Recommending measurements based on detected waveform type

Patent metadata

Field	Value
Publication number	US-11181553-B2
Application number	US-202016811753-A
Country	US
Kind code	B2
Filing date	Mar 6, 2020
Priority date	Sep 12, 2016
Publication date	Nov 23, 2021
Grant date	Nov 23, 2021

Abstract

An oscilloscope including an input port for receiving training data including waveforms and corresponding known classifications and a processor for training a plurality of classifiers on the training data. Training includes iteratively applying each classifier to each waveform of the training data to obtain corresponding predicted waveform classifications and comparing the predicted waveform classifications with the known classifications. Classifiers are corrected when predicted waveform classifications does not match the known classifications. Models for each classification are constructed with suggested measurements or actions. Subsequently, live waveform data is captured by the oscilloscope and the classifiers are applied to the live data. When a confidence value for a single classification exceeds a threshold, the waveform data is classified, and suggested measurements or actions are implemented in the oscilloscope based on the classification.

First claim

We claim:

1. A test and measurement instrument comprising:
an input port configured to receive measurement data;
a processor coupled to the input port and configured to:
apply a plurality of trained classifiers to the measurement data to determine a confidence value for each of the plurality of trained classifiers,
determine whether the confidence value for each of the plurality of trained classifiers exceeds a stored confidence threshold, and
determine a classification for the measurement data when a confidence value for a single trained classifier exceeds a stored confidence threshold,
select a single model corresponding to the classification, the selected model corresponding to a single classifier and to one or more suggested actions, and
recommend the suggested actions to a user; and

a user control coupled to the processor, the user control configured to receive a selection from the user,
wherein the processor is further configured to, in response to the selection from the user, configure the test and measurement instrument to employ the suggested actions corresponding to the selected model when capturing a waveform received over the input port.

2. The test and measurement instrument of claim 1 , wherein the plurality of classifiers includes at least one decision forest.

3. The test and measurement instrument of claim 1 , wherein the plurality of classifiers employ a plurality of machine learning algorithms with specified machine learning algorithms selected to classify particular waveform types.

4. The test and measurement instrument of claim 1 , wherein the classifiers determine a classification for the measurement data by examining signal amplitude, time characteristics, jitter, or power.

5. The test and measurement instrument of claim 1 , wherein the model corresponding to the classification indicates a type of waveform incoming over the input port.

6. The test and measurement instrument of claim 1 , wherein the model corresponding to the classification indicates a bus connected to the input port.

7. The test and measurement instrument of claim 1 , further comprising a display, wherein the processor is further configured to recommend the suggested actions to the user by altering the display to disable actions that are not relevant to the selected model.

8. The test and measurement instrument of claim 1 , wherein the processor is further configured to initiate suggested actions without direct user interaction.

9. The test and measurement instrument of claim 1 , wherein each of the plurality of trained classifiers is trained during a learning phase, and wherein a trained state of the classifiers established by the learning phase is stored in a memory of the test and measurement instrument.

10. The test and measurement instrument of claim 9 , wherein the learning phase is performed on a master test and measurement instrument, and the trained state is duplicated from the master test and measurement instrument and stored in a memory of the test and measurement instrument during manufacturing.

11. The test and measurement instrument of claim 1 , wherein the suggested actions corresponding to the selected model are set during a learning phase, and wherein a trained state of the selected model established by the learning phase is stored in a memory of the test and measurement instrument.

12. The test and measurement instrument of claim 11 , wherein the learning phase is performed on a master test and measurement instrument, and the trained state is duplicated from the master test and measurement instrument and stored in a memory of the test and measurement instrument during manufacturing.

13. The test and measurement instrument of claim 1 , wherein the processor is further configured to output an alert indicating an unsuccessful classification when the confidence value for two of the plurality of trained classifiers exceeds a stored confidence threshold or when the confidence value does not exceed a stored confidence threshold for any of the plurality of trained classifiers.

14. A method of operating a test and measurement instrument, comprising:
receiving evaluation data during an evaluation operational phase of the test and measurement instrument;
applying a plurality of trainable classifiers to the evaluation data to determine a confidence value for reach of the plurality of trainable classifiers, wherein each classifier indicates whether the evaluation data matches a model corresponding to the classifier when the confidence value of the trainable classifier exceeds a stored confidence threshold;
determining a classification for the evaluation data when only one classifier indicates a match; and
altering a user interface of the test and measurement instrument to recommend a suggested action to a user based on the classification.

15. The method of claim 14 , wherein receiving evaluation data comprises receiving measurement data from a device under test at an input port of the test and measurement instrument.

16. The method of claim 14 , wherein receiving evaluation data comprises receiving data indicating a state of the test and measurement instrument.

17. The method of claim 14 , wherein each trainable classifier of the plurality of trainable classifiers operates according to a set of preconfigured rules.

18. The method of claim 17 , wherein the plurality of trainable classifiers are applied to the evaluation data by a machine learning module, and wherein the machine learning module is configured to modify the rules during a training operational phase of the test and measurement instrument.

19. The method of claim 14 , wherein the suggested action is associated with the model.

20. A non-transitory computer-readable medium containing instructions that, when executed by a processor in a test and measurement instrument, cause the test and measurement instrument to perform the method of claim 14 .

Assignees

• Tektronix Inc

Inventors

• Absher Ian R
• Strong Kraig M

Classifications

• G06F18/2148 Primary

  characterised by the process organisation or structure, e.g. boosting cascade · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06F18/24

  Classification techniques · CPC title

• G06N20/20 Primary

  Ensemble learning · CPC title

• G01R23/16

  Spectrum analysis; Fourier analysis · CPC title