• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.54-63
• /
• 2023

High and intermittent loading cycles induce fatigue damage to transmission components, resulting in premature gearbox failure. To identify gearbox defects, numerous vibration-based diagnostics techniques, using several artificial intelligence (AI) algorithms, have recently been presented. In this paper, an optimized deep belief network (DBN) model for gearbox problem diagnosis was designed based on time-frequency visual pattern identification. To optimize the hyperparameters of the model, a particle swarm optimization (PSO) approach was integrated into the DBN. The proposed model was tested on two gearbox datasets: a wind turbine gearbox and an experimental gearbox. The optimized DBN model demonstrated strong and robust performance in classification accuracy. In addition, the accuracy of the generated datasets was compared using traditional ML and DL algorithms. Furthermore, the proposed model was evaluated on different partitions of the dataset. The results showed that, even with a small amount of sample data, the optimized DBN model achieved high accuracy in diagnosis.

• International Journal of Industrial Entomology and Biomaterials
• /
• v.47 no.1
• /
• pp.1-11
• /
• 2023

The Indian golden muga silkworm, Antheraea assamensis Helfer is an economically important wild silkworm endemic to Northeastern part of India. In recent years, climate change has posed a threat to muga silk production due to the requirement that larvae be reared outdoors. Since the muga silkworm larvae are exposed to the vagaries of nature, the changing climate has increased the incidence of microbial diseases in the rearing fields. Accurate diagnosis of the disease causing pathogens and its associated epidemiology are prerequisites to manage the diseases in the rearing field. Although conventional microbial culturing methods are widely used to identify pathogenic bacteria, they would not provide meaningful information on a wide variety of silkworm pathogens. The information on use of molecular diagnostic tools in detection of microbial pathogens of wild silk moths is very limited. A wide range of molecular and immunodiagnostic techniques including denaturing gradient gel electrophoresis (DGGE), random amplified polymorphism (RAPD), 16S rRNA/ITSA gene sequencing, multiplex polymerase chain reaction (M-PCR), fluorescence in situ hybridization (FISH), immunofluorescence, and repetitive-element PCR (Rep-PCR), have been used for detecting and characterizing the pathogens of insects with economic significance. Nevertheless, the application of these molecular tools for detecting and typing entomopathogens in surveillance studies of muga silkworm rearing is very limited. Here, we discuss the possible application of these molecular techniques, their advantages and major limitations. These methods show promise in better management of diseases in muga ecosystem.

• Journal of Biomedical Engineering Research
• /
• v.3 no.2
• /
• pp.83-94
• /
• 1982

This paper presents a practical approach to develop computer algorithm for automatic diagnosis electrocardiogram(ECG) based on a decision table techniques.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.87-87
• /
• 2000

In this paper, an integrated design of fault detection, diagnosis and reconfigurable control tot multi-input and multi-output system is proposed. It is based on the interacting multiple model estimation algorithm, which is one of the most cost-effective adaptive estimation techniques for systems involving structural and/or parametric changes. This research focuses on the method to recover the performance of a system with failed actuators by switching plant models and controllers appropriately. The proposed scheme is applied to a fault tolerant control design for flight control system.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.23 no.1
• /
• pp.34-40
• /
• 2009

After a research on appearance diagnosis and fish, bird, horse, and turtle types, this study concluded as following. Appearance diagnosis is a technique that exams five jang organs by color and shape of eye, nose, mouth, and ear. Four HyungSang types-including fish, bird, horse and turtle types-are evaluated upon the external shape that are created while type of seed changes. Appearance diagnosis focuses on five jang organs. Four HyungSang types focus on external shape, but are eventually related to five jang organs. Thus, two different techniques possess a point in common; five jang organs. The assignment of nose, eye, ear and mouth to the Five elements varies between two techniques. On the viewpoint of formation, appearance diagnosis assigns them to metal-water-wood-fire-earth and movement, and four HyungSang types do to wood-fire-earth-metal-water and constitution. On the viewpoint of body/use and static/dynamic, appearance diagnosis assigns them to metal-water-wood-fire-earth and constitution, and four HyungSang types do to wood-fire-earth-metal-water and movement. If nose, eye, ear, and mouth are assigned by on four HyungSang types, which are based on external shape, the assignment can be utilized in diagnosis. If, however, they are assigned by appearance diagnosis, it can be focus on treatment. Five jang organs and six fu organs are affected by internal conditions because they are located inside of human body, while four HyungSang types are affected by external conditions because it deals with external shape. If a disease occurs in the developed part of the body, it would be difficult to be cured because four HyungSang types depend on external shapes.

• Journal of Computing Science and Engineering
• /
• v.10 no.4
• /
• pp.118-127
• /
• 2016

An improved sample balanced genetic algorithm and Extreme Learning Machine (iSBGA-ELM) was designed for accurate diagnosis of Alzheimer disease (AD) and identification of biomarkers associated with AD in this paper. The proposed AD diagnosis approach uses a set of magnetic resonance imaging scans in Open Access Series of Imaging Studies (OASIS) public database to build an efficient AD classifier. The approach contains two steps: "voxels selection" based on an iSBGA and "AD classification" based on the ELM. In the first step, the proposed iSBGA searches for a robust subset of voxels with promising properties for further AD diagnosis. The robust subset of voxels chosen by iSBGA is then used to build an AD classifier based on the ELM. A robust subset of voxels keeps a high generalization performance of AD classification in various scenarios and highlights the importance of the chosen voxels for AD research. The AD classifier with maximum classification accuracy is created using an optimal subset of robust voxels. It represents the final AD diagnosis approach. Experiments with the proposed iSBGA-ELM using OASIS data set showed an average testing accuracy of 87%. Experiments clearly indicated the proposed iSBGA-ELM was efficient for AD diagnosis. It showed improvements over existing techniques.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.16 no.1 s.106
• /
• pp.27-33
• /
• 2006

Fault diagnosis and condition monitoring for rotating machines are important for efficiency and accident prevention. The process of fault diagnosis is to extract the feature of signals and to classify each state. Conventionally, fault diagnosis has been developed by combining signal processing techniques for spectral analysis and pattern recognition, however these methods are not able to diagnose correctly for certain rotating machines and some faulty phenomena. In this paper, we add a minimum detection error algorithm to the previous method to reduce detection error rate. Vibration signals of the induction motor are measured and divided into subband signals. Each subband signal is processed to obtain the RMS, standard deviation and the statistic data for constructing the feature extraction vectors. We make a study of the fault diagnosis system that the feature extraction vectors are applied to K-means clustering algorithm and minimum detection error algorithm.

• Journal of Electrical Engineering and Technology
• /
• v.8 no.2
• /
• pp.288-294
• /
• 2013

The diagnosis of motor failures using an on-line method has been the aim of many researchers and studies. Several spectral analysis techniques have been developed and are used to facilitate on-line diagnosis methods in industry. This paper discusses the first application of a motor flux spectral analysis to the identification of broken rotor bar (BRB) faults in induction motors using a multiple signal classification (MUSIC) technique as an on-line diagnosis method. The proposed method measures the leakage flux in the radial direction using a radial flux sensor which is designed as a search coil and is installed between stator slots. The MUSIC technique, which requires fewer number of data samples and has a higher detection accuracy than the traditional fast Fourier transform (FFT) method, then calculates the motor load condition and extracts any abnormal signals related to motor failures in order to identify BRB faults. Experimental results clearly demonstrate that the proposed method is a promising candidate for an on-line diagnosis method to detect motor failures.

• 한국가시화정보학회:학술대회논문집
• /
• 2001.12a
• /
• pp.23-35
• /
• 2001

Due to advances in digital image processing, computer and optical hardware, it is possible to extract full flow information from visualized flow images. Recently, the PIV/PTV methods have been accepted as a reliable velocity field measurement technique. In my laboratory, several velocity field measurement techniques have been developed and they were applied to various thermo-fluid flow problems. In this paper, some of the industrial applications will be discussed. As a result, the PIV/PTV technique was proved to be a powerful tool for industrial fluid flow diagnosis.

• Journal of Korean Society for Quality Management
• /
• v.21 no.1
• /
• pp.78-95
• /
• 1993

The art of designing and analyzing fault-tolerant computers is surveyed with special emphasis on problems of analyzing the behavior of computers that have autonomous repair capability. The survey covers the following topics : (1) general issues in computer reliability, (2) fault-tolerance state relations and requirements, (3) computational hierarchy, (4) fault characteristics, (5) fault diagnosis, (6) fault-tolerance schemes for logic network and machines, (7) fault-coverage effects, and (8) fault-tree analysis of coverage. This paper does not include techniques for verifying nonredundant hardware or system software designs or for verifying the correctness of application programs.