Organic Rankine Cycle Waste Heat Research Articles

Energy, Exergy and Environmental Analysis of ORC Waste Heat Recovery from Container Ship Exhaust Gases Based on Voyage Cycle

Recovering the waste heat of a marine main engine (M/E) to generate electricity was an environmental way to minimize the carbon dioxide emissions for ships, especially with organic Rankine cycle (ORC) technology. The M/E had variable loads and operating times during voyage cycle, which directly affected the ORC thermodynamic potential. In this paper, a voyage cycle-based waste heat utilization from the M/E was introduced to provide reliable evaluation for proposing and designing ORC. The effect of various M/E loads and operating times on ORC performance among three dry-type substances was analyzed. The environmental impact was presented based on the data from one voyage cycle navigation of objective container ship. The results showed that Cyclohexane was capable of net power while Benzene was more suitable for thermal efficiency. The evaporator and condenser were the main irreversible components of the ORC system and required further optimization. Taking the operational profile into consideration, the evaporation pressures were 922–1248 kPa (Cyclohexane), 932–1235 kPa (Benzene) and 592–769 kPa (Toluene), respectively. During the voyage cycle, the carbon dioxide emissions were 99.68 tons (Cyclohexane), 96.32 tons (Benzene) and 60.99 tons (Toluene), respectively. This study provided certain reference for the design and investigation of ORC application to further improve the energy efficiency for container ship.

On mixtures as working fluids of air-cooled ORC bottoming power plants of gas turbines

The use of mixtures as working fluids of organic Rankine cycle (ORC) waste heat recovery (WHR) power plants has been proposed in the past to improve the matching between the temperature profile of the hot and the cold streams of condensers and evaporators, thus to possibly increase the energy conversion efficiency of the system. The goal of this study is to assess the benefits in terms of efficiency, environmental (GWP) and operational safety (flammability) that can be obtained by selecting optimal binary mixtures as working fluids of air-cooled ORC bottoming power plants of medium-capacity industrial gas turbines. Furthermore, two thermodynamic cycle configurations are analyzed, namely the simple recuperated cycle and the so-called split-cycle configurations. The benchmark case is a combined cycle power plant formed by an industrial gas turbine and an air-cooled recuperated ORC power unit with cyclopentane as the working fluid. The results of this study indicate that binary mixtures provide the designer with a wider choice of optimal working fluids, however, in the case of the recuperated-cycle configuration, no improvement in terms of combined cycle efficiency over the benchmark case can be achieved. The split-cycle configuration leads to an increase of combined cycle efficiency of the order of 1.5%, both in case of pure and blended working fluids. Furthermore, for this cycle configuration the use of Novec 649 as working fluid is advantageous because it is environmentally and operationally safe, and it does not involve any penalty in terms of combined cycle efficiency if compared to the benchmark case. Additionally, the use of this fluid would lead to a more compact turbine, as the corresponding thermodynamic cycle would determine a turbine volume flow ratio that is half of the value of the benchmark case and a specific enthalpy difference over the expansion that is one fifth.

Data-driven identification and fast model predictive control of the ORC waste heat recovery system by using Koopman operator

Organic Rankine Cycle (ORC) has received its wide application in low-grade waste heat recovery (WHR) technology for its significant performance and easy access to its components. Given the highly fluctuating nature of the waste heat source, Model Predictive Control (MPC) is usually utilized to realize the reasonable adjustment of ORC based WHR systems and has performed satisfactorily. In order to apply MPC, a relatively precise model should be built up for the ORC system which ensures acceptable control performance. However, popular modeling methods based on the mechanism of the ORC establish the high-dimensional nonlinear model and suffer from computational costs when utilizing complicated nonlinear MPC. Even if linear MPC is employed for the purpose of reducing the calculation amount, the model obtained by linearization near the operating points usually makes it valid locally, thus bringing about suboptimal or unstable control performance. To address this problem, the Koopman operator is introduced for the data-driven identification and MPC of the ORC system. Koopman identification constructs a linear model in the lifted space in which the ORC system possesses nearly global linear evolution and enables the prediction of the nonlinear ORC dynamics from measurement data. In view of the possible online calculation burden increment caused by the rise of variable dimension through lifting action, the fast Koopman MPC (FKMPC) algorithm is thus proposed based on the invariance of the Hessian matrix of the optimization problem to shorten the computing time. Simulations on setpoint tracking and disturbance rejection are performed to verify the established model accuracy and the control effectiveness of the proposed strategy in comparison with other approaches.

Information theory-based dynamic feature capture and global multi-objective optimization approach for organic Rankine cycle (ORC) considering road environment

Efficient capture and global optimization of organic Rankine cycle (ORC) operating features in road environment is the key to obtain actual waste heat recovery potential. The complexity of time-varying characteristics intensifies the nonlinear coupling relationship between ORC performance and parameters. This paper first designs and builds an ORC experimental system for recovering waste heat from internal combustion engine (ICE). The experimental system includes ICE and its measurement subsystem, ORC subsystem, expander lubrication subsystem, cooling subsystem, and ORC measurement subsystem. R245fa is used as working fluid; The expander adopts a specially designed single screw expander. The performance of ORC waste heat recovery is tested by adjusting the operating conditions of the ICE, expander, pump, and valve opening. The temperature range of waste heat is 627–686 K. Subsequently, a dynamic feature capture and global multi-objective optimization approach for ORC is proposed. The results show that the precision of dynamic feature capture can be improved at least 41.78% with the introduction of information theory in complex environment. Frequent fluctuation of vehicle speed is not conducive to the improvement of evaporator inlet temperature at working fluid side. As the speed of the vehicle is greatly reduced, the evaporator inlet temperature drops sharply. The frequent fluctuation of speed will intensify the nonlinear correlation between operating parameters and system performance and make the system performance more dependent on the coupling correlation between operating parameters. The approach proposed in this paper can provide a new idea for efficient capture of dynamic characteristics and global multi-objective optimization of ORC in road environment.

Alleviating the thermal aging of three-way catalyst applied to natural gas engine based on organic Rankine cycle

Natural gas (NG) is a possible pathway for developing countries to reduce transportation carbon footprint. However, its high exhaust temperature decreases the thermal efficiency of NG engines and accelerates the thermal aging of three-way catalyst (TWC). This study proposes to place an organic Rankine cycle waste heat recovery (ORC-WHR) system between an NG engine and its TWC to recover exhaust energy and extend the useful life of TWC. The feasibility of this design concept is confirmed by the simulation results of an experimentally validated 1D NG engine model combined with an ORC-WHR model at three TWC working temperatures representing field-average, modern, and future TWC technologies. Results show that the decrease in the outlet temperature of the ORC-WHR system benefits the availability of exhaust energy, improving the overall efficiency of the engine plus ORC-WHR system and extending the useful life of the TWC. Hence, more advanced catalyst technologies, which can achieve high conversion efficiency at lower temperatures, are deemed more favorable for ORC-WHR coupling. The cost-effectiveness of such combinations is better due to more exhaust energy recovered and less noble metal catalyst needed to be added.

Low carbon economic dispatch of integrated energy system considering extended electric heating demand response

Retrofitting coal-fired units with carbon capture plants is an important means to achieve low-carbon improvements in integrated energy systems (IES). However, the lack of flexible resources restricts the development of carbon capture power plants, and the uncertainty of IES affects the reliability of system. With this background, this study proposes a low-carbon economic dispatch strategy considering extended electric heating demand response. Firstly, the organic Rankine cycle waste heat power generation is introduced to decouple the “power determined by heat” mode of combined heat and power. Secondly, incentive-based electric load demand response, as well as comfort fuzziness-based heat load demand response are considered. Subsequently, a data-driven distributionally robust optimization model is developed to solve the source-load uncertainty problem, where the confidence set of the uncertainty probability distribution is constrained by both 1-norm and ∞-norm constraints. The column and constraint generation (C&CG) algorithm is used to solve the model and obtain the operating output configuration. Finally, the test system verifies the effectiveness of the proposed method.

Energy, Exergy, and Economic (3E) Analysis of Transcritical Carbon Dioxide Refrigeration System Based on ORC System

This paper used the energy, exergy, and economic analysis of a carbon dioxide (CO2) transcritical two-stage compression system based on organic Rankine cycle (ORC) waste heat recovery technology. When the intermediate pressure and high-pressure compressor outlet pressure were changed, respectively, this study simulated the change in system energy efficiency by adding the ORC for waste heat recovery, calculated the ratio of exergy loss of each component, and performed an economic analysis of the coupled system. The results show that adding waste heat recovery can effectively increase the energy efficiency of the system, and among all components, the heat exchanger had the largest exergy loss, while the evaporator had the highest capital investment and maintenance costs.

Effect of tooth head modification on the performance of a scroll expander for ORC waste heat recovery system

In order to cope with the energy crisis and improve energy efficiency, the use of organic Rankine cycle (ORC) to convert low-quality heat energy into electricity and use it is an effective method. Based on the ORC waste heat recovery system of vehicle engine, this paper explores the flow heat transfer and deformation law of the core component scroll expander under different tooth head corrections. Deformation has a significant impact on the performance of the expander. In this study, several flow-thermal-solid coupling models based on double circular arc correction and double circular arc plus straight-line correction are established. The effects of tooth head correction on the strength and stiffness of tooth head, flow field distribution of suction chamber and deformation characteristics of tooth head are studied. Finally, the deformation law of scroll tooth head with different correction angles was discussed. The results show that the EA-SAL correction makes the wall curvature of the tooth head change greatly, and the flow field in the center of the tooth head becomes more uneven and complicated. The tooth head area under EA-SAL modification is larger, and the tooth head strength and stiffness are improved by about 6%. Within a certain angle range, the tooth head deformation after EA-SAL correction is slightly larger than that after PMP correction, but the difference between them decreases and even reverses with the increase of angle. The maximum deformation of the EA-SAL modified tooth head under internal pressure is about 20% smaller than that of PMP. With a given initial correction angle ∅, the deformation of the corrected tooth head caused by a pressure or temperature load reduces when the correction angle γ is reduced, Therefore, reducing the correction angle properly is helpful to reduce the deformation of the tooth head.

Evaluating the thermodynamic potential for carbon capture from internal combustion engines

This work explores the potential for use of carbon dioxide separation processes, colloquially known as carbon capture, to accelerate decarbonization of the transport sector. Thermal swing absorption processes using an aqueous, CO2-selective solvent, provide an efficient means of separating CO2 from other exhaust gas constituents. Amine-based solvents–well known from acid gas treating and other post-combustion carbon capture processes–are highly selective, have a fast rate of reaction with CO2, and can use waste heat to drive the separation process. This work demonstrates how amine-based processes can be deployed for carbon removal from a generic exhaust gas source produced by an internal combustion engine (ICE) using waste heat in the exhaust. It includes an estimation of the exhaust enthalpy-limited capture rate for various sources considering the capture system performance, the CO2 concentration, and the exhaust temperature.CO2 capture rates of around 25–80% are shown to be thermodynamically feasible for various ICE applications using waste exhaust heat for solvent regeneration. Rates of around 15–50% are attainable without providing additional energy, if exhaust heat is also used to power the capture system pump and compressor. Although a higher exhaust CO2 concentration reduces the specific energy requirements of the separation process, the total energy required for a given capture rate increases due to the greater amount of CO2 removed. Thus, maximum capture rates are highest for applications with high exhaust temperature and low CO2 concentration (such as diesel generators), and lowest for applications with very low exhaust temperature such as ships. This analysis also shows that the potential for CO2 avoidance using carbon capture systems far exceeds that of organic rankine cycle waste heat recovery systems. Overall, expanding the use of carbon capture to ICE applications can provide an efficient means of utilizing waste exhaust heat while providing significant reductions in the energy industry's scope 3 greenhouse gas emissions.

Low-Carbon Economic Dispatching of Multi-Energy Virtual Power Plant with Carbon Capture Unit Considering Uncertainty and Carbon Market

Multi-energy virtual power plants (MEVPPs) effectively realize multi-energy coupling. Low-carbon transformation of coal-fired units at the source side and consideration of demand response resources at the load side are important ways to achieve carbon peak and carbon neutralization. Based on this, this paper proposes a low-carbon economic dispatch model for the MEVPP system considering source-load coordination with comprehensive demand response. Combined with the characteristics of organic Rankine cycle (ORC) waste heat power generation and comprehensive demand response energy to increase the flexibility on both sides of the source and load, the problem of insufficient carbon capture during the peak load period in the process of low-carbon transformation of thermal power units has been improved. First, the ORC waste heat recovery device is introduced into the MEVPP system to decouple the cogeneration unit’s “heat-based electricity” constraint, which improves the flexibility of the unit’s power output. Secondly, we consider the synergistic effect of the comprehensive demand response and ORC waste heat recovery device and analyze the source-load coordination low-carbon dispatch mechanism. Finally, an example simulation is carried out in a typical system. The simulation example shows that this method effectively improves the carbon capture level of carbon capture power plants, takes into account the economy and low carbon of the system, and can provide a reference for the low-carbon economic dispatch of the MEVPP system.

Multi-objective optimization and algorithm improvement on thermal coupling of SOFC-GT-ORC integrated system

Optimizing thermal coupling of an integrated system and improving its energy cascade utilization (ECU) level are important ways to improve system performance. An integrated power generation system consisting of an anode recirculation internal reforming solid oxide fuel cell (ARIR-SOFC), a gas turbine (GT), an organic Rankine cycle (ORC) waste heat recovery system and a liquefied natural gas (LNG) supply system is established. Additionally, heat exchange network (HEN) subsystem formed by heat exchange streams is specially considered to further improve ECU level. Optimization model is proposed where HEN scheme is optimized simultaneously with operating parameters and working fluids of ORC. Because of the complexity of model, it is key to focus on the solution strategy. An adaptive improved multi-objective particle swarm optimization (IMOPSO) algorithm is established to improve diversity and accuracy of solutions. Finally, a case is solved and results show that HEN scheme plays an important role in system performance.

A review of the research status of scroll expander

In order to solve the problem of energy crisis and take the road of sustainable development, the development of renewable energy and recycling of low-grade waste heat have attracted more and more attention. As a new type of volumetric energy conversion device, scroll expander is wi dely used in Organic Rankine Cycle (ORC) waste heat recovery, because of its advantages such as small size and so on. Scroll profile is one of the main factors affecting scroll expander performance. Compared with the traditional constant section scroll profile with same suction volume, volume ratio and shell size, the new type of variable section scroll profile could reduce scroll tooth height, better mechanical properties and improve efficiency, therefore making it more suitable for working under complex operating conditions. In order to reduce the head invasion rate, airflow friction factor, the power loss at the air inlet, and improve the pneumatic power conversion efficiency, a new head correction method is proposed. Although R123, R134 and R245 are the most commonly used working medium in scroll fluid machinery, the selection of working medium in scroll expander is still a key problem. The overall performance of the scroll expander can be improved by designing different inlet shapes and positions or double-symmetrical exhaust ports. The radial leakage caused by axial clearance of scroll expander can be improved by developing new scroll profile to reduce the length of radial leakage line and optimizing the design of scroll top sealing mechanism. The tangential leakage caused by radial clearance can be improved by enhancing the manufacturing precision and installation accuracy of scroll plate and designing the radial variable mechanism. At present, fewer research has been carried out on the leakage of scroll expander. Therefore reducing the leakage loss to improve the performance of scroll expander is of great significance in the future research.

A novel analysis framework for the organic Rankine cycle waste heat recovery system: From the viewpoint of turbine design

The turbine is crucial equipment in the ORC system, not only has a significant influence on system efficiency but also dominates the equipment investment costs. In this paper, a novel design framework for the radial inflow turbine is proposed, aiming to promote the standardization or serialization design of the ORC turbine, and the innovativeness of combining it into the system analysis is illustrated. The reliability of the design framework is examined by comparing with CFD simulation, nearly all of the deviations within ±5%. Better prediction accuracy can be achieved when R is close to 0.6, and the suitable value of α4 is 65° to realize a better turbine performance. Some other results reveal that the Ẇout has a positive proportional to r4 and Ma4, but ηts is not sensitive to them. Besides from the viewpoint of thermodynamics, the ηts of the turbine is hardly affected by the type of working fluid. For the case study, the turbine with R236ea has achieved the best matching degree with the heat source, which improves near 10% of the total output power for the MGT-ORC system. This paper gives new ideas for ORC turbine design and system analysis which contributes to promoting its application.

Direct integration of an organic Rankine cycle into an internal combustion engine cooling system for comprehensive and simplified waste heat recovery

Cogeneration systems based on internal combustion engines (ICE) provide decent efficiency and flexibility. In order to further improve the efficiency, organic Rankine cycle (ORC) can be used to convert high temperature (waste) heat from flue gas to electricity. There is a large amount of heat in jacket cooling at lower temperatures for which there is often no demand so it has to be rejected into the ambient. Previous systems trying to utilise this heat in the ORC cycle end up as too complex and expensive. This study introduces an innovative jacket cooling method. In the cooling system of an ICE, instead of typical water or oil-based heat transfer fluids, the working fluid of an ORC is used as the engine coolant, recovering the low-potential heat. Preheated organic fluid is then directly used in the bottoming ORC with further heat input from the flue gas. This concept allows utilising both low and high potential heat from the cooling of the ICE and from the flue gas recovery, while omitting the intermediate heat-transfer circuits commonly found in ORC waste heat recovery applications. Presented thermodynamic analysis shows a strong dependency of the ORC utilisation efficiency on cooling fluid allowed pressure in the ICE jacket and on the heat flow ratio between the coolant and the flue gas of the ICE. A baseline study with a specific 83 kWe ICE with the novel configuration provides an improvement of nearly 10 kW in comparison with 7 kW of an ORC utilising only flue gas. More general parametric analysis has shown the potential of the ORC power output improvement by more than 60% for specific ICE types and higher pressures and temperatures in the engine cooling circuit. In a cogeneration regime, these benefits in electrical power output come at the cost of a very slight decrease in overall efficiency.

Organic Rankine Cycle (ORC) as waste heat recovery system for micro-cogeneration: A preliminary study

Although the energy consumption pattern has been optimized, the main problem facing by energy revolution is the low conversion efficiency of renewable energy and waste heat. Among the utilization technologies of these waste heat, organic Rankine cycle (ORC), which has characteristics of simple structure and high efficiency is chosen as the potential candidate to overcome this situation. However, ORC is facing several limitations including having low turbine performance leading to low power production. Additionally, the design of ORC and the heat recovery system should be improved to reduce the investment cost. One of the ways to increase the performance of this ORC is to design ORC waste heat recovery system for cogeneration. Thus, this study will be focused on to identify the effect of different heat exchanger positions to the ORC thermal performance and to investigate the effect of integrating ORC for cogeneration. In order to achieve this, identification of the suitable heat exchanger for ORC will be performed by modelling and simulation to predict the effect of the new design to the ORC thermal performance. Then, the improved novel ORC design will be integrated to a cogeneration system to simulate the power produced by the combined system.

A Q-learning based transient power optimization method for organic Rankine cycle waste heat recovery system in heavy duty diesel engine applications

In recent years, the organic Rankine cycle waste heat recovery (ORC-WHR) technology gains popularity in heavy-duty diesel engine applications. Drastic fluctuations of the waste heat caused by variable daily operation of mobile heavy-duty trucks bring an extreme transient power optimization challenge to ORC-WHR systems. Existing power optimization methods either neglect transient behavior of the Rankine cycle system or compromise model accuracy for computation efficiency. Different from literature, this study first time proposes a model-free reinforcement learning method to achieve online transient power optimization for the ORC-WHR system and explains the benefits of learning method in this application. A tabular Q-learning is formulated to optimize the net power on an experimentally validated ORC-WHR system. Q-learning is explained in detail using states, action, and policy information. To quantify the power optimization of the proposed method, Proper-Integral-Derivative method, state-of-art offline and online Dynamic Programming methods are implemented. The results showed that Q-learning generated 22% more cumulative energy than the energy Proper-Integral-Derivative method generated. Furthermore, Q-learning produces 96.6% of cumulative energy that the offline Dynamic Programming generates over a transient engine condition, while it requires less computation cost and is executed online. Additionally, the Q-learning produces 0.5% more cumulative energy than the machine learning-based online Dynamic Programming results and exhibits better vapor temperature robustness than the online Dynamic Programming method (4 °C-28 °C superheat by Q-learning vs. 5 °C-94 °C superheat by online Dynamic Programming). Given the excellent power production performance, low computation cost requirement and high robustness, the proposed Q-learning method has the potential to improve the power production of the ORC-WHR system with different configurations.

Control of Organic Rankine Cycle, a neuro-fuzzy approach

Undesirable emissions in internal combustion engines are of major concern due to their negative effect on the human health and global warming. Implementing an organic Rankine cycle (ORC) in mobile applications can help to mitigate their negative effect by transferring some of their wasted heat into useful electrical or mechanical energy. Considering the stringent regulations in automobile industry ensuring the safety of equipment before implementing them on the vehicles is vital. In this study, a novel control approach is proposed to ensure the safe operation of Organic Rankine Cycle (ORC) waste heat recovery (WHR) system and stabilize its work output when subjected to transient heat sources in a range of waste heat from heavy-duty diesel engines. The control strategy comprises a neuro-fuzzy controller based on the inverse dynamics of the ORC system to control the superheating at the evaporator outlet by adjusting the pump speed and a PI controller to maintain the expander work output by regulating the mass flow rate at the expander inlet. The performance of the control strategy is investigated with respect to set-point tracking and its robustness is tested in the presence of noises. The simulation results indicate an enhancement in the controller performance by combination of feedforward and feedback controllers based on neuro-fuzzy technologies. The proposed control scheme not only can obtain satisfactory transient response under various loading conditions, but also can achieve desirable disturbance rejection performance.

Modeling of an Organic Rankine Cycle Waste Heat Recovery system for automotive engine applications

The remarkable investments made by manufacturers over the last few decades have contributed to improving the performance of internal combustion engines in every aspect: lower polluting emissions, greater specific power and thermal efficiency. Despite this, on an average, about 40% of the thermal power theoretically available from the combustion of the fuel is still stored in the exhaust gases and therefore dispersed in the environment. In this work the modeling and validation of a waste heat recovery (WHR) plant will be described, combining the engine with a low temperature Organic Rankine Cycle (ORC) system, in order to investigate the feasibility of this system on board of a vehicle, analyzing the quantity of thermal power recovered and made available in the form of electrical power. The ORC plant is modeled using a 0D/1D thermo-fluid dynamic approach. Starting from experimental tests, a map-based model for the piston pump and the scroll expander has been developed. The model has been validated through the use of a vector optimization technique, exploiting a genetic algorithm (MOGA). Subsequently, this system has been coupled to a spark ignition engine for automotive applications, adapting its speed range to comply with the ORC experimental tests. To have an accurate control over the expander inlet temperature, a bypass circuit and two throttles actuated by a PI controller have been implemented. The simulations were performed by considering 18 engine points at maximum load and different rpm. An average thermal efficiency increase of the system of 2.6% was obtained by introducing the recovery plant, and wide improvement chance can be foreseen in the case of ORC full-power use.

Bioethanol produced from regenerative wooden resource to operate an organic Rankine cycle-waste heat recovery system in case of a tractor propulsion Diesel engine: preliminary simulation results

Bioethanol has become by nowadays a common-used organic agent by thermal installations in direct modes, like dual or single alternative fuel for classic engines, or in indirect modes, as primary source in fuel cells, or operating thermal energy recovery systems, which is the subject of the present work. Among all the other well-known industrial obtaining methods, avoiding higher costs and improving process efficiency, the enzymatic fermentation of the saccharide components coming from wooden biomass ensures a more profitable way to produce bioethanol, with the requested properties in order to operate as a thermal agent in an Organic Rankine Cycle (ORC) installation. The aim of using this system is to increase the efficiency of a tractor-turbocharged Diesel engine by its waste heat recovery (WHR).

Prediction and optimization of isentropic efficiency of vortex pump under full operating conditions in Organic Rankine Cycle waste heat recovery system based on deep learning and intelligent algorithm

The isentropic efficiency of vortex pump in Organic Rankine Cycle (ORC) system has an important influence on the performance of the system. In this paper, vortex pump experimental data and deep learning are combined to construct an experimental data-driven isentropic efficiency prediction model of vortex pump under full operating conditions. The activation function and the number of hidden layer nodes in the model are filtered by nested screening technique. Through bilinear interpolation algorithm, the influence of vortex pump operation parameters on the isentropic efficiency is analyzed. In addition, the optimization boundary is selected in the four-dimensional space. Finally, the deep learning prediction model is combined with Linear Decreasing Inertia Weight Particle Swarm Optimization (LDIWPSO) to predict and optimize the maximum isentropic efficiency of vortex pump under full operating conditions. Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE) and Coefficient of Determination (R-square) are combined to evaluate the prediction accuracy of the model. The prediction and optimization results show that the maximum isentropic efficiency of vortex pump can reach 22.89%. The combination of deep learning and LDIWPSO can predict and optimize the maximum isentropic efficiency for vortex pump with high precision. It also provides a reference for the maximum value of vortex pump isentropic efficiency in theoretical analysis and numerical simulation.