• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.2
• /
• pp.407-414
• /
• 2007

A sensor fault detection scheme(SFDS) for a class of nonlinear systems that can be represented by Takagi-Sugeno fuzzy model is proposed. Basically, the SFDS may be considered as a multiple observer scheme(MOS) in which the bank of state observers and the detection & isolation logic are included. However, the proposed scheme has two great differences from the conventional MOSs. First, the proposed scheme includes fuzzy fault detection observers(FFDO) that are constructed based on the T-S fuzzy model that provides very good approximation to nonlinear dynamic systems. Secondly, unlike the conventional MOS, the FFDOS are driven not parallelly but sequentially according to the predetermined sequence to avoid the massive computational burden, which is known to be the biggest obstacle to the practical application of the multiple observer based FDI schemes. During the operating time, each FFDO generates the residuals carrying the information of a specified fault, and the corresponding fault detection logic unit performs the logical operations to detect and isolate the fault of interest. The proposed scheme is applied to an inverted pendulum control system for sensor fault detection/isolation. Simulation study shows the practical feasibility of the proposed scheme.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.229-231
• /
• 2006

NLPCA(Nonlinear Principal Component Analysis) is a novel technique for multivariate data analysis, similar to the well-known method of principal component analysis. NLPCA operates by a feedforward neural network called AANN(Auto Associative Neural Network) which performs the identity mapping. In this work, a sensor fault detection system based on NLPCA is presented. To verify its applicability, simulation study on the data supplied from sensor network is executed.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.11
• /
• pp.1117-1124
• /
• 2011

An integrated fault detection and isolation method is proposed in this paper. The main objective of this paper is development fault detection, isolation and diagnosis algorithm based on the DKF (Decentralized Kalman Filter) and the bank of IMM (Interacting Multiple Model) filters using penalty scalar for both partial and total faults and the outlier detection algorithm for preventing false alarm also included. The proposed FDI (Fault Detection and Isolation) scheme is developed in four phases. In the first phase, the outlier detection filter is designed to prevent false alarm as a pre-filter. In the second phases, two local filters and master filter are designed to detect sensor faults. In the third phases, the proposed FDI scheme checks sensor residual to isolate sensor faults and 11 EKFs actuator fault models are designed to detect wherever actuator faults occur. In the last phases, four filters are designed to identify the fault type which is either the total fault or partial fault. The developed scheme can deal with not only sensor and actuator faults, but also preventing false alarm. An important feature of the proposed FDI scheme can decreases fault isolation time and figure out not only fault detection and isolation but also fault type identification. To verify the proposed FDI algorithm performance, the Simulator is also developed under the Matlab/Simulink environment.

• Proceedings of the KIEE Conference
• /
• 2001.07b
• /
• pp.1165-1168
• /
• 2001

The effect of sensor faults in DTC based induction motor drives is analyzed and a fault detection problem is treated. An adaptive gain scheduling observer is proposed for the design of DTC controller and a fault detection system. The observer provides not only the estimate of stator flux, a key variable in DTC system, but also the estimates of stator current, rotor speed that are useful for fault detection purpose. Simulations for various type of sensor faults are performed to evaluate the performance of the overall control system and the proposed sensor fault detection scheme.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.2
• /
• pp.41-47
• /
• 1997

Fault diagnosis problem is currently a subject of extensive research in the control field. Although there are several works on the fault detection and isolation observers and the residual generators, those are con- cerned with only the detection of actuator failures or sensor failures. So, the perfect detection and isolation for the actuator and sensor failures is strongly required in the field of the practical applications. In this paper, a strategy of fault diagnosis using multiple proportional integral (PI) observers including the magnitude of actuator failures is provided. It is shown that actuator failures are detected and isolated perfectly by monitoring the integrated error between actual output and estimated output by a PI observer. Also in presence of complex actuator and sensor failures, these failures are detected and isolated by multiple PI observers.

• Structural Monitoring and Maintenance
• /
• v.5 no.1
• /
• pp.51-65
• /
• 2018

A number of sensing techniques have been implemented for detecting defects in civil infrastructures instead of onsite human inspections in structural health monitoring. However, the issue of faults in sensors has not received much attention. This issue may lead to incorrect interpretation of data and false alarms. To overcome these challenges, this article presents a deep learning-based method with a new architecture of Stateful Long Short Term Memory Neural Networks (S-LSTM NN) for detecting sensor fault without going into details of the fault features. As LSTMs are capable of learning data features automatically, and the proposed method works without an accurate mathematical model. The detection of four types of sensor faults are studied in this paper. Non-stationary acceleration responses of a three-span continuous bridge when under operational conditions are studied. A deep network model is applied to the measured bridge data with estimation to detect the sensor fault. Another set of sensor output data is used to supervise the network parameters and backpropagation algorithm to fine tune the parameters to establish a deep self-coding network model. The response residuals between the true value and the predicted value of the deep S-LSTM network was statistically analyzed to determine the fault threshold of sensor. Experimental study with a cable-stayed bridge further indicated that the proposed method is robust in the detection of the sensor fault.

• Journal of information and communication convergence engineering
• /
• v.6 no.2
• /
• pp.207-212
• /
• 2008

There are several sensors in the liquid cargo ship. In the liquid cargo ship, we can get values from various sensors that are level sensor, temperature sensor, pressure sensor, oxygen sensor, VOCs sensor, high overfill sensor, etc. It is important to guarantee the reliability of sensors. In order to guarantee the reliability of sensors, we have to study the diagnosis of sensor fault. The technology of smart sensor is widely used. In this paper, the technology of smart sensor is applied to diagnosis of level sensor fault for liquid cargo ship. In order to diagnose sensor fault and find the sensor position, in this paper, we proposed algorithms of diagnosis of sensor fault using independent sensor diagnosis unit and self fault diagnosis using sensor modeling. Proposed methods are demonstrated by experiment and simulation. The results show that the proposed approach is useful. Proposed methods are useful to develop smart level sensor.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.17 no.5
• /
• pp.26-30
• /
• 2009

In this paper, a robust model based fault detection for varying temperature is proposed, To develop a robust force estimation model, it needs temperature information because the force sensor's output is affected by a temperature variation. If an EPB system does not include a temperature sensor, the model has a much larger error than an EPB system with a built-in temperature sensor. Therefore, the temperature is estimated by using Ohm's law. The force model is applied with a motor current, battery voltage, operation mode, and the estimated temperature to detect a force sensor's abnormal signal fault. The residual is calculated by comparing the value of the measured force and the estimated force. Fault information is collected by using the output of the evaluated residual with the adaptive thresholds. A proposed robust model based fault detection for varying temperature was verified by HILS (Hardware in the Loop Simulation).

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.6
• /
• pp.241-251
• /
• 2002

The effect of sensor faults in direct torque control(DTC) based induction motor drives is analyzed and a new Instrument fault detection isolation scheme(IFDIS) is proposed. The proposed IFDIS, which operated in real-time, detects and isolates the incipient fault(s) of speed sensor and current sensors that provide the feedback information. The scheme consists of an adaptive gain scheduling observer as a residual generator and a special sequential test logic unit. The observer provides not only the estimate of stator flux, a key variable in DTC system, but also the estimates of stator current and rotor speed that are useful for fault detection. With the test logic, the IFDIS has the functionality of fault isolation that only multiple estimator based IFDIS schemes can have. Simulation results for various type of sensor faults show the detection and isolation performance of the IFDIS and the applicability of this scheme to fault tolerant control system design.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.10
• /
• pp.1009-1013
• /
• 2009

In this paper, a robust fault detection method for varying temperature based on fuzzy model is proposed. To develop a robust force estimation model, it needs temperature information because the output of force sensor is affected by a temperature variation. The nonlinear dynamic system, such as the parking force of the EPB (Electronic Parking Brake) system is necessary to have a higher order equation model. But, because of the calculation time, the higher order equation model is hard to be used in real application. In case of the lower order equation model, the result is not as accurate as acceptable. To solve this problem, the robust fuzzy model-based fault detection is developed. A proposed fault detection method for varying temperature is verified by HILS (hardware in the loop simulation).