Equipment Fault Detection Research Articles

Using SVM based method for equipment fault detection in a thermal power plant

Due to the growing demand on electricity, how to improve the efficiency of equipment in a thermal power plant has become one of the critical issues. Reports indicate that efficiency and availability are heavily dependant upon high reliability and maintainability. Recently, the concept of e-maintenance has been introduced to reduce the cost of maintenance. In e-maintenance systems, the intelligent fault detection system plays a crucial role for identifying failures. Data mining techniques are at the core of such intelligent systems and can greatly influence their performance. Applying these techniques to fault detection makes it possible to shorten shutdown maintenance and thus increase the capacity utilization rates of equipment. Therefore, this work proposes a support vector machines (SVM) based model which integrates a dimension reduction scheme to analyze the failures of turbines in thermal power facilities. Finally, a real case from a thermal power plant is provided to evaluate the effectiveness of the proposed SVM based model. Experimental results show that SVM outperforms linear discriminant analysis (LDA) and back-propagation neural networks (BPN) in classification performance.

이중화된 진동 정보 판별 기법과 고장 파형 분류를 이용한 선박 엔진의 고장 감지

현재 진동 정보를 통해 기계 설비의 상태나 고장 유무를 판단하는 연구들이 다수 진행 중에 있는데, 대부분의 연구에서는 설비에 대한 진동을 모니터링하거나 고장 유무를 판별하여 사용자에게 알리는 수준이다. 본 논문에서는 진동 정보 적용 대상을 선박으로 정하고, 진동에 의한 고장 진단과 판별을 보다 정교하게 수행하는 선박 엔진 감지 기법과 시스템을 제안하였다. 일차적으로 이중화된 진동 정보 판별 기법을 적용하여 진동 정보를 확인한 다음에 고장 유무를 검사한다. 만일 고장이 발생한 경우에는 적분을 이용하여 고장 진동 파형에 대한 넓이를 기준으로 어떤 유형의 고장인지를 판별할 수 있는 기법을 적용하였다. 또한 선박의 진동 경향 분석과 엔진 안전 보존을 목적으로 진동 정보를 데이터베이스에 저장하고 추적할 수 있도록 시스템을 구현하였다. 제안 시스템을 선박 엔진의 고장 판별 유무와 고장 진동 파형 감별 인자에 대해 실험을 수행한 결과 고장 판별은 약 98% 정확성을 가졌고 고장 진동 파형 감별에서는 약 72% 정확성을 가졌다. Recently, there have been some researches in the equipment fault detection based on shock and vibration information. Most research of them is based on shock and vibration monitoring to determine the equipment fault or not. Different with engine fault detection based on shock and vibration information we focus on detection of engine for boat and system control. First, it use the duplicated-checking method for shock and vibration information to determine the engine fault or not. If there is a fault happened, we use the integral to determine the error engine shock wave width and detect the fault area. On the other hand, we use the engine trend analysis and standard of safety engine to implement the shock and vibration information database. Our simulation results show that the probability of engine fault determination is 98% and the probability of engine fault detection is 72%

A Reliable Model-Based Approach for the Detection of Equipment Faults in a Chemical Reactor

In this paper a real-time system for detecting changes in dynamic systems is designed. The cumulative sum (CUSUM) or the Page-Hinkley test is intended to reveal any drift from the normal behavior of the process. The process behavior under its normal operating conditions is established by a reliable model. In order to obtain this reliable model for the process dynamics, the black-box identification by means of a NARMAX (Nonlinear Auto-Regressive Moving Average with eXogenous) model has been chosen in this study. It is based on the neural network approach. This paper will show the choice and the performance of this neural network in the training and the test phases. A study is related to the inputs number, hidden neurons used and their influence on the behavior of the neural predictor. Three statistical criterions are used for the validation of the experimental data. After describing the system architecture and the proposed methodology of the fault detection, we present a realistic application such as a reactor in order to show the technique's potential. The purpose is to detect the change presence and pinpoint the moment it occurred.

FAULT DETECTION AND ISOLATION STUDY FOR POWER PLANT PROCESS AND CONTROL SYSTEMS

For existed plants with minimum equipments to automatic control it is necessary to increase the safety control by using digital equipments for distributed control using modern methods for monitoring and control. It is necessary to improve the methods for early detection of process and equipment faults. This study reports the implementation test details and methods for fault detection in terms of benefits for the power plant.

Cluster trending analysis for control loop assessment and diagnosis

Highly reliable automated systems require health monitoring capable of detecting any equipment faults as they occur and identifying the faulty components. Loop re-tuning can improve the performance when the operating environment has changed. However, if some equipment in the loop is malfunctioning, the simple control loop re-tuning will be less effective in improving the loop performance. Therefore, it is important to design a loop performance monitoring system with the capability of monitoring both the loop performance and the faults of equipment in-loop. This paper presents a new mechanism for control loop performance monitoring and equipment fault detection, based on cluster trending analysis. This mechanism is very sensitive to small signal variations and capable of detecting the abnormal signals embedded in the normal signals.

Simultaneous Fault Detection and Classification for Semiconductor Manufacturing Tools

Increasingly there is a need for fast, accurate, and sensitive detection of equipment and process faults to maintain high process yields and rapid fault classification (diagnosis) of the cause in order to minimize tool downtime in semiconductor manufacturing. Current methods treat fault detection and classification as a two-step process. We present a novel method to simultaneously detect and classify faults in a single-step using fault-specific control charts. These control charts are designed to discriminate between specific fault classes and the normal process operation as well as all other fault classes. Using a set of experimental data collected from an industrial plasma etcher, we demonstrate that, if the fault-specific charts are constructed using an orthogonal linear discriminant approach, they are effective in simultaneously detecting and classifying a given fault. We also demonstrate that this methodology has improved sensitivity for detection of faults when compared to other commonly used methods of fault detection. © 2003 The Electrochemical Society. All rights reserved.

Fault detection for linear analog IC-the method of short-circuit admittance parameters

A fault detection method, i.e. the short-circuit admittance parameters method, for linear analog ICs is proposed in this paper. Only two voltage measurements at the ports of the circuit are suggested to decide whether the circuit is working normally. This method can be used to design automatic circuit fault detection equipment for technicians to decide whether there are any faults in linear analog circuits. The attractive merits of this method are component parameter tolerance and error reduction in measurement and calculation.

Multivariate Zero-Inflated Poisson Models and Their Applications

The zero-inflated Poisson (ZIP) distribution has been shown to be useful for modeling outcomes of manufacturing processes producing numerous defect-free products. When there are several types of defects, the multivariate ZIP (MZIP) model can be useful to detect specific process equipment problems and to reduce multiple types of defects simultaneously. This article proposes types of MZIP models and investigates distributional properties of an MZIP model. Finite-sample simulation studies show that, compared to the method of moments, the maximum likelihood method has smaller bias and variance, as well as more accurate coverage probability in estimating model parameters and zero-defect probability. Real-life examples from a major electronic equipment manufacturer illustrate how the proposed procedures are useful in a manufacturing environment for equipment-fault detection and for covariate effect studies.

Equipment Fault Detection by Parametric Identification - Application to Chemical Reactor.

Equipment faults in industrial chemical reactors lead to variations in product quality. Due to the highly energetic potential of the reaction mass, they can in addition cause runaways or major incidents. The methodology for detecting process anomalies in a chemical reactor, is based on a parametric estimation-prediction of the reaction mixture. The recursive least square method with forgetting factor has been retained to appreciate the evolution of parameters in real time. Thus allowing us, to point out a criterion of decision based on relative prediction error between two successive vector parameters. In this paper, we consider only the stirred jacketed chemical reactor which is largely use in pharmaceutical fine chemistry. Two incidents linked to the hydrodynamic cited by Etchelles (Etchelles., 1994) as main causes of reported incidents are studied: a change in the fluid flow regime in the jacket and the immediate stop of the agitator. In each case, a dynamic simulation model, based on energetic balances, is established to represent the most accurate reactor thermal behaviour.

Production evaluation of real-time statistical process control on a sub-0.5 μm inductively coupled metal etch process

The semiconductor manufacturing industry is demanding improved algorithms for the detection and isolation of equipment faults. The real-time statistical process control (RTSPC) algorithm analyzes real-time sensor and actuator data for the detection of such faults. The software was evaluated using SECS-II (Serial Equipment Communication Standard) data from several commercial plasma etchers. These data were used to build statistical models which were then applied to data recorded during subsequent wafer processing. RTSPC was able to detect several faults related to failure of rf matching networks. For one of the rf match failures, the RTSPC alarm preceded the component failure by several weeks. This alarm was correlated to a shift in the critical dimension of wafers processed in this etcher. The statistical data filters included within RTSPC are discussed, as well as the characterization of the real-time data. Emphasis is placed on whether uni-variate, multivariate, or time-varying statistics are required to detect the faults seen on the etchers, and additional algorithms which would enhance the fault detection capability.

Equipment fault detection using spatial signatures

This paper describes a new methodology for equipment fault detection. The key features of this methodology are that it allows for the incorporation of spatial information and that it can be used to detect and diagnose equipment faults simultaneously. This methodology consists of constructing a virtual wafer surface from spatial data and using physically based spatial signature metrics to compare the virtual wafer surface to an established baseline process surface in order to detect equipment faults. Statistical distributional studies of the spatial signature metrics provide the justification of determining the significance of the spatial signature. Data collected from a rapid thermal chemical vapor deposition (RTCVD) process and from a plasma enhanced chemical vapor deposition (PECVD) process are used to illustrate the procedures. This method detected equipment faults for all 11 wafers that were subjected to induced equipment faults in the RTCVD process, and even diagnosed the type of equipment fault for 10 of these wafers. This method also detected 42 of 44 induced equipment faults in the PECVD process.

Detection of equipment faults in automatically controlled processes

AbstractBased on the UBET, a new strategy for identifying faulty equipment for dynamic chemical processes under automatic control is presented. The strategy is designed to distinguish between measurement biases, controller biases, and process leaks. For illustration purposes, application is given to a level control process under pseudo‐steady state. This approach was inspired by the work of Rollins and Devanathan to identify biased measurements under dynamic conditions. Advantages of this method are that it is not computationally intensive, can accurately detect and specifically identify the type of fault, and can accurately determine the time when the fault occurs.

Defect studies on single and bilayer resist systems

Defect detection equipment and procedures to qualify resist systems with regard to defects have been investigated. An analysis was carried out for two bilayer resist systems which were compared to a single layer resist. One of the bilayer resists was developed for the mid-UV exposure range, the other for deep-UV. It showed that the pinhole-limited yield measured by metal–oxide–semiconductor test structures is approximately 10% lower for one of the bilayer resists compared to a single layer resist. The other bilayer resist scheme was compared to a single layer resist with regard to particulates. Here the dry-developed bilayer resist scheme showed approximately four times higher additive defect densities than the wet-developed single layer resist. A short dry etch process for opening an anti reflective coating underneath a single layer resist increased the defect densities. Water rinse steps are capable of reducing these defect levels substantially. The dry-developed resist schemes had higher defect densities, but it is certainly possible to reduce these to the densities of single layer resists.

Development of Ultrasonic Testing Equipment Incorporating Electromagnetic Acoustic Transducer

This paper describes an automatic flaw detection equipment and heat-resistant ultrasonic transducer for plate thickness measurement. The automatic flaw detection equipment is used during in-service inspection. It comprises an angle-beam electromagnetic acoustic transducer (EMAT), mounted on a vehicle, for scanning the pipe surface to be inspected. The EMAT functions without direct contact with the pipe surface through a coupling liquid, the vehicle does not require a guide track installed on the pipe surface, since it is equipped with magnetic wheels that adhere to the pipe, permitting it to travel along the circumferential weld joint of a carbon steel pipe. Another heat-resistant ultrasonic transducer is a normal beam EMAT and is used during plant operation. As a result, the automatic flaw detection equipment could detect a 1 mm deep notch cut on a test piece of 25 mm thick carbon steel plate. The vehicle location accuracy on the piping was ±2 mm. The normal beam EMAT could measure the plate thickness, within ±0.3 mm accuracy for the range of plate thickness 4 mm to 12 mm at 300°C.

Development of ultrasonic testing equipment incorporating electromagnetic acoustic transducer.

This paper describes an automatic flaw detection equipment and heat-resistant ultrasonic transducer for plate thickness measurement. The automatic flaw detection equipment is used during in-service inspection. It comprises an angle-beam electromagnetic acoustic transducer (EMAT), mounted on a vehicle, for scanning the pipe surface to be inspected. The EMAT functions without direct contact with the pipe surface through a coupling liquid, the vehicle does not require a guide track installed on the pipe surface, since it is equipped with magnetic wheels that adhere to the pipe, permitting it to travel along the circumferential weld joint of a carbon steel pipe. Another heat-resistant ultrasonic transducer is a normal beam EMAT and is used during plant operation. As a result, the automatic flaw detection equipment could detect a 1 mm deep notch cut on a test piece of 25 mm thick carbon steel plate. The vehicle location accuracy on the piping was ±2 mm. The normal beam EMAT could measure the plate thickness, w...

大径溶接鋼管の内外面磁粉探傷

In order to improve the surface quality assurance of the pipe, Nippon Kokan K. K constructed the magnetic particle flaw detection equipment for the complete outside and inside surface of the pipe.Magnetic particle inspection has been used for a long time, but not a few techniques have depended on customary practice. Then, we investigated theoretically diffusion of magnetic flux and method of evaluation of residual magnetism.The results obtained are summarized as follows:(1) The theoretical model for a calculation of residual magnetism is made.(2) The new method of evaluation of residual magnetism by artificial defects is established.The magnetic particle flaw detection equipment for the large diameter pipe, that was installed based on the previous investigations, has been running favourably since June 1983.

An experimental study of the acousto-elastic effect in a rolled plate of steel

The acousto-elastic effect in rolled steel is studied experimentally by transmitting ultrasonic transverse waves and measuring amplitudes of reflected echoes. A Y- cut quartz transducer with a frequency 4.8 MH z and ultrasonic flaw detection equipment are used for generation and detection of waves, and three tensile specimens with different orientations are prepared from a rolled plate so as to ascertain an important role of its slight orthotropy. At first the variation of amplitude with the transducer direction is examined in the unstressed state, and the slight orthotropy of each specimen is determined quantitatively. Then the variation of amplitude with the tensile stress is examined in the elastic range. The results depend clearly on the orientation of each specimen, and rotation of polarization direction is affirmed in the specimen with an inclination 45° against the rolling direction. Quantitative discussions about the whole experimental results give the conclusion that the acousto elastic effect in this rolled plate obeys the relations which were proposed theoretically by one of the authors.

Diagnostic Ultrasound in Medicine

The application of ultrasonic technology in medicine has taken place in the last fifteen years and was made possible by far sighted and determined individuals who initially made use of industrial flaw detection equipment. In the last decade medical ultrasonics has developed into a multi-million pound business and has become an important aid to diagnosis and patient management. In this article we describe the use of ultrasonics as a method of investigating the internal structures of the body for diagnostic purposes. Other applications of ultrasonics in medicine include humidifiers and the use of instruments based on the Doppler principle for measuring the velocity of blood flowing in vessels.

A high-speed ultrasonic testing machine for tubes

An ultrasonic flaw detection equipment has been developed for testing steel tubes at speeds compatible with modern rates of production. The system uses a series of identical probes arranged in a ring encircling the tube. Fast sequential pulsing of the probes, together with slow rotation of the tubes gives effective circumferential scanning speeds several times faster than is obtainable by purely mechanical methods. The probe rings are immersed in a small tank of water through which the tube is passed via specially designed water retaining valves.

The testing of ultrasonic flaw detection equipment: Materials Research, 1, No. 1, p. 37 (1962)

The testing of ultrasonic flaw detection equipment: Materials Research, 1, No. 1, p. 37 (1962)