Application of Multiple Regression and Adaptive Neuro-Fuzzy Inference System for Prediction of Surface Roughness in EDM

2012 ◽  
Author(s):  
S. S. Baraskar ◽  
S. S. Banwait
Keyword(s):  
Experimental Data ◽  
Surface Roughness ◽  
Multiple Regression ◽  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Input Output ◽  
Output Data ◽  
Data Set ◽  
Inference System ◽  
Neuro Fuzzy

A manufacturing system is oriented towards higher production rate, better quality and reduced cost and time to make a product. Surface roughness is an index parameter for determining the quality of a machined product and is influenced by various input process parameters. Surface roughness prediction in Electrical Discharge Machine (EDM) is being attempted with many methodologies, yet there is a need to develop robust, autonomous and accurate predictive system. This work proposes the application of hybrid intelligent technique, multiple regression and adaptive neuro-fuzzy inference system (ANFIS) for prediction of surface roughness in EDM. An experimental data set is obtained with current, pulse-on time and pulse-off time as input parameters and surface roughness as output parameter. Central composite rotatable design was used to plan the experiments. Multiple regression model is developed using the experimental data, to generate additional input-output data set. The input-output data set is used for training and validation of the proposed technique. After validation, data are forwarded for prediction of surface roughness. The proposed hybrid model for the prediction of surface roughness has very good agreement with the experimental results.

Adaptive Neuro-Fuzzy Inference System Modelling of Surface Roughness in High Speed Turning of AISI P 20 Tool Steel

2011 ◽  
Vol 314-316 ◽  
pp. 341-345
Author(s):  
Bo Di Cui
Keyword(s):  
Experimental Data ◽  
Surface Roughness ◽  
Tool Steel ◽  
Fuzzy Inference System ◽  
High Speed ◽  
Fuzzy Inference ◽  
System Modelling ◽  
Inference System ◽  
High Speed Turning ◽  
Neuro Fuzzy

Accurate predictive modelling is an essential prerequisite for optimization and control of production in modern manufacturing environments. In this paper, an adaptive neuro-fuzzy inference system (ANFIS) model was developed to predict the surface roughness in high speed turning of AISI P 20 tool steel. Experiments were designed and performed to collect the training and testing data for the proposed model based on orthogonal array. For decreasing the complexity of the ANFIS structure, principal component analysis (PCA) was used to deal with the experimental data. The comparison between predictions and experimental data showed that the proposed method was both effective and efficient for modelling surface roughness.

Prediction of Concrete Strength Using Fuzzy Neural Networks

2011 ◽  
Vol 243-249 ◽  
pp. 6121-6126 ◽  
Author(s):  
Jing Xu ◽  
Xiu Li Wang
Keyword(s):  
Neural Networks ◽  
Compressive Strength ◽  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Concrete Strength ◽  
Fuzzy Neural Networks ◽  
Output Data ◽  
Inference System ◽  
Neuro Fuzzy ◽  
Fuzzy Neural

The purpose of this paper is to develop the Ⅰ-PreConS (Intelligent PREdiction system of CONcrete Strength) that predicts the compressive strength of concrete to improve the accuracy of concrete undamaged inspection. For this purpose, the system is developed with adaptive neuro－fuzzy inference system (ANFIS) that can learn cube test results as training patterns. ANFIS does not need a specific equation form differ from traditional prediction models. Instead of that, it needs enough input-output data. Also, it can continuously re-train the new data, so that it can conveniently adapt to new data. In the study, adaptive neuro－fuzzy inference system (ANFIS) based on Takagi-Sugeno rules is built up to prediction concrete strength. According to the expert experience, the relationship between the rebound value and concrete strength tends to power function. So the common logarithms of rebound value and strength value are used as the inputs and outputs of the ANFIS. System parameter sets are iteratively adjusted according to input and output data samples by a hybrid-learning algorithm. In the system, in order to improve of the ANFIS, condition parameter sets can be determined by the back propagation gradient descent method and conclusion parameter sets can be determined by the least squares method. As a result, the concrete strength can be inferred by the fuzzy inference. The method takes full advantage of the characteristics of the abilities of Fuzzy Neural Networks (FNN) including automatic learning, generation and fuzzy logic inference. The experiment shows that the average relative error of the predicted results is 10.316% and relative standard error is 12.895% over all the 508 samples, which are satisfied with the requirements of practical engineering. The ANFIS-based model is very efficient for prediction the compressive strength of in-service concrete.

scholarly journals Modelling Unconfined Groundwater Recharge Using Adaptive Neuro-Fuzzy Inference System

Processes ◽  
2020 ◽  
Vol 8 (10) ◽  
pp. 1280
Author(s):  
Khaled Mohamed Nabil I. Elsayed ◽  
Rabee Rustum ◽  
Adebayo J. Adeloye
Keyword(s):  
Groundwater Recharge ◽  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Monitoring Site ◽  
Data Set ◽  
Inference System ◽  
The North ◽  
Neuro Fuzzy ◽  
Ground Water Recharge ◽  
Human Thinking

Estimating groundwater recharge using mathematical models such as water budget or soil water balance method has been proved to be very difficult due to the complex, uncertain multidimensional nature of the process, despite the simplicity of the concept. Artificial Intelligence (AI) techniques have been proposed to deal with this complexity and uncertainty in a similar way to human thinking and reasoning. This study proposed the use of the Adaptive Neuro-Fuzzy Inference System (ANFIS) to model unconfined groundwater recharge using a set of data records from Kaharoa monitoring site in the North Island of New Zealand. Fifty-three data points, comprising a set of input parameters such as rainfall, temperature, sunshine hours, and radiation, for a period of approximately four and a half years, have been used to estimate ground water recharge. The results suggest that the ANFIS model is overall a reliable estimator for groundwater recharge, the correlation coefficient of the model reached 93% using independent data set. The method is easy, flexible and reliable; hence, it is recommended to be used for similar applications.

Developing Adaptive Neuro-Fuzzy Inference System for Controlling the Intelligent Universal Transformers in ADA

2012 ◽  
Vol 433-440 ◽  
pp. 3969-3973
Author(s):  
Maryam Sadeghi ◽  
Majid Gholami
Keyword(s):  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Voltage Regulation ◽  
Current Control ◽  
Distribution Automation ◽  
Membership Functions ◽  
Back Propagation Algorithm ◽  
Input Output ◽  
Inference System ◽  
Neuro Fuzzy

This approach is carry out for developing the Adaptive Neuro-Fuzzy Inference System (ANFIS) for controlling the forthcoming Intelligent Universal Transformer (IUT) in regard of voltages and current control in both input and output stages which is optimized by particle swarm optimization. Current or voltages errors and their time derivative have been considered as the inputs of Nero Fuzzy controller for elaborating the firing angles of converters in IUT basic construction. ANFIS constructed from a fuzzy inference system (FIS) in which the membership function parameters are tuned according to the back propagation algorithm or in conjunction to the least squares method. A neural network maps inputs through input membership functions and associated parameters, and output membership functions and associated parameters to outputs which interprets the input-output map. The associated parameters of membership functions change through the learning algorithm by a gradient vector modeling the input output data in case of given parameters. Optimization method will be investigated to adjust the parameters according to error reduction computed by sum of the squared variation from actual outputs to the desired ones. Advanced Distribution Automation (ADA) is the state of art introducing for tomorrows distribution automation with the new invention in management and control. ADA is equipping by the Intelligent Equipment Devices (IED) in which IUT is a key point introducing as an intelligent transformer subjecting for tomorrows distribution automation in the near future. The proposed ANFIS is a control scheme develop for controlling the IUT by bringing the major advantages like harmonic Filtering, voltage regulation, automatic sag correction, energy storage, 48V DC option, three phase outputs in term of one phase input, reliable divers power as 240V 400HZ for communication utilization and two other 240V 60 HZ outputs, dynamic system monitoring and robustness in major disturbances occurred in terms of input and load variation.

The Adaptive Neuro-Fuzzy Inference System (ANFIS) Application for the Ammonium Removal from Aqueous Solution Predicting by Biochar

2018 ◽  
Vol 931 ◽  
pp. 985-990
Author(s):  
Ahmed S. Khalil ◽  
Sergey V. Starovoytov ◽  
Nikolai S. Serpokrylov
Keyword(s):  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Absolute Error ◽  
Pilot Scale ◽  
Fish Farms ◽  
Anfis Model ◽  
Data Set ◽  
Inference System ◽  
Ammonium Removal ◽  
Neuro Fuzzy

The adaptive neuro-fuzzy inference system (ANFIS) model was developed to predict the removal of ammonium () from wastewater. The ANFIS model was developed and validated with a data set from a pilot-scale of adsorption system treating aqueous solutions and wastewater from fish farms. The data sets consist of four parameters, which include pH, temperature, an initial concentration of ammonium and amount of adsorbent. The adsorbent was biochar obtained from rice straw. The ANFIS models performance was assessed through the root mean absolute error (RMSE) and was validated by testing data. The results of the study show that the adaptive neuro-fuzzy inference system (ANFIS) is able to predict the percentage of ammonium removal from adsorption column according to the input variables with acceptable accuracy, suggesting that the adaptive neuro-fuzzy inference system model is a valuable tool for estimating the quality of fish farms water. This model of ANFIS leads to cost reduction because prediction can be done without resorting to efforts that require cost and time.

Sign in / Sign up

Export Citation Format

Share Document