• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1186-1207
• /
• 2024

Bearings are one of the main components of mechanical equipment and one of the primary components prone to faults. Therefore, conducting fault diagnosis on bearings is a key issue in mechanical equipment research. Belief rule base (BRB) is essentially an expert system that effectively integrates qualitative and quantitative information, demonstrating excellent performance in fault diagnosis. However, class imbalance often occurs in the diagnosis task, which poses challenges to the diagnosis. Models with interpretability can enhance decision-makers' trust in the output results. However, the randomness in the optimization process can undermine interpretability, thereby reducing the level of trustworthiness in the results. Therefore, a hierarchical BRB model based on extreme gradient boosting (XGBoost) feature selection with interpretability (HFS-IBRB) is proposed in this paper. Utilizing a main BRB alongside multiple sub-BRBs allows for the conversion of a multi-classification challenge into several distinct binary classification tasks, thereby leading to enhanced accuracy. By incorporating interpretability constraints into the model, interpretability is effectively ensured. Finally, the case study of the actual dataset of bearing fault diagnosis demonstrates the ability of the HFS-IBRB model to perform accurate and interpretable diagnosis.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.65 no.1
• /
• pp.41-46
• /
• 2016

It has been proven that the dissolved gas analysis (DGA) is the most effective and convenient method to diagnose the transformers. The DGA is a simple, inexpensive, and non intrusive technique. Among the various diagnosis methods, IEC 60599 has been widely used in transformer in service. But this method cannot offer accurate diagnosis for all the faults. This paper proposes a fault diagnosis method of oil-filled power transformers using IEC code based neuro-fuzzy model. The proposed method proceeds two steps. First, IEC 60599 method is applied to diagnosis. If IEC code can't determine the fault type, neuro-fuzzy model is applied to effectively classify the fault type. To demonstrate the validity of the proposed method, experiment is performed and its results are illustrated.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.41 no.10
• /
• pp.931-940
• /
• 2017

This paper describes a predictive fault diagnosis algorithm for autonomous vehicles based on a kinematic model that uses a sliding mode observer. To ensure the safety of autonomous vehicles, reliable information about the environment and vehicle dynamic states is required. A predictive algorithm that can interactively diagnose longitudinal environment and vehicle acceleration information is proposed in this paper to evaluate the reliability of sensors. To design the diagnosis algorithm, a longitudinal kinematic model is used based on a sliding mode observer. The reliability of the fault diagnosis algorithm can be ensured because the sliding mode observer utilized can reconstruct the relative acceleration despite faulty signals in the longitudinal environment information. Actual data based performance evaluations are conducted with various fault conditions for a reasonable performance evaluation of the predictive fault diagnosis algorithm presented in this paper. The evaluation results show that the proposed diagnosis algorithm can reasonably diagnose the faults in the longitudinal environment and acceleration information for all fault conditions.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.548-555
• /
• 2021

This paper outlines the basic concepts, approaches and research trends of fault diagnosis and fault tolerant control applied to industrial processes, facilities, and motor drives. The main role of fault diagnosis for industrial processes is to create effective indicators to determine the defect status of the process and then take appropriate measures against failures or hazadous accidents. The technologies of fault detection and diagnosis have been developed to determine whether a process has a trend or pattern, or whether a particular process variable is functioning normally. Firstly, data-driven based and model-based techniques were described. Secondly, fault detection and diagnosis techniques for industrial processes are described. Thirdly, passive and active fault tolerant control techniques are considered. Finally, major faults occurring in AC motor drives were listed, described their characteristics and fault diagnosis and fault tolerant control techniques are outlined for this purpose.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.10a
• /
• pp.442-445
• /
• 1997

A challenging activity in the manufacturing industry is to perform in real time the continuous monitoring of the process state, the situation assessment and identification of the problem on line and diagnosis of the cause and importance of the problem if he process does not work properly. This paper describes LAT(Ladder Analysis Tool) system for fault tree generation to improving the fault diagnosis of CNC machine tools. The system consists of 4 steps which can automatically ladder analysis from ladder diagram to two diagnosis function models. The two diagnostic models based on he ladder diagram is switching function model and step switching function model. This system tries to overcome diagnosis deficiencies present machine tool.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.11
• /
• pp.928-934
• /
• 2002

A natural way to cope with fault tolerant control (FTC) problems is to modify the control parameters according to an online identification of the system parameters when a fault occurs. However. due to not only difficulties Inherent to the online multivariable identification in closed-loop systems, such as modeling errors, noise or the lack of excitation signals, but also long time requirement to identify the post-fault system and implemeutation of control problems during the identification process, we propose an alternative approach based on the observer-based fault detection and isolation (FDI) and model reference adaptive control (MRAC). The proposed robust fault diagnosis method is based on a bank of observers. We also propose a model reference adaptive control with changeable reference models according to the occurred faults. Simulation results of a flight control example show the validity and applicability of the proposed algorithms.

• Journal of the Korean Society of Safety
• /
• v.31 no.4
• /
• pp.35-41
• /
• 2016

In order to guarantee the process safety and prevent accidents, the deviations from normal operating conditions should be monitored and their root causes have to be identified as soon as possible. The statistical theories-based method among various fault diagnosis methods has been gaining popularity, due to simplicity and quickness. However, according to fault magnitudes, the scalar value generated by statistical methods can be changed and this point can lead to produce wrong information. To solve this difficulty, this work employs PCA (Principal Component Analysis) based method with qualitative information. In the case study of our previous study, the number of assumed faults is much smaller than that of process variables. In the case study of this study, the number of predefined faults is 19, while that of process variables is 6. It means that a fault diagnosis becomes more difficult and it is really hard to isolate a single fault with a small number of variables. The PCA model is constructed under normal operation data in order to get a loading vector and the data set of assumed faulty conditions is applied with PCA model. The significant changes on PC (Principal Components) axes are monitored with CUSUM (Cumulative Sum Control Chart) and recorded to make the information, which can be used to identify the types of fault.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.714-717
• /
• 1996

This paper presents a fault detection and diagnosis methodologies based on weighted symptom model and pattern matching between the coming fault propagation trend and the simulated one. At the first step, backward chaining is used to find the possible cause candidates for the faults. The weighted symptom model(WSM) is used to generate those candidates. The weight is determined from dynamic simulation. Using WSMs, the methodology can generate the cause candidates and rank them according to the probability. Secondly, the fault propagation trends identified from the partial or complete sequence of measurements are compared to the standard fault propagation trends stored a priori. A pattern matching algorithm based on a number of triangular episodes is used to effectively match those trends. The standard trends have been generated using dynamic simulation and stored a priori. The proposed methodology has been illustrated using two case studies and showed satisfactory diagnostic resolution.

• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• pp.822-829
• /
• 2022

According to existing study into the remote fault diagnosis procedure, the current diagnostic approach has an imperfect decision model, which only supports communication in a close distance. An Internet of Things (IoT)-based remote fault diagnostic approach for wind power equipment is created to address this issue and expand the communication distance of fault diagnosis. Specifically, a decision model for active power coordination is built with the mechanical energy storage of power generation equipment with a remote diagnosis mode set by decision tree algorithms. These models help calculate the failure frequency of bearings in power generation equipment, summarize the characteristics of failure types and detect the operation status of wind power equipment through IoT. In addition, they can also generate the point inspection data and evaluate the equipment status. The findings demonstrate that the average communication distances of the designed remote diagnosis method and the other two remote diagnosis methods are 587.46 m, 435.61 m, and 454.32 m, respectively, indicating its application value.

• The KIPS Transactions:PartC
• /
• v.9C no.4
• /
• pp.497-504
• /
• 2002

This paper proposes fault diagnosis and correction algorithms using agent collaboration, and a management model for managing network configuration faults. This management model is composed of three processes-fault detection, fault diagnosis and fault correction. Each process, based on RBR, operates on using rules which are consisted in Rule-based Knowledge Database. Proposed algorithm selves the complex fault problem that a system could not work out by itself, using agent collaboration. And the algorithm does efficiently diagnose and correct network configuration faults in abnormal network states.