 11 %), or unaffected (＋/−1 %) in temperate climates. Cases also highlight several advantages of hybrid systems relative to non-hybrid systems such as total economic value and the systems’ ability to mitigate potentially negative consequences attributed to off-design performance.

Performance analysis and application of a novel combined cooling, heating and power system integrated with multi-energy storage system

The dynamic fluctuations of user energy demand places the combined cooling, heating and power (CCHP) system in a perpetual state of off-design operation, leading to significant performance deterioration. Integrating an energy storage system with the CCHP system is an effective approach to this issue. However, conventional methods often segregate the storage of cooling load, heating load and power of CCHP system, limiting their conversion and resulting in suboptimal utilization and low efficiency. Therefore, this study proposes a novel CCHP system integrated with multi-energy storage system, allowing flexible release cooling load, heating load and power to meet diverse user load profiles. Mathematical modeling, thermodynamic analysis and environmental assessment are conducted. The case study demonstrates that the proposed system surpasses the conventional CCHP system in exergy efficiency ηex, primary energy rate PER, primary energy saving ratio PESR, carbon dioxide emission reduction ratio CDERR and cost saving ratio CSR of the proposed system increase by 3.1 %, 13.6 %, 9.0 %, 6.2 % and 8.4 %, respectively. The proposed system effectively balances user energy demand and energy supplied by the CCHP system, efficient utilization of diverse energies, significantly enhancing off-design performance, and yielding high efficiency, energy saving, and reduced carbon emissions.

Thermal energy storage capacity configuration and energy distribution scheme for a 1000MWe S–CO2 coal-fired power plant to realize high-efficiency full-load adjustability

The flexibility transformation of coal-fired power plants (CFPP) is of significant importance for the new power system primarily based on new energy sources. Coupling thermal energy storage (TES) technology is one effective approach to enhance the load-following capability of CFPPs. In this study, the S–CO2 CFPP coupled with TES technology is taken as the research object. An integrated dynamic energy analysis model, from components to the entire system, is established for variable working conditions. A comprehensive comparison is made among different TES methods, including flue gas TES, CO2 TES and electrical heating TES, in terms of system's minimum output power, thermal efficiency, energy round-trip efficiency and other off-design performance indicators. Furthermore, through hierarchical integrated configuration of the three thermal energy storage methods, efficient load regulation from 0% to 100% is achieved for the S–CO2 CFPP. The results indicate that, to achieve efficient load regulation from 0% to 100% for a 1000 MWe S–CO2 CFPP, the priority configuration for thermal energy storage is CO2 TES, followed by flue gas TES and electrical heating TES, with powers of 285.17 MWth, 342.80 MWth, and 329.95 MWth, respectively. The overall heat storage/release ratio is 3.43:1 and the energy storage round-trip efficiency is 73.58%. Compared to using only electrical heating TES, the addition of 142.34 MWth of TES improves the energy round-trip efficiency by 11 percentage points.

A universal ANN-based approach predicting PCHEs’ off-design performance across various operating conditions of sCO2 RCBCs

This paper proposes a universal approach that employs artificial neural networks (ANN) to predict the off-design performance of printed circuit heat exchangers (PCHEs) using supercritical carbon dioxide (sCO2) fluid. PCHEs are widely studied precoolers and recuperators of sCO2 power cycles, for which predicting their off-design heat transfer performance is challenging due to the fluid’s dramatic non-linear property variations. Due to their narrow valid range and constrained expressing ability, the existing empirical correlations might introduce significant out-of-scope errors that result in diverged simulation results, slow convergence and abnormal quitting. This work addresses the issue by proposing an ANN-based Nusselt number correlation, ANNu, to predict the off-design performance of PCHEs quickly and universally over the vast operating range of sCO2 cycles. Multiple techniques were adopted to promote ANNu’s prediction accuracy and generalization, such as consolidating 494 training data, data-driven input selection, and global optimization for the networks’ architecture and hyperparameters. This paper comprehensively evaluates ANNu’s performance by comparing its predictions with ten empirical correlations over four typical real-world scenarios, where ANNu features an overall MSE of 83.4222 and overall MAPE of 16.285 % that rank the second best and third best among eleven candidates (even overpassing two references), respectively. Moreover, ANNu exhibits good generalization and reliability, featuring MAPEs ranging from 9.89 % to 27.73 % when processing unmet experiment data from sCO2 PCHE applications.

Multi-objective optimization research of open and closed air brayton cycle

Air Brayton cycle obtains the significant advantages of high efficiency, compact structure, easy medium requirement and so on, which is one of the most suitable choices for the mobile nuclear power conversion system. In this paper, system-component combined design method is used to establish the open and closed air Brayton cycle of diverse configurations. Based on performance and compactness targets, the multi-objective optimization is carried out to find the optimal design by nondominated sorting genetic algorithm II and entropy weight method. According to the analysis, the closed intercooling reheating recuperating cycle is the configuration with the best comprehensive performance, with cycle efficiency of 33.58 %, power density of 175.39 kW m−3 and power mass ratio of 68.60 kW t−1. The open simple recuperating cycle is the configuration with the smallest volume and mass, with cycle efficiency of 20.01 %, system volume of 6.56 m3 and system mass of 19.98 t. The closed intercooling recuperating cycle is the most balanced configuration, with cycle efficiency of 31.33 %, volume of 9.06 m3 and system mass of 24.97 t. Based on the optimal results, off-design performance analysis of different environmental conditions is also carried out for the configurations above.

Peer-to-peer energy trading with energy trading consistency in interconnected multi-energy microgrids: A multi-agent deep reinforcement learning approach

Multi-energy microgrid technology is an essential for addressing the diversification of energy demand and local consumption of renewable energy sources. Peer-to-peer energy trading has emerged as a promising paradigm for the design of a decentralized trading framework. Therefore, this paper investigated the external peer-to-peer energy trading problem and internal energy conversion problem of interconnected multi-energy microgrids. The concept of energy trading consistency to avoid unreasonable energy trading behavior is first proposed and an off-design performance model of the energy conversion device is considered to more accurately reflect the operating status of the device. The complex decision-making problem with significantly large high-dimensional data is formulated as a partially observable Markov decision process and solved using the proposed multi-agent deep reinforcement learning approach combining the centralized training decentralized execution framework and soft actor-critic algorithm. Finally, the effectiveness of the proposed method was verified through a case simulation. The simulation results showed that the proposed method can reduce the total cost compared with the rule-based method.

A falling particle receiver thermal model for system-level analysis of solar tower plants

Falling particle receivers are one of the most promising new generation solar tower technologies. They have the advantage of being directly heated, thus relaxing flux limitations associated with conventional receivers, and being able to achieve very high temperatures (>1000 °C) without degradation. The goal of this work is the development of a thermal model able to describe the behaviour of a falling particle receiver under different operating conditions, to provide the value of its thermal efficiency within reasonable computational time so that the model can be applied for optimization of solar tower plants at system-level. The thermal model was developed starting from models described in literature, upgrading them with various features (e.g., 2D/3D discretization, drag force effect, etc.) to describe more in detail the heat transfer phenomena occurring during receiver operation. The obtained model results were verified against CFD showing better agreement than the original model. Furthermore, the thermal model was employed in a case study with the goal of optimizing the receiver size for a given solar field and performing off-design and annual performance analyses. Results showed that the adoption of multiple stages increases performance compared to a free-falling particle receiver both under nominal and off-design conditions, and the higher the number of stages the better is the performance. A free-falling particle receiver showed a yearly thermal efficiency of 72.0 %, while the five stages one achieved 75.3 %. In addition, recirculation was investigated as part load strategy for improving performance of the free-falling receiver, but the benefits in terms of performance were limited.

Effect of the Return-channel Geometric Parameters on the Performance of a Centrifugal Compressor with a High-flow Coefficient

The return-channel of a preceding stage in a multi-stage centrifugal compressor has a significant effect on the aerodynamic performance of the current and subsequent stages. However, due to the relatively complex nature of the return-channel configuration with many geometric parameters, no general design guidance is available in the literature. In this study, numerical methods are used to study the effects of different geometric parameters of a return-channel on the performance of a high-flow-coefficient centrifugal compressor. A multi-objective genetic algorithm is applied to optimize the return-channel. The effects of different geometric parameters on the performance are then studied using a sensitivity analysis method. Calculation results show that the residual vortex intensity at the outlet of the return-channel is affected by the geometric angles of the inlet and outlet of the return-channel blades. The flow uniformity at the stage outlet is primarily affected by the geometric angle of the blade outlet and the number of blades. The overall performance of the compressor stage is primarily affected by the geometric angle of the blade inlet and the lateral inclination angle of the cover plate. Calculation results for a two-stage compressor consisting of the optimized first stage and its following stage show that the outlet flow field of the first stage is more uniform than the original first stage. Additionally, at the design operating condition, the polytropic efficiency and pressure ratio of the entire unit increase by 1.07% and 4.07%, respectively. The polytropic efficiency and pressure ratio for the second stage increase by 2.34% and 3.51%, respectively. The impeller head coefficient increases by 7.33%. The theoretical analysis shows that for high-flow-coefficient centrifugal compressors, reducing the residual vortex intensity of the outlet flow field of the return-channel in a stage can significantly improve the off-design performance of the following stage.

A comprehensive preliminary design methodology and an optimization workflow for single-stage radial-outflow turbines and application for 10 MW sCO2 turbines

Development of efficient turbines for sCO2 power cycles is crucial to increase the efficiency, economic feasibility, and competitiveness of future thermal power plants. Radial-outflow turbines are recently considered as a viable power block option for sCO2 power cycles for several applications. This research aims at presenting a detailed and replicable design procedure for radial-outflow turbines. A detailed one-dimensional design method was first developed and validated, then an optimization design workflow was developed using this one-dimensional design method. Utilizing this workflow, the impact of some key design parameters on turbine performance was studied. It was found that the velocity ratio, specific speed, and flow coefficient have significant impact on turbine performance, the reaction degree has moderate impact, and the diameter ratio has the lowest impact. The criterion of selecting the design variables was given and its applicability to different boundary conditions and constraints has also been illustrated. Furthermore, a test case turbine of 10 MW power scale was designed using the developed method, and 3D CFD simulations were performed to study the on-design and off-design performance of the designed turbine. Results show that high efficiency (above 90.0 %) and overall good off-design performance can be obtained from sCO2 radial-outflow turbines in the 10 MW power scale using the developed design methodology when the design parameters are properly selected. The developed 1D design and optimization method is directly applicable to other working fluids and can be easily extended to design multistage radial-outflow turbines.

Off-design performance evaluation of thermally integrated pumped thermal electricity storage systems with solar energy

Pumped thermal electricity storage that integrates with low-grade heat source (thermally integrated PTES, TI-PTES) have gained widespread attention due to the superior performance compared to traditional PTES systems. In this work, a TI-PTES system integrated with solar energy is constructed. R1233zd(E) is employed as the working fluid in the system. Select solar data from four typical days (Vernal Equinox, Summer Solstice, Autumn Equinox, Winter Solstice) throughout the year in Chuxiong City, Yunnan Province, which has abundant solar resources. Design conditions for the system are determined by a multi-objective optimization approach, and based on this, the off-design performance of both the charge and discharge processes are studied. The off-design models for the main components of the system are established. In the charge process, the weather conditions from 10:00 to 15:00 on a typical day are selected for a 6-hour charge period, and a parameter analysis of the system is conducted under different weather conditions. In the discharge process, the off-design performance of the system under different load levels is analyzed for two operating modes: constant pressure mode and variable pressure mode. The results indicate that in the charge process, the values of the compressor power under off-design conditions (Wcomp,off), the mass flow rates of the heat pump system (mRHP), and thermal energy storage system (mts) of Winter Solstice are the highest from 11:00 to 15:00 compared to the other 3 days. In the discharge process, the power-to-power efficiency (ηPTP) and Levelized Cost of Storage (LCOS) of the Vernal Equinox and Autumn Equinox reach their maximum (74.47 %) and minimum (0.247 $·kWh−1) values at an 80 % load level under variable pressure mode. Under constant pressure mode, the power-to-power efficiency and LCOS of the Vernal Equinox and Autumn Equinox reach their maximum (74.34 %) and minimum (0.232 $·kWh−1) values at 70 % and 40 % load levels. Comparing the off-design performance between the variable pressure mode and constant pressure mode in the discharge process, the variable pressure operation mode is recommended for load levels between 78 % and 85 %, while the constant pressure operation mode is recommended for load levels between 40 % and 78 %, as well as between 85 % and 120 %. The obtained results can serve as a reference for the off-design performance analysis of TI-PTES.

Multi-condition operating characteristics and optimization of a small-scale ORC system

The multi-condition operating characteristics of an organic Rankine cycle (ORC) are crucial to the development of the practical unit. This work developed a steady-state model of a small-scale ORC prototype built and tested in the lab. The influence of heat source/sink parameters, component design, and operation strategies are analyzed. It is found that the optimal output power and thermal efficiency correspond to the similar expander rotating speed but diverse working fluid mass flow rate. The higher mass flow rate is beneficial to the output power whereas deteriorates the thermal efficiency. Heat source temperature and flow rates mainly affect the unit output power while the ambient temperature and humidity influence both the output power and thermal efficiency. The condenser fouling resistance leads to a significant reduction of expander output power and system thermal efficiency. However, the effect of the evaporator fouling resistance could be neglected due to its sufficient redundant area. The long-term climate conditions and operating strategies profoundly impact the unit's off-design performance. The annual constant output power operation can be achieved by adjusting the working fluid mass flow rate. The thermal efficiency of the unit is damaged while pursuing the output power stability in winter and spring.

Extensive design and aerodynamic performance investigation of diffuser augmented wind turbine (DAWT) guided by generalized actuator disc theory

Shrouding a turbine boosts power, lowers cut-in speed, but raises installation costs, and limits adaptability to wind shifts. A compact, wide-angle DAWT with competitive capacity is crucial for practical installations. Small turbines, often in fluctuating wind sites, necessitate thorough off-design performance analysis. A relatively short, wide-angle GOE431 diffuser is optimized by an efficient response surface method. Inverse blade element method, combined with actuator disc DAWT CFD considering wake swirl, shapes 90 cm-diameter rotor blade with minimal iterations. Implications of Generalized Actuator Disc Theory on DAWT design and performance are addressed with three-dimensional CFD for the first time. This approach unveiled substantial room for improving DAWT efficiency and uncovered key factors causing deviations from ideal performance. Tip leakage and diffuser losses constituted 9.5% of overall energy losses, with wake rotation, blade efficiency, and blade drag at 9.2%. Tip-hub losses, finite blade number, rotor-diffuser interaction, suboptimal rotor, and turbulence contributed to 12.1% in three-bladed DAWT, reaching CP,max = 0.746, with tip losses about one-third of bare turbine. Six-bladed DAWT raised CP by 93%, from 0.417 to 0.805, achieving 75% of ideal DAWT. Finite blade number led to reduced attack angles, higher tip losses, and limited flow expansion, contributing significantly to energy losses. As blade number and design tip-speed-ratio increased, blade Reynolds number decreased, suggesting an optimal combination to minimize energy losses. At off-design, a strong connection existed between thrust coefficient, diffuser efficiency, and Cp increase in wide-angle diffuser DAWTs. Maintaining CT near CT,opt (0.786) at high tip-speed-ratio led to significant Cp rise.

Off-design performance analysis of a radial fan using experimental, computational, and artificial intelligence approaches

Radial fans play a critical role as indispensable turbomachines in various industrial sectors. However, the conventional manufacturing process for these fans is often characterized by its resource-intensive and time-consuming nature. Traditionally, computational fluid dynamics (CFD) has been the go-to method for predicting and analyzing the performance of radial fans at different geometrical and operational conditions. Yet, in recent years, the rapid advancements in machine learning (ML) and deep learning (DL) techniques, particularly the rise of artificial neural networks (ANNs), have propelled significant progress in the field of predicting and optimizing the performance of radial fans. The present study aims to analyze the performance of a radial fan through a comprehensive experimental investigation and a meticulous three-dimensional numerical simulation. Subsequently, in order to predict the off-design performance of the fan, an extensive set of numerical simulations is conducted at various volumetric flow rates and rotational speeds. These simulations are used to analyze the fan performance and identify the most efficient operating condition. Moreover, the simulations serve as inputs for a finely-tuned ANN architecture. The predictive accuracy of the ANN model for both interpolation and extrapolation cases is then compared against two alternative techniques, namely support vector machine (SVM) and random forest (RF). The results explicitly highlight the superiority of the ANN model in terms of its predictive accuracy, thereby solidifying its position as the most reliable method for predicting the performance of radial fans.