Operating Conditions Research Articles

DQM: Data Quality Metrics for AI Components in the Industry

In industrial settings, measuring the quality of data used to represent an intended domain of use and its operating conditions is crucial and challenging. Thus, this paper aims to present a set of metrics addressing this data quality issue in the form of a library, named DQM (Data Quality Metrics), for Machine Learning (ML) use. Additional metrics specific to industrial application are developed in the proposed library. This work aims also to assess various data and datasets types. Those metrics are used to characterize the training and evaluating datasets involved in the process of building ML models for industrial use cases. Two categories of metrics are implemented in DQM: inherent data metrics, are the ones evaluating the quality of a given dataset independently from the ML model such as statistical proprieties and attributes, and model dependent metrics which are those implemented to measure the quality of the dataset by considering the ML model outputs such the gap between two datasets in regards to a given ML model. DQM is used in the scope of the Confiance.ai program to evaluate datasets used for industrial purposes such as autonomous driving.

The Electrooxidation of Synthetic Bipyridyl Herbicide Wastewaters with Boron-Doped Diamond Electrodes: A Technical and Economic Study to Boost Their Application for Pollution Prevention in the Agricultural Sector

Boron-doped diamond electrodes (BDDEs) offer a highly efficient pathway to mineralize recalcitrant compounds due to their reduced energy requirements, fewer chemical inputs, and mechanical stability. In this work, the electrochemical degradation of paraquat (PQ) and diquat (DQ) was studied using an undivided cell (Condiacell®-type) at circumneutral pH, and under galvanostatic control. The roles of applied current density, volumetric flow rate, and herbicide concentration were systematically studied through a central composite design (CCD) using a closed-flow reaction setup. Under the best operating conditions (i.e., for PQ: 1.6 mA/cm2, 80 mL/min, and 70 mL/min, and 70 mg/L; and for DQ: 1.5 mA/cm2, 80 mL/min, and 73 mg/L), a spectrophotometric analysis evidenced that the herbicides were satisfactorily removed (ca. 100%) while mineralization degrees were above 90%. Furthermore, the produced effluents yielded significant increases in seed germination and root length, which suggest a reduction in toxicity. Energy consumptions of 0.13 and 0.18 kWh/g of TOC are reported with the electrochemical cells for the PQ and DQ treatments, respectively. The PQ and DQ treatments by electrooxidation are estimated to emit nearly 2.7 and 38.9 kg CO2/m3 of water treated, with a cost around USD 250/m3. Carbon emissions could be greatly decreased for PQ (0.28 kg CO2/m3) and DQ (0.40 kg CO2/m3) if electricity were generated from renewable resources. Although this study suggests that the use of BDDE can be considered as a green alternative for agrochemical removal due to lower carbon emissions, the environmental profile of the process is determined by the degree of renewability of the electrical grid of each country or region.

Ensemble Pretrained Convolutional Neural Networks for the Classification of Insulator Surface Conditions

Overhead transmission line insulators are non-conductive materials that separate conductors from grounded transmission towers. Once in operation, they frequently experience environmental pollution and electrical or mechanical stress. Since adverse operational conditions can lead to insulation failure, regular inspections are essential to prevent power outages. To this end, this paper proposes a novel technique based on deep convolutional neural networks (CNNs) to classify high-voltage insulator surface conditions based on their image. Successful applications of CNNs in computer vision have led to several pretrained architectures for image classification. To use these pretrained models, a practitioner typically fine-tunes and selects one final model via a model selection stage and discards all other models. In contrast with many existing studies that use such a “winner-takes-all” approach, here, we identify the best subset of seven popular pretrained CNN architectures that are combined by soft voting to form an ensemble classifier. From a machine learning (ML) perspective, this focus is warranted because the convolutional base of each pretrained architecture operates as a feature extractor and an ensemble of them works as a combination of various feature extraction rules. Our numerical experiments demonstrate the advantage of the identified ensemble model to individual pretrained architectures.

Study on Operation Effect of Two-Stage MSL System for Rural Decentralized Sewage Treatment

To improve the removal efficiency of rural domestic sewage, a two-stage multi-soil-layer sewage treatment system with an “aeration section + non-aeration section” was designed, and its treatment performance was observed under different influent loads and aeration intensities. The experiment ran for a total of 150 days, and the results showed that the two-stage multi-soil-layer (MSL) system could effectively reduce the effluent concentration of sewage to meet discharge standards. Under the operating conditions of an influent hydraulic load of 1000 L·m−2·d−1 and an air–water ratio of 4:1, the final effluent average concentrations of COD, NH3-N, TN, and TP were 106.5 mg·L−1, 7.4 mg·L−1, 13.9 mg·L−1, 0.12 mg·L−1, and 18.6 mg·L−1, respectively, with average removal rates of 85.3%, 82%, 72.5%, 96%, and 85%. A longer hydraulic retention time and ideal anoxic conditions were ensured by designing a certain effluent height in the system. Adding aeration to the system allowed for a synchronous nitrification–denitrification reaction under reasonable influent loads, ultimately enabling the effluent to meet discharge standards.

A Novel Capacitance Estimation Method of Modular Multilevel Converters for Motor Drives Using Recurrent Neural Networks with Long Short-Term Memory

Accurate estimation of submodule capacitance in modular multilevel converters (MMCs) is essential for optimal performance and reliability, particularly in motor drive applications such as permanent magnet synchronous motor (PMSM) drives. This paper presents a novel approach utilizing recurrent neural networks with long short-term memory (RNN–LSTM) to precisely estimate capacitance in MMC-based PMSM drives. By leveraging simulation data from MATLAB, the LSTM neural network is trained to predict capacitance based on voltage, current, and their temporal variations. The proposed LSTM architecture effectively captures the dynamic behavior of MMCs in PMSM drives, providing high-precision capacitance estimates. The results demonstrate significant improvements in estimation accuracy, validated through mean squared error (MSE) metrics and comparative analysis of actual versus estimated capacitance. The method’s robustness is further confirmed under varying operating conditions, highlighting its practical utility for real-time applications in power electronic systems.

The Application of PID Control in DC Motor Control Systems

Abstract. The application of Proportional-Integral-Derivative (PID) control in direct current (DC) motor control systems is essential for achieving high levels of precision and reliability in both industrial and robotic applications. As DC motors are widely utilized in environments requiring accurate speed and torque control, this study seeks to address common challenges such as overshoot, instability, and sluggish response times that can compromise performance. The research is centered on the development and implementation of a PID-based control strategy using MATLAB/Simulink as the primary tool for simulation and testing. The study involves detailed simulation models and experimental validation, using data collected from controlled lab environments to evaluate the effectiveness of various tuning methods. These methods include adjusting the proportional, integral, and derivative gains to optimize motor responsiveness and system stability. The results indicate that with appropriate tuning, PID controllers can significantly enhance DC motor performance, leading to reduced overshoot, faster response times, and greater overall system reliability. The research concludes that adaptive PID control strategies, which dynamically adjust parameters in response to changing operating conditions, provide a robust solution for improving DC motor control in complex, dynamic, and nonlinear environments. This study lays the groundwork for future innovations in automation and precision-driven industries, offering insights that could be applied across a wide range of applications.

A Quantitative Method of Carbon Emission Reduction for Electrochemical Energy Storage Based on the Clean Development Mechanism

Electrochemical energy storage (EES) plays a crucial role in reducing the curtailed power from wind and solar PV power (WSP) generation and enhancing the decarbonization effects of power systems. However, research on quantifying the carbon emission reduction effects of EES methods in the engineering field is still insufficient, which constrains decision-makers from making intuitive assessments of the decarbonization effects of energy storage. Therefore, drawing on the principles of the clean development mechanism (CDM), this paper proposes a method for quantifying the carbon emission reductions of a standalone EES station. Firstly, based on the design principles of building marginal emission factor in the CDM, a method for calculating the BM weight of WSP is proposed. Secondly, three quantification methods for the carbon emission reductions of EES are presented based on the complexity of the calculations. Lastly, to analyze the impacts of different operational conditions and calculation methods on the carbon emission reduction of energy storage systems, a dispatch model is constructed for various operational scenarios. The results of the case study indicate that different calculation methods yield varying results in terms of the carbon emission reductions of energy storage systems, with the sharply value method yielding the smallest reduction and the output curve method yielding the largest reduction. Additionally, when considering the losses in the state of charge (SOC) of an energy storage system and reducing the overall output fluctuations of WSP-EES, the carbon emission reduction potential of the energy storage will decrease. This study establishes a theoretical basis for quantifying the carbon emission reductions of standalone electrochemical energy storage systems, aiding decision-makers in gaining a deeper understanding of the role of electrochemical energy storage in carbon reduction and operational value.

Analysis and Verification of cooling structure of superconducting motors for electrical aircraft propulsion

The hydrogen-powered aviation hybrid technology is one of the important directions of the development of electrical aircraft propulsion. Superconducting motors (SCMs) are the core components of a hydrogen-powered aircraft due to their high power-to-weight ratio. Among SCMs, partial SCMs with superconducting armature windings and permanent magnets (SC-PMMs) are the research front and hotspots. This study focuses on the key issue of cooling the superconducting (SC) coils of SC-PMMs. The advantages and disadvantages of three cooling structures, namely core conduction cooling, coil immersion cooling, and core and coil immersion cooling, are compared. The temperature of the SC coils in different cooling structures is simulated and analyzed in detail. The obtained results show that the temperature of the coils in the core and coil immersion cooling structure is not much different from that in the coil immersion cooling structure, with a temperature difference of about 1.5 K only. However, the implementation of the core and coil immersion cooling structure is much easier. Therefore, an SC-PMM prototype is developed using it as the cooling structure, and the temperature change in the prototype under different operating conditions is investigated experimentally. The obtained results show that the final stable temperature during the cooling process is 76.8 K, and the coil on the top is more likely to quench than that at the bottom. The maximum frequency and maximum current at which the prototype can operate stably for a long time are 200 Hz and 49 A, respectively. This study verifies the effectiveness of the core and coil immersion cooling structure, obtains the quench prone area in SC-PMMs, and lays the foundation for the development of high-performance and highly reliable SCMs.

A meta transfer learning-driven few-shot fault diagnosis method for combine harvester gearboxes

Combine harvester gearboxes operate for extended periods under variable operating conditions, making it costly to gather sufficient fault data. A meta transfer learning-driven fault diagnosis method for combine harvester gearboxes is proposed to solve the complex operating conditions and scarce fault samples. The meta learning is employed to train the model so that the performance of the proposed method is not contingent upon the quantity of training data. The multi-step loss optimization (MSL) method is introduced to improve the inner loop and address the unstable update gradients in training. The enhanced method uses each task to refine the model updating strategy, thus circumventing the gradient explosion and decay. The proposed method employs conditional domain adversarial network to extract deep discriminative features from both domains. The batch feature constraint (BFC) is proposed to balance the features’ transferability and class discriminability. A weight-balancing strategy is employed to reconstruct the training loss function, enabling gearbox fault diagnosis under variable operating conditions with few-shot data. The effectiveness of the proposed method is validated through data collected from the combined harvester gearbox’s fault diagnosis experimental rig.

Ultrasonic-assisted radial jet reattachment atomizer

Ultrasonic atomization, a powerful method using high-frequency sound waves, has gained notable significance across diverse industries due to its capacity to disintegrate liquids into very fine droplets. The use of ultrasonic vibrations for spray formation can effectively address the challenges associated with conventional methods, including the requirement for high temperatures and high-pressure fluids. Compared to conventional methods, ultrasonic atomizers can deliver a spray with lower velocity, operate at lower temperatures, produce smaller particle sizes, achieve high evaporation rates, and impose low mechanical stress. The radial jet reattachment (RJR) nozzle is a unique design to modify a jet’s flow and improve its transport characteristics, especially in air drying and cooling processes. In this paper, a novel technology is utilized with the combination of an RJR nozzle and ultrasonic atomization to atomize most liquids. The corresponding atomization rate, mist droplet size distribution, and mist droplet velocity distribution, influenced by liquid properties, temperature change, transducer mesh pore size, and applied voltage have been investigated in this paper. The energy consumption ratios, defined as the ratio of thermal energy required to evaporate liquid divided by ultrasonic energy, are analyzed based on atomization rate and applied power, showing very promising results among atomizing methods. Furthermore, the results in terms of the droplet average diameter and mean velocity as well as the resultant volumetric flow rate under different operating conditions and for all working fluids considered have been correlated with the aid of non-dimensional parameters. In addition, certain potential applications based on the remarkable characteristics of the ultrasonic-assisted RJR atomizer such as misting liquids and spray drying are highlighted.

Optimization of C5+ production by CO2 recycle at an integrated Tri-reforming and Fischer-Tropsch process

Integration of Tri-reforming and Fischer-Tropsch processes is a novel approach for conversion of CO2 into C5+ liquid hydrocarbon. Tri-reforming converts CO2 into syngas and does not require external heat source due to methane oxidation reaction that occurs at the beginning of reactor. Fischer-Tropsch synthesis converts produced syngas in the reformer to hydrocarbon fuels. In this research, plug reactors have been modeled in a heterogeneous and one-dimensional form, and the mass and energy equations governing them in steady state have been developed. The accuracy of models is validated with literature data. Then an optimization problem aiming at maximal C5+ production is compiled with specific limitations imposed on operating conditions. Based on the modeling results, 95 % of CO2 produced at Fischer-Tropsch and 92 % CO2 produced at Tri-reforming process is captured and injected into Tri-reforming reactor for conversion into hydrocarbon fuels. Modeling results revealed that the mole fractions of C2-C4 and C5+ at outlet of Fischer-Tropsch are 0.117 and 0.023 which could be purified in separators and used as clean energy carriers. The suggested integrated route for CO2 capture and conversion into green fuels offers both environmental and technical advantages.

Station-based, free-float, or hybrid: An operating mode analysis of a bike-sharing system

The profit-oriented bike-sharing industry, such as Mobike in China and Limebike in the USA, has widely adopted the free-float mode, which allows users to rent and return bikes without any restrictions with regard to stations. Compared to the traditional station-based mode, this new mode improves convenience and satisfies a variety of travel demands, but it also results in higher operating costs and lower number of available bikes (the number of bikes can be found). So far, no theoretical study has been done comparing the performance levels of the two different operating modes. Some bike-sharing firms are now attempting to design a hybrid operating mode that combines the advantages of the two modes. We design a mixed-integer program to model these three operating modes under different operating conditions. The model captures some of the new features of free-float bike-sharing systems. These new features include discounts for returning bikes to designated stations, different numbers of available bikes at stations and free-float areas, differences in station-based return levels as well as in convenience levels in the three operating modes. This study also considers the interactions between the free-float and station-based modes in meeting the demand and in managing relocation processes. Extensive numerical experiments are conducted and the results reveal that in more than half of the total cases under different parameter settings, the profits of the hybrid mode outperform the profits of the other two modes. The station-based mode is suitable for settings with high convenience levels, low number of available free-float bikes, and limited budgets for bike acquisitions, whereas the free-float mode can ensure high profits with low convenience levels and a large number of bikes being available. Our models can serve as a decision-making tool for bike-sharing firms in their selection of an optimal operating mode.

Chemical looping gasification of vinegar residue with enhanced LD slag composite Ca-Fe oxygen carrier for syngas production

Biomass chemical looping gasification (BCLG) is an emerging technology that enables waste co-processing into clean energy. A laboratory-scale vertical fixed-bed reactor was used to conduct CLG experiments with vinegar residue (VR) as a biomass fuel, and the effect of enhanced LD slag composite Ca-Fe material as an oxygen carrier (OC) on the production of syngas from BCLG was investigated. This study analyzed the influence of LD slag proportion, kinds of OC, and operational conditions (temperature, oxygen carrier/biomass (OC/B) ratio, and steam/biomass (S/B) ratio) on gasification performance. Results indicate that the syngas yield under the gasification operating conditions at about 850 °C, OC/B = 1, and S/B = 2.5 obtained 1.36 Nm3/kg, the CCE and CGE achieved about 80.82 % and 98.16 %, respectively, and the H2/CO molar ratio was as high as 2.57. The OCs multi-redox cycle test revealed that after undergoing 10 redox cycles under the conditions mentioned above, the gas yield, CCE, and CGE were reduced to varying extents, but still maintained impressive reactivity. The mechanism analysis showed that the performance degradation of the LD slag composite Ca-Fe OC during the multi-cycle process was related to its agglomeration due to thermal stress and steam. This study provides a new perspective on the synthesis of low-cost OCs and the co-utilization of solid wastes.

Investigate the impact wear failure behavior of CoMoCr engine valve and valve seat pairs under harsh conditions

The wear of sealing face is one of the main reasons for the failure of engine valve and valve seat pair. Changes in engine combustion load, running time, temperature, and other operating conditions can affect the wear of valve-valve seat pair. In this work, the CoMoCr alloy cladding valves and valve seat were used as the pair, to investigate the influencing mechanism of combustion load and valve lift on wear. Three groups of tests under different combinations of combustion loads and valve lifts were completed on self-designed testing rig. The results demonstrate that the increase of combustion load and valve lift exacerbate the wear of the valve and valve seat, and valve lift has a more significant effect on wear than combustion load. The increased combustion load worsens the microslip process and intensifies the abrasive wear process. Whereas valve lift enhances the impact process, causing the dense tribofilm on the material surface to delaminate due to fatigue. Destruction of the tribofilm prevented effective protection of the underlying material, which increased wear process.

Modular Synthesis of α-Quaternary Chiral β-Lactams via Three-Component Asymmetric Kinugasa/Aldol or Kinugasa/Mannich Cascade Reactions.

The β-lactam scaffolds are the prevalent structural units in antibiotics and natural products. Herein, three-component asymmetric Kinugasa/aldol and Kinugasa/Mannich cascade reactions have been developed for constructing α-quaternary chiral β-lactams. This strategy enables sequential assembly of alkynes, nitrones and aldehydes (or imines) and creates three contiguous stereogenic centers, controlled by copper(I) catalysts and chiral bis(oxazolidine) ligands. The developed protocol features high enantioselectivity, good reaction efficiency, and mild operational conditions representing a practical and sustainable synthetic tool for the construction of functionalized chiral β-lactams.

Slaughterhouse wastewater remediation using carbonized sawdust followed by textile filtration

Slaughterhouse wastewater (SWW) is considered an industrial wastewater, which seriously harms the environment due to the high concentration of contaminants such as biochemical oxygen demand (BOD), chemical oxygen demand (COD), and total suspended solids (TSS). Additionally, the wastewater from slaughterhouses contains harmful bacteria. This study used a lap-scale model to treat SWW from a local private slaughterhouse. The treatment process involves three stages: adsorption using activated carbon, which is derived from sawdust, followed by sedimentation, and finally, a slow sand filter with a modified layer of woven textile cotton. The first two steps were tested to obtain the ideal operation condition of the treatment system. After the final step of treatment, we evaluated the overall process using a modified slow sand filter (MSSF). We used a Jar test to determine the optimal dosage of activated carbon from sawdust (ACS). The monitored parameters were physicochemical, such as turbidity, total suspended solids (TSS), total dissolved solids (TDS), biochemical oxygen demand (BOD), chemical oxygen demand (COD), total phosphorus (TP), and total nitrogen (TN). The bacteriological examination included both total coliform count (TCC) and fecal coliform count (FCC). The results of the jar test revealed that the optimal ACS dose was 2.0 g/l. After adjusting the contact time and pH levels for the adsorption process, we discovered that the ideal contact time was 100 min and the ideal pH level was 4.0. Finally, we evaluated the entire treatment system by applying the MSSF after the sedimentation process, and found that the removal efficiencies of turbidity, BOD, COD, TSS, TDS, TP, and TN were 97.14, 94.80, 91.80, 98.96, 81.17, 81.12, and 82.50%, respectively. This is in addition to the filter's ability to remove bacteria counts at a rate of up to 98.93 and 99.13% of TCC and FCC, respectively.

Computational Fluid Dynamics Analysis and Optimization of a Doublesuction Turbine Agitator

Background: As one of the essential pieces of chemical equipment, a reactor provides the necessary reaction space and conditions for the materials involved in the reaction during the stirring process. However, under typical operating conditions, issues such as uneven gas distribution, suboptimal gas-liquid mixing, and low product yield often arise in gas-liquid phase reactors. Purpose: To address the issues prevalent in current stirred reactors, a new design for a stirred reactor equipped with a double-suction turbine agitator was developed. Method: In this paper, a stirred reactor equipped with a double-suction turbine agitator was designed, and its three-dimensional modeling was conducted using SolidWorks. Computational Fluid Dynamics (CFD) simulations, based on the Euler-Euler two-phase approach with the RNG k −ε turbulence model, were performed to assess variables such as stirring speed, installation height, blade diameter and agitator inner diameter. The dispersion characteristics and flow field behaviors of the gas-liquid two-phase under varying conditions were comparatively analyzed. Optimizations were conducted across various parameters to enhance the gas mixing efficiency in the liquid phase. Result: The results show that a diameter of 370mm for the double-suction turbine agitator, an installation height of 640mm, a blade diameter of 500mm, and an inner hole diameter of 200mm yield optimal gas-liquid two-phase mixing performance. This configuration results in a broad and uniform gas distribution within the reactor, maintaining a desired high level of gas holdup at specific positions. Conclusion: The double suction turbine agitator is a type of radial agitator. During operation, it induces significant centrifugal forces in the liquid, exerts a robust shear effect, and enhances the mixing of the gas-liquid phases, thereby increasing the production efficiency of the product.

Enhanced removal of tetracycline using three-dimensional electrochemical system with Fe/N/S co-doped coffee grounds biochar particle electrodes: Performance and mechanism

In this study, Fe/N/S co-doped biochar was prepared from coffee grounds for using as particle electrodes (PE) to construct a three-dimensional electrochemical system (3DES). Tetracycline (TC) was selected as the simulated contaminant to evaluate the performance of 3DES in removing trace organic contaminates form water. First, characteristics analysis revealed that the PE was the micron-level carbon-based solid material with good electric conductivity, excellent catalytic performance and stability. Then, the performance of the 3DES was evaluated. About 92 % of TC and 76 % of total organic carbon (TOC) was removed under optimal operation conditions of potassium peroxydisulfate (PDS) addition of 3 mM, current density of 100 mA·cm−2, PE dosage of 0.5 g·L−1 and solution initial pH of 7. The 3DES exhibited satisfactory stability and application prospect for trace organic contaminates treatment in real water. Furthermore, analysis of the reactive oxidized species (ROS) revealed that the 1O2 and O2•− contributed much more to the TC removal than •OH and SO4•−. In addition, three possible pathways of TC removal in 3EDS was proposed. TC was degraded to organics with simple structures through functional group removal, ring-opening, and CO bond rupturing, and finally mineralized into CO2, H2O, and NO3-, etc. Finally, toxicity evaluation of the intermediate products indicated that the ecological risks of TC was effectively reduced through 3DES. This study provided a new strategy for resource utilization of carbon-based solid waste and efficient treatment of refractory wastewater.

ANN modeling and RSM optimization of ultrasound-assisted extraction of protodioscin-rich extracts from Tribulus terrestris L.

Tribulus terrestris L. is a herb renowned for its abundance of saponins, flavonoids, and alkaloids, which are utilized in treating various health conditions. Protodioscin functions by enhancing the conversion of testosterone into potent dihydrotestosterone, stimulating an increase in libido, red blood cell production from the bone marrow, and muscle development. Contemporary ultrasound-assisted-extraction (UAE) process employing green extraction solvents was selected to design the required separation system. The experimental plan was developed based on the independent operating variables – extraction time, operating temperature and solvent system composition in order to determine the influence of defined parameters and their interactions on the extraction yield and the presence of protodioscin. The 3D-RSM approach was introduced to determine the optimal values of studied independent variables in the area of maximal extraction yield. UAE process performed at optimal operating conditions generated maximal extraction yield (31 %, w/w) and protodioscin content of 5.9 mg/g dry plant matrix. Experimental data was used to develop an ANN for the defined extraction system using the operating variables values as the input matrix and observed yield as target matrix. Successfully designed and trained ANN generated high correlation (r = 0.9992) between observed data and predictive model’ outputs, and MSE value of 0.29107.

Optimization of ANN Models Using Metaheuristic Algorithms for Prediction of Tailpipe Emissions in Biodiesel Engine

ABSTRACTMachine learning techniques are gaining momentum in the present‐day context in most engineering applications due to their versatility and accuracy. They facilitate faster data processing coupled with a high degree of accuracy. They are extensively used in understanding and modeling engine combustion and emissions. Engine emissions significantly contribute to environmental degradation. In the current study, an effort has been made to compare the emissions recorded from a four‐stroke single‐cylinder biodiesel engine with those obtained using artificial neural network (ANN) models, where the hyperparameters have been optimized using nature‐inspired metaheuristic optimization algorithms like JAYA, WOA, ROA, and WaOA. The study was conducted using diesel and cardanol‐methanol‐diesel blends of B10M10, B20M10, and B30M10, by varying the fuel injection pressure from 180 bar (standard injection timing) to 220 bar with an interval of 20 bar. Furthermore, experiments were conducted with oxygen enrichment at concentrations of 3%, 5%, and 7% w/w on the standard oxygen concentration of air. The study showed a remarkable reduction of 59% in CO emissions at 220 bar fuel injection pressure with 7% w/w oxygen enrichment for the B30M10 blend as compared to 180 bar without oxygen enrichment. A similar reduction of 32.6% and 16.6% were observed for HC emissions and smoke opacity for the same operating conditions. However, a rising trend of 50% was observed for NOx emissions for the same blend and operating conditions. The findings indicate that the data recorded conforms with that obtained by using the ANN model optimized through these metaheuristic algorithms.