Non-dominated Sorting Genetic Algorithm Research Articles

Multiobjective Optimisation of Flotation Variables Using Controlled-NSGA-II and Paretosearch

Finding the optimum operating points for the maximisation of flotation recovery and concentrate grade can be a very difficult task, owing to the inverse relationship that exists between these two key performance indicators. For this reason, techniques that can accurately find the trade-off are critical for flotation process optimisation. This work extracted well-assessed Gaussian process predictive functions as objective functions for a comparative multiobjective optimisation study using the paretosearch algorithm (PA) and the controlled elitist non-dominated sorting genetic algorithm (controlled-NSGA-II). The main aim was the concomitant maximisation of the copper recovery and the concentrate grade. Comparison of the two applied techniques revealed that the PA discovered the best set of the pareto-optimal solution for both the recovery (93.4%) and concentrate-grade (17.4 wt.%) maximisation.

Optimization of a wideband discrete Raman amplifier in a P2O5-doped optical fiber using multi-objective grey wolf algorithm

This paper demonstrates the use of the multi-objective grey wolf algorithm to optimize a discrete Raman amplifier (DRA) in a P2O5-doped optical fiber. Specifically, the multi-objective grey wolf algorithm is combined with the DRA to carry out a process that seeks to maximize the gain and minimize the ripple. The P2O5-doped optical fiber employed in this study has a Raman gain coefficient spectrum with multiple peaks with different frequency shifts. This allows them to be combined in more complex ways than optical fibers with a single peak in the Raman gain spectrum. Consequently, the gain curve produced with this fiber has the potential to be more adjustable even when fewer pumps are used. Thus, this paper explores this fact to perform, to the best of our knowledge, the first specialized optimization process reported in the scientific literature of a wideband discrete Raman amplifier in a P2O5-doped optical fiber. With a different gain profile of this fiber compared to those of traditional standard optical fibers, it was possible to design a wideband DRA, going from 1530 nm to 1675 nm, covering C+L+U bands, maintaining a ripple of up to 8 dB with a net gain of 14 dB using only 3 pumps. Moreover, this work demonstrates for the first time, through a comparative analysis, that the multi-objective grey wolf algorithm performs better than the standard and well-known non-dominated sorting genetic optimization algorithm to optimize a DRA in a P2O5-doped optical fiber. The proposed DRA is a feasible, low-cost, and simple alternative for building fiber amplifiers for future high-bandwidth and wideband wavelength division multiplexing (WDM) communication systems, network infrastructures such as data centers, undersea cables, 5G and beyond, and cutting-edge research applications.

Enhancing pressure ulcer prevention through optimized design of a multi-cellular foam mattress

Sustained mechanical loading on skeletal muscle tissue can lead to degeneration and cell damage over time, resulting in the development of pressure ulcers, particularly in hospital mattresses or for wheelchair-bound users. The primary risk factors for this damage are tissue ischemia caused by pressure in the contact area and tissue compressive strain. In this study, a multi-cell, multi-material foam mattress for the upper comfort layer was developed, with the aim of simultaneously minimizing soft tissue compressive strain and maximum surface pressure on the human buttocks zone. The levels of these factors were estimated using the finite element method (FEM). A multi-objective optimization (MOO) approach was employed, coupling the non-dominated sorting genetic algorithm (NSGA-II) with FEM. This algorithm helped determine the required compressive strength and the optimal cell configurations to achieve the desired outcomes. The majority of the optimal solutions exhibited contact pressures (Cpresss) below the recommended threshold to avoid local tissue ischemia. The optimized cellular material configurations resulted in soft tissue compressive strain of 12% and Cpress of 3.4 kPa, indicating longer safety times for supine support on the foam mattress without the need for repositioning. The optimization process utilized 5 softer foam materials out of the 9 firmness levels tested to achieve these results. The proposed multi-cell, multi-material foam mattress model shows promise for the prevention of pressure sores, as suggested by the optimization findings.

Optimal replicator dynamic controller for semi active control of long span cable stayed bridge with considering special variability of seismic excitations

Cable-stayed bridges are lifeline infrastructures. However, due to their design and structural characteristics, they are sensitive to the vibrations. Thus, vibration control in these structures is essential. Semi-active control systems have gained significant attention due to their high performance and adaptability. However, the implementation of these systems has always faced serious challenges particularly when it comes to developing appropriate control algorithms because semi active devices have complex and non-linear characteristics. Inspired by evolutionary game theory, the author utilizes the replicator dynamic controller concept to optimize the performance of MR dampers to improve the vibration reduction of cable-stayed bridges. Two key parameters in the proposed control methodologies using replicator dynamics are the total population (total available resources or the sum of actuator forces) and the growth rate. Instead of using the sensitivity analysis that has been done in previous studies for vibration reduction of highway bridges using a replicator controller, the author used an evolutionary algorithm named the nondominated sorting genetic algorithm (NSGA-II) to create an optimal replicator dynamic controller for more effective vibration reduction. The proposed methodology is evaluated through its numerical application to a second-generation benchmark example based on the Bill Emerson Memorial Bridge, which considers a more realistic behavior of the cable-stayed bridge by accounting for multiple support excitations. The study indicates that the optimal replicator dynamic controller improves the vibration reduction performance of MR dampers. Specifically, deck displacement is reduced by 46 % compared to passive control system and shear forces at the tower base are reduced by 33 % compared to active control systems for the El Centro earthquake. The results indicate that the proposed Replicator Dynamic Controller optimized through NSGA-II provides a robust and effective solution for improving seismic resilience of cable-stayed bridges.

Investigation of EDM erosion behavior for Ni-based superalloy using experimental and machine learning approach

The rapid growth of the global population and the consequent increase in manufacturing activities have heightened the need for sustainable practices to protect the environment. Non-traditional manufacturing processes, such as electric discharge machining (EDM), often use oil-based dielectric fluids like kerosene, which emit toxic fumes and aerosols, contributing to environmental pollution. To address this, the reuse of waste cooking oil (WCO) as a dielectric fluid in EDM presents a promising solution. This method not only tackles the issue of waste oil disposal but also supports the circular economy by repurposing waste materials. EDM, frequently criticized for its low cutting rates, can be enhanced by using nitrogen assisted modified Cu electrodes (cryogenically treated (CT)). This study focused on machining the difficult-to-cut nickel-based superalloy, IN718 by incorporating Sillimanite nano-powder with Span-60 (S-60). The erosion performance characteristics such as material removal rate (MRR), electrode wear rate (EWR), and accuracy index (AI) were evaluated. An artificial neural network (ANN) was employed to predict and correlate experimental and predicted values. Significant improvements were achieved using the non-dominated sorting genetic algorithm (NSGA-II) in the confirmation investigations. With a non-treated (NT) Cu electrode, the confirmatory experiments showed a 79.81 % increase in MRR, an 18.99 % decrease in EWR, and a 0.89 % improvement in AI. For the CT Cu electrode, MRR increased by 85.48 %, EWR decreased by 32.90 %, and AI improved by 0.53 % when using optimal processing parameters. This study demonstrates the potential for significant environmental and performance benefits in EDM by reusing WCO and optimizing electrode treatments.

Multi-criteria study and machine learning optimization of a novel heat integration for combined electricity, heat, and hydrogen production: Application of biogas-fueled S-Graz plant and biogas steam reforming

The current research introduces an environmentally friendly heat design method by employing biogas fuel, aiming to yield electricity, hydrogen, and heating load simultaneously. The proposed arrangement consists of a biogas-powered S-Graz plant and a biogas steam reforming cycle. Although methane-fueled S-Graz plants for multigeneration purposes have been studied in previous studies, research on employing biogas fuel to launch a S-Graz plant and integrating a biogas steam reforming cycle with such a plant has yet to be examined. The model is simulated using the engineering equation solver software, and the study includes thermodynamic, exergoeconomic, and sustainability assessments to show the potential of the suggested configuration. By conducting a sensitivity study, a machine learning optimization method within MATLAB is implemented to exhibit the final optimal solution for the proposed arrangement. This optimization uses artificial neural networks and a non-dominated sorting genetic algorithm-II algorithm in a triple-objective framework based on energy efficiency, sustainability index, and products’ specific cost. The optimization demonstrates that the mentioned objectives reach optimal values of 58.26 %, 4.56, and 15.56 $/GJ, respectively. Also, the optimal net output power and hydrogen production rate equal 5746 kW and 1.45 m3/s, respectively. Besides, the process determines the optimal exergy efficiency, total net present value, and payback period as 52.70 %, 50.3 M$, and 8.96 years, respectively. The total investment cost rate for this system also is found to be 219.8 $/h.

Design and optimization of annular gap in a nozzle for dyeing machines

The annular nozzle is an important part of the dyeing machine as its impact and traction performance directly affect the quality and efficiency of dyeing. The annular gap forms the core of the nozzle. In this paper, the performance differences between six nozzles with different annular gap shapes were analyzed under various conditions using numerical simulation. The results indicate that the performance of the cone straight nozzle is more stable than other nozzle shapes under various conditions. To further enhance the performance of the nozzle, a multi-objective optimization of the cone straight nozzle structure was performed using a backpropagation neural network and a non-dominated sorting genetic algorithm, thereby obtaining the optimal combination of structural parameters. Finally, the optimization results were verified via experiments and numerical simulations. The results show that the pulling force of the optimized cone straight nozzle is more than 10% higher than that before optimization.

Responding to low-carbon shipping via a novel BOG-ORC-CCS system onboard LNG carrier: 4E analyses and optimization

As the international LNG trade market is booming, the LNG carrier fleet has expanded year after year. How to reduce energy consumption in boil-off gas (BOG) re-liquefaction process and CO2 generated during transportation has become a hot topic. This paper obtains ideas from the LNG cold energy contained in LNG carriers, and proposes a novel BOG-ORC-CCS system for direct BOG re-liquefaction, Organic Rankine cycle (ORC) and carbon capture and storage (CCS). The BOG-ORC-CCS system recycles waste heat from the ship while realizing the LNG cold energy gradient utilization. The reference ship (Q-Flex) is specified under the framework of Energy Efficiency Design Index (EEDI) phase Ⅲ requirement and the BOG-ORC-CCS system is simulated by Aspen HYSYS software. A comprehensive evaluation of the system performance is carried out under the guidance of energy, exergy, economic and environment (4E) modeling. The results of the 4E analyses show that the proposed BOG-ORC-CCS system has the advantage of low energy consumption and good economic performance. Finally, a multi-objective optimization of the system performance in 4E aspects: system energy and exergy efficiency (ηen,sys×ηex,sys), payback period (PBP) and primary energy saved (PES) are carried out by the third-generation non-dominated sorting genetic algorithm (NSGA-Ⅲ). As a result, the optimal solutions are as follows: ηen,sys is 50.91%, ηex,sys is 54.00%, PBP is 1.55 years and PES is 1.32 MWh, while Load of 75%, TL5 is −136.01 °C, pB5 is 1.82 MPa and ScrL2 is 99.88%. Additionally, SEC is 0.20 kWh/kg, which is much lower than that of conventional indirect re-liquefaction. This demonstrates the feasibility of the BOG-ORC-CCS system on LNG carriers.

Health status assessment of pump station units based on spatio-temporal fusion and uncertainty information

An effective health status assessment (HSA) for pump station units (PSUs) is crucial for accurately determining their real status and providing technical support for safe operational decisions. Due to the limitations of existing data-driven HSA methods, which primarily focus on the temporal dependencies of monitoring signals and fail to explore the complex interconnections among signals comprehensively. Moreover, when constructing performance degradation indices based on linear differences, these methods do not effectively integrate heterogeneous signals, resulting in an incomplete and inaccurate assessment of the overall system degradation. This paper proposes a real-time comprehensive HSA method for PSUs based on multi-source heterogeneous uncertainty information. Initially, a health benchmark model (HBM) is built using CrossGNN, which possesses cross-scale and cross-variable interaction capabilities, to precisely capture the temporal dependencies and dynamic relationships among variables in monitoring signals. Subsequently, key measurement points that reflect the operational status of the PSUs are identified through correlation analysis to establish multi-source evaluation indices. Then, considering the uncertainty in signal changes, a novel health degradation index (HDI) is developed using Mahalanobis distance (MD) and the Gaussian Cloud Model (GCM) to analyze changes in unit status. Furthermore, a weighting calculation method based on the non-dominated sorting genetic algorithm (NSGA-II) is proposed to establish a real-time comprehensive health index (RCHDI) for a thorough assessment of PSUs status. Finally, the effectiveness of the proposed method is validated through a case study using data from a pump station in the South-to-North Water Diversion Project in China. The results show that, compared to other studies, the proposed method significantly improves the stability and smoothness of the state assessment curve, with increases of 21.5% and 47.1% respectively, providing a new perspective for comprehensively assessing the health status of PSUs.V

Improved NSGA2 algorithm for recovery of interrupted departure flights

To solve the problem of airline flight disruption caused by emergencies, the disrupted departing flights are restored, a dual-objective optimization model is constructed to minimize the total delay cost of airlines and minimize the total delay time of passengers. An adaptive non-dominated sorting genetic algorithm based on dominance intensity is designed, and three improved operations are proposed: a fast dominance sorting method, a new congestion distance and an adaptive elite retention strategy. The proposed algorithm is verified by the operation data of an airline at Fuzhou Airport. The experimental results show that compared with the traditional plan-first-serve method, the solution obtained by the proposed algorithm is greatly optimized. Compared with the constraint method, the solution time is generally lower than the constraint method and the solution result is close to the optimal result obtained by the constraint method. Compared with multi-objective optimization algorithms such as NSGA2 and MOEAD, the proposed algorithm shows better performance and can solve the problem effectively and efficiently, providing a basis for airlines to achieve optimized solutions.

Multi-objective optimization of FCC separation system based on NSGA-Ⅱ

Based on the industrial production data, the simulation of the separation process of a 2 million tons/year FCC unit including the fractionation and the absorption-stabilization systems were conducted on Aspen Plus software. To optimize the operation process, multi-objective optimization was performed integrating the Aspen Plus platform and MATLAB environment utilizing the improved non-dominated sorting genetic algorithm (NSGA-Ⅱ). The established multi-objective optimization model was used for the operating variable screening, the genetic algebra selection and the optimal solution determination. During the optimization, the total yield of LPG and stable gasoline was aimed as the first optimization objective while the energy consumption of the whole system as the second objective. Five expressions were applied as the constraint functions and nine operating variables were conducted as the decision variables. The results showed that the performances of FCC separation system have been greatly improved after optimization. Some optimization strategies are advised for the whole system. The total yield of LPG and stabilized gasoline increases by 2. 44 %, and the energy consumption of the separation system decreases by 41. 79 %. In addition, the CO2 emission is reduced by 23.59 t/h and the total annual cost (TAC) is reduced by $0.89 million/year. It has been revealed that the multi-objective optimization method based on NSGA-Ⅱ algorithm is useful for the guidance of the optimization of industrial petrochemical process.

Machine learning – enabled inverse design of shell-based lattice metamaterials with optimal sound and energy absorption

ABSTRACT Currently, the development in shell-based lattice, is increasingly focused on multifunctionality, with growing interest in combining sound and energy absorption. However, few studies have explored the multi-objective inverse design process. Herein, we propose a new approach using machine learning (ML) to optimise both the mechanical and acoustic performances of shell-based lattices. Firstly, the K-Nearest Neighbour and Artificial Neural Network are employed to predict the properties of different configurations. Then the non-dominated sorting genetic algorithm is employed to generate the desired structures. Finally, the lightweight metamaterials generated achieve optimal multifunctional performances (an energy absorption capacity of 50% higher than typical Gyroid structure and a sound absorption coefficient near 1 at specific frequency band). Besides, the potential trade-off phenomenon of mechanical and acoustic properties is also presented by our work. Overall, this work presents a new concept to use ML and genetic algorithm for multi-functional inverse design for shell lattice metamaterials.

Multi-segmented tube design and multi-objective optimization of deep coaxial borehole heat exchanger

Deep coaxial borehole heat exchanger (DCBHE) is a key component to extract medium-deep geothermal energy for low-carbon building heating. It is a convention that both center tube and annuals tube are respectively using a single material. However, a basic idea behind this study is using non-linear design to ask for performance improvement. It is assumed that non-uniform tube design pattern can meet different heat exchanger demand at different depth under a geothermal gradient dominated underground environment. The whole study is to prove this conjecture and make it useful for engineering application. A new numerical model is put forward to considered multi-segmented structure in heat transfer computation and a nondominated sorting genetic algorithm (NSGA-Ⅱ) is adopted in optimization process. The results of this study show that the optimized designed case can increase outlet temperature by 3 °C while reducing investment of 10000RMB. In addition, a home-made software is developed to perform the thermal and economic evaluation of DCBHE as well as automatically optimization of this multi-segmented structure. This study can provide a new model, algorithm, results and software tool for better utilizations of deep geothermal energy.

Hybrid extreme gradient boosting regressor models for the multi-objective mixture design optimization of cementitious mixtures incorporating mine tailings as fine aggregates

The design of cementitious mixtures incorporating mine tailings as fine aggregates is a multi-objective optimization (MOO) problem, in which both the uniaxial compressive strength (UCS) and cost of the mixtures need to be considered simultaneously. Given that data-driven methods have shown promising results when solving similar MOO problems, this study developed an extreme gradient boosting regressor (XGBR) model on a dataset extracted from the literature to predict the UCS. Among the efforts taken to improve the models, a genetic algorithm (GA)-based XGBR model demonstrated the optimal prediction performance, with an R2 of 0.959. Next, the GA-XGBR model and a cost equation were used as objective functions in the MOO problem. The non-dominated sorting genetic algorithm with elite strategy (NSGA-II) was selected to solve the optimization problem. A case study was conducted, generating mixture designs that offered improved trade-offs between cost and UCS compared to experimental designs. Finally, a graphical user interface was developed to provide access to the prediction model and optimization method. Overall, this work can be used as a guide for optimal mixture designs as it facilitates informed decision-making before the actual applications.

Development of ANN model for predicting mechanical properties of 3D printed PEEK polymer using FDM and optimization of process parameters for better mechanical properties

Additive manufacturing (AM) has evolved from a proven technology to a rapid prototyping tool with great potential. This technology is widely used in many industries such as automotive, aerospace, and medical; fused deposition modeling (FDM) is a popular 3D printing technique for producing PEEK (polyether ether ketone) parts, including implant prosthetic teeth. In this study, artificial neural network (ANN) modeling, parametric optimization, and experimental examination of PEEK 3D printing were conducted to enhance 3D printing processes. In this study, four critical process factors (infill density, layer height, printing speed, and infill pattern) influence the surface roughness, mechanical strength, and elastic modulus of the printed samples. Utilizing a 4–12–3 network design, this study demonstrates that an ANN model with an average error of less than 5% is optimal for all three responses. Furthermore, the study employed a teaching and learning based optimization algorithm (TLBO) and a non-dominated sorting genetic algorithm (NSGA) to optimize the printing process to obtain improved mechanical properties. The findings highlight TLBO’s ability to minimize surface roughness to 6.01 μm and NSGA’s capability to maximize the elastic modulus to 1253.35 MPa and ultimate tensile strength to 65.55 MPa. Microstructural studies supported the results obtained through parametric analysis and optimization.

Design of high-temperature sodium heat pipe with composite wick based on non-dominated sorting genetic algorithm (NSGA)

As small modular reactors continue to advance, heat pipe reactors (HPRs) are being developed by multiple organizations. Designing heat pipes with optimal heat transfer capability is crucial for the effective performance of HPRs. Based on NSGA-III genetic algorithm, this paper presented the design method of a high-temperature heat pipe featuring a composite wick. The study examined the influence of heat pipe structure parameters on performance parameters and heat transfer limits. Based on the analysis, we built multi-objective modeling of heat pipe and obtained the optimal structural parameters by NSGA-III. Verification confirmed that the heat pipe met the Mach number and effective capillary radius requirements. This study provided valuable insights for improving heat pipe manufacturing techniques and reactor miniaturization.

Physics-informed and data-driven hybrid method for transmission accuracy design optimization of planetary roller screw mechanism

The planetary roller screw mechanism (PRSM) faces an ever-increasing precision transmission demand in current advanced equipment. The relationship between machining errors and transmission accuracy remains elusive due to the over-simplified physical models and small-sample experimental datasets. This work proposes a physics-informed and data-driven hybrid strategy for PRSM transmission accuracy evaluation and tolerance optimization. In the physical model, a PRSM transmission accuracy model is developed to calculate transmission error that considers 16 machining errors in eccentric, nominal diameter, pitch, flank angle, and roller consistency. In the dataset establishment, thread profile measurements and dynamic leadscrew inspections are conducted for the machining error and transmission accuracy data acquisition. A data augmentation approach combining the physical model with the generative adversarial network is utilized to predict travel deviation, variations, and axial backlash and estimate machining error contribution with the small-sample experimental dataset. It is firstly found that the roller consistency of nominal diameter significantly affects PRSM travel variation V2π with a 17.3 % importance value. With the developed framework, the key tolerances for screw, roller, nut, and roller consistency are optimized toward a typical precision transmission requirement using the non-dominated sorting genetic algorithm. It also provides a tolerance grade recommendation table with PRSM transmission accuracy level in engineering practice.

Building retrofitting towards net zero energy under climate change

Abstract The challenge in Net-Zero Energy Building (NZEB) retrofitting is to identify the most effective measures to address energy performance issues. This paper presents a machine learning model for optimizing retrofit measures to achieve NZEB under the influence of climate change. Specifically, the non-dominated sorting genetic algorithm (NSGA-III) minimizes energy consumption and the predicted percentage of dissatisfaction (PPD) while achieving a NZE balance, thereby obtaining the Pareto front. The Order of Preference by Similarity to Ideal Solution (TOPSIS) ranking technique is then applied to the Pareto front to obtain an optimal solution. Various passive energy retrofit measures are investigated, and renewable retrofit measures are employed to cover the required energy. This process is repeated for different time frames to consider the impact of climate change on selecting retrofit measures. The results clearly indicate that, for retrofitting a residential NZEB, higher insulation values are needed for future scenarios compared to the present scenario due to the effects of climate change. Using the future scenarios defined by the Shared Socioeconomic Pathways framework, a higher level of envelope insulation and renewable retrofit measures are required to achieve NZEB in the Sustainable Future scenario compared to the Fossil Fuel-dependent Future scenario, with increases of 35% and 50%, respectively.

Data-driven corrosion failure probabilistic assessment model for reinforced concrete structures

The corrosion-induced failure of marine reinforced concrete structures, stemming from prolonged exposure to environments with elevated chloride content, poses a significant threat to structural integrity and serviceability. Traditional models predominantly depend on prior information to estimate the spatial stochastic degradation of aging structures, leading to a lack of comprehensiveness and accuracy in evaluation results. To address these limitations, a data-driven probabilistic assessment model for corrosion failure is proposed. This model incorporates a pre-training phase that integrates electrochemical simulations with long-term exposure data to establish the spatiotemporal distribution of corrosion failures, thereby facilitating a thorough assessment of overall damage by quantifying the corrosion failure proportion while propagating epistemic uncertainty. Subsequently, a multivariate function is derived using the non-dominated sorting genetic algorithm to elucidate the relationship between input and output variables. The efficacy of the data-driven model is evaluated through experimental observations and model predictions. The Hangzhou Bay Bridge project serves as a case study, wherein this model is demonstrated using actual data obtained from exposure experiments and field detection. Furthermore, the proposed model enables a rapid prejudgment of corrosion failure proportion, significantly reducing diagnostic time compared to conventional procedures.

The Effects of Laser-Assisted Winding Process Parameters on the Tensile Properties of Carbon Fiber/Polyphenylene Sulfide Composites.

Currently, there is limited research on the in situ forming process of thermoplastic prepreg tape winding, and the unclear impact of process parameters on mechanical properties during manufacturing is becoming increasingly prominent. The study aimed to investigate the influence of process parameters on the mechanical properties of thermoplastic composite materials (CFRP) using laser-assisted CF/PPS winding forming technology. The melting point and decomposition temperature of CF/PPS materials were determined using DSC and TGA instruments, and based on the operating parameters of the laser-assisted winding equipment, the process parameter range for this fabrication technology was designed. A numerical model for the temperature of laser-heated CF/PPS prepreg was established, and based on the filament winding process setup, the heating temperature and tensile strength were simulated and tested. The effects of process parameters on the heating temperature of the prepreg and the tensile strength of NOL rings were then analyzed. The non-dominated sorting genetic algorithm (NSGA-II) was employed to globally optimize the process parameters, aiming to maximize winding rate and tensile strength. The results indicated that core mold temperature, winding rate, laser power, and their interactions significantly affected mechanical properties. The optimal settings were 90 °C, 418.6 mm/s, and 525 W, achieving a maximum tensile strength of 2571.51 MPa. This study provides valuable insights into enhancing the forming efficiency of CF/PPS-reinforced high-performance engineering thermoplastic composites.