Model-based Condition Monitoring Research Articles

Model-based condition monitoring of PEM fuel cell using Hotelling T2 control limit

Although a variety of design and control strategies have been proposed to improve the performance of polymer electrolyte membrane (PEM) fuel cell systems, temporary faults in such systems still might occur during operations due to the complexity of the physical process and the functional limitations of some components. The development of an effective condition monitoring system that can detect these faults in a timely manner is complicated by the operating condition variation, the significant variability/uncertainty of the fuel cell system, and the measurement noise. In this research, we propose a model-based condition monitoring scheme that employs the Hotelling T 2 statistical analysis for fault detection of PEM fuel cells. Under a given operating condition, the instantaneous load current, the temperature and fuel/gas source pressures of the fuel cell are measured. These measurements are then fed into a lumped parameter dynamic fuel cell model for the establishment of the baseline under the same operating condition for comparison. The fuel cell operation is simulated under statistical sampling of parametric uncertainties with specified statistics (mean and variance) that account for the system variability/uncertainty and measurement noise. This yields a group of output voltages (under the same operating condition but with uncertainties) as the baseline. Fault detection is facilitated by comparing the real-time measurement of the fuel cell output voltage with the baseline voltages by employing the Hotelling T 2 statistical analysis. The baseline voltages are used to evaluate the output T 2 statistics under normal operating condition. Then, with a given confidence level the upper control limit can be specified. Fault condition will be declared if the T 2 statistics of real-time voltage measurement exceeds the upper control limit. This model-based robust condition monitoring scheme can deal with the operating condition variation, various uncertainties in a fuel cell system, and measurement noise. Our analysis indicates that this scheme has very high detection sensitivity and can detect the fault conditions at the early stage.

DYNAMIC MODELLING FOR CONDITION MONITORING OF GAS TURBINES: GENETIC ALGORITHMS APPROACH

The problem of model-based condition monitoring of aero gas turbine engines is considered. Genetic algorithms are applied for the dynamic modelling of aero engines by estimating parameters of the linear reduced-order model. The use of genetic algorithms affords flexibility in the choice of performance metrics. Real engine data is used to investigate the performance genetic algorithms and this approach is compared with traditional modelling techniques used in industry.

Uncertainty in model-based condition monitoring

Model-based techniques for automated condition monitoring of HVAC systems have been under development for some years. The generation of false alarms has been identified as a principal factor affecting the potential usefulness of condition monitoring in HVAC applications. Results from the application of these methods to systems installed in real buildings have highlighted the difficulty in selecting good alarm thresholds that balance robustness (lack of false alarms) and sensitivity (early detection). This paper demonstrates that this balance can be met in a transparent and analytical manner, through the application of uncertainty analysis. The paper discusses the sources of uncertainty associated with component models and system measurements. A condition monitoring scheme applied to a typical HVAC cooling coil subsystem installed in a real building is presented. Faults are artificially introduced into the system and are used in conjunction with fault-free operation to demonstrate the sensitivity and robustness of the scheme. The principle conclusions drawn by the paper consider the likely minimum magnitudes of faults that can be detected in typical HVAC systems, without false alarm generation. More broadly however, the paper demonstrates that the issue of uncertainty affects all aspects of system monitoring, modelling and control.

Model-based condition monitoring of a HVAC cooling coil sub-system in a real building

A comparison of the performance of two fault detection and diagnosis methods applied to a cooling coil subsystem in an air-handling unit installed in a real building is presented. Both methods employ a first principles based reference model of the target system. One scheme carries out diagnosis using expert rules and the other recursively re-estimates selected parameters of the system model that correspond to particular faults. The procedures and information required to configure the schemes for condition monitoring are discussed. The results of testing the methods on an HVAC cooling coil subsystem in a commercial office building in the UK over an entire cooling season are reported. Both methods were able to both detect faults and provide some diagnosis. The expert rule method, however, appears to be more robust. Issues associated with the con” guration and implementation of both methods are discussed in terms of performance and cost.

Fuzzy model-based condition monitoring and fault diagnosis of a diesel engine cooling system

This paper describes a fuzzy model-based diagnostic system and its application to the cooling system of a diesel engine. The aim is to develop generic cost-effective knowledge-based techniques for condition monitoring and fault diagnosis of engine systems. A number of fuzzy systems have been developed to model the cooling system components. Residuals are generated on line by comparison of measured data with model outputs. The residuals are then analysed on line and classified into a number of fuzzy classes symptomatic of potential system conditions. A fuzzy rule-based system is designed to infer a number of typical fault conditions from the estimated state of the valve and patterns in the residual classes. The ability to diagnose certain faults in the system depends on the state of the thermostatic valve. The diagnostic systems have been tested with data obtained by experimental simulation of a number of target fault conditions on a diesel generator set test bed. In five test cases for separate cooling system operating conditions, the diagnostic system's successful diagnosis rate ranged between 73 and 97.7 per cent of the test data.

Fuzzy model-based condition monitoring and fault diagnosis of a diesel engine cooling system

This paper describes a fuzzy model-based diagnostic system and its application to the cooling system of a diesel engine. The aim is to develop generic cost-effective knowledge-based techniques for condition monitoring and fault diagnosis of engine systems. A number of fuzzy systems have been developed to model the cooling system components. Residuals are generated on line by comparison of measured data with model outputs. The residuals are then analysed on line and classified into a number of fuzzy classes symptomatic of potential system conditions. A fuzzy rule-based system is designed to infer a number of typical fault conditions from the estimated state of the valve and patterns in the residual classes. The ability to diagnose certain faults in the system depends on the state of the thermostatic valve. The diagnostic systems have been tested with data obtained by experimental simulation of a number of target fault conditions on a diesel generator set test bed. In five test cases for separate cooling system operating conditions, the diagnostic system's successful diagnosis rate ranged between 73 and 97.7 per cent of the test data.

Model-based condition monitoring of an actuator system driven by a brushless DC motor

Air pressure in passenger aircrafts is controlled by opening and closing an outflow valve, which serves to release air from the cabin. Early identification of potential malfunctions in the underlying actuator-driven system is important both from the point of view of cost-efficient maintenance as well as overall safety. This paper presents a system for diagnosing faults in a valve actuator driven by a brushless DC motor during off-line pre-flight tests. First, a simple mathematical model of the drive is developed. Based on this, parity relations are derived with the aim of fault detection. Fault isolation is realised by means of an approximate reasoning technique referred to as transferable belief model (TBM). The problem of distinguishing between faults with the same fault signatures is addressed. It is shown that additional improvements in terms of diagnostic resolution can be achieved by applying parameter estimation. The proposed FDI scheme is tested on the actual drive under various faults. The achieved performance features high diagnostic resolution, diagnostic stability and accuracy.

Model-based condition monitoring of gas turbines for power generation duty

This letter has presented an overview of activities to date with respect to the development and demonstration of anomaly detection functions, which analyze key parameters from an industrial gas turbine during its starting sequence. The software modules have been shown to be able to successfully detect anomalies in the start sequences. The software has been developed using a combination of simulated and actual plant performance data and is currently in the process of being implemented in the field. In the longer term, as the level of operational experience and knowledge grows, the anomaly detection functions can be augmented to include prognostic and diagnostic functionality. This will permit not only the detection of anomalous behavior but also the provision of information to plant operators as to the suspected cause of the anomaly.

A Concept of Teaching Model-Based Condition Monitoring

Maintaining the technical currency becomes one of the challenging tasks facing industrial professionals. There is a strong need to extend the traditional topics such as feedback control, with topics concerning condition monitoring and automatic fault diagnosis. A framework for disseminating basic underlying knowledge through the life-cycle paradigm is presented. The paper addresses the design requirements and practical guidelines with experimental validation on laboratory test processes. The approach should help the practitioners to better understand the potentials of model-based fault diagnosis in industrial practice.