Kyusung Kim

Induction motor fault diagnosis based on neuropredictors and wavelet signal processing

Early detection and diagnosis of incipient faults is desirable for online condition assessment, product quality assurance and improved operational efficiency of induction motors running off power supply mains. In this paper, a model-based fault diagnosis system is developed for induction motors, using recurrent dynamic neural networks for transient response prediction and multi-resolution signal processing for nonstationary signal feature extraction. In addition to nameplate information required for the initial setup, the proposed diagnosis system uses measured motor terminal currents and voltages, and motor speed. The effectiveness of the diagnosis system is demonstrated through staged motor faults of electrical and mechanical origin. The developed system is scalable to different power ratings and it has been successfully demonstrated with data from 2.2-, 373-, and 597-kW induction motors. Incremental tuning is used to adapt the diagnosis system during commissioning on a new motor, significantly reducing the system development time.

Sensorless fault diagnosis of induction motors

Early detection and diagnosis of incipient faults is desirable for online condition assessment, product quality assurance, and improved operational efficiency of induction motors. In this paper, a speed-sensorless fault diagnosis system is developed for induction motors, using recurrent dynamic neural networks and multiresolution or Fourier-based signal processing for transient or quasi-steady-state operation, respectively. In addition to nameplate information required for the initial system setup, the proposed fault diagnosis system uses only motor terminal voltages and currents. The effectiveness of the proposed diagnosis system in detecting the most widely encountered motor electrical and mechanical faults is demonstrated through extensive staged faults. The developed system is scalable to different power ratings and it has been successfully demonstrated with data from 2.2, 373 and 597 kW induction motors.

Reducing the Impact of False Alarms in Induction Motor Fault Diagnosis

Early detection and diagnosis of incipient faults is desirable for on-line condition assessment, product quality assurance, and improved operational efficiency of induction motors. At the same time, reducing the probability of false alarms increases the confidence of equipment owners in this new technology. In this paper a model-based fault diagnosis system recently proposed by the authors for induction motors is experimentally compared for fault detection and false alarm performance with a more traditional signal-based motor fault estimator. In addition to the nameplate information required for the initial set-up, the proposed model-based fault diagnosis system uses measured motor terminal currents and voltages, and motor speed. The motor model embedded in the diagnosis system is empirically obtained using dynamic recurrent neural networks, and the resulting residuals are processed using wavelet packet decomposition. The effectiveness of the model-based diagnosis system in detecting the most widely encountered motor electrical and mechanical faults, while minimizing the impact of false alarms resulting from power supply and load variations, is demonstrated through extensive testing with staged motor faults. The model-based fault diagnosis system is scalable to motors of different power ratings and it has been successfully tested with fault data from 2.2 kW. 373 kW, and 597 kW induction motors.

Sensorless detection of mechanical faults in electromechanical systems

Practical early fault detection and diagnosis systems must exhibit high level of detection accuracy, while exhibiting acceptably low false alarm rates. Further, it is desirable not to make use of add-on sensors, and require minimal information regarding the specific machine component parameters and design. In this paper the development and experimental demonstration of a sensorless detection and diagnosis system is presented for incipient faults in electromechanical systems, such as electric motors. The developed system uses recent developments in dynamic recurrent neural networks and wavelet signal processing. The signals utilized are only the motor currents and voltages, whereas the transient mechanical speed is estimated from these measurements using a recently developed speed filter. The effectiveness of the fault diagnosis system is demonstrated by detecting a wide range of mechanical faults at varying levels of deterioration. Furthermore, the ability of the diagnosis system to discriminate between false alarms and actual incipient failure conditions is demonstrated. Experimental test results from small machines, 2.2 kW, and large machines, 373 and 597 kW, are presented demonstrating the effectiveness of the proposed approach to scale-up with motor power rating.

Signal-based versus model-based fault diagnosis-a trade-off in complexity and performance

Early detection and diagnosis of incipient faults is desirable not only for on-line condition assessment but also for product quality assurance and improved operational efficiency of induction motors. At the same time, reducing the probability of false alarms increases the confidence levels of equipment owners in this new technology. In this paper, a model-based fault detection and diagnosis system that has been proposed is tested for its effectiveness in minimizing the probability of false alarms. The proposed system is compared to the more traditional signal-based motor fault estimator. In addition to nameplate information required for the initial set-up, the proposed model-based fault detection and diagnosis system uses measured motor terminal currents and voltages, and motor speed. The motor model embedded in the diagnosis system is empirically obtained using dynamic recurrent neural networks. Receiver operating characteristic (ROC) curves are constructed to demonstrate the performance trade-offs of the two estimators, while observing their relative complexity.

Detection of induction motor faults-combining signal-based and model-based techniques

Effective detection and diagnosis of incipient faults is desirable for on-line condition assessment, product quality assurance and improved operational efficiency of induction motors running off the power supply mains. In this paper, an empirical model-based fault diagnosis system is developed for induction motors using recurrent dynamic neural networks and multiresolution signal processing methods. In addition to nameplate information required for the initial set-up, the proposed diagnosis system uses measured motor terminal currents and voltages, and motor speed. The effectiveness of the diagnosis system is demonstrated through motor faults of electrical and mechanical origin staged in small and large motors.

Model-Based Avionics System Fault Simulation and Detection

In integrated modular avionics making distinctions between hardware and software faults is not easy. Interactions and propagation of fault effects complicate the fault detection and isolation task. Avionics systems combine physical processes, computational hardware, and software systems, and present unique challenges to performing root cause analysis when faults occur, and then establishing the effects of faults on overall system behavior and performance. However, systematic analyses of these conditions are important for establishing overall flight safety. This paper proposes a model based approach to study the fault propagation and fault detection in an integrated avionics system. The failures of power supply module, GPS, and Integrated Navigation Solution (INAV) are simulated and the fault detection and isolation methods are discussed. Sample case studies illustrate the effectiveness of our approach.

Model-based incipient fault diagnosis - multi-step neuro-predictors and multiresolution signal processing

Timely detection and diagnosis of incipient faults is desirable for online condition assessment purposes. In this paper, a model-based fault diagnosis system is developed for induction motors, using recurrent neural networks for multistep transient response prediction and multiresolution signal processing for nonstationary signal feature extraction. The proposed diagnosis system uses only measured motor terminal currents and voltages, and motor speed. The effectiveness of the diagnosis system is demonstrated through staged motor faults of electrical and mechanical origin. Scaling of the diagnosis system to machines with different power ratings is demonstrated with data from 2.2 kW, 373 kW and 597 kW induction motors.

Development and experimental demonstration of a model-based fault detection system for electromechanical systems

Electromechanical systems, such as electric motors driving dynamic loads like pumps and compressors, often develop incipient faults that result in down-time. There is a large number of such fault classes, and their precise signatures depend on numerous parameters including variations in the motor power supply and driven load. Practical fault detection and diagnosis systems must exhibit high level of detection accuracy and acceptably low false alarm rates. They must have broad applicability, require installation of minimal extra sensors, and not require the use of detailed machine information for operation. In this paper the development and experimental demonstration of a model-based detection system for incipient electric machine faults is presented. The developed fault detection system uses recent developments in dynamic recurrent neural networks and multi-resolution signal processing. The sensors utilized axe only those measuring the motor current and voltage. The effectiveness of the developed system is demonstrated by detecting stator, rotor and bearing faults at the early stages of development. Furthermore, the ability of the system to discriminate between false alarm caused by poor power quality, variations in the driven load level, and actual incipient faults is demonstrated.