• International Journal of Internet, Broadcasting and Communication
• /
• v.9 no.2
• /
• pp.20-26
• /
• 2017

Process control is crucial in many industries, especially in semiconductor manufacturing. In such large-volume multistage manufacturing systems, a product has to go through a very large number of processing steps with reentrant) before being completed. This manufacturing system has many machines of different types for processing a high mix of products. Each process step has specific quality standards and most of them have nonlinear dynamics due to physical and/or chemical reactions. Moreover, many of the processing steps suffer from drift or disturbance. To assure high stability and yield, on-line quality monitoring of the wafers is required. In this paper we develop a real-time fault detection system on semiconductor manufacturing process. Proposed system is superior to other incremental fault detection system and shows similar performance compared to batch way.

• Journal of Welding and Joining
• /
• v.28 no.4
• /
• pp.81-86
• /
• 2010

In resistance spot welding, regardless of the optimal condition, bad weld quality was still produced due to complicated manufacturing processes such as electrode wear, misalignment between the electrode and workpiece, poor part fit-up, and etc.. Therefore, the goal of this study was to measure the process signal which contains weld quality information, and to develop the process fault monitoring system. Welding force signal obtained through variety experimental conditions was analyzed and divided into three categories: good, shunt, and poor fit-up group. And then a monitoring algorithm made up of an artificial neural network that could estimate the process fault of each different category based on pattern was developed.

• Journal of the Korean Institute of Gas
• /
• v.5 no.2 s.14
• /
• pp.1-8
• /
• 2001

Fault tree construction for hazard assessment requires so much time and labor, so it is very difficult to be applied to the large scale chemical plant. In this study, for the synthesis of fault tree in chemical processes, the object-oriented knowledge framework is proposed to represent the deviations of process variables in the equipment and cause-consequence relationship with equipment faults. The cause of fault is searched by using the object-oriented modeling of equipments and the connectivity among equipments, and then a fault tree is synthesized. we have discussed the performance of the methodology on nitric acid cooling process to evaluate its effectiveness.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.15 no.4
• /
• pp.23-29
• /
• 2016

Rotary machine is major equipment in industry. The rotary machine is applied for a machine tool, ship, vehicle, power plant, and so on. But a spindle fault increase product's expense and decrease quality of a workpiece in machine tool. A turbine in power plant is directly connected to human safety. National crisis could be happened by stopping of rotary machine in nuclear plant. Therefore, it is very important to know rotary machine condition in industry field. This study mentioned fault diagnosis algorithm with statistical parameter and empirical mode decomposition. Vibration locations can be found by analyze kurtosis of data from triaxial axis. Support vector of data determine threshold using hyperplane with fault location. Empirical mode decomposition is used to find fault caused by intrinsic mode. This paper suggested algorithm to find direction and causes from generated fault.

• Transactions on Electrical and Electronic Materials
• /
• v.6 no.6
• /
• pp.262-271
• /
• 2005

In order to achieve timely and accurate fault detection of plasma etching process, neural network based time series modeling has been applied to reactive ion etching (RIE) using two different in-situ plasma-monitoring sensors called optical emission spectroscopy (OES) and residual gas analyzer (RGA). Four different subsystems of RIE (such as RF power, chamber pressure, and two gas flows) were considered as potential sources of fault, and multiple degrees of faults were tested. OES and RGA data were simultaneously collected while the etching of benzocyclobutene (BCB) in a $SF_6/O_2$ plasma was taking place. To simulate established TSNNs as incipient fault detectors, each TSNN was trained to learn the parameters at t, t+T, ... , and t+4T. This prediction scheme could effectively compensate run-time-delay (RTD) caused by data preprocessing and computation. Satisfying results are presented in this paper, and it turned out that OES is more sensitive to RF power and RGA is to chamber pressure and gas flows. Therefore, the combination of these two sensors is recommended for better fault detection, and they show a potential to the applications of not only incipient fault detection but also incipient real-time diagnosis.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.64 no.1
• /
• pp.35-40
• /
• 2015

Generators are the most complex and expensive single element in a power system. The generator protection relays should to minimize damage during fault states and must be designed for maximum reliability. A conventional CDR(Current Differential Relaying) technique based on DFT(Discrete Fourier Transform) filter have the disadvantages that the time information can lead to loss in the process of converting the signal from the time domain to the frequency domain. A WT(Wavelet transform) and WT analysis is known that it is possible with the local analysis of the fault and transient signal. In this paper, to overcome the defects in the DFT process, an application of WT for fault detection of generator is presented. This paper describes an selection of mother Wavelet to detect faults of generator. Using collected data from the fault simulation with ATPdraw, we analyzed the several mother Wavelet through the course of MLD(multi-level decomposition) using MATLAB software. Finally, it can be seen that the proposed technique using detail coefficient of Daubechies level 2 which can be fault discriminant of generator.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.959-964
• /
• 1993

We developed fault diagnosis fuzzy expert system for ACS(Advanced Control System). ACS is a DCS(Distributed Control System) with advanced control algorithm fault tolerance capabilities, fault diagnosis functions, and so on. Fuzzy expert system developed for an ACS in this paper gives an operator alarm signal depending on the state of process value and manipulated value, and the cause of alarm in real time. Simple experiment result with several rules for the-fault-diagnosis of drum level loop in Seoul-Power-Plant.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.02a
• /
• pp.239-240
• /
• 2012

With advancements in semiconductor device technologies, manufacturing processes are getting more complex and it became more difficult to maintain tighter process control. As the number of processing step increased for fabricating complex chip structure, potential fault inducing factors are prevail and their allowable margins are continuously reduced. Therefore, one of the key to success in semiconductor manufacturing is highly accurate and fast fault detection and classification at each stage to reduce any undesired variation and identify the cause of the fault. Sensors in the equipment are used to monitor the state of the process. The idea is that whenever there is a fault in the process, it appears as some variation in the output from any of the sensors monitoring the process. These sensors may refer to information about pressure, RF power or gas flow and etc. in the equipment. By relating the data from these sensors to the process condition, any abnormality in the process can be identified, but it still holds some degree of certainty. Our hypothesis in this research is to capture the features of equipment condition data from healthy process library. We can use the health data as a reference for upcoming processes and this is made possible by mathematically modeling of the acquired data. In this work we demonstrate the use of recurrent neural network (RNN) has been used. RNN is a dynamic neural network that makes the output as a function of previous inputs. In our case we have etch equipment tool set data, consisting of 22 parameters and 9 runs. This data was first synchronized using the Dynamic Time Warping (DTW) algorithm. The synchronized data from the sensors in the form of time series is then provided to RNN which trains and restructures itself according to the input and then predicts a value, one step ahead in time, which depends on the past values of data. Eight runs of process data were used to train the network, while in order to check the performance of the network, one run was used as a test input. Next, a mean squared error based probability generating function was used to assign probability of fault in each parameter by comparing the predicted and actual values of the data. In the future we will make use of the Bayesian Networks to classify the detected faults. Bayesian Networks use directed acyclic graphs that relate different parameters through their conditional dependencies in order to find inference among them. The relationships between parameters from the data will be used to generate the structure of Bayesian Network and then posterior probability of different faults will be calculated using inference algorithms.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.27 no.11
• /
• pp.587-595
• /
• 2015

In this study, fault symptoms were simulated and analyzed for a single-effect absorption chiller. The fault patterns of fault detection parameters were tabulated using the fault symptom simulation results. Fault detection and diagnosis by a process history-based method were performed for the in-situ experiment of a single-effect absorption chiller. Simulated fault modes for the in-situ experimental study are the decreases in cooling water and chilled water mass flow rates. Five no-fault reference models for fault detection of a single-effect absorption chiller were developed using fault-free steady-state data. A sensitivity analysis of fault detection using the normalized distance method was carried out with respect to fault progress. When mass flow rates of the cooling and chilled water decrease by more than 19.3% and 17.8%, respectively, the fault can be detected using the normalized distance method, and COP reductions are 6.8% and 4.7%, respectively, compared with normal operation performance. The pattern recognition method for fault diagnosis of a single-effect absorption chiller was found to indicate each failure mode accurately.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.368-369
• /
• 2011

This article suggests an online-based remote fault current mode discrimination method in order to identify the causes of the power line faults with various causes. For that, it refers to existing cause identification methods and categorizes modes by fault causes based on statistical techniques beforehand and performs the pretreatment process of fault currents by each cause acquired from the fault recorder into a topological plane in order to extract the characteristics of fault currents by each cause. After that, for the fault mode categorization, it discriminates modes by each cause using data by each cause as leaning data through utilizing RBF network based on FCM allowing self-organization in deciding the middle layer. And then it tests the validity of the suggested method as applying it to the data of the actual fault currents acquired from the fault recorder in the electric power transmission center.