Showing 7 results for Khani
Mohammad Reza Mehregan, Arman Rezasoltani, Amir Mohammad Khani, Ali Hosseinzade Kashan,
Volume 0, Issue 0 (IN PRESS 2025)
Abstract
In the modern industrial view, it is strategically imperative to predict failure of industrial machinery with a view to reducing the occurrence of unexpected failures and enhancing operational efficiency. This study seeks to introduce a new hybrid machine learning model for predictive maintenance, combining the use of deep learning and advanced ensemble machine learning models. The model presented follows a stacking ensemble structure, where XGBoost, CatBoost, Gradient Boosting, and a deep neural network are base learners. Thereafter, the LightGBM, acting as a meta-model, is used to collect its predictions. Further, in this study, the Optuna hyperparameter optimization framework is employed to optimize the hyperparameters automatically, and the NearMiss algorithm solves the class imbalance problem by enhancing the representation of the minority class and removing the bias in favor of the majority class. As can be seen in the experimental results, the combined model outperforms the single models, achieving an outstanding accuracy of 96.17%. This is followed by a precision of 97.86%, a recall of 94.4%, and an F1 score of 96.1%. It is worth noting that though the XGBoost models' independent results were high (with an F1 score of 89/41) and better than the 16 individual models studied in this paper and regarded as a comparison to the hybrid model, the hybrid model significantly defeated the independent models by nearly 7 percentage points, hence the strong suit of the smart ensemble framework in model combination. The model has been tried using industrial data with 10000 records of a milling machine system, which is representative of most industrial machinery. The model aids in making decisions in preventive maintenance processes in a more informed and timely way by detecting failures accurately before they happen, avoiding unwanted situations of unplanned downtime and operation costs. One can arrive at the conclusion based on these results that the mentioned hybrid model can offer a solid and workable way of predicting failures in the industrial context and can also be integrated into the actual maintenance processes without any issues.
H. Arabi, M.t Salehi, B. Mirzakhani, M.r. Aboutalebi , S.h. Seyedein , S. Khoddam,
Volume 19, Issue 5 (IJES 2008)
Abstract
Hot torsion test (HTT) has extensively been used to analysis and physically model flow behavior and microstructure evolution of materials and alloys during hot deformation processes. In this test, the specimen geometry has a great influence in obtaining reliable test results. In this paper, the interaction of thermal-mechanical conditions and geometry of the HTT specimen was studied. The commercial finite element package ANSYS was utilized for prediction of temperature distribution during reheating treatment and a thermo-rigid viscoplastic FE code, THORAX.FOR, was used to predict thermo-mechanical parameters during the test for API-X70 micro alloyed steel. Simulation results show that no proper geometry and dimension selection result in non uniform temperature within specimen and predicted to have effects on the consequence assessment of material behavior during hot deformation. Recommendations on finding proper specimen geometry for reducing temperature gradient along the gauge part of specimen will be given to create homogeneous temperature as much as possible in order to avoid uncertainty in consequent results of HTT.
Hosein Saghaei, Hosein Didehkhani ,
Volume 20, Issue 4 (IJIEPR 2010)
Abstract
This research aims at presenting a fuzzy model to evaluate and select Six-Sigma projects. For this purpose, a model of fuzzy analytic network process (ANP) was designed to consider the relation and mutual impact among the factors. In order to evaluate the projects, nine sub-criteria were considered which were classified into three categories of business, finance and procedural ones. Also to consider the ambiguity related to the pairwise comparisons being used in the research, the fuzzy logic was employed. The fuzzy algorithm being used is in the method of Mikhailov which has various advantages such as the presentation of consistency index and weight vector in a crisp form. At the end, in order to show the applicability, the proposed methodology was applied in an automobile part manufacturing firm.
T.b. Pankhania, V.k. Modi,
Volume 22, Issue 3 (IJIEPR 2011)
Abstract
For any organization sound marketing strategy and quality assurance play vital role in the growth of the organization. The price, quality and service, service centers, friendly attitude, Discounts on sales, esthetics, store location and appearance, ease of operations, guarantees and warranties, adopting new ideas, and flexible payments terms were considered to study the perceptions of the respondents. The ultimate aim is to uphold the turnover of the organization and to create good market penetration of the goods produced in highly competitive business world .
Mohammad Khalilzadeh, Alborz Hajikhani, Seyed Jafar Sadjadi,
Volume 28, Issue 1 (IJIEPR 2017)
Abstract
The present paper aims to propose a fuzzy multi-objective model to allocate order to supplier in uncertainty conditions and for multi-period, multi-source, and multi-product problems at two levels with wastages considerations. The cost including the purchase, transportation, and ordering costs, timely delivering or deference shipment quality or wastages which are amongst major quality aspects, partial coverage of suppliers in respect of distance and finally, suppliers weights which make the products orders more realistic are considered as the measures to evaluate the suppliers in the proposed model. Supplier's weights in the fifth objective function are obtained using fuzzy TOPSIS technique. Coverage and wastes parameters in this model are considered as random triangular fuzzy number. Multi-objective imperial competitive optimization (MOICA) algorithm has been used to solve the model,. To demonstrate applicability of MOICA, we applied non-dominated sorting genetic algorithm (NSGA-II). Taguchi technique is executed to tune the parameters of both algorithms and results are analyzed using quantitative criteria and performing parametric.
Ali Salmasnia, Mohammad Reza Maleki, Esmaeil Safikhani,
Volume 34, Issue 2 (IJIEPR 2023)
Abstract
In some applications, the number of quality characteristics is larger than the number of observations within subgroups. Common multivariate control charts to monitor the variability of such high-dimensional processes are unsuitable because the sample covariance matrix is not positive semi-definite and invertible. Moreover, the impact of gauge imprecision on detection capability of multivariate control charts under high-dimensional setting has been clearly neglected in the literature. To overcome these shortcomings, this paper develops a ridge penalized likelihood ratio chart for Phase II monitoring of high-dimensional process in the presence of measurement system errors. The developed control chart departures from the assumption of sparse variability shifts in which the assignable cause can only affects a few elements of the covariance matrix. Then, to compensate for the adverse impact of gauge impression, the developed chart is extended by employing multiple measurements on each sampled item. Simulation studies are carried out to study the impact of imprecise measurements on detectability of the developed monitoring scheme under different shift patterns. The results show that the gauge inability negatively affects the run-length distribution of the developed control chart. It is also found that the extended chart under multiple measurements strategy can effectively reduce the error impact.
Amin Amini, Alireza Alinezhad, Davood Gharakhani,
Volume 35, Issue 2 (IJIEPR 2024)
Abstract
The selection of a sustainable supplier is a multi-criteria decision-making issue that covers a range of criteria (quantitative-qualitative). Selecting the most eco-friendly suppliers requires balancing tangible and intangible elements that may be out of sync. The problem gets more complicated when volume discounts are taken into account, as the buyer needs to decide between two issues: 1) What are the best sustainable suppliers? 2) Which amount needs to be bought from each of the selected eco-friendly suppliers? In current study a combined attitude of best-worst method (BWM) ameliorated via multi-objective mixed integer programming (MOMIP) and rough sets theory is developed. The aim of this work is to contemporaneously ascertain the order quantity allocated to these suppliers in the case of multiple sourcing, multiple products with multiple criteria and with capacity constraints of suppliers and the number of suppliers to employ. In this situation, price reductions are offered by suppliers based on add up commerce volume, not on the amount or assortment of items acquired from them. Finally, a solution approach is proposed to solve the multi-objective model, and the model is demonstrated using a case study in Iran Khodro Company (IKCO). The results indicate that ISACO is the most sustainable supplier and the most orders are assigned to this supplier.
