Prediction and optimization of dual-fuel marine engine emissions and performance using combined ANN with PSO algorithms

Ma, Cheng; Yao, Chong; Song, Enzhe; Ding, Shun-Liang

doi:10.1177/1468087421990476

Cited by 24 publications

(8 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…therefore, the boundary range of the SR is shown in Figure 2, and the range of the remaining parameters is shown in Table 3. In order to obtain the experimental data required for modeling while avoiding the increased costs associated with extensive testing, this study relies on V-optimization and space-filling experimental design methods for the condition point design [16][17][18]. The main injection time is utilized as a local input whereas the other parameters are used as global inputs since it has the largest impact on engine characteristics.…”

Section: Input and Output Parameters And Rangesmentioning

confidence: 99%

Multi-Objective Optimization Study of Dual-Fuel Engine Emissions and Economy

Ma,

Li,

Pang

et al. 2023

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

In the multi-objective performance optimization process for dual-fuel engines, the conflict between emissions and fuel efficiency is a consideration. To find a satisfactory compromise among many optimal solutions, reduce the difficulty of selecting solutions, and respond to different needs, a decision-making preference optimization strategy is introduced. The reliability prediction algorithm of the micro-ignition diesel/natural gas (NG) dual-fuel engine is built using support vector machines (SVM). The performance prediction model is combined with the optimization algorithm, and the preference information of the decision-maker (DM) is introduced into the optimization process, to guide the population evolution process to the direction that the DM is interested in, and achieve multi-objective preference optimization. Selecting nitrogen oxide (NOx) emission and braking specific fuel consumption rate (BSFC) as the optimization targets, the optimal Pareto front surface is obtained. It can be seen from the simulation results that after introducing the decision preference, the evolution of the population can proceed in the direction of interest to the DM. Preference optimization can be achieved by rationally configuring the preference strength parameter δ, the weight vector w, and the reference point g. The combination of control parameters corresponding to the two preferences was downloaded to the ECU for bench test, and compared with the original data, it was found that when low emissions are preferred, the NOx emission meets the IMO Tier-III limit under all working conditions, and the average NOx emission is 1.22g·(kW·h)-1, which is 78.9% lower than the original engine. At the same time, it was found that even with lower emissions, fuel consumption was reduced by 4.94% compared to the original engine. The preference for lower fuel consumption is 3.68% lower than the preference for lower emissions, but the deterioration of NOx emissions is obvious.

show abstract

Section: Input and Output Parameters And Rangesmentioning

confidence: 99%

Multi-Objective Optimization Study of Dual-Fuel Engine Emissions and Economy

Ma,

Li,

Pang

et al. 2023

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

show abstract

“…Each particle has its own position and velocity to move around the search space. The particles are evaluated using a fitness function to see how close they are to the optimal solution (Das et al, 2014; Da Silva et al, 2018; Ma et al, 2022; Pandey et al, 2020).…”

Section: 1 Neural Emulatormentioning

confidence: 99%

Enhancement neural control scheme performance using PSO adaptive rate: Experimentation on a transesterification reactor

Yassin

Zribi

Atig

et al. 2022

Journal of Vibration and Control

View full text Add to dashboard Cite

An arbitrary choice of the neural controller adaptive rate can have a negative effect on the performance of the closed-loop system. In this study, we propose a novel methodology for neural controller adaptive rate using Particle Swarm Optimization algorithm. The developed control scheme is composed of a recurrent neural networks emulator and controller with decoupled adaptive rates. Constraints on the adaptive rate are derived from the Lyapunov stability method. Particle Swarm Optimization is proposed as a mechanism to optimize the adaptive rate of the NC to improve the closed-loop performances. The advantages of the proposed new control algorithm are as follows: (1) online optimal choice of adaptive rate, which reduces the effort for searching an adequate neural controller adaptive rate when considering the conventional methods and (2) ensuring stability, faster convergence, disturbance rejection, and good tracking. The efficiency of the proposed PSO adaptive rate is demonstrated with numerical control of SISO nonlinear system. The obtained results prove the efficiency of the proposed NC compared to those obtained with existing methods. An application of the developed approach on a semi-batch reactor is presented to validate simulations results.

show abstract

“…PSO is an optimization algorithm based on prediction of bird behavior [59]. Compared with other optimization algorithms, the PSO algorithm is more prominent in optimization efficiency and stability [60].…”

Section: Expert Decision Model Of Ipso Algorithmmentioning

confidence: 99%

Dynamic Quality Monitoring System to Assess the Quality of Asphalt Concrete Pavement

Zhang

Philbin

et al. 2021

Buildings

View full text Add to dashboard Cite

With the rapid development of new technologies, such as big data, the Internet of Things (IoT) and intelligent sensing, the traditional asphalt pavement construction quality evaluation method has been unable to meet the needs of road digital construction. At the same time, the development of such technologies enables a new management system for asphalt pavement construction. In this study, firstly, the dynamic quality monitoring system of asphalt concrete pavement is established by adopting the BeiDou Navigation Satellite System, intelligent sensing, the IoT and 5G technology. This allows key technical indicators to be collected and transmitted for the whole process of asphalt mixture, which includes the mixing plant, transport vehicle, paving and compaction. Secondly, combined with AHP and the entropy weight (EW) method, the index combination weight is calculated. The comprehensive index for the pavement digital construction quality index (PCQ) is proposed to reflect the impact of monitoring indicators on pavement quality. An expert decision-making model is formed by using the improved particle swarm optimization (PSO) algorithm coupled with radial basis function neural network (RBF). Finally, the digital monitoring index and pavement performance index are connected to establish a full-time and multi-dimensional digital construction quality evaluation model. This study is verified by a database created from the digital monitoring data of pavement construction collected from a highway construction project. The system proposed in this study can accurately reflect the quality of pavement digital construction and solve the lag problem existing in the feedback of construction site.

show abstract

Prediction and optimization of dual-fuel marine engine emissions and performance using combined ANN with PSO algorithms

Cited by 24 publications

References 45 publications

Multi-Objective Optimization Study of Dual-Fuel Engine Emissions and Economy

Multi-Objective Optimization Study of Dual-Fuel Engine Emissions and Economy

Enhancement neural control scheme performance using PSO adaptive rate: Experimentation on a transesterification reactor

Dynamic Quality Monitoring System to Assess the Quality of Asphalt Concrete Pavement

Contact Info

Product

Resources

About