A Neuro-Fuzzy-Regression Algorithm for Improved Prediction of Manufacturing Lead Time with Machine Breakdowns

Asadzadeh, Seyed Mohammad; Azadeh, A.; Ziaeifar, Amin

doi:10.1177/1063293x11424512

Cited by 22 publications

(16 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MLP : Also called multilayer NN with feedforward connections, it is a DL model of excellence that approximates a given function f ( x ) by neurons, where each one in one layer is connected directly to the neurons of the subsequent layer and uses sigmoid activation functions (Asadzadeh et al, 2011; Goodfellow et al, 2016). A feed-forward network is defined as y = f ( x ; normalθ ) that learns the values of the parameter θ , which results in the best approximation function.…”

Section: Methodsmentioning

confidence: 99%

RETRACTED: Deep learning framework for leaf damage identification

Sánchez-DelaCruz

Lopez

Alabazares

et al. 2021

Concurrent Engineering

View full text Add to dashboard Cite

Foliar disease is common problem in plants; it appears as an abnormal change in the plant’s characteristics, such as the presence of lesions and discolorations, among others. These problems may be related to plant growth, which causes a decrease in crop production, impacting the agricultural economy. The causes of leaf damage can be variable, such as bacteria, viruses, nutritional deficiencies, or even consequences of climate change. Motivated to find a solution for this problem, we aim that using image processing and machine learning algorithms (MLA), these symptomatic characteristics of the leaf can be used to classify diseases. Then, contributions of this research are (i) the use of image processing methods in the feature extraction (characteristics), and (ii) the combination of assembled algorithms with deep learning to classify foliar features of Valencia orange (Citrus Sinensis) tree leaves. Combining these two classification approaches, we get optimal rates in binary datasets and highly competitive percentages in multiclass sets. This, using a database of images of three types of foliar damage of local plants. Result of combination of these two classification strategies is an exceptional reliable alternative for leaf damage identification of orange and other citrus plants.

show abstract

Section: Methodsmentioning

confidence: 99%

RETRACTED: Deep learning framework for leaf damage identification

Sánchez-DelaCruz

Lopez

Alabazares

et al. 2021

Concurrent Engineering

View full text Add to dashboard Cite

show abstract

“…The authors evaluate several order dispatching rules to determine which has a positive influence on the accuracy of the forecast of flow time and therefore better predict the tardiness of orders. A more advanced approach is described by Asadzadeh [10] who develops an algorithm that combines artificial neural network theory with a blend of conventional and fuzzy regression. The algorithm described has the role of improving the accuracy of lead time forecasting within a manufacturing environment.…”

Section: Forecasting Of Manufacturing Performance In Manufacturingmentioning

confidence: 99%

“…Forecasting is regarded as the complex procedure through which the upcoming development of an analyzed time series is predicted based on an extrapolation of previously recorded data and on an analysis of the available planned information or future environmental conditions that might affect the respective system [4,[8][9][10]. As portrayed in Figure 1, a forecasting process is usually comprised of two components: an objective mathematical model and subjective human input [9].…”

Section: Forecasting Of Manufacturing Performance In Manufacturingmentioning

confidence: 99%

Early Indication System for Critical Situations in Job-shop Production

2014

View full text Add to dashboard Cite

Job-shop production can be very complex and extremely volatile, especially when part variability is high and orders require an increasingly large amount of processing steps. Achieving a manufacturing performance that is robust against volatilities is of great importance in such systems. We therefore develop an early indication system to detect potentially problematic situations (e.g. processing delays) in a job-shop and to forecast a set of key performance indicators with the aim of increasing the robustness of manufacturing performance by improved reaction possibilities. We compare the results predicted by the early indication system with a discrete-event simulation. Our findings show that 67.8% of the processes that developed issues in the simulated environment were detected by the system beforehand, while the schedule deviation forecasting had an error rate of 34.4%.

show abstract

“…The first study that proposed a neuro-fuzzy regression algorithm to develop a forecasting model of weekly manufacturing lead time estimation, considering the breakdown time indicator in an actual assembly shop -a producer of heavy electric motors -was done by Asadzadeh et al [37]. The input data were the sum of failure times, the sum of repair times, and the sum of processing times, and were collected for 70 weeks with 70 observations.…”

Section: Current Methods To Tackle Uncertaintymentioning

confidence: 99%

Modelling Production Uncertainties Using the Adaptive Neuro-Fuzzy Inference System

Azizi

Ali

Ping

2015

The South African Journal of Industrial Engineering

View full text Add to dashboard Cite

Production throughput measures the performance and behaviour of a production system. Production throughput modelling is complex because of uncertainties in the production line. This study examined the potential application of the adaptive neuro-fuzzy inference system (ANFIS) to modelling the throughput of production under five significant production uncertainties: scrap, setup time, break time, demand, and lead time of manufacturing. The effects of these uncertainties on the production of floor tiles were studied by performing 104 observations on the production uncertainties over 104 weeks, based on a weekly production plan in a tile manufacturing industry. The results of the ANFIS model were compared with the multiple linear regression (MLR) model. The results showed that the ANFIS model was capable of forecasting production throughput under uncertainty with higher accuracy than was the MLR model, indicated by an R-squared of 98 per cent. OPSOMMINGProduksie deurset meet die vertoning en gedrag van 'n produksiesisteem. Produksie deurset modellering is ingewikkeld as gevolg van die onsekerhede in die produksielyn. Hierdie studie ondersoek die toepassing van die aanpasbare neuro-wasige afleidingsisteem om die deurset van produksie onderhewe aan vyf noemenswaardige produksie onsekerhede, naamlik skroot, opstel tyd, breek tyd, aanvraag en die vervaardiging leityd. Die effek van hierdie onsekerhede op die vervaardiging van vloerteëls is ondersoek deur 104 weeklikse observasies op die produksie onsekerhede oor 'n tydperk van 104 weke te neem. Die resultate van die model is vergelyk met 'n meervoudige lineêre regressie model. Die resultate toon dat die aanpasbare neuro-wasige afleidingsisteem in staat was om produksie deurset onderhewe aan onsekerheid te voorspel met 'n hoër akkuraatheid as die meervoudige lineêre regressie model. Dit word aangedui met 'n bepaalheidskoëffisient van 98 persent.

show abstract

A Neuro-Fuzzy-Regression Algorithm for Improved Prediction of Manufacturing Lead Time with Machine Breakdowns

Cited by 22 publications

References 58 publications

RETRACTED: Deep learning framework for leaf damage identification

RETRACTED: Deep learning framework for leaf damage identification

Early Indication System for Critical Situations in Job-shop Production

Modelling Production Uncertainties Using the Adaptive Neuro-Fuzzy Inference System

Contact Info

Product

Resources

About