Fault Diagnosis of Marine Diesel Engines Based on SOM Neural Network

2011 ◽  
Vol 219-220 ◽  
pp. 809-813 ◽  
Author(s):  
Qiang Song ◽  
Ai Min Wang
Keyword(s):  
Neural Network ◽  
Diesel Engines ◽  
Learning Algorithm ◽  
Learning Network ◽  
Marine Diesel ◽  
Som Neural Network ◽  
The Cost ◽  
Fully Connected ◽  
High Degree ◽  
Self Learning

SOM neural network is a fully connected array of neurons composed of non-teachers and self-learning network, which has a strong nonlinear mapping ability and flexible network structure and a high degree of fault tolerance and robustness. This paper introduces the structure of SOM neural network and learning algorithm and presents an instance of marine diesel engines in MATLAB environment. The diagnosis of marine diesel engine showed that the model can reduce the cost of diagnosis and increase the efficiency of diagnosis. There will be well application prospect in practice.

scholarly journals Self Learning Gaming Bot using CNN.

2020 ◽  
Vol 9 (4) ◽  
pp. 2397-2401
Keyword(s):  
Neural Network ◽  
Reinforcement Learning ◽  
Learning Algorithm ◽  
Intelligent Agent ◽  
Maximum Score ◽  
Input Method ◽  
Present Universe ◽  
High Level ◽  
Fully Connected ◽  
Self Learning

In the present universe of current gaming condition bots are the intelligent agent that assumes a prominent job in the popularity of a game in the market. As these bots have gotten very unsurprising to the games. So here we are proposed an AI model for playing games with high level inputs using reinforcement learning. Algorithm works in the Atari Environment i.e. we are using 2D game. This model consists of the CNN (convolution neural network) for the inputs which is fully connected layers and find out the actions according to the inputs. In this learning -based approach, bots learned how to attack and ignore opponents so that bot can get maximum score. In this learning -based approach, bots learned how to attack and ignore opponents so that bot can get maximum score Then we tried the combine the input method which results maximum score of the bot in the environment for the better performance.

scholarly journals Research on improved wavelet convolutional wavelet neural networks

2020 ◽  
Author(s):  
Jing-Wei Liu ◽  
Fang-Ling Zuo ◽  
Ying-Xiao Guo ◽  
Tian-Yue Li ◽  
Jia-Ming Chen
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
High Performance ◽  
Learning Algorithm ◽  
Wavelet Neural Network ◽  
Deep Learning Algorithm ◽  
Main Work ◽  
Good Ability ◽  
Fully Connected

AbstractConvolutional neural network (CNN) is recognized as state of the art of deep learning algorithm, which has a good ability on the image classification and recognition. The problems of CNN are as follows: the precision, accuracy and efficiency of CNN are expected to be improved to satisfy the requirements of high performance. The main work is as follows: Firstly, wavelet convolutional neural network (wCNN) is proposed, where wavelet transform function is added to the convolutional layers of CNN. Secondly, wavelet convolutional wavelet neural network (wCwNN) is proposed, where fully connected neural network (FCNN) of wCNN and CNN are replaced by wavelet neural network (wNN). Thirdly, image classification experiments using CNN, wCNN and wCwNN algorithms, and comparison analysis are implemented with MNIST dataset. The effect of the improved methods are as follows: (1) Both precision and accuracy are improved. (2) The mean square error and the rate of error are reduced. (3) The complexitie of the improved algorithms is increased.

scholarly journals Partial Label Learning Based on Fully Connected Deep Neural Network

2022 ◽  
Vol 16 ◽  
pp. 287-297
Author(s):  
Houjie Li ◽  
Lei Wu ◽  
Jianjun He ◽  
Ruirui Zheng ◽  
Yu Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Process Model ◽  
Deep Neural Network ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Ground Truth ◽  
Training Sample ◽  
Support Vector ◽  
Partial Label Learning ◽  
Fully Connected

The ambiguity of training samples in the partial label learning framework makes it difficult for us to develop learning algorithms and most of the existing algorithms are proposed based on the traditional shallow machine learn- ing models, such as decision tree, support vector machine, and Gaussian process model. Deep neu- ral networks have demonstrated excellent perfor- mance in many application fields, but currently it is rarely used for partial label learning frame- work. This study proposes a new partial label learning algorithm based on a fully connected deep neural network, in which the relationship between the candidate labels and the ground- truth label of each training sample is established by defining three new loss functions, and a regu- larization term is added to prevent overfitting. The experimental results on the controlled U- CI datasets and real-world partial label datasets reveal that the proposed algorithm can achieve higher classification accuracy than the state-of- the-art partial label learning algorithms.

Impact of Nitrogen Oxides Emission Reduction Methods on Specific Fuel Consumption of Marine Diesel Engines

2021 ◽  
Vol 23 ◽  
pp. 279-289
Author(s):  
Jerzy Herdzik
Keyword(s):  
Nitrogen Oxides ◽  
Fuel Consumption ◽  
Diesel Engines ◽  
Emission Reduction ◽  
Specific Fuel Consumption ◽  
Marine Diesel ◽  
Reduction Methods ◽  
The One ◽  
Tier 3 ◽  
The Cost

The paper has been presented the methods of nitrogen oxides emission reduction to fulfill the Tier 2 and Tier 3 requirements of the Annex VI of MARPOL Convention. It has been shown the development of marine two-stroke diesel engines and the change of nitrogen oxides emission from 1960 to 2000 and later up to 2020 after the implementation of NOx emission reduction methods. Specific fuel consumption before 2000, and as a prediction and given data in the manufacturers manuals for Tier 3 engines up to 2020, and as only a prediction up to 2030 has been analyzed and elaborated. Impact of nitrogen oxides reduction methods on the specific fuel consumption of the marine diesel engine has been evaluated. Additional emission of some gases to the atmosphere due to the implementation of reduction methods has been determined. EGR and SCR systems have got a lot of imperfections: required to install additional reduction systems (investment cost, required volume in the engine room), need maintenance and operation costs, produced wastes during treatment process. The estimated additional cost is about 0.8 USD/MWh of produced energy, taking into account only the cost of excessive used fuel. The whole increased cost may reach the level two-three times more due to cleaning systems investment costs, their operational cost and waste disposal. It has been the one of the reasons of worsening the transport effectiveness and competitiveness.

CHARACTERIZING ONE-LAYER ASSOCIATIVE NEURAL NETWORKS WITH OPTIMAL NOISE-REDUCTION ABILITY

1992 ◽  
Vol 06 (05) ◽  
pp. 1009-1025 ◽  
Author(s):  
TAO WANG ◽  
XIAOLIANG XING ◽  
XINHUA ZHUANG
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Cost Function ◽  
Noise Reduction ◽  
Gradient Descent ◽  
Storage Capacity ◽  
Learning Algorithm ◽  
Optimal Learning ◽  
The Neural Network ◽  
The Cost

In this paper, we describe an optimal learning algorithm for designing one-layer neural networks by means of global minimization. Taking the properties of a well-defined neural network into account, we derive a cost function to measure the goodness of the network quantitatively. The connection weights are determined by the gradient descent rule to minimize the cost function. The optimal learning algorithm is formed as either the unconstraint-based or the constraint-based minimization problem. It ensures the realization of each desired associative mapping with the best noise reduction ability in the sense of optimization. We also investigate the storage capacity of the neural network, the degree of noise reduction for a desired associative mapping, and the convergence of the learning algorithm in an analytic way. Finally, a large number of computer experimental results are presented.

scholarly journals PSO–SOM Neural Network Algorithm for Series Arc Fault Detection

2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Na Qu ◽  
Jiatong Chen ◽  
Jiankai Zuo ◽  
Jinhai Liu
Keyword(s):  
Neural Network ◽  
Classification Accuracy ◽  
Pso Algorithm ◽  
Self Organization ◽  
Detection Accuracy ◽  
Competitive Neural Network ◽  
Neural Network Algorithm ◽  
Som Network ◽  
Som Neural Network ◽  
Self Learning

Self-organizing feature map (SOM) neural network is a kind of competitive neural network with unsupervised learning. It has the strong abilities of self-organization and self-learning. However, the classification accuracy of SOM neural network may decrease when the features of tested object are not obvious. In this paper, the particle swarm optimization (PSO) algorithm is used to optimize the weight values of SOM network. Three indexes, i.e., intra-class density, standard deviation and sample difference, are used to judge the weight value, which can improve the classification accuracy of the SOM network. PSO–SOM network is applied to the detection of series arc fault in electrical circuits and compared with conventional SOM network and learning vector quantization (LVQ) network. The detection accuracy of the PSO–SOM network is 95%, which is higher than conventional SOM network and LVQ network.

NEURAL NETWORK CONTROL SYSTEMS THAT LEARN TO PERFORM APPROPRIATELY

2001 ◽  
Vol 11 (01) ◽  
pp. 79-88 ◽  
Author(s):  
JOHN A. BULLINARIA ◽  
PATRICIA M. RIDDELL
Keyword(s):  
Neural Network ◽  
Control Systems ◽  
Gradient Descent ◽  
Learning Algorithm ◽  
Network Control ◽  
Oculomotor Control ◽  
Evolution And Development ◽  
Learning Rates ◽  
Network Control Systems ◽  
The Cost

Setting up a neural network with a learning algorithm that determines how it can best operate is an efficient way to formulate control systems for many engineering applications, and is often much more feasible than direct programming. This paper examines three important aspects of this approach: the details of the cost function that is used with the gradient descent learning algorithm, how the resulting system depends on the initial pre-learning connection weights, and how the resulting system depends on the pattern of learning rates chosen for the different components of the system. We explore these issues by explicit simulations of a toy model that is a simplified abstraction of part of the human oculomotor control system. This allows us to compare our system with that produced by human evolution and development. We can then go on to consider how we might improve on the human system and apply what we have learnt to control systems that have no human analogue.

scholarly journals Modeling and prediction for diesel performance based on deep neural network combined with virtual sample

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Hainan Zheng ◽  
Honggen Zhou ◽  
Chao Kang ◽  
Zan Liu ◽  
Zhenhuan Dou ◽  
...  
Keyword(s):  
Neural Network ◽  
Diesel Engine ◽  
Deep Neural Network ◽  
Performance Models ◽  
Virtual Sample ◽  
Network Method ◽  
Key Factor ◽  
Marine Diesel ◽  
The Cost ◽  
Generation Technology

AbstractThe performance models are the critical step for condition monitoring and fault diagnosis of diesel engines, and are an important bridge to describe the link between input parameters and targets. Large-scale experimental methods with higher economic costs are often adopted to construct accurate performance models. To ensure the accuracy of the model and reduce the cost of the test, a novel method for modeling the performances of marine diesel engine is proposed based on deep neural network method coupled with virtual sample generation technology. Firstly, according to the practical experience, the four parameters including speed, power, lubricating oil temperature and pressure are selected as the input factors for establishing the performance models. Besides, brake specific fuel consumption, vibration and noise are adopted to assess the status of marine diesel engine. Secondly, small sample experiments for diesel engine are performed under multiple working conditions. Moreover, the experimental sample data are diffused for obtaining valid extended data based on virtual sample generation technology. Then, the performance models are established using the deep neural network method, in which the diffusion data set is adopted to reduce the cost of testing. Finally, the accuracy of the developed model is verified through experiment, and the parametric effects on performances are discussed. The results indicate that the overall prediction accuracy is more than 93%. Moreover, power is the key factor affecting brake specific fuel consumption with a weighting of 30% of the four input factors. While speed is the key factor affecting vibration and noise with a weighting of 30% and 30.5%, respectively.

Sign in / Sign up

Export Citation Format

Share Document