Journal of Applied Research on Industrial Engineering
Volume:8 Issue: 3, Summer 2021

Many factors may influence the accuracy of part count by weight, but one of the most ubiquitous and often overlooked causes is part variability. In this work, experiments were performed to quantify the weight variation of injection molded parts and to measure the maximum number of those parts that could be accurately counted by weight. A model and working equations that account for tolerances of both the mold cavity and plastic were derived to estimate how part variability affects the weight counting of a single set of parts. Within experimental uncertainty, the model gave estimates that agreed with the actual part counts.

This paper describes a new technique for implementing an Artificial Neural Network (ANN) using Field Programmable Gate Array (FPGA). The goal is design the Low Drop Output (LDO) voltage-regulator circuit with the desired features depending on the application. (The first novelty is designing an LDO with variable features). Voltage regulators bring voltage changes to a stable and acceptable level, especially for products using portable devices. The fragmentary neural network algorithm is modeled using the Xilinx generator system and it can be implemented in Xilinx FPGA (the second novelty is implanting fragmentary ANN in FPGA for parallel computations and real time design). The neural network is trained using the levenberg-Marquardt algorithm which is the data collected from HSPICE software. In Matlab, the tangent-sigmoid function is used as a neuron activation function, but the block set provided by the Xilinx generator system does not have a tangent-sigmoid operator, so the tan-sigmoid operator is modeled on the Maclaurin expansion (the third novelty is using Maclaurin series for approximation function along with the reduction of connections in the neural network to reduce many blocks in FPGA). In this paper, the similarity of the tangent-sigmoid function produced using Matlab and the approximation of the performance of this function using the Maclaurin series are shown. When the inputs are between -0.5 to +0.5, the simulated results show that the absolute error between the values of tan-sigmoid function based on Matlab and Xilinx System Generator using Maclaurin power series are not more than 0.17%. The performance modeling of the system generator with 0.996515% accuracy of Matlab modeling.

In composite production, hydrophilic nature of plant fibres results in poor interfacial adhesion between polar-hydrophilic fibre and non-polar-hydrophobic matrix and dimensional instability of the resulting product. Therefore, there is need to reduce the percentage of water absorption of natural fibres before incorporating them in composite. Bamboo fibre polyester composites were subjected to three modification treatments which are mercerization, acetylation and mercerized-acetylation at fibre content levels of 10, 20 30, 40 and 50 wt % in order to reduce the moisture absorption of the composites. Taguchi method was used to optimize the parameter settings for reduced moisture absorption. The diffusion coefficient, absorption coefficient and permeability coefficient of the composites for each fibre treatment was used to study the absorption kinetics. Mercerized-acetylated fibre composites show the best moisture absorption performance among all the considered treatments. The application of optimization techniques and statistical analysis was used to improve the processes of bamboo fibre polyester composite production in order to achieve improved moisture degradation behavior of the composite and promote the expansion of natural fibres application in engineering.

Nowadays, many accidents, malfunctions, and quality defects are happening in production systems due to Human Errors Probability (HEP). Human Reliability Analysis (HRA) methods have been proposed to measure the HEP based on Performance Shaping Factors (PSFs), but these methods do not have a procedure to select the effective PSFs and consider the PSFs dependency. In this paper, we propose an Artificial Neural Network based Human Reliability Analysis (ANNHRA) in cooperation with Response Surface Method (RSM). This framework uses the advantage Systematic Human Error Reduction and Prediction Approach (SHERPA) method to quantify the PSFs and the ANN and RSM to consider the PSFs dependency and select the most effective PSFs. This framework decreases the time and cost and increases the accuracy of HRA. The proposed framework has been applied to a real case and the provided results show that human reliability can be calculated more effectively using ANNHRA framework.

The aim of this paper is to introduce a formulation of fully fuzzy transportation problems involving pentagonal and hexagonal fuzzy numbers for the transportation costs and values of supplies and demands.  We introduce new technique for improve methods for solving the fully fuzzy transportation problems with parameters given as the pentagonal and hexagonal fuzzy numbers. Algorithms are proposed to find the non-negative fuzzy optimal solution of fully fuzzy transportation problems with parameters given as pentagonal and hexagonal fuzzy numbers. This technique is also best optimal solution in the literature and illustrated with numerical examples.

In conventional DEA models, it is supposed real-valued inputs and outputs while every measure must be determined as an input or output. However, in some cases, there are flexible measures which can only take integer values in two-stage network DEA. In all previous researches has not been mentioned the classification flexible measures while some inputs, outputs, and flexible measures can only take integer values in two-stage network DEA. So in this paper, we propose integer-valued FNDEA approach is based on envelopment form of CCR that evaluates the relative efficiency of DMUs and determines the status of flexible measures in the presence of integer data in basic and general two-stage network structures. Our model can determine projection points of inputs, outputs, and flexible measures in the presence of integer data in two-stage network DEA. Numerical examples are used to illustrate the procedure.

Bending is one of the most frequently used processes in the sheet metal products industry. The major users are mainly the automotive, aeronautics and electrical engineering industries. It is necessarily a cold forming operation of a flat material, with or without lubricant, obtained notably by exceeding its elastic limit. After retraction of the tools and relaxation of the stresses, a springback consequently occurs and a permanent deformation persists causing certain geometric modifications of the product. As a matter of fact, this phenomenon, will absolutely affect the angle and curvature of the bend, for such reason it must be taken into consideration in order to manufacture sheet metal parts bent within acceptable tolerance limits. However, the value of this springback is influenced by a multiplicity of process parameters, such as the thickness of the sheet, the hold time of the bending operation, the material properties and last but not least the depth of strike of the tool. In this paper, we have developed a model for predicting springback in the air V-bending process using the design of experiments method. Four three-level factors were considered in order to model springback in using the response surface method (RSM). The experimental tests were carefully carried out on a HACO press brake and on aluminum, ordinary steel and stainless steel specimens with different thicknesses. The in-depth study of the response surfaces to the different tests with the method of analysis of variance (ANOVA), allowed us to determine a robust empirical model linking the springback to the variables of the study. In addition, several relevant numerical simulations using the finite element method (FEM) with software (Abaqus) were performed to predict the evolution of springback when varying the parameters in the field of design of experiments. In fact, the comparison of the values predicted by the two approaches shows a satisfactory agreement.