WO2002018962A1

WO2002018962A1 - Computerized method and system for determining degradation of dc link capacitors

Info

Publication number: WO2002018962A1
Application number: PCT/US2000/025651
Authority: WO
Inventors: Ajith Kuttannair Kumar; Bret Dwayne Worden; Jason A. Dean
Original assignee: General Electric Co
Current assignee: General Electric Co
Priority date: 2000-08-30
Filing date: 2000-09-19
Publication date: 2002-03-07
Anticipated expiration: 2003-02-28
Also published as: CA2387969A1; AU2002237013A1

Abstract

System and method for determining degradation of one or more respective capacitors (e.g., 54, 154) in a DC link of a power converter system is provided. The system includes a signal monitor (202) configured to monitor a respective signals indicative of an estimated capacitor value based on a first set of operating and environmental conditions. Memory (210) is configured to store a nominal capacitor value based on a second set of operating and environmental conditions. A database (214) is configured to store the adjusted capacitor value to generate historical data of the respective capacitor value. A diagnostics module (216) is configured to execute analysis on the historical data to determine the presence of incipient faults in the respective DC link capacitor.

Description

COMPUTERIZED METHOD AND SYSTEM

FOR DETERMINING DEGRADATION

OF DC LINK CAPACITORS

BACKGROUND OF THE INVENTION

The present invention relates generally to power conversion systems, such as inverters used in locomotives, electric or hybrid buses, power generation systems, etc., having one or more capacitors in a DC link, and, more particularly, to system and method for determining degradation of the DC link capacitors. The description below is given for purposes of illustration and not of limitation in the context of a locomotive. As will be appreciated by those skilled in the art, a locomotive is a complex electromechanical system comprised of several complex subsystems. Each of these subsystems, such as the DC link capacitors, is built from components which over time fail. The ability to automatically predict failures before they occur in the locomotive subsystems is desirable for several reasons. For example, in the case of the DC link capacitors, that ability is important for reducing the occurrence of primary failures which result in stoppage of cargo and passenger transportation. These failures can be very expensive in terms of lost revenue due to delayed cargo delivery, lost productivity of passengers, other trains delayed due to the failed one, and expensive on-site repair of the failed locomotive. Further, some of those primary failures could result in secondary failures that in turn damage other subsystems and/or components.

It will be further appreciated that the ability to predict failures before they occur in the DC link capacitors would allow for conducting condition-based maintenance, that is, maintenance conveniently scheduled at the most appropriate time based on statistically and probabilistically meaningful information, as opposed to maintenance performed regardless of the actual condition of the subsystems, such as would be the case if the maintenance is routinely performed independently of whether the subsystem actually needs the maintenance or not. Needless to say, a condition- based maintenance is believed to result in a more economically efficient operation and maintenance of the locomotive due to substantially large savings in cost. Further, such type of proactive and high-quality maintenance will create an immeasurable, but very real, good will generated due to increased customer satisfaction. For example, each customer is likely to experience improved transportation and maintenance operations that are even more efficiently and reliably conducted while keeping costs affordable since a condition-based maintenance of the locomotive will simultaneously result in lowering maintenance cost and improving locomotive reliability. As suggested above, it is desired to develop a predictive diagnostic strategy that is suitable to predict incipient failures in the DC link capacitors. Previous attempts to overcome the above-mentioned issues have been generally limited to diagnostics after a problem has occurred, as opposed to prognostics, that is, predicting a failure prior to its occurrence. For example, previous attempts to diagnose problems occurring in a locomotive have been performed by experienced personnel who have in-depth individual training and experience in working with locomotives. Typically, these experienced individuals use available information that has been recorded in a log. Looking through the log, the experienced individuals use their accumulated experience and training in mapping incidents occurring in locomotive subsystems to problems that may be causing the incidents. If the incident-problem scenario is simple, then this approach works fairly well for diagnosing problems. However, if the incident-problem scenario is complex, then it is very difficult to diagnose and correct any failures associated with the incident and much less to prognosticate the problems before they occur. Presently, some computer-based systems are being used to automatically diagnose problems in a locomotive in order to overcome some of the disadvantages associated with completely relying on experienced personnel. Once again, the emphasis on such computer-based systems is to diagnose problems upon their occurrence, as opposed to prognosticating the problems before they occur. Typically, such computer-based systems have utilized a mapping between the observed symptoms of the failures and the equipment problems using techniques such as a table look up, a symptom-problem matrix, and production rules. These techniques may work well for simplified systems having simple mappings between symptoms and problems. However, complex equipment and process diagnostics seldom have simple correspondences between the symptoms and the problems. Unfortunately, as suggested above, the usefulness of these techniques have been generally limited to diagnostics and thus even such computer-based systems have not been able to provide any effective solution to being able to predict failures before they occur.

In view of the above-mentioned considerations, there is a general need to be able to quickly and efficiently prognosticate any failures before such failures occur in the DC link capacitors of the locomotive, while minimizing the need for human interaction and optimizing the repair and maintenance needs of the subsystem so as to able to take corrective action before any actual failure occurs.

SUMMARY OF THE INVENTION

Generally speaking, the foregoing needs are fulfilled by providing a computerized method for determining degradation of one or more respective capacitors in a DC link of a power converter system. The method allows for monitoring a signal indicative of an estimated capacitor value based on a first set of operating and environmental conditions. The method further allows for providing a nominal capacitor value based on a second set of operating and environmental conditions and for storing the adjusted capacitor value to generate historical data of the respective capacitor value. Analysis is executed on the historical data to determine the presence of incipient faults in the respective DC link capacitor.

The present invention generally fulfills the foregoing needs by providing in another aspect thereof a system for predicting faults of one or more respective capacitors in a DC link of a power converter system. The system comprises a signal monitor configured to monitor a respective signals indicative of an estimated capacitor value based on a first set of operating and environmental conditions. Memory is configured to store a nominal capacitor value based on a second set of operating and environmental conditions. A database is configured to store the adjusted capacitor value to generate historical data of the respective capacitor value. A diagnostics module is configured to execute analysis on the historical data to determine the presence of incipient faults in the respective DC link capacitor. DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic of an exemplary power conversion system embodying one aspect of the present invention;

FIG. 2 is a block diagram of an exemplary processor including respective modules that may be used for detecting incipient failures of DC link capacitors, either onboard the vehicle, at a remote diagnostic service center, or both;

FIG. 3, made up of FIGS. 3A and 3B, is a flow charts illustrating exemplary actions that may be executed by the processor of FIG. 2;

FIG. 4 is a plot illustrating an exemplary voltage discharge signal across a respective DC link capacitor; Fig. 5 is a plot illustrating an exemplary trend over time in the value of a respective DC link capacitor, which trend may be indicative of an incipient fault in the capacitor; and

FIG. 6 is a plot illustrating an exemplary shift in the value of a respective DC link capacitor, which shift may be indicative of a fault condition in the capacitor.

Before any embodiment of the invention is explained in detail, it is to be understood that the invention is not limited in its application to the details of construction and the arrangements of components set forth in the following description or illustrated in the drawings. The invention is capable of other embodiments and of being practiced or being carried out in various ways. Also, it is to be understood that the phraseology and terminology used herein is for the purpose of description and should not be regarded as limiting.

DETAILED DESCRIPTION OF THE INVENTION

To generate an understanding of the present invention, reference is first made to FIG. 1, which shows an exemplary power conversion system 10 for conveying power between a DC power source 12 and an electric load comprising first and second motors 16 and 18 electrically connected in parallel. By way of example, motors 16 and 18 may be three-phase AC induction-type traction motors used for propelling a vehicle, such as a transit vehicle or locomotive (not shown), and the DC source 12, in the case of a transit vehicle, may comprise a wayside power distribution system including either a third rail or an overhead catenary with which a current collector on the vehicle makes sliding or rolling contact. It will be appreciated that the power source in a locomotive could be the output of a rectifier device that receives power from a suitable alternator onboard the locomotive. In FIG. 1, the relatively positive line 17 represents such a current collector, and the negative line 19 represents a conductor in contact with a grounded rail serving as the other terminal of the DC source.

The power conversion system 10 includes a controllable DC-to-AC converter, such as an inverter 20 having a pair of DC terminals 22 and 24 on its source side and a set of three AC terminals 26, 28, and 30 on its motor side. The DC terminal 22 is connected via a conductor 40 to the line 17 of the positive potential, and the terminal 24 is connected via relatively negative conductors 41 and 42 to the other line 19 of the DC power source 12. The conductors 40-42 thus serve as a DC link between the source 12 and the inverter 20. The AC terminals 26, 28, and 30 are respectively connected to the three different phases of each of the AC motors 16 and 18.

During motoring, i.e., when electrical power is being conveyed from the source to the motors, direct current is supplied to the inverter through its DC terminals 22 and 24, and the inverter operates to convert this direct current into alternating current supplied through AC terminals 26, 28, and 30 to the motors 16 and 18. The inverter is controlled by suitable controls which may be internal or external (such as shown by a controller 70 in FIG. 1) for varying the amplitude and frequency of the alternating voltage at its AC terminals to provide the needed acceleration or deceleration of the vehicle driven by the motors 16 and 18. As will be appreciated by those skilled in the art, any well known pulse width modulation (PWM) control technique, such as sine-triangle comparison, space vector modulation or duty cycle area modulation, can be used for inverter operation. The controller may comprise a computer or a microprocessor, for example.

The power conversion system 10 has alternative motoring and electrical braking modes of operation. During electrical braking, each of the motors 16 and 18 operates as an electrical generator driven by the inertia of the transit vehicle, returning power to the system 10. This return power flows through the inverter 20 in a reverse direction from the direction of flow during motoring and appears as a unipolarity voltage and direct current at the DC terminals 22 and 24.

The conversion system 10 is designed to provide for both dynamic braking and regenerative braking. Dynamic braking is effected by connecting across the conductors 40 and 42 of the DC link a dynamic braking resistor 34 through which at least some of the braking current can be made to flow, thus dissipating electric energy in the form of heat. For controlling current in the resistor 34, a DC-to DC converter, such as a DC power chopper 36 is connected in series therewith. As is well known to persons skilled in the art, the chopper 36 is a solid-state switch that can be repetitively turned on and off by controller 70, for example, which, in one form, controls the ratio of the "on time" to the "off time" during successive intervals each of fixed duration. The average magnitude of current in the resistor varies directly with this ratio.

For attenuating harmonics generated by operation of the power conversion system 10 and for effectively isolating the system from any undesirable electrical transients in the DC power source 12, a single-stage electrical filter of the L-C type is included in the connections between the source 12 and the inverter 20. The filter may comprise a series line-filter inductor 62 connected in the path of current between the line 17 and the positive conductor 40 of the DC link, and shunt capacitors 54 and 56. The first capacitor 54 (referred to as the DC link capacitor) spans the conductors 40 and 41 and thus is directly connected between the two DC terminals 22 and 24 of the inverter. The second capacitor 56 (referred to as the line capacitor) spans the conductors 40 and 42 and thus is interconnected in parallel with the capacitor 54. The filter serves to attenuate harmonics generated by operation of the inverter 20 so that such harmonics are isolated from the DC source 12 and will not interfere with the usual wayside signaling system. During motoring, the DC link capacitor 54 serves mainly as the required "stiff voltage source for the inverter 20. In the electrical braking mode of operation, the line capacitor 56 serves mainly as a filter for the chopper 36, providing a temporary path for braking current during the off periods of the chopper in the dynamic braking circuit (which comprises resistor 34 and chopper 36) which, as can be seen in FIG. 1, is connected across this capacitor. For disconnecting the power conversion system 10, an electric circuit breaker 60, applied in a conventional manner, is provided between the system and the DC power source. This circuit breaker 60 is operated by the controller 70 in response to an operator's command or to fault conditions forcing the circuit breaker to an open condition. In the illustrative system of FIG. 1, a closed contactor 66 may represent a current collector in sliding contact with a wayside conductor. The contactor 66 may be a pantograph for an overhead conductor or a spring biased shoe for contacting a third rail.

Current to the propulsion system is monitored by a current monitor 68 of a type well known in the art. Monitor 68 generates a signal I_I representative of the magnitude and frequency of current in the DC conductor 40. The voltage at DC link conductor 40 is indicated by signal V_L obtained through buffer resistor 76 connected to conductor 40. The filter capacitors 54 and 56 can be discharged through discharge resistor 78 via discharge contactor 80. As shown in FIG. 4, and further described below, a voltage signal across each respective DC link capacitor may be monitored during respective discharge conditions to record the discharge time τ of the DC link capacitor. The recorded data may be accumulated and monitored over time, locally or remotely, to detect trends and/or shifts indicative of incipient faults in the DC link capacitor since the value of the time constant for discharging the capacitor from a known starting value to a predefined lesser value is directly proportional to the actual value of the capacitor.

In a typical transit vehicle, there may be a second voltage source inverter, in addition to the inverter described above, for supplying alternating current to two more traction motors for propelling the vehicle. FIG. 1 illustrates a power conversion system including such an additional inverter and with third and fourth AC motors being connected to the set of the AC terminals on its motor side. Components common to those described above are designated by the same reference numerals plus 100.

The positive DC terminal 122 on the source side of the second inverter 120 is connected, via the conductor 40 of the DC link, to the line 17 of positive potential, and the relatively negative DC terminal 124 is connected, via a separate conductor 141 and the common conductor 42, to the other line 19 of the DC power source 12. The AC terminals 126, 128, and 130 of the inverter 120 are respectively connected to three different phases of each of the AC motors 116 and 118. A second DC link capacitor 154 individually associated with the inverter 120, is directly connected between the DC terminals 122 and 124, and a line capacitor 56 shared by both of the inverters 20 and 120 and both of the choppers 36 and 136 span the conductors 40 and 42 of the DC link capacitors 54 and 154 during the motoring mode of operation of the conversion system.

As is shown FIG. 1, a second dynamic braking circuit, comprising the series combination of another dynamic braking resistor 134 and a second electric power chopper 136, is connected between the DC link conductors 40 and 42 and hence across the line capacitor 56. In addition to sharing the common shunt line capacitor 56, the two inverters 20 and 120 utilize the same series line-filter inductor 62 which is connected on the DC power source side of the capacitor 56 between the DC link conductor 40 and the line 17. The two inverters 20 and 120 can be controlled by controller 70 which responds to alternative command signals from interlocked throttle and brake controllers 72 and 74, respectively. The controller 70 also receives feedback signals representative of sensed values of voltage, current, and other selected variables in each of the inverters 20 and 120. To operate in a dynamic braking mode, the controller 70 derives a train of suitably timed periodic signals that determine the repetitive on and off intervals of the choppers 36 and 136, and it varies the ratio of these intervals as desired. As suggested above, it is desirable to detect degradation and incipient faults of the DC link capacitors.

A processor system 200 may be coupled to the respective circuit made up of DC link capacitor 54 and discharge resistor 78 and to the circuit made up of DC link capacitor 154 and discharge resistor 178 to monitor and collect a voltage signal that would allow the processor to assess the condition of a respective DC link capacitor. The monitored signal is indicative of an estimated capacitor value based on a first set of operating and environmental conditions, such as ambient temperature, locomotive- to-locomotive variation, discharge resistor variation, etc. As suggested above, processor 200 may include a timer that allows for measuring, at times when the DC power supply, inverter and motors are inactive, the discharge time of the capacitor, or more specifically allows for measuring the amount of time it takes the monitored voltage signal to reach a predefined level from a known starting voltage level. The predefined level may vary as a function of the starting voltage level. Using basic RC circuit principles, one can readily calculate the value of the DC link capacitor and populate a database 214 (FIG. 2) containing historical data values of each respective DC link capacitor. It will be appreciated that processor system 200 may be installed on-board, that is, local relative to system 10, or could be installed at a remote diagnostics service center that would allow a service provider to monitor a fleet of locomotives using suitable diagnostic tools 216 that when run on the database of historical data of respective data link capacitors would allow a trend detection module 218 for detecting trends, such as shown in FIG. 5, or for detecting sudden shifts in the value of the respective DC link capacitor, such as shown in FIG. 6. A fault prediction module 220 would allow for declaring an incipient fault condition in the DC link capacitor, if, for example, the trend in the historical values of the capacitors exceeds a predefined rate of change, or, if, for example, the shift in the capacitor value exceeds a predefined level. The fault prediction module could be configured to provide based on the historical data, a probabilistic determination of when a DC link capacitor failure is likely to occur. By way of example, signal transmission from the locomotive to the diagnostics site could be implemented using a suitable transmitter 222 (FIG. 2) that may be part of a wireless data communication system (not shown).

FIG. 2 shows further details regarding processor system 200 that includes a signal monitor 202 that receives the voltage signal indicative of the estimated capacitor value based on the first set of operating and environmental conditions, that is, conditions affecting the capacitor being evaluated. As shown in FIG. 2, an adjuster module 204, drawn in dashed lines, may be optionally coupled to signal monitor 202 to adjust the monitored signal for deviations from a nominal capacitance value that may be based on a second set operating and environmental conditions to generate an adjusted capacitor value, that is, the second set of operating and environmental conditions may correspond to ideal operating and environmental conditions as opposed to the actual conditions being experienced by a given capacitor. The adjusted capacitor value may be derived through suitable adjusting factors that may be analytically and/or experimentally derived by collecting actual data and/or simulation data that takes into account multiple scenarios of locomotive operation, and should preferably include a sufficiently large sample of locomotives and/or propulsion subsystems so as to statistically demonstrate the validity and accuracy of the correcting factors. A submodule 206 in adjuster module 204 allows for retrieving and/or generating the respective adjusting factors.

A comparator module 208 may be coupled to signal monitor module 202 to receive the estimated capacitor value. In the event adjuster module 204 is used, then comparator module 208 may be coupled to adjuster module 204 to receive the adjusted capacitor value. In either case, comparator module 208 allows for comparing the value of the capacitor value against the nominal capacitor value to determine the condition of the respective DC link capacitor. As suggested above, the estimated value of the capacitor, as estimated by measuring its discharge time characteristics, may be adjusted for deviations due to the various external factors or may be the unadjusted estimated capacitor value. A memory 210 may be used for storing a programmable look-up table (LUT) for storing a first range of capacitor values so that estimated capacitor values within that first range are indicative of acceptable DC link capacitor performance. Memory 210 may further be used for storing a second range of capacitor values so that estimated capacitor values within the second range are indicative of degraded DC link capacitor performance. Memory 210 may be further used to store the nominal capacitor value. It will be appreciated that the techniques of the present invention need not be limited to first and second ranges being that additional ranges may be employed if finer gradation is desired.

A status module 212 may be used for generating and issuing a signal indicative of a degraded DC link capacitor performance when the capacitor value is beyond the first range of stored capacitor values and within the second range of capacitor values, that is, a cautionary signal that could be analogized to a yellow light in a traffic light. Similarly, module 212 may be used for generating and issuing a signal indicative of unacceptable DC link capacitor performance when the capacitor value is outside the second range of capacitor values, that is, a warning signal that could be analogized to a red light in a traffic light that requires immediate action by the operator, such as performance reduction, scheduling a repair, or replacement of a given DC link capacitor. In one exemplary implementation, capacitor values within about 16% of the adjusted nominal value of the capacitor may be considered normal values. Capacitor values within about 33% to about 50% relative to the adjusted nominal value of the capacitor may result in degraded operation of the locomotive while capacitor values below 50% of the nominal value of the capacitor will result in locomotive shut down. It will be appreciated that the foregoing numerical ranges are merely illustrative of one exemplary embodiment and are not meant to restrict this aspect of the present invention.

FIG. 4 is an exemplary flow chart of one aspect of the method of the present invention for determining degradation in the condition of the DC link capacitors of the locomotive. Upon start of operations in step 300, step 302 allows for monitoring a signal indicative of an estimated capacitor value. Optional step 304, represented in a block drawn with dashed lines, allows for adjusting the value of the monitored signal for deviations from a nominal capacitor value due to predetermined external variables or conditions to generate an adjusted capacitor value. Step 306 allows for comparing the value of the, adjusted or unadjusted, capacitor value against the nominal capacitor value to determine the condition of the respective DC link capacitor. Step 308 allows for determining whether the estimated capacitor value is within the first range of capacitor values stored in the LUT. If the answer is yes, then step 310 allows for declaring that the respective DC link capacitor has acceptable performance and the process is ready to start another iteration through connecting node B. If in step 308 the answer is no, then through connecting node A, step 312 allows for determining whether the estimated capacitor value is within a second range of capacitor values stored in the LUT. If the answer is yes, then step 314 allows for declaring that the respective DC link capacitor has degraded. If the answer is no, then step 318, prior to return step 324, allows for determining whether the capacitor value is outside the second range of capacitor values stored in the LUT. If the answer is yes, then step 320 allows for declaring or indicating an unacceptable DC link capacitor performance. This indication will generally require suitable corrective action by the user. As discussed in the context of FIG. 3, step 316 allows for issuing the yellow cautionary signal, that is, a signal indicative of DC link capacitor degradation. Similarly, step 322 allows for issuing the high-level warning signal that could be analogized to a red light in a traffic light that requires immediate action by the operator. It will be appreciated that the detection technique of the present invention can be conveniently "fine-tuned" or optimized by collecting actual locomotive or simulation data that allows for measuring the predicting accuracy of the detection algorithm by using well-understood statistical tools that enable to compute the probability that in fact an actual degradation condition will be detected.

It will be understood that the specific embodiment of the invention shown and described herein is exemplary only. Numerous variations, changes, substitutions and equivalents will now occur to those skilled in the art without departing from the spirit and scope of the present invention. Accordingly, it is intended that all subject matter described herein and shown in the accompanying drawings be regarded as illustrative only and not in a limiting sense and that the scope of the invention be solely determined by the appended claims.

Claims

WHAT IS CLAIMED IS:

1. A computerized method for determining degradation of one or more respective capacitors (e.g., 54, 154) in a DC link of a power converter system, the method comprising: monitoring a signal indicative of an estimated capacitor value based on a first set of operating and environmental conditions; providing a nominal capacitor value based on a second set of operating and environmental conditions; adjusting the value of the estimated capacitor value to account for any differences between the first and second set of conditions; storing the adjusted capacitor value to generate historical data of the respective capacitor value; executing analysis on the historical data to determine the presence of incipient faults in the respective capacitor.

2. The method of claim 1 wherein said method is locally executed relative to the power converter system.

3. The method of claim 1 further comprising transmitting the monitored signal indicative of the estimated capacitor value to a remote diagnostic service center.

4. The method of claim 3 wherein the adjusting, storing and executing steps are executed at said service center.

5. The method of claim 1 wherein one or more of the steps executed subsequent to the monitoring step are executed at a remote diagnostic service center.

6. The method of claim 1 further comprising a step of storing a first range of capacitor values.

7. The method of claim 6 wherein adjusted capacitor values within that first range are indicative of acceptable DC link capacitor performance.

8. The method of claim 7 further comprising a step of storing a second range of cap acitor values .

9. The method of claim 8 wherein adjusted capacitor values within that second range are indicative of degraded DC link capacitor performance.

10. The method of claim 9 further comprising a step of issuing a signal indicative of an alert status for the DC link capacitor when the estimated capacitor values are within the second range of capacitor values.

11. The method of claim 9 further comprising a step of issuing a signal indicative of unacceptable DC link capacitor performance when the estimated capacitor values are outside the second range of capacitor values.

12. The method of claim 1 wherein the monitoring step comprises monitoring a voltage signal indicative of the time for discharging the respective capacitor to a respective voltage level through a respective discharging resistor.

13. The method of claim 1 wherein the power converter system comprises an inverter coupled to drive an AC traction motor in a vehicle.

14. The method of claim 13 wherein the vehicle comprises a locomotive.

15. The method of claim 1 wherein the adjusting step comprises generating a respective adjusting factor for the respective capacitor.

16. The method of claim 1 wherein the presence of the incipient faults is determined upon detecting a respective trend in the estimated capacitor value.

17. The method of claim 1 wherein the presence of the incipient faults is determined upon detecting a respective shift in the estimated capacitor value.

18. A system for determining degradation of one or more respective capacitors (e.eg., 54, 154) in a DC link of a power converter system, the system comprising: a signal monitor (202) configured to monitor a respective signal indicative of an estimated capacitor value based on a first set of operating and environmental conditions; memory (210) configured to store a nominal capacitor value based on a second set of operating and environmental conditions; an adjuster module (204) configured to adjust the value of the estimated capacitor value to account for any differences between the first and second set of conditions; a database (214) configured to store the adjusted capacitor value to generate historical data of the respective capacitor value; and a diagnostics module (216) configured to execute analysis on the historical data to determine the presence of incipient faults in the respective capacitor.

19. The fault-predicting system of claim 18 further comprising a status alert module (212) configured to issue a signal indicative of an alert status for the respective DC link capacitor when the estimated capacitor values are within a predefined range of capacitor values.

20. The fault-predicting system of claim 19 wherein the status alert module is further configured to issue a signal indicative of unacceptable DC link capacitor performance when the estimated capacitor values are beyond the predefined range of capacitor values.

21. The fault-predicting system of claim 18 wherein the signal monitor is coupled to monitor a voltage signal indicative of the time for discharging the respective capacitor to a respective voltage level through a respective discharge resistor.

22. The fault-predicting system of claim 18 wherein the power converter system comprises an inverter (e.g., 20) coupled to drive an AC traction motor (e.g., 18) in a vehicle.

23. The fault-predicting system of claim 18 wherein said system is locally situated relative to the power converter system.

24. The fault-predicting system of claim 18 further comprising a transmitter (222) configured to transmit the monitored signal indicative of the estimated capacitor value to a remote diagnostic service center.

25. The fault-predicting system of claim 18 wherein the database (214) and diagnostic module (216) are situated at said service center.

26. A method for predicting faults of one or more respective capacitors (e.g., 54, 154) in a DC link of a power converter system, the method comprising: monitoring a signal indicative of an estimated capacitor value, said signal comprising a voltage signal indicative of the time for discharging the respective capacitor to a respective voltage level through a respective discharge resistor; comparing the estimated value of the capacitor against a nominal capacitor value to determine whether the capacitor value is within an acceptable range; storing the estimated capacitor value to generate historical data of the respective capacitor value; and executing analysis on the historical data to determine the presence of incipient faults in the respective DC link capacitor.

27. A system for predicting faults of one or of one or more respective capacitors (e.g., 54, 154) in a DC link of a power converter system, the system comprising: a signal monitor (202) configured to monitor a respective signal indicative of an estimated capacitor value, said signal comprising a voltage signal indicative of the time for discharging the respective capacitor to a respective voltage level through a respective discharge resistor; a comparator module (208) coupled to receive the estimated capacitor value, the comparator module configured to compare the estimated value of the capacitor against a nominal capacitor value to determine whether the capacitor value is within an acceptable range; a database (214) configured to store the estimated capacitor value to generate historical data of the respective capacitor value; and a diagnostics module (216) configured to execute analysis on the historical data to determine the presence of incipient faults in the respective capacitor.