An Application of Artificial Neural Network to Diesel Engine Modelling

Brzozowska, Lucyna; Brzozowski, Krzysztof; Nowakowski, J.

doi:10.1109/idaacs.2005.282958

Cited by 9 publications

(5 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the proposed model is based on another type of network with a radial type of activation function (RBF) with a single neuron on the output layer. RBF-type networks are usually used in tasks where the local character of approximation is more preferable (Brzozowska et al, 2005;Sordyl and Brzozowski, 2018). In RBF-type artificial neural networks, the most popular base function is the Gauss function:…”

Section: Modelmentioning

confidence: 99%

See 1 more Smart Citation

Analysis and Prediction of Vehicles Speed in Free-Flow Traffic

Maczyński

Brzozowski

Ryguła

2021

Transport and Telecommunication Journal

Self Cite

View full text Add to dashboard Cite

Speed is a crucial factor in the frequency and severity of road accidents. Light and heavy vehicles speed in free-flow traffic at six locations on Poland’s national road network was analyzed. The results were used to formulate two models predicting the mean speed in free-flow traffic for both light and heavy vehicles. The first one is a multiple linear regression model, the second is based on an artificial neural network with a radial type of neuron function. A set of the following input parameters is used: average hourly traffic, the percentage of vehicles in free-flow traffic, geometric parameters of the road section (lane and hard shoulder width), type of day and time (hour). The ANN model was found to be more effective for predicting the mean free-flow speed of vehicles. Assuming a 5% acceptable error of indication, the ANN model predicted the mean free-flow speed correctly in 84% of cases for light and 89% for heavy vehicles.

show abstract

Section: Modelmentioning

confidence: 99%

“…where is an additional scaling coefficient. The values of unknown scaling coefficients were obtained by solving an optimization task (Brzozowska et al, 2005). To solve the task, the genetic algorithm was used with the real-value representation of genes in the chromosome (Rothlauf, 2006).…”

mentioning

confidence: 99%

Analysis and Prediction of Vehicles Speed in Free-Flow Traffic

Maczyński

Brzozowski

Ryguła

2021

Transport and Telecommunication Journal

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another research area in engine design is modeling of different parts of engines [12][13][14]. Modeling is done for different reasons.…”

Section: Introductionmentioning

confidence: 99%

Design of the Permanent Magnet Synchronous Motor Used in Electric Vehicles With the Help of the Particle Swarm Algorithm and Ansys-Maxwell

ÖZÜPAK,

ÇINAR

2023

Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi

View full text Add to dashboard Cite

Performance and efficiency are among the most important parameters in electric motors. Improvements to the engine not only increase engine performance, but also affect production costs. Permanent Magnet Synchronous Motor (PMSM) is a motor widely used in electric vehicles with its high torque density, high efficiency and production advantages. In this study, 110 kW (Adjust-Speed Permanent Magnet Synchronous Motor) AS-PMSM was designed for electric vehicle applications. The results of ANSYS-Maxwell and Particle Swarm Optimization (PSO) algorithms and the calculations of the optimized design were compared in line with the obtained data. In the design study, theoretical calculations, PSO algorithm and finite element method (FEM) based ANSYS-Maxwell software were used. Based on these values, the computer aided design of the engine was carried out. First of all, the basic design and performance criteria of the engine were determined. Parameters of the motor such as torque ripple, iron loss, efficiency and electromagnetic analysis were analyzed and optimized with ANSYS-Maxwell. Then, electrical, magnetic and performance analyzes of the motor were made. How the engine performance changes with the methods used has been examined in detail. Efficiency values were determined under various operating conditions in engine performance studies. The validity of the improvement study and the verification of the design study were examined by comparing the ANSYS results with the PSO algorithm results. The analysis results showed that the designed electric motor met the desired power values and design performance criteria.

show abstract

“…Mohd Noor et al 22 took advantage of ANN technique to predict brake power, exhaust gas temperature, and the output torque. Brzonzowska et al 23 also proposed an ANN model to reproduce those processes. The recurrent neural networks (RNNs) with feedback connects has demonstrated that it has a strong ability to predict the time series task on the nonlinear system.…”

Section: Introductionmentioning

confidence: 99%

A long short-term memory neural network approach for the hardware-in-the-loop simulation of diesel generator sets

Wang

2019

Measurement and Control

View full text Add to dashboard Cite

The electronic speed governor plays an important role in diesel generator sets. The ideal method for developing and debugging the electronic governor is to simulate the diesel engine’s dynamic characteristics with the hardware-in-the-loop simulation system. In this system, the diesel engine can be replaced by a mathematical model. Our research proposed a novel diesel engine modeling method using the long short-term memory neural network for simulating dynamic characteristics of the rotational speed of diesel generator sets. The proposed model is trained and tested on the data of the real diesel generator sets. With different power loads and unloads, experimental results demonstrated that this method was able to successfully simulate the dynamic characteristics of diesel generator sets. In addition, comparing to other existing methods provided a conclusion that the performance of the model was better than others. Finally, the proposed model was deployed on an established hardware-in-the-loop simulation system. The results further demonstrated that this model was able to reproduce the diesel generator sets’ dynamic characteristics.

show abstract

An Application of Artificial Neural Network to Diesel Engine Modelling

Cited by 9 publications

References 1 publication

Analysis and Prediction of Vehicles Speed in Free-Flow Traffic

Analysis and Prediction of Vehicles Speed in Free-Flow Traffic

Design of the Permanent Magnet Synchronous Motor Used in Electric Vehicles With the Help of the Particle Swarm Algorithm and Ansys-Maxwell

A long short-term memory neural network approach for the hardware-in-the-loop simulation of diesel generator sets

Contact Info

Product

Resources

About