Optimizing Neural Network Parameters Using Taguchi’s Design of Experiments Approach: An Application for Equivalent Stress Prediction Model of Automobile Chassis

Patel, Tushar M.; Bhatt, Nilesh M.

doi:10.1007/s42154-018-0045-5

Cited by 4 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the network has been trained, the optimal values of the ANN parameters are derived based on the performance statistics. When the Taguchi approach is employed to optimise the parameters, the ANN outperforms random parameter values (Patel and Bhatt, 2018).…”

Section: Introductionmentioning

confidence: 99%

Experimental investigation of emission parameters of diesel engine fueled with various plastic pyrolysis oils

Modi,

Patel

2023

Int. J. Eng. Sci. Tech

View full text Add to dashboard Cite

Plastic has various advantages and is becoming more ubiquitous by the year, yet recycling and disposal remain challenges for the world. We conduct tests in this study to evaluate the appropriateness of various Plastic Pyrolysis Oils (PPOs) made from Low Density Polyethylene (LDPE), High Density Polyethylene (HDPE), and Polypropylene (PP) for diesel engine fuel. Determine which type of plastic pyrolysis oil would function best as an alternative fuel in an experimental investigation. The elemental composition of pyrolysis oil generated from LDPE, HDPE, and PP to diesel was assessed, tabulated, and compared in this study. This study examines emission characteristics (Nitrogen Oxide (NOX), Hydro Carbon (HC), and Carbon Monoxide (CO)) for Diesel, LDPE, HDPE and PP in CI engines using different injection pressure, compression ratio, and load in a specific configuration. In the result of experimental work the CO emission range for diesel and LDPE is exceeded only during overload situations or when the engine load is 100%. The average NOX emission is lowest when PP is used in comparison to other fuels, and the highest NOX emission occurs when LDPE is utilised as a fuel. Increased fumigation rates may be to blame for the rising hydrocarbon content of plastic oil. Unburned hydrocarbon levels are lower at lighter loads due to increased oxygen availability. The use of this whole pyrolysis oil results in a significant decrease in Nitrogen Oxide (NOX), Hydro Carbon (HC), and Carbon Monoxide (CO) exhaust emissions. With the help of this current study. one can solve plastic waste disposal problem and also find any unknown fuel (PPOs) that can be used as an alternative fuel for CI engine or not.

show abstract

Section: Introductionmentioning

confidence: 99%

Experimental investigation of emission parameters of diesel engine fueled with various plastic pyrolysis oils

Modi,

Patel

2023

Int. J. Eng. Sci. Tech

View full text Add to dashboard Cite

show abstract

“…Using a statistical approach to optimize the performance of CNN models not only helps build optimum networks according to required criteria, but also makes models more explainable. Statistical experimental designs have been widely applied to various optimization problems [21][22][23] including parameter optimization of perceptron neural networks [24][25][26]. However, for proper optimization of the hyperparameters of deep learning networks, the design of experiment (DOE) is powerful technique, and, to our knowledge, this has never been investigated.…”

Section: Introductionmentioning

confidence: 99%

A Statistical Approach to Provide Explainable Convolutional Neural Network Parameter Optimization

Akbarzadeh¹,

Ahderom²,

Alameh³

2019

IJCIS

View full text Add to dashboard Cite

Algorithms based on convolutional neural networks (CNNs) have been great attention in image processing due to their ability to find patterns and recognize objects in a wide range of scientific and industrial applications. Finding the best network and optimizing its hyperparameters for a specific application are central challenges for CNNs. Most state-of-the-art CNNs are manually designed, while techniques for automatically finding the best architecture and hyperparameters are computationally intensive, and hence, there is a need to severely limit their search space. This paper proposes a fast statistical method for CNN parameter optimization, which can be applied in many CNN applications and provides more explainable results. The authors specifically applied Taguchi based experimental designs for network optimization in a basic network, a simplified Inception network and a simplified Resnet network, and conducted a comparison analysis to assess their respective performance and then to select the hyperparameters and networks that facilitate faster training and provide better accuracy. The results show that up to a 6% increase in classification accuracy can be achieved after parameter optimization.

show abstract

A Battery Capacity Estimation Framework Combining Hybrid Deep Neural Network and Regional Capacity Calculation Based on Real-World Operating Data

Wang

Liu

et al. 2023

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

Optimizing Neural Network Parameters Using Taguchi’s Design of Experiments Approach: An Application for Equivalent Stress Prediction Model of Automobile Chassis

Cited by 4 publications

References 19 publications

Experimental investigation of emission parameters of diesel engine fueled with various plastic pyrolysis oils

Experimental investigation of emission parameters of diesel engine fueled with various plastic pyrolysis oils

A Statistical Approach to Provide Explainable Convolutional Neural Network Parameter Optimization

A Battery Capacity Estimation Framework Combining Hybrid Deep Neural Network and Regional Capacity Calculation Based on Real-World Operating Data

Contact Info

Product

Resources

About