A Cost-Driven Design Methodology for Additive Manufactured Variable Platforms in Product Families

2016 ◽  
Vol 138 (4) ◽  
Author(s):  
Xiling Yao ◽  
Seung Ki Moon ◽  
Guijun Bi
Keyword(s):  
Design Methodology ◽  
Fuzzy Inference ◽  
Production Costs ◽  
Activity Based Costing ◽  
Platform Design ◽  
Product Families ◽  
Inference System ◽  
Design Changes ◽  
Wide Range ◽  
Functional Part

Additive manufacturing (AM) has evolved from prototyping to functional part fabrication for a wide range of applications. Challenges exist in developing new product design methodologies to utilize AM-enabled design freedoms while limiting costs at the same time. When major design changes are made to a part, undesired high cost increments may be incurred due to significant adjustments of AM process settings. In this research, we introduce the concept of an additive manufactured variable product platform and its associated process setting platform. Design and process setting adjustments based on a reference part are constrained within a bounded feasible space (FS) in order to limit cost increments. In this paper, we develop a cost-driven design methodology for product families implemented with additive manufactured variable platforms. A fuzzy time-driven activity-based costing (FTDABC) approach is introduced to estimate AM production costs based on process settings. Time equations in the FTDABC are computed in a trained adaptive neuro-fuzzy inference system (ANFIS). The process setting adjustment's FS boundary is identified by solving a multi-objective optimization problem. Variable platform design parameter limitations are computed in a Mamdani-type expert system, and then used as constraints in the design optimization to maximize customer perceived utility. Case studies on designing an R/C racing car family illustrate the proposed methodology and demonstrate that the optimized additive manufactured variable platforms can improve product performances at lower costs than conventional consistent platform-based design.

The Additive Manufacturing Process Setting Feasible Space Exploration and Association With Variable Product Platform Design

2015 ◽  
Author(s):  
Xiling Yao ◽  
Seung Ki Moon ◽  
Guijun Bi
Keyword(s):  
Additive Manufacturing ◽  
Production Cost ◽  
Fuzzy Inference ◽  
Design Parameters ◽  
Product Platform ◽  
Activity Based Costing ◽  
Inference System ◽  
Wide Range ◽  
The Cost ◽  
Feasible Space

Additive manufacturing (AM) has evolved from prototyping to functional part fabrication for a wide range of applications. AM process settings have significant impact to both part quality and production cost, which makes the process setting adjustment a key consideration during product development and manufacturing. This research aims to investigate the relationship among process setting adjustments, costs, and component design parameters. Platform-based product family design and process family planning are used in this research as the strategy to provide product diversity while controlling cost. In this paper, the concept of a variable product platform and its corresponding AM process setting variants are proposed to describe the characteristics of additive manufactured platform modules. AM production cost drivers are identified. A Fuzzy Time-Driven Activity-Based Costing (FTDABC) approach is proposed to estimate the cost increment due to process setting adjustments. Time equations in the FTDABC are computed in a trained Adaptive Neuro-Fuzzy Inference System (ANFIS). The process setting adjustment’s feasible space boundary searching is formulated as an optimization problem, with minimizing the cost increment and maximizing the design parameters’ variability as objective functions. The upper and lower limits of variable platform module’s design parameters are mapped from process setting adjustments in a Mamdani-type expert system. The proposed methodology is illustrated in the analysis of a honeycomb-shaped bumper, which is taken as a variable platform module for a family of R/C racing cars. The result provides boundaries for design parameters, which confines the AM-enabled design space for product platform modules.

COVID-19 Outbreak Prediction with Machine Learning

2020 ◽  
Author(s):  
Sina Faizollahzadeh Ardabili ◽  
Amir Mosavi ◽  
Pedram Ghamisi ◽  
Filip Ferdinand ◽  
Annamaria R. Varkonyi-Koczy ◽  
...  
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Fuzzy Inference ◽  
Control Measures ◽  
Future Research ◽  
Complex Nature ◽  
Inference System ◽  
Wide Range ◽  
Standard Models ◽  
High Level

Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed-decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and they are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models needs to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak as an alternative to SIR and SEIR models. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP, and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research. Paper further suggests that real novelty in outbreak prediction can be realized through integrating machine learning and SEIR models.

Real-Time Control of a Rotary Inverted Pendulum using Robust LQR-based ANFIS Controller

2018 ◽  
Vol 19 (3-4) ◽  
pp. 379-389 ◽  
Author(s):  
Ishan Chawla ◽  
Ashish Singla
Keyword(s):  
Fuzzy Inference System ◽  
Inverted Pendulum ◽  
Fuzzy Inference ◽  
Sliding Mode ◽  
Linear Quadratic Regulator ◽  
Linear Quadratic ◽  
Inference System ◽  
Wide Range ◽  
Lqr Controller ◽  
Rotary Inverted Pendulum

AbstractFrom the last five decades, inverted pendulum (IP) has been considered as a benchmark problem in the control literature due to its inherit nature of instability, non-linearity and underactuation. Its applicability in wide range of practical systems, demands the need of a robust controller. It is found in the literature that wide range of controllers had been tested on this problem, out of which the most robust being sliding mode controller while the most optimal being linear quadratic regulator (LQR) controller. The former has a problem of discontinuity and chattering, while the latter lacks the property of robustness. To address the robustness issue in LQR controller, this paper proposes a novel robust LQR-based adaptive neural based fuzzy inference system controller, which is a hybrid of LQR and fuzzy inference system. The proposed controller is designed and implemented on rotary inverted pendulum. Further, to validate the robustness of proposed controller to parametric uncertainties, pendulum mass is varied. Simulation and experimental results show that as compared to LQR controller, the proposed controller is robust to variations in pendulum mass and has shown satisfactory performance.

Analyzing of the sensitivity of chip formation during machining process

Sensor Review ◽  
2017 ◽  
Vol 37 (4) ◽  
pp. 448-450 ◽  
Author(s):  
Srdjan Jovic ◽  
Dragan Lazarevic ◽  
Aleksa Vulovic
Keyword(s):  
Chip Formation ◽  
Design Methodology ◽  
Fuzzy Inference ◽  
Machining Process ◽  
Machining Parameters ◽  
Important Indicator ◽  
Inference System ◽  
Content Type ◽  
Neuro Fuzzy

Purpose The paper aims to analyze chip formation during machining process since it can be a very important indicator for the quality of the machining process, as some chip forms can be undesirable. Design/methodology/approach It is essential to determine the sensitivity of the chip formation on the basis of different machining parameters. The main goal of the study was to analyze the sensitivity of the chip formation during the machining process by using adaptive neuro-fuzzy inference system (ANFIS). Findings According to the results, the chip formation is the most sensitive to feed rate. Originality/value Different cutting tests were performed to monitor the chip formation on the basis of the cutting forces and the cutting displacement. ANFIS was used to estimate the sensitivity of the chip formation during the cutting process on the basis of different parameters.

scholarly journals COVID-19 Outbreak Prediction with Machine Learning

2020 ◽  
Author(s):  
Sina Faizollahzadeh Ardabili ◽  
Amir Mosavi ◽  
Pedram Ghamisi ◽  
Filip Ferdinand ◽  
Annamaria R. Varkonyi-Koczy ◽  
...  
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Fuzzy Inference ◽  
Control Measures ◽  
Future Research ◽  
Complex Nature ◽  
Inference System ◽  
Wide Range ◽  
Standard Models ◽  
High Level

Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed-decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and they are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models needs to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak as an alternative to SIR and SEIR models. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP, and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research. Paper further suggests that real novelty in outbreak prediction can be realized through integrating machine learning and SEIR models.

scholarly journals A Knowledge-based System for Control of the Environment for Single-stem Roses

HortScience ◽  
1996 ◽  
Vol 31 (4) ◽  
pp. 654c-654
Author(s):  
Kuanglin Chao ◽  
Richard S. Gates ◽  
Robert G. Anderson
Keyword(s):  
Fuzzy Inference System ◽  
Crop Production ◽  
Fuzzy Inference ◽  
Knowledge Engineering ◽  
Production Costs ◽  
Economic Optimization ◽  
Inference System ◽  
Knowledge Based ◽  
Conflicting Demands ◽  
Nondestructive Measurements

Knowledge engineering offers substantial opportunities for integrating and managing conflicting demands in greenhouse crop production. A fuzzy inference system was developed to balance conflicting requirements of producing a high-quality, single-stem rose crop while simultaneously controlling production costs of heating and ventilation. An adaptive neuro-fuzzy inference system was built to predict the rose status of `Lady Diana' single-stem roses from nondestructive measurements. The fuzzy inference system was capable of making a critical decision based on the principle of economic optimization. Temperature set points for two greenhouses with similar rose status were treated significantly different by the fuzzy inference system due to differences in greenhouse energy consumption. Moderate reduction in heating energy costs could be realized with the fuzzy inference system.

scholarly journals ANFIS for Tamil Phoneme Classification

2019 ◽  
Vol 8 (6) ◽  
pp. 2907-2914
Keyword(s):  
Neural Networks ◽  
Markov Models ◽  
Fuzzy Inference ◽  
Hybrid Architecture ◽  
Phoneme Recognition ◽  
Inference System ◽  
Phoneme Classification ◽  
Neuro Fuzzy ◽  
Wide Range ◽  
Non Linear Systems

Phoneme recognition is an intricate problem lying under non-linear systems. Most research in this area revolve around try to model the pattern of features observed in the speech spectra with the use of Hidden Markov Models (HMM), various types of neural networks like deep recurrent neural networks, time delay neural networks, etc. for efficient phoneme recognition. In this paper, we study the effectiveness of the hybrid architecture, the Adaptive Neuro-Fuzzy Inference System (ANFIS) for capturing the spectral features of the speech signal to handle the problem of Phoneme Recognition. In spite of a wide range of research in this field, here we examine the power of ANFIS for least explored Tamil phoneme recognition problem. The experimental results have shown the ability of the model to learn the patterns associated with various phonetic classes, indicated with recognition improvement in terms of accuracy to its counterparts.

scholarly journals Predictive Modeling of Henry’s Law Constant in Chemical Structures Using LSSVM and ANFIS Algorithms

2020 ◽  
Author(s):  
Qikai Wang ◽  
Aiqin Yao ◽  
Manouchehr Shokri ◽  
Adrienn A. Dineva
Keyword(s):  
Chemical Structure ◽  
Fuzzy Inference ◽  
Low Cost ◽  
Support Vector ◽  
Inference System ◽  
Chemical Structures ◽  
Neuro Fuzzy ◽  
Wide Range ◽  
Accuracy Of Measurement

Henry’s constants for different existing compounds in water have great importance in transfer calculations. Measurement of these constants face different difficulties including high costs of experiment and low accuracy of measurement apparatus. Due to these facts, proposing a low cost and accurate approach becomes highlighted. To this end, adaptive neuro-fuzzy inference system (ANFIS) and least squares support vector machine (LSSVM) have been used as Henry’s constant predictor tools. The molecular structure of compounds has been used as inputs of models. After training the models, the visual and mathematical studies of outputs have been done. The coefficients of determination of LSSVM and ANFIS algorithms are 0.999 and 0.990 respectively. According to the comprehensiveness of databank and accurate prediction of algorithms, it can be concluded that LSSVM and ANFIS algorithms are accurate methods for prediction of Henry’s constant in wide range of chemical structure of compounds in water.

scholarly journals COVID-19 Outbreak Prediction with Machine Learning

2020 ◽  
Author(s):  
Sina F. Ardabili ◽  
Amir Mosavi ◽  
Pedram Ghamisi ◽  
Filip Ferdinand ◽  
Annamaria R. Varkonyi-Koczy ◽  
...  
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Fuzzy Inference ◽  
Control Measures ◽  
Future Research ◽  
Complex Nature ◽  
Inference System ◽  
Wide Range ◽  
Standard Models ◽  
High Level

Abstract Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed-decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and they are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models needs to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak as an alternative to susceptible-infected-recovered (SIR) and susceptible-exposed-infectious-recovered (SEIR) models. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP, and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research. Paper further suggests that real novelty in outbreak prediction can be realized through integrating machine learning and SEIR models.

Sign in / Sign up

Export Citation Format

Share Document