International Journal of Industrial Engineering: Theory, Applications and Practice
Not a member yet
943 research outputs found
Sort by
Interval Robust Design on Quality Improvement for Non-Normal and Contaminated Responses
No full textThe basis of robust parameter design is the creation of a design that can resist the negative effects caused by uncontrollable or difficult-to-control external and environmental factors, which affect the product parameters in achieving product design during product realization activities. Robustness is the ability of a product or process to be least affected by variabilities caused by external factors. The success of the response surface methodology generally depends on a model chosen to fit the data distribution. Making incorrect assumptions regarding data distribution when creating response surface models can affect the effectiveness of the quality improvement strategy used. Non-normal or contaminated data is a common phenomenon in quality improvement applications. Although non-normal data is common in robust parameter applications, it is often the case that users ignore the underlying distribution shape of the data at the modeling stage and use normal theory techniques naively. This study proposes a dual response surface approach based on robust confidence intervals for cases where the experimental data do not meet normality assumptions or have contaminated data distribution. A new dual response surface methodology is proposed based on modeling the confidence interval, confidence interval, and confidence interval formulations with the response surface methodology. All the proposed methods make the process median unbiased for the mean using the skewness of the experimental data. Two well-known experimental design studies are used to demonstrate the procedure and its advantages
ANALYSIS FOR HEART DISEASE PREDICTION USING DEEP NEURAL NETWORK AND VGG_19 CONVOLUTION NEURAL NETWORK
No full textIn the medical field, the prediction of heart disease has been most complicated in recent times. People in the modern day are dying suddenly from heart disease and cardiac attacks. It is very much important to make decisions for heart disease prediction by providing machine learning, deep learning, and data Mining. For heart disease, there is a vast quantity of information accessible on diagnosis, treatment, ECHO, ECG, and other factors. In this study, a unique CNN-based architecture is used to classify the histopathological pictures in the public health care data set for heart disease using the VGG-19. Before classifying the data, a deep neural network is helpful for choosing and extracting its features. The proposed model has two fully connected layers and fifteen convolutional layers, and the training approach comprises free training of the data. Utilizing two separate optimizers, the various activations are compared with their purpose to identify them accurately. The suggested model outperforms excellent performance in comparison to conventional architectures with an accuracy of 95.46%
RELIABILITY-BASED MAINTENANCE STRATEGY FOR A MILITARY WEAPON SYSTEM – A CASE STUDY
Get PDFMilitary Weapons Systems are currently facing increasing use in a worldwide intensification of military conflicts, leading to various changes to improve and solve problems in logistics operations. The main objective of this paper is to use RCM (Reliability Centered Maintenance) and FMECA (Failure Modes, Effects, and Criticality Analysis) methodology applied to this High-Tech Weapon System to identify the need for spare parts by improving the current maintenance plan. A functional analysis was performed. Then, functional failures, failure modes, and effects are defined. This methodology manages the identified risks, knowing which components have a high failure rate, improving maintenance plans, and identifying the need for spare parts at the earliest possible stage. Thus, the study was supported by “ReliaSoft RCM++” software that facilitates the RCM analysis approach. This software supports all major RCM industry standards such as ATA, MSG-3, MIL-STD-1629A, SAE JA1011, and SAE JA1012 and provides complete capabilities for FMECA. This study aims to identify the systems, subsystems, and components that frequently fail, ensuring operational capability and corrective actions to improve the weapon system’s plans, maintenance schedules, and availability. This technique is powerful as decision support to the Military Logistics Command because it identifies the need for spare parts as early as possible
HUMAN MACHINE INTERFACE DESIGN OF INDUSTRIAL AUTOMATED MACHINE USING SIMATIC SCADA SYSTEM
Get PDFIn an industrial world full of technological advancements where competitiveness is the essential objective, automation has become a fundamental necessity to achieve higher productivity with less chance of error in a limited time. Additionally, regular monitoring of processes is required to improve system performance and ensure employee safety. In this paper, a method for realizing an automated weighing and bagging machine is proposed, and special emphasis is placed on the weighing system. A simulated process prototype based on a SCADA (Supervisory Control and Data Acquisition) system and PLC (Programmable Logic Controller) of weighing and bag packing machines is designed to fill and close bags with the product. Operators can monitor the process and control outputs through the HMI (Human Machine Interface) screen
SPACE-TIME GRAPH-BASED CONVOLUTIONAL NEURAL NETWORKS OF STUDY ON MOVEMENT RECOGNITION OF FOOTBALL PLAYERS
Get PDFBehaviour recognition technology is an interdisciplinary technology, integrating many research achievements in computer vision, deep learning, pattern recognition and other fields. The key information of bone data on human behavior can not only accurately describe the motion posture of the human body in three-dimensional space, but also its rigid connection structure is robust to various external interference factors. However, the behavioral recognition algorithm is influenced by different factors such as background, light and environment, which is easy to lead to unstable recognition accuracy and limited application scenarios. To address this problem, in this paper, we propose a noise filtering algorithm based on data correlation and skeleton energy model filtering, construct a set of football player data sets, using the ST-GCN algorithm to train the skeleton characteristics of football players, and construct a behavior recognition system applied to football players. Finally, by comparing the accuracy of Deep LSTM, 2s-AGCN and the algorithm in this paper, the accuracy of TOP1 and TOP5 is 39.97% and 66.34%, respectively, which are significantly higher than the other two algorithms. It can realize the statistics of athletes and analyze the technical and tactical movements of players on the football field
RELATIONSHIP OF DEW POINT AND AMBIENT TEMPERATURE VARIATION ON WELD QUALITY
Get PDFThis investigation deals with the study of the effect of environmental parameters viz dew point temperature, relative humidity, ambient air temperature, and job surface temperature on robotic MAG (Metal active gas) welded joint quality. Weld samples taken were mass manufacturing welded structures of a heavy-large scale industry, which were further subjected to semi-automatic ultrasonic testing to assess defects within welded joints. The trend of defects observed and recorded after ultrasonic testing of weld joints was co-related with the trend of atmospheric parameters for a span of four years to establish a linear empirical relationship. It has been established that variations in atmospheric parameters resulted in variations in the trend of weld defects. These variations were studied to get the empirical relationship to establish the effect of variation in atmospheric parameters on weld quality or defects in joints. It has been observed that whenever there was a drop in the "difference in ambient air temperature & dew point temperature, especially less than 5", a drop in ultrasonic testing straight pass % was observed than the average value
A HYBRID MCDM METHOD TO IDENTIFY CRITICAL FACTORS OF FOREIGN DIRECT INVESTMENT
No full textThe purpose of this study was to understand the varied importance of critical factors (CFs) that affect foreign direct investment (FDI) and optimize the allocation of limited resources to the CFs to increase chances for international business success. We used eclectic theory as a framework. The fuzzy analytic hierarchy process (FAHP) and the concept of the Vlse Kriterijumska Optimizacija Kompromisno Resenje (VIKOR) acceptable advantage were used to obtain the weights of the CFs and to identify the CFs objectively. Sensitivity analysis was performed to optimize the CFs. With the derivation of the CF weights, Taiwanese catering firms (i.e., the focal sample) can improve the allocation of their resources to the CFs to reduce the risk of FDI failure. Management implications, factor path analysis, and study contributions are also discussed
DYNAMIC COLLISION DETECTION OF UNMANNED SHIP BASED ON WIRELESS COMMUNICATION
No full textIn order to improve the detection accuracy of the collision detection system for unmanned ships at sea, this paper proposes a dynamic collision detection method based on improved ZigBee network wireless communication technology. The collision parameter detection model of unmanned ships at sea based on the ZigBee network and wireless communication network control is constructed. The communication network model is established by using wireless sensor network communication and radio frequency identification tag recognition technology. The experimental results show that the system can more accurately analyze and detect the collision of unmanned ships at sea and judge the route information of ships when there are obstacles. The collision dynamic detection accuracy of the system is 25% higher than that of traditional methods on average, and the performance is superior
ANALYZING AIRLINE DELAY PROPAGATION AND DELAY CAUSE USING A GAUSSIAN NETWORK
No full textWe developed a delay propagation model for an airline network using a Gaussian network approach. By analyzing US flight data in a case study, we evaluated the effects of delay propagation within an airline network. The model has several advantages, such as accounting for non-independent and identically distributed delay profiles, providing a more accurate representation of the observed delay propagation process, and identifying weak links in an airline network. Various scenario studies of delay propagation revealed that the Gaussian network model could capture the effect of delay propagation more precisely than previous studies. Moreover, the Gaussian network model could identify weak links through a statistical approach in an airline network. These perspectives may be valuable in developing approaches for managing the delay propagation and alleviating its subsequent effect
SIMULATION META-MODEL OF ASSEMBLY LINE WITH CONWIP CONTROL
Get PDFThis research navigates the application of simulation meta-modeling in understanding and controlling assembly line dynamics. Aimed at unveiling the relationship between input factors and output parameters in a production system, a precise meta-model was devised based on real system data and simulation statistics. The meta-model predicts parameteR-values within a verified validity range, simplifying complex variable relationships for enhanced decision-making in intricate systems. The accuracy of the model was notable within the tested range of CONWIP cards from 1 to 25, showcasing reliable output approximation. This study highlights the classical approach to simulation meta-modeling as cumbersome, propelling the quest for further simplification in analyzing complex production systems. The utilization of simulation meta-modeling emerged as a pivotal tool for validating complex simulation models and swiftly testing system sensitivity to input factor alterations. Noteworthy findings include the identification of an optimal number of CONWIP cards for maximizing throughput without excessive increases in Work-In-Progress or throughput time. The research also underscores the potential of 5th-degree polynomial models in approximating production performance and throughput time accurately, offering robust tools for informed decision-making. This venture marks a significant stride towards a more streamlined, accurate, and efficient analysis of complex production systems, showcasing the promising applicability of simulation meta-modeling in industrial engineering and production management