# US 2017/0285086 A1 · Active shaft grounding system with diagnostic waveform analysis

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2017/0285086 A1
- Document ID: US20170285086A1
- Status: Published application
- Kind: A1
- Application number: 15/362,875
- Filed: 2016-11-29
- Published: 2017-10-05
- Earliest claimed: 2016-04-05
- Assignees: Siemens Energy, Inc.
- Applicants: Siemens Energy, Inc.
- Inventors: Edward David Thompson
- Web page: https://patentgrep.com/patent/US20170285086A1

## CPC

- G01R 31/50: Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections (testing of sparking plugs H01T13/58)
- G01R 19/04: Measuring peak values {or amplitude or envelope} of AC or of pulses
- G01R 31/34: Testing dynamo-electric machines
- G01R 31/343: {in operation}
- G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12)

## Abstract

A system that applies a counteracting voltage or current to a rotating shaft to minimize a grounding voltage signal of the shaft, measures and analyzes the counteracting signal, and provides expert system logic that compares prior learned waveforms and models of baseline, fault, and degradation waveforms to operational waveforms to determine and predict faults and degradation events. Self-learning logic analyzes the operational waveforms to look for changes, and finds or predicts fault and degradation events in relation to archived characteristics of earlier waveforms. It then adds characteristics of predictive waveforms to the database of model waveforms, and updates rules and thresholds in the expert logic based on the found predictors. It may further calculate and continuously refine a counteracting signal waveform to minimize the shaft grounding waveform.

## Claims

### Claim 1

A computer-implemented method for operating a shaft grounding system, the method comprising executing on a processor the steps of:
receiving a signal associated with a shaft of a rotating equipment, wherein the signal is responsive to a counteracting voltage or current applied to the shaft to reduce a grounding voltage or current of the shaft;
characterizing a signal waveform of said signal over time to diagnose a condition of the rotating equipment; and
providing an intervention for the rotating equipment responsive to the diagnosis.

### Claim 2 (depends on 1)

The method of claim 1, wherein the processor further executes the steps of:
comparing a shape aspect of the signal waveform to a shape aspect of a model waveform in a database of baseline and fault model waveforms; and
providing the intervention for the rotating equipment based on the step of comparing when the signal waveform indicates a behavior of the rotating equipment that deviates from an expected behavior thereof represented by the model waveforms.

### Claim 3 (depends on 2)

The method of claim 2, wherein the step of providing the intervention comprises producing an automatic intervention via an output from the processor to a control system of the rotating equipment that changes an operating behavior of the rotating equipment.

### Claim 4 (depends on 1)

The method of claim 1, wherein the processor further executes the steps of:
identifying a repeating pattern of faults indicated by the signal waveform;
comparing the repeating pattern to a predictive fault repetition pattern stored in a database to determine the condition of the rotating equipment.

### Claim 5 (depends on 1)

The method of claim 1, wherein the processor further executes the steps of:
identifying and characterizing a series of repeating anomalies in the signal waveform; and
diagnosing the condition of the rotating equipment based on at least one of a shape aspect, progressive shape changes, and a frequency of occurrence of the anomalies of the series.

### Claim 6 (depends on 1)

The method of claim 1, wherein the processor further executes the steps of:
self-learning characteristics of the signal waveform that statistically precede a non-periodic anomaly in the signal waveform; and
diagnosing the condition of the rotating equipment responsive to a prediction of the non-periodic anomaly based on the step of self-learning.

### Claim 7 (depends on 1)

The method of claim 1, wherein the processor further executes the steps of:
collecting the signal as a time series of voltage or current at a sample rate of at least 2 kHz; and
characterizing the time series by at least one of a wavelet transform, a Fourier transform, a principal component analysis, a neural network, and a support vector machine algorithm; and
correlating the characterized time series with a baseline waveform model and a fault waveform model to diagnose the condition of the rotating equipment.

### Claim 8 (depends on 1)

The method of claim 1, wherein the processor further executes the steps of:
creating and storing a plurality of baseline waveform models in a database that characterize acceptable baseline conditions of the rotating equipment;
creating and storing a plurality of fault waveform models in the database that characterize degraded or fault conditions of the rotating equipment;
creating a signal waveform model that characterizes the signal waveform;
integrating operational parameters of the rotating equipment under given operating conditions thereof directly into the signal waveform model, the baseline waveform models, and the fault waveform models; and
correlating the signal waveform model to at least one of a baseline waveform models and a fault waveform model from the database to diagnose the condition of the rotating equipment.

### Claim 9 (depends on 1)

The method of claim 1, wherein the processor further executes the steps of:
creating and storing a plurality of baseline waveform models in a database that characterize acceptable baseline waveforms for respective sub-ranges of operating conditions of the rotating equipment;
creating and storing a plurality of fault waveform models in the database that characterize waveforms of degraded or fault conditions for the respective sub-ranges of operating conditions of the rotating equipment;
inputting operational data related to the rotating equipment; and
selecting a waveform model from the database based on the operational data, and comparing the selected waveform model to a model of the signal waveform to diagnose the condition of the rotating equipment.

### Claim 10 (depends on 9)

The method of claim 9, wherein the processor further executes the steps of:
identifying faults and degradations in the rotating equipment by executing expert system logic that uses at least one of a Fourier transform, a wavelet transform, a principle component analysis, a neural network, and a support vector machine to model and compare the signal waveform to the selected waveform model in view of the operational data;
archiving the models of the signal waveforms over time;
analyzing changes in the archived signal waveforms that precede fault and degradation events identified by the expert system logic; and
providing self-learning by automatically updating the fault waveform models in the database and updating the expert system logic, or parameters thereof, to provide a prediction of future faults and degradations based on recognition of the precedent changes in the archived signal waveforms.

### Claim 11 (depends on 1)

The method of claim 1, wherein the processor further executes the steps of:
creating and storing models of expected waveforms of the signal during well-tuned operations of the rotating equipment based on the characterization of the signal waveform after a manual tuning and verification thereof;
incorporating operational parameters of the rotating equipment directly into the models of the expected waveforms, wherein each said model of an expected waveform provides a specification envelope for an acceptable waveform under a given operating condition; and
modeling signal waveforms of the rotating equipment, and indicating a fault or predicted problem if a component of a signal waveform model falls outside the specification envelope of an expected waveform model under the given operating condition.

### Claim 12 (depends on 1)

The method of claim 1, wherein the processor further executes the steps of:
creating and storing installation-specific models of expected waveforms of the signal based on the characterization of the signal waveform, each said installation-specific model comprising a specification envelope for a waveform under a given operating condition of the rotating equipment at a given installation;
creating a set of modified models by enlarging the specification envelopes of the installation-specific models, wherein the enlarged specification envelopes apply to a given machine model of the rotating equipment for a range of installations;
creating a set of further modified models by further enlarging the specification envelopes of the installation-specific models, wherein the further enlarged specification envelopes apply to a machine type of the rotating equipment including plural models thereof; and
further comprising providing the modified models and the further modified models to a database accessible to multiple installations of machines of the machine type of the rotating equipment;
wherein at least some of said machines of the machine type comprise a processor that executes the steps of indicating a fault or predicted problem if a characteristic of a signal waveform of the machine falls outside one of the enlarged specification envelopes or one of the further enlarged specification envelopes.

### Claim 13 (depends on 1)

The method of claim 1, wherein the processor further executes the steps of:
creating and storing models of expected waveforms of the signal, wherein each said model comprises an installation-specific specification envelope for characteristics of the signal in a given installation of the rotating equipment;
creating machine model specification envelopes for the expected waveform models by enlarging the installation-specific specification envelopes to create machine model specification envelopes that apply to a given machine model of the rotating equipment for a range of installations thereof;
creating machine type specification envelopes for the expected waveform models by further enlarging the installation-specific specification envelopes to create machine type specification envelopes that apply to a given machine type of the rotating equipment for a range of machine models thereof;
further comprising providing the expected waveform models, the machine model specification envelopes thereof, and the machine type specification envelopes thereof to a database; and
modeling signal waveforms in an additional rotating equipment of the given machine type to diagnose a condition of the additional rotating equipment.

### Claim 14 (depends on 1)

The method of claim 1, further comprising applying the counteracting voltage or current to the shaft to reduce the grounding voltage or current of the shaft, wherein the processor further executes the steps of determining and predicting faults and potential degradations in the rotating equipment by characterizing and analyzing the waveform of the counteracting voltage or current of the shaft in comparison to a waveform of the grounding voltage or current of the shaft.

### Claim 15 (depends on 1)

The method of claim 1, wherein the processor further executes the steps of:
determining a response delay between an application of the counteracting voltage or current and a respective reduction in the grounding voltage or current by comparing characteristics of the counteracting voltage or current to corresponding response characteristics of the grounding voltage or current; and
analyzing the response delay to diagnose the condition of the rotating equipment.

### Claim 16 (depends on 1)

The method of claim 1, wherein the processor further executes the steps of:
predicting a continuing waveform of the grounding voltage or current based on periodic aspects thereof;
computing a waveform for the counteracting voltage or current that will minimize the predicted continuing waveform of the grounding voltage;
applying the counteracting voltage or current to the shaft in a form of the counteracting waveform; and
diagnosing the condition of the rotating equipment by analyzing characterized waveforms of the counteracting voltage or current and the grounding voltage or current.

### Claim 17 (depends on 1)

The method of claim 1, wherein the processor further executes the steps of characterizing a waveform of the grounding voltage or current, and analyzing at least one of the following parameters to diagnose the condition of the rotating equipment:
a) the grounding waveform with the counteracting waveform applied;
b) a waveform calculated as a mathematical difference between the grounding waveform and the counteracting waveform with the counteracting waveform applied;
c) a waveform calculated as a mathematical difference between the grounding waveform and the counteracting waveform with the counteracting waveform not applied;
d) a phase difference between specific corresponding features in the grounding waveform and the counteracting waveform; and
e) a difference in waveform shape between the grounding waveform and the counteracting waveform.

### Claim 18 (depends on 1)

The method of claim 1, wherein the processor further executes the steps of characterizing a waveform of the grounding voltage or current, and analyzing at least two of the following parameters to diagnose the condition of the rotating equipment:
a) the counteracting waveform;
b) the grounding waveform with the counteracting waveform applied;
c) the grounding waveform without the counteracting waveform applied;
d) a waveform calculated as a mathematical difference between the grounding waveform and the counteracting waveform with the counteracting waveform applied;
e) a waveform calculated as a mathematical difference between the grounding waveform and the counteracting waveform with the counteracting waveform not applied;
f) a phase difference between specific corresponding features in the grounding waveform and the counteracting waveform; and
g) a difference in waveform shape between the grounding waveform and the counteracting waveform.

### Claim 19

A shaft grounding system of a rotating equipment comprising:
a device that generates a counteracting voltage or current that reduces a grounding voltage or current between a shaft of the rotating equipment and a chassis or ground thereof; and
a waveform analysis device that characterizes a waveform of said counteracting voltage or current, compares the counteracting waveform to a self-learned family of expected waveforms in a database of model waveforms, and diagnoses or predicts a fault or degradation of the rotating equipment when the counteracting waveform indicates behavior that deviates from a behavior represented by at least one of the expected waveforms;
wherein the waveform analysis device archives models of counteracting waveforms of the rotating equipment over time; analyzes earlier changes in the archived counteracting waveforms relative to later fault and degradation events identified by expert logic, and updates the expert logic to provide a prediction of future faults and degradations based on recognition of said earlier changes, providing a self-learning expert system.
