Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Service robot movement system fault diagnosis method and device based on time sequence characteristics

A technology for robot motion and system failure, which is applied in measurement devices, neural learning methods, and testing of machine/structural components. Improve and other issues to achieve the effect of ensuring authenticity and improving accuracy

Active Publication Date: 2019-09-13
SHANDONG UNIV
View PDF7 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The diagnosis model only extracts features from the fault data at a single moment, ignoring the time series characteristics of the fault data, making the training samples cover insufficient information, resulting in the failure to further improve the accuracy of system fault diagnosis

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Service robot movement system fault diagnosis method and device based on time sequence characteristics
  • Service robot movement system fault diagnosis method and device based on time sequence characteristics
  • Service robot movement system fault diagnosis method and device based on time sequence characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] figure 1 It is a flowchart of a method for diagnosing faults in the kinematic system of a service robot based on time series features in this embodiment.

[0040] Such as figure 1 As shown, a time-series feature-based service robot motion system fault diagnosis method in this embodiment includes:

[0041] S101: Generating time series training samples in a sliding window manner for the original data.

[0042] Wherein, the raw data includes velocity, angular velocity and acceleration.

[0043] Different from the BP neural network, the neural network model based on time series has certain requirements on the format of the input data. The BP neural network only needs to concatenate the characteristic data into a vector and directly input it into the model. The neural network based on time series needs to input the characteristic data within a period of time into the model. The feature dimension is one more time dimension than the BP neural network. .

[0044] The speci...

Embodiment 2

[0084] Such as Figure 4 As shown, a time-series feature-based service robot motion system fault diagnosis device in this embodiment includes a cloud server and a robot-side detection device;

[0085] The cloud server includes:

[0086] A training sample generation module, which is used to generate time series training samples in the form of a sliding window to the original data; wherein, the original data includes velocity, angular velocity and acceleration;

[0087] A fault feature selection module, which is used to perform weighted fusion using multiple random forest models and multiple gradient boosting tree models to form a random module, and use the random model to select fault features from training samples;

[0088] The fault classification module is used to input the selected fault feature data into the GRU neural network, extract the time series features of the fault, input the data at the last moment of the sliding window into the BP neural network, extract the fau...

Embodiment 3

[0100] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the following figure 1 The steps in the service robot kinematic system fault diagnosis method based on time series features are shown.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a service robot movement system fault diagnosis method and device based on time sequence characteristics. The service robot movement system fault diagnosis method based on timesequence characteristics comprises the following steps that: adopting a sliding window way for original data to generate a time sequence training sample; adopting a plurality of random forest models and a plurality of gradient boosting tree models to carry out weighting fusion to form a random module, and utilizing a random model to carry out fault characteristic selection in the training sample;and inputting selected fault characteristic data into a GRU (Gated Recurrent Unit) neural network, extracting the time sequence characteristics of the fault, inputting the last moment data of the sliding window into a BP (Back Propagation) neural network, extracting the fault characteristics of a current moment, and carrying out fault classification after the time sequence characteristics and thefault characteristics of the current moment are combined.

Description

technical field [0001] The disclosure belongs to the field of fault diagnosis of robots, and in particular relates to a method and device for fault diagnosis of a motion system of a service robot based on time series features. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] With the development of artificial intelligence and Internet of Things technology, service robots have made great breakthroughs in terms of software and hardware resource allocation and function realization. Service robots have powerful functions and rich application scenarios, which provide great convenience for people's lives. However, it is very difficult to popularize service robots now. On the one hand, the reason is that the product intelligence level is not enough, and on the other hand, the reason is that the product safety is low. [0004] In recent years, w...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G01M13/00G06K9/62G06N3/04G06N3/08
CPCG01M13/00G06N3/084G06N3/045G06F18/24323
Inventor 周风余郭仁和袁宪锋梁姣万方沈冬冬王淑倩
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com